1 files changed, 40 insertions, 16 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index b7ed3767564..adc7e905818 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1177,7 +1177,11 @@ int isolate_lru_page(struct page *page)
 }
 
 /*
- * Are there way too many processes in the direct reclaim path already?
+ * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
+ * then get resheduled. When there are massive number of tasks doing page
+ * allocation, such sleeping direct reclaimers may keep piling up on each CPU,
+ * the LRU list will go small and be scanned faster than necessary, leading to
+ * unnecessary swapping, thrashing and OOM.
  */
 static int too_many_isolated(struct zone *zone, int file,
 		struct scan_control *sc)
@@ -1198,6 +1202,14 @@ static int too_many_isolated(struct zone *zone, int file,
 		isolated = zone_page_state(zone, NR_ISOLATED_ANON);
 	}
 
+	/*
+	 * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
+	 * won't get blocked by normal direct-reclaimers, forming a circular
+	 * deadlock.
+	 */
+	if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS)
+		inactive >>= 3;
+
 	return isolated > inactive;
 }
 
@@ -1679,13 +1691,24 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 
 	if (global_reclaim(sc)) {
 		free  = zone_page_state(zone, NR_FREE_PAGES);
-		/* If we have very few page cache pages,
-		   force-scan anon pages. */
 		if (unlikely(file + free <= high_wmark_pages(zone))) {
+			/*
+			 * If we have very few page cache pages, force-scan
+			 * anon pages.
+			 */
 			fraction[0] = 1;
 			fraction[1] = 0;
 			denominator = 1;
 			goto out;
+		} else if (!inactive_file_is_low_global(zone)) {
+			/*
+			 * There is enough inactive page cache, do not
+			 * reclaim anything from the working set right now.
+			 */
+			fraction[0] = 0;
+			fraction[1] = 1;
+			denominator = 1;
+			goto out;
 		}
 	}
 
@@ -1752,7 +1775,7 @@ out:
 /* Use reclaim/compaction for costly allocs or under memory pressure */
 static bool in_reclaim_compaction(struct scan_control *sc)
 {
-	if (COMPACTION_BUILD && sc->order &&
+	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
 			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
 			 sc->priority < DEF_PRIORITY - 2))
 		return true;
@@ -2005,7 +2028,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			if (zone->all_unreclaimable &&
 					sc->priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
-			if (COMPACTION_BUILD) {
+			if (IS_ENABLED(CONFIG_COMPACTION)) {
 				/*
 				 * If we already have plenty of memory free for
 				 * compaction in this zone, don't free any more.
@@ -2421,7 +2444,8 @@ static bool zone_balanced(struct zone *zone, int order,
 				    balance_gap, classzone_idx, 0))
 		return false;
 
-	if (COMPACTION_BUILD && order && !compaction_suitable(zone, order))
+	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
+	    !compaction_suitable(zone, order))
 		return false;
 
 	return true;
@@ -2546,7 +2570,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 							int *classzone_idx)
 {
-	int all_zones_ok;
+	struct zone *unbalanced_zone;
 	unsigned long balanced;
 	int i;
 	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
@@ -2580,7 +2604,7 @@ loop_again:
 		unsigned long lru_pages = 0;
 		int has_under_min_watermark_zone = 0;
 
-		all_zones_ok = 1;
+		unbalanced_zone = NULL;
 		balanced = 0;
 
 		/*
@@ -2684,7 +2708,7 @@ loop_again:
 			 * Do not reclaim more than needed for compaction.
 			 */
 			testorder = order;
-			if (COMPACTION_BUILD && order &&
+			if (IS_ENABLED(CONFIG_COMPACTION) && order &&
 					compaction_suitable(zone, order) !=
 						COMPACT_SKIPPED)
 				testorder = 0;
@@ -2719,7 +2743,7 @@ loop_again:
 			}
 
 			if (!zone_balanced(zone, testorder, 0, end_zone)) {
-				all_zones_ok = 0;
+				unbalanced_zone = zone;
 				/*
 				 * We are still under min water mark.  This
 				 * means that we have a GFP_ATOMIC allocation
@@ -2752,7 +2776,7 @@ loop_again:
 				pfmemalloc_watermark_ok(pgdat))
 			wake_up(&pgdat->pfmemalloc_wait);
 
-		if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
+		if (!unbalanced_zone || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
 			break;		/* kswapd: all done */
 		/*
 		 * OK, kswapd is getting into trouble.  Take a nap, then take
@@ -2762,7 +2786,7 @@ loop_again:
 			if (has_under_min_watermark_zone)
 				count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
 			else
-				congestion_wait(BLK_RW_ASYNC, HZ/10);
+				wait_iff_congested(unbalanced_zone, BLK_RW_ASYNC, HZ/10);
 		}
 
 		/*
@@ -2781,7 +2805,7 @@ out:
 	 * high-order: Balanced zones must make up at least 25% of the node
 	 *             for the node to be balanced
 	 */
-	if (!(all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))) {
+	if (unbalanced_zone && (!order || !pgdat_balanced(pgdat, balanced, *classzone_idx))) {
 		cond_resched();
 
 		try_to_freeze();
@@ -2951,7 +2975,7 @@ static int kswapd(void *p)
 	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
 	balanced_classzone_idx = classzone_idx;
 	for ( ; ; ) {
-		int ret;
+		bool ret;
 
 		/*
 		 * If the last balance_pgdat was unsuccessful it's unlikely a
@@ -3119,7 +3143,7 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 	int nid;
 
 	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
-		for_each_node_state(nid, N_HIGH_MEMORY) {
+		for_each_node_state(nid, N_MEMORY) {
 			pg_data_t *pgdat = NODE_DATA(nid);
 			const struct cpumask *mask;
 
@@ -3175,7 +3199,7 @@ static int __init kswapd_init(void)
 	int nid;
 
 	swap_setup();
-	for_each_node_state(nid, N_HIGH_MEMORY)
+	for_each_node_state(nid, N_MEMORY)
  		kswapd_run(nid);
 	hotcpu_notifier(cpu_callback, 0);
 	return 0;