19 files changed, 369 insertions, 332 deletions

diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index 5e1f345b58dd..288cc9e96395 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -112,6 +112,62 @@ static __always_inline void atomic_long_dec(atomic_long_t *l)
 	ATOMIC_LONG_PFX(_dec)(v);
 }
 
+#define ATOMIC_LONG_FETCH_OP(op, mo)					\
+static inline long							\
+atomic_long_fetch_##op##mo(long i, atomic_long_t *l)			\
+{									\
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;		\
+									\
+	return (long)ATOMIC_LONG_PFX(_fetch_##op##mo)(i, v);		\
+}
+
+ATOMIC_LONG_FETCH_OP(add, )
+ATOMIC_LONG_FETCH_OP(add, _relaxed)
+ATOMIC_LONG_FETCH_OP(add, _acquire)
+ATOMIC_LONG_FETCH_OP(add, _release)
+ATOMIC_LONG_FETCH_OP(sub, )
+ATOMIC_LONG_FETCH_OP(sub, _relaxed)
+ATOMIC_LONG_FETCH_OP(sub, _acquire)
+ATOMIC_LONG_FETCH_OP(sub, _release)
+ATOMIC_LONG_FETCH_OP(and, )
+ATOMIC_LONG_FETCH_OP(and, _relaxed)
+ATOMIC_LONG_FETCH_OP(and, _acquire)
+ATOMIC_LONG_FETCH_OP(and, _release)
+ATOMIC_LONG_FETCH_OP(andnot, )
+ATOMIC_LONG_FETCH_OP(andnot, _relaxed)
+ATOMIC_LONG_FETCH_OP(andnot, _acquire)
+ATOMIC_LONG_FETCH_OP(andnot, _release)
+ATOMIC_LONG_FETCH_OP(or, )
+ATOMIC_LONG_FETCH_OP(or, _relaxed)
+ATOMIC_LONG_FETCH_OP(or, _acquire)
+ATOMIC_LONG_FETCH_OP(or, _release)
+ATOMIC_LONG_FETCH_OP(xor, )
+ATOMIC_LONG_FETCH_OP(xor, _relaxed)
+ATOMIC_LONG_FETCH_OP(xor, _acquire)
+ATOMIC_LONG_FETCH_OP(xor, _release)
+
+#undef ATOMIC_LONG_FETCH_OP
+
+#define ATOMIC_LONG_FETCH_INC_DEC_OP(op, mo)					\
+static inline long							\
+atomic_long_fetch_##op##mo(atomic_long_t *l)				\
+{									\
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;		\
+									\
+	return (long)ATOMIC_LONG_PFX(_fetch_##op##mo)(v);		\
+}
+
+ATOMIC_LONG_FETCH_INC_DEC_OP(inc,)
+ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _relaxed)
+ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _acquire)
+ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _release)
+ATOMIC_LONG_FETCH_INC_DEC_OP(dec,)
+ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _relaxed)
+ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _acquire)
+ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _release)
+
+#undef ATOMIC_LONG_FETCH_INC_DEC_OP
+
 #define ATOMIC_LONG_OP(op)						\
 static __always_inline void						\
 atomic_long_##op(long i, atomic_long_t *l)				\
@@ -124,9 +180,9 @@ atomic_long_##op(long i, atomic_long_t *l)				\
 ATOMIC_LONG_OP(add)
 ATOMIC_LONG_OP(sub)
 ATOMIC_LONG_OP(and)
+ATOMIC_LONG_OP(andnot)
 ATOMIC_LONG_OP(or)
 ATOMIC_LONG_OP(xor)
-ATOMIC_LONG_OP(andnot)
 
 #undef ATOMIC_LONG_OP
 
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 74f1a3704d7a..9ed8b987185b 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -61,6 +61,18 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return c c_op i;						\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = cmpxchg(&v->counter, c, c c_op i)) != c)		\
+		c = old;						\
+									\
+	return c;							\
+}
+
 #else
 
 #include <linux/irqflags.h>
@@ -88,6 +100,20 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return ret;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	raw_local_irq_save(flags);					\
+	ret = v->counter;						\
+	v->counter = v->counter c_op i;					\
+	raw_local_irq_restore(flags);					\
+									\
+	return ret;							\
+}
+
 #endif /* CONFIG_SMP */
 
