From a3d03ecaf9fe722bf96e4ef4a2f5e42ef652ddeb Mon Sep 17 00:00:00 2001 From: Zhaolei Date: Mon, 13 Apr 2009 15:23:53 +0800 Subject: tracing: Fix power tracer header Before patch: # tracer: power # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | [ 676.875865889] CSTATE: Going to C1 on cpu 0 for 0.005911463 [ 676.882938805] CSTATE: Going to C1 on cpu 0 for 0.104796532 ... After patch: # tracer: power # # TIMESTAMP STATE EVENT # | | | [ 676.875865889] CSTATE: Going to C1 on cpu 0 for 0.005911463 [ 676.882938805] CSTATE: Going to C1 on cpu 0 for 0.104796532 ... v2: Use seq_puts instead of seq_printf Signed-off-by: Zhao Lei Cc: Arjan van de Ven Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Tom Zanussi LKML-Reference: <49E2E889.5000903@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/trace_power.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c index bae791ebcc51..118439709fb7 100644 --- a/kernel/trace/trace_power.c +++ b/kernel/trace/trace_power.c @@ -186,6 +186,12 @@ static enum print_line_t power_print_line(struct trace_iterator *iter) return TRACE_TYPE_UNHANDLED; } +static void power_print_header(struct seq_file *s) +{ + seq_puts(s, "# TIMESTAMP STATE EVENT\n"); + seq_puts(s, "# | | |\n"); +} + static struct tracer power_tracer __read_mostly = { .name = "power", @@ -194,6 +200,7 @@ static struct tracer power_tracer __read_mostly = .stop = stop_power_trace, .reset = power_trace_reset, .print_line = power_print_line, + .print_header = power_print_header, }; static int init_power_trace(void) -- cgit From 4be6f6bb66111c9468733a4ed9cad10dc3a762c0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 13 Apr 2009 14:39:33 -0700 Subject: mm: move the scan_unevictable_pages sysctl to the vm table vm knobs should go in the vm table. Probably too late for randomize_va_space though. Signed-off-by: Peter Zijlstra Acked-by: Lee Schermerhorn Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4286b62b34a0..e3d2c7dd59b9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -902,16 +902,6 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif -#ifdef CONFIG_UNEVICTABLE_LRU - { - .ctl_name = CTL_UNNUMBERED, - .procname = "scan_unevictable_pages", - .data = &scan_unevictable_pages, - .maxlen = sizeof(scan_unevictable_pages), - .mode = 0644, - .proc_handler = &scan_unevictable_handler, - }, -#endif #ifdef CONFIG_SLOW_WORK { .ctl_name = CTL_UNNUMBERED, @@ -1302,6 +1292,16 @@ static struct ctl_table vm_table[] = { .extra2 = &one, }, #endif +#ifdef CONFIG_UNEVICTABLE_LRU + { + .ctl_name = CTL_UNNUMBERED, + .procname = "scan_unevictable_pages", + .data = &scan_unevictable_pages, + .maxlen = sizeof(scan_unevictable_pages), + .mode = 0644, + .proc_handler = &scan_unevictable_handler, + }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt -- cgit From f1671f6d783a2385d32e11f456cbe32f0e4b4b49 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 13 Apr 2009 14:40:03 -0700 Subject: ptrace: fix exit_ptrace() vs ptrace_traceme() race Pointed out by Roland. The bug was recently introduced by me in "forget_original_parent: split out the un-ptrace part", commit 39c626ae47c469abdfd30c6e42eff884931380d6. Since that patch we have a window after exit_ptrace() drops tasklist and before forget_original_parent() takes it again. In this window the child can do ptrace(PTRACE_TRACEME) and nobody can untrace this child after that. Change ptrace_traceme() to not attach to the exiting ->real_parent. We don't report the error in this case, we pretend we attach right before ->real_parent calls exit_ptrace() which should untrace us anyway. Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/ptrace.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 64191fa09b7e..dfcd83ceee3b 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -604,10 +604,11 @@ repeat: ret = security_ptrace_traceme(current->parent); /* - * Set the ptrace bit in the process ptrace flags. - * Then link us on our parent's ptraced list. + * Check PF_EXITING to ensure ->real_parent has not passed + * exit_ptrace(). Otherwise we don't report the error but + * pretend ->real_parent untraces us right after return. */ - if (!ret) { + if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace |= PT_PTRACED; __ptrace_link(current, current->real_parent); } -- cgit From 3d26dcf7679c5cc6c9f3b95ffdb2152fba2b7fae Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 13 Apr 2009 14:40:08 -0700 Subject: kernel/sys.c: clean up sys_shutdown exit path Impact: cleanup, fix Clean up sys_shutdown() exit path. Factor out common code. Return correct error code instead of always 0 on failure. Signed-off-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index 51dbb55604e8..e7998cf31498 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -360,6 +360,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg) { char buffer[256]; + int ret = 0; /* We only trust the superuser with rebooting the system. */ if (!capable(CAP_SYS_BOOT)) @@ -397,7 +398,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, kernel_halt(); unlock_kernel(); do_exit(0); - break; + panic("cannot halt"); case LINUX_REBOOT_CMD_POWER_OFF: kernel_power_off(); @@ -417,29 +418,22 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, #ifdef CONFIG_KEXEC case LINUX_REBOOT_CMD_KEXEC: - { - int ret; - ret = kernel_kexec(); - unlock_kernel(); - return ret; - } + ret = kernel_kexec(); + break; #endif #ifdef CONFIG_HIBERNATION case LINUX_REBOOT_CMD_SW_SUSPEND: - { - int ret = hibernate(); - unlock_kernel(); - return ret; - } + ret = hibernate(); + break; #endif default: - unlock_kernel(); - return -EINVAL; + ret = -EINVAL; + break; } unlock_kernel(); - return 0; + return ret; } static void deferred_cad(struct work_struct *dummy) -- cgit From 132380a06b24704fd6c9be55c44d4ef3972cead2 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 2 Apr 2009 14:18:25 +0800 Subject: tracing, sched: mark get_parent_ip() notrace Impact: remove overly redundant tracing entries When tracer is "function" or "function_graph", way too much "get_parent_ip" entries are recorded in ring_buffer. Signed-off-by: Lai Jiangshan Acked-by: Frederic Weisbecker Acked-by: Steven Rostedt LKML-Reference: <49D458B1.5000703@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 5724508c3b66..e90e70ed36a3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4846,7 +4846,7 @@ void scheduler_tick(void) #endif } -unsigned long get_parent_ip(unsigned long addr) +notrace unsigned long get_parent_ip(unsigned long addr) { if (in_lock_functions(addr)) { addr = CALLER_ADDR2; -- cgit From 557055bebe9212dfa6b9f5df811dfd0dac77ec55 Mon Sep 17 00:00:00 2001 From: Zhaolei Date: Mon, 13 Apr 2009 16:02:34 +0800 Subject: tracing: Fix branch tracer header Before patch: # tracer: branch # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | <...>-2981 [000] 24008.872738: [ ok ] trace_irq_handler_exit:irq_event_types.h:41 <...>-2981 [000] 24008.872742: [ ok ] note_interrupt:spurious.c:229 ... After patch: # tracer: branch # # TASK-PID CPU# TIMESTAMP CORRECT FUNC:FILE:LINE # | | | | | | <...>-2985 [000] 26329.142970: [ ok ] slab_free:slub.c:1776 <...>-2985 [000] 26329.142972: [ ok ] trace_kmem_cache_free:kmem_event_types.h:191 ... Signed-off-by: Zhao Lei Acked-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Tom Zanussi LKML-Reference: <49E2F19A.3040006@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/trace_branch.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index ad8c22efff41..8333715e4066 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -155,6 +155,13 @@ static enum print_line_t trace_branch_print(struct trace_iterator *iter, return TRACE_TYPE_HANDLED; } +static void branch_print_header(struct seq_file *s) +{ + seq_puts(s, "# TASK-PID CPU# TIMESTAMP CORRECT" + " FUNC:FILE:LINE\n"); + seq_puts(s, "# | | | | | " + " |\n"); +} static struct trace_event trace_branch_event = { .type = TRACE_BRANCH, @@ -169,6 +176,7 @@ static struct tracer branch_trace __read_mostly = #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_branch, #endif /* CONFIG_FTRACE_SELFTEST */ + .print_header = branch_print_header, }; __init static int init_branch_tracer(void) -- cgit From ef631b0ca01655d24e9ca7e199262c4a46416a26 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 13 Apr 2009 21:31:16 -0700 Subject: rcu: Make hierarchical RCU less IPI-happy This patch fixes a hierarchical-RCU performance bug located by Anton Blanchard. The problem stems from a misguided attempt to provide a work-around for jiffies-counter failure. This work-around uses a per-CPU n_rcu_pending counter, which is incremented on each call to rcu_pending(), which in turn is called from each scheduling-clock interrupt. Each CPU then treats this counter as a surrogate for the jiffies counter, so that if the jiffies counter fails to advance, the per-CPU n_rcu_pending counter will cause RCU to invoke force_quiescent_state(), which in turn will (among other things) send resched IPIs to CPUs that have thus far failed to pass through an RCU quiescent state. Unfortunately, each CPU resets only its own counter after sending a batch of IPIs. This means that the other CPUs will also (needlessly) send -another- round of IPIs, for a full N-squared set of IPIs in the worst case every three scheduler-clock ticks until the grace period finally ends. It is not reasonable for a given CPU to reset each and every n_rcu_pending for all the other CPUs, so this patch instead simply disables the jiffies-counter "training wheels", thus eliminating the excessive IPIs. Note that the jiffies-counter IPIs do not have this problem due to the fact that the jiffies counter is global, so that the CPU sending the IPIs can easily reset things, thus preventing the other CPUs from sending redundant IPIs. Note also that the n_rcu_pending counter remains, as it will continue to be used for tracing. It may also see use to update the jiffies counter, should an appropriate kick-the-jiffies-counter API appear. Located-by: Anton Blanchard Tested-by: Anton Blanchard Signed-off-by: Paul E. McKenney Cc: anton@samba.org Cc: akpm@linux-foundation.org Cc: dipankar@in.ibm.com Cc: manfred@colorfullife.com Cc: cl@linux-foundation.org Cc: josht@linux.vnet.ibm.com Cc: schamp@sgi.com Cc: niv@us.ibm.com Cc: dvhltc@us.ibm.com Cc: ego@in.ibm.com Cc: laijs@cn.fujitsu.com Cc: rostedt@goodmis.org Cc: peterz@infradead.org Cc: penberg@cs.helsinki.fi Cc: andi@firstfloor.org Cc: "Paul E. McKenney" LKML-Reference: <12396834793575-git-send-email-> Signed-off-by: Ingo Molnar --- include/linux/rcutree.h | 3 +-- kernel/rcutree.c | 19 ++++--------------- kernel/rcutree_trace.c | 14 +++++--------- 3 files changed, 10 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 0cdda00f2b2a..58b2aa5312b9 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -161,9 +161,8 @@ struct rcu_data { unsigned long offline_fqs; /* Kicked due to being offline. */ unsigned long resched_ipi; /* Sent a resched IPI. */ - /* 5) state to allow this CPU to force_quiescent_state on others */ + /* 5) For future __rcu_pending statistics. */ long n_rcu_pending; /* rcu_pending() calls since boot. */ - long n_rcu_pending_force_qs; /* when to force quiescent states. */ int cpu; }; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 7f3266922572..d2a372fb0b9b 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -530,8 +530,6 @@ static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp) rdp->qs_pending = 1; rdp->passed_quiesc = 0; rdp->gpnum = rsp->gpnum; - rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending + - RCU_JIFFIES_TILL_FORCE_QS; } /* @@ -578,8 +576,6 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rsp->gpnum++; rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */ rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; - rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending + - RCU_JIFFIES_TILL_FORCE_QS; record_gp_stall_check_time(rsp); dyntick_record_completed(rsp, rsp->completed - 1); note_new_gpnum(rsp, rdp); @@ -1055,7 +1051,6 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) { unsigned long flags; long lastcomp; - struct rcu_data *rdp = rsp->rda[smp_processor_id()]; struct rcu_node *rnp = rcu_get_root(rsp); u8 signaled; @@ -1066,16 +1061,13 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) return; /* Someone else is already on the job. */ } if (relaxed && - (long)(rsp->jiffies_force_qs - jiffies) >= 0 && - (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) >= 0) + (long)(rsp->jiffies_force_qs - jiffies) >= 0) goto unlock_ret; /* no emergency and done recently. */ rsp->n_force_qs++; spin_lock(&rnp->lock); lastcomp = rsp->completed; signaled = rsp->signaled; rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; - rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending + - RCU_JIFFIES_TILL_FORCE_QS; if (lastcomp == rsp->gpnum) { rsp->n_force_qs_ngp++; spin_unlock(&rnp->lock); @@ -1144,8 +1136,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) * If an RCU GP has gone long enough, go check for dyntick * idle CPUs and, if needed, send resched IPIs. */ - if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 || - (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0) + if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0) force_quiescent_state(rsp, 1); /* @@ -1230,8 +1221,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), if (unlikely(++rdp->qlen > qhimark)) { rdp->blimit = LONG_MAX; force_quiescent_state(rsp, 0); - } else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 || - (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0) + } else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0) force_quiescent_state(rsp, 1); local_irq_restore(flags); } @@ -1290,8 +1280,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Has an RCU GP gone long enough to send resched IPIs &c? */ if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) && - ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 || - (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0)) + ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)) return 1; /* nothing to do */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 4ee954f6a8d5..4b1875ba9404 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -49,14 +49,12 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) return; - seq_printf(m, "%3d%cc=%ld g=%ld pq=%d pqc=%ld qp=%d rpfq=%ld rp=%x", + seq_printf(m, "%3d%cc=%ld