linux-rt-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [ANNOUNCE] 3.0.7-rt20
@ 2011-10-19  9:59 Thomas Gleixner
  2011-10-19 14:17 ` Rolando Martins
  2011-10-25  9:28 ` Yong Zhang
  0 siblings, 2 replies; 3+ messages in thread
From: Thomas Gleixner @ 2011-10-19  9:59 UTC (permalink / raw)
  To: LKML; +Cc: linux-rt-users

Dear RT Folks,

I'm pleased to announce the 3.0.7-rt20 release.

3.0.7-rt19 is an not announced intermediate release, which only
updates to 3.0.7. No rt changes except dropping patches which made it
into 3.0.7.

Changes from 3.0.7-rt19 to 3.0.7-rt20

  * Fix a long standing RT throttling problem with cgroups and
    RT_GROUP_SCHED (Peter Zijlstra, Thanks to Carsten Emde for
    providing the debug information!)

  * Minor fixes (Yong Zhang)

Delta patch against 3.0.7-rt19

  https://tglx.de/~tglx/rt/patch-3.0.7-rt19-rt20.patch.gz

also appended below.


Patch against 3.0.7 can be found here:

  https://tglx.de/~tglx/rt/patch-3.0.7-rt20.patch.gz


The split quilt queue is available at:

  https://tglx.de/~tglx/rt/patches-3.0.7-rt20.tar.gz

Known issues:

  Yong discovered a non critical cpuhotplug problem, which needs some
  more thought. Will try to address that in the next days as traveling
  allows (about to head to Prague for a long RTLWS/KS/LinuxCon/ELCE
  week).

Enjoy,

	tglx

--------------->
Index: linux-2.6/kernel/cpu.c
===================================================================
--- linux-2.6.orig/kernel/cpu.c
+++ linux-2.6/kernel/cpu.c
@@ -139,7 +139,7 @@ static int cpu_unplug_begin(unsigned int
 	struct task_struct *tsk;
 
 	init_completion(&hp->synced);
-	tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d\n", cpu);
+	tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
 	if (IS_ERR(tsk))
 		return (PTR_ERR(tsk));
 	kthread_bind(tsk, cpu);
Index: linux-2.6/kernel/printk.c
===================================================================
--- linux-2.6.orig/kernel/printk.c
+++ linux-2.6/kernel/printk.c
@@ -1282,8 +1282,8 @@ void printk_tick(void)
 
 int printk_needs_cpu(int cpu)
 {
-	if (cpu_is_offline(cpu))
-		printk_tick();
+	if (unlikely(cpu_is_offline(cpu)))
+		__this_cpu_write(printk_pending, 0);
 	return __this_cpu_read(printk_pending);
 }
 
Index: linux-2.6/kernel/sched_rt.c
===================================================================
--- linux-2.6.orig/kernel/sched_rt.c
+++ linux-2.6/kernel/sched_rt.c
@@ -556,12 +556,9 @@ static inline int balance_runtime(struct
 
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 {
-	int i, idle = 1;
+	int i, idle = 1, throttled = 0;
 	const struct cpumask *span;
 
-	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
-		return 1;
-
 	span = sched_rt_period_mask();
 	for_each_cpu(i, span) {
 		int enqueue = 0;
@@ -596,12 +593,17 @@ static int do_sched_rt_period_timer(stru
 			if (!rt_rq_throttled(rt_rq))
 				enqueue = 1;
 		}
+		if (rt_rq->rt_throttled)
+			throttled = 1;
 
 		if (enqueue)
 			sched_rt_rq_enqueue(rt_rq);
 		raw_spin_unlock(&rq->lock);
 	}
 
+	if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))
+		return 1;
+
 	return idle;
 }
 
@@ -633,8 +635,24 @@ static int sched_rt_runtime_exceeded(str
 		return 0;
 
 	if (rt_rq->rt_time > runtime) {
-		rt_rq->rt_throttled = 1;
-		printk_once(KERN_WARNING "sched: RT throttling activated\n");
+		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+		/*
+		 * Don't actually throttle groups that have no runtime assigned
+		 * but accrue some time due to boosting.
+		 */
+		if (likely(rt_b->rt_runtime)) {
+			rt_rq->rt_throttled = 1;
+			printk_once(KERN_WARNING "sched: RT throttling activated\n");
+		} else {
+			/*
+			 * In case we did anyway, make it go away,
+			 * replenishment is a joke, since it will replenish us
+			 * with exactly 0 ns.
+			 */
+			rt_rq->rt_time = 0;
+		}
+
 		if (rt_rq_throttled(rt_rq)) {
 			sched_rt_rq_dequeue(rt_rq);
 			return 1;
@@ -662,7 +680,8 @@ static void update_curr_rt(struct rq *rq
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;
 
