1 files changed, 181 insertions, 59 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 440a733fe2e9..72babac71dea 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -61,6 +61,8 @@ struct scan_control {
 	 * In this context, it doesn't matter that we scan the
 	 * whole list at once. */
 	int swap_cluster_max;
+
+	int swappiness;
 };
 
 /*
@@ -108,7 +110,7 @@ struct shrinker {
  * From 0 .. 100.  Higher means more swappy.
  */
 int vm_swappiness = 60;
-static long total_memory;
+long vm_total_pages;	/* The total number of pages which the VM controls */
 
 static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
@@ -288,11 +290,23 @@ static void handle_write_error(struct address_space *mapping,
 	unlock_page(page);
 }
 
+/* possible outcome of pageout() */
+typedef enum {
+	/* failed to write page out, page is locked */
+	PAGE_KEEP,
+	/* move page to the active list, page is locked */
+	PAGE_ACTIVATE,
+	/* page has been sent to the disk successfully, page is unlocked */
+	PAGE_SUCCESS,
+	/* page is clean and locked */
+	PAGE_CLEAN,
+} pageout_t;
+
 /*
  * pageout is called by shrink_page_list() for each dirty page.
  * Calls ->writepage().
  */
-pageout_t pageout(struct page *page, struct address_space *mapping)
+static pageout_t pageout(struct page *page, struct address_space *mapping)
 {
 	/*
 	 * If the page is dirty, only perform writeback if that write
@@ -337,6 +351,8 @@ pageout_t pageout(struct page *page, struct address_space *mapping)
 		struct writeback_control wbc = {
 			.sync_mode = WB_SYNC_NONE,
 			.nr_to_write = SWAP_CLUSTER_MAX,
+			.range_start = 0,
+			.range_end = LLONG_MAX,
 			.nonblocking = 1,
 			.for_reclaim = 1,
 		};
@@ -727,7 +743,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		 * how much memory
 		 * is mapped.
 		 */
-		mapped_ratio = (sc->nr_mapped * 100) / total_memory;
+		mapped_ratio = (sc->nr_mapped * 100) / vm_total_pages;
 
 		/*
 		 * Now decide how much we really want to unmap some pages.  The
@@ -741,7 +757,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		 * A 100% value of vm_swappiness overrides this algorithm
 		 * altogether.
 		 */
-		swap_tendency = mapped_ratio / 2 + distress + vm_swappiness;
+		swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
 
 		/*
 		 * Now use this metric to decide whether to start moving mapped
@@ -957,6 +973,7 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 		.may_writepage = !laptop_mode,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.may_swap = 1,
+		.swappiness = vm_swappiness,
 	};
 
 	inc_page_state(allocstall);
@@ -1021,10 +1038,6 @@ out:
  * For kswapd, balance_pgdat() will work across all this node's zones until
  * they are all at pages_high.
  *
- * If `nr_pages' is non-zero then it is the number of pages which are to be
- * reclaimed, regardless of the zone occupancies.  This is a software suspend
- * special.
- *
  * Returns the number of pages which were actually freed.
  *
  * There is special handling here for zones which are full of pinned pages.
@@ -1042,10 +1055,8 @@ out:
  * the page allocator fallback scheme to ensure that aging of pages is balanced
  * across the zones.
  */
-static unsigned long balance_pgdat(pg_data_t *pgdat, unsigned long nr_pages,
-				int order)
+static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 {
-	unsigned long to_free = nr_pages;
 	int all_zones_ok;
 	int priority;
 	int i;
@@ -1055,7 +1066,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, unsigned long nr_pages,
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.may_swap = 1,
-		.swap_cluster_max = nr_pages ? nr_pages : SWAP_CLUSTER_MAX,
+		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.swappiness = vm_swappiness,
 	};
 
 loop_again:
@@ -1082,31 +1094,26 @@ loop_again:
 
 		all_zones_ok = 1;
 
-		if (nr_pages == 0) {
-			/*
-			 * Scan in the highmem->dma direction for the highest
-			 * zone which needs scanning
-			 */
-			for (i = pgdat->nr_zones - 1; i >= 0; i--) {
-				struct zone *zone = pgdat->node_zones + i;
+		/*
+		 * Scan in the highmem->dma direction for the highest
+		 * zone which needs scanning
+		 */
+		for (i = pgdat->nr_zones - 1; i >= 0; i--) {
+			struct zone *zone = pgdat->node_zones + i;
 