 #ifndef atomic_add_return
@@ -98,6 +124,26 @@ ATOMIC_OP_RETURN(add, +)
 ATOMIC_OP_RETURN(sub, -)
 #endif
 
+#ifndef atomic_fetch_add
+ATOMIC_FETCH_OP(add, +)
+#endif
+
+#ifndef atomic_fetch_sub
+ATOMIC_FETCH_OP(sub, -)
+#endif
+
+#ifndef atomic_fetch_and
+ATOMIC_FETCH_OP(and, &)
+#endif
+
+#ifndef atomic_fetch_or
+ATOMIC_FETCH_OP(or, |)
+#endif
+
+#ifndef atomic_fetch_xor
+ATOMIC_FETCH_OP(xor, ^)
+#endif
+
 #ifndef atomic_and
 ATOMIC_OP(and, &)
 #endif
@@ -110,6 +156,7 @@ ATOMIC_OP(or, |)
 ATOMIC_OP(xor, ^)
 #endif
 
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index d48e78ccad3d..dad68bf46c77 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -27,16 +27,23 @@ extern void	 atomic64_##op(long long a, atomic64_t *v);
 #define ATOMIC64_OP_RETURN(op)						\
 extern long long atomic64_##op##_return(long long a, atomic64_t *v);
 
-#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+#define ATOMIC64_FETCH_OP(op)						\
+extern long long atomic64_fetch_##op(long long a, atomic64_t *v);
+
+#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
 
 ATOMIC64_OPS(add)
 ATOMIC64_OPS(sub)
 
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op)
+
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 1cceca146905..fe297b599b0a 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -194,7 +194,7 @@ do {									\
 })
 #endif
 
-#endif
+#endif	/* CONFIG_SMP */
 
 /* Barriers for virtual machine guests when talking to an SMP host */
 #define virt_mb() __smp_mb()
@@ -207,5 +207,44 @@ do {									\
 #define virt_store_release(p, v) __smp_store_release(p, v)
 #define virt_load_acquire(p) __smp_load_acquire(p)
 
+/**
+ * smp_acquire__after_ctrl_dep() - Provide ACQUIRE ordering after a control dependency
+ *
+ * A control dependency provides a LOAD->STORE order, the additional RMB
+ * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
+ * aka. (load)-ACQUIRE.
+ *
+ * Architectures that do not do load speculation can have this be barrier().
+ */
+#ifndef smp_acquire__after_ctrl_dep
+#define smp_acquire__after_ctrl_dep()		smp_rmb()
+#endif
+
+/**
+ * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
+ * @ptr: pointer to the variable to wait on
+ * @cond: boolean expression to wait for
+ *
+ * Equivalent to using smp_load_acquire() on the condition variable but employs
+ * the control dependency of the wait to reduce the barrier on many platforms.
+ *
+ * Due to C lacking lambda expressions we load the value of *ptr into a
+ * pre-named variable @VAL to be used in @cond.
+ */
+#ifndef smp_cond_load_acquire
+#define smp_cond_load_acquire(ptr, cond_expr) ({		\
+	typeof(ptr) __PTR = (ptr);				\
+	typeof(*ptr) VAL;					\
+	for (;;) {						\
+		VAL = READ_ONCE(*__PTR);			\
+		if (cond_expr)					\
+			break;					\
+		cpu_relax();					\
+	}							\
+	smp_acquire__after_ctrl_dep();				\
+	VAL;							\
+})
+#endif
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
index 0f1c6f315cdc..a84e28e0c634 100644
--- a/include/asm-generic/cputime_nsecs.h
+++ b/include/asm-generic/cputime_nsecs.h
@@ -50,6 +50,8 @@ typedef u64 __nocast cputime64_t;
 	(__force u64)(__ct)
 #define nsecs_to_cputime(__nsecs)	\
 	(__force cputime_t)(__nsecs)
+#define nsecs_to_cputime64(__nsecs)	\
+	(__force cputime64_t)(__nsecs)
 
 
 /*
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index e56272c919b5..bf2d34c9d804 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -108,11 +108,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	u32 val;
 
 	preempt_disable();
-	if (unlikely(get_user(val, uaddr) != 0))
+	if (unlikely(get_user(val, uaddr) != 0)) {
+		preempt_enable();
 		return -EFAULT;
+	}
 