-	schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));
+	schedstat_set(curr->se.statistics.exec_max,
+		      max(curr->se.statistics.exec_max, delta_exec));
 
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
Index: linux-2.6/kernel/workqueue.c
===================================================================
--- linux-2.6.orig/kernel/workqueue.c
+++ linux-2.6/kernel/workqueue.c
@@ -3274,14 +3274,14 @@ static void flush_gcwq(struct global_cwq
 
 	spin_unlock_irq(&gcwq->lock);
 
-	gcwq = get_gcwq(get_cpu());
+	gcwq = get_gcwq(get_cpu_light());
 	spin_lock_irq(&gcwq->lock);
 	list_for_each_entry_safe(work, nw, &non_affine_works, entry) {
 		list_del_init(&work->entry);
 		___queue_work(get_work_cwq(work)->wq, gcwq, work);
 	}
 	spin_unlock_irq(&gcwq->lock);
-	put_cpu();
+	put_cpu_light();
 }
 
 static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb,
Index: linux-2.6/localversion-rt
===================================================================
--- linux-2.6.orig/localversion-rt
+++ linux-2.6/localversion-rt
@@ -1 +1 @@
--rt19
+-rt20

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [ANNOUNCE] 3.0.7-rt20
  2011-10-19  9:59 [ANNOUNCE] 3.0.7-rt20 Thomas Gleixner
@ 2011-10-19 14:17 ` Rolando Martins
  2011-10-25  9:28 ` Yong Zhang
  1 sibling, 0 replies; 3+ messages in thread
From: Rolando Martins @ 2011-10-19 14:17 UTC (permalink / raw)
  To: Peter Zijlstra; +Cc: LKML, linux-rt-users, Thomas Gleixner

Hi to all,
this fixed my issues with cgroups and RT_GROUP_SCHED.
A big thanks to the RT maintainers, specially to Peter Zijlstra.
This patch provides the best performance I ever experience while using
RT_GROUP_SCHED!

Thanks,
Rolando

>  * Fix a long standing RT throttling problem with cgroups and
>    RT_GROUP_SCHED (Peter Zijlstra, Thanks to Carsten Emde for
>    providing the debug information!)