g=%ld pq=%d pqc=%ld qp=%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', rdp->completed, rdp->gpnum, rdp->passed_quiesc, rdp->passed_quiesc_completed, - rdp->qs_pending, - rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending, - (int)(rdp->n_rcu_pending & 0xffff)); + rdp->qs_pending); #ifdef CONFIG_NO_HZ seq_printf(m, " dt=%d/%d dn=%d df=%lu", rdp->dynticks->dynticks, @@ -102,14 +100,12 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) return; - seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d,%ld,%ld", + seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? "\"Y\"" : "\"N\"", rdp->completed, rdp->gpnum, rdp->passed_quiesc, rdp->passed_quiesc_completed, - rdp->qs_pending, - rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending, - rdp->n_rcu_pending); + rdp->qs_pending); #ifdef CONFIG_NO_HZ seq_printf(m, ",%d,%d,%d,%lu", rdp->dynticks->dynticks, @@ -123,7 +119,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) static int show_rcudata_csv(struct seq_file *m, void *unused) { - seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",\"rpfq\",\"rp\","); + seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\","); #ifdef CONFIG_NO_HZ seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\","); #endif /* #ifdef CONFIG_NO_HZ */ -- cgit From 6ec3cfeca04622e3d80c9270191cd7f5f88214af Mon Sep 17 00:00:00 2001 From: "Pallipadi, Venkatesh" Date: Mon, 13 Apr 2009 15:20:58 -0700 Subject: x86, irq: Remove IRQ_DISABLED check in process context IRQ move As discussed in the thread here: http://marc.info/?l=linux-kernel&m=123964468521142&w=2 Eric W. Biederman observed: > It looks like some additional bugs have slipped in since last I looked. > > set_irq_affinity does this: > ifdef CONFIG_GENERIC_PENDING_IRQ > if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { > cpumask_copy(desc->affinity, cpumask); > desc->chip->set_affinity(irq, cpumask); > } else { > desc->status |= IRQ_MOVE_PENDING; > cpumask_copy(desc->pending_mask, cpumask); > } > #else > > That IRQ_DISABLED case is a software state and as such it has nothing to > do with how safe it is to move an irq in process context. [...] > > The only reason we migrate MSIs in interrupt context today is that there > wasn't infrastructure for support migration both in interrupt context > and outside of it. Yes. The idea here was to force the MSI migration to happen in process context. One of the patches in the series did disable_irq(dev->irq); irq_set_affinity(dev->irq, cpumask_of(dev->cpu)); enable_irq(dev->irq); with the above patch adding irq/manage code check for interrupt disabled and moving the interrupt in process context. IIRC, there was no IRQ_MOVE_PCNTXT when we were developing this HPET code and we ended up having this ugly hack. IRQ_MOVE_PCNTXT was there when we eventually submitted the patch upstream. But, looks like I did a blind rebasing instead of using IRQ_MOVE_PCNTXT in hpet MSI code. Below patch fixes this. i.e., revert commit 932775a4ab622e3c99bd59f14cc and add PCNTXT to HPET MSI setup. Also removes copying of desc->affinity in generic code as set_affinity routines are doing it internally. Reported-by: "Eric W. Biederman" Signed-off-by: Venkatesh Pallipadi Acked-by: "Eric W. Biederman" Cc: "Li Shaohua" Cc: Gary Hade Cc: "lcm@us.ibm.com" Cc: suresh.b.siddha@intel.com LKML-Reference: <20090413222058.GB8211@linux-os.sc.intel.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/io_apic.c | 2 ++ kernel/irq/manage.c | 5 ++--- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index a2789e42e162..30da617d18e4 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3670,12 +3670,14 @@ int arch_setup_hpet_msi(unsigned int irq) { int ret; struct msi_msg msg; + struct irq_desc *desc = irq_to_desc(irq); ret = msi_compose_msg(NULL, irq, &msg); if (ret < 0) return ret; hpet_msi_write(irq, &msg); + desc->status |= IRQ_MOVE_PCNTXT; set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq, "edge"); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 7e2e7dd4cd2f..2734eca59243 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -109,10 +109,9 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) spin_lock_irqsave(&desc->lock, flags); #ifdef CONFIG_GENERIC_PENDING_IRQ - if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { - cpumask_copy(desc->affinity, cpumask); + if (desc->status & IRQ_MOVE_PCNTXT) desc->chip->set_affinity(irq, cpumask); - } else { + else { desc->status |= IRQ_MOVE_PENDING; cpumask_copy(desc->pending_mask, cpumask); } -- cgit From 297dbf50d7ab0539cf9cf7f2a66918665a18e45e Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Wed, 15 Apr 2009 10:37:04 +0530 Subject: swap: Remove code handling bio_alloc failure with __GFP_WAIT Remove code handling bio_alloc failure with __GFP_WAIT. Signed-off-by: Nikanth Karthikesan Signed-off-by: Jens Axboe --- kernel/power/swap.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 505f319e489c..8ba052c86d48 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -64,8 +64,6 @@ static int submit(int rw, pgoff_t page_off, struct page *page, struct bio *bio; bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1); - if (!bio) - return -ENOMEM; bio->bi_sector = page_off * (PAGE_SIZE >> 9); bio->bi_bdev = resume_bdev; bio->bi_end_io = end_swap_bio_read; -- cgit From 5b1d07ed0e5b2707f786957c7a40eb2f399c84a8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 15 Apr 2009 19:35:01 +0100 Subject: RCU: Don't try and predeclare inline funcs as it upsets some versions of gcc Don't try and predeclare inline funcs like this: static inline void wait_migrated_callbacks(void) ... static void _rcu_barrier(enum rcu_barrier type) { ... wait_migrated_callbacks(); } ... static inline void wait_migrated_callbacks(void) { wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count)); } as it upsets some versions of gcc under some circumstances: kernel/rcupdate.c: In function `_rcu_barrier': kernel/rcupdate.c:125: sorry, unimplemented: inlining failed in call to 'wait_migrated_callbacks': function body not available kernel/rcupdate.c:152: sorry, unimplemented: called from here This can be dealt with by simply putting the static variables (rcu_migrate_*) at the top, and moving the implementation of the function up so that it replaces its forward declaration. Signed-off-by: David Howells Cc: Dipankar Sarma Cc: Paul E. McKenney Signed-off-by: Linus Torvalds --- kernel/rcupdate.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 2c7b8457d0d2..a967c9feb90a 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -58,6 +58,10 @@ static DEFINE_MUTEX(rcu_barrier_mutex); static struct completion rcu_barrier_completion; int rcu_scheduler_active __read_mostly; +static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0); +static struct rcu_head rcu_migrate_head[3]; +static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq); + /* * Awaken the corresponding synchronize_rcu() instance now that a * grace period has elapsed. @@ -122,7 +126,10 @@ static void rcu_barrier_func(void *type) } } -static inline void wait_migrated_callbacks(void); +static inline void wait_migrated_callbacks(void) +{ + wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count)); +} /* * Orchestrate the specified type of RCU barrier, waiting for all @@ -179,21 +186,12 @@ void rcu_barrier_sched(void) } EXPORT_SYMBOL_GPL(rcu_barrier_sched); -static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0); -static struct rcu_head rcu_migrate_head[3]; -static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq); - static void rcu_migrate_callback(struct rcu_head *notused) { if (atomic_dec_and_test(&rcu_migrate_type_count)) wake_up(&rcu_migrate_wq); } -static inline void wait_migrated_callbacks(void) -{ - wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count)); -} - static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self, unsigned long action, void *hcpu) { -- cgit From 381512cf3d27f63f7a45b1bbe7d2d609c2ea3b74 Mon Sep 17 00:00:00 2001 From: Gautham R Shenoy Date: Tue, 14 Apr 2009 09:09:36 +0530 Subject: sched: Avoid printing sched_group::__cpu_power for default case Commit 46e0bb9c12f4 ("sched: Print sched_group::__cpu_power in sched_domain_debug") produces a messy dmesg output while attempting to print the sched_group::__cpu_power for each group in the sched_domain hierarchy. Fix this by avoid printing the __cpu_power for default cases. (i.e, __cpu_power == SCHED_LOAD_SCALE). [ Impact: reduce syslog clutter ] Reported-by: Tony Luck Signed-off-by: Gautham R Shenoy Fixed-by: Tony Luck Cc: a.p.zijlstra@chello.nl LKML-Reference: <20090414033936.GA534@in.ibm.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index e90e70ed36a3..b902e587a3a0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7367,8 +7367,12 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpumask_or(groupmask, groupmask, sched_group_cpus(group)); cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); - printk(KERN_CONT " %s (__cpu_power = %d)", str, - group->__cpu_power); + + printk(KERN_CONT " %s", str); + if (group->__cpu_power != SCHED_LOAD_SCALE) { + printk(KERN_CONT " (__cpu_power = %d)", + group->__cpu_power); + } group = group->next; } while (group != sd->groups); -- cgit From 79d381c9f2354b594dcab9b04dfcc0debf7294fe Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Thu, 16 Apr 2009 19:30:18 -0400 Subject: kernel/softirq.c: fix sparse warning Fix sparse warning in kernel/softirq.c. warning: do-while statement is not a compound statement Signed-off-by: H Hartley Sweeten LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/softirq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/softirq.c b/kernel/softirq.c index 2fecefacdc5b..b525dd348511 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -472,9 +472,9 @@ void tasklet_kill(struct tasklet_struct *t) printk("Attempt to kill tasklet from interrupt\n"); while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { - do + do { yield(); - while (test_bit(TASKLET_STATE_SCHED, &t->state)); + } while (test_bit(TASKLET_STATE_SCHED, &t->state)); } tasklet_unlock_wait(t); clear_bit(TASKLET_STATE_SCHED, &t->state); -- cgit From c8a250058656495be02c00de61e26b017c86ef00 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 17 Apr 2009 09:40:49 +0200 Subject: lockdep: more robust lockdep_map init sequence Steven Rostedt reported: > OK, I think I figured this bug out. This is a lockdep issue with respect > to tracepoints. > > The trace points in lockdep are called all the time. Outside the lockdep > logic. But if lockdep were to trigger an error / warning (which this run > did) we might be in trouble. For new locks, like the dentry->d_lock, that > are created, they will not get a name: > > void lockdep_init_map(struct lockdep_map *lock, const char *name, > struct lock_class_key *key, int subclass) > { > if (unlikely(!debug_locks)) > return; > > When a problem is found by lockdep, debug_locks becomes false. Thus we > stop allocating names for locks. This dentry->d_lock I had, now has no > name. Worse yet, I have CONFIG_DEBUG_VM set, that scrambles non > initialized memory. Thus, when the trace point was hit, it had junk for > the lock->name, and the machine crashed. Ah, nice catch. I think we should put at least the name in regardless. Ensure we at least initialize the trivial entries of the depmap so that they can be relied upon, even when lockdep itself decided to pack up and go home. [ Impact: fix lock tracing after lockdep warnings. ] Reported-by: Steven Rostedt Signed-off-by: Peter Zijlstra Acked-by: Steven Rostedt Cc: Andrew Morton Cc: Frederic Weisbecker LKML-Reference: <1239954049.23397.4156.camel@laptop> Signed-off-by: Ingo Molnar --- kernel/lockdep.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index b0f011866969..accb40cdb12a 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -2490,13 +2490,20 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, void lockdep_init_map(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass) { - if (unlikely(!debug_locks)) + lock->class_cache = NULL; +#ifdef CONFIG_LOCK_STAT + lock->cpu = raw_smp_processor_id(); +#endif + + if (DEBUG_LOCKS_WARN_ON(!name)) { + lock->name = "NULL"; return; + } + + lock->name = name; if (DEBUG_LOCKS_WARN_ON(!key)) return; - if (DEBUG_LOCKS_WARN_ON(!name)) - return; /* * Sanity check, the lock-class key must be persistent: */ @@ -2505,12 +2512,11 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, DEBUG_LOCKS_WARN_ON(1); return; } - lock->name = name; lock->key = key; - lock->class_cache = NULL; -#ifdef CONFIG_LOCK_STAT - lock->cpu = raw_smp_processor_id(); -#endif + + if (unlikely(!debug_locks)) + return; + if (subclass) register_lock_class(lock, subclass, 1); } -- cgit From ff54250a0ebab7f90a5f848a0ba63f999830c872 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 18 Apr 2009 21:44:24 -0700 Subject: Remove 'recurse into child resources' logic from 'reserve_region_with_split()' This function is not actually used right now, since the original use case for it was done with insert_resource_expand_to_fit() instead. However, we now have another usage case that wants to basically do a "reserve IO resource, splitting around existing resources", however that one doesn't actually want the "recurse into the conflicting resource" logic at all. And since recursing into the conflicting resource was the most complex part, and isn't wanted, just remove it. Maybe we'll some day want both versions, but we can just resurrect the logic then. Tested-by: Yinghai Lu Signed-off-by: Linus Torvalds --- kernel/resource.c | 46 ++++++++++++---------------------------------- 1 file changed, 12 insertions(+), 34 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index fd5d7d574bb9..ac5f3a36923f 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -533,43 +533,21 @@ static void __init __reserve_region_with_split(struct resource *root, res->end = end; res->flags = IORESOURCE_BUSY; - for (;;) { - conflict = __request_resource(parent, res); - if (!conflict) - break; - if (conflict != parent) { - parent = conflict; - if (!(conflict->flags & IORESOURCE_BUSY)) - continue; - } - - /* Uhhuh, that didn't work out.. */ - kfree(res); - res = NULL; - break; - } - - if (!res) { - /* failed, split and try again */ - - /* conflict covered whole area */ - if (conflict->start <= start && conflict->end >= end) - return; + conflict = __request_resource(parent, res); + if (!conflict) + return; - if (conflict->start > start) - __reserve_region_with_split(root, start, conflict->start-1, name); - if (!