linux-kernel - Re: perf: perf_fuzzer triggers instant reboot

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAHA+R7PCQRScYi3PF2dTQ-Hgoe7wv6GC4utBoF_pt5ZCRyOFuA@mail.gmail.com>
Date:	Tue, 30 Sep 2014 10:58:43 -0700
From:	Cong Wang <cwang@...pensource.com>
To:	Vince Weaver <vincent.weaver@...ne.edu>
Cc:	Peter Zijlstra <peterz@...radead.org>,
	Sasha Levin <sasha.levin@...cle.com>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	Paul Mackerras <paulus@...ba.org>,
	Ingo Molnar <mingo@...hat.com>,
	Arnaldo Carvalho de Melo <acme@...nel.org>
Subject: Re: perf: perf_fuzzer triggers instant reboot

On Sun, Sep 28, 2014 at 10:21 PM, Vince Weaver <vincent.weaver@...ne.edu> wrote:
> On Thu, 25 Sep 2014, Cong Wang wrote:
>
>> On Wed, Sep 24, 2014 at 9:59 PM, Vince Weaver <vincent.weaver@...ne.edu> wrote:
>
>> > Now that just might mean the patch pushed the code around enough so my
>> > test doesn't trigger, but there is hope that maybe this fixes things.
>>
>> I read this as it fixes your crash as well?
>
> It makes a testcase I have stop triggering an instant reboot, but there
> have been various attempts to fix similar problems over the past few
> months and so far the general family of lockups/reboots still remains.
>
> I'll have to start fuzzing with 3.17-rc7 and see if things are better now,
> but it can take days to trigger this class of bugs.

Great! Thanks for testing!

>
>> Sure, as I said in the changelog, it is a soft lockup which was triggered on
>> dozens of machines here, it is actually pretty straightforward:
>
> so you managed to trigger it with the perf utility?


Yes, it should be some job in our data center running perf.

> Do you have the exact command line that triggered it?
>

No, I didn't check /proc/<pid>/cmdline when I was debugging this.
What's more important, it was triggered by some job in data center,
hard to reproduce manually.

Hope this helps.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/