1 files changed, 151 insertions, 62 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index ba8228e0a80..613e89f471d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -148,8 +148,8 @@ static struct zone_reclaim_stat *get_reclaim_stat(struct zone *zone,
 	return &zone->reclaim_stat;
 }
 
-static unsigned long zone_nr_pages(struct zone *zone, struct scan_control *sc,
-				   enum lru_list lru)
+static unsigned long zone_nr_lru_pages(struct zone *zone,
+				struct scan_control *sc, enum lru_list lru)
 {
 	if (!scanning_global_lru(sc))
 		return mem_cgroup_zone_nr_pages(sc->mem_cgroup, zone, lru);
@@ -286,7 +286,12 @@ static inline int page_mapping_inuse(struct page *page)
 
 static inline int is_page_cache_freeable(struct page *page)
 {
-	return page_count(page) - !!page_has_private(page) == 2;
+	/*
+	 * A freeable page cache page is referenced only by the caller
+	 * that isolated the page, the page cache radix tree and
+	 * optional buffer heads at page->private.
+	 */
+	return page_count(page) - page_has_private(page) == 2;
 }
 
 static int may_write_to_queue(struct backing_dev_info *bdi)
@@ -361,7 +366,6 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 	 * block, for some throttling. This happens by accident, because
 	 * swap_backing_dev_info is bust: it doesn't reflect the
 	 * congestion state of the swapdevs.  Easy to fix, if needed.
-	 * See swapfile.c:page_queue_congested().
 	 */
 	if (!is_page_cache_freeable(page))
 		return PAGE_KEEP;
@@ -531,7 +535,7 @@ redo:
 		 * unevictable page on [in]active list.
 		 * We know how to handle that.
 		 */
-		lru = active + page_is_file_cache(page);
+		lru = active + page_lru_base_type(page);
 		lru_cache_add_lru(page, lru);
 	} else {
 		/*
@@ -821,7 +825,7 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 	if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
 		return ret;
 
-	if (mode != ISOLATE_BOTH && (!page_is_file_cache(page) != !file))
+	if (mode != ISOLATE_BOTH && page_is_file_cache(page) != file)
 		return ret;
 
 	/*
@@ -935,6 +939,16 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			/* Check that we have not crossed a zone boundary. */
 			if (unlikely(page_zone_id(cursor_page) != zone_id))
 				continue;
+
+			/*
+			 * If we don't have enough swap space, reclaiming of
+			 * anon page which don't already have a swap slot is
+			 * pointless.
+			 */
+			if (nr_swap_pages <= 0 && PageAnon(cursor_page) &&
+					!PageSwapCache(cursor_page))
+				continue;
+
 			if (__isolate_lru_page(cursor_page, mode, file) == 0) {
 				list_move(&cursor_page->lru, dst);
 				mem_cgroup_del_lru(cursor_page);
@@ -961,7 +975,7 @@ static unsigned long isolate_pages_global(unsigned long nr,
 	if (file)
 		lru += LRU_FILE;
 	return isolate_lru_pages(nr, &z->lru[lru].list, dst, scanned, order,
-								mode, !!file);
+								mode, file);
 }
 
 /*
@@ -976,7 +990,7 @@ static unsigned long clear_active_flags(struct list_head *page_list,
 	struct page *page;
 
 	list_for_each_entry(page, page_list, lru) {
-		lru = page_is_file_cache(page);
+		lru = page_lru_base_type(page);
 		if (PageActive(page)) {
 			lru += LRU_ACTIVE;
 			ClearPageActive(page);
@@ -1034,6 +1048,31 @@ int isolate_lru_page(struct page *page)
 }
 
 /*
+ * Are there way too many processes in the direct reclaim path already?
+ */
+static int too_many_isolated(struct zone *zone, int file,
+		struct scan_control *sc)
+{
+	unsigned long inactive, isolated;
+
+	if (current_is_kswapd())
+		return 0;
+
+	if (!scanning_global_lru(sc))
+		return 0;
+
+	if (file) {
+		inactive = zone_page_state(zone, NR_INACTIVE_FILE);
+		isolated = zone_page_state(zone, NR_ISOLATED_FILE);
+	} else {
+		inactive = zone_page_state(zone, NR_INACTIVE_ANON);
+		isolated = zone_page_state(zone, NR_ISOLATED_ANON);
+	}
+
+	return isolated > inactive;
+}
+
+/*
  * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
  * of reclaimed pages
  */
@@ -1048,6 +1087,14 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	int lumpy_reclaim = 0;
 
