1 files changed, 57 insertions, 10 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index fb9584641ac7..090bfb605ecf 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -951,7 +951,7 @@ out:
 	return freed;
 }
 
-void drop_slab_node(int nid)
+static void drop_slab_node(int nid)
 {
 	unsigned long freed;
 	int shift = 0;
@@ -1021,6 +1021,39 @@ static void handle_write_error(struct address_space *mapping,
 	unlock_page(page);
 }
 
+static bool skip_throttle_noprogress(pg_data_t *pgdat)
+{
+	int reclaimable = 0, write_pending = 0;
+	int i;
+
+	/*
+	 * If kswapd is disabled, reschedule if necessary but do not
+	 * throttle as the system is likely near OOM.
+	 */
+	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+		return true;
+
+	/*
+	 * If there are a lot of dirty/writeback pages then do not
+	 * throttle as throttling will occur when the pages cycle
+	 * towards the end of the LRU if still under writeback.
+	 */
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		struct zone *zone = pgdat->node_zones + i;
+
+		if (!populated_zone(zone))
+			continue;
+
+		reclaimable += zone_reclaimable_pages(zone);
+		write_pending += zone_page_state_snapshot(zone,
+						  NR_ZONE_WRITE_PENDING);
+	}
+	if (2 * write_pending <= reclaimable)
+		return true;
+
+	return false;
+}
+
 void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
 {
 	wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason];
@@ -1056,8 +1089,16 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
 		}
 
 		break;
+	case VMSCAN_THROTTLE_CONGESTED:
+		fallthrough;
 	case VMSCAN_THROTTLE_NOPROGRESS:
-		timeout = HZ/2;
+		if (skip_throttle_noprogress(pgdat)) {
+			cond_resched();
+			return;
+		}
+
+		timeout = 1;
+
 		break;
 	case VMSCAN_THROTTLE_ISOLATED:
 		timeout = HZ/50;
@@ -3321,7 +3362,7 @@ again:
 	if (!current_is_kswapd() && current_may_throttle() &&
 	    !sc->hibernation_mode &&
 	    test_bit(LRUVEC_CONGESTED, &target_lruvec->flags))
-		reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED);
 
 	if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
 				    sc))
@@ -3386,16 +3427,16 @@ static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc)
 	}
 
 	/*
-	 * Do not throttle kswapd on NOPROGRESS as it will throttle on
-	 * VMSCAN_THROTTLE_WRITEBACK if there are too many pages under
-	 * writeback and marked for immediate reclaim at the tail of
-	 * the LRU.
+	 * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will
+	 * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages
+	 * under writeback and marked for immediate reclaim at the tail of the
+	 * LRU.
 	 */
-	if (current_is_kswapd())
+	if (current_is_kswapd() || cgroup_reclaim(sc))
 		return;
 
 	/* Throttle if making no progress at high prioities. */
-	if (sc->priority < DEF_PRIORITY - 2)
+	if (sc->priority == 1 && !sc->nr_reclaimed)
 		reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS);
 }
 
@@ -3415,6 +3456,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	unsigned long nr_soft_scanned;
 	gfp_t orig_mask;
 	pg_data_t *last_pgdat = NULL;
+	pg_data_t *first_pgdat = NULL;
 
 	/*
 	 * If the number of buffer_heads in the machine exceeds the maximum
@@ -3478,14 +3520,19 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			/* need some check for avoid more shrink_zone() */
 		}
 
+		if (!first_pgdat)
+			first_pgdat = zone->zone_pgdat;
+
 		/* See comment about same check for global reclaim above */
 		if (zone->zone_pgdat == last_pgdat)
 			continue;
 		last_pgdat = zone->zone_pgdat;
 		shrink_node(zone->zone_pgdat, sc);
-		consider_reclaim_throttle(zone->zone_pgdat, sc);
 	}
 
+	if (first_pgdat)
+		consider_reclaim_throttle(first_pgdat, sc);
+
 	/*
 	 * Restore to original mask to avoid the impact on the caller if we
 	 * promoted it to __GFP_HIGHMEM.