(conflict->flags & IORESOURCE_BUSY)) { - resource_size_t common_start, common_end; + /* failed, split and try again */ + kfree(res); - common_start = max(conflict->start, start); - common_end = min(conflict->end, end); - if (common_start < common_end) - __reserve_region_with_split(root, common_start, common_end, name); - } - if (conflict->end < end) - __reserve_region_with_split(root, conflict->end+1, end, name); - } + /* conflict covered whole area */ + if (conflict->start <= start && conflict->end >= end) + return; + if (conflict->start > start) + __reserve_region_with_split(root, start, conflict->start-1, name); + if (conflict->end < end) + __reserve_region_with_split(root, conflict->end+1, end, name); } void __init reserve_region_with_split(struct resource *root, -- cgit From 6a7c7eaf71b636f197d73b381a2ab729ebdcfb2e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 19 Apr 2009 20:08:42 +0200 Subject: PM/Suspend: Introduce two new platform callbacks to avoid breakage Commit 900af0d973856d6feb6fc088c2d0d3fde57707d3 (PM: Change suspend code ordering) changed the ordering of suspend code in such a way that the platform .prepare() callback is now executed after the device drivers' late suspend callbacks have run. Unfortunately, this turns out to break ARM platforms that need to talk via I2C to power control devices during the .prepare() callback. For this reason introduce two new platform suspend callbacks, .prepare_late() and .wake(), that will be called just prior to disabling non-boot CPUs and right after bringing them back on line, respectively, and use them instead of .prepare() and .finish() for ACPI suspend. Make the PM core execute the .prepare() and .finish() platform suspend callbacks where they were executed previously (that is, right after calling the regular suspend methods provided by device drivers and right before executing their regular resume methods, respectively). It is not necessary to make analogous changes to the hibernation code and data structures at the moment, because they are only used by ACPI platforms. Signed-off-by: Rafael J. Wysocki Reported-by: Russell King Acked-by: Len Brown --- drivers/acpi/sleep.c | 8 ++++---- include/linux/suspend.h | 36 ++++++++++++++++++++++++++---------- kernel/power/main.c | 24 +++++++++++++++++------- 3 files changed, 47 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 779e4e500df4..d060e6fd7fd5 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -300,9 +300,9 @@ static int acpi_suspend_state_valid(suspend_state_t pm_state) static struct platform_suspend_ops acpi_suspend_ops = { .valid = acpi_suspend_state_valid, .begin = acpi_suspend_begin, - .prepare = acpi_pm_prepare, + .prepare_late = acpi_pm_prepare, .enter = acpi_suspend_enter, - .finish = acpi_pm_finish, + .wake = acpi_pm_finish, .end = acpi_pm_end, }; @@ -328,9 +328,9 @@ static int acpi_suspend_begin_old(suspend_state_t pm_state) static struct platform_suspend_ops acpi_suspend_ops_old = { .valid = acpi_suspend_state_valid, .begin = acpi_suspend_begin_old, - .prepare = acpi_pm_disable_gpes, + .prepare_late = acpi_pm_disable_gpes, .enter = acpi_suspend_enter, - .finish = acpi_pm_finish, + .wake = acpi_pm_finish, .end = acpi_pm_end, .recover = acpi_pm_finish, }; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 3e3a4364cbff..795032edfc46 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -58,10 +58,17 @@ typedef int __bitwise suspend_state_t; * by @begin(). * @prepare() is called right after devices have been suspended (ie. the * appropriate .suspend() method has been executed for each device) and - * before the nonboot CPUs are disabled (it is executed with IRQs enabled). - * This callback is optional. It returns 0 on success or a negative - * error code otherwise, in which case the system cannot enter the desired - * sleep state (@enter() and @finish() will not be called in that case). + * before device drivers' late suspend callbacks are executed. It returns + * 0 on success or a negative error code otherwise, in which case the + * system cannot enter the desired sleep state (@prepare_late(), @enter(), + * @wake(), and @finish() will not be called in that case). + * + * @prepare_late: Finish preparing the platform for entering the system sleep + * state indicated by @begin(). + * @prepare_late is called before disabling nonboot CPUs and after + * device drivers' late suspend callbacks have been executed. It returns + * 0 on success or a negative error code otherwise, in which case the + * system cannot enter the desired sleep state (@enter() and @wake()). * * @enter: Enter the system sleep state indicated by @begin() or represented by * the argument if @begin() is not implemented. @@ -69,19 +76,26 @@ typedef int __bitwise suspend_state_t; * error code otherwise, in which case the system cannot enter the desired * sleep state. * - * @finish: Called when the system has just left a sleep state, right after - * the nonboot CPUs have been enabled and before devices are resumed (it is - * executed with IRQs enabled). + * @wake: Called when the system has just left a sleep state, right after + * the nonboot CPUs have been enabled and before device drivers' early + * resume callbacks are executed. + * This callback is optional, but should be implemented by the platforms + * that implement @prepare_late(). If implemented, it is always called + * after @enter(), even if @enter() fails. + * + * @finish: Finish wake-up of the platform. + * @finish is called right prior to calling device drivers' regular suspend + * callbacks. * This callback is optional, but should be implemented by the platforms * that implement @prepare(). If implemented, it is always called after - * @enter() (even if @enter() fails). + * @enter() and @wake(), if implemented, even if any of them fails. * * @end: Called by the PM core right after resuming devices, to indicate to * the platform that the system has returned to the working state or * the transition to the sleep state has been aborted. * This callback is optional, but should be implemented by the platforms - * that implement @begin(), but platforms implementing @begin() should - * also provide a @end() which cleans up transitions aborted before + * that implement @begin(). Accordingly, platforms implementing @begin() + * should also provide a @end() which cleans up transitions aborted before * @enter(). * * @recover: Recover the platform from a suspend failure. @@ -93,7 +107,9 @@ struct platform_suspend_ops { int (*valid)(suspend_state_t state); int (*begin)(suspend_state_t state); int (*prepare)(void); + int (*prepare_late)(void); int (*enter)(suspend_state_t state); + void (*wake)(void); void (*finish)(void); void (*end)(void); void (*recover)(void); diff --git a/kernel/power/main.c b/kernel/power/main.c index f172f41858bb..f99ed6a75eac 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -291,20 +291,26 @@ static int suspend_enter(suspend_state_t state) device_pm_lock(); + if (suspend_ops->prepare) { + error = suspend_ops->prepare(); + if (error) + goto Done; + } + error = device_power_down(PMSG_SUSPEND); if (error) { printk(KERN_ERR "PM: Some devices failed to power down\n"); - goto Done; + goto Platfrom_finish; } - if (suspend_ops->prepare) { - error = suspend_ops->prepare(); + if (suspend_ops->prepare_late) { + error = suspend_ops->prepare_late(); if (error) goto Power_up_devices; } if (suspend_test(TEST_PLATFORM)) - goto Platfrom_finish; + goto Platform_wake; error = disable_nonboot_cpus(); if (error || suspend_test(TEST_CPUS)) @@ -326,13 +332,17 @@ static int suspend_enter(suspend_state_t state) Enable_cpus: enable_nonboot_cpus(); - Platfrom_finish: - if (suspend_ops->finish) - suspend_ops->finish(); + Platform_wake: + if (suspend_ops->wake) + suspend_ops->wake(); Power_up_devices: device_power_up(PMSG_RESUME); + Platfrom_finish: + if (suspend_ops->finish) + suspend_ops->finish(); + Done: device_pm_unlock(); -- cgit From 24b6f16ecf37f918a1934d590e9e71c100d6388f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Apr 2009 03:25:41 -0400 Subject: No need for crossing to mountpoint in audit_tag_tree() is_under() will DTRT anyway. And yes, is_subdir() behaviour is intentional. Signed-off-by: Al Viro --- fs/dcache.c | 1 - kernel/audit_tree.c | 3 --- 2 files changed, 4 deletions(-) (limited to 'kernel') diff --git a/fs/dcache.c b/fs/dcache.c index 761d30be2683..1fcffebfb44f 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2149,7 +2149,6 @@ int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) int result; unsigned long seq; - /* FIXME: This is old behavior, needed? Please check callers. */ if (new_dentry == old_dentry) return 1; diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 917ab9525568..6e7351739a82 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -734,9 +734,6 @@ int audit_tag_tree(char *old, char *new) dentry = dget(path.dentry); path_put(&path); - if (dentry == tagged->mnt_root && dentry == mnt->mnt_root) - follow_up(&mnt, &dentry); - list_add_tail(&list, &tagged->mnt_list); mutex_lock(&audit_filter_mutex); -- cgit From 8e19608e8b5c001e4a66ce482edc474f05fb7355 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Tue, 21 Apr 2009 12:24:00 -0700 Subject: clocksource: pass clocksource to read() callback Pass clocksource pointer to the read() callback for clocksources. This allows us to share the callback between multiple instances. [hugh@veritas.com: fix powerpc build of clocksource pass clocksource mods] [akpm@linux-foundation.org: cleanup] Signed-off-by: Magnus Damm Acked-by: John Stultz Cc: Thomas Gleixner Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mach-at91/at91rm9200_time.c | 2 +- arch/arm/mach-at91/at91sam926x_time.c | 2 +- arch/arm/mach-davinci/time.c | 2 +- arch/arm/mach-imx/time.c | 2 +- arch/arm/mach-ixp4xx/common.c | 2 +- arch/arm/mach-msm/timer.c | 4 ++-- arch/arm/mach-netx/time.c | 2 +- arch/arm/mach-ns9xxx/time-ns9360.c | 2 +- arch/arm/mach-omap1/time.c | 2 +- arch/arm/mach-omap2/timer-gp.c | 2 +- arch/arm/mach-pxa/time.c | 2 +- arch/arm/mach-realview/core.c | 2 +- arch/arm/mach-versatile/core.c | 2 +- arch/arm/plat-mxc/time.c | 2 +- arch/arm/plat-omap/common.c | 4 ++-- arch/arm/plat-orion/time.c | 2 +- arch/avr32/kernel/time.c | 2 +- arch/blackfin/kernel/time-ts.c | 12 ++++++------ arch/ia64/kernel/cyclone.c | 2 +- arch/ia64/kernel/time.c | 4 ++-- arch/ia64/sn/kernel/sn2/timer.c | 2 +- arch/m68knommu/platform/68328/timers.c | 2 +- arch/m68knommu/platform/coldfire/dma_timer.c | 2 +- arch/m68knommu/platform/coldfire/pit.c | 2 +- arch/m68knommu/platform/coldfire/timers.c | 2 +- arch/mips/kernel/cevt-txx9.c | 2 +- arch/mips/kernel/csrc-bcm1480.c | 2 +- arch/mips/kernel/csrc-ioasic.c | 6 +++--- arch/mips/kernel/csrc-r4k.c | 2 +- arch/mips/kernel/csrc-sb1250.c | 2 +- arch/mips/kernel/i8253.c | 2 +- arch/mips/nxp/pnx8550/common/time.c | 2 +- arch/mips/sgi-ip27/ip27-timer.c | 2 +- arch/powerpc/kernel/time.c | 8 ++++---- arch/s390/kernel/time.c | 2 +- arch/sh/kernel/time_32.c | 2 +- arch/sh/kernel/timers/timer-tmu.c | 2 +- arch/sparc/kernel/time_64.c | 7 ++++++- arch/um/kernel/time.c | 2 +- arch/x86/kernel/hpet.c | 6 +++--- arch/x86/kernel/i8253.c | 2 +- arch/x86/kernel/kvmclock.c | 7 ++++++- arch/x86/kernel/tsc.c | 2 +- arch/x86/kernel/vmiclock_32.c | 2 +- arch/x86/lguest/boot.c | 2 +- arch/x86/xen/time.c | 7 ++++++- drivers/char/hpet.c | 2 +- drivers/clocksource/acpi_pm.c | 12 ++++++------ drivers/clocksource/cyclone.c | 2 +- drivers/clocksource/scx200_hrt.c | 2 +- drivers/clocksource/tcb_clksrc.c | 2 +- include/linux/clocksource.h | 6 +++--- kernel/time/clocksource.c | 8 ++++---- kernel/time/jiffies.c | 2 +- 54 files changed, 94 insertions(+), 79 deletions(-) (limited to 'kernel') diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c index 1ff1bda0a894..309f3511aa20 100644 --- a/arch/arm/mach-at91/at91rm9200_time.c +++ b/arch/arm/mach-at91/at91rm9200_time.c @@ -85,7 +85,7 @@ static struct irqaction at91rm9200_timer_irq = { .handler = at91rm9200_timer_interrupt }; -static cycle_t read_clk32k(void) +static cycle_t read_clk32k(struct clocksource *cs) { return read_CRTR(); } diff --git a/arch/arm/mach-at91/at91sam926x_time.c b/arch/arm/mach-at91/at91sam926x_time.c index b63e1d5f1bad..4bd56aee4370 100644 --- a/arch/arm/mach-at91/at91sam926x_time.c +++ b/arch/arm/mach-at91/at91sam926x_time.c @@ -31,7 +31,7 @@ static u32 pit_cnt; /* access only w/system irq blocked */ * Clocksource: just a monotonic counter of MCK/16 cycles. * We don't care whether or not PIT irqs are enabled. */ -static cycle_t read_pit_clk(void) +static cycle_t read_pit_clk(struct clocksource *cs) { unsigned long flags; u32 elapsed; diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c index f8bcd29d17a6..6c227d4ba998 100644 --- a/arch/arm/mach-davinci/time.c +++ b/arch/arm/mach-davinci/time.c @@ -238,7 +238,7 @@ static void __init timer_init(void) /* * clocksource */ -static cycle_t read_cycles(void) +static cycle_t read_cycles(struct clocksource *cs) { struct timer_s *t = &timers[TID_CLOCKSOURCE]; diff --git a/arch/arm/mach-imx/time.c b/arch/arm/mach-imx/time.c index aff0ebcfa847..5aef18b599e5 100644 --- a/arch/arm/mach-imx/time.c +++ b/arch/arm/mach-imx/time.c @@ -73,7 +73,7 @@ static void __init imx_timer_hardware_init(void) IMX_TCTL(TIMER_BASE) = TCTL_FRR | TCTL_CLK_PCLK1 | TCTL_TEN; } -cycle_t imx_get_cycles(void) +cycle_t imx_get_cycles(struct clocksource *cs) { return IMX_TCN(TIMER_BASE); } diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c index f4656d2ac8a8..1e93dfee7543 100644 --- a/arch/arm/mach-ixp4xx/common.c +++ b/arch/arm/mach-ixp4xx/common.c @@ -401,7 +401,7 @@ void __init ixp4xx_sys_init(void) /* * clocksource */ -cycle_t ixp4xx_get_cycles(void) +cycle_t ixp4xx_get_cycles(struct clocksource *cs) { return *IXP4XX_OSTS; } diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c index 444d9c0f5ca6..4855b8ca5101 100644 --- a/arch/arm/mach-msm/timer.c +++ b/arch/arm/mach-msm/timer.c @@ -57,12 +57,12 @@ static irqreturn_t msm_timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static cycle_t msm_gpt_read(void) +static cycle_t msm_gpt_read(struct clocksource *cs) { return readl(MSM_GPT_BASE + TIMER_COUNT_VAL); } -static cycle_t msm_dgt_read(void) +static