summaryrefslogtreecommitdiff
path: root/include/linux/memcontrol.h
diff options
context:
space:
mode:
authorVladimir Davydov <vdavydov@parallels.com>2014-12-13 03:56:38 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2014-12-13 23:42:49 +0300
commit8135be5a8012f4c7e95218563855e16c09a8271b (patch)
tree49e85409f82f5973a0cbf21e3e3eac382daa515b /include/linux/memcontrol.h
parentae6e71d3d900c398bdb346ac25733b2efa9b3752 (diff)
downloadlinux-8135be5a8012f4c7e95218563855e16c09a8271b.tar.xz
memcg: fix possible use-after-free in memcg_kmem_get_cache()
Suppose task @t that belongs to a memory cgroup @memcg is going to allocate an object from a kmem cache @c. The copy of @c corresponding to @memcg, @mc, is empty. Then if kmem_cache_alloc races with the memory cgroup destruction we can access the memory cgroup's copy of the cache after it was destroyed: CPU0 CPU1 ---- ---- [ current=@t @mc->memcg_params->nr_pages=0 ] kmem_cache_alloc(@c): call memcg_kmem_get_cache(@c); proceed to allocation from @mc: alloc a page for @mc: ... move @t from @memcg destroy @memcg: mem_cgroup_css_offline(@memcg): memcg_unregister_all_caches(@memcg): kmem_cache_destroy(@mc) add page to @mc We could fix this issue by taking a reference to a per-memcg cache, but that would require adding a per-cpu reference counter to per-memcg caches, which would look cumbersome. Instead, let's take a reference to a memory cgroup, which already has a per-cpu reference counter, in the beginning of kmem_cache_alloc to be dropped in the end, and move per memcg caches destruction from css offline to css free. As a side effect, per-memcg caches will be destroyed not one by one, but all at once when the last page accounted to the memory cgroup is freed. This doesn't sound as a high price for code readability though. Note, this patch does add some overhead to the kmem_cache_alloc hot path, but it is pretty negligible - it's just a function call plus a per cpu counter decrement, which is comparable to what we already have in memcg_kmem_get_cache. Besides, it's only relevant if there are memory cgroups with kmem accounting enabled. I don't think we can find a way to handle this race w/o it, because alloc_page called from kmem_cache_alloc may sleep so we can't flush all pending kmallocs w/o reference counting. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Acked-by: Christoph Lameter <cl@linux.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux/memcontrol.h')
-rw-r--r--include/linux/memcontrol.h14
1 files changed, 12 insertions, 2 deletions
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b74942a9e22f..7c95af8d552c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -400,8 +400,8 @@ int memcg_cache_id(struct mem_cgroup *memcg);
void memcg_update_array_size(int num_groups);
-struct kmem_cache *
-__memcg_kmem_get_cache(struct kmem_cache *cachep);
+struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
+void __memcg_kmem_put_cache(struct kmem_cache *cachep);
int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order);
void __memcg_uncharge_slab(struct kmem_cache *cachep, int order);
@@ -494,6 +494,12 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
return __memcg_kmem_get_cache(cachep);
}
+
+static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
+{
+ if (memcg_kmem_enabled())
+ __memcg_kmem_put_cache(cachep);
+}
#else
#define for_each_memcg_cache_index(_idx) \
for (; NULL; )
@@ -528,6 +534,10 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
{
return cachep;
}
+
+static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
+{
+}
#endif /* CONFIG_MEMCG_KMEM */
#endif /* _LINUX_MEMCONTROL_H */