1 files changed, 108 insertions, 69 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index c26986c85ce0..79c809895fba 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -262,27 +262,6 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 	return ret;
 }
 
-/* Called without lock on whether page is mapped, so answer is unstable */
-static inline int page_mapping_inuse(struct page *page)
-{
-	struct address_space *mapping;
-
-	/* Page is in somebody's page tables. */
-	if (page_mapped(page))
-		return 1;
-
-	/* Be more reluctant to reclaim swapcache than pagecache */
-	if (PageSwapCache(page))
-		return 1;
-
-	mapping = page_mapping(page);
-	if (!mapping)
-		return 0;
-
-	/* File is mmap'd by somebody? */
-	return mapping_mapped(mapping);
-}
-
 static inline int is_page_cache_freeable(struct page *page)
 {
 	/*
@@ -579,6 +558,65 @@ redo:
 	put_page(page);		/* drop ref from isolate */
 }
 
+enum page_references {
+	PAGEREF_RECLAIM,
+	PAGEREF_RECLAIM_CLEAN,
+	PAGEREF_KEEP,
+	PAGEREF_ACTIVATE,
+};
+
+static enum page_references page_check_references(struct page *page,
+						  struct scan_control *sc)
+{
+	int referenced_ptes, referenced_page;
+	unsigned long vm_flags;
+
+	referenced_ptes = page_referenced(page, 1, sc->mem_cgroup, &vm_flags);
+	referenced_page = TestClearPageReferenced(page);
+
+	/* Lumpy reclaim - ignore references */
+	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+		return PAGEREF_RECLAIM;
+
+	/*
+	 * Mlock lost the isolation race with us.  Let try_to_unmap()
+	 * move the page to the unevictable list.
+	 */
+	if (vm_flags & VM_LOCKED)
+		return PAGEREF_RECLAIM;
+
+	if (referenced_ptes) {
+		if (PageAnon(page))
+			return PAGEREF_ACTIVATE;
+		/*
+		 * All mapped pages start out with page table
+		 * references from the instantiating fault, so we need
+		 * to look twice if a mapped file page is used more
+		 * than once.
+		 *
+		 * Mark it and spare it for another trip around the
+		 * inactive list.  Another page table reference will
+		 * lead to its activation.
+		 *
+		 * Note: the mark is set for activated pages as well
+		 * so that recently deactivated but used pages are
+		 * quickly recovered.
+		 */
+		SetPageReferenced(page);
+
+		if (referenced_page)
+			return PAGEREF_ACTIVATE;
+
+		return PAGEREF_KEEP;
+	}
+
+	/* Reclaim if clean, defer dirty pages to writeback */
+	if (referenced_page)
+		return PAGEREF_RECLAIM_CLEAN;
+
+	return PAGEREF_RECLAIM;
+}
+
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -590,16 +628,15 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 	struct pagevec freed_pvec;
 	int pgactivate = 0;
 	unsigned long nr_reclaimed = 0;
-	unsigned long vm_flags;
 
 	cond_resched();
 
 	pagevec_init(&freed_pvec, 1);
 	while (!list_empty(page_list)) {
+		enum page_references references;
 		struct address_space *mapping;
 		struct page *page;
 		int may_enter_fs;
-		int referenced;
 
 		cond_resched();
 
@@ -641,17 +678,16 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto keep_locked;
 		}
 
-		referenced = page_referenced(page, 1,
-						sc->mem_cgroup, &vm_flags);
-		/*
-		 * In active use or really unfreeable?  Activate it.
-		 * If page which have PG_mlocked lost isoltation race,
-		 * try_to_unmap moves it to unevictable list
-		 */
-		if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
-					referenced && page_mapping_inuse(page)
-					&& !(vm_flags & VM_LOCKED))
+		references = page_check_references(page, sc);
+		switch (references) {
+		case PAGEREF_ACTIVATE:
 			goto activate_locked;
+		case PAGEREF_KEEP:
+			goto keep_locked;
+		case PAGEREF_RECLAIM:
+		case PAGEREF_RECLAIM_CLEAN:
+			; /* try to reclaim the page below */
+		}
 
 		/*
 		 * Anonymous process memory has backing store?
@@ -685,7 +721,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		}
 
 		if (PageDirty(page)) {
-			if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced)
+			if (references == PAGEREF_RECLAIM_CLEAN)
 				goto keep_locked;
 			if (!may_enter_fs)
 				goto keep_locked;
@@ -1350,9 +1386,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 			continue;
 		}
 
-		/* page_referenced clears PageReferenced */
-		if (page_mapping_inuse(page) &&
-		    page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
+		if (page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
 			nr_rotated++;
 			/*
 			 * Identify referenced, file-backed active pages and
@@ -1501,6 +1535,13 @@ 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);
 
