slub: fix a possible memleak in __slab_alloc()

commit 73736e0387ba0e6d2b703407b4d26168d31516a7 upstream.

Zhihua Che reported a possible memleak in slub allocator on
CONFIG_PREEMPT=y builds.

It is possible current thread migrates right before disabling irqs in
__slab_alloc(). We must check again c->freelist, and perform a normal
allocation instead of scratching c->freelist.

Many thanks to Zhihua Che for spotting this bug, introduced in 2.6.39

V2: Its also possible an IRQ freed one (or several) object(s) and
populated c->freelist, so its not a CONFIG_PREEMPT only problem.

Reported-by: Zhihua Che <zhihua.che@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/mm/slub.c b/mm/slub.c
index 35f351f..0d0901e 100644 (file)
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1818,6 +1818,11 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
        if (unlikely(!node_match(c, node)))
                goto another_slab;
 
+       /* must check again c->freelist in case of cpu migration or IRQ */
+       object = c->freelist;
+       if (object)
+               goto update_freelist;
+
        stat(s, ALLOC_REFILL);
 
 load_freelist:
@@ -1827,6 +1832,7 @@ load_freelist:
        if (kmem_cache_debug(s))
                goto debug;
 
+update_freelist:
        c->freelist = get_freepointer(s, object);
        page->inuse = page->objects;
        page->freelist = NULL;