* perf oops/recursive fault using BTS
@ 2015-10-27 8:24 Dave Jones
2015-10-27 18:58 ` Vince Weaver
0 siblings, 1 reply; 3+ messages in thread
From: Dave Jones @ 2015-10-27 8:24 UTC (permalink / raw)
To: Linux Kernel; +Cc: vincent.weaver
I was experimenting with a variant of Vince's bts_kernel test
(https://github.com/deater/perf_event_tests/blob/master/tests/x86_intel/bts_kernel.c)
and hit this..
Oops: 0000 [#1] PREEMPT SMP
CPU: 3 PID: 2471 Comm: a.out Not tainted 4.3.0-rc6-wopr+ #1
task: ffff8805f0b3e400 ti: ffff8801f81d4000 task.ti: ffff8801f81d4000
RIP: 0010:[<ffffffff9d13e44c>] [<ffffffff9d13e44c>] perf_mmap_close+0x3c/0x250
RSP: 0000:ffff8801f81d7b78 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 000000000952ecf3 RSI: ffff88082fc78ea0 RDI: ffff8808026de800
RBP: ffff8801f81d7bc8 R08: 0000000000018ea0 R09: ffff88080c201000
R10: ffffea00151ae460 R11: 0000000000000000 R12: ffff8807071d2000
R13: ffff8808026de800 R14: ffff8807071d2678 R15: ffff8805f0b3e400
FS: 0000000000000000(0000) GS:ffff88082fc60000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000c0 CR3: 000000001dc0b000 CR4: 00000000001406e0
Stack:
ffff8801f81d7c00 ffff8805f0b3e9f8 ffff8807ed482de8 ffff8805f0b3e400
00000000c88a8a46 ffff8807071d2678 ffff8807071d2000 ffff8805f0b3e9f8
ffff8807ed482de8 ffff8805f0b3e400 ffff8801f81d7be8 ffffffff9d17852a
Call Trace:
[<ffffffff9d17852a>] remove_vma+0x2a/0x60
[<ffffffff9d17bdfd>] exit_mmap+0x12d/0x160
[<ffffffff9d07040f>] mmput+0x4f/0xf0
[<ffffffff9d07458e>] do_exit+0x31e/0xaa0
[<ffffffff9d075b53>] do_group_exit+0x43/0xb0
[<ffffffff9d080deb>] get_signal+0x23b/0x640
[<ffffffff9d003b97>] do_signal+0x37/0x6b0
[<ffffffff9d03e306>] ? force_sig_info_fault.constprop.23+0x76/0x90
[<ffffffff9d090000>] ? kthread_bind+0x40/0x40
[<ffffffff9d03e356>] ? is_prefetch.isra.18+0x36/0x260
[<ffffffff9d090000>] ? kthread_bind+0x40/0x40
[<ffffffff9d03eeb0>] ? mm_fault_error+0x110/0x130
[<ffffffff9d03f30a>] ? __do_page_fault+0x43a/0x470
[<ffffffff9d001b06>] prepare_exit_to_usermode+0xb6/0x110
[<ffffffff9d6c76ea>] retint_user+0x8/0x1d
Code: 83 ec 28 65 48 8b 04 25 28 00 00 00 48 89 45 d0 31 c0 48 8b 87 a0 00 00 00 4c 8b a8 c8 00 00 00 4c 89 ef e8 57 ec ff ff 48 89 c3 <48> 8b 80 c0 00 00 00 48 89 45 c0 48 8b 83 b8 00 00 00 48 89 45
RIP [<ffffffff9d13e44c>] perf_mmap_close+0x3c/0x250
RSP <ffff8801f81d7b78>
CR2: 00000000000000c0
---[ end trace 9362dce880c51b19 ]---
Fixing recursive fault but reboot is needed!
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: perf oops/recursive fault using BTS
2015-10-27 8:24 perf oops/recursive fault using BTS Dave Jones
@ 2015-10-27 18:58 ` Vince Weaver
2015-10-27 22:03 ` Dave Jones
0 siblings, 1 reply; 3+ messages in thread
From: Vince Weaver @ 2015-10-27 18:58 UTC (permalink / raw)
To: Dave Jones, Linux Kernel, Peter Zijlstra, Ingo Molnar, Stephane Eranian
On Tue, 27 Oct 2015, Dave Jones wrote:
> I was experimenting with a variant of Vince's bts_kernel test
> (https://github.com/deater/perf_event_tests/blob/master/tests/x86_intel/bts_kernel.c)
> and hit this..
what type of machine was this on?
