Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 959c8963 authored by Vladimir Davydov's avatar Vladimir Davydov Committed by Linus Torvalds
Browse files

memcg, slab: fix barrier usage when accessing memcg_caches 



Each root kmem_cache has pointers to per-memcg caches stored in its
memcg_params::memcg_caches array.  Whenever we want to allocate a slab
for a memcg, we access this array to get per-memcg cache to allocate
from (see memcg_kmem_get_cache()).  The access must be lock-free for
performance reasons, so we should use barriers to assert the kmem_cache
is up-to-date.

First, we should place a write barrier immediately before setting the
pointer to it in the memcg_caches array in order to make sure nobody
will see a partially initialized object.  Second, we should issue a read
barrier before dereferencing the pointer to conform to the write
barrier.

However, currently the barrier usage looks rather strange.  We have a
write barrier *after* setting the pointer and a read barrier *before*
reading the pointer, which is incorrect.  This patch fixes this.

Signed-off-by: default avatarVladimir Davydov <vdavydov@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 1aa13254

mm/memcontrol.c

+10 −14
Original line number Diff line number Diff line
@@ -3274,12 +3274,14 @@ void memcg_register_cache(struct kmem_cache *s) 
	list_add(&s->memcg_params->list, &memcg->memcg_slab_caches);

	mutex_unlock(&memcg->slab_caches_mutex);



	root->memcg_params->memcg_caches[id] = s;

	/*

	 * the readers won't lock, make sure everybody sees the updated value,

	 * so they won't put stuff in the queue again for no reason

	 * Since readers won't lock (see cache_from_memcg_idx()), we need a

	 * barrier here to ensure nobody will see the kmem_cache partially

	 * initialized.

	 */

	wmb();

	smp_wmb();



	root->memcg_params->memcg_caches[id] = s;

}



void memcg_unregister_cache(struct kmem_cache *s)
@@ -3605,7 +3607,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, 
					  gfp_t gfp)

{

	struct mem_cgroup *memcg;

	int idx;

	struct kmem_cache *memcg_cachep;



	VM_BUG_ON(!cachep->memcg_params);

	VM_BUG_ON(!cachep->memcg_params->is_root_cache);
@@ -3619,15 +3621,9 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, 
	if (!memcg_can_account_kmem(memcg))

		goto out;



	idx = memcg_cache_id(memcg);



	/*

	 * barrier to mare sure we're always seeing the up to date value.  The

	 * code updating memcg_caches will issue a write barrier to match this.

	 */

	read_barrier_depends();

	if (likely(cache_from_memcg_idx(cachep, idx))) {

		cachep = cache_from_memcg_idx(cachep, idx);

	memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg));

	if (likely(memcg_cachep)) {

		cachep = memcg_cachep;

		goto out;

	}

mm/slab.h

+11 −1
Original line number Diff line number Diff line
@@ -163,9 +163,19 @@ static inline const char *cache_name(struct kmem_cache *s) 
static inline struct kmem_cache *

cache_from_memcg_idx(struct kmem_cache *s, int idx)

{

	struct kmem_cache *cachep;



	if (!s->memcg_params)

		return NULL;

	return s->memcg_params->memcg_caches[idx];

	cachep = s->memcg_params->memcg_caches[idx];



	/*

	 * Make sure we will access the up-to-date value. The code updating

	 * memcg_caches issues a write barrier to match this (see

	 * memcg_register_cache()).

	 */

	smp_read_barrier_depends();

	return cachep;

}



static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)