vmscan: page_check_references(): check low order lumpy reclaim properly

If vmscan is under lumpy reclaim mode, it have to ignore referenced bit
for making contenious free pages.  but current page_check_references()
doesn't.

Fix it.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/vmscan.c

@@ -77,6 +77,12 @@ struct scan_control {
 
 	int order;
 
+	/*
+	 * Intend to reclaim enough contenious memory rather than to reclaim
+	 * enough amount memory. I.e, it's the mode for high order allocation.
+	 */
+	bool lumpy_reclaim_mode;
+
 	/* Which cgroup do we reclaim from */
 	struct mem_cgroup *mem_cgroup;
 
@@ -575,7 +581,7 @@ static enum page_references page_check_references(struct page *page,
 	referenced_page = TestClearPageReferenced(page);
 
 	/* Lumpy reclaim - ignore references */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+	if (sc->lumpy_reclaim_mode)
 		return PAGEREF_RECLAIM;
 
 	/*
@@ -1125,7 +1131,6 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 	unsigned long nr_scanned = 0;
 	unsigned long nr_reclaimed = 0;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
-	int lumpy_reclaim = 0;
 
 	while (unlikely(too_many_isolated(zone, file, sc))) {
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -1135,17 +1140,6 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 			return SWAP_CLUSTER_MAX;
 	}
 
-	/*
-	 * If we need a large contiguous chunk of memory, or have
-	 * trouble getting a small set of contiguous pages, we
-	 * will reclaim both active and inactive pages.
-	 *
-	 * We use the same threshold as pageout congestion_wait below.
-	 */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		lumpy_reclaim = 1;
-	else if (sc->order && priority < DEF_PRIORITY - 2)
-		lumpy_reclaim = 1;
 
 	pagevec_init(&pvec, 1);
 
@@ -1158,7 +1152,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		unsigned long nr_freed;
 		unsigned long nr_active;
 		unsigned int count[NR_LRU_LISTS] = { 0, };
-		int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
+		int mode = sc->lumpy_reclaim_mode ? ISOLATE_BOTH : ISOLATE_INACTIVE;
 		unsigned long nr_anon;
 		unsigned long nr_file;
 
@@ -1211,7 +1205,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		 * but that should be acceptable to the caller
 		 */
 		if (nr_freed < nr_taken && !current_is_kswapd() &&
-		    lumpy_reclaim) {
+		    sc->lumpy_reclaim_mode) {
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 			/*
@@ -1639,6 +1633,21 @@ out:
 	}
 }
 
+static void set_lumpy_reclaim_mode(int priority, struct scan_control *sc)
+{
+	/*
+	 * If we need a large contiguous chunk of memory, or have
+	 * trouble getting a small set of contiguous pages, we
+	 * will reclaim both active and inactive pages.
+	 */
+	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+		sc->lumpy_reclaim_mode = 1;
+	else if (sc->order && priority < DEF_PRIORITY - 2)
+		sc->lumpy_reclaim_mode = 1;
+	else
+		sc->lumpy_reclaim_mode = 0;
+}
+
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
@@ -1653,6 +1662,8 @@ static void shrink_zone(int priority, struct zone *zone,
 
 	get_scan_count(zone, sc, nr, priority);
 
+	set_lumpy_reclaim_mode(priority, sc);
+
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
 		for_each_evictable_lru(l) {