memcg: fix direct softlimit reclaim to be called in limit path

Commit d149e3b25d7c ("memcg: add the soft_limit reclaim in global direct
reclaim") adds a softlimit hook to shrink_zones().  By this, soft limit
is called as

   try_to_free_pages()
       do_try_to_free_pages()
           shrink_zones()
               mem_cgroup_soft_limit_reclaim()

Then, direct reclaim is memcg softlimit hint aware, now.

But, the memory cgroup's "limit" path can call softlimit shrinker.

   try_to_free_mem_cgroup_pages()
       do_try_to_free_pages()
           shrink_zones()
               mem_cgroup_soft_limit_reclaim()

This will cause a global reclaim when a memcg hits limit.

This is bug. soft_limit_reclaim() should be called when
scanning_global_lru(sc) == true.

And the commit adds a variable "total_scanned" for counting softlimit
scanned pages....it's not "total".  This patch removes the variable and
update sc->nr_scanned instead of it.  This will affect shrink_slab()'s
scan condition but, global LRU is scanned by softlimit and I think this
change makes sense.

TODO: avoid too much scanning of a zone when softlimit did enough work.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Ying Han <yinghan@google.com>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8ff834e..4f49535 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1995,14 +1995,13 @@ restart:
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, struct zonelist *zonelist,
                                        struct scan_control *sc)
 {
        struct zoneref *z;
        struct zone *zone;
        unsigned long nr_soft_reclaimed;
        unsigned long nr_soft_scanned;
-       unsigned long total_scanned = 0;
 
        for_each_zone_zonelist_nodemask(zone, z, zonelist,
                                        gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2017,19 +2016,23 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
                                continue;
                        if (zone->all_unreclaimable && priority != DEF_PRIORITY)
                                continue;       /* Let kswapd poll it */
+                       /*
+                        * This steals pages from memory cgroups over softlimit
+                        * and returns the number of reclaimed pages and
+                        * scanned pages. This works for global memory pressure
+                        * and balancing, not for a memcg's limit.
+                        */
+                       nr_soft_scanned = 0;
+                       nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+                                               sc->order, sc->gfp_mask,
+                                               &nr_soft_scanned);
+                       sc->nr_reclaimed += nr_soft_reclaimed;
+                       sc->nr_scanned += nr_soft_scanned;
+                       /* need some check for avoid more shrink_zone() */
                }
 
-               nr_soft_scanned = 0;
-               nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
-                                                       sc->order, sc->gfp_mask,
-                                                       &nr_soft_scanned);
-               sc->nr_reclaimed += nr_soft_reclaimed;
-               total_scanned += nr_soft_scanned;
-
                shrink_zone(priority, zone, sc);
        }
-
-       return total_scanned;
 }
 
 static bool zone_reclaimable(struct zone *zone)
@@ -2094,7 +2097,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
                sc->nr_scanned = 0;
                if (!priority)
                        disable_swap_token(sc->mem_cgroup);
-               total_scanned += shrink_zones(priority, zonelist, sc);
+               shrink_zones(priority, zonelist, sc);
                /*
                 * Don't shrink slabs when reclaiming memory from
                 * over limit cgroups