Re: perf-related lockup on 3.11

From: Paul E. McKenney
Date: Thu Sep 12 2013 - 13:31:11 EST


On Wed, Sep 11, 2013 at 11:35:24AM -0400, Vince Weaver wrote:
>
> I got this hard lockup running my perf_fuzzer on 3.11 on a core2.
> I guess I should try to reproduce it on linus-git but was hoping
> I could wait until -rc1 before trying that.
>
> I'm not really sure where to report lockups like this because it's sort
> of unclear what exactly the problem is. perf? ftrace? nmi? rcu?

RCU is an innocent bystander on this one. (Honest, officer!)

You see rcu_nmi_enter() because it is called on NMI.

Thanx, Paul

> Vince
>
>
> [ 4022.356007] ------------[ cut here ]------------
> [ 4022.356007] WARNING: CPU: 0 PID: 3393 at kernel/watchdog.c:245 watchdog_overf
> low_callback+0x9b/0xa6()
> [ 4022.356007] Watchdog detected hard LOCKUP on cpu 0
> [ 4022.356007] Modules linked in: cpufreq_userspace cpufreq_stats cpufreq_powers
> ave cpufreq_conservative f71882fg coretemp acpi_cpufreq mperf mcs7830 usbnet psm
> ouse pcspkr serio_raw evdev video wmi ohci_pci processor button thermal_sys ohci
> _hcd i2c_nforce2 sg ehci_pci ehci_hcd sd_mod usbcore usb_common
> [ 4022.356007] CPU: 0 PID: 3393 Comm: perf_fuzzer Not tainted 3.11.0 #2
> [ 4022.356007] Hardware name: AOpen DE7000/nMCP7ALPx-DE R1.06 Oct.19.2012, BIO
> S 080015 10/19/2012
> [ 4022.356007] 00000000000000f5 ffff88011fc07c48 ffffffff81508364 ffff88011fc07
> c58
> [ 4022.356007] ffffffff8103cc81 ffffffff817d132a ffffffff8109b2e9 ffff88011b30e
> 400
> [ 4022.356007] ffff88011fc07ef8 ffff88011fc07d58 0000000000000000 ffff88011fc07
> ca8
> [ 4022.356007] Call Trace:
> [ 4022.356007] <NMI> [<ffffffff81508364>] ? dump_stack+0x41/0x55
> [ 4022.356007] [<ffffffff8103cc81>] ? warn_slowpath_common+0x81/0x9c
> [ 4022.356007] [<ffffffff8109b2e9>] ? watchdog_overflow_callback+0x9b/0xa6
> [ 4022.356007] [<ffffffff8103cd3e>] ? warn_slowpath_fmt+0x46/0x48
> [ 4022.356007] [<ffffffff8109b257>] ? watchdog_overflow_callback+0x9/0xa6
> [ 4022.356007] [<ffffffff8109b2e9>] ? watchdog_overflow_callback+0x9b/0xa6
> [ 4022.356007] [<ffffffff810c90d8>] ? __perf_event_overflow+0x12e/0x1ab
> [ 4022.356007] [<ffffffff810c50ea>] ? perf_event_update_userpage+0x16/0xce
> [ 4022.356007] [<ffffffff81017dc8>] ? intel_pmu_save_and_restart+0xe/0x22
> [ 4022.356007] [<ffffffff81018a2f>] ? intel_pmu_handle_irq+0x2c4/0x35b
> [ 4022.356007] [<ffffffff815122fc>] ? ftrace_call+0x5/0x2f
> [ 4022.356007] [<ffffffff8150b2ad>] ? _raw_spin_unlock_irqrestore+0xf/0x11
> [ 4022.356007] [<ffffffff8150ccab>] ? perf_event_nmi_handler+0x24/0x3d
> [ 4022.356007] [<ffffffff8150c4dd>] ? nmi_handle+0x5e/0x13a
> [ 4022.356007] [<ffffffff810a0d70>] ? rcu_nmi_enter+0x9/0x5b
> [ 4022.356007] [<ffffffff8150c660>] ? do_nmi+0xa7/0x2bd
> [ 4022.356007] [<ffffffff8150bc77>] ? end_repeat_nmi+0x1e/0x2e
> [ 4022.356007] [<ffffffff8150b2ad>] ? _raw_spin_unlock_irqrestore+0xf/0x11
> [ 4022.356007] [<ffffffff8150b2ad>] ? _raw_spin_unlock_irqrestore+0xf/0x11
> [ 4022.356007] [<ffffffff8150b2ad>] ? _raw_spin_unlock_irqrestore+0xf/0x11
> [ 4022.356007] <<EOE>> [<ffffffff810bdf89>] ? perf_trace_event_unreg+0x3a/0xbd
> [ 4022.356007] [<ffffffff810be03a>] ? perf_trace_destroy+0x2e/0x3b
> [ 4022.356007] [<ffffffff810c5f5d>] ? free_event+0xf6/0x11e
> [ 4022.356007] [<ffffffff810cab5c>] ? SYSC_perf_event_open+0x6e4/0x771
> [ 4022.356007] [<ffffffff81055666>] ? put_pid+0xe/0x4f
> [ 4022.356007] [<ffffffff815126c6>] ? system_call_fastpath+0x1a/0x1f
> [ 4022.356007] ---[ end trace c426f99910c1c076 ]---
>
> --
> 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/
>

--
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/