3 files changed, 25 insertions, 18 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d66bc8abe0af..8e3bc949ebcc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1826,7 +1826,8 @@ deferred_grow_zone(struct zone *zone, unsigned int order)
 						 first_deferred_pfn)) {
 		pgdat->first_deferred_pfn = ULONG_MAX;
 		pgdat_resize_unlock(pgdat, &flags);
-		return true;
+		/* Retry only once. */
+		return first_deferred_pfn != ULONG_MAX;
 	}
 
 	/*
diff --git a/mm/page_io.c b/mm/page_io.c
index 189415852077..a39aac2f8c8d 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -137,8 +137,10 @@ out:
 	unlock_page(page);
 	WRITE_ONCE(bio->bi_private, NULL);
 	bio_put(bio);
-	blk_wake_io_task(waiter);
-	put_task_struct(waiter);
+	if (waiter) {
+		blk_wake_io_task(waiter);
+		put_task_struct(waiter);
+	}
 }
 
 int generic_swapfile_activate(struct swap_info_struct *sis,
@@ -395,11 +397,12 @@ int swap_readpage(struct page *page, bool synchronous)
 	 * Keep this task valid during swap readpage because the oom killer may
 	 * attempt to access it in the page fault retry time check.
 	 */
-	get_task_struct(current);
-	bio->bi_private = current;
 	bio_set_op_attrs(bio, REQ_OP_READ, 0);
-	if (synchronous)
+	if (synchronous) {
 		bio->bi_opf |= REQ_HIPRI;
+		get_task_struct(current);
+		bio->bi_private = current;
+	}
 	count_vm_event(PSWPIN);
 	bio_get(bio);
 	qc = submit_bio(bio);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7889f583ced9..910e02c793ff 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3644,19 +3644,18 @@ out:
 }
 
 /*
- * pgdat->kswapd_classzone_idx is the highest zone index that a recent
- * allocation request woke kswapd for. When kswapd has not woken recently,
- * the value is MAX_NR_ZONES which is not a valid index. This compares a
- * given classzone and returns it or the highest classzone index kswapd
- * was recently woke for.
+ * The pgdat->kswapd_classzone_idx is used to pass the highest zone index to be
+ * reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is not
+ * a valid index then either kswapd runs for first time or kswapd couldn't sleep
+ * after previous reclaim attempt (node is still unbalanced). In that case
+ * return the zone index of the previous kswapd reclaim cycle.
  */
 static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
-					   enum zone_type classzone_idx)
+					   enum zone_type prev_classzone_idx)
 {
 	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		return classzone_idx;
-
-	return max(pgdat->kswapd_classzone_idx, classzone_idx);
+		return prev_classzone_idx;
+	return pgdat->kswapd_classzone_idx;
 }
 
 static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3797,7 +3796,7 @@ kswapd_try_sleep:
 
 		/* Read the new order and classzone_idx */
 		alloc_order = reclaim_order = pgdat->kswapd_order;
-		classzone_idx = kswapd_classzone_idx(pgdat, 0);
+		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
 		pgdat->kswapd_order = 0;
 		pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
 
@@ -3851,8 +3850,12 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
 	if (!cpuset_zone_allowed(zone, gfp_flags))
 		return;
 	pgdat = zone->zone_pgdat;
-	pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat,
-							   classzone_idx);
+
+	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
+		pgdat->kswapd_classzone_idx = classzone_idx;
+	else
+		pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx,
+						  classzone_idx);
 	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;