diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f4ec4e7ca4cd2b64f9cfb2ea8845eba90373e549..930de943727117043c0274f35cbe6e70d5eb8160 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2091,6 +2091,7 @@ struct memcg_stock_pcp {
 #define FLUSHING_CACHED_CHARGE	(0)
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
+static DEFINE_MUTEX(percpu_charge_mutex);
 
 /*
  * Try to consume stocked charge on this cpu. If success, one page is consumed
@@ -2197,8 +2198,7 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
 
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
-		if (mem_cgroup_same_or_subtree(root_mem, stock->cached) &&
-				test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
+		if (test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
 			flush_work(&stock->work);
 	}
 out:
@@ -2213,14 +2213,22 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
  */
 static void drain_all_stock_async(struct mem_cgroup *root_mem)
 {
+	/*
+	 * If someone calls draining, avoid adding more kworker runs.
+	 */
+	if (!mutex_trylock(&percpu_charge_mutex))
+		return;
 	drain_all_stock(root_mem, false);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /* This is a synchronous drain interface. */
 static void drain_all_stock_sync(struct mem_cgroup *root_mem)
 {
 	/* called when force_empty is called */
+	mutex_lock(&percpu_charge_mutex);
 	drain_all_stock(root_mem, true);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /*