1 files changed, 37 insertions, 36 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9734e62654fa..0cc3c1eb15f5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -502,6 +502,15 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 			sc.nid = 0;
 
 		freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible);
+		/*
+		 * Bail out if someone want to register a new shrinker to
+		 * prevent the regsitration from being stalled for long periods
+		 * by parallel ongoing shrinking.
+		 */
+		if (rwsem_is_contended(&shrinker_rwsem)) {
+			freed = freed ? : 1;
+			break;
+		}
 	}
 
 	up_read(&shrinker_rwsem);
@@ -1384,7 +1393,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
 		if (page_is_file_cache(page) && !PageDirty(page) &&
-		    !__PageMovable(page)) {
+		    !__PageMovable(page) && !PageUnevictable(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
@@ -2111,8 +2120,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
  *   10TB     320        32GB
  */
 static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
-				 struct mem_cgroup *memcg,
-				 struct scan_control *sc, bool actual_reclaim)
+				 struct scan_control *sc, bool trace)
 {
 	enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
@@ -2132,17 +2140,13 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
 	active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
 
-	if (memcg)
-		refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
-	else
-		refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
 	/*
 	 * When refaults are being observed, it means a new workingset
 	 * is being established. Disable active list protection to get
 	 * rid of the stale workingset quickly.
 	 */
-	if (file && actual_reclaim && lruvec->refaults != refaults) {
+	refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
+	if (file && lruvec->refaults != refaults) {
 		inactive_ratio = 0;
 	} else {
 		gb = (inactive + active) >> (30 - PAGE_SHIFT);
@@ -2152,7 +2156,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 			inactive_ratio = 1;
 	}
 
-	if (actual_reclaim)
+	if (trace)
 		trace_mm_vmscan_inactive_list_is_low(pgdat->node_id, sc->reclaim_idx,
 			lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive,
 			lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active,
@@ -2162,12 +2166,10 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 }
 
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
-				 struct lruvec *lruvec, struct mem_cgroup *memcg,
-				 struct scan_control *sc)
+				 struct lruvec *lruvec, struct scan_control *sc)
 {
 	if (is_active_lru(lru)) {
-		if (inactive_list_is_low(lruvec, is_file_lru(lru),
-					 memcg, sc, true))
+		if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true))
 			shrink_active_list(nr_to_scan, lruvec, sc, lru);
 		return 0;
 	}
@@ -2267,7 +2269,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 			 * anonymous pages on the LRU in eligible zones.
 			 * Otherwise, the small LRU gets thrashed.
 			 */
-			if (!inactive_list_is_low(lruvec, false, memcg, sc, false) &&
+			if (!inactive_list_is_low(lruvec, false, sc, false) &&
 			    lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
 					>> sc->priority) {
 				scan_balance = SCAN_ANON;
@@ -2285,7 +2287,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * lruvec even if it has plenty of old anonymous pages unless the
 	 * system is under heavy pressure.
 	 */
-	if (!inactive_list_is_low(lruvec, true, memcg, sc, false) &&
+	if (!inactive_list_is_low(lruvec, true, sc, false) &&
 	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
 		scan_balance = SCAN_FILE;
 		goto out;
@@ -2438,7 +2440,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 				nr[lru] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(lru, nr_to_scan,
-							    lruvec, memcg, sc);
+							    lruvec, sc);
 			}
 		}
 
@@ -2505,7 +2507,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+	if (inactive_list_is_low(lruvec, false, sc, true))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
 }
@@ -2830,12 +2832,8 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat)
 		unsigned long refaults;
 		struct lruvec *lruvec;
 
-		if (memcg)
-			refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
-		else
-			refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
 		lruvec = mem_cgroup_lruvec(pgdat, memcg);
+		refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
 		lruvec->refaults = refaults;
 	} while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
 }
@@ -3183,7 +3181,7 @@ static void age_active_anon(struct pglist_data *pgdat,
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
 
-		if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+		if (inactive_list_is_low(lruvec, false, sc, true))
 			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 					   sc, LRU_ACTIVE_ANON);
 
@@ -3441,19 +3439,18 @@ 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,
@@ -3594,7 +3591,7 @@ 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;
 
@@ -3645,8 +3642,12 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
 		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;