On Wed, Oct 19, 2011 at 10:59 AM, Thomas Gleixner <tglx@linutronix.de> wrote:
> Dear RT Folks,
>
> I'm pleased to announce the 3.0.7-rt20 release.
>
> 3.0.7-rt19 is an not announced intermediate release, which only
> updates to 3.0.7. No rt changes except dropping patches which made it
> into 3.0.7.
>
> Changes from 3.0.7-rt19 to 3.0.7-rt20
>
>  * Fix a long standing RT throttling problem with cgroups and
>    RT_GROUP_SCHED (Peter Zijlstra, Thanks to Carsten Emde for
>    providing the debug information!)
>
>  * Minor fixes (Yong Zhang)
>
> Delta patch against 3.0.7-rt19
>
>  https://tglx.de/~tglx/rt/patch-3.0.7-rt19-rt20.patch.gz
>
> also appended below.
>
>
> Patch against 3.0.7 can be found here:
>
>  https://tglx.de/~tglx/rt/patch-3.0.7-rt20.patch.gz
>
>
> The split quilt queue is available at:
>
>  https://tglx.de/~tglx/rt/patches-3.0.7-rt20.tar.gz
>
> Known issues:
>
>  Yong discovered a non critical cpuhotplug problem, which needs some
>  more thought. Will try to address that in the next days as traveling
>  allows (about to head to Prague for a long RTLWS/KS/LinuxCon/ELCE
>  week).
>
> Enjoy,
>
>        tglx
>
> --------------->
> Index: linux-2.6/kernel/cpu.c
> ===================================================================
> --- linux-2.6.orig/kernel/cpu.c
> +++ linux-2.6/kernel/cpu.c
> @@ -139,7 +139,7 @@ static int cpu_unplug_begin(unsigned int
>        struct task_struct *tsk;
>
>        init_completion(&hp->synced);
> -       tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d\n", cpu);
> +       tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
>        if (IS_ERR(tsk))
>                return (PTR_ERR(tsk));
>        kthread_bind(tsk, cpu);
> Index: linux-2.6/kernel/printk.c
> ===================================================================
> --- linux-2.6.orig/kernel/printk.c
> +++ linux-2.6/kernel/printk.c
> @@ -1282,8 +1282,8 @@ void printk_tick(void)
>
>  int printk_needs_cpu(int cpu)
>  {
> -       if (cpu_is_offline(cpu))
> -               printk_tick();
> +       if (unlikely(cpu_is_offline(cpu)))
> +               __this_cpu_write(printk_pending, 0);
>        return __this_cpu_read(printk_pending);
>  }
>
> Index: linux-2.6/kernel/sched_rt.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched_rt.c
> +++ linux-2.6/kernel/sched_rt.c
> @@ -556,12 +556,9 @@ static inline int balance_runtime(struct
>
>  static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
>  {
> -       int i, idle = 1;
> +       int i, idle = 1, throttled = 0;
>        const struct cpumask *span;
>
> -       if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
> -               return 1;
> -
>        span = sched_rt_period_mask();
>        for_each_cpu(i, span) {
>                int enqueue = 0;
> @@ -596,12 +593,17 @@ static int do_sched_rt_period_timer(stru
>                        if (!rt_rq_throttled(rt_rq))
>                                enqueue = 1;
>                }
> +               if (rt_rq->rt_throttled)
> +                       throttled = 1;
>
>                if (enqueue)
>                        sched_rt_rq_enqueue(rt_rq);
>                raw_spin_unlock(&rq->lock);
>        }
>
> +       if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))
> +               return 1;
> +
>        return idle;
>  }
>
> @@ -633,8 +635,24 @@ static int sched_rt_runtime_exceeded(str
>                return 0;
>
>        if (rt_rq->rt_time > runtime) {
> -               rt_rq->rt_throttled = 1;
> -               printk_once(KERN_WARNING "sched: RT throttling activated\n");
> +               struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
> +
> +               /*
> +                * Don't actually throttle groups that have no runtime assigned
> +                * but accrue some time due to boosting.
> +                */
> +               if (likely(rt_b->rt_runtime)) {
> +                       rt_rq->rt_throttled = 1;
> +                       printk_once(KERN_WARNING "sched: RT throttling activated\n");
> +               } else {
> +                       /*
> +                        * In case we did anyway, make it go away,
> +                        * replenishment is a joke, since it will replenish us
> +                        * with exactly 0 ns.
> +                        */
> +                       rt_rq->rt_time = 0;
> +               }
> +
>                if (rt_rq_throttled(rt_rq)) {
>                        sched_rt_rq_dequeue(rt_rq);
>                        return 1;
> @@ -662,7 +680,8 @@ static void update_curr_rt(struct rq *rq
>        if (unlikely((s64)delta_exec < 0))
>                delta_exec = 0;
>
> -       schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));
> +       schedstat_set(curr->se.statistics.exec_max,
> +                     max(curr->se.statistics.exec_max, delta_exec));
>
>        curr->se.sum_exec_runtime += delta_exec;
>        account_group_exec_runtime(curr, delta_exec);
> Index: linux-2.6/kernel/workqueue.c
> ===================================================================
> --- linux-2.6.orig/kernel/workqueue.c
> +++ linux-2.6/kernel/workqueue.c
> @@ -3274,14 +3274,14 @@ static void flush_gcwq(struct global_cwq
>
>        spin_unlock_irq(&gcwq->lock);
>
> -       gcwq = get_gcwq(get_cpu());
> +       gcwq = get_gcwq(get_cpu_light());
>        spin_lock_irq(&gcwq->lock);
>        list_for_each_entry_safe(work, nw, &non_affine_works, entry) {
>                list_del_init(&work->entry);
>                ___queue_work(get_work_cwq(work)->wq, gcwq, work);
>        }
>        spin_unlock_irq(&gcwq->lock);
> -       put_cpu();
> +       put_cpu_light();
>  }
>
>  static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb,
> Index: linux-2.6/localversion-rt
> ===================================================================
> --- linux-2.6.orig/localversion-rt
> +++ linux-2.6/localversion-rt
> @@ -1 +1 @@
> --rt19
> +-rt20
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [ANNOUNCE] 3.0.7-rt20
  2011-10-19  9:59 [ANNOUNCE] 3.0.7-rt20 Thomas Gleixner
  2011-10-19 14:17 ` Rolando Martins
@ 2011-10-25  9:28 ` Yong Zhang
  1 sibling, 0 replies; 3+ messages in thread
From: Yong Zhang @ 2011-10-25  9:28 UTC (permalink / raw)
  To: Thomas Gleixner; +Cc: LKML, linux-rt-users

