mm: fix slab->page _count corruption when using slub
authorPravin B Shelar <pshelar@nicira.com>
Wed, 20 Jun 2012 19:52:56 +0000 (12:52 -0700)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Mon, 16 Jul 2012 16:03:49 +0000 (09:03 -0700)
commitd3ae4a87530c1e10c0705995c87fe8a7b4267f4b
tree3881f8a77c7788fd8720b5c680f3feca5aa87a6d
parent3cc270f7fcd34b08d37ed51fb4c25b0f513f2e65
mm: fix slab->page _count corruption when using slub

commit abca7c4965845924f65d40e0aa1092bdd895e314 upstream.

On arches that do not support this_cpu_cmpxchg_double() slab_lock is used
to do atomic cmpxchg() on double word which contains page->_count.  The
page count can be changed from get_page() or put_page() without taking
slab_lock.  That corrupts page counter.

Fix it by moving page->_count out of cmpxchg_double data.  So that slub
does no change it while updating slub meta-data in struct page.

[akpm@linux-foundation.org: use standard comment layout, tweak comment text]
Reported-by: Amey Bhide <abhide@nicira.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
include/linux/mm_types.h