lkml.org 
[lkml]   [2013]   [Nov]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: perf/tracepoint yet another lockup

OK, managed to capture a crash, not sure if it was the same as the
previous one in the thread.

In this case it looks like it is tracepoint event 0x25 which I think is
vsyscall/emulate_vsyscall/id:37
Although I can't get this to trigger in a standalone workload (it seems to
trigger best under some sort of load).

So are all tracepoints unsafe? Or just a subset?

[18367.468004] ------------[ cut here ]------------
[18367.468004] WARNING: CPU: 0 PID: 17541 at kernel/watchdog.c:245 watchdog_ove)
[18367.468004] Watchdog detected hard LOCKUP on cpu 0
[18367.468004] Modules linked in: cpufreq_userspace cpufreq_stats cpufreq_powern
[18367.468004] CPU: 0 PID: 17541 Comm: perf_fuzzer Not tainted 3.12.0 #2
[18367.468004] Hardware name: AOpen DE7000/nMCP7ALPx-DE R1.06 Oct.19.2012, BI2
[18367.468004] 00000000000000f5 ffff88011fc07c48 ffffffff8151aad6 ffff88011fc08
[18367.468004] ffffffff8103cd68 ffff88011fc07c78 ffffffff810a101c ffff88011b310
[18367.468004] ffff88011fc07ef8 ffff88011fc07d58 0000000000000000 ffff88011fc08
[18367.468004] Call Trace:
[18367.468004] <NMI> [<ffffffff8151aad6>] ? dump_stack+0x41/0x53
[18367.468004] [<ffffffff8103cd68>] ? warn_slowpath_common+0x81/0x9c
[18367.468004] [<ffffffff810a101c>] ? watchdog_overflow_callback+0x9b/0xa6
[18367.468004] [<ffffffff8103ce25>] ? warn_slowpath_fmt+0x46/0x48
[18367.468004] [<ffffffff810c9df2>] ? perf_prepare_sample+0x167/0x2f4
[18367.468004] [<ffffffff810a101c>] ? watchdog_overflow_callback+0x9b/0xa6
[18367.468004] [<ffffffff810ca4a2>] ? __perf_event_overflow+0x12e/0x1ab
[18367.468004] [<ffffffff810167d3>] ? intel_pmu_lbr_read+0x253/0x349
[18367.468004] [<ffffffff81018c95>] ? intel_pmu_handle_irq+0x2b8/0x34d
[18367.468004] [<ffffffff8151dc88>] ? _raw_spin_lock+0x12/0x2a
[18367.468004] [<ffffffff8151edfc>] ? nmi_handle+0xa8/0x13a
[18367.468004] [<ffffffff8151f473>] ? perf_event_nmi_handler+0x24/0x3d
[18367.468004] [<ffffffff8151edb2>] ? nmi_handle+0x5e/0x13a
[18367.468004] [<ffffffff8151ef35>] ? do_nmi+0xa7/0x2bd
[18367.468004] [<ffffffff8151e537>] ? end_repeat_nmi+0x1e/0x2e
[18367.468004] [<ffffffff81049a6f>] ? __lock_task_sighand+0x4a/0x6a
[18367.468004] [<ffffffff81049a6f>] ? __lock_task_sighand+0x4a/0x6a
[18367.468004] [<ffffffff81049a6f>] ? __lock_task_sighand+0x4a/0x6a
[18367.468004] <<EOE>> <IRQ> [<ffffffff8104b055>] ? do_send_sig_info+0x2c/0x5
[18367.468004] [<ffffffff8111f683>] ? send_sigio_to_task+0xeb/0xf5
[18367.468004] [<ffffffff8111f737>] ? send_sigio+0xaa/0xdd
[18367.468004] [<ffffffff8111f7d3>] ? kill_fasync+0x69/0x86
[18367.468004] [<ffffffff810cabf9>] ? perf_event_wakeup+0x8c/0xa1
[18367.468004] [<ffffffff810c494d>] ? __irq_work_run+0x5f/0x7b
[18367.468004] [<ffffffff81005f82>] ? smp_trace_irq_work_interrupt+0x4b/0x7e
[18367.468004] [<ffffffff815261ca>] ? trace_irq_work_interrupt+0x6a/0x70
[18367.468004] [<ffffffff8151da07>] ? _raw_spin_unlock_irqrestore+0xf/0x11
[18367.468004] [<ffffffff810a3a89>] ? rcu_process_callbacks+0x4a4/0x4b8
[18367.468004] [<ffffffff8105b8f3>] ? enqueue_hrtimer+0x51/0x7b
[18367.468004] [<ffffffff81041027>] ? __do_softirq+0x102/0x208
[18367.468004] [<ffffffff81027608>] ? lapic_next_event+0x1d/0x21
[18367.468004] [<ffffffff8105c187>] ? hrtimer_interrupt+0x119/0x1c6
[18367.468004] [<ffffffff815263dc>] ? call_softirq+0x1c/0x30
[18367.468004] [<ffffffff810041b9>] ? do_softirq+0x38/0x6d
[18367.468004] [<ffffffff81040d1c>] ? irq_exit+0x45/0xa1
[18367.468004] [<ffffffff81526a14>] ? smp_trace_apic_timer_interrupt+0x83/0x91
[18367.468004] [<ffffffff8152597a>] ? trace_apic_timer_interrupt+0x6a/0x70
[18367.468004] <EOI> [<ffffffff8151dc88>] ? _raw_spin_lock+0x12/0x2a
[18367.468004] [<ffffffff81133680>] ? sync_inodes_sb+0x10a/0x1a0
[18367.468004] [<ffffffff811373d3>] ? fdatawrite_one_bdev+0x17/0x17
[18367.468004] [<ffffffff8111446f>] ? iterate_supers+0x6e/0xc0
[18367.468004] [<ffffffff8113741f>] ? sys_sync+0x35/0x83
[18367.468004] [<ffffffff81524c96>] ? system_call_fastpath+0x1a/0x1f
[18367.468004] ---[ end trace 73e6e6b3ff98085b ]---
[18367.468004] perf samples too long (8137810 > 20000), lowering kernel.perf_ev0
[18367.468004] INFO: NMI handler (perf_event_nmi_handler) took too long to run:s
[18378.460001] perf samples too long (8074239 > 40000), lowering kernel.perf_ev0
[18379.284001] perf samples too long (8011165 > 76923), lowering kernel.perf_ev0
[18380.132001] perf samples too long (7948583 > 142857), lowering kernel.perf_e0
[18380.980001] perf samples too long (7886490 > 250000), lowering kernel.perf_e0
[18381.828001] perf samples too long (7824882 > 500000), lowering kernel.perf_e0



\
 
 \ /
  Last update: 2013-11-11 23:41    [W:0.181 / U:0.128 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site