1 files changed, 77 insertions, 66 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d196f46c8808..b07c48b09a93 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -52,6 +52,9 @@ struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
 
+	/* Number of pages freed so far during a call to shrink_zones() */
+	unsigned long nr_reclaimed;
+
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -617,7 +620,6 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 					referenced && page_mapping_inuse(page))
 			goto activate_locked;
 
-#ifdef CONFIG_SWAP
 		/*
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
@@ -625,20 +627,10 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (PageAnon(page) && !PageSwapCache(page)) {
 			if (!(sc->gfp_mask & __GFP_IO))
 				goto keep_locked;
-			switch (try_to_munlock(page)) {
-			case SWAP_FAIL:		/* shouldn't happen */
-			case SWAP_AGAIN:
-				goto keep_locked;
-			case SWAP_MLOCK:
-				goto cull_mlocked;
-			case SWAP_SUCCESS:
-				; /* fall thru'; add to swap cache */
-			}
-			if (!add_to_swap(page, GFP_ATOMIC))
+			if (!add_to_swap(page))
 				goto activate_locked;
 			may_enter_fs = 1;
 		}
-#endif /* CONFIG_SWAP */
 
 		mapping = page_mapping(page);
 
@@ -752,6 +744,8 @@ free_it:
 		continue;
 
 cull_mlocked:
+		if (PageSwapCache(page))
+			try_to_free_swap(page);
 		unlock_page(page);
 		putback_lru_page(page);
 		continue;
@@ -759,7 +753,7 @@ cull_mlocked:
 activate_locked:
 		/* Not a candidate for swapping, so reclaim swap space. */
 		if (PageSwapCache(page) && vm_swap_full())
-			remove_exclusive_swap_page_ref(page);
+			try_to_free_swap(page);
 		VM_BUG_ON(PageActive(page));
 		SetPageActive(page);
 		pgactivate++;
@@ -1173,11 +1167,6 @@ static inline void note_zone_scanning_priority(struct zone *zone, int priority)
 		zone->prev_priority = priority;
 }
 
-static inline int zone_is_near_oom(struct zone *zone)
-{
-	return zone->pages_scanned >= (zone_lru_pages(zone) * 3);
-}
-
 /*
  * This moves pages from the active list to the inactive list.
  *
@@ -1248,6 +1237,13 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		list_add(&page->lru, &l_inactive);
 	}
 
+	/*
+	 * Move the pages to the [file or anon] inactive list.
+	 */
+	pagevec_init(&pvec, 1);
+	pgmoved = 0;
+	lru = LRU_BASE + file * LRU_FILE;
+
 	spin_lock_irq(&zone->lru_lock);
 	/*
 	 * Count referenced pages from currently used mappings as
@@ -1255,15 +1251,9 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * This helps balance scan pressure between file and anonymous
 	 * pages in get_scan_ratio.
 	 */
-	zone->recent_rotated[!!file] += pgmoved;
-
-	/*
-	 * Move the pages to the [file or anon] inactive list.
-	 */
-	pagevec_init(&pvec, 1);
+	if (scan_global_lru(sc))
+		zone->recent_rotated[!!file] += pgmoved;
 
-	pgmoved = 0;
-	lru = LRU_BASE + file * LRU_FILE;
 	while (!list_empty(&l_inactive)) {
 		page = lru_to_page(&l_inactive);
 		prefetchw_prev_lru_page(page, &l_inactive, flags);
@@ -1336,12 +1326,6 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	unsigned long anon_prio, file_prio;
 	unsigned long ap, fp;
 
-	anon  = zone_page_state(zone, NR_ACTIVE_ANON) +
-		zone_page_state(zone, NR_INACTIVE_ANON);
-	file  = zone_page_state(zone, NR_ACTIVE_FILE) +
-		zone_page_state(zone, NR_INACTIVE_FILE);
-	free  = zone_page_state(zone, NR_FREE_PAGES);
-
 	/* If we have no swap space, do not bother scanning anon pages. */
 	if (nr_swap_pages <= 0) {
 		percent[0] = 0;
@@ -1349,6 +1333,12 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 		return;
 	}
 
