1 files changed, 57 insertions, 14 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 777af57fd8c8..4649929401f8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1083,6 +1083,48 @@ static int too_many_isolated(struct zone *zone, int file,
 }
 
 /*
+ * Returns true if the caller should wait to clean dirty/writeback pages.
+ *
+ * If we are direct reclaiming for contiguous pages and we do not reclaim
+ * everything in the list, try again and wait for writeback IO to complete.
+ * This will stall high-order allocations noticeably. Only do that when really
+ * need to free the pages under high memory pressure.
+ */
+static inline bool should_reclaim_stall(unsigned long nr_taken,
+					unsigned long nr_freed,
+					int priority,
+					int lumpy_reclaim,
+					struct scan_control *sc)
+{
+	int lumpy_stall_priority;
+
+	/* kswapd should not stall on sync IO */
+	if (current_is_kswapd())
+		return false;
+
+	/* Only stall on lumpy reclaim */
+	if (!lumpy_reclaim)
+		return false;
+
+	/* If we have relaimed everything on the isolated list, no stall */
+	if (nr_freed == nr_taken)
+		return false;
+
+	/*
+	 * For high-order allocations, there are two stall thresholds.
+	 * High-cost allocations stall immediately where as lower
+	 * order allocations such as stacks require the scanning
+	 * priority to be much higher before stalling.
+	 */
+	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+		lumpy_stall_priority = DEF_PRIORITY;
+	else
+		lumpy_stall_priority = DEF_PRIORITY / 3;
+
+	return priority <= lumpy_stall_priority;
+}
+
+/*
  * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
  * of reclaimed pages
  */
@@ -1176,14 +1218,9 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		nr_scanned += nr_scan;
 		nr_freed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
 
-		/*
-		 * If we are direct reclaiming for contiguous pages and we do
-		 * not reclaim everything in the list, try again and wait
-		 * for IO to complete. This will stall high-order allocations
-		 * but that should be acceptable to the caller
-		 */
-		if (nr_freed < nr_taken && !current_is_kswapd() &&
-		    lumpy_reclaim) {
+		/* Check if we should syncronously wait for writeback */
+		if (should_reclaim_stall(nr_taken, nr_freed, priority,
+					lumpy_reclaim, sc)) {
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 			/*
@@ -1464,20 +1501,26 @@ static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
 	return low;
 }
 
+static int inactive_list_is_low(struct zone *zone, struct scan_control *sc,
+				int file)
+{
+	if (file)
+		return inactive_file_is_low(zone, sc);
+	else
+		return inactive_anon_is_low(zone, sc);
+}
+
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 	struct zone *zone, struct scan_control *sc, int priority)
 {
 	int file = is_file_lru(lru);
 
-	if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) {
-		shrink_active_list(nr_to_scan, zone, sc, priority, file);
+	if (is_active_lru(lru)) {
+		if (inactive_list_is_low(zone, sc, file))
+		    shrink_active_list(nr_to_scan, zone, sc, priority, file);
 		return 0;
 	}
 
-	if (lru == LRU_ACTIVE_ANON && inactive_anon_is_low(zone, sc)) {
-		shrink_active_list(nr_to_scan, zone, sc, priority, file);
-		return 0;
-	}
 	return shrink_inactive_list(nr_to_scan, zone, sc, priority, file);
 }