1 files changed, 70 insertions, 66 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index eea668d9cff6..89dd0f742507 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -281,17 +281,34 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 				nr_pages_scanned, lru_pages,
 				max_pass, delta, total_scan);
 
-	while (total_scan >= batch_size) {
+	/*
+	 * Normally, we should not scan less than batch_size objects in one
+	 * pass to avoid too frequent shrinker calls, but if the slab has less
+	 * than batch_size objects in total and we are really tight on memory,
+	 * we will try to reclaim all available objects, otherwise we can end
+	 * up failing allocations although there are plenty of reclaimable
+	 * objects spread over several slabs with usage less than the
+	 * batch_size.
+	 *
+	 * We detect the "tight on memory" situations by looking at the total
+	 * number of objects we want to scan (total_scan). If it is greater
+	 * than the total number of objects on slab (max_pass), we must be
+	 * scanning at high prio and therefore should try to reclaim as much as
+	 * possible.
+	 */
+	while (total_scan >= batch_size ||
+	       total_scan >= max_pass) {
 		unsigned long ret;
+		unsigned long nr_to_scan = min(batch_size, total_scan);
 
-		shrinkctl->nr_to_scan = batch_size;
+		shrinkctl->nr_to_scan = nr_to_scan;
 		ret = shrinker->scan_objects(shrinker, shrinkctl);
 		if (ret == SHRINK_STOP)
 			break;
 		freed += ret;
 
-		count_vm_events(SLABS_SCANNED, batch_size);
-		total_scan -= batch_size;
+		count_vm_events(SLABS_SCANNED, nr_to_scan);
+		total_scan -= nr_to_scan;
 
 		cond_resched();
 	}
@@ -352,16 +369,17 @@ unsigned long shrink_slab(struct shrink_control *shrinkctl,
 	}
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
-		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
-			if (!node_online(shrinkctl->nid))
-				continue;
-
-			if (!(shrinker->flags & SHRINKER_NUMA_AWARE) &&
-			    (shrinkctl->nid != 0))
-				break;
-
+		if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) {
+			shrinkctl->nid = 0;
 			freed += shrink_slab_node(shrinkctl, shrinker,
-				 nr_pages_scanned, lru_pages);
+					nr_pages_scanned, lru_pages);
+			continue;
+		}
+
+		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
+			if (node_online(shrinkctl->nid))
+				freed += shrink_slab_node(shrinkctl, shrinker,
+						nr_pages_scanned, lru_pages);
 
 		}
 	}
@@ -603,7 +621,7 @@ void putback_lru_page(struct page *page)
 	bool is_unevictable;
 	int was_unevictable = PageUnevictable(page);
 
-	VM_BUG_ON(PageLRU(page));
+	VM_BUG_ON_PAGE(PageLRU(page), page);
 
 redo:
 	ClearPageUnevictable(page);
@@ -794,8 +812,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (!trylock_page(page))
 			goto keep;
 
-		VM_BUG_ON(PageActive(page));
-		VM_BUG_ON(page_zone(page) != zone);
+		VM_BUG_ON_PAGE(PageActive(page), page);
+		VM_BUG_ON_PAGE(page_zone(page) != zone, page);
 
 		sc->nr_scanned++;
 
@@ -1079,14 +1097,14 @@ activate_locked:
 		/* Not a candidate for swapping, so reclaim swap space. */
 		if (PageSwapCache(page) && vm_swap_full())
 			try_to_free_swap(page);
-		VM_BUG_ON(PageActive(page));
+		VM_BUG_ON_PAGE(PageActive(page), page);
 		SetPageActive(page);
 		pgactivate++;
 keep_locked:
 		unlock_page(page);
 keep:
 		list_add(&page->lru, &ret_pages);
-		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
+		VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
 	}
 
 	free_hot_cold_page_list(&free_pages, 1);
@@ -1240,7 +1258,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
 
-		VM_BUG_ON(!PageLRU(page));
+		VM_BUG_ON_PAGE(!PageLRU(page), page);
 
 		switch (__isolate_lru_page(page, mode)) {
 		case 0:
@@ -1295,7 +1313,7 @@ int isolate_lru_page(struct page *page)
 {
 	int ret = -EBUSY;
 
-	VM_BUG_ON(!page_count(page));
+	VM_BUG_ON_PAGE(!page_count(page), page);
 
 	if (PageLRU(page)) {
 		struct zone *zone = page_zone(page);
@@ -1366,7 +1384,7 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
 		struct page *page = lru_to_page(page_list);
 		int lru;
 
-		VM_BUG_ON(PageLRU(page));
+		VM_BUG_ON_PAGE(PageLRU(page), page);
 		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
 			spin_unlock_irq(&zone->lru_lock);
@@ -1586,7 +1604,7 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
 		page = lru_to_page(list);
 		lruvec = mem_cgroup_page_lruvec(page, zone);
 