-	if (val == oldval && unlikely(put_user(newval, uaddr) != 0))
+	if (val == oldval && unlikely(put_user(newval, uaddr) != 0)) {
+		preempt_enable();
 		return -EFAULT;
+	}
 
 	*uval = val;
 	preempt_enable();
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index eed3bbe88c8a..7ef015eb3403 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -191,7 +191,7 @@ static inline void writeq(u64 value, volatile void __iomem *addr)
 #define readl_relaxed readl
 #endif
 
-#ifndef readq_relaxed
+#if defined(readq) && !defined(readq_relaxed)
 #define readq_relaxed readq
 #endif
 
@@ -207,7 +207,7 @@ static inline void writeq(u64 value, volatile void __iomem *addr)
 #define writel_relaxed writel
 #endif
 
-#ifndef writeq_relaxed
+#if defined(writeq) && !defined(writeq_relaxed)
 #define writeq_relaxed writeq
 #endif
 
@@ -585,6 +585,16 @@ static inline u32 ioread32(const volatile void __iomem *addr)
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef ioread64
+#define ioread64 ioread64
+static inline u64 ioread64(const volatile void __iomem *addr)
+{
+	return readq(addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef iowrite8
 #define iowrite8 iowrite8
 static inline void iowrite8(u8 value, volatile void __iomem *addr)
@@ -609,11 +619,21 @@ static inline void iowrite32(u32 value, volatile void __iomem *addr)
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef iowrite64
+#define iowrite64 iowrite64
+static inline void iowrite64(u64 value, volatile void __iomem *addr)
+{
+	writeq(value, addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef ioread16be
 #define ioread16be ioread16be
 static inline u16 ioread16be(const volatile void __iomem *addr)
 {
-	return __be16_to_cpu(__raw_readw(addr));
+	return swab16(readw(addr));
 }
 #endif
 
@@ -621,15 +641,25 @@ static inline u16 ioread16be(const volatile void __iomem *addr)
 #define ioread32be ioread32be
 static inline u32 ioread32be(const volatile void __iomem *addr)
 {
-	return __be32_to_cpu(__raw_readl(addr));
+	return swab32(readl(addr));
+}
+#endif
+
+#ifdef CONFIG_64BIT
+#ifndef ioread64be
+#define ioread64be ioread64be
+static inline u64 ioread64be(const volatile void __iomem *addr)
+{
+	return swab64(readq(addr));
 }
 #endif
+#endif /* CONFIG_64BIT */
 
 #ifndef iowrite16be
 #define iowrite16be iowrite16be
 static inline void iowrite16be(u16 value, void volatile __iomem *addr)
 {
-	__raw_writew(__cpu_to_be16(value), addr);
+	writew(swab16(value), addr);
 }
 #endif
 
@@ -637,10 +667,20 @@ static inline void iowrite16be(u16 value, void volatile __iomem *addr)
 #define iowrite32be iowrite32be
 static inline void iowrite32be(u32 value, volatile void __iomem *addr)
 {
-	__raw_writel(__cpu_to_be32(value), addr);
+	writel(swab32(value), addr);
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef iowrite64be
+#define iowrite64be iowrite64be
+static inline void iowrite64be(u64 value, volatile void __iomem *addr)
+{
+	writeq(swab64(value), addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef ioread8_rep
 #define ioread8_rep ioread8_rep
 static inline void ioread8_rep(const volatile void __iomem *addr, void *buffer,
@@ -668,6 +708,17 @@ static inline void ioread32_rep(const volatile void __iomem *addr,
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef ioread64_rep
+#define ioread64_rep ioread64_rep
+static inline void ioread64_rep(const volatile void __iomem *addr,
+				void *buffer, unsigned int count)
+{
+	readsq(addr, buffer, count);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef iowrite8_rep
 #define iowrite8_rep iowrite8_rep
 static inline void iowrite8_rep(volatile void __iomem *addr,
@@ -697,6 +748,18 @@ static inline void iowrite32_rep(volatile void __iomem *addr,
 	writesl(addr, buffer, count);
 }
 #endif
+
+#ifdef CONFIG_64BIT
+#ifndef iowrite64_rep
+#define iowrite64_rep iowrite64_rep
+static inline void iowrite64_rep(volatile void __iomem *addr,
+				 const void *buffer,
+				 unsigned int count)
+{
+	writesq(addr, buffer, count);
+}
+#endif
+#endif /* CONFIG_64BIT */
 #endif /* CONFIG_GENERIC_IOMAP */
 
