diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d0e57a3cda1899c156274d53e49e11be42957f87..58a08fc7414aaf4de59b57a924994dfa43452468 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -230,10 +230,30 @@ struct mem_cgroup {
 	 * the counter to account for memory usage
 	 */
 	struct res_counter res;
-	/*
-	 * the counter to account for mem+swap usage.
-	 */
-	struct res_counter memsw;
+
+	union {
+		/*
+		 * the counter to account for mem+swap usage.
+		 */
+		struct res_counter memsw;
+
+		/*
+		 * rcu_freeing is used only when freeing struct mem_cgroup,
+		 * so put it into a union to avoid wasting more memory.
+		 * It must be disjoint from the css field.  It could be
+		 * in a union with the res field, but res plays a much
+		 * larger part in mem_cgroup life than memsw, and might
+		 * be of interest, even at time of free, when debugging.
+		 * So share rcu_head with the less interesting memsw.
+		 */
+		struct rcu_head rcu_freeing;
+		/*
+		 * But when using vfree(), that cannot be done at
+		 * interrupt time, so we must then queue the work.
+		 */
+		struct work_struct work_freeing;
+	};
+
 	/*
 	 * Per cgroup active and inactive list, similar to the
 	 * per zone LRU lists.
@@ -4779,6 +4799,27 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	return NULL;
 }
 
+/*
+ * Helpers for freeing a vzalloc()ed mem_cgroup by RCU,
+ * but in process context.  The work_freeing structure is overlaid
+ * on the rcu_freeing structure, which itself is overlaid on memsw.
+ */
+static void vfree_work(struct work_struct *work)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = container_of(work, struct mem_cgroup, work_freeing);
+	vfree(memcg);
+}
+static void vfree_rcu(struct rcu_head *rcu_head)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
+	INIT_WORK(&memcg->work_freeing, vfree_work);
+	schedule_work(&memcg->work_freeing);
+}
+
 /*
  * At destroying mem_cgroup, references from swap_cgroup can remain.
  * (scanning all at force_empty is too costly...)
@@ -4802,9 +4843,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 
 	free_percpu(memcg->stat);
 	if (sizeof(struct mem_cgroup) < PAGE_SIZE)
-		kfree(memcg);
+		kfree_rcu(memcg, rcu_freeing);
 	else
-		vfree(memcg);
+		call_rcu(&memcg->rcu_freeing, vfree_rcu);
 }
 
 static void mem_cgroup_get(struct mem_cgroup *memcg)