-		VM_BUG_ON(PageLRU(page));
+		VM_BUG_ON_PAGE(PageLRU(page), page);
 		SetPageLRU(page);
 
 		nr_pages = hpage_nr_pages(page);
@@ -2279,7 +2297,12 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	struct zone *zone;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
+	unsigned long lru_pages = 0;
 	bool aborted_reclaim = false;
+	struct reclaim_state *reclaim_state = current->reclaim_state;
+	struct shrink_control shrink = {
+		.gfp_mask = sc->gfp_mask,
+	};
 
 	/*
 	 * If the number of buffer_heads in the machine exceeds the maximum
@@ -2289,6 +2312,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	if (buffer_heads_over_limit)
 		sc->gfp_mask |= __GFP_HIGHMEM;
 
+	nodes_clear(shrink.nodes_to_scan);
+
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
 		if (!populated_zone(zone))
@@ -2300,6 +2325,10 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		if (global_reclaim(sc)) {
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
+
+			lru_pages += zone_reclaimable_pages(zone);
+			node_set(zone_to_nid(zone), shrink.nodes_to_scan);
+
 			if (sc->priority != DEF_PRIORITY &&
 			    !zone_reclaimable(zone))
 				continue;	/* Let kswapd poll it */
@@ -2336,6 +2365,20 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		shrink_zone(zone, sc);
 	}
 
+	/*
+	 * Don't shrink slabs when reclaiming memory from over limit cgroups
+	 * but do shrink slab at least once when aborting reclaim for
+	 * compaction to avoid unevenly scanning file/anon LRU pages over slab
+	 * pages.
+	 */
+	if (global_reclaim(sc)) {
+		shrink_slab(&shrink, sc->nr_scanned, lru_pages);
+		if (reclaim_state) {
+			sc->nr_reclaimed += reclaim_state->reclaimed_slab;
+			reclaim_state->reclaimed_slab = 0;
+		}
+	}
+
 	return aborted_reclaim;
 }
 
@@ -2376,13 +2419,9 @@ static bool all_unreclaimable(struct zonelist *zonelist,
  * 		else, the number of pages reclaimed
  */
 static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
-					struct scan_control *sc,
-					struct shrink_control *shrink)
+					  struct scan_control *sc)
 {
 	unsigned long total_scanned = 0;
-	struct reclaim_state *reclaim_state = current->reclaim_state;
-	struct zoneref *z;
-	struct zone *zone;
 	unsigned long writeback_threshold;
 	bool aborted_reclaim;
 
@@ -2397,32 +2436,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		aborted_reclaim = shrink_zones(zonelist, sc);
 
-		/*
-		 * Don't shrink slabs when reclaiming memory from over limit
-		 * cgroups but do shrink slab at least once when aborting
-		 * reclaim for compaction to avoid unevenly scanning file/anon
-		 * LRU pages over slab pages.
-		 */
-		if (global_reclaim(sc)) {
-			unsigned long lru_pages = 0;
-
-			nodes_clear(shrink->nodes_to_scan);
-			for_each_zone_zonelist(zone, z, zonelist,
-					gfp_zone(sc->gfp_mask)) {
-				if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
-					continue;
-
-				lru_pages += zone_reclaimable_pages(zone);
-				node_set(zone_to_nid(zone),
-					 shrink->nodes_to_scan);
-			}
-
-			shrink_slab(shrink, sc->nr_scanned, lru_pages);
-			if (reclaim_state) {
-				sc->nr_reclaimed += reclaim_state->reclaimed_slab;
-				reclaim_state->reclaimed_slab = 0;
-			}
-		}
 		total_scanned += sc->nr_scanned;
 		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
 			goto out;
@@ -2584,9 +2597,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.target_mem_cgroup = NULL,
 		.nodemask = nodemask,
 	};
-	struct shrink_control shrink = {
-		.gfp_mask = sc.gfp_mask,
-	};
 
 	/*
 	 * Do not enter reclaim if fatal signal was delivered while throttled.
@@ -2600,7 +2610,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 				sc.may_writepage,
 				gfp_mask);
 
-	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
 
@@ -2667,9 +2677,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
 	};
-	struct shrink_control shrink = {
-		.gfp_mask = sc.gfp_mask,
-	};
 
 	/*
 	 * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
@@ -2684,7 +2691,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					    sc.may_writepage,
 					    sc.gfp_mask);
 
-	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
@@ -3340,9 +3347,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 		.order = 0,
 		.priority = DEF_PRIORITY,
 	};
-	struct shrink_control shrink = {
-		.gfp_mask = sc.gfp_mask,
-	};
 	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
 	struct task_struct *p = current;
 	unsigned long nr_reclaimed;
@@ -3352,7 +3356,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	p->reclaim_state = NULL;
 	lockdep_clear_current_reclaim_state();
@@ -3701,7 +3705,7 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages)
 		if (page_evictable(page)) {
 			enum lru_list lru = page_lru_base_type(page);
 
-			VM_BUG_ON(PageActive(page));
+			VM_BUG_ON_PAGE(PageActive(page), page);
 			ClearPageUnevictable(page);
 			del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE);
 			add_page_to_lru_list(page, lruvec, lru);