On Wed, Oct 19, 2011 at 11:59:09AM +0200, Thomas Gleixner wrote:
> Dear RT Folks,
> 
> I'm pleased to announce the 3.0.7-rt20 release.
> 
> 3.0.7-rt19 is an not announced intermediate release, which only
> updates to 3.0.7. No rt changes except dropping patches which made it
> into 3.0.7.
> 

Got below warning during cpu hotplug:

[  356.523928] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: posixcputmr/9/63
[  356.523935] caller is kmem_cache_free+0x43/0x240
[  356.523937] Pid: 63, comm: posixcputmr/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.523939] Call Trace:
[  356.523947]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.523951]  [<ffffffff81134c23>] kmem_cache_free+0x43/0x240
[  356.523956]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.523960]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.523964]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.523969]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.523973]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.523978]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.523981]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.523986]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.523991]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.523996]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.524000]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524005]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.524009]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524013]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.524017]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.524021]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  356.524026] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: posixcputmr/9/63
[  356.524029] caller is kmem_cache_free+0xb9/0x240
[  356.524031] Pid: 63, comm: posixcputmr/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.524032] Call Trace:
[  356.524036]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.524040]  [<ffffffff81134c99>] kmem_cache_free+0xb9/0x240
[  356.524044]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.524048]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.524051]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.524055]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.524058]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.524062]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.524065]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.524069]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.524073]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.524077]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.524081]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524085]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.524089]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524093]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.524097]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.524100]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  356.524103] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: posixcputmr/9/63
[  356.524105] caller is kmem_cache_free+0xd0/0x240
[  356.524107] Pid: 63, comm: posixcputmr/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.524108] Call Trace:
[  356.524112]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.524116]  [<ffffffff81134cb0>] kmem_cache_free+0xd0/0x240
[  356.524120]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.524123]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.524127]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.524130]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.524134]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.524138]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.524141]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.524145]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.524149]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.524153]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.524157]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524161]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.524165]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524169]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.524173]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.524176]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  356.524179] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: posixcputmr/9/63
[  356.524182] caller is unlock_slab_and_free_delayed+0x28/0xf0
[  356.524183] Pid: 63, comm: posixcputmr/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.524185] Call Trace:
[  356.524189]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.524193]  [<ffffffff81134648>] unlock_slab_and_free_delayed+0x28/0xf0
[  356.524197]  [<ffffffff81134ce5>] kmem_cache_free+0x105/0x240
[  356.524201]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.524204]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.524208]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.524212]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.524215]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.524219]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.524222]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.524226]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.524230]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.524234]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.524238]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524242]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.524246]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524250]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.524254]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.524257]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  356.524259] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: posixcputmr/9/63
[  356.524262] caller is unlock_slab_and_free_delayed+0x5d/0xf0
[  356.524264] Pid: 63, comm: posixcputmr/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.524265] Call Trace:
[  356.524269]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.524273]  [<ffffffff8113467d>] unlock_slab_and_free_delayed+0x5d/0xf0
[  356.524277]  [<ffffffff81134ce5>] kmem_cache_free+0x105/0x240
[  356.524281]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.524284]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.524288]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.524292]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.524295]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.524299]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.524302]  [<ffffffff810793b0>] ? cpu_timer_fire+0xa0/0xa0
[  356.524306]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.524310]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.524314]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.524318]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524322]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.524326]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.524330]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.524334]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.524337]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  356.528436] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: watchdog/9/68