 #ifdef __KERNEL__
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
index d8f8622fa044..650fede33c25 100644
--- a/include/asm-generic/iomap.h
+++ b/include/asm-generic/iomap.h
@@ -30,12 +30,20 @@ extern unsigned int ioread16(void __iomem *);
 extern unsigned int ioread16be(void __iomem *);
 extern unsigned int ioread32(void __iomem *);
 extern unsigned int ioread32be(void __iomem *);
+#ifdef CONFIG_64BIT
+extern u64 ioread64(void __iomem *);
+extern u64 ioread64be(void __iomem *);
+#endif
 
 extern void iowrite8(u8, void __iomem *);
 extern void iowrite16(u16, void __iomem *);
 extern void iowrite16be(u16, void __iomem *);
 extern void iowrite32(u32, void __iomem *);
 extern void iowrite32be(u32, void __iomem *);
+#ifdef CONFIG_64BIT
+extern void iowrite64(u64, void __iomem *);
+extern void iowrite64be(u64, void __iomem *);
+#endif
 
 /*
  * "string" versions of the above. Note that they
diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h
index fd694cfd678a..c54829d3de37 100644
--- a/include/asm-generic/mutex-dec.h
+++ b/include/asm-generic/mutex-dec.h
@@ -80,7 +80,7 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
 static inline int
 __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
-	if (likely(atomic_cmpxchg_acquire(count, 1, 0) == 1))
+	if (likely(atomic_read(count) == 1 && atomic_cmpxchg_acquire(count, 1, 0) == 1))
 		return 1;
 	return 0;
 }
diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h
index a6b4a7bd6ac9..3269ec4e195f 100644
--- a/include/asm-generic/mutex-xchg.h
+++ b/include/asm-generic/mutex-xchg.h
@@ -91,8 +91,12 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
 static inline int
 __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
-	int prev = atomic_xchg_acquire(count, 0);
+	int prev;
 
+	if (atomic_read(count) != 1)
+		return 0;
+
+	prev = atomic_xchg_acquire(count, 0);
 	if (unlikely(prev < 0)) {
 		/*
 		 * The lock was marked contended so we must restore that
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 9401f4819891..d4458b6dbfb4 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -806,4 +806,12 @@ static inline int pmd_clear_huge(pmd_t *pmd)
 #define io_remap_pfn_range remap_pfn_range
 #endif
 
+#ifndef has_transparent_hugepage
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define has_transparent_hugepage() 1
+#else
+#define has_transparent_hugepage() 0
+#endif
+#endif
+
 #endif /* _ASM_GENERIC_PGTABLE_H */
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 5d8ffa3e6f8c..c1cde3577551 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -7,10 +7,10 @@
 
 static __always_inline int preempt_count(void)
 {
-	return current_thread_info()->preempt_count;
+	return READ_ONCE(current_thread_info()->preempt_count);
 }
 
-static __always_inline int *preempt_count_ptr(void)
+static __always_inline volatile int *preempt_count_ptr(void)
 {
 	return &current_thread_info()->preempt_count;
 }
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 35a52a880b2f..9f0681bf1e87 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -22,14 +22,33 @@
 #include <asm-generic/qspinlock_types.h>
 
 /**
+ * queued_spin_unlock_wait - wait until the _current_ lock holder releases the lock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * There is a very slight possibility of live-lock if the lockers keep coming
+ * and the waiter is just unfortunate enough to not see any unlock state.
+ */
+#ifndef queued_spin_unlock_wait
+extern void queued_spin_unlock_wait(struct qspinlock *lock);
+#endif
+
+/**
  * queued_spin_is_locked - is the spinlock locked?
  * @lock: Pointer to queued spinlock structure
  * Return: 1 if it is locked, 0 otherwise
  */
+#ifndef queued_spin_is_locked
 static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
 {
+	/*
+	 * See queued_spin_unlock_wait().
+	 *
+	 * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL
+	 * isn't immediately observable.
+	 */
 	return atomic_read(&lock->val);
 }
+#endif
 
