slub: min order when debug_guardpage_minorder > 0
authorStanislaw Gruszka <sgruszka@redhat.com>
Tue, 10 Jan 2012 23:07:32 +0000 (15:07 -0800)
committerLinus Torvalds <torvalds@linux-foundation.org>
Wed, 11 Jan 2012 00:30:43 +0000 (16:30 -0800)
Disable slub debug facilities and allocate slabs at minimal order when
debug_guardpage_minorder > 0 to increase probability to catch random
memory corruption by cpu exception.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/slub.c

index 025f6ac..d99acbf 100644 (file)
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3654,6 +3654,9 @@ void __init kmem_cache_init(void)
        struct kmem_cache *temp_kmem_cache_node;
        unsigned long kmalloc_size;
 
+       if (debug_guardpage_minorder())
+               slub_max_order = 0;
+
        kmem_size = offsetof(struct kmem_cache, node) +
                                nr_node_ids * sizeof(struct kmem_cache_node *);