cycle_t msm_dgt_read(struct clocksource *cs) { return readl(MSM_DGT_BASE + TIMER_COUNT_VAL) >> MSM_DGT_SHIFT; } diff --git a/arch/arm/mach-netx/time.c b/arch/arm/mach-netx/time.c index f201fddb594f..82801dbf0579 100644 --- a/arch/arm/mach-netx/time.c +++ b/arch/arm/mach-netx/time.c @@ -104,7 +104,7 @@ static struct irqaction netx_timer_irq = { .handler = netx_timer_interrupt, }; -cycle_t netx_get_cycles(void) +cycle_t netx_get_cycles(struct clocksource *cs) { return readl(NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKSOURCE)); } diff --git a/arch/arm/mach-ns9xxx/time-ns9360.c b/arch/arm/mach-ns9xxx/time-ns9360.c index 41df69721769..77281260358a 100644 --- a/arch/arm/mach-ns9xxx/time-ns9360.c +++ b/arch/arm/mach-ns9xxx/time-ns9360.c @@ -25,7 +25,7 @@ #define TIMER_CLOCKEVENT 1 static u32 latch; -static cycle_t ns9360_clocksource_read(void) +static cycle_t ns9360_clocksource_read(struct clocksource *cs) { return __raw_readl(SYS_TR(TIMER_CLOCKSOURCE)); } diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c index 495a32c287b4..4d56408d3cff 100644 --- a/arch/arm/mach-omap1/time.c +++ b/arch/arm/mach-omap1/time.c @@ -198,7 +198,7 @@ static struct irqaction omap_mpu_timer2_irq = { .handler = omap_mpu_timer2_interrupt, }; -static cycle_t mpu_read(void) +static cycle_t mpu_read(struct clocksource *cs) { return ~omap_mpu_timer_read(1); } diff --git a/arch/arm/mach-omap2/timer-gp.c b/arch/arm/mach-omap2/timer-gp.c index 9fc13a2cc3f4..1cb2c0909c2b 100644 --- a/arch/arm/mach-omap2/timer-gp.c +++ b/arch/arm/mach-omap2/timer-gp.c @@ -138,7 +138,7 @@ static inline void __init omap2_gp_clocksource_init(void) {} * clocksource */ static struct omap_dm_timer *gpt_clocksource; -static cycle_t clocksource_read_cycles(void) +static cycle_t clocksource_read_cycles(struct clocksource *cs) { return (cycle_t)omap_dm_timer_read_counter(gpt_clocksource); } diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c index 8eb3830fbb0b..750c448db672 100644 --- a/arch/arm/mach-pxa/time.c +++ b/arch/arm/mach-pxa/time.c @@ -125,7 +125,7 @@ static struct clock_event_device ckevt_pxa_osmr0 = { .set_mode = pxa_osmr0_set_mode, }; -static cycle_t pxa_read_oscr(void) +static cycle_t pxa_read_oscr(struct clocksource *cs) { return OSCR; } diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index 9ab947c14f26..942e1a7eb9b2 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -715,7 +715,7 @@ static struct irqaction realview_timer_irq = { .handler = realview_timer_interrupt, }; -static cycle_t realview_get_cycles(void) +static cycle_t realview_get_cycles(struct clocksource *cs) { return ~readl(timer3_va_base + TIMER_VALUE); } diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c index 565776680d8c..1f929c391af7 100644 --- a/arch/arm/mach-versatile/core.c +++ b/arch/arm/mach-versatile/core.c @@ -948,7 +948,7 @@ static struct irqaction versatile_timer_irq = { .handler = versatile_timer_interrupt, }; -static cycle_t versatile_get_cycles(void) +static cycle_t versatile_get_cycles(struct clocksource *cs) { return ~readl(TIMER3_VA_BASE + TIMER_VALUE); } diff --git a/arch/arm/plat-mxc/time.c b/arch/arm/plat-mxc/time.c index ef1b3cd85bd3..dab3357196fb 100644 --- a/arch/arm/plat-mxc/time.c +++ b/arch/arm/plat-mxc/time.c @@ -36,7 +36,7 @@ static enum clock_event_mode clockevent_mode = CLOCK_EVT_MODE_UNUSED; /* clock source */ -static cycle_t mxc_get_cycles(void) +static cycle_t mxc_get_cycles(struct clocksource *cs) { return __raw_readl(TIMER_BASE + MXC_TCN); } diff --git a/arch/arm/plat-omap/common.c b/arch/arm/plat-omap/common.c index d1797147732f..433021f3d7cc 100644 --- a/arch/arm/plat-omap/common.c +++ b/arch/arm/plat-omap/common.c @@ -185,7 +185,7 @@ console_initcall(omap_add_serial_console); #include -static cycle_t omap_32k_read(void) +static cycle_t omap_32k_read(struct clocksource *cs) { return omap_readl(TIMER_32K_SYNCHRONIZED); } @@ -207,7 +207,7 @@ unsigned long long sched_clock(void) { unsigned long long ret; - ret = (unsigned long long)omap_32k_read(); + ret = (unsigned long long)omap_32k_read(&clocksource_32k); ret = (ret * clocksource_32k.mult_orig) >> clocksource_32k.shift; return ret; } diff --git a/arch/arm/plat-orion/time.c b/arch/arm/plat-orion/time.c index 6fa2923e6dca..2faf9dba4ef7 100644 --- a/arch/arm/plat-orion/time.c +++ b/arch/arm/plat-orion/time.c @@ -41,7 +41,7 @@ static u32 ticks_per_jiffy; /* * Clocksource handling. */ -static cycle_t orion_clksrc_read(void) +static cycle_t orion_clksrc_read(struct clocksource *cs) { return 0xffffffff - readl(TIMER0_VAL); } diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c index 0ff46bf873b0..f27aa3b259fa 100644 --- a/arch/avr32/kernel/time.c +++ b/arch/avr32/kernel/time.c @@ -18,7 +18,7 @@ #include -static cycle_t read_cycle_count(void) +static cycle_t read_cycle_count(struct clocksource *cs) { return (cycle_t)sysreg_read(COUNT); } diff --git a/arch/blackfin/kernel/time-ts.c b/arch/blackfin/kernel/time-ts.c index 0ed2badfd746..27646121280a 100644 --- a/arch/blackfin/kernel/time-ts.c +++ b/arch/blackfin/kernel/time-ts.c @@ -58,16 +58,11 @@ static inline unsigned long long cycles_2_ns(cycle_t cyc) return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR; } -static cycle_t read_cycles(void) +static cycle_t read_cycles(struct clocksource *cs) { return __bfin_cycles_off + (get_cycles() << __bfin_cycles_mod); } -unsigned long long sched_clock(void) -{ - return cycles_2_ns(read_cycles()); -} - static struct clocksource clocksource_bfin = { .name = "bfin_cycles", .rating = 350, @@ -77,6 +72,11 @@ static struct clocksource clocksource_bfin = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +unsigned long long sched_clock(void) +{ + return cycles_2_ns(read_cycles(&clocksource_bfin)); +} + static int __init bfin_clocksource_init(void) { set_cyc2ns_scale(get_cclk() / 1000); diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c index 790ef0d87e12..71e35864d2e2 100644 --- a/arch/ia64/kernel/cyclone.c +++ b/arch/ia64/kernel/cyclone.c @@ -21,7 +21,7 @@ void __init cyclone_setup(void) static void __iomem *cyclone_mc; -static cycle_t read_cyclone(void) +static cycle_t read_cyclone(struct clocksource *cs) { return (cycle_t)readq((void __iomem *)cyclone_mc); } diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 641c8b61c4f1..604c1a35db33 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -33,7 +33,7 @@ #include "fsyscall_gtod_data.h" -static cycle_t itc_get_cycles(void); +static cycle_t itc_get_cycles(struct clocksource *cs); struct fsyscall_gtod_data_t fsyscall_gtod_data = { .lock = SEQLOCK_UNLOCKED, @@ -383,7 +383,7 @@ ia64_init_itm (void) } } -static cycle_t itc_get_cycles(void) +static cycle_t itc_get_cycles(struct clocksource *cs) { u64 lcycle, now, ret; diff --git a/arch/ia64/sn/kernel/sn2/timer.c b/arch/ia64/sn/kernel/sn2/timer.c index cf67fc562054..21d6f09e3447 100644 --- a/arch/ia64/sn/kernel/sn2/timer.c +++ b/arch/ia64/sn/kernel/sn2/timer.c @@ -23,7 +23,7 @@ extern unsigned long sn_rtc_cycles_per_second; -static cycle_t read_sn2(void) +static cycle_t read_sn2(struct clocksource *cs) { return (cycle_t)readq(RTC_COUNTER_ADDR); } diff --git a/arch/m68knommu/platform/68328/timers.c b/arch/m68knommu/platform/68328/timers.c index 6bafefa546e5..309f725995bf 100644 --- a/arch/m68knommu/platform/68328/timers.c +++ b/arch/m68knommu/platform/68328/timers.c @@ -75,7 +75,7 @@ static struct irqaction m68328_timer_irq = { /***************************************************************************/ -static cycle_t m68328_read_clk(void) +static cycle_t m68328_read_clk(struct clocksource *cs) { unsigned long flags; u32 cycles; diff --git a/arch/m68knommu/platform/coldfire/dma_timer.c b/arch/m68knommu/platform/coldfire/dma_timer.c index 772578b1084f..a5f562823d7a 100644 --- a/arch/m68knommu/platform/coldfire/dma_timer.c +++ b/arch/m68knommu/platform/coldfire/dma_timer.c @@ -34,7 +34,7 @@ #define DMA_DTMR_CLK_DIV_16 (2 << 1) #define DMA_DTMR_ENABLE (1 << 0) -static cycle_t cf_dt_get_cycles(void) +static cycle_t cf_dt_get_cycles(struct clocksource *cs) { return __raw_readl(DTCN0); } diff --git a/arch/m68knommu/platform/coldfire/pit.c b/arch/m68knommu/platform/coldfire/pit.c index 2a12e7fa9748..61b96211f8ff 100644 --- a/arch/m68knommu/platform/coldfire/pit.c +++ b/arch/m68knommu/platform/coldfire/pit.c @@ -125,7 +125,7 @@ static struct irqaction pit_irq = { /***************************************************************************/ -static cycle_t pit_read_clk(void) +static cycle_t pit_read_clk(struct clocksource *cs) { unsigned long flags; u32 cycles; diff --git a/arch/m68knommu/platform/coldfire/timers.c b/arch/m68knommu/platform/coldfire/timers.c index 454f25493491..1ba8a3731653 100644 --- a/arch/m68knommu/platform/coldfire/timers.c +++ b/arch/m68knommu/platform/coldfire/timers.c @@ -78,7 +78,7 @@ static struct irqaction mcftmr_timer_irq = { /***************************************************************************/ -static cycle_t mcftmr_read_clk(void) +static cycle_t mcftmr_read_clk(struct clocksource *cs) { unsigned long flags; u32 cycles; diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c index eccf7d6096bd..2e911e3da8d3 100644 --- a/arch/mips/kernel/cevt-txx9.c +++ b/arch/mips/kernel/cevt-txx9.c @@ -22,7 +22,7 @@ static struct txx9_tmr_reg __iomem *txx9_cs_tmrptr; -static cycle_t txx9_cs_read(void) +static cycle_t txx9_cs_read(struct clocksource *cs) { return __raw_readl(&txx9_cs_tmrptr->trr); } diff --git a/arch/mips/kernel/csrc-bcm1480.c b/arch/mips/kernel/csrc-bcm1480.c index 868745e7184b..51489f8a825e 100644 --- a/arch/mips/kernel/csrc-bcm1480.c +++ b/arch/mips/kernel/csrc-bcm1480.c @@ -28,7 +28,7 @@ #include -static cycle_t bcm1480_hpt_read(void) +static cycle_t bcm1480_hpt_read(struct clocksource *cs) { return (cycle_t) __raw_readq(IOADDR(A_SCD_ZBBUS_CYCLE_COUNT)); } diff --git a/arch/mips/kernel/csrc-ioasic.c b/arch/mips/kernel/csrc-ioasic.c index 1d5f63cf8997..b551f48d3a07 100644 --- a/arch/mips/kernel/csrc-ioasic.c +++ b/arch/mips/kernel/csrc-ioasic.c @@ -25,7 +25,7 @@ #include #include -static cycle_t dec_ioasic_hpt_read(void) +static cycle_t dec_ioasic_hpt_read(struct clocksource *cs) { return ioasic_read(IO_REG_FCTR); } @@ -47,13 +47,13 @@ void __init dec_ioasic_clocksource_init(void) while (!ds1287_timer_state()) ; - start = dec_ioasic_hpt_read(); + start = dec_ioasic_hpt_read(&clocksource_dec); while (i--) while (!ds1287_timer_state()) ; - end = dec_ioasic_hpt_read(); + end = dec_ioasic_hpt_read(&clocksource_dec); freq = (end - start) * 10; printk(KERN_INFO "I/O ASIC clock frequency %dHz\n", freq); diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c index f1a2893931ed..e95a3cd48eea 100644 --- a/arch/mips/kernel/csrc-r4k.c +++ b/arch/mips/kernel/csrc-r4k.c @@ -10,7 +10,7 @@ #include -static cycle_t c0_hpt_read(void) +static cycle_t c0_hpt_read(struct clocksource *cs) { return read_c0_count(); } diff --git a/arch/mips/kernel/csrc-sb1250.c b/arch/mips/kernel/csrc-sb1250.c index 92212bbb8e45..d14d3d1907fa 100644 --- a/arch/mips/kernel/csrc-sb1250.c +++ b/arch/mips/kernel/csrc-sb1250.c @@ -33,7 +33,7 @@ * The HPT is free running from SB1250_HPT_VALUE down to 0 then starts over * again. */ -static cycle_t sb1250_hpt_read(void) +static cycle_t sb1250_hpt_read(struct clocksource *cs) { unsigned int count; diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c index 689719e34f08..ed20e7fe65e3 100644 --- a/arch/mips/kernel/i8253.c +++ b/arch/mips/kernel/i8253.c @@ -128,7 +128,7 @@ void __init setup_pit_timer(void) * to just read by itself. So use jiffies to emulate a free * running counter: */ -static cycle_t pit_read(void) +static cycle_t pit_read(struct clocksource *cs) { unsigned long flags; int count; diff --git a/arch/mips/nxp/pnx8550/common/time.c b/arch/mips/nxp/pnx8550/common/time.c index cf293b279098..8df43e9e4d90 100644 --- a/arch/mips/nxp/pnx8550/common/time.c +++ b/arch/mips/nxp/pnx8550/common/time.c @@ -35,7 +35,7 @@ static unsigned long cpj; -static cycle_t hpt_read(void) +static cycle_t hpt_read(struct clocksource *cs) { return read_c0_count2(); } diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c index f024057a35f8..f10a7cd64f7e 100644 --- a/arch/mips/sgi-ip27/ip27-timer.c +++ b/arch/mips/sgi-ip27/ip27-timer.c @@ -159,7 +159,7 @@ static void __init hub_rt_clock_event_global_init(void) setup_irq(irq, &hub_rt_irqaction); } -static cycle_t hub_rt_read(void) +static cycle_t hub_rt_read(struct clocksource *cs) { return REMOTE_HUB_L(cputonasid(0), PI_RT_COUNT); } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 926ea864e34f..48571ac56fb7 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -77,7 +77,7 @@ #include #include -static cycle_t rtc_read(void); +static cycle_t rtc_read(struct clocksource *); static struct clocksource clocksource_rtc = { .name = "rtc", .rating = 400, @@ -88,7 +88,7 @@ static struct clocksource clocksource_rtc = { .read = rtc_read, }; -static cycle_t timebase_read(void); +static cycle_t timebase_read(struct clocksource *); static struct clocksource clocksource_timebase = { .name = "timebase", .rating = 400, @@ -766,12 +766,12 @@ unsigned long read_persistent_clock(void) } /* clocksource code */ -static cycle_t rtc_read(void) +static cycle_t rtc_read(struct clocksource *cs) { return (cycle_t)get_rtc(); } -static cycle_t timebase_read(void) +static cycle_t timebase_read(struct clocksource *cs) { return (cycle_t)get_tb(); } diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 6ded50dfa75a..ef596d020573 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -201,7 +201,7 @@ unsigned long read_persistent_clock(void) return ts.tv_sec; } -static cycle_t read_tod_clock(void) +static cycle_t read_tod_clock(struct clocksource *cs) { return get_clock(); } diff --git a/arch/sh/kernel/time_32.c b/arch/sh/kernel/time_32.c index c34e1e0f9b02..1700d2465f6c 100644 --- a/arch/sh/kernel/time_32.c +++ b/arch/sh/kernel/time_32.c @@ -208,7 +208,7 @@ unsigned long long sched_clock(void) if (!clocksource_sh.rating) return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ); - cycles = clocksource_sh.read(); + cycles = clocksource_sh.read(&clocksource_sh); return cyc2ns(&clocksource_sh, cycles); } #endif diff --git a/arch/sh/kernel/timers/timer-tmu.c b/arch/sh/kernel/timers/timer-tmu.c index c5d3396f5960..fe8d8930ccb6 100644 --- a/arch/sh/kernel/timers/timer-tmu.c +++ b/arch/sh/kernel/timers/timer-tmu.c @@ -81,7 +81,7 @@ static int tmu_timer_stop(void) */ static int tmus_are_scaled; -static cycle_t tmu_timer_read(void) +static cycle_t tmu_timer_read(struct clocksource *cs) { return ((cycle_t)(~_tmu_read(TMU1)))<get_tick(); +} + void __init time_init(void) { unsigned long freq = sparc64_init_timers(); @@ -827,7 +832,7 @@ void __init time_init(void) clocksource_tick.mult = clocksource_hz2mult(freq, clocksource_tick.shift); - clocksource_tick.read = tick_ops->get_tick; + clocksource_tick.read = clocksource_tick_read; printk("clocksource: mult[%x] shift[%d]\n", clocksource_tick.mult, clocksource_tick.shift); diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index b13a87a3ec95..c8b9c469fcd7 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -65,7 +65,7 @@ static irqreturn_t um_timer(int irq, void *dev) return IRQ_HANDLED; } -static cycle_t itimer_read(void) +static cycle_t itimer_read(struct clocksource *cs) { return os_nsecs() / 1000; } diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 648b3a2a3a44..3f0019e0a229 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -722,7 +722,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n, /* * Clock source related code */ -static cycle_t read_hpet(void) +static cycle_t read_hpet(struct clocksource *cs) { return (cycle_t)hpet_readl(HPET_COUNTER); } @@ -756,7 +756,7 @@ static int hpet_clocksource_register(void) hpet_restart_counter(); /* Verify whether hpet counter works */ - t1 = read_hpet(); + t1 = hpet_readl(HPET_COUNTER); rdtscll(start); /* @@ -770,7 +770,7 @@ static int hpet_clocksource_register(void) rdtscll(now); } while ((now - start) < 200000UL); - if (t1 == read_hpet()) { + if (t1 == hpet_readl(HPET_COUNTER)) { printk(KERN_WARNING "HPET counter not counting. HPET disabled\n"); return -ENODEV; diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 3475440baa54..c2e0bb0890d4 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -129,7 +129,7 @@ void __init setup_pit_timer(void) * to just read by itself. So use jiffies to emulate a free * running counter: */ -static cycle_t pit_read(void) +static cycle_t pit_read(struct clocksource *cs) { static int old_count; static u32 old_jifs; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 137f2e8132df..223af43f1526 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -77,6 +77,11 @@ static cycle_t kvm_clock_read(void) return ret; } +static cycle_t kvm_clock_get_cycles(struct clocksource *cs) +{ + return kvm_clock_read(); +} + /* * If we don't do that, there is the possibility that the guest * will calibrate under heavy load - thus, getting a lower lpj - @@ -107,7 +112,7 @@ static void kvm_get_preset_lpj(void) static struct clocksource kvm_clock = { .name = "kvm-clock", - .read = kvm_clock_read, + .read = kvm_clock_get_cycles, .rating = 400, .mask = CLOCKSOURCE_MASK(64), .mult = 1 << KVM_SCALE, diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 7a567ebe6361..d57de05dc430 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -699,7 +699,7 @@ static struct clocksource clocksource_tsc; * code, which is necessary to support wrapping clocksources like pm * timer. */ -static cycle_t read_tsc(void) +static cycle_t read_tsc(struct clocksource *cs) { cycle_t ret = (cycle_t)get_cycles(); diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index d303369a7bad..2b3eb82efeeb 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -283,7 +283,7 @@ void __devinit vmi_time_ap_init(void) /** vmi clocksource */ static struct clocksource clocksource_vmi; -static cycle_t read_real_cycles(void) +static cycle_t read_real_cycles(struct clocksource *cs) { cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL); return max(ret, clocksource_vmi.cycle_last); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index a2085368a3dc..ca7ec44bafc3 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -663,7 +663,7 @@ static unsigned long lguest_tsc_khz(void) /* If we can't use the TSC, the kernel falls back to our lower-priority * "lguest_clock", where we read the time value given to us by the Host. */ -static cycle_t lguest_clock_read(void) +static cycle_t lguest_clock_read(struct clocksource *cs) { unsigned long sec, nsec; diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 14f240623497..0a5aa44299a5 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -213,6 +213,11 @@ cycle_t xen_clocksource_read(void) return ret; } +static cycle_t xen_clocksource_get_cycles(struct clocksource *cs) +{ + return xen_clocksource_read(); +} + static void xen_read_wallclock(struct timespec *ts) { struct shared_info *s = HYPERVISOR_shared_info; @@ -241,7 +246,7 @@ int xen_set_wallclock(unsigned long now) static struct clocksource xen_clocksource __read_mostly = { .name = "xen", .rating = 400, - .read = xen_clocksource_read, + .read = xen_clocksource_get_cycles, .mask = ~0, .mult = 1< value1) diff --git a/drivers/clocksource/cyclone.c b/drivers/clocksource/cyclone.c index 8615059a8729..64e528e8bfa6 100644 --- a/drivers/clocksource/cyclone.c +++ b/drivers/clocksource/cyclone.c @@ -19,7 +19,7 @@ int use_cyclone = 0; static void __iomem *cyclone_ptr; -static cycle_t read_cyclone(void) +static cycle_t read_cyclone(struct clocksource *cs) { return (cycle_t)readl(cyclone_ptr); } diff --git a/drivers/clocksource/scx200_hrt.c b/drivers/clocksource/scx200_hrt.c index b92da677aa5d..27f4d9637b62 100644 --- a/drivers/clocksource/scx200_hrt.c +++ b/drivers/clocksource/scx200_hrt.c @@ -43,7 +43,7 @@ MODULE_PARM_DESC(ppm, "+-adjust to actual XO freq (ppm)"); /* The base timer frequency, * 27 if selected */ #define HRT_FREQ 1000000 -static cycle_t read_hrt(void) +static cycle_t read_hrt(struct clocksource *cs) { /* Read the timer value */ return (cycle_t) inl(scx200_cb_base + SCx200_TIMER_OFFSET); diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c index 254f1064d973..01b886e68822 100644 --- a/drivers/clocksource/tcb_clksrc.c +++ b/drivers/clocksource/tcb_clksrc.c @@ -39,7 +39,7 @@ static void __iomem *tcaddr; -static cycle_t tc_get_cycles(void) +static cycle_t tc_get_cycles(struct clocksource *cs) { unsigned long flags; u32 lower, upper; diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 573819ef4cc0..0d96cde9ee5d 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -143,7 +143,7 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, * 400-499: Perfect * The ideal clocksource. A must-use where * available. - * @read: returns a cycle value + * @read: returns a cycle value, passes clocksource as argument * @mask: bitmask for two's complement * subtraction of non 64 bit counters * @mult: cycle to nanosecond multiplier (adjusted by NTP) @@ -162,7 +162,7 @@ struct clocksource { char *name; struct list_head list; int rating; - cycle_t (*read)(void); + cycle_t (*read)(struct clocksource *cs); cycle_t mask; u32 mult; u32 mult_orig; @@ -271,7 +271,7 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant) */ static inline cycle_t clocksource_read(struct clocksource *cs) { - return cs->read(); + return cs->read(cs); } /** diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index c46c931a7fe7..ecfd7b5187e0 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -181,12 +181,12 @@ static void clocksource_watchdog(unsigned long data) resumed = test_and_clear_bit(0, &watchdog_resumed); - wdnow = watchdog->read(); + wdnow = watchdog->read(watchdog); wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask); watchdog_last = wdnow; list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { - csnow = cs->read(); + csnow = cs->read(cs); if (unlikely(resumed)) { cs->wd_last = csnow; @@ -247,7 +247,7 @@ static void clocksource_check_watchdog(struct clocksource *cs) list_add(&cs->wd_list, &watchdog_list); if (!started && watchdog) { - watchdog_last = watchdog->read(); + watchdog_last = watchdog->read(watchdog); watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask)); @@ -268,7 +268,7 @@ static void clocksource_check_watchdog(struct clocksource *cs) cse->flags &= ~CLOCK_SOURCE_WATCHDOG; /* Start if list is not empty */ if (!list_empty(&watchdog_list)) { - watchdog_last = watchdog->read(); + watchdog_last = watchdog->read(watchdog); watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 06f197560f3b..c3f6c30816e3 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -50,7 +50,7 @@ */ #define JIFFIES_SHIFT 8 -static cycle_t jiffies_read(void) +static cycle_t jiffies_read(struct clocksource *cs) { return (cycle_t) jiffies; } -- cgit From 4614e6adafa2c5e6c3a9c245af2807fa7bc5117a Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Tue, 21 Apr 2009 12:24:02 -0700 Subject: clocksource: add enable() and disable() callbacks Add enable() and disable() callbacks for clocksources. This allows us to put unused clocksources in power save mode. The functions clocksource_enable() and clocksource_disable() wrap the callbacks and are inserted in the timekeeping code to enable before use and disable after switching to a new clocksource. Signed-off-by: Magnus Damm Acked-by: John Stultz Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/clocksource.h | 31 +++++++++++++++++++++++++++++++ kernel/time/timekeeping.c | 12 +++++++++--- 2 files changed, 40 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 0d96cde9ee5d..5a40d14daa9f 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -144,6 +144,8 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, * The ideal clocksource. A must-use where * available. * @read: returns a cycle value, passes clocksource as argument + * @enable: optional function to enable the clocksource + * @disable: optional function to disable the clocksource * @mask: bitmask for two's complement * subtraction of non 64 bit counters * @mult: cycle to nanosecond multiplier (adjusted by NTP) @@ -163,6 +165,8 @@ struct clocksource { struct list_head list; int rating; cycle_t (*read)(struct clocksource *cs); + int (*enable)(struct clocksource *cs); + void (*disable)(struct clocksource *cs); cycle_t mask; u32 mult; u32 mult_orig; @@ -274,6 +278,33 @@ static inline cycle_t clocksource_read(struct clocksource *cs) return cs->read(cs); } +/** + * clocksource_enable: - enable clocksource + * @cs: pointer to clocksource + * + * Enables the specified clocksource. The clocksource callback + * function should start up the hardware and setup mult and field + * members of struct clocksource to reflect hardware capabilities. + */ +static inline int clocksource_enable(struct clocksource *cs) +{ + return cs->enable ? cs->enable(cs) : 0; +} + +/** + * clocksource_disable: - disable clocksource + * @cs: pointer to clocksource + * + * Disables the specified clocksource. The clocksource callback + * function should power down the now unused hardware block to + * save power. + */ +static inline void clocksource_disable(struct clocksource *cs) +{ + if (cs->disable) + cs->disable(cs); +} + /** * cyc2ns - converts clocksource cycles to nanoseconds * @cs: Pointer to clocksource diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 900f1b6598d1..687dff49f6e7 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -182,7 +182,7 @@ EXPORT_SYMBOL(do_settimeofday); */ static void change_clocksource(void) { - struct clocksource *new; + struct clocksource *new, *old; new = clocksource_get_next(); @@ -191,11 +191,16 @@ static void change_clocksource(void) clocksource_forward_now(); - new->raw_time = clock->raw_time; + if (clocksource_enable(new)) + return; + new->raw_time = clock->raw_time; + old = clock; clock = new; + clocksource_disable(old); + clock->cycle_last = 0; - clock->cycle_last = clocksource_read(new); + clock->cycle_last = clocksource_read(clock); clock->error = 0; clock->xtime_nsec = 0; clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH); @@ -292,6 +297,7 @@ void __init timekeeping_init(void) ntp_init(); clock = clocksource_get_next(); + clocksource_enable(clock); clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH); clock->cycle_last = clocksource_read(clock); -- cgit From b48ccb095a0c9257241261ec2bd1cbb1bdabc48b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Apr 2009 09:36:52 +0200 Subject: locking: clarify kernel-taint warning message Andi Kleen reported this message triggering on non-lockdep kernels: Disabling lockdep due to kernel taint Clarify the message to say 'lock debugging' - debug_locks_off() turns off all things lock debugging, not just lockdep. [ Impact: change kernel warning message text ] Reported-by: Andi Kleen Cc: Peter Zijlstra Cc: Andrew Morton Signed-off-by: Ingo Molnar --- kernel/panic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index 934fb377f4b3..3dcaa1661357 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -221,7 +221,7 @@ void add_taint(unsigned flag) * post-warning case. */ if (flag != TAINT_CRAP && flag != TAINT_WARN && __debug_locks_off()) - printk(KERN_WARNING "Disabling lockdep due to kernel taint\n"); + printk(KERN_WARNING "Disabling lock debugging due to kernel taint\n"); set_bit(flag, &tainted_mask); } -- cgit From 418df63c2d94f238ac7e1d1d53be35dd6b7a7252 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Wed, 22 Apr 2009 12:01:49 +0100 Subject: Delete slow-work timers properly Slow-work appears to delete its timer as soon as the first user unregisters, even though other users could be active. At the same time, it never seems to delete slow_work_oom_timer. Arrange for both to happen in the shutdown path. Signed-off-by: Jonathan Corbet Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/slow-work.