Re: perf: perf_fuzzer triggers instant reboot

[Vince Weaver]

On Tue, 9 Sep 2014, Vince Weaver wrote:
> 
> [  751.656861] NOHZ: local_softirq_pending 100
> [  756.009271] traps: perf_fuzzer[4236] trap invalid opcode ip:4044c0 sp:7fffb0ed6f90 error:0
> [  756.017590] BUG: unable to handle kernel paging request

so it turns out that while it seems reproducible, it must be some sort of 
race condition and only happens like 75% of the time on a 3.17-rc4 kernel.

Almost managed to get an oops that last time:

[  222.457213] NOHZ: local_softirq_pending 100
[  222.712448] NOHZ: local_softirq_pending 100
[  222.947573] NOHZ: local_softirq_pending 100
[  229.168047] BUG: unable to handle kernel NULL pointer dereference at 0000000000000087
[  229.172003] IP: [<ffffffff81062cde>] scheduler_tick+0x56/0xbb
[  229.172003] PGD c4b72067 PUD c52df067 PMD 0 
[  229.172003] Thread overran stack, or stack corrupted
[  229.172003] Oops: 0000 [#1] SMP 
[  229.172003] Modules linked in: cpufreq_userspace cpufreq_stats cpufreq_powersave cpufreq_conservative f71882fg mcs7830 usbnet coretemp evdev psmouse pcspkr ohci_pci ohci_hcd  
^P<C0><FF><FF><E8><FF><FF><A8>A!^A<88><FF><FF>hA!^A<88><FF>
<FF>^P}<CB>7(OCE) 

any advice on tracking this down?  I can fire up ftrace but it's unclear 
to me I will get anything useful as the system insta-reboots pretty 
quickly.

Vince
--
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/