 /**
  * queued_spin_value_unlocked - is the spinlock structure unlocked?
@@ -92,26 +111,12 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock)
 static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 {
 	/*
-	 * smp_mb__before_atomic() in order to guarantee release semantics
+	 * unlock() needs release semantics:
 	 */
-	smp_mb__before_atomic();
-	atomic_sub(_Q_LOCKED_VAL, &lock->val);
+	(void)atomic_sub_return_release(_Q_LOCKED_VAL, &lock->val);
 }
 #endif
 
-/**
- * queued_spin_unlock_wait - wait until current lock holder releases the lock
- * @lock : Pointer to queued spinlock structure
- *
- * There is a very slight possibility of live-lock if the lockers keep coming
- * and the waiter is just unfortunate enough to not see any unlock state.
- */
-static inline void queued_spin_unlock_wait(struct qspinlock *lock)
-{
-	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
-		cpu_relax();
-}
-
 #ifndef virt_spin_lock
 static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 {
diff --git a/include/asm-generic/rtc.h b/include/asm-generic/rtc.h
deleted file mode 100644
index 4e3b6558331e..000000000000
--- a/include/asm-generic/rtc.h
+++ /dev/null
@@ -1,247 +0,0 @@
-/* 
- * include/asm-generic/rtc.h
- *
- * Author: Tom Rini <trini@mvista.com>
- *
- * Based on:
- * drivers/char/rtc.c
- *
- * Please read the COPYING file for all license details.
- */
-
-#ifndef __ASM_RTC_H__
-#define __ASM_RTC_H__
-
-#include <linux/mc146818rtc.h>
-#include <linux/rtc.h>
-#include <linux/bcd.h>
-#include <linux/delay.h>
-#ifdef CONFIG_ACPI
-#include <linux/acpi.h>
-#endif
-
-#define RTC_PIE 0x40		/* periodic interrupt enable */
-#define RTC_AIE 0x20		/* alarm interrupt enable */
-#define RTC_UIE 0x10		/* update-finished interrupt enable */
-
-/* some dummy definitions */
-#define RTC_BATT_BAD 0x100	/* battery bad */
-#define RTC_SQWE 0x08		/* enable square-wave output */
-#define RTC_DM_BINARY 0x04	/* all time/date values are BCD if clear */
-#define RTC_24H 0x02		/* 24 hour mode - else hours bit 7 means pm */
-#define RTC_DST_EN 0x01	        /* auto switch DST - works f. USA only */
-
-/*
- * Returns true if a clock update is in progress
- */
-static inline unsigned char rtc_is_updating(void)
-{
-	unsigned char uip;
-	unsigned long flags;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return uip;
-}
-
-static inline unsigned int __get_rtc_time(struct rtc_time *time)
-{
-	unsigned char ctrl;
-	unsigned long flags;
-	unsigned char century = 0;
-
-#ifdef CONFIG_MACH_DECSTATION
-	unsigned int real_year;
-#endif
-
-	/*
-	 * read RTC once any update in progress is done. The update
-	 * can take just over 2ms. We wait 20ms. There is no need to
-	 * to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP.
-	 * If you need to know *exactly* when a second has started, enable
-	 * periodic update complete interrupts, (via ioctl) and then 
-	 * immediately read /dev/rtc which will block until you get the IRQ.
-	 * Once the read clears, read the RTC time (again via ioctl). Easy.
-	 */
-	if (rtc_is_updating())
-		mdelay(20);
-
-	/*
-	 * Only the values that we read from the RTC are set. We leave
-	 * tm_wday, tm_yday and tm_isdst untouched. Even though the
-	 * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated
-	 * by the RTC when initially set to a non-zero value.
-	 */
-	spin_lock_irqsave(&rtc_lock, flags);
-	time->tm_sec = CMOS_READ(RTC_SECONDS);
-	time->tm_min = CMOS_READ(RTC_MINUTES);
-	time->tm_hour = CMOS_READ(RTC_HOURS);
-	time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH);
-	time->tm_mon = CMOS_READ(RTC_MONTH);
-	time->tm_year = CMOS_READ(RTC_YEAR);
-#ifdef CONFIG_MACH_DECSTATION
-	real_year = CMOS_READ(RTC_DEC_YEAR);
-#endif
-#ifdef CONFIG_ACPI
-	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
-	    acpi_gbl_FADT.century)
-		century = CMOS_READ(acpi_gbl_FADT.century);
-#endif