+	while (unlikely(too_many_isolated(zone, file, sc))) {
+		congestion_wait(WRITE, HZ/10);
+
+		/* We are about to die and free our memory. Return now. */
+		if (fatal_signal_pending(current))
+			return SWAP_CLUSTER_MAX;
+	}
+
 	/*
 	 * If we need a large contiguous chunk of memory, or have
 	 * trouble getting a small set of contiguous pages, we
@@ -1072,10 +1119,26 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		unsigned long nr_active;
 		unsigned int count[NR_LRU_LISTS] = { 0, };
 		int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
+		unsigned long nr_anon;
+		unsigned long nr_file;
 
 		nr_taken = sc->isolate_pages(sc->swap_cluster_max,
 			     &page_list, &nr_scan, sc->order, mode,
 				zone, sc->mem_cgroup, 0, file);
+
+		if (scanning_global_lru(sc)) {
+			zone->pages_scanned += nr_scan;
+			if (current_is_kswapd())
+				__count_zone_vm_events(PGSCAN_KSWAPD, zone,
+						       nr_scan);
+			else
+				__count_zone_vm_events(PGSCAN_DIRECT, zone,
+						       nr_scan);
+		}
+
+		if (nr_taken == 0)
+			goto done;
+
 		nr_active = clear_active_flags(&page_list, count);
 		__count_vm_events(PGDEACTIVATE, nr_active);
 
@@ -1088,8 +1151,10 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		__mod_zone_page_state(zone, NR_INACTIVE_ANON,
 						-count[LRU_INACTIVE_ANON]);
 
-		if (scanning_global_lru(sc))
-			zone->pages_scanned += nr_scan;
+		nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
+		nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
+		__mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon);
+		__mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file);
 
 		reclaim_stat->recent_scanned[0] += count[LRU_INACTIVE_ANON];
 		reclaim_stat->recent_scanned[0] += count[LRU_ACTIVE_ANON];
@@ -1123,18 +1188,12 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		}
 
 		nr_reclaimed += nr_freed;
+
 		local_irq_disable();
-		if (current_is_kswapd()) {
-			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
+		if (current_is_kswapd())
 			__count_vm_events(KSWAPD_STEAL, nr_freed);
-		} else if (scanning_global_lru(sc))
-			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
-
 		__count_zone_vm_events(PGSTEAL, zone, nr_freed);
 
-		if (nr_taken == 0)
-			goto done;
-
 		spin_lock(&zone->lru_lock);
 		/*
 		 * Put back any unfreeable pages.
@@ -1153,8 +1212,8 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 			SetPageLRU(page);
 			lru = page_lru(page);
 			add_page_to_lru_list(zone, page, lru);
-			if (PageActive(page)) {
-				int file = !!page_is_file_cache(page);
+			if (is_active_lru(lru)) {
+				int file = is_file_lru(lru);
 				reclaim_stat->recent_rotated[file]++;
 			}
 			if (!pagevec_add(&pvec, page)) {
@@ -1163,10 +1222,13 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 				spin_lock_irq(&zone->lru_lock);
 			}
 		}
+		__mod_zone_page_state(zone, NR_ISOLATED_ANON, -nr_anon);
+		__mod_zone_page_state(zone, NR_ISOLATED_FILE, -nr_file);
+
   	} while (nr_scanned < max_scan);
-	spin_unlock(&zone->lru_lock);
+
 done:
-	local_irq_enable();
+	spin_unlock_irq(&zone->lru_lock);
 	pagevec_release(&pvec);
 	return nr_reclaimed;
 }
@@ -1215,15 +1277,10 @@ static void move_active_pages_to_lru(struct zone *zone,
 
 	while (!list_empty(list)) {
 		page = lru_to_page(list);
-		prefetchw_prev_lru_page(page, list, flags);
 
 		VM_BUG_ON(PageLRU(page));
 		SetPageLRU(page);
 
-		VM_BUG_ON(!PageActive(page));
-		if (!is_active_lru(lru))
-			ClearPageActive(page);	/* we are de-activating */
-
 		list_move(&page->lru, &zone->lru[lru].list);
 		mem_cgroup_add_lru_list(page, lru);
 		pgmoved++;
@@ -1244,7 +1301,7 @@ static void move_active_pages_to_lru(struct zone *zone,
 static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 			struct scan_control *sc, int priority, int file)
 {
-	unsigned long pgmoved;
+	unsigned long nr_taken;
 	unsigned long pgscanned;
 	unsigned long vm_flags;
 	LIST_HEAD(l_hold);	/* The pages which were snipped off */
@@ -1252,10 +1309,11 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	LIST_HEAD(l_inactive);
 	struct page *page;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+	unsigned long nr_rotated = 0;
 
