diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 03c503def835..c5aa0c2cb68b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -631,6 +631,9 @@ struct memcg_vmstats_percpu {
 	/* Cgroup1: threshold notifications & softlimit tree updates */
 	unsigned long		nr_page_events;
 	unsigned long		targets[MEM_CGROUP_NTARGETS];
+
+	/* Stats updates since the last flush */
+	unsigned int		stats_updates;
 };
 
 struct memcg_vmstats {
@@ -645,6 +648,9 @@ struct memcg_vmstats {
 	/* Pending child counts during tree propagation */
 	long			state_pending[MEMCG_NR_STAT];
 	unsigned long		events_pending[NR_MEMCG_EVENTS];
+
+	/* Stats updates since the last flush */
+	atomic64_t		stats_updates;
 };
 
 /*
@@ -664,9 +670,7 @@ struct memcg_vmstats {
  */
 static void flush_memcg_stats_dwork(struct work_struct *w);
 static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
-static DEFINE_PER_CPU(unsigned int, stats_updates);
 static atomic_t stats_flush_ongoing = ATOMIC_INIT(0);
-static atomic_t stats_flush_threshold = ATOMIC_INIT(0);
 static u64 flush_last_time;
 
 #define FLUSH_TIME (2UL*HZ)
@@ -693,26 +697,37 @@ static void memcg_stats_unlock(void)
 	preempt_enable_nested();
 }
 
+
+static bool memcg_should_flush_stats(struct mem_cgroup *memcg)
+{
+	return atomic64_read(&memcg->vmstats->stats_updates) >
+		MEMCG_CHARGE_BATCH * num_online_cpus();
+}
+
 static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 {
+	int cpu = smp_processor_id();
 	unsigned int x;
 
 	if (!val)
 		return;
 
-	cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id());
+	cgroup_rstat_updated(memcg->css.cgroup, cpu);
+
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
+		x = __this_cpu_add_return(memcg->vmstats_percpu->stats_updates,
+					  abs(val));
+
+		if (x < MEMCG_CHARGE_BATCH)
+			continue;
 
-	x = __this_cpu_add_return(stats_updates, abs(val));
-	if (x > MEMCG_CHARGE_BATCH) {
 		/*
-		 * If stats_flush_threshold exceeds the threshold
-		 * (>num_online_cpus()), cgroup stats update will be triggered
-		 * in __mem_cgroup_flush_stats(). Increasing this var further
-		 * is redundant and simply adds overhead in atomic update.
+		 * If @memcg is already flush-able, increasing stats_updates is
+		 * redundant. Avoid the overhead of the atomic update.
 		 */
-		if (atomic_read(&stats_flush_threshold) <= num_online_cpus())
-			atomic_add(x / MEMCG_CHARGE_BATCH, &stats_flush_threshold);
-		__this_cpu_write(stats_updates, 0);
+		if (!memcg_should_flush_stats(memcg))
+			atomic64_add(x, &memcg->vmstats->stats_updates);
+		__this_cpu_write(memcg->vmstats_percpu->stats_updates, 0);
 	}
 }
 
@@ -731,13 +746,12 @@ static void do_flush_stats(void)
 
 	cgroup_rstat_flush(root_mem_cgroup->css.cgroup);
 
-	atomic_set(&stats_flush_threshold, 0);
 	atomic_set(&stats_flush_ongoing, 0);
 }
 
 void mem_cgroup_flush_stats(void)
 {
-	if (atomic_read(&stats_flush_threshold) > num_online_cpus())
+	if (memcg_should_flush_stats(root_mem_cgroup))
 		do_flush_stats();
 }
 
@@ -751,8 +765,8 @@ void mem_cgroup_flush_stats_ratelimited(void)
 static void flush_memcg_stats_dwork(struct work_struct *w)
 {
 	/*
-	 * Always flush here so that flushing in latency-sensitive paths is
-	 * as cheap as possible.
+	 * Deliberately ignore memcg_should_flush_stats() here so that flushing
+	 * in latency-sensitive paths is as cheap as possible.
 	 */
 	do_flush_stats();
 	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
@@ -5788,6 +5802,10 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 			}
 		}
 	}
+	statc->stats_updates = 0;
+	/* We are in a per-cpu loop here, only do the atomic write once */
+	if (atomic64_read(&memcg->vmstats->stats_updates))
+		atomic64_set(&memcg->vmstats->stats_updates, 0);
 }
 
 #ifdef CONFIG_MMU