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/slow-work.c b/kernel/slow-work.c index cf2bc01186ef..b28d19135f43 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -609,14 +609,14 @@ void slow_work_unregister_user(void) if (slow_work_user_count == 0) { printk(KERN_NOTICE "Slow work thread pool: Shutting down\n"); slow_work_threads_should_exit = true; + del_timer_sync(&slow_work_cull_timer); + del_timer_sync(&slow_work_oom_timer); wake_up_all(&slow_work_thread_wq); wait_for_completion(&slow_work_last_thread_exited); printk(KERN_NOTICE "Slow work thread pool:" " Shut down complete\n"); } - del_timer_sync(&slow_work_cull_timer); - mutex_unlock(&slow_work_user_lock); } EXPORT_SYMBOL(slow_work_unregister_user); -- cgit From 0c8454f56623505a99463405fd7d5664adfbb094 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 25 Apr 2009 00:16:06 +0200 Subject: PM/Hibernate: Fix waiting for image device to appear on resume Commit c751085943362143f84346d274e0011419c84202 ("PM/Hibernate: Wait for SCSI devices scan to complete during resume") added a call to scsi_complete_async_scans() to software_resume(), so that it waited for the SCSI scanning to complete, but the call was added at a wrong place. Namely, it should have been added after wait_for_device_probe(), which is called only if the image partition hasn't been specified yet. Also, it's reasonable to check if the image partition is present and only wait for the device probing and SCSI scanning to complete if it is not the case. Additionally, since noresume is checked right at the beginning of software_resume() and the function returns immediately if it's set, it doesn't make sense to check it once again later. Signed-off-by: Rafael J. Wysocki Signed-off-by: Linus Torvalds --- kernel/power/disk.c | 51 +++++++++++++++++++++++++++------------------------ 1 file changed, 27 insertions(+), 24 deletions(-) (limited to 'kernel') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 0854770b63b9..e71ca9cd81b2 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -645,13 +645,6 @@ static int software_resume(void) if (noresume) return 0; - /* - * We can't depend on SCSI devices being available after loading one of - * their modules if scsi_complete_async_scans() is not called and the - * resume device usually is a SCSI one. - */ - scsi_complete_async_scans(); - /* * name_to_dev_t() below takes a sysfs buffer mutex when sysfs * is configured into the kernel. Since the regular hibernate @@ -663,32 +656,42 @@ static int software_resume(void) * here to avoid lockdep complaining. */ mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING); + + if (swsusp_resume_device) + goto Check_image; + + if (!strlen(resume_file)) { + error = -ENOENT; + goto Unlock; + } + + pr_debug("PM: Checking image partition %s\n", resume_file); + + /* Check if the device is there */ + swsusp_resume_device = name_to_dev_t(resume_file); if (!swsusp_resume_device) { - if (!strlen(resume_file)) { - mutex_unlock(&pm_mutex); - return -ENOENT; - } /* * Some device discovery might still be in progress; we need * to wait for this to finish. */ wait_for_device_probe(); + /* + * We can't depend on SCSI devices being available after loading + * one of their modules until scsi_complete_async_scans() is + * called and the resume device usually is a SCSI one. + */ + scsi_complete_async_scans(); + swsusp_resume_device = name_to_dev_t(resume_file); - pr_debug("PM: Resume from partition %s\n", resume_file); - } else { - pr_debug("PM: Resume from partition %d:%d\n", - MAJOR(swsusp_resume_device), - MINOR(swsusp_resume_device)); + if (!swsusp_resume_device) { + error = -ENODEV; + goto Unlock; + } } - if (noresume) { - /** - * FIXME: If noresume is specified, we need to find the - * partition and reset it back to normal swap space. - */ - mutex_unlock(&pm_mutex); - return 0; - } + Check_image: + pr_debug("PM: Resume from partition %d:%d\n", + MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); pr_debug("PM: Checking hibernation image.\n"); error = swsusp_check(); -- cgit From cad81bc2529ab8c62b6fdc83a1c0c7f4a87209eb Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 27 Apr 2009 01:41:34 +0200 Subject: ptrace: ptrace_attach: fix the usage of ->cred_exec_mutex ptrace_attach() needs task->cred_exec_mutex, not current->cred_exec_mutex. Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Acked-by: David Howells Signed-off-by: James Morris --- kernel/ptrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index dfcd83ceee3b..0692ab5a0d67 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -188,7 +188,7 @@ int ptrace_attach(struct task_struct *task) /* Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently under ptrace. */ - retval = mutex_lock_interruptible(¤t->cred_exec_mutex); + retval = mutex_lock_interruptible(&task->cred_exec_mutex); if (retval < 0) goto out; @@ -232,7 +232,7 @@ repeat: bad: write_unlock_irqrestore(&tasklist_lock, flags); task_unlock(task); - mutex_unlock(¤t->cred_exec_mutex); + mutex_unlock(&task->cred_exec_mutex); out: return retval; } -- cgit From 7267fa6819467669f5cc2ba81a615dcc88158b4b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 29 Apr 2009 00:16:21 -0400 Subject: tracing: fix ref count in splice pages The pages allocated for the splice binary buffer did not initialize the ref count correctly. This caused pages not to be freed and causes a drastic memory leak. Thanks to logdev I was able to trace the tracer to find where the leak was. [ Impact: stop memory leak when using splice ] Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/trace/trace.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1ce5dc6372b8..a884c09006c4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3448,6 +3448,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, if (!ref) break; + ref->ref = 1; ref->buffer = info->tr->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer); if (!ref->page) { -- cgit From f5f293a4e3d0a0c52cec31de6762c95050156516 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 29 Apr 2009 14:44:49 +0200 Subject: sched: account system time properly Andrew Gallatin reported that IRQ and SOFTIRQ times were sometime not reported correctly on recent kernels, and even bisected to commit 457533a7d3402d1d91fbc125c8bd1bd16dcd3cd4 ([PATCH] fix scaled & unscaled cputime accounting) as the first bad commit. Further analysis pointed that commit 79741dd35713ff4f6fd0eafd59fa94e8a4ba922d ([PATCH] idle cputime accounting) was the real cause of the problem. account_process_tick() was not taking into account timer IRQ interrupting the idle task servicing a hard or soft irq. On mostly idle cpu, irqs were thus not accounted and top or mpstat could tell user/admin that cpu was 100 % idle, 0.00 % irq, 0.00 % softirq, while it was not. [ Impact: fix occasionally incorrect CPU statistics in top/mpstat ] Reported-by: Andrew Gallatin Re-reported-by: Andrew Morton Signed-off-by: Eric Dumazet Acked-by: Martin Schwidefsky Cc: rick.jones2@hp.com Cc: brice@myri.com Cc: Paul Mackerras Cc: Benjamin Herrenschmidt LKML-Reference: <49F84BC1.7080602@cosmosbay.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index b902e587a3a0..26efa475bdc1 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4732,7 +4732,7 @@ void account_process_tick(struct task_struct *p, int user_tick) if (user_tick) account_user_time(p, one_jiffy, one_jiffy_scaled); - else if (p != rq->idle) + else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) account_system_time(p, HARDIRQ_OFFSET, one_jiffy, one_jiffy_scaled); else -- cgit From 6e85c5ba73c07b990798087e9b858c065db2b234 Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Wed, 29 Apr 2009 19:14:32 -0400 Subject: kernel/posix-cpu-timers.c: fix sparse warning Sparse reports the following in kernel/posix-cpu-timers.c: warning: symbol 'firing' shadows an earlier one Signed-off-by: H Hartley Sweeten Cc: Subrata Modak LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/posix-cpu-timers.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index c9dcf98b4463..bece7c0b67b2 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1420,19 +1420,19 @@ void run_posix_cpu_timers(struct task_struct *tsk) * timer call will interfere. */ list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) { - int firing; + int cpu_firing; + spin_lock(&timer->it_lock); list_del_init(&timer->it.cpu.entry); - firing = timer->it.cpu.firing; + cpu_firing = timer->it.cpu.firing; timer->it.cpu.firing = 0; /* * The firing flag is -1 if we collided with a reset * of the timer, which already reported this * almost-firing as an overrun. So don't generate an event. */ - if (likely(firing >= 0)) { + if (likely(cpu_firing >= 0)) cpu_timer_fire(timer); - } spin_unlock(&timer->it_lock); } } -- cgit From d7226fb6ec5d4f325e4e7fd905894e2ea3eb3ae0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 1 May 2009 15:16:04 +0200 Subject: Revert "genirq: assert that irq handlers are indeed running in hardirq context" This reverts commit 044d408409cc4e1bc75c886e27ca85c270db104c. The commit added a warning when handle_IRQ_event() is called outside of hard interrupt context. This breaks the generic tasklet based interrupt resend mechanism which is used when the hardware has no way to retrigger the interrupt. So we get a warning for a use case which is correct and worked for years. Remove it. Signed-off-by: Thomas Gleixner --- kernel/irq/handle.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index d82142be8dd2..26e08754744f 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -363,8 +363,6 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) irqreturn_t ret, retval = IRQ_NONE; unsigned int status = 0; - WARN_ONCE(!in_irq(), "BUG: IRQ handler called from non-hardirq context!"); - if (!(action->flags & IRQF_DISABLED)) local_irq_enable_in_hardirq(); -- cgit From 74a03b69d1b5ce00a568e142ca97e76b7f5239c6 Mon Sep 17 00:00:00 2001 From: john stultz Date: Fri, 1 May 2009 13:10:25 -0700 Subject: clockevents: prevent endless loop in tick_handle_periodic() tick_handle_periodic() can lock up hard when a one shot clock event device is used in combination with jiffies clocksource. Avoid an endless loop issue by requiring that a highres valid clocksource be installed before we call tick_periodic() in a loop when using ONESHOT mode. The result is we will only increment jiffies once per interrupt until a continuous hardware clocksource is available. Without this, we can run into a endless loop, where each cycle through the loop, jiffies is updated which increments time by tick_period or more (due to clock steering), which can cause the event programming to think the next event was before the newly incremented time and fail causing tick_periodic() to be called again and the whole process loops forever. [ Impact: prevent hard lock up ] Signed-off-by: John Stultz Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner Cc: stable@kernel.org --- kernel/time/tick-common.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 21a5ca849514..83c4417b6a3c 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -93,7 +93,17 @@ void tick_handle_periodic(struct clock_event_device *dev) for (;;) { if (!clockevents_program_event(dev, next, ktime_get())) return; - tick_periodic(cpu); + /* + * Have to be careful here. If we're in oneshot mode, + * before we call tick_periodic() in a loop, we need + * to be sure we're using a real hardware clocksource. + * Otherwise we could get trapped in an infinite + * loop, as the tick_periodic() increments jiffies, + * when then will increment time, posibly causing + * the loop to trigger again and again. + */ + if (timekeeping_valid_for_hres()) + tick_periodic(cpu); next = ktime_add(next, tick_period); } } -- cgit From 9e4a5bda89034502fb144331e71a0efdfd5fae97 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Thu, 30 Apr 2009 15:08:57 -0700 Subject: mm: prevent divide error for small values of vm_dirty_bytes Avoid setting less than two pages for vm_dirty_bytes: this is necessary to avoid potential division by 0 (like the following) in get_dirty_limits(). [ 49.951610] divide error: 0000 [#1] PREEMPT SMP [ 49.952195] last sysfs file: /sys/devices/pci0000:00/0000:00:01.1/host0/target0:0:0/0:0:0:0/block/sda/uevent [ 49.952195] CPU 1 [ 49.952195] Modules linked in: pcspkr [ 49.952195] Pid: 3064, comm: dd Not tainted 2.6.30-rc3 #1 [ 49.952195] RIP: 0010:[] [] get_dirty_limits+0xe9/0x2c0 [ 49.952195] RSP: 0018:ffff88001de03a98 EFLAGS: 00010202 [ 49.952195] RAX: 00000000000000c0 RBX: ffff88001de03b80 RCX: 28f5c28f5c28f5c3 [ 49.952195] RDX: 0000000000000000 RSI: 00000000000000c0 RDI: 0000000000000000 [ 49.952195] RBP: ffff88001de03ae8 R08: 0000000000000000 R09: 0000000000000000 [ 49.952195] R10: ffff88001ddda9a0 R11: 0000000000000001 R12: 0000000000000001 [ 49.952195] R13: ffff88001fbc8218 R14: ffff88001de03b70 R15: ffff88001de03b78 [ 49.952195] FS: 00007fe9a435b6f0(0000) GS:ffff8800025d9000(0000) knlGS:0000000000000000 [ 49.952195] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 49.952195] CR2: 00007fe9a39ab000 CR3: 000000001de38000 CR4: 00000000000006e0 [ 49.952195] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 49.952195] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 49.952195] Process dd (pid: 3064, threadinfo ffff88001de02000, task ffff88001ddda250) [ 49.952195] Stack: [ 49.952195] ffff88001fa0de00 ffff88001f2dbd70 ffff88001f9fe800 000080b900000000 [ 49.952195] 00000000000000c0 ffff8800027a6100 0000000000000400 ffff88001fbc8218 [ 49.952195] 0000000000000000 0000000000000600 ffff88001de03bb8 ffffffff802d3ed7 [ 49.952195] Call Trace: [ 49.952195] [] balance_dirty_pages_ratelimited_nr+0x1d7/0x3f0 [ 49.952195] [] ? ext3_writeback_write_end+0x9e/0x120 [ 49.952195] [] generic_file_buffered_write+0x12f/0x330 [ 49.952195] [] __generic_file_aio_write_nolock+0x26d/0x460 [ 49.952195] [] ? generic_file_aio_write+0x52/0xd0 [ 49.952195] [] generic_file_aio_write+0x69/0xd0 [ 49.952195] [] ext3_file_write+0x26/0xc0 [ 49.952195] [] do_sync_write+0xf1/0x140 [ 49.952195] [] ? get_lock_stats+0x2a/0x60 [ 49.952195] [] ? autoremove_wake_function+0x0/0x40 [ 49.952195] [] vfs_write+0xcb/0x190 [ 49.952195] [] sys_write+0x50/0x90 [ 49.952195] [] system_call_fastpath+0x16/0x1b [ 49.952195] Code: 00 00 00 2b 05 09 1c 17 01 48 89 c6 49 0f af f4 48 c1 ee 02 48 89 f0 48 f7 e1 48 89 d6 31 d2 48 c1 ee 02 48 0f af 75 d0 48 89 f0 <48> f7 f7 41 8b 95 ac 01 00 00 48 89 c7 49 0f af d4 48 c1 ea 02 [ 49.952195] RIP [] get_dirty_limits+0xe9/0x2c0 [ 49.952195] RSP [ 50.096523] ---[ end trace 008d7aa02f244d7b ]--- Signed-off-by: Andrea Righi Cc: Peter Zijlstra Cc: David Rientjes Cc: Dave Chinner Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 4 ++++ kernel/sysctl.c | 5 ++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 97c4b3284329..b716d33912d8 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -90,6 +90,10 @@ will itself start writeback. If dirty_bytes is written, dirty_ratio becomes a function of its value (dirty_bytes / the amount of dirtyable system memory). +Note: the minimum value allowed for dirty_bytes is two pages (in bytes); any +value lower than this limit will be ignored and the old configuration will be +retained. + ============================================================== dirty_expire_centisecs diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e3d2c7dd59b9..ea78fa101ad6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -103,6 +103,9 @@ static unsigned long one_ul = 1; static int one_hundred = 100; static int one_thousand = 1000; +/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ +static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; + /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ static int maxolduid = 65535; static int minolduid; @@ -1006,7 +1009,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &dirty_bytes_handler, .strategy = &sysctl_intvec, - .extra1 = &one_ul, + .extra1 = &dirty_bytes_min, }, { .procname = "dirty_writeback_centisecs", -- cgit From 381a80e6df396eaabef2c00f85974a4579ac1c70 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 6 May 2009 16:02:50 -0700 Subject: inotify: use GFP_NOFS in kernel_event() to work around a lockdep false-positive There is what we believe to be a false positive reported by lockdep. inotify_inode_queue_event() => take inotify_mutex => kernel_event() => kmalloc() => SLOB => alloc_pages_node() => page reclaim => slab reclaim => dcache reclaim => inotify_inode_is_dead => take inotify_mutex => deadlock The plan is to fix this via lockdep annotation, but that is proving to be quite involved. The patch flips the allocation over to GFP_NFS to shut the warning up, for the 2.6.30 release. Hopefully we will fix this for real in 2.6.31. I'll queue a patch in -mm to switch it back to GFP_KERNEL so we don't forget. ================================= [ INFO: inconsistent lock state ] 2.6.30-rc2-next-20090417 #203 --------------------------------- inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage. kswapd0/380 [HC0[0]:SC0[0]:HE1:SE1] takes: (&inode->inotify_mutex){+.