From 5660048ccac8735d9bc0a46325a02e6a6518b5b2 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <jweiner@redhat.com>
Date: Thu, 12 Jan 2012 17:17:59 -0800
Subject: mm: move memcg hierarchy reclaim to generic reclaim code

Memory cgroup limit reclaim and traditional global pressure reclaim will
soon share the same code to reclaim from a hierarchical tree of memory
cgroups.

In preparation of this, move the two right next to each other in
shrink_zone().

The mem_cgroup_hierarchical_reclaim() polymath is split into a soft
limit reclaim function, which still does hierarchy walking on its own,
and a limit (shrinking) reclaim function, which relies on generic
reclaim code to walk the hierarchy.

Signed-off-by: Johannes Weiner <jweiner@redhat.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Ying Han <yinghan@google.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/vmscan.c | 43 +++++++++++++++++++++++++++++++++++++++----
 1 file changed, 39 insertions(+), 4 deletions(-)

(limited to 'mm/vmscan.c')

diff --git a/mm/vmscan.c b/mm/vmscan.c
index e0627d07c3a..136c7eb0ad8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2104,12 +2104,43 @@ restart:
 static void shrink_zone(int priority, struct zone *zone,
 			struct scan_control *sc)
 {
-	struct mem_cgroup_zone mz = {
-		.mem_cgroup = sc->target_mem_cgroup,
+	struct mem_cgroup *root = sc->target_mem_cgroup;
+	struct mem_cgroup_reclaim_cookie reclaim = {
 		.zone = zone,
+		.priority = priority,
 	};
+	struct mem_cgroup *memcg;
+
+	if (global_reclaim(sc)) {
+		struct mem_cgroup_zone mz = {
+			.mem_cgroup = NULL,
+			.zone = zone,
+		};
+
+		shrink_mem_cgroup_zone(priority, &mz, sc);
+		return;
+	}
+
+	memcg = mem_cgroup_iter(root, NULL, &reclaim);
+	do {
+		struct mem_cgroup_zone mz = {
+			.mem_cgroup = memcg,
+			.zone = zone,
+		};
 
-	shrink_mem_cgroup_zone(priority, &mz, sc);
+		shrink_mem_cgroup_zone(priority, &mz, sc);
+		/*
+		 * Limit reclaim has historically picked one memcg and
+		 * scanned it with decreasing priority levels until
+		 * nr_to_reclaim had been reclaimed.  This priority
+		 * cycle is thus over after a single memcg.
+		 */
+		if (!global_reclaim(sc)) {
+			mem_cgroup_iter_break(root, memcg);
+			break;
+		}
+		memcg = mem_cgroup_iter(root, memcg, &reclaim);
+	} while (memcg);
 }
 
 /*
@@ -2374,6 +2405,10 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 		.order = 0,
 		.target_mem_cgroup = mem,
 	};
+	struct mem_cgroup_zone mz = {
+		.mem_cgroup = mem,
+		.zone = zone,
+	};
 
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
@@ -2389,7 +2424,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 	 * will pick up pages from other mem cgroup's as well. We hack
 	 * the priority and make it zero.
 	 */
-	shrink_zone(0, zone, &sc);
+	shrink_mem_cgroup_zone(0, &mz, &sc);
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
-- 
cgit v1.2.3