Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

mm, slab: lock the correct nodelist after reenabling irqs

Browse source 
cache_grow() can reenable irqs so the cpu (and node) can change, so ensure
that we take list_lock on the correct nodelist.

This fixes an issue with commit 072bb0aa5e ("mm: sl[au]b: add
knowledge of PFMEMALLOC reserve pages") where list_lock for the wrong
node was taken after growing the cache.

Reported-and-tested-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
David Rientjes 2012-08-28 19:57:21 -07:00 committed by Linus Torvalds
parent c182ae42cc
commit 51cd8e6ff2
1 changed files with 1 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
mm/slab.c
View file

@ -3260,6 +3260,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
/* cache_grow can reenable interrupts, then ac could change. */
ac = cpu_cache_get(cachep);
node = numa_mem_id();
/* no objects in sight? abort */
if (!x && (ac->avail == 0 || force_refill))