memcg, slab: fix races in per-memcg cache creation/destruction

We obtain a per-memcg cache from a root kmem_cache by dereferencing an
entry of the root cache's memcg_params::memcg_caches array.  If we find
no cache for a memcg there on allocation, we initiate the memcg cache
creation (see memcg_kmem_get_cache()).  The cache creation proceeds
asynchronously in memcg_create_kmem_cache() in order to avoid lock
clashes, so there can be several threads trying to create the same
kmem_cache concurrently, but only one of them may succeed.  However, due
to a race in the code, it is not always true.  The point is that the
memcg_caches array can be relocated when we activate kmem accounting for
a memcg (see memcg_update_all_caches(), memcg_update_cache_size()).  If
memcg_update_cache_size() and memcg_create_kmem_cache() proceed
concurrently as described below, we can leak a kmem_cache.

Asume two threads schedule creation of the same kmem_cache.  One of them
successfully creates it.  Another one should fail then, but if
memcg_create_kmem_cache() interleaves with memcg_update_cache_size() as
follows, it won't:

  memcg_create_kmem_cache()             memcg_update_cache_size()
  (called w/o mutexes held)             (called with slab_mutex,
                                         set_limit_mutex held)
  -------------------------             -------------------------

  mutex_lock(&memcg_cache_mutex)

                                        s->memcg_params=kzalloc(...)

  new_cachep=cache_from_memcg_idx(cachep,idx)
  // new_cachep==NULL => proceed to creation

                                        s->memcg_params->memcg_caches[i]
                                            =cur_params->memcg_caches[i]

  // kmem_cache_create_memcg takes slab_mutex
  // so we will hang around until
  // memcg_update_cache_size finishes, but
  // nothing will prevent it from succeeding so
  // memcg_caches[idx] will be overwritten in
  // memcg_register_cache!

  new_cachep = kmem_cache_create_memcg(...)
  mutex_unlock(&memcg_cache_mutex)

Let's fix this by moving the check for existence of the memcg cache to
kmem_cache_create_memcg() to be called under the slab_mutex and make it
return NULL if so.

A similar race is possible when destroying a memcg cache (see
kmem_cache_destroy()).  Since memcg_unregister_cache(), which clears the
pointer in the memcg_caches array, is called w/o protection, we can race
with memcg_update_cache_size() and omit clearing the pointer.  Therefore
memcg_unregister_cache() should be moved before we release the
slab_mutex.

Signed-off-by: Vladimir 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: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 014a4f1..d2da65c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3264,6 +3264,12 @@
 	if (is_root_cache(s))
 		return;
 
+	/*
+	 * Holding the slab_mutex assures nobody will touch the memcg_caches
+	 * array while we are modifying it.
+	 */
+	lockdep_assert_held(&slab_mutex);
+
 	root = s->memcg_params->root_cache;
 	memcg = s->memcg_params->memcg;
 	id = memcg_cache_id(memcg);
@@ -3283,6 +3289,7 @@
 	 * before adding it to the memcg_slab_caches list, otherwise we can
 	 * fail to convert memcg_params_to_cache() while traversing the list.
 	 */
+	VM_BUG_ON(root->memcg_params->memcg_caches[id]);
 	root->memcg_params->memcg_caches[id] = s;
 
 	mutex_lock(&memcg->slab_caches_mutex);
@@ -3299,6 +3306,12 @@
 	if (is_root_cache(s))
 		return;
 
+	/*
+	 * Holding the slab_mutex assures nobody will touch the memcg_caches
+	 * array while we are modifying it.
+	 */
+	lockdep_assert_held(&slab_mutex);
+
 	root = s->memcg_params->root_cache;
 	memcg = s->memcg_params->memcg;
 	id = memcg_cache_id(memcg);
@@ -3312,6 +3325,7 @@
 	 * after removing it from the memcg_slab_caches list, otherwise we can
 	 * fail to convert memcg_params_to_cache() while traversing the list.
 	 */
+	VM_BUG_ON(!root->memcg_params->memcg_caches[id]);
 	root->memcg_params->memcg_caches[id] = NULL;
 
 	css_put(&memcg->css);
@@ -3464,22 +3478,13 @@
 						  struct kmem_cache *cachep)
 {
 	struct kmem_cache *new_cachep;
-	int idx;
 
 	BUG_ON(!memcg_can_account_kmem(memcg));
 
-	idx = memcg_cache_id(memcg);
-
 	mutex_lock(&memcg_cache_mutex);
-	new_cachep = cache_from_memcg_idx(cachep, idx);
-	if (new_cachep)
-		goto out;
-
 	new_cachep = kmem_cache_dup(memcg, cachep);
 	if (new_cachep == NULL)
 		new_cachep = cachep;
-
-out:
 	mutex_unlock(&memcg_cache_mutex);
 	return new_cachep;
 }
diff --git a/mm/slab_common.c b/mm/slab_common.c
index db24ec4..f34707e 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -180,6 +180,18 @@
 	if (err)
 		goto out_unlock;
 
+	if (memcg) {
+		/*
+		 * Since per-memcg caches are created asynchronously on first
+		 * allocation (see memcg_kmem_get_cache()), several threads can
+		 * try to create the same cache, but only one of them may
+		 * succeed. Therefore if we get here and see the cache has
+		 * already been created, we silently return NULL.
+		 */
+		if (cache_from_memcg_idx(parent_cache, memcg_cache_id(memcg)))
+			goto out_unlock;
+	}
+
 	/*
 	 * Some allocators will constraint the set of valid flags to a subset
 	 * of all flags. We expect them to define CACHE_CREATE_MASK in this
@@ -261,11 +273,11 @@
 		list_del(&s->list);
 
 		if (!__kmem_cache_shutdown(s)) {
+			memcg_unregister_cache(s);
 			mutex_unlock(&slab_mutex);
 			if (s->flags & SLAB_DESTROY_BY_RCU)
 				rcu_barrier();
 
-			memcg_unregister_cache(s);
 			memcg_free_cache_params(s);
 			kfree(s->name);
 			kmem_cache_free(kmem_cache, s);