Currently, sc.scap_cluster_max has double meanings.

 1) reclaim batch size as isolate_lru_pages()'s argument
 2) reclaim baling out thresolds

The two meanings pretty unrelated. Thus, Let's separate it.
this patch doesn't change any behavior.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/vmscan.c

@@ -55,6 +55,9 @@ struct scan_control {
 	/* Number of pages freed so far during a call to shrink_zones() */
 	unsigned long nr_reclaimed;
 
+	/* How many pages shrink_list() should reclaim */
+	unsigned long nr_to_reclaim;
+
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -1599,6 +1602,7 @@ static void shrink_zone(int priority, struct zone *zone,
 	enum lru_list l;
 	unsigned long nr_reclaimed = sc->nr_reclaimed;
 	unsigned long swap_cluster_max = sc->swap_cluster_max;
+	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	int noswap = 0;
 
@@ -1643,8 +1647,7 @@ static void shrink_zone(int priority, struct zone *zone,
 		 * with multiple processes reclaiming pages, the total
 		 * freeing target can get unreasonably large.
 		 */
-		if (nr_reclaimed > swap_cluster_max &&
-			priority < DEF_PRIORITY && !current_is_kswapd())
+		if (nr_reclaimed > nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 
@@ -1742,6 +1745,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
+	unsigned long writeback_threshold;
 
 	delayacct_freepages_start();
 
@@ -1777,7 +1781,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			}
 		}
 		total_scanned += sc->nr_scanned;
-		if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+		if (sc->nr_reclaimed >= sc->nr_to_reclaim) {
 			ret = sc->nr_reclaimed;
 			goto out;
 		}
@@ -1789,8 +1793,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		 * that's undesirable in laptop mode, where we *want* lumpy
 		 * writeout.  So in laptop mode, write out the whole world.
 		 */
-		if (total_scanned > sc->swap_cluster_max +
-					sc->swap_cluster_max / 2) {
+		writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
+		if (total_scanned > writeback_threshold) {
 			wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
 			sc->may_writepage = 1;
 		}
@@ -1836,6 +1840,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.may_unmap = 1,
 		.may_swap = 1,
 		.swappiness = vm_swappiness,
@@ -1894,6 +1899,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.may_unmap = 1,
 		.may_swap = !noswap,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem_cont,
@@ -1959,6 +1965,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.may_unmap = 1,
 		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		/*
+		 * kswapd doesn't want to be bailed out while reclaim. because
+		 * we want to put equal scanning pressure on each zone.
+		 */
+		.nr_to_reclaim = ULONG_MAX,
 		.swappiness = vm_swappiness,
 		.order = order,
 		.mem_cgroup = NULL,
@@ -2629,6 +2640,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.may_swap = 1,
 		.swap_cluster_max = max_t(unsigned long, nr_pages,
 				       SWAP_CLUSTER_MAX),
+		.nr_to_reclaim = max_t(unsigned long, nr_pages,
+				       SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
 		.swappiness = vm_swappiness,
 		.order = order,