1 files changed, 31 insertions, 16 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index faa0a088f9cc..4f49535d4cd3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1124,8 +1124,20 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
                                         nr_lumpy_dirty++;
                                 scan++;
                         } else {
-                                /* the page is freed already. */
-                                if (!page_count(cursor_page))
+                                /*
+                                 * Check if the page is freed already.
+                                 *
+                                 * We can't use page_count() as that
+                                 * requires compound_head and we don't
+                                 * have a pin on the page here. If a
+                                 * page is tail, we may or may not
+                                 * have isolated the head, so assume
+                                 * it's not free, it'd be tricky to
+                                 * track the head status without a
+                                 * page pin.
+                                 */
+                                if (!PageTail(cursor_page) &&
+                                    !atomic_read(&cursor_page->_count))
                                         continue;
                                 break;
                         }
@@ -1983,14 +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) {
@@ -2005,19 +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)
@@ -2081,8 +2096,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
         for (priority = DEF_PRIORITY; priority >= 0; priority--) {
                 sc->nr_scanned = 0;
                 if (!priority)
-                        disable_swap_token();
-                total_scanned += shrink_zones(priority, zonelist, sc);
+                        disable_swap_token(sc->mem_cgroup);
+                shrink_zones(priority, zonelist, sc);
                 /*
                  * Don't shrink slabs when reclaiming memory from
                  * over limit cgroups
@@ -2407,7 +2422,7 @@ loop_again:
 
                 /* The swap token gets in the way of swapout... */
                 if (!priority)
-                        disable_swap_token();
+                        disable_swap_token(NULL);
 
                 all_zones_ok = 1;
                 balanced = 0;