[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20140517170037.GA11096@twins.programming.kicks-ass.net>
Date: Sat, 17 May 2014 19:00:37 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Sasha Levin <sasha.levin@...cle.com>
Cc: Theodore Ts'o <tytso@....edu>,
Hannes Frederic Sowa <hannes@...essinduktion.org>,
"H. Peter Anvin" <hpa@...ux.intel.com>,
Ingo Molnar <mingo@...nel.org>, acme@...stprotocols.net,
LKML <linux-kernel@...r.kernel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Dave Jones <davej@...hat.com>, price@....edu
Subject: Re: BUG_ON drivers/char/random.c:986 (Was: perf: use after free in
perf_remove_from_context)
On Sat, May 17, 2014 at 12:24:32PM -0400, Sasha Levin wrote:
> On 05/16/2014 10:18 PM, Theodore Ts'o wrote:
> > On Fri, May 16, 2014 at 05:46:22PM -0700, Hannes Frederic Sowa wrote:
> >> > This should do the trick:
> >> > dd if=/dev/urandom of=/dev/zero bs=67108707
> >> >
> >> > I suspect ee1de406ba6eb1 ("random: simplify accounting logic") as the
> >> > culprit.
> > Yep, that it's it. Thanks for noticing this so quickly! I'll push
> > the following patch to Linus.
>
> Peter, could you describe the infrastructure you're running on? I don't
> think Dave or myself have ever hit this issue, and I wonder what made you
> stumble on it.
I'm running it on a WSP-EP, 2 nodes, 6 cores per node, 2 threads per
core for a total of 24 cpus.
I'm running trinity as user, and using:
MALLOC_CHECK_=0 ./trinity -xinit_module -xreboot -xshutdown -xunshare -xnfsservctl -xclock_nanosleep -xuselib -xumount -xmount -m --quiet -C 400 -l off -xmremap
to run it.
I'm currently also running with syscall and a few other trace bits
enabled, but I suppose that shouldn't affect things too much.
The machine is running Debian wheezy with a few choice testing bits.
Content of type "application/pgp-signature" skipped
Powered by blists - more mailing lists