vmscan: kswapd carefully call compaction

With CONFIG_COMPACTION enabled, kswapd does not try to free contiguous
free pages, even when it is woken for a higher order request.

This could be bad for eg.  jumbo frame network allocations, which are done
from interrupt context and cannot compact memory themselves.  Higher than
before allocation failure rates in the network receive path have been
observed in kernels with compaction enabled.

Teach kswapd to defragment the memory zones in a node, but only if
required and compaction is not deferred in a zone.

[akpm@linux-foundation.org: reduce scope of zones_need_compaction]
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Hillf Danton <dhillf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 45 insertions, 18 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index d9ebebe1a2a..36f0f61f4a2 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -675,44 +675,61 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 
 
 /* Compact all zones within a node */
-static int compact_node(int nid)
+static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 {
 	int zoneid;
-	pg_data_t *pgdat;
 	struct zone *zone;
 
-	if (nid < 0 || nid >= nr_node_ids || !node_online(nid))
-		return -EINVAL;
-	pgdat = NODE_DATA(nid);
-
 	/* Flush pending updates to the LRU lists */
 	lru_add_drain_all();
 
 	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
-		struct compact_control cc = {
-			.nr_freepages = 0,
-			.nr_migratepages = 0,
-			.order = -1,
-			.sync = true,
-		};
 
 		zone = &pgdat->node_zones[zoneid];
 		if (!populated_zone(zone))
 			continue;
 
-		cc.zone = zone;
-		INIT_LIST_HEAD(&cc.freepages);
-		INIT_LIST_HEAD(&cc.migratepages);
+		cc->nr_freepages = 0;
+		cc->nr_migratepages = 0;
+		cc->zone = zone;
+		INIT_LIST_HEAD(&cc->freepages);
+		INIT_LIST_HEAD(&cc->migratepages);
 
-		compact_zone(zone, &cc);
+		if (cc->order < 0 || !compaction_deferred(zone))
+			compact_zone(zone, cc);
 
-		VM_BUG_ON(!list_empty(&cc.freepages));
-		VM_BUG_ON(!list_empty(&cc.migratepages));
+		VM_BUG_ON(!list_empty(&cc->freepages));
+		VM_BUG_ON(!list_empty(&cc->migratepages));
 	}
 
 	return 0;
 }
 
+int compact_pgdat(pg_data_t *pgdat, int order)
+{
+	struct compact_control cc = {
+		.order = order,
+		.sync = false,
+	};
+
+	return __compact_pgdat(pgdat, &cc);
+}
+
+static int compact_node(int nid)
+{
+	pg_data_t *pgdat;
+	struct compact_control cc = {
+		.order = -1,
+		.sync = true,
+	};
+
+	if (nid < 0 || nid >= nr_node_ids || !node_online(nid))
+		return -EINVAL;
+	pgdat = NODE_DATA(nid);
+
+	return __compact_pgdat(pgdat, &cc);
+}
+
 /* Compact all nodes in the system */
 static int compact_nodes(void)
 {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d7dad2a4e69..b2b4c4a0ada 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2919,6 +2919,8 @@ out:
 	 * and it is potentially going to sleep here.
 	 */
 	if (order) {
+		int zones_need_compaction = 1;
+
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
@@ -2939,9 +2941,17 @@ out:
 				goto loop_again;
 			}
 
+			/* Check if the memory needs to be defragmented. */
+			if (zone_watermark_ok(zone, order,
+				    low_wmark_pages(zone), *classzone_idx, 0))
+				zones_need_compaction = 0;
+
 			/* If balanced, clear the congested flag */
 			zone_clear_flag(zone, ZONE_CONGESTED);
 		}
+
+		if (zones_need_compaction)
+			compact_pgdat(pgdat, order);
 	}
 
 	/*