+	anon  = zone_page_state(zone, NR_ACTIVE_ANON) +
+		zone_page_state(zone, NR_INACTIVE_ANON);
+	file  = zone_page_state(zone, NR_ACTIVE_FILE) +
+		zone_page_state(zone, NR_INACTIVE_FILE);
+	free  = zone_page_state(zone, NR_FREE_PAGES);
+
 	/* If we have very few page cache pages, force-scan anon pages. */
 	if (unlikely(file + free <= zone->pages_high)) {
 		percent[0] = 100;
@@ -1408,14 +1398,15 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
-static unsigned long shrink_zone(int priority, struct zone *zone,
+static void shrink_zone(int priority, struct zone *zone,
 				struct scan_control *sc)
 {
 	unsigned long nr[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
-	unsigned long nr_reclaimed = 0;
 	unsigned long percent[2];	/* anon @ 0; file @ 1 */
 	enum lru_list l;
+	unsigned long nr_reclaimed = sc->nr_reclaimed;
+	unsigned long swap_cluster_max = sc->swap_cluster_max;
 
 	get_scan_ratio(zone, sc, percent);
 
@@ -1431,7 +1422,7 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 			}
 			zone->lru[l].nr_scan += scan;
 			nr[l] = zone->lru[l].nr_scan;
-			if (nr[l] >= sc->swap_cluster_max)
+			if (nr[l] >= swap_cluster_max)
 				zone->lru[l].nr_scan = 0;
 			else
 				nr[l] = 0;
@@ -1450,16 +1441,28 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 					nr[LRU_INACTIVE_FILE]) {
 		for_each_evictable_lru(l) {
 			if (nr[l]) {
-				nr_to_scan = min(nr[l],
-					(unsigned long)sc->swap_cluster_max);
+				nr_to_scan = min(nr[l], swap_cluster_max);
 				nr[l] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(l, nr_to_scan,
-							zone, sc, priority);
+							    zone, sc, priority);
 			}
 		}
+		/*
+		 * On large memory systems, scan >> priority can become
+		 * really large. This is fine for the starting priority;
+		 * we want to put equal scanning pressure on each zone.
+		 * However, if the VM has a harder time of freeing pages,
+		 * with multiple processes reclaiming pages, the total
+		 * freeing target can get unreasonably large.
+		 */
+		if (nr_reclaimed > swap_cluster_max &&
+			priority < DEF_PRIORITY && !current_is_kswapd())
+			break;
 	}
 
+	sc->nr_reclaimed = nr_reclaimed;
+
 	/*
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
@@ -1470,7 +1473,6 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
 
 	throttle_vm_writeout(sc->gfp_mask);
-	return nr_reclaimed;
 }
 
 /*
@@ -1484,16 +1486,13 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
  * b) The zones may be over pages_high but they must go *over* pages_high to
  *    satisfy the `incremental min' zone defense algorithm.
  *
- * Returns the number of reclaimed pages.
- *
  * 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)
 {
 	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
-	unsigned long nr_reclaimed = 0;
 	struct zoneref *z;
 	struct zone *zone;
 
@@ -1524,10 +1523,8 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
 							priority);
 		}
 
-		nr_reclaimed += shrink_zone(priority, zone, sc);
+		shrink_zone(priority, zone, sc);
 	}
-
-	return nr_reclaimed;
 }
 
 /*
@@ -1552,7 +1549,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	int priority;
 	unsigned long ret = 0;
 	unsigned long total_scanned = 0;
-	unsigned long nr_reclaimed = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long lru_pages = 0;
 	struct zoneref *z;
@@ -1580,7 +1576,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
-		nr_reclaimed += shrink_zones(priority, zonelist, sc);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -1588,13 +1584,13 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		if (scan_global_lru(sc)) {
 			shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
 			if (reclaim_state) {
-				nr_reclaimed += reclaim_state->reclaimed_slab;
+				sc->nr_reclaimed += reclaim_state->reclaimed_slab;
 				reclaim_state->reclaimed_slab = 0;
 			}
 		}
 		total_scanned += sc->nr_scanned;
-		if (nr_reclaimed >= sc->swap_cluster_max) {
-			ret = nr_reclaimed;
+		if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+			ret = sc->nr_reclaimed;
 			goto out;
 		}
 