I'm cc-ing the perf developers because I'm not sure if they monitor
linux-kernel directly.
Vince
>
> Oops: 0000 [#1] PREEMPT SMP
> CPU: 3 PID: 2471 Comm: a.out Not tainted 4.3.0-rc6-wopr+ #1
> task: ffff8805f0b3e400 ti: ffff8801f81d4000 task.ti: ffff8801f81d4000
> RIP: 0010:[<ffffffff9d13e44c>] [<ffffffff9d13e44c>] perf_mmap_close+0x3c/0x250
> RSP: 0000:ffff8801f81d7b78 EFLAGS: 00010246
> RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
> RDX: 000000000952ecf3 RSI: ffff88082fc78ea0 RDI: ffff8808026de800
> RBP: ffff8801f81d7bc8 R08: 0000000000018ea0 R09: ffff88080c201000
> R10: ffffea00151ae460 R11: 0000000000000000 R12: ffff8807071d2000
> R13: ffff8808026de800 R14: ffff8807071d2678 R15: ffff8805f0b3e400
> FS: 0000000000000000(0000) GS:ffff88082fc60000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 00000000000000c0 CR3: 000000001dc0b000 CR4: 00000000001406e0
> Stack:
> ffff8801f81d7c00 ffff8805f0b3e9f8 ffff8807ed482de8 ffff8805f0b3e400
> 00000000c88a8a46 ffff8807071d2678 ffff8807071d2000 ffff8805f0b3e9f8
> ffff8807ed482de8 ffff8805f0b3e400 ffff8801f81d7be8 ffffffff9d17852a
> Call Trace:
> [<ffffffff9d17852a>] remove_vma+0x2a/0x60
> [<ffffffff9d17bdfd>] exit_mmap+0x12d/0x160
> [<ffffffff9d07040f>] mmput+0x4f/0xf0
> [<ffffffff9d07458e>] do_exit+0x31e/0xaa0
> [<ffffffff9d075b53>] do_group_exit+0x43/0xb0
> [<ffffffff9d080deb>] get_signal+0x23b/0x640
> [<ffffffff9d003b97>] do_signal+0x37/0x6b0
> [<ffffffff9d03e306>] ? force_sig_info_fault.constprop.23+0x76/0x90
> [<ffffffff9d090000>] ? kthread_bind+0x40/0x40
> [<ffffffff9d03e356>] ? is_prefetch.isra.18+0x36/0x260
> [<ffffffff9d090000>] ? kthread_bind+0x40/0x40
> [<ffffffff9d03eeb0>] ? mm_fault_error+0x110/0x130
> [<ffffffff9d03f30a>] ? __do_page_fault+0x43a/0x470
> [<ffffffff9d001b06>] prepare_exit_to_usermode+0xb6/0x110
> [<ffffffff9d6c76ea>] retint_user+0x8/0x1d
> Code: 83 ec 28 65 48 8b 04 25 28 00 00 00 48 89 45 d0 31 c0 48 8b 87 a0 00 00 00 4c 8b a8 c8 00 00 00 4c 89 ef e8 57 ec ff ff 48 89 c3 <48> 8b 80 c0 00 00 00 48 89 45 c0 48 8b 83 b8 00 00 00 48 89 45
> RIP [<ffffffff9d13e44c>] perf_mmap_close+0x3c/0x250
> RSP <ffff8801f81d7b78>
> CR2: 00000000000000c0
> ---[ end trace 9362dce880c51b19 ]---
> Fixing recursive fault but reboot is needed!
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: perf oops/recursive fault using BTS
2015-10-27 18:58 ` Vince Weaver
@ 2015-10-27 22:03 ` Dave Jones
0 siblings, 0 replies; 3+ messages in thread
From: Dave Jones @ 2015-10-27 22:03 UTC (permalink / raw)
To: Vince Weaver; +Cc: Linux Kernel, Peter Zijlstra, Ingo Molnar, Stephane Eranian
On Tue, Oct 27, 2015 at 02:58:49PM -0400, Vince Weaver wrote:
> On Tue, 27 Oct 2015, Dave Jones wrote:
>
> > I was experimenting with a variant of Vince's bts_kernel test
> > (https://github.com/deater/perf_event_tests/blob/master/tests/x86_intel/bts_kernel.c)
> > and hit this..
>
> what type of machine was this on?
>
i7-5820K
Dave
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2015-10-27 22:03 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-10-27 8:24 perf oops/recursive fault using BTS Dave Jones
2015-10-27 18:58 ` Vince Weaver
2015-10-27 22:03 ` Dave Jones
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).