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
-	pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
+	nr_taken = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
 					ISOLATE_ACTIVE, zone,
 					sc->mem_cgroup, 1, file);
 	/*
@@ -1265,16 +1323,16 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	if (scanning_global_lru(sc)) {
 		zone->pages_scanned += pgscanned;
 	}
-	reclaim_stat->recent_scanned[!!file] += pgmoved;
+	reclaim_stat->recent_scanned[file] += nr_taken;
 
 	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	if (file)
-		__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
+		__mod_zone_page_state(zone, NR_ACTIVE_FILE, -nr_taken);
 	else
-		__mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
+		__mod_zone_page_state(zone, NR_ACTIVE_ANON, -nr_taken);
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
 	spin_unlock_irq(&zone->lru_lock);
 
-	pgmoved = 0;  /* count referenced (mapping) mapped pages */
 	while (!list_empty(&l_hold)) {
 		cond_resched();
 		page = lru_to_page(&l_hold);
@@ -1288,7 +1346,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		/* page_referenced clears PageReferenced */
 		if (page_mapping_inuse(page) &&
 		    page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
-			pgmoved++;
+			nr_rotated++;
 			/*
 			 * Identify referenced, file-backed active pages and
 			 * give them one more trip around the active list. So
@@ -1304,6 +1362,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 			}
 		}
 
+		ClearPageActive(page);	/* we are de-activating */
 		list_add(&page->lru, &l_inactive);
 	}
 
@@ -1317,13 +1376,13 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * helps balance scan pressure between file and anonymous pages in
 	 * get_scan_ratio.
 	 */
-	reclaim_stat->recent_rotated[!!file] += pgmoved;
+	reclaim_stat->recent_rotated[file] += nr_rotated;
 
 	move_active_pages_to_lru(zone, &l_active,
 						LRU_ACTIVE + file * LRU_FILE);
 	move_active_pages_to_lru(zone, &l_inactive,
 						LRU_BASE   + file * LRU_FILE);
-
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
 	spin_unlock_irq(&zone->lru_lock);
 }
 
@@ -1429,10 +1488,10 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	unsigned long ap, fp;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
-	anon  = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) +
-		zone_nr_pages(zone, sc, LRU_INACTIVE_ANON);
-	file  = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) +
-		zone_nr_pages(zone, sc, LRU_INACTIVE_FILE);
+	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
+	file  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
 
 	if (scanning_global_lru(sc)) {
 		free  = zone_page_state(zone, NR_FREE_PAGES);
@@ -1526,6 +1585,7 @@ static void shrink_zone(int priority, struct zone *zone,
 	enum lru_list l;
 	unsigned long nr_reclaimed = sc->nr_reclaimed;
 	unsigned long swap_cluster_max = sc->swap_cluster_max;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	int noswap = 0;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
@@ -1540,17 +1600,14 @@ static void shrink_zone(int priority, struct zone *zone,
 		int file = is_file_lru(l);
 		unsigned long scan;
 
-		scan = zone_nr_pages(zone, sc, l);
+		scan = zone_nr_lru_pages(zone, sc, l);
 		if (priority || noswap) {
 			scan >>= priority;
 			scan = (scan * percent[file]) / 100;
 		}
-		if (scanning_global_lru(sc))
-			nr[l] = nr_scan_try_batch(scan,
-						  &zone->lru[l].nr_saved_scan,
-						  swap_cluster_max);
-		else
-			nr[l] = scan;
+		nr[l] = nr_scan_try_batch(scan,
+					  &reclaim_stat->nr_saved_scan[l],
+					  swap_cluster_max);
 	}
 
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
@@ -1685,7 +1742,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
 
-			lru_pages += zone_lru_pages(zone);
+			lru_pages += zone_reclaimable_pages(zone);
 		}
 	}
 
@@ -1902,7 +1959,7 @@ loop_again:
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
-			lru_pages += zone_lru_pages(zone);
+			lru_pages += zone_reclaimable_pages(zone);
 		}
 