-				if (!populated_zone(zone))
-					continue;
+			if (!populated_zone(zone))
+				continue;
 
-				if (zone->all_unreclaimable &&
-						priority != DEF_PRIORITY)
-					continue;
+			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
+				continue;
 
-				if (!zone_watermark_ok(zone, order,
-						zone->pages_high, 0, 0)) {
-					end_zone = i;
-					goto scan;
-				}
+			if (!zone_watermark_ok(zone, order, zone->pages_high,
+					       0, 0)) {
+				end_zone = i;
+				goto scan;
 			}
-			goto out;
-		} else {
-			end_zone = pgdat->nr_zones - 1;
 		}
+		goto out;
 scan:
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
@@ -1133,11 +1140,9 @@ scan:
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;
 
-			if (nr_pages == 0) {	/* Not software suspend */
-				if (!zone_watermark_ok(zone, order,
-						zone->pages_high, end_zone, 0))
-					all_zones_ok = 0;
-			}
+			if (!zone_watermark_ok(zone, order, zone->pages_high,
+					       end_zone, 0))
+				all_zones_ok = 0;
 			zone->temp_priority = priority;
 			if (zone->prev_priority > priority)
 				zone->prev_priority = priority;
@@ -1162,8 +1167,6 @@ scan:
 			    total_scanned > nr_reclaimed + nr_reclaimed / 2)
 				sc.may_writepage = 1;
 		}
-		if (nr_pages && to_free > nr_reclaimed)
-			continue;	/* swsusp: need to do more work */
 		if (all_zones_ok)
 			break;		/* kswapd: all done */
 		/*
@@ -1179,7 +1182,7 @@ scan:
 		 * matches the direct reclaim path behaviour in terms of impact
 		 * on zone->*_priority.
 		 */
-		if ((nr_reclaimed >= SWAP_CLUSTER_MAX) && !nr_pages)
+		if (nr_reclaimed >= SWAP_CLUSTER_MAX)
 			break;
 	}
 out:
@@ -1261,7 +1264,7 @@ static int kswapd(void *p)
 		}
 		finish_wait(&pgdat->kswapd_wait, &wait);
 
-		balance_pgdat(pgdat, 0, order);
+		balance_pgdat(pgdat, order);
 	}
 	return 0;
 }
@@ -1290,35 +1293,154 @@ void wakeup_kswapd(struct zone *zone, int order)
 
 #ifdef CONFIG_PM
 /*
- * Try to free `nr_pages' of memory, system-wide.  Returns the number of freed
- * pages.
+ * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
+ * from LRU lists system-wide, for given pass and priority, and returns the
+ * number of reclaimed pages
+ *
+ * For pass > 3 we also try to shrink the LRU lists that contain a few pages
+ */
+static unsigned long shrink_all_zones(unsigned long nr_pages, int pass,
+				      int prio, struct scan_control *sc)
+{
+	struct zone *zone;
+	unsigned long nr_to_scan, ret = 0;
+
+	for_each_zone(zone) {
+
+		if (!populated_zone(zone))
+			continue;
+
+		if (zone->all_unreclaimable && prio != DEF_PRIORITY)
+			continue;
+
+		/* For pass = 0 we don't shrink the active list */
+		if (pass > 0) {
+			zone->nr_scan_active += (zone->nr_active >> prio) + 1;
+			if (zone->nr_scan_active >= nr_pages || pass > 3) {
+				zone->nr_scan_active = 0;
+				nr_to_scan = min(nr_pages, zone->nr_active);
+				shrink_active_list(nr_to_scan, zone, sc);
+			}
+		}
+
+		zone->nr_scan_inactive += (zone->nr_inactive >> prio) + 1;
+		if (zone->nr_scan_inactive >= nr_pages || pass > 3) {
+			zone->nr_scan_inactive = 0;
+			nr_to_scan = min(nr_pages, zone->nr_inactive);
+			ret += shrink_inactive_list(nr_to_scan, zone, sc);
+			if (ret >= nr_pages)
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Try to free `nr_pages' of memory, system-wide, and return the number of
+ * freed pages.
+ *
+ * Rather than trying to age LRUs the aim is to preserve the overall
+ * LRU order by reclaiming preferentially
+ * inactive > active > active referenced > active mapped
  */
 unsigned long shrink_all_memory(unsigned long nr_pages)
 {
-	pg_data_t *pgdat;
-	unsigned long nr_to_free = nr_pages;
+	unsigned long lru_pages, nr_slab;
 	unsigned long ret = 0;
-	unsigned retry = 2;
-	struct reclaim_state reclaim_state = {
-		.reclaimed_slab = 0,
+	int pass;
+	struct reclaim_state reclaim_state;
+	struct zone *zone;
+	struct scan_control sc = {
+		.gfp_mask = GFP_KERNEL,
+		.may_swap = 0,
+		.swap_cluster_max = nr_pages,
+		.may_writepage = 1,
+		.swappiness = vm_swappiness,
 	};
 
