1 files changed, 66 insertions, 40 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index faa0a088f9cc..5ed24b94c5e6 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
@@ -2311,7 +2326,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
                 return true;
 
         /* Check the watermark levels */
-        for (i = 0; i < pgdat->nr_zones; i++) {
+        for (i = 0; i <= classzone_idx; i++) {
                 struct zone *zone = pgdat->node_zones + i;
 
                 if (!populated_zone(zone))
@@ -2329,7 +2344,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
                 }
 
                 if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone),
-                                                        classzone_idx, 0))
+                                                        i, 0))
                         all_zones_ok = false;
                 else
                         balanced += zone->present_pages;
@@ -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;
@@ -2436,7 +2451,6 @@ loop_again:
                         if (!zone_watermark_ok_safe(zone, order,
                                         high_wmark_pages(zone), 0, 0)) {
                                 end_zone = i;
-                                *classzone_idx = i;
                                 break;
                         }
                 }
@@ -2495,18 +2509,18 @@ loop_again:
                                 KSWAPD_ZONE_BALANCE_GAP_RATIO);
                         if (!zone_watermark_ok_safe(zone, order,
                                         high_wmark_pages(zone) + balance_gap,
-                                        end_zone, 0))
+                                        end_zone, 0)) {
                                 shrink_zone(priority, zone, &sc);
-                        reclaim_state->reclaimed_slab = 0;
-                        nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
-                        sc.nr_reclaimed += reclaim_state->reclaimed_slab;
-                        total_scanned += sc.nr_scanned;
 
-                        if (zone->all_unreclaimable)
-                                continue;
-                        if (nr_slab == 0 &&
-                            !zone_reclaimable(zone))
-                                zone->all_unreclaimable = 1;
+                                reclaim_state->reclaimed_slab = 0;
+                                nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
+                                sc.nr_reclaimed += reclaim_state->reclaimed_slab;
+                                total_scanned += sc.nr_scanned;
+
+                                if (nr_slab == 0 && !zone_reclaimable(zone))
+                                        zone->all_unreclaimable = 1;
+                        }
+
                         /*
                          * If we've done a decent amount of scanning and
                          * the reclaim ratio is low, start doing writepage
@@ -2516,6 +2530,12 @@ loop_again:
                             total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
                                 sc.may_writepage = 1;
 
+                        if (zone->all_unreclaimable) {
+                                if (end_zone && end_zone == i)
+                                        end_zone--;
+                                continue;
+                        }
+
                         if (!zone_watermark_ok_safe(zone, order,
                                         high_wmark_pages(zone), end_zone, 0)) {
                                 all_zones_ok = 0;
@@ -2694,8 +2714,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
  */
 static int kswapd(void *p)
 {
-        unsigned long order;
-        int classzone_idx;
+        unsigned long order, new_order;
+        int classzone_idx, new_classzone_idx;
         pg_data_t *pgdat = (pg_data_t*)p;
         struct task_struct *tsk = current;
 
@@ -2725,17 +2745,23 @@ static int kswapd(void *p)
         tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
         set_freezable();
 
-        order = 0;
-        classzone_idx = MAX_NR_ZONES - 1;
+        order = new_order = 0;
+        classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
         for ( ; ; ) {
-                unsigned long new_order;
-                int new_classzone_idx;
                 int ret;
 
-                new_order = pgdat->kswapd_max_order;
-                new_classzone_idx = pgdat->classzone_idx;
-                pgdat->kswapd_max_order = 0;
-                pgdat->classzone_idx = MAX_NR_ZONES - 1;
+                /*
+                 * If the last balance_pgdat was unsuccessful it's unlikely a
+                 * new request of a similar or harder type will succeed soon
+                 * so consider going to sleep on the basis we reclaimed at
+                 */
+                if (classzone_idx >= new_classzone_idx && order == new_order) {
+                        new_order = pgdat->kswapd_max_order;
+                        new_classzone_idx = pgdat->classzone_idx;
+                        pgdat->kswapd_max_order =  0;
+                        pgdat->classzone_idx = pgdat->nr_zones - 1;
+                }
+
                 if (order < new_order || classzone_idx > new_classzone_idx) {
                         /*
                          * Don't sleep if someone wants a larger 'order'
@@ -2748,7 +2774,7 @@ static int kswapd(void *p)
                         order = pgdat->kswapd_max_order;
                         classzone_idx = pgdat->classzone_idx;
                         pgdat->kswapd_max_order = 0;
-                        pgdat->classzone_idx = MAX_NR_ZONES - 1;
+                        pgdat->classzone_idx = pgdat->nr_zones - 1;
                 }
 
                 ret = try_to_freeze();