[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <66e0b8f575075d009bdb3633837951a3@ulrik.uio.no>
Date: Wed, 20 Apr 2011 17:15:02 +0200
From: Vegard Nossum <vegardno@....uio.no>
To: Eric Dumazet <eric.dumazet@...il.com>
Cc: Christoph Lameter <cl@...ux.com>,
Pekka Enberg <penberg@...helsinki.fi>,
<casteyde.christian@...e.fr>,
Andrew Morton <akpm@...ux-foundation.org>,
<netdev@...r.kernel.org>, <bugzilla-daemon@...zilla.kernel.org>,
<bugme-daemon@...zilla.kernel.org>
Subject: Re: [Bugme-new] [Bug 33502] New: Caught 64-bit read from
uninitialized memory in __alloc_skb
On Wed, 20 Apr 2011 17:01:27 +0200, Eric Dumazet
<eric.dumazet@...il.com> wrote:
> Le mercredi 20 avril 2011 à 09:42 -0500, Christoph Lameter a écrit :
>
>> Avoiding the irq handling yields the savings that improve the
>> fastpath. if
>> you do both then there is only a regression left. So lets go with
>> disabling the CMPXCHG_LOCAL.
>
> OK, let's do that then.
>
> Thanks
>
> [PATCH v4] slub: dont use cmpxchg_double if KMEMCHECK or
> DEBUG_PAGEALLOC
>
> Christian Casteyde reported a KMEMCHECK splat in slub code.
>
> Problem is now we are lockless and allow IRQ in slab_alloc(), the
> object
> we manipulate from freelist can be allocated and freed right before
> we
> try to read object->next.
>
> Same problem can happen with DEBUG_PAGEALLOC
>
> Just dont use cmpxchg_double() if either CONFIG_KMEMCHECK or
> CONFIG_DEBUG_PAGEALLOC is defined.
>
> Reported-by: Christian Casteyde <casteyde.christian@...e.fr>
> Signed-off-by: Eric Dumazet <eric.dumazet@...il.com>
> Cc: Andrew Morton <akpm@...ux-foundation.org>
> Cc: Pekka Enberg <penberg@...helsinki.fi>
> Cc: Vegard Nossum <vegardno@....uio.no>
> Cc: Christoph Lameter <cl@...ux.com>
Thanks, guys. I wonder: Is it possible to make a reproducible test-case
(e.g. loadable module) for this?
Also, pardon my ignorance, but can you explain why this is a bug with
kmemcheck/page-alloc debug and not without them?
Thanks,
Vegard
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists