Messages in this thread |  | | Date | Tue, 18 Feb 2014 13:30:21 -0500 (EST) | From | Vince Weaver <> | Subject | Re: x86_pmu_start WARN_ON. |
| |
On Mon, 17 Feb 2014, Peter Zijlstra wrote:
> Enable CONFIG_FRAME_POINTER for better stack traces; I suspect the > list_del_event() is just random stack garbage. The path that makes sense > is: > wait_rcu()->__wait_for_common()->schedule_timeout()
Here's an updated stack trace on 3.14-rc3 with CONFIG_FRAME_POINTER enabled, in case it's helpful:
[ 237.004035] ------------[ cut here ]------------ [ 237.008016] WARNING: CPU: 1 PID: 2791 at arch/x86/kernel/cpu/perf_event.c:1076 x86_pmu_start+0x41/0x113() [ 237.008016] Modules linked in: cpufreq_userspace cpufreq_stats cpufreq_powersave cpufreq_conservative f71882fg mcs7830 usbnet evdev wmi acpi_cpufreq video coretemp psmouse processor thermal_sys button ohci_pci ohci_hcd serio_raw pcspkr i2c_nforce2 sg ehci_pci ehci_hcd sd_mod usbcore usb_common [ 237.008016] CPU: 1 PID: 2791 Comm: pec_1076_warn Not tainted 3.14.0-rc3+ #10 [ 237.008016] Hardware name: AOpen DE7000/nMCP7ALPx-DE R1.06 Oct.19.2012, BIOS 080015 10/19/2012 [ 237.008016] 0000000000000434 ffff8800cae6b9d8 ffffffff8150e4ff 0000000000000434 [ 237.008016] 0000000000000000 ffff8800cae6ba18 ffffffff8103d64e ffff8800cae6ba48 [ 237.008016] ffffffff81012b10 0000000000000021 ffff88011b31dc00 ffff88011fc8b940 [ 237.008016] Call Trace: [ 237.008016] [<ffffffff8150e4ff>] dump_stack+0x49/0x62 [ 237.008016] [<ffffffff8103d64e>] warn_slowpath_common+0x7c/0x96 [ 237.008016] [<ffffffff81012b10>] ? x86_pmu_start+0x41/0x113 [ 237.008016] [<ffffffff8103d67d>] warn_slowpath_null+0x15/0x17 [ 237.008016] [<ffffffff81012b10>] x86_pmu_start+0x41/0x113 [ 237.008016] [<ffffffff81012dba>] x86_pmu_enable+0x1d8/0x27d [ 237.008016] [<ffffffff810bff5b>] perf_pmu_enable+0x21/0x23 [ 237.008016] [<ffffffff810c3073>] perf_event_context_sched_in+0x79/0x9a [ 237.008016] [<ffffffff810c30ba>] __perf_event_task_sched_in+0x26/0x10f [ 237.008016] [<ffffffff81069913>] ? idle_balance+0x125/0x161 [ 237.008016] [<ffffffff81065937>] finish_task_switch+0x41/0xa8 [ 237.008016] [<ffffffff8150ef2c>] __schedule+0x48f/0x4e3 [ 237.008016] [<ffffffff8105aec3>] ? __hrtimer_start_range_ns+0x2e8/0x2fa [ 237.008016] [<ffffffff8150f0df>] schedule+0x6e/0x70 [ 237.008016] [<ffffffff8150e53a>] schedule_timeout+0x22/0xbd [ 237.008016] [<ffffffff8150e518>] ? dump_stack+0x62/0x62 [ 237.008016] [<ffffffff8150f685>] __wait_for_common+0xc6/0x142 [ 237.008016] [<ffffffff810658a3>] ? try_to_wake_up+0x1a8/0x1a8 [ 237.008016] [<ffffffff81082d21>] ? T.944+0x1de/0x1de [ 237.008016] [<ffffffff8150f7ce>] wait_for_completion+0x1f/0x21 [ 237.008016] [<ffffffff81080b99>] wait_rcu_gp+0x46/0x4f [ 237.008016] [<ffffffff81080ba2>] ? wait_rcu_gp+0x4f/0x4f [ 237.008016] [<ffffffff81082773>] synchronize_sched+0x29/0x2b [ 237.008016] [<ffffffff810b8031>] perf_trace_event_unreg+0x36/0xc8 [ 237.008016] [<ffffffff810b80f9>] perf_trace_destroy+0x36/0x46 [ 237.008016] [<ffffffff810c2079>] tp_perf_event_destroy+0x9/0xb [ 237.008016] [<ffffffff810c26f2>] __free_event+0x35/0x5d [ 237.008016] [<ffffffff810c64ca>] free_event+0x10d/0x116 [ 237.008016] [<ffffffff810c6550>] perf_event_release_kernel+0x7d/0x88 [ 237.008016] [<ffffffff810c65fe>] put_event+0xa3/0xac [ 237.008016] [<ffffffff810c6617>] perf_release+0x10/0x14 [ 237.008016] [<ffffffff8110e08a>] __fput+0xeb/0x1b0 [ 237.008016] [<ffffffff8110e1b7>] ____fput+0x9/0xb [ 237.008016] [<ffffffff81055e21>] task_work_run+0x83/0x9b [ 237.008016] [<ffffffff81002ac6>] do_notify_resume+0x58/0x5f [ 237.008016] [<ffffffff81517f30>] int_signal+0x12/0x17 [ 237.008016] ---[ end trace a07d99177587379f ]--- [ 237.008016] IN: VMW: idx=33 state=0 type=0 config=0 samp_per=5e619d890
|  |