-	ctrl = CMOS_READ(RTC_CONTROL);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-	{
-		time->tm_sec = bcd2bin(time->tm_sec);
-		time->tm_min = bcd2bin(time->tm_min);
-		time->tm_hour = bcd2bin(time->tm_hour);
-		time->tm_mday = bcd2bin(time->tm_mday);
-		time->tm_mon = bcd2bin(time->tm_mon);
-		time->tm_year = bcd2bin(time->tm_year);
-		century = bcd2bin(century);
-	}
-
-#ifdef CONFIG_MACH_DECSTATION
-	time->tm_year += real_year - 72;
-#endif
-
-	if (century)
-		time->tm_year += (century - 19) * 100;
-
-	/*
-	 * Account for differences between how the RTC uses the values
-	 * and how they are defined in a struct rtc_time;
-	 */
-	if (time->tm_year <= 69)
-		time->tm_year += 100;
-
-	time->tm_mon--;
-
-	return RTC_24H;
-}
-
-#ifndef get_rtc_time
-#define get_rtc_time	__get_rtc_time
-#endif
-
-/* Set the current date and time in the real time clock. */
-static inline int __set_rtc_time(struct rtc_time *time)
-{
-	unsigned long flags;
-	unsigned char mon, day, hrs, min, sec;
-	unsigned char save_control, save_freq_select;
-	unsigned int yrs;
-#ifdef CONFIG_MACH_DECSTATION
-	unsigned int real_yrs, leap_yr;
-#endif
-	unsigned char century = 0;
-
-	yrs = time->tm_year;
-	mon = time->tm_mon + 1;   /* tm_mon starts at zero */
-	day = time->tm_mday;
-	hrs = time->tm_hour;
-	min = time->tm_min;
-	sec = time->tm_sec;
-
-	if (yrs > 255)	/* They are unsigned */
-		return -EINVAL;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-#ifdef CONFIG_MACH_DECSTATION
-	real_yrs = yrs;
-	leap_yr = ((!((yrs + 1900) % 4) && ((yrs + 1900) % 100)) ||
-			!((yrs + 1900) % 400));
-	yrs = 72;
-
-	/*
-	 * We want to keep the year set to 73 until March
-	 * for non-leap years, so that Feb, 29th is handled
-	 * correctly.
-	 */
-	if (!leap_yr && mon < 3) {
-		real_yrs--;
-		yrs = 73;
-	}
-#endif
-
-#ifdef CONFIG_ACPI
-	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
-	    acpi_gbl_FADT.century) {
-		century = (yrs + 1900) / 100;
-		yrs %= 100;
-	}
-#endif
-
-	/* These limits and adjustments are independent of
-	 * whether the chip is in binary mode or not.
-	 */
-	if (yrs > 169) {
-		spin_unlock_irqrestore(&rtc_lock, flags);
-		return -EINVAL;
-	}
-
-	if (yrs >= 100)
-		yrs -= 100;
-
-	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY)
-	    || RTC_ALWAYS_BCD) {
-		sec = bin2bcd(sec);
-		min = bin2bcd(min);
-		hrs = bin2bcd(hrs);
-		day = bin2bcd(day);
-		mon = bin2bcd(mon);
-		yrs = bin2bcd(yrs);
-		century = bin2bcd(century);
-	}
-
-	save_control = CMOS_READ(RTC_CONTROL);
-	CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
-	save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
-	CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
-
-#ifdef CONFIG_MACH_DECSTATION
-	CMOS_WRITE(real_yrs, RTC_DEC_YEAR);
-#endif
-	CMOS_WRITE(yrs, RTC_YEAR);
-	CMOS_WRITE(mon, RTC_MONTH);
-	CMOS_WRITE(day, RTC_DAY_OF_MONTH);
-	CMOS_WRITE(hrs, RTC_HOURS);
-	CMOS_WRITE(min, RTC_MINUTES);
-	CMOS_WRITE(sec, RTC_SECONDS);
-#ifdef CONFIG_ACPI
-	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
-	    acpi_gbl_FADT.century)
-		CMOS_WRITE(century, acpi_gbl_FADT.century);
-#endif
-
-	CMOS_WRITE(save_control, RTC_CONTROL);
-	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
-
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	return 0;
-}
-
-#ifndef set_rtc_time
-#define set_rtc_time	__set_rtc_time
-#endif
-
-static inline unsigned int get_rtc_ss(void)
-{
-	struct rtc_time h;
-
-	get_rtc_time(&h);
-	return h.tm_sec;
-}
-
-static inline int get_rtc_pll(struct rtc_pll_info *pll)
-{
-	return -EINVAL;
-}
-static inline int set_rtc_pll(struct rtc_pll_info *pll)
-{
-	return -EINVAL;
-}
-
-#endif /* __ASM_RTC_H__ */
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index d6d5dc98d7da..5be122e3d326 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -41,8 +41,8 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
 