+	/* If we have no swap space, do not bother scanning anon pages. */
+	if (!sc->may_swap || (nr_swap_pages <= 0)) {
+		percent[0] = 0;
+		percent[1] = 100;
+		return;
+	}
+
 	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) +
@@ -1598,22 +1639,20 @@ static void shrink_zone(int priority, struct zone *zone,
 	unsigned long nr_reclaimed = sc->nr_reclaimed;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	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. */
-	if (!sc->may_swap || (nr_swap_pages <= 0)) {
-		noswap = 1;
-		percent[0] = 0;
-		percent[1] = 100;
-	} else
-		get_scan_ratio(zone, sc, percent);
+	get_scan_ratio(zone, sc, percent);
 
 	for_each_evictable_lru(l) {
 		int file = is_file_lru(l);
 		unsigned long scan;
 
+		if (percent[file] == 0) {
+			nr[l] = 0;
+			continue;
+		}
+
 		scan = zone_nr_lru_pages(zone, sc, l);
-		if (priority || noswap) {
+		if (priority) {
 			scan >>= priority;
 			scan = (scan * percent[file]) / 100;
 		}
@@ -1694,8 +1733,7 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 				continue;
 			note_zone_scanning_priority(zone, priority);
 
-			if (zone_is_all_unreclaimable(zone) &&
-						priority != DEF_PRIORITY)
+			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
 			sc->all_unreclaimable = 0;
 		} else {
@@ -1922,7 +1960,7 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
 		if (!populated_zone(zone))
 			continue;
 
-		if (zone_is_all_unreclaimable(zone))
+		if (zone->all_unreclaimable)
 			continue;
 
 		if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
@@ -2012,8 +2050,7 @@ loop_again:
 			if (!populated_zone(zone))
 				continue;
 
-			if (zone_is_all_unreclaimable(zone) &&
-			    priority != DEF_PRIORITY)
+			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;
 
 			/*
@@ -2056,13 +2093,9 @@ loop_again:
 			if (!populated_zone(zone))
 				continue;
 
-			if (zone_is_all_unreclaimable(zone) &&
-					priority != DEF_PRIORITY)
+			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;
 
-			if (!zone_watermark_ok(zone, order,
-					high_wmark_pages(zone), end_zone, 0))
-				all_zones_ok = 0;
 			temp_priority[i] = priority;
 			sc.nr_scanned = 0;
 			note_zone_scanning_priority(zone, priority);
@@ -2087,12 +2120,11 @@ loop_again:
 						lru_pages);
 			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
-			if (zone_is_all_unreclaimable(zone))
+			if (zone->all_unreclaimable)
 				continue;
-			if (nr_slab == 0 && zone->pages_scanned >=
-					(zone_reclaimable_pages(zone) * 6))
-					zone_set_flag(zone,
-						      ZONE_ALL_UNRECLAIMABLE);
+			if (nr_slab == 0 &&
+			    zone->pages_scanned >= (zone_reclaimable_pages(zone) * 6))
+				zone->all_unreclaimable = 1;
 			/*
 			 * If we've done a decent amount of scanning and
 			 * the reclaim ratio is low, start doing writepage
@@ -2102,13 +2134,18 @@ loop_again:
 			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
 
-			/*
-			 * We are still under min water mark. it mean we have
-			 * GFP_ATOMIC allocation failure risk. Hurry up!
-			 */
-			if (!zone_watermark_ok(zone, order, min_wmark_pages(zone),
-					      end_zone, 0))
-				has_under_min_watermark_zone = 1;
+			if (!zone_watermark_ok(zone, order,
+					high_wmark_pages(zone), end_zone, 0)) {
+				all_zones_ok = 0;
+				/*
+				 * We are still under min water mark.  This
+				 * means that we have a GFP_ATOMIC allocation
+				 * failure risk. Hurry up!
+				 */
+				if (!zone_watermark_ok(zone, order,
+					    min_wmark_pages(zone), end_zone, 0))
+					has_under_min_watermark_zone = 1;
+			}
 
 		}
 		if (all_zones_ok)
@@ -2550,6 +2587,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	 * and RECLAIM_SWAP.
 	 */
 	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
+	lockdep_set_current_reclaim_state(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
@@ -2593,6 +2631,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 
 	p->reclaim_state = NULL;
 	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
+	lockdep_clear_current_reclaim_state();
 	return sc.nr_reclaimed >= nr_pages;
 }
 
@@ -2615,7 +2654,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	    zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
 		return ZONE_RECLAIM_FULL;
 
-	if (zone_is_all_unreclaimable(zone))
+	if (zone->all_unreclaimable)
 		return ZONE_RECLAIM_FULL;
 
 	/*