Re: [stable] [perf] overflow/perf_count_sw_cpu_clock crashes recentkernels

[Greg KH]

On Thu, Jul 28, 2011 at 08:47:10PM +0200, Peter Zijlstra wrote:
> On Wed, 2011-07-27 at 14:51 -0400, Vince Weaver wrote:
> > [  392.504845] ------------[ cut here ]------------
> > [  392.504962] WARNING: at kernel/smp.c:320 smp_call_function_single+0x6c/0xf2()
> > [  392.505074] Hardware name: Precision M4500
> > [  392.505181] Modules linked in: acpi_cpufreq cpufreq_conservative mperf cpufreq_powersave cpufreq_userspace cpufreq_stats uinput nouveau snd_hda_codec_hdmi ttm drm_kms_helper mxm_wmi snd_hda_codec_idt iwlagn mac80211 snd_hda_intel snd_hda_codec cfg80211 dell_laptop snd_hwdep video processor ehci_hcd dell_wmi sparse_keymap psmouse sdhci_pci rfkill snd_pcm sdhci thermal_sys pcspkr ac battery wmi serio_raw snd_timer snd_page_alloc evdev i2c_i801 dcdbas button
> > [  392.509709] Pid: 2310, comm: overflow_allcou Not tainted 3.0.0 #43
> > [  392.509819] Call Trace:
> > [  392.509925]  <IRQ>  [<ffffffff81041bb0>] ? warn_slowpath_common+0x78/0x8c
> > [  392.510144]  [<ffffffff810a4d19>] ? perf_exclude_event.part.23+0x31/0x31
> > [  392.510257]  [<ffffffff8106b7c5>] ? smp_call_function_single+0x6c/0xf2
> > [  392.510369]  [<ffffffff810a38aa>] ? task_function_call+0x42/0x4c
> > [  392.510476]  [<ffffffff810a50e4>] ? update_cgrp_time_from_event+0x2c/0x2c
> > [  392.510589]  [<ffffffff810a5a9d>] ? perf_event_disable+0x45/0x8c
> > [  392.510700]  [<ffffffff810a8e89>] ? __perf_event_overflow+0xf1/0x1a3
> > [  392.510812]  [<ffffffff8103c7bb>] ? select_task_rq_fair+0x349/0x574
> > [  392.510924]  [<ffffffff810a7f0a>] ? perf_ctx_adjust_freq+0x42/0xe6
> > [  392.511038]  [<ffffffff8105f152>] ? sched_clock_cpu+0xb/0xc3
> > [  392.511152]  [<ffffffff8100ded5>] ? paravirt_read_tsc+0x5/0x8
> > [  392.511262]  [<ffffffff8100e320>] ? native_sched_clock+0x27/0x2f
> > [  392.511366]  [<ffffffff810a9500>] ? perf_event_overflow+0x10/0x10
> > [  392.511476]  [<ffffffff810a959f>] ? perf_swevent_hrtimer+0x9f/0xda
> > [  392.511599]  [<ffffffff8105ca04>] ? run_posix_cpu_timers+0x23/0x346
> > [  392.511721]  [<ffffffff8131c2ef>] ? rb_insert_color+0xb1/0xd9
> > [  392.511841]  [<ffffffff8105d373>] ? __run_hrtimer+0xac/0x135
> > [  392.511960]  [<ffffffff8105daa3>] ? hrtimer_interrupt+0xdb/0x195
> > [  392.512083]  [<ffffffff8108d040>] ? check_for_new_grace_period.isra.32+0x99/0xa4
> > [  392.512220]  [<ffffffff8108d201>] ? __rcu_process_callbacks+0x72/0x2b7
> > [  392.512345]  [<ffffffff8102437c>] ? hpet_interrupt_handler+0x23/0x2b
> > [  392.512469]  [<ffffffff81089446>] ? handle_irq_event_percpu+0x50/0x180
> > [  392.512592]  [<ffffffff81046f76>] ? __do_softirq+0x13e/0x177
> > [  392.512713]  [<ffffffff810f680c>] ? send_sigio+0x95/0xab
> > [  392.512832]  [<ffffffff810895aa>] ? handle_irq_event+0x34/0x52
> > [  392.512952]  [<ffffffff8108b433>] ? handle_edge_irq+0x9f/0xc6
> > [  392.513072]  [<ffffffff8100a831>] ? handle_irq+0x1d/0x21
> > [  392.513192]  [<ffffffff8100a561>] ? do_IRQ+0x42/0x98
> > [  392.513314]  [<ffffffff81593053>] ? common_interrupt+0x13/0x13
> > [  392.513438]  <EOI> 
> > [  392.513542] ---[ end trace 12f3f913316a2866 ]--- 
> 
> The below patch is for -stable only, upstream has a much larger patch
> that contains the below hunk.

What is that commit id so it can be properly referenced in the patch
below?  And what tree should this patch go into?  .39?  3.0?  Anything
newer?

thanks,

greg k-h

> 
> ---
> Subject: perf: Fix software event overflow
> 
> Vince found that under certain circumstances software event overflows
> go wrong and deadlock. Avoid trying to delete a timer from the timer
> callback.
> 
> Cc: stable@xxxxxxxxxx
> Reported-by: Vince Weaver <vweaver1@xxxxxxxxxxxx>
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
> ---
>  kernel/events/core.c |    7 ++-----
>  1 files changed, 2 insertions(+), 5 deletions(-)
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 9efe710..32a6151 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -5016,11 +5016,8 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
>  	if (events && atomic_dec_and_test(&event->event_limit)) {
>  		ret = 1;
>  		event->pending_kill = POLL_HUP;
> -		if (nmi) {
> -			event->pending_disable = 1;
> -			irq_work_queue(&event->pending);
> -		} else
> -			perf_event_disable(event);
> +		event->pending_disable = 1;
> +		irq_work_queue(&event->pending);
>  	}
>  
>  	if (event->overflow_handler)
> 
> 
> _______________________________________________
> stable mailing list
> stable@xxxxxxxxxxxxxxxx
> http://linux.kernel.org/mailman/listinfo/stable
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/