@@ -1617,7 +1613,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
 	if (!sc->all_unreclaimable && scan_global_lru(sc))
-		ret = nr_reclaimed;
+		ret = sc->nr_reclaimed;
 out:
 	/*
 	 * Now that we've scanned all the zones at this priority level, note
@@ -1712,7 +1708,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 	int priority;
 	int i;
 	unsigned long total_scanned;
-	unsigned long nr_reclaimed;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
@@ -1731,7 +1726,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 
 loop_again:
 	total_scanned = 0;
-	nr_reclaimed = 0;
+	sc.nr_reclaimed = 0;
 	sc.may_writepage = !laptop_mode;
 	count_vm_event(PAGEOUTRUN);
 
@@ -1817,11 +1812,11 @@ loop_again:
 			 */
 			if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
 						end_zone, 0))
-				nr_reclaimed += shrink_zone(priority, zone, &sc);
+				shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
 						lru_pages);
-			nr_reclaimed += reclaim_state->reclaimed_slab;
+			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
 			if (zone_is_all_unreclaimable(zone))
 				continue;
@@ -1835,7 +1830,7 @@ loop_again:
 			 * even in laptop mode
 			 */
 			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
-			    total_scanned > nr_reclaimed + nr_reclaimed / 2)
+			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
 		}
 		if (all_zones_ok)
@@ -1853,7 +1848,7 @@ loop_again:
 		 * matches the direct reclaim path behaviour in terms of impact
 		 * on zone->*_priority.
 		 */
-		if (nr_reclaimed >= SWAP_CLUSTER_MAX)
+		if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
 			break;
 	}
 out:
@@ -1872,10 +1867,27 @@ out:
 
 		try_to_freeze();
 
+		/*
+		 * Fragmentation may mean that the system cannot be
+		 * rebalanced for high-order allocations in all zones.
+		 * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
+		 * it means the zones have been fully scanned and are still
+		 * not balanced. For high-order allocations, there is
+		 * little point trying all over again as kswapd may
+		 * infinite loop.
+		 *
+		 * Instead, recheck all watermarks at order-0 as they
+		 * are the most important. If watermarks are ok, kswapd will go
+		 * back to sleep. High-order users can still perform direct
+		 * reclaim if they wish.
+		 */
+		if (sc.nr_reclaimed < SWAP_CLUSTER_MAX)
+			order = sc.order = 0;
+
 		goto loop_again;
 	}
 
-	return nr_reclaimed;
+	return sc.nr_reclaimed;
 }
 
 /*
@@ -2227,7 +2239,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
 	int priority;
-	unsigned long nr_reclaimed = 0;
 	struct scan_control sc = {
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
 		.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
@@ -2260,9 +2271,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		priority = ZONE_RECLAIM_PRIORITY;
 		do {
 			note_zone_scanning_priority(zone, priority);
-			nr_reclaimed += shrink_zone(priority, zone, &sc);
+			shrink_zone(priority, zone, &sc);
 			priority--;
-		} while (priority >= 0 && nr_reclaimed < nr_pages);
+		} while (priority >= 0 && sc.nr_reclaimed < nr_pages);
 	}
 
 	slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
@@ -2286,13 +2297,13 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		 * Update nr_reclaimed by the number of slab pages we
 		 * reclaimed from this zone.
 		 */
-		nr_reclaimed += slab_reclaimable -
+		sc.nr_reclaimed += slab_reclaimable -
 			zone_page_state(zone, NR_SLAB_RECLAIMABLE);
 	}
 
 	p->reclaim_state = NULL;
 	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
-	return nr_reclaimed >= nr_pages;
+	return sc.nr_reclaimed >= nr_pages;
 }
 
 int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
@@ -2472,7 +2483,7 @@ void scan_mapping_unevictable_pages(struct address_space *mapping)
  * back onto @zone's unevictable list.
  */
 #define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size */
-void scan_zone_unevictable_pages(struct zone *zone)
+static void scan_zone_unevictable_pages(struct zone *zone)
 {
 	struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list;
 	unsigned long scan;
@@ -2514,7 +2525,7 @@ void scan_zone_unevictable_pages(struct zone *zone)
  * that has possibly/probably made some previously unevictable pages
  * evictable.
  */
-void scan_all_zones_unevictable_pages(void)
+static void scan_all_zones_unevictable_pages(void)
 {
 	struct zone *zone;