+.?.}, at: [] inotify_inode_is_dead+0x35/0xb0 {RECLAIM_FS-ON-W} state was registered at: [] mark_held_locks+0x68/0x90 [] lockdep_trace_alloc+0xf5/0x100 [] __kmalloc_node+0x31/0x1e0 [] kernel_event+0xe2/0x190 [] inotify_dev_queue_event+0x126/0x230 [] inotify_inode_queue_event+0xc6/0x110 [] vfs_create+0xcd/0x140 [] do_filp_open+0x88d/0xa20 [] do_sys_open+0x98/0x140 [] sys_open+0x20/0x30 [] system_call_fastpath+0x16/0x1b [] 0xffffffffffffffff irq event stamp: 690455 hardirqs last enabled at (690455): [] _spin_unlock_irqrestore+0x44/0x80 hardirqs last disabled at (690454): [] _spin_lock_irqsave+0x32/0xa0 softirqs last enabled at (690178): [] __do_softirq+0x202/0x220 softirqs last disabled at (690157): [] call_softirq+0x1c/0x50 other info that might help us debug this: 2 locks held by kswapd0/380: #0: (shrinker_rwsem){++++..}, at: [] shrink_slab+0x37/0x180 #1: (&type->s_umount_key#17){++++..}, at: [] shrink_dcache_memory+0x11f/0x1e0 stack backtrace: Pid: 380, comm: kswapd0 Not tainted 2.6.30-rc2-next-20090417 #203 Call Trace: [] print_usage_bug+0x19f/0x200 [] ? save_stack_trace+0x2f/0x50 [] mark_lock+0x4bb/0x6d0 [] ? check_usage_forwards+0x0/0xc0 [] __lock_acquire+0xc62/0x1ae0 [] ? slob_free+0x10c/0x370 [] lock_acquire+0xe1/0x120 [] ? inotify_inode_is_dead+0x35/0xb0 [] mutex_lock_nested+0x63/0x420 [] ? inotify_inode_is_dead+0x35/0xb0 [] ? inotify_inode_is_dead+0x35/0xb0 [] ? sched_clock+0x9/0x10 [] ? lock_release_holdtime+0x35/0x1c0 [] inotify_inode_is_dead+0x35/0xb0 [] dentry_iput+0xbc/0xe0 [] d_kill+0x33/0x60 [] __shrink_dcache_sb+0x2d3/0x350 [] shrink_dcache_memory+0x15a/0x1e0 [] shrink_slab+0x125/0x180 [] kswapd+0x560/0x7a0 [] ? isolate_pages_global+0x0/0x2c0 [] ? autoremove_wake_function+0x0/0x40 [] ? trace_hardirqs_on+0xd/0x10 [] ? kswapd+0x0/0x7a0 [] kthread+0x5b/0xa0 [] child_rip+0xa/0x20 [] ? restore_args+0x0/0x30 [] ? kthread+0x0/0xa0 [] ? child_rip+0x0/0x20 [eparis@redhat.com: fix audit too] Cc: Al Viro Cc: Matt Mackall Cc: Christoph Lameter Signed-off-by: Wu Fengguang Signed-off-by: Eric Paris Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/inotify/inotify_user.c | 2 +- kernel/auditfilter.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index bed766e435b5..1634319e2404 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -220,7 +220,7 @@ static struct inotify_kernel_event * kernel_event(s32 wd, u32 mask, u32 cookie, rem = 0; } - kevent->name = kmalloc(len + rem, GFP_KERNEL); + kevent->name = kmalloc(len + rem, GFP_NOFS); if (unlikely(!kevent->name)) { kmem_cache_free(event_cachep, kevent); return NULL; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index a6fe71fd5d1b..713098ee5a02 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1028,7 +1028,7 @@ static void audit_update_watch(struct audit_parent *parent, if (audit_enabled) { struct audit_buffer *ab; - ab = audit_log_start(NULL, GFP_KERNEL, + ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE); audit_log_format(ab, "auid=%u ses=%u", audit_get_loginuid(current), @@ -1067,7 +1067,7 @@ static void audit_remove_parent_watches(struct audit_parent *parent) e = container_of(r, struct audit_entry, rule); if (audit_enabled) { struct audit_buffer *ab; - ab = audit_log_start(NULL, GFP_KERNEL, + ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE); audit_log_format(ab, "auid=%u ses=%u", audit_get_loginuid(current), -- cgit From 57adc4d2dbf968fdbe516359688094eef4d46581 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 6 May 2009 16:02:53 -0700 Subject: Eliminate thousands of warnings with gcc 3.2 build When building with gcc 3.2 I get thousands of warnings such as include/linux/gfp.h: In function `allocflags_to_migratetype': include/linux/gfp.h:105: warning: null format string due to passing a NULL format string to warn_slowpath() in #define __WARN() warn_slowpath(__FILE__, __LINE__, NULL) Split this case out into a separate call. This also shrinks the kernel slightly: text data bss dec hex filename 4802274 707668 712704 6222646 5ef336 vmlinux text data bss dec hex filename 4799027 703572 712704 6215303 5ed687 vmlinux due to removeing one argument from the commonly-called __WARN(). [akpm@linux-foundation.org: reduce scope of `empty'] Acked-by: Jesper Nilsson Acked-by: Johannes Weiner Acked-by: Arjan van de Ven Signed-off-by: Andi Kleen Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/bug.h | 7 ++++--- kernel/panic.c | 13 ++++++++++--- 2 files changed, 14 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index e727fe0d1451..4b6755984d24 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -58,12 +58,13 @@ struct bug_entry { */ #ifndef __WARN #ifndef __ASSEMBLY__ -extern void warn_slowpath(const char *file, const int line, +extern void warn_slowpath_fmt(const char *file, const int line, const char *fmt, ...) __attribute__((format(printf, 3, 4))); +extern void warn_slowpath_null(const char *file, const int line); #define WANT_WARN_ON_SLOWPATH #endif -#define __WARN() warn_slowpath(__FILE__, __LINE__, NULL) -#define __WARN_printf(arg...) warn_slowpath(__FILE__, __LINE__, arg) +#define __WARN() warn_slowpath_null(__FILE__, __LINE__) +#define __WARN_printf(arg...) warn_slowpath_fmt(__FILE__, __LINE__, arg) #else #define __WARN_printf(arg...) do { printk(arg); __WARN(); } while (0) #endif diff --git a/kernel/panic.c b/kernel/panic.c index 3dcaa1661357..874ecf1307ae 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -340,7 +340,7 @@ void oops_exit(void) } #ifdef WANT_WARN_ON_SLOWPATH -void warn_slowpath(const char *file, int line, const char *fmt, ...) +void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...) { va_list args; char function[KSYM_SYMBOL_LEN]; @@ -356,7 +356,7 @@ void warn_slowpath(const char *file, int line, const char *fmt, ...) if (board) printk(KERN_WARNING "Hardware name: %s\n", board); - if (fmt) { + if (*fmt) { va_start(args, fmt); vprintk(fmt, args); va_end(args); @@ -367,7 +367,14 @@ void warn_slowpath(const char *file, int line, const char *fmt, ...) print_oops_end_marker(); add_taint(TAINT_WARN); } -EXPORT_SYMBOL(warn_slowpath); +EXPORT_SYMBOL(warn_slowpath_fmt); + +void warn_slowpath_null(const char *file, int line) +{ + static const char *empty = ""; + warn_slowpath_fmt(file, line, empty); +} +EXPORT_SYMBOL(warn_slowpath_null); #endif #ifdef CONFIG_CC_STACKPROTECTOR -- cgit From 201517a7f3ec497fff545a7659c6c876f89f9054 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 7 May 2009 16:31:26 -0400 Subject: kprobes: fix to use text_mutex around arm/disarm kprobe Fix kprobes to lock text_mutex around some arch_arm/disarm_kprobe() which are newly added by commit de5bd88d5a5cce3cacea904d3503e5ebdb3852a2. Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Mathieu Desnoyers Cc: Jim Keniston Cc: Ingo Molnar Signed-off-by: Linus Torvalds --- kernel/kprobes.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index a5e74ddee0e2..c0fa54b276d9 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -319,6 +319,22 @@ struct kprobe __kprobes *get_kprobe(void *addr) return NULL; } +/* Arm a kprobe with text_mutex */ +static void __kprobes arm_kprobe(struct kprobe *kp) +{ + mutex_lock(&text_mutex); + arch_arm_kprobe(kp); + mutex_unlock(&text_mutex); +} + +/* Disarm a kprobe with text_mutex */ +static void __kprobes disarm_kprobe(struct kprobe *kp) +{ + mutex_lock(&text_mutex); + arch_disarm_kprobe(kp); + mutex_unlock(&text_mutex); +} + /* * Aggregate handlers for multiple kprobes support - these handlers * take care of invoking the individual kprobe handlers on p->list @@ -538,7 +554,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) ap->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed) /* Arm the breakpoint again. */ - arch_arm_kprobe(ap); + arm_kprobe(ap); } return 0; } @@ -789,11 +805,8 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p) * enabled and not gone - otherwise, the breakpoint would * already have been removed. We save on flushing icache. */ - if (!kprobes_all_disarmed && !kprobe_disabled(old_p)) { - mutex_lock(&text_mutex); - arch_disarm_kprobe(p); - mutex_unlock(&text_mutex); - } + if (!kprobes_all_disarmed && !kprobe_disabled(old_p)) + disarm_kprobe(p); hlist_del_rcu(&old_p->hlist); } else { if (p->break_handler && !kprobe_gone(p)) @@ -810,7 +823,7 @@ noclean: if (!kprobe_disabled(old_p)) { try_to_disable_aggr_kprobe(old_p); if (!kprobes_all_disarmed && kprobe_disabled(old_p)) - arch_disarm_kprobe(old_p); + disarm_kprobe(old_p); } } return 0; @@ -1364,7 +1377,7 @@ int __kprobes disable_kprobe(struct kprobe *kp) try_to_disable_aggr_kprobe(p); if (!kprobes_all_disarmed && kprobe_disabled(p)) - arch_disarm_kprobe(p); + disarm_kprobe(p); out: mutex_unlock(&kprobe_mutex); return ret; @@ -1393,7 +1406,7 @@ int __kprobes enable_kprobe(struct kprobe *kp) } if (!kprobes_all_disarmed && kprobe_disabled(p)) - arch_arm_kprobe(p); + arm_kprobe(p); p->flags &= ~KPROBE_FLAG_DISABLED; if (p != kp) -- cgit From 6f5bbff9a1b7d6864a495763448a363bbfa96324 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 6 May 2009 01:34:22 -0400 Subject: Convert obvious places to deactivate_locked_super() Signed-off-by: Al Viro --- drivers/mtd/mtdsuper.c | 3 +-- fs/9p/vfs_super.c | 5 +---- fs/afs/super.c | 3 +-- fs/btrfs/super.c | 12 ++++-------- fs/cifs/cifsfs.c | 3 +-- fs/devpts/inode.c | 5 ++--- fs/ecryptfs/main.c | 5 ++--- fs/libfs.c | 3 +-- fs/nfs/super.c | 15 +++++---------- fs/proc/root.c | 3 +-- fs/ubifs/super.c | 3 +-- kernel/cgroup.c | 3 +-- 12 files changed, 21 insertions(+), 42 deletions(-) (limited to 'kernel') diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c index 92285d0089c2..af8b42e0a55b 100644 --- a/drivers/mtd/mtdsuper.c +++ b/drivers/mtd/mtdsuper.c @@ -74,8 +74,7 @@ static int get_sb_mtd_aux(struct file_system_type *fs_type, int flags, ret = fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (ret < 0) { - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); return ret; } diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 7d23214e5599..0d29a57c63e6 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -174,10 +174,7 @@ P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n"); return 0; release_sb: - if (sb) { - up_write(&sb->s_umount); - deactivate_super(sb); - } + deactivate_locked_super(sb); free_stat: kfree(st); diff --git a/fs/afs/super.c b/fs/afs/super.c index aee239a048cb..2753f16dd315 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -405,8 +405,7 @@ static int afs_get_sb(struct file_system_type *fs_type, sb->s_flags = flags; ret = afs_fill_super(sb, ¶ms); if (ret < 0) { - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); goto error; } sb->s_options = new_opts; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 3536bdb2d7cb..6dfae5b28f59 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -502,8 +502,7 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, if (s->s_root) { if ((flags ^ s->s_flags) & MS_RDONLY) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); error = -EBUSY; goto error_close_devices; } @@ -517,8 +516,7 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, error = btrfs_fill_super(s, fs_devices, data, flags & MS_SILENT ? 1 : 0); if (error) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); goto error_free_subvol_name; } @@ -535,15 +533,13 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, mutex_unlock(&s->s_root->d_inode->i_mutex); if (IS_ERR(root)) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); error = PTR_ERR(root); goto error_free_subvol_name; } if (!root->d_inode) { dput(root); - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); error = -ENXIO; goto error_free_subvol_name; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 355e0efec0cf..5e6d35804d73 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -602,8 +602,7 @@ cifs_get_sb(struct file_system_type *fs_type, rc = cifs_read_super(sb, data, dev_name, flags & MS_SILENT ? 