diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a308c8eacf20..43b77363ab8e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1051,8 +1051,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return x;
 }
 
-void mem_cgroup_flush_stats(void);
-void mem_cgroup_flush_stats_ratelimited(void);
+void mem_cgroup_flush_stats(struct mem_cgroup *memcg);
+void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg);
 
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val);
@@ -1563,11 +1563,11 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
-static inline void mem_cgroup_flush_stats(void)
+static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 {
 }
 
-static inline void mem_cgroup_flush_stats_ratelimited(void)
+static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 {
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c5aa0c2cb68b..b08b9cd4a3a8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -670,7 +670,6 @@ 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 atomic_t stats_flush_ongoing = ATOMIC_INIT(0);
 static u64 flush_last_time;
 
 #define FLUSH_TIME (2UL*HZ)
@@ -731,35 +730,40 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 	}
 }
 
-static void do_flush_stats(void)
+static void do_flush_stats(struct mem_cgroup *memcg)
 {
-	/*
-	 * We always flush the entire tree, so concurrent flushers can just
-	 * skip. This avoids a thundering herd problem on the rstat global lock
-	 * from memcg flushers (e.g. reclaim, refault, etc).
-	 */
-	if (atomic_read(&stats_flush_ongoing) ||
-	    atomic_xchg(&stats_flush_ongoing, 1))
+	if (mem_cgroup_is_root(memcg))
+		WRITE_ONCE(flush_last_time, jiffies_64);
+
+	cgroup_rstat_flush(memcg->css.cgroup);
+}
+
+/*
+ * mem_cgroup_flush_stats - flush the stats of a memory cgroup subtree
+ * @memcg: root of the subtree to flush
+ *
+ * Flushing is serialized by the underlying global rstat lock. There is also a
+ * minimum amount of work to be done even if there are no stat updates to flush.
+ * Hence, we only flush the stats if the updates delta exceeds a threshold. This
+ * avoids unnecessary work and contention on the underlying lock.
+ */
+void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_disabled())
 		return;
 
-	WRITE_ONCE(flush_last_time, jiffies_64);
+	if (!memcg)
+		memcg = root_mem_cgroup;
 
-	cgroup_rstat_flush(root_mem_cgroup->css.cgroup);
-
-	atomic_set(&stats_flush_ongoing, 0);
+	if (memcg_should_flush_stats(memcg))
+		do_flush_stats(memcg);
 }
 
-void mem_cgroup_flush_stats(void)
-{
-	if (memcg_should_flush_stats(root_mem_cgroup))
-		do_flush_stats();
-}
-
-void mem_cgroup_flush_stats_ratelimited(void)
+void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 {
 	/* Only flush if the periodic flusher is one full cycle late */
 	if (time_after64(jiffies_64, READ_ONCE(flush_last_time) + 2*FLUSH_TIME))
-		mem_cgroup_flush_stats();
+		mem_cgroup_flush_stats(memcg);
 }
 
 static void flush_memcg_stats_dwork(struct work_struct *w)
@@ -768,7 +772,7 @@ static void flush_memcg_stats_dwork(struct work_struct *w)
 	 * Deliberately ignore memcg_should_flush_stats() here so that flushing
 	 * in latency-sensitive paths is as cheap as possible.
 	 */
-	do_flush_stats();
+	do_flush_stats(root_mem_cgroup);
 	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
 }
 
@@ -1643,7 +1647,7 @@ static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 	 *
 	 * Current memory state:
 	 */
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		u64 size;
@@ -4193,7 +4197,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v)
 	int nid;
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
 		seq_printf(m, "%s=%lu", stat->name,
@@ -4274,7 +4278,7 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 
 	BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats));
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
 		unsigned long nr;
@@ -4770,7 +4774,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
 	*pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
@@ -6865,7 +6869,7 @@ static int memory_numa_stat_show(struct seq_file *m, void *v)
 	int i;
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		int nid;
@@ -8096,7 +8100,11 @@ bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
 			break;
 		}
 
-		cgroup_rstat_flush(memcg->css.cgroup);
+		/*
+		 * mem_cgroup_flush_stats() ignores small changes. Use
+		 * do_flush_stats() directly to get accurate stats for charging.
+		 */
+		do_flush_stats(memcg);
 		pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE;
 		if (pages < max)
 			continue;
@@ -8161,8 +8169,10 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
 static u64 zswap_current_read(struct cgroup_subsys_state *css,
 			      struct cftype *cft)
 {
-	cgroup_rstat_flush(css->cgroup);
-	return memcg_page_state(mem_cgroup_from_css(css), MEMCG_ZSWAP_B);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	mem_cgroup_flush_stats(memcg);
+	return memcg_page_state(memcg, MEMCG_ZSWAP_B);
 }
 
 static int zswap_max_show(struct seq_file *m, void *v)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f0eba9ef3332..b4ca3563bcf4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2226,7 +2226,7 @@ static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc)
 	 * Flush the memory cgroup stats, so that we read accurate per-memcg
 	 * lruvec stats for heuristics.
 	 */
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(sc->target_mem_cgroup);
 
 	/*
 	 * Determine the scan balance between anon and file LRUs.
diff --git a/mm/workingset.c b/mm/workingset.c
index 6b9871f5a2e8..2a2a34234df9 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -464,8 +464,12 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset)
 
 	rcu_read_unlock();
 
-	/* Flush stats (and potentially sleep) outside the RCU read section */
-	mem_cgroup_flush_stats_ratelimited();
+	/*
+	 * Flush stats (and potentially sleep) outside the RCU read section.
+	 * XXX: With per-memcg flushing and thresholding, is ratelimiting
+	 * still needed here?
+	 */
+	mem_cgroup_flush_stats_ratelimited(eviction_memcg);
 
 	eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
 	refault = atomic_long_read(&eviction_lruvec->nonresident_age);
@@ -676,7 +680,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 		struct lruvec *lruvec;
 		int i;
 
-		mem_cgroup_flush_stats();
+		mem_cgroup_flush_stats(sc->memcg);
 		lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
 		for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
 			pages += lruvec_page_state_local(lruvec,
diff --git a/mm/zswap.c b/mm/zswap.c
index 015425ed9003..ac31fec176e9 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -641,7 +641,7 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
 		return 0;
 
 #ifdef CONFIG_MEMCG_KMEM
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 	nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
 	nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED);
 #else