lkml.org 
[lkml]   [2011]   [Nov]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: WARNING: at mm/slub.c:3357, kernel BUG at mm/slub.c:3413
From
On Mon, 2011-11-21 at 20:51 +0100, Markus Trippelsdorf wrote:
>> On 2011.11.21 at 19:52 +0100, Markus Trippelsdorf wrote:
>> > On 2011.11.21 at 19:39 +0100, Eric Dumazet wrote:
>> > > Le lundi 21 novembre 2011 à 18:35 +0100, Markus Trippelsdorf a écrit :
>> > >
>> > > > New one:
>> > >
>> > > ...
>> > >
>> > > I was just wondering if you were using CONFIG_CGROUPS=y, and if yes, if
>> > > you could try to disable it.
>> >
>> > # CONFIG_CGROUPS is not set
>> >
>> > (I never enable CGROUPS on my machines)
>>
>> Just for the record, I've attached full dmesg and my .config.
>> (Will continue testing tomorrow)

On Mon, Nov 21, 2011 at 10:27 PM, Benjamin Herrenschmidt
<benh@kernel.crashing.org> wrote:
> Note that I hit a similar looking crash (sorry, I couldn't capture a
> backtrace back then) on a PowerMac G5 (ppc64) while doing a large rsync
> transfer yesterday with -rc2-something (cfcfc9ec) and
> Christian Kujau (CC) seems to be able to reproduce something similar on
> some other ppc platform (Christian, what is your setup ?)
>
> We haven't hit the poison checks, more like bad pointer derefs, almost
> always in SLUB coming from skb alloc or free.
>
> In my case, it's not easy to reproduce, so a bisection would be
> error-prone.

Does CONFIG_SLAB make all the issues go away or are you still able to
reproduce corruption with it? I'm asking because we have the per-cpu
partial list patches in 3.2-rc1 and I'd like to rule them out as a
suspect.

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

\
 
 \ /
  Last update: 2011-11-21 22:33    [W:0.522 / U:0.772 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site