[  356.528440] caller is kmem_cache_free+0x43/0x240
[  356.528442] Pid: 68, comm: watchdog/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.528443] Call Trace:
[  356.528449]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.528453]  [<ffffffff81134c23>] kmem_cache_free+0x43/0x240
[  356.528457]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.528461]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.528464]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.528468]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.528472]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.528478]  [<ffffffff810bd9a0>] ? watchdog_enable+0x220/0x220
[  356.528482]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.528486]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.528491]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.528495]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528499]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.528503]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528507]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.528511]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.528515]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  356.528520] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: watchdog/9/68
[  356.528523] caller is kmem_cache_free+0xb9/0x240
[  356.528525] Pid: 68, comm: watchdog/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.528526] Call Trace:
[  356.528530]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.528534]  [<ffffffff81134c99>] kmem_cache_free+0xb9/0x240
[  356.528538]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.528541]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.528544]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.528548]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.528552]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.528556]  [<ffffffff810bd9a0>] ? watchdog_enable+0x220/0x220
[  356.528560]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.528564]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.528568]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.528572]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528576]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.528579]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528583]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.528587]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.528591]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  356.528593] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: watchdog/9/68
[  356.528596] caller is kmem_cache_free+0xd0/0x240
[  356.528597] Pid: 68, comm: watchdog/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.528599] Call Trace:
[  356.528602]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.528606]  [<ffffffff81134cb0>] kmem_cache_free+0xd0/0x240
[  356.528610]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.528613]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.528617]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.528621]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.528624]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.528628]  [<ffffffff810bd9a0>] ? watchdog_enable+0x220/0x220
[  356.528632]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.528636]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.528640]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.528644]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528648]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.528652]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528656]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.528660]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.528663]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  356.528666] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: watchdog/9/68
[  356.528668] caller is unlock_slab_and_free_delayed+0x28/0xf0
[  356.528670] Pid: 68, comm: watchdog/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.528671] Call Trace:
[  356.528675]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.528679]  [<ffffffff81134648>] unlock_slab_and_free_delayed+0x28/0xf0
[  356.528683]  [<ffffffff81134ce5>] kmem_cache_free+0x105/0x240
[  356.528687]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.528690]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.528694]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.528698]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.528701]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.528705]  [<ffffffff810bd9a0>] ? watchdog_enable+0x220/0x220
[  356.528709]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.528713]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.528717]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.528721]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528725]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.528729]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528733]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.528737]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.528740]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  356.528743] BUG: using smp_processor_id() in preemptible [00000000 00000000] code: watchdog/9/68
[  356.528746] caller is unlock_slab_and_free_delayed+0x5d/0xf0
[  356.528747] Pid: 68, comm: watchdog/9 Tainted: G        W   3.0.7-rt20-00826-g3a88799 #3
[  356.528749] Call Trace:
[  356.528752]  [<ffffffff81357db0>] debug_smp_processor_id+0x110/0x130
[  356.528757]  [<ffffffff8113467d>] unlock_slab_and_free_delayed+0x5d/0xf0
[  356.528761]  [<ffffffff81134ce5>] kmem_cache_free+0x105/0x240
[  356.528765]  [<ffffffff8104c577>] __cleanup_sighand+0x27/0x30
[  356.528768]  [<ffffffff81052e76>] release_task+0x246/0x540
[  356.528771]  [<ffffffff81052c4d>] ? release_task+0x1d/0x540
[  356.528775]  [<ffffffff815bfe55>] ? _raw_spin_unlock+0x35/0x60
[  356.528779]  [<ffffffff81054c9e>] do_exit+0x65e/0x8e0
[  356.528783]  [<ffffffff810bd9a0>] ? watchdog_enable+0x220/0x220
[  356.528787]  [<ffffffff81076600>] kthread+0xa0/0xb0
[  356.528791]  [<ffffffff815be17e>] ? rt_spin_lock_slowunlock+0x1e/0x80
[  356.528795]  [<ffffffff81037d29>] ? sub_preempt_count+0xa9/0xe0
[  356.528799]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528803]  [<ffffffff815c1a54>] kernel_thread_helper+0x4/0x10
[  356.528807]  [<ffffffff815bfdeb>] ? _raw_spin_unlock_irq+0x3b/0x70
[  356.528811]  [<ffffffff815c0184>] ? retint_restore_args+0xe/0xe
[  356.528815]  [<ffffffff81076560>] ? kthreadd+0x160/0x160
[  356.528818]  [<ffffffff815c1a50>] ? gs_change+0xb/0xb
[  357.967865] CPU 21 MCA banks CMCI:2 CMCI:3 CMCI:5

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2011-10-25  9:28 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-10-19  9:59 [ANNOUNCE] 3.0.7-rt20 Thomas Gleixner
2011-10-19 14:17 ` Rolando Martins
2011-10-25  9:28 ` Yong Zhang

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).