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg_acquire(&sem->count, tmp,
+	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
+		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
 				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
 			return 1;
 		}
@@ -53,7 +53,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 /*
  * lock for writing
  */
-static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
+static inline void __down_write(struct rw_semaphore *sem)
 {
 	long tmp;
 
@@ -63,16 +63,23 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 		rwsem_down_write_failed(sem);
 }
 
-static inline void __down_write(struct rw_semaphore *sem)
+static inline int __down_write_killable(struct rw_semaphore *sem)
 {
-	__down_write_nested(sem, 0);
+	long tmp;
+
+	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
+				     (atomic_long_t *)&sem->count);
+	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
+		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
+			return -EINTR;
+	return 0;
 }
 
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
 
-	tmp = cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
+	tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
 		      RWSEM_ACTIVE_WRITE_BIAS);
 	return tmp == RWSEM_UNLOCKED_VALUE;
 }
@@ -100,14 +107,6 @@ static inline void __up_write(struct rw_semaphore *sem)
 }
 
 /*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	atomic_long_add(delta, (atomic_long_t *)&sem->count);
-}
-
-/*
  * downgrade write lock to read lock
  */
 static inline void __downgrade_write(struct rw_semaphore *sem)
@@ -127,13 +126,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		rwsem_downgrade_wake(sem);
 }
 
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
-}
-
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_GENERIC_RWSEM_H */
diff --git a/include/asm-generic/seccomp.h b/include/asm-generic/seccomp.h
index c9ccafa0d99a..e74072d23e69 100644
--- a/include/asm-generic/seccomp.h
+++ b/include/asm-generic/seccomp.h
@@ -29,4 +29,18 @@
 #define __NR_seccomp_sigreturn		__NR_rt_sigreturn
 #endif
 
+#ifdef CONFIG_COMPAT
+#ifndef get_compat_mode1_syscalls
+static inline const int *get_compat_mode1_syscalls(void)
+{
+	static const int mode1_syscalls_32[] = {
+		__NR_seccomp_read_32, __NR_seccomp_write_32,
+		__NR_seccomp_exit_32, __NR_seccomp_sigreturn_32,
+		0, /* null terminated */
+	};
+	return mode1_syscalls_32;
+}
+#endif
+#endif /* CONFIG_COMPAT */
+
 #endif /* _ASM_GENERIC_SECCOMP_H */
diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
index 3d1a3af5cf59..a2508a8f9a9c 100644
--- a/include/asm-generic/siginfo.h
+++ b/include/asm-generic/siginfo.h
@@ -17,21 +17,6 @@
 struct siginfo;
 void do_schedule_next_timer(struct siginfo *info);
 
-#ifndef HAVE_ARCH_COPY_SIGINFO
-
-#include <linux/string.h>
-
-static inline void copy_siginfo(struct siginfo *to, struct siginfo *from)
-{
-	if (from->si_code < 0)
-		memcpy(to, from, sizeof(*to));
-	else
-		/* _sigchld is currently the largest know union member */
-		memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld));
-}
-
-#endif
-
 extern int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from);
 