1 : 0); if (rc) { - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); return rc; } sb->s_flags |= MS_ACTIVE; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 63a4a59e4148..21165cf934ff 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -389,11 +389,10 @@ static int devpts_get_sb(struct file_system_type *fs_type, return 0; out_dput: - dput(s->s_root); + dput(s->s_root); /* undo dget() in simple_set_mnt() */ out_undo_sget: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); return error; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index ccabd5faa04d..9f0aa9883c28 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -614,9 +614,8 @@ static int ecryptfs_get_sb(struct file_system_type *fs_type, int flags, } goto out; out_abort: - dput(sb->s_root); - up_write(&sb->s_umount); - deactivate_super(sb); + dput(sb->s_root); /* aka mnt->mnt_root, as set by get_sb_nodev() */ + deactivate_locked_super(sb); out: return rc; } diff --git a/fs/libfs.c b/fs/libfs.c index cd223190c4e9..80046ddf5063 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -246,8 +246,7 @@ int get_sb_pseudo(struct file_system_type *fs_type, char *name, return 0; Enomem: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); return -ENOMEM; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 1679a164c8c9..d2d67781c579 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2111,8 +2111,7 @@ out_err_nosb: error_splat_root: dput(mntroot); error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); goto out; } @@ -2208,8 +2207,7 @@ out_err_noserver: return error; error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); dprintk("<-- nfs_xdev_get_sb() = %d [splat]\n", error); return error; } @@ -2469,8 +2467,7 @@ out_free: error_splat_root: dput(mntroot); error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); goto out; } @@ -2564,8 +2561,7 @@ out_err_noserver: return error; error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); dprintk("<-- nfs4_xdev_get_sb() = %d [splat]\n", error); return error; } @@ -2649,8 +2645,7 @@ out_err_noserver: return error; error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); dprintk("<-- nfs4_referral_get_sb() = %d [splat]\n", error); return error; } diff --git a/fs/proc/root.c b/fs/proc/root.c index 1e15a2b176e8..b080b791d9e3 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -67,8 +67,7 @@ static int proc_get_sb(struct file_system_type *fs_type, sb->s_flags = flags; err = proc_fill_super(sb); if (err) { - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); return err; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index faa44f90608a..e9f7a754c4f7 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2055,8 +2055,7 @@ static int ubifs_get_sb(struct file_system_type *fs_type, int flags, return 0; out_deact: - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); out_close: ubi_close_volume(ubi); return err; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 382109b5baeb..a7267bfd3765 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1133,8 +1133,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, free_cg_links: free_cg_links(&tmp_cg_links); drop_new_super: - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); return ret; } -- cgit From cd17cbfda004fe5f406c01b318c6378d9895896f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 15 May 2009 11:32:24 +0200 Subject: Revert "mm: add /proc controls for pdflush threads" This reverts commit fafd688e4c0c34da0f3de909881117d374e4c7af. Work is progressing to switch away from pdflush as the process backing for flushing out dirty data. So it seems pointless to add more knobs to control pdflush threads. The original author of the patch did not have any specific use cases for adding the knobs, so we can easily revert this before 2.6.30 to avoid having to maintain this API forever. Signed-off-by: Jens Axboe --- Documentation/sysctl/vm.txt | 28 ---------------------------- include/linux/writeback.h | 2 -- kernel/sysctl.c | 23 ----------------------- mm/pdflush.c | 31 ++++++++++++------------------- 4 files changed, 12 insertions(+), 72 deletions(-) (limited to 'kernel') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index b716d33912d8..c302ddf629a0 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -39,8 +39,6 @@ Currently, these files are in /proc/sys/vm: - nr_hugepages - nr_overcommit_hugepages - nr_pdflush_threads -- nr_pdflush_threads_min -- nr_pdflush_threads_max - nr_trim_pages (only if CONFIG_MMU=n) - numa_zonelist_order - oom_dump_tasks @@ -469,32 +467,6 @@ The default value is 0. ============================================================== -nr_pdflush_threads_min - -This value controls the minimum number of pdflush threads. - -At boot time, the kernel will create and maintain 'nr_pdflush_threads_min' -threads for the kernel's lifetime. - -The default value is 2. The minimum value you can specify is 1, and -the maximum value is the current setting of 'nr_pdflush_threads_max'. - -See 'nr_pdflush_threads_max' below for more information. - -============================================================== - -nr_pdflush_threads_max - -This value controls the maximum number of pdflush threads that can be -created. The pdflush algorithm will create a new pdflush thread (up to -this maximum) if no pdflush threads have been available for >= 1 second. - -The default value is 8. The minimum value you can specify is the -current value of 'nr_pdflush_threads_min' and the -maximum is 1000. - -============================================================== - overcommit_memory: This value contains a flag that enables memory overcommitment. diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9c1ed1fb6ddb..93445477f86a 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -168,8 +168,6 @@ void writeback_set_ratelimit(void); /* pdflush.c */ extern int nr_pdflush_threads; /* Global so it can be exported to sysctl read-only. */ -extern int nr_pdflush_threads_max; /* Global so it can be exported to sysctl */ -extern int nr_pdflush_threads_min; /* Global so it can be exported to sysctl */ #endif /* WRITEBACK_H */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ea78fa101ad6..b2970d56fb76 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -101,7 +101,6 @@ static int __maybe_unused one = 1; static int __maybe_unused two = 2; static unsigned long one_ul = 1; static int one_hundred = 100; -static int one_thousand = 1000; /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; @@ -1033,28 +1032,6 @@ static struct ctl_table vm_table[] = { .mode = 0444 /* read-only*/, .proc_handler = &proc_dointvec, }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "nr_pdflush_threads_min", - .data = &nr_pdflush_threads_min, - .maxlen = sizeof nr_pdflush_threads_min, - .mode = 0644 /* read-write */, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &one, - .extra2 = &nr_pdflush_threads_max, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "nr_pdflush_threads_max", - .data = &nr_pdflush_threads_max, - .maxlen = sizeof nr_pdflush_threads_max, - .mode = 0644 /* read-write */, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &nr_pdflush_threads_min, - .extra2 = &one_thousand, - }, { .ctl_name = VM_SWAPPINESS, .procname = "swappiness", diff --git a/mm/pdflush.c b/mm/pdflush.c index f2caf96993f8..235ac440c44e 100644 --- a/mm/pdflush.c +++ b/mm/pdflush.c @@ -57,14 +57,6 @@ static DEFINE_SPINLOCK(pdflush_lock); */ int nr_pdflush_threads = 0; -/* - * The max/min number of pdflush threads. R/W by sysctl at - * /proc/sys/vm/nr_pdflush_threads_max/min - */ -int nr_pdflush_threads_max __read_mostly = MAX_PDFLUSH_THREADS; -int nr_pdflush_threads_min __read_mostly = MIN_PDFLUSH_THREADS; - - /* * The time at which the pdflush thread pool last went empty */ @@ -76,7 +68,7 @@ static unsigned long last_empty_jifs; * Thread pool management algorithm: * * - The minimum and maximum number of pdflush instances are bound - * by nr_pdflush_threads_min and nr_pdflush_threads_max. + * by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS. * * - If there have been no idle pdflush instances for 1 second, create * a new one. @@ -142,13 +134,14 @@ static int __pdflush(struct pdflush_work *my_work) * To throttle creation, we reset last_empty_jifs. */ if (time_after(jiffies, last_empty_jifs + 1 * HZ)) { - if (list_empty(&pdflush_list) && - nr_pdflush_threads < nr_pdflush_threads_max) { - last_empty_jifs = jiffies; - nr_pdflush_threads++; - spin_unlock_irq(&pdflush_lock); - start_one_pdflush_thread(); - spin_lock_irq(&pdflush_lock); + if (list_empty(&pdflush_list)) { + if (nr_pdflush_threads < MAX_PDFLUSH_THREADS) { + last_empty_jifs = jiffies; + nr_pdflush_threads++; + spin_unlock_irq(&pdflush_lock); + start_one_pdflush_thread(); + spin_lock_irq(&pdflush_lock); + } } } @@ -160,7 +153,7 @@ static int __pdflush(struct pdflush_work *my_work) */ if (list_empty(&pdflush_list)) continue; - if (nr_pdflush_threads <= nr_pdflush_threads_min) + if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS) continue; pdf = list_entry(pdflush_list.prev, struct pdflush_work, list); if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) { @@ -266,9 +259,9 @@ static int __init pdflush_init(void) * Pre-set nr_pdflush_threads... If we fail to create, * the count will be decremented. */ - nr_pdflush_threads = nr_pdflush_threads_min; + nr_pdflush_threads = MIN_PDFLUSH_THREADS; - for (i = 0; i < nr_pdflush_threads_min; i++) + for (i = 0; i < MIN_PDFLUSH_THREADS; i++) start_one_pdflush_thread(); return 0; } -- cgit From 364b5b7b1d793a7f98be55b6b154716dcae78dfc Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Wed, 13 May 2009 21:56:59 -0500 Subject: sysrq, intel_fb: fix sysrq g collision Commit 79e539453b34e35f39299a899d263b0a1f1670bd introduced a regression where you cannot use sysrq 'g' to enter kgdb. The solution is to move the intel fb sysrq over to V for video instead of G for graphics. The SMP VOYAGER code to register for the sysrq-v is not anywhere to be found in the mainline kernel, so the comments in the code were cleaned up as well. This patch also cleans up the sysrq definitions for kgdb to make it generic for the kernel debugger, such that the sysrq 'g' can be used in the future to enter a gdbstub or another kernel debugger. Signed-off-by: Jason Wessel Acked-by: Jesse Barnes Acked-by: Randy Dunlap Signed-off-by: Andrew Morton --- drivers/char/sysrq.c | 4 ++-- drivers/gpu/drm/i915/intel_fb.c | 4 ++-- kernel/kgdb.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c index b0a6a3e51924..d6a807f4077d 100644 --- a/drivers/char/sysrq.c +++ b/drivers/char/sysrq.c @@ -406,7 +406,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = { &sysrq_showlocks_op, /* d */ &sysrq_term_op, /* e */ &sysrq_moom_op, /* f */ - /* g: May be registered by ppc for kgdb */ + /* g: May be registered for the kernel debugger */ NULL, /* g */ NULL, /* h - reserved for help */ &sysrq_kill_op, /* i */ @@ -431,7 +431,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = { &sysrq_sync_op, /* s */ &sysrq_showstate_op, /* t */ &sysrq_mountro_op, /* u */ - /* v: May be registered at init time by SMP VOYAGER */ + /* v: May be registered for frame buffer console restore */ NULL, /* v */ &sysrq_showstate_blocked_op, /* w */ /* x: May be registered on ppc/powerpc for xmon */ diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index 3e094beecb99..e4652dcdd9bb 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -864,7 +864,7 @@ static void intelfb_sysrq(int dummy1, struct tty_struct *dummy3) static struct sysrq_key_op sysrq_intelfb_restore_op = { .handler = intelfb_sysrq, - .help_msg = "force-fb(G)", + .help_msg = "force-fb(V)", .action_msg = "Restore framebuffer console", }; @@ -898,7 +898,7 @@ int intelfb_probe(struct drm_device *dev) ret = intelfb_single_fb_probe(dev); } - register_sysrq_key('g', &sysrq_intelfb_restore_op); + register_sysrq_key('v', &sysrq_intelfb_restore_op); return ret; } diff --git a/kernel/kgdb.c b/kernel/kgdb.c index e4dcfb2272a4..9147a3190c9d 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -1583,8 +1583,8 @@ static void sysrq_handle_gdb(int key, struct tty_struct *tty) static struct sysrq_key_op sysrq_gdb_op = { .handler = sysrq_handle_gdb, - .help_msg = "Gdb", - .action_msg = "GDB", + .help_msg = "debug(G)", + .action_msg = "DEBUG", }; #endif -- cgit From 0f6f49a8cd0163fdb1723ed29f01fc65177108dc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 16 May 2009 13:41:28 -0700 Subject: Fix caller information for warn_slowpath_null Ian Campbell noticed that since "Eliminate thousands of warnings with gcc 3.2 build" (commit 57adc4d2dbf968fdbe516359688094eef4d46581) all WARN_ON()'s currently appear to come from warn_slowpath_null(), eg: WARNING: at kernel/softirq.c:143 warn_slowpath_null+0x1c/0x20() because now that warn_slowpath_null() is in the call path, the __builtin_return_address(0) returns that, rather than the place that caused the warning. Fix this by splitting up the warn_slowpath_null/fmt cases differently, using a common helper function, and getting the return address in the right place. This also happens to avoid the unnecessary stack usage for the non-stdargs case, and just generally cleans things up. Make the function name printout use %pS while at it. Cc: Ian Campbell Cc: Jesper Nilsson Cc: Johannes Weiner Cc: Arjan van de Ven Cc: Andi Kleen Cc: Hugh Dickins Cc: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/panic.c | 35 ++++++++++++++++++++--------------- 1 file changed, 20 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index 874ecf1307ae..984b3ecbd72c 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -340,39 +340,44 @@ void oops_exit(void) } #ifdef WANT_WARN_ON_SLOWPATH -void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...) -{ +struct slowpath_args { + const char *fmt; va_list args; - char function[KSYM_SYMBOL_LEN]; - unsigned long caller = (unsigned long)__builtin_return_address(0); - const char *board; +}; - sprint_symbol(function, caller); +static void warn_slowpath_common(const char *file, int line, void *caller, struct slowpath_args *args) +{ + const char *board; printk(KERN_WARNING "------------[ cut here ]------------\n"); - printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file, - line, function); + printk(KERN_WARNING "WARNING: at %s:%d %pS()\n", file, line, caller); board = dmi_get_system_info(DMI_PRODUCT_NAME); if (board) printk(KERN_WARNING "Hardware name: %s\n", board); - if (*fmt) { - va_start(args, fmt); - vprintk(fmt, args); - va_end(args); - } + if (args) + vprintk(args->fmt, args->args); print_modules(); dump_stack(); print_oops_end_marker(); add_taint(TAINT_WARN); } + +void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...) +{ + struct slowpath_args args; + + args.fmt = fmt; + va_start(args.args, fmt); + warn_slowpath_common(file, line, __builtin_return_address(0), &args); + va_end(args.args); +} EXPORT_SYMBOL(warn_slowpath_fmt); void warn_slowpath_null(const char *file, int line) { - static const char *empty = ""; - warn_slowpath_fmt(file, line, empty); + warn_slowpath_common(file, line, __builtin_return_address(0), NULL); } EXPORT_SYMBOL(warn_slowpath_null); #endif -- cgit