 	current->reclaim_state = &reclaim_state;
-repeat:
-	for_each_online_pgdat(pgdat) {
-		unsigned long freed;
 
-		freed = balance_pgdat(pgdat, nr_to_free, 0);
-		ret += freed;
-		nr_to_free -= freed;
-		if ((long)nr_to_free <= 0)
+	lru_pages = 0;
+	for_each_zone(zone)
+		lru_pages += zone->nr_active + zone->nr_inactive;
+
+	nr_slab = read_page_state(nr_slab);
+	/* If slab caches are huge, it's better to hit them first */
+	while (nr_slab >= lru_pages) {
+		reclaim_state.reclaimed_slab = 0;
+		shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+		if (!reclaim_state.reclaimed_slab)
 			break;
+
+		ret += reclaim_state.reclaimed_slab;
+		if (ret >= nr_pages)
+			goto out;
+
+		nr_slab -= reclaim_state.reclaimed_slab;
 	}
-	if (retry-- && ret < nr_pages) {
-		blk_congestion_wait(WRITE, HZ/5);
-		goto repeat;
+
+	/*
+	 * We try to shrink LRUs in 5 passes:
+	 * 0 = Reclaim from inactive_list only
+	 * 1 = Reclaim from active list but don't reclaim mapped
+	 * 2 = 2nd pass of type 1
+	 * 3 = Reclaim mapped (normal reclaim)
+	 * 4 = 2nd pass of type 3
+	 */
+	for (pass = 0; pass < 5; pass++) {
+		int prio;
+
+		/* Needed for shrinking slab caches later on */
+		if (!lru_pages)
+			for_each_zone(zone) {
+				lru_pages += zone->nr_active;
+				lru_pages += zone->nr_inactive;
+			}
+
+		/* Force reclaiming mapped pages in the passes #3 and #4 */
+		if (pass > 2) {
+			sc.may_swap = 1;
+			sc.swappiness = 100;
+		}
+
+		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
+			unsigned long nr_to_scan = nr_pages - ret;
+
+			sc.nr_mapped = read_page_state(nr_mapped);
+			sc.nr_scanned = 0;
+
+			ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
+			if (ret >= nr_pages)
+				goto out;
+
+			reclaim_state.reclaimed_slab = 0;
+			shrink_slab(sc.nr_scanned, sc.gfp_mask, lru_pages);
+			ret += reclaim_state.reclaimed_slab;
+			if (ret >= nr_pages)
+				goto out;
+
+			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
+				blk_congestion_wait(WRITE, HZ / 10);
+		}
+
+		lru_pages = 0;
 	}
+
+	/*
+	 * If ret = 0, we could not shrink LRUs, but there may be something
+	 * in slab caches
+	 */
+	if (!ret)
+		do {
+			reclaim_state.reclaimed_slab = 0;
+			shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+			ret += reclaim_state.reclaimed_slab;
+		} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+
+out:
 	current->reclaim_state = NULL;
+
 	return ret;
 }
 #endif
@@ -1360,7 +1482,6 @@ static int __init kswapd_init(void)
 		pgdat->kswapd = find_task_by_pid(pid);
 		read_unlock(&tasklist_lock);
 	}
-	total_memory = nr_free_pagecache_pages();
 	hotcpu_notifier(cpu_callback, 0);
 	return 0;
 }
@@ -1416,6 +1537,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.swap_cluster_max = max_t(unsigned long, nr_pages,
 					SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
+		.swappiness = vm_swappiness,
 	};
 
 	disable_swap_token();