 #endif
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 9dbb739cafa0..c6d667187608 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -107,6 +107,12 @@ struct mmu_gather {
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
 	unsigned int		batch_count;
+	/*
+	 * __tlb_adjust_range  will track the new addr here,
+	 * that that we can adjust the range after the flush
+	 */
+	unsigned long addr;
+	int page_size;
 };
 
 #define HAVE_GENERIC_MMU_GATHER
@@ -115,23 +121,20 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
 							unsigned long end);
-int __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
-
-/* tlb_remove_page
- *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
- *	required.
- */
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (!__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
+extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
+				   int page_size);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address)
 {
 	tlb->start = min(tlb->start, address);
 	tlb->end = max(tlb->end, address + PAGE_SIZE);
+	/*
+	 * Track the last address with which we adjusted the range. This
+	 * will be used later to adjust again after a mmu_flush due to
+	 * failed __tlb_remove_page
+	 */
+	tlb->addr = address;
 }
 
 static inline void __tlb_reset_range(struct mmu_gather *tlb)
@@ -144,6 +147,40 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	}
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	if (__tlb_remove_page_size(tlb, page, page_size)) {
+		tlb_flush_mmu(tlb);
+		tlb->page_size = page_size;
+		__tlb_adjust_range(tlb, tlb->addr);
+		__tlb_remove_page_size(tlb, page, page_size);
+	}
+}
+
+static bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	return __tlb_remove_page_size(tlb, page, PAGE_SIZE);
+}
+
+/* tlb_remove_page
+ *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
+ *	required.
+ */
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	return tlb_remove_page_size(tlb, page, PAGE_SIZE);
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page)
+{
+	/* active->nr should be zero when we call this */
+	VM_BUG_ON_PAGE(tlb->active->nr, page);
+	tlb->page_size = PAGE_SIZE;
+	__tlb_adjust_range(tlb, tlb->addr);
+	return __tlb_remove_page(tlb, page);
+}
+
 /*
  * In the case of tlb vma handling, we can optimise these away in the
  * case where we're doing a full MM flush.  When we're doing a munmap,
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 339125bb4d2c..24563970ff7b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -164,7 +164,7 @@
 
 #define ___OF_TABLE(cfg, name)	_OF_TABLE_##cfg(name)
 #define __OF_TABLE(cfg, name)	___OF_TABLE(cfg, name)
-#define OF_TABLE(cfg, name)	__OF_TABLE(config_enabled(cfg), name)
+#define OF_TABLE(cfg, name)	__OF_TABLE(IS_ENABLED(cfg), name)
 #define _OF_TABLE_0(name)
 #define _OF_TABLE_1(name)						\
 	. = ALIGN(8);							\
@@ -245,7 +245,17 @@
 
 #define INIT_TASK_DATA(align)						\
 	. = ALIGN(align);						\
-	*(.data..init_task)
+	VMLINUX_SYMBOL(__start_init_task) = .;				\
+	*(.data..init_task)						\
+	VMLINUX_SYMBOL(__end_init_task) = .;
+
+/*
+ * Allow architectures to handle ro_after_init data on their
+ * own by defining an empty RO_AFTER_INIT_DATA.
+ */
+#ifndef RO_AFTER_INIT_DATA
+#define RO_AFTER_INIT_DATA *(.data..ro_after_init)
+#endif
 
 /*
  * Read only Data
@@ -255,7 +265,7 @@
 	.rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {		\
 		VMLINUX_SYMBOL(__start_rodata) = .;			\
 		*(.rodata) *(.rodata.*)					\
-		*(.data..ro_after_init)	/* Read only after init */	\
+		RO_AFTER_INIT_DATA	/* Read only after init */	\
 		*(__vermagic)		/* Kernel version magic */	\
 		. = ALIGN(8);						\
 		VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .;		\
@@ -540,15 +550,19 @@
 
 #define INIT_TEXT							\
 	*(.init.text)							\
+	*(.text.startup)						\
 	MEM_DISCARD(init.text)
 
 #define EXIT_DATA							\
 	*(.exit.data)							\
+	*(.fini_array)							\
+	*(.dtors)							\
 	MEM_DISCARD(exit.data)						\
 	MEM_DISCARD(exit.rodata)
 
 #define EXIT_TEXT							\
 	*(.exit.text)							\
+	*(.text.exit)							\
 	MEM_DISCARD(exit.text)
 
 #define EXIT_CALL							\