 		/*
@@ -1946,7 +2003,7 @@ loop_again:
 			if (zone_is_all_unreclaimable(zone))
 				continue;
 			if (nr_slab == 0 && zone->pages_scanned >=
-						(zone_lru_pages(zone) * 6))
+					(zone_reclaimable_pages(zone) * 6))
 					zone_set_flag(zone,
 						      ZONE_ALL_UNRECLAIMABLE);
 			/*
@@ -2113,12 +2170,39 @@ void wakeup_kswapd(struct zone *zone, int order)
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
-unsigned long global_lru_pages(void)
+/*
+ * The reclaimable count would be mostly accurate.
+ * The less reclaimable pages may be
+ * - mlocked pages, which will be moved to unevictable list when encountered
+ * - mapped pages, which may require several travels to be reclaimed
+ * - dirty pages, which is not "instantly" reclaimable
+ */
+unsigned long global_reclaimable_pages(void)
+{
+	int nr;
+
+	nr = global_page_state(NR_ACTIVE_FILE) +
+	     global_page_state(NR_INACTIVE_FILE);
+
+	if (nr_swap_pages > 0)
+		nr += global_page_state(NR_ACTIVE_ANON) +
+		      global_page_state(NR_INACTIVE_ANON);
+
+	return nr;
+}
+
+unsigned long zone_reclaimable_pages(struct zone *zone)
 {
-	return global_page_state(NR_ACTIVE_ANON)
-		+ global_page_state(NR_ACTIVE_FILE)
-		+ global_page_state(NR_INACTIVE_ANON)
-		+ global_page_state(NR_INACTIVE_FILE);
+	int nr;
+
+	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
+	     zone_page_state(zone, NR_INACTIVE_FILE);
+
+	if (nr_swap_pages > 0)
+		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
+		      zone_page_state(zone, NR_INACTIVE_ANON);
+
+	return nr;
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -2133,6 +2217,7 @@ static void shrink_all_zones(unsigned long nr_pages, int prio,
 {
 	struct zone *zone;
 	unsigned long nr_reclaimed = 0;
+	struct zone_reclaim_stat *reclaim_stat;
 
 	for_each_populated_zone(zone) {
 		enum lru_list l;
@@ -2149,11 +2234,14 @@ static void shrink_all_zones(unsigned long nr_pages, int prio,
 						l == LRU_ACTIVE_FILE))
 				continue;
 
-			zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1;
-			if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) {
+			reclaim_stat = get_reclaim_stat(zone, sc);
+			reclaim_stat->nr_saved_scan[l] +=
+						(lru_pages >> prio) + 1;
+			if (reclaim_stat->nr_saved_scan[l]
+						>= nr_pages || pass > 3) {
 				unsigned long nr_to_scan;
 
-				zone->lru[l].nr_saved_scan = 0;
+				reclaim_stat->nr_saved_scan[l] = 0;
 				nr_to_scan = min(nr_pages, lru_pages);
 				nr_reclaimed += shrink_list(l, nr_to_scan, zone,
 								sc, prio);
@@ -2190,7 +2278,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 
 	current->reclaim_state = &reclaim_state;
 
-	lru_pages = global_lru_pages();
+	lru_pages = global_reclaimable_pages();
 	nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
 	/* If slab caches are huge, it's better to hit them first */
 	while (nr_slab >= lru_pages) {
@@ -2232,7 +2320,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 
 			reclaim_state.reclaimed_slab = 0;
 			shrink_slab(sc.nr_scanned, sc.gfp_mask,
-					global_lru_pages());
+				    global_reclaimable_pages());
 			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
 			if (sc.nr_reclaimed >= nr_pages)
 				goto out;
@@ -2249,7 +2337,8 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 	if (!sc.nr_reclaimed) {
 		do {
 			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
+			shrink_slab(nr_pages, sc.gfp_mask,
+				    global_reclaimable_pages());
 			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
 		} while (sc.nr_reclaimed < nr_pages &&
 				reclaim_state.reclaimed_slab > 0);
@@ -2569,7 +2658,7 @@ static void check_move_unevictable_page(struct page *page, struct zone *zone)
 retry:
 	ClearPageUnevictable(page);
 	if (page_evictable(page, NULL)) {
-		enum lru_list l = LRU_INACTIVE_ANON + page_is_file_cache(page);
+		enum lru_list l = page_lru_base_type(page);
 
 		__dec_zone_state(zone, NR_UNEVICTABLE);
 		list_move(&page->lru, &zone->lru[l].list);