diff --git a/mm/swap.c b/mm/swap.c
index 66e3c5033688..5341ae93861f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -713,9 +713,10 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
  */
 void lru_add_drain_all(void)
 {
+	static seqcount_t seqcount = SEQCNT_ZERO(seqcount);
 	static DEFINE_MUTEX(lock);
 	static struct cpumask has_work;
-	int cpu;
+	int cpu, seq;
 
 	/*
 	 * Make sure nobody triggers this path before mm_percpu_wq is fully
@@ -724,7 +725,19 @@ void lru_add_drain_all(void)
 	if (WARN_ON(!mm_percpu_wq))
 		return;
 
+	seq = raw_read_seqcount_latch(&seqcount);
+
 	mutex_lock(&lock);
+
+	/*
+	 * Piggyback on drain started and finished while we waited for lock:
+	 * all pages pended at the time of our enter were drained from vectors.
+	 */
+	if (__read_seqcount_retry(&seqcount, seq))
+		goto done;
+
+	raw_write_seqcount_latch(&seqcount);
+
 	cpumask_clear(&has_work);
 
 	for_each_online_cpu(cpu) {
@@ -745,6 +758,7 @@ void lru_add_drain_all(void)
 	for_each_cpu(cpu, &has_work)
 		flush_work(&per_cpu(lru_add_drain_work, cpu));
 
+done:
 	mutex_unlock(&lock);
 }
 #else