1 files changed, 230 insertions, 111 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 440a733fe2e9..ff2ebe9458a3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -34,6 +34,7 @@
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
 #include <linux/delay.h>
+#include <linux/kthread.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -46,8 +47,6 @@ struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
 
-	unsigned long nr_mapped;	/* From page_state */
-
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -61,6 +60,8 @@ 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 +109,7 @@ 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);
@@ -214,7 +215,7 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 				break;
 			if (shrink_ret < nr_before)
 				ret += nr_before - shrink_ret;
-			mod_page_state(slabs_scanned, this_scan);
+			count_vm_events(SLABS_SCANNED, this_scan);
 			total_scan -= this_scan;
 
 			cond_resched();
@@ -288,11 +289,23 @@ 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 +350,8 @@ 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,
 		};
@@ -554,7 +569,7 @@ keep:
 	list_splice(&ret_pages, page_list);
 	if (pagevec_count(&freed_pvec))
 		__pagevec_release_nonlru(&freed_pvec);
-	mod_page_state(pgactivate, pgactivate);
+	count_vm_events(PGACTIVATE, pgactivate);
 	return nr_reclaimed;
 }
 
@@ -644,11 +659,11 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		nr_reclaimed += nr_freed;
 		local_irq_disable();
 		if (current_is_kswapd()) {
-			__mod_page_state_zone(zone, pgscan_kswapd, nr_scan);
-			__mod_page_state(kswapd_steal, nr_freed);
+			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
+			__count_vm_events(KSWAPD_STEAL, nr_freed);
 		} else
-			__mod_page_state_zone(zone, pgscan_direct, nr_scan);
-		__mod_page_state_zone(zone, pgsteal, nr_freed);
+			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
+		__count_vm_events(PGACTIVATE, nr_freed);
 
 		if (nr_taken == 0)
 			goto done;
@@ -727,7 +742,9 @@ 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 = ((global_page_state(NR_FILE_MAPPED) +
+				global_page_state(NR_ANON_PAGES)) * 100) /
+					vm_total_pages;
 
 		/*
 		 * Now decide how much we really want to unmap some pages.  The
@@ -741,7 +758,7 @@ 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
@@ -824,11 +841,10 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		}
 	}
 	zone->nr_active += pgmoved;
-	spin_unlock(&zone->lru_lock);
 
-	__mod_page_state_zone(zone, pgrefill, pgscanned);
-	__mod_page_state(pgdeactivate, pgdeactivate);
-	local_irq_enable();
+	__count_zone_vm_events(PGREFILL, zone, pgscanned);
+	__count_vm_events(PGDEACTIVATE, pgdeactivate);
+	spin_unlock_irq(&zone->lru_lock);
 
 	pagevec_release(&pvec);
 }
@@ -957,9 +973,10 @@ 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);
+	count_vm_event(ALLOCSTALL);
 
 	for (i = 0; zones[i] != NULL; i++) {
 		struct zone *zone = zones[i];
@@ -972,7 +989,6 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 	}
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
-		sc.nr_mapped = read_page_state(nr_mapped);
 		sc.nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
@@ -1021,10 +1037,6 @@ 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 +1054,8 @@ 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;
@@ -1055,16 +1065,15 @@ 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:
 	total_scanned = 0;
 	nr_reclaimed = 0;
 	sc.may_writepage = !laptop_mode;
-	sc.nr_mapped = read_page_state(nr_mapped);
-
-	inc_page_state(pageoutrun);
+	count_vm_event(PAGEOUTRUN);
 
 	for (i = 0; i < pgdat->nr_zones; i++) {
 		struct zone *zone = pgdat->node_zones + i;
@@ -1082,31 +1091,26 @@ 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 +1137,9 @@ 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 +1164,6 @@ 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 +1179,7 @@ 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:
@@ -1220,7 +1220,6 @@ static int kswapd(void *p)
 	};
 	cpumask_t cpumask;
 
-	daemonize("kswapd%d", pgdat->node_id);
 	cpumask = node_to_cpumask(pgdat->node_id);
 	if (!cpus_empty(cpumask))
 		set_cpus_allowed(tsk, cpumask);
@@ -1261,7 +1260,7 @@ static int kswapd(void *p)
 		}
 		finish_wait(&pgdat->kswapd_wait, &wait);
 
-		balance_pgdat(pgdat, 0, order);
+		balance_pgdat(pgdat, order);
 	}
 	return 0;
 }
@@ -1290,35 +1289,152 @@ 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 = global_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_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
@@ -1328,7 +1444,7 @@ repeat:
    not required for correctness.  So if the last cpu in a node goes
    away, we get changed to run anywhere: as the first one comes back,
    restore their cpu bindings. */
-static int cpu_callback(struct notifier_block *nfb,
+static int __devinit cpu_callback(struct notifier_block *nfb,
 				  unsigned long action, void *hcpu)
 {
 	pg_data_t *pgdat;
@@ -1346,21 +1462,35 @@ static int cpu_callback(struct notifier_block *nfb,
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
+/*
+ * This kswapd start function will be called by init and node-hot-add.
+ * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
+ */
+int kswapd_run(int nid)
+{
+	pg_data_t *pgdat = NODE_DATA(nid);
+	int ret = 0;
+
+	if (pgdat->kswapd)
+		return 0;
+
+	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+	if (IS_ERR(pgdat->kswapd)) {
+		/* failure at boot is fatal */
+		BUG_ON(system_state == SYSTEM_BOOTING);
+		printk("Failed to start kswapd on node %d\n",nid);
+		ret = -1;
+	}
+	return ret;
+}
+
 static int __init kswapd_init(void)
 {
-	pg_data_t *pgdat;
+	int nid;
 
 	swap_setup();
-	for_each_online_pgdat(pgdat) {
-		pid_t pid;
-
-		pid = kernel_thread(kswapd, pgdat, CLONE_KERNEL);
-		BUG_ON(pid < 0);
-		read_lock(&tasklist_lock);
-		pgdat->kswapd = find_task_by_pid(pid);
-		read_unlock(&tasklist_lock);
-	}
-	total_memory = nr_free_pagecache_pages();
+	for_each_online_node(nid)
+ 		kswapd_run(nid);
 	hotcpu_notifier(cpu_callback, 0);
 	return 0;
 }
@@ -1387,11 +1517,6 @@ int zone_reclaim_mode __read_mostly;
 #define RECLAIM_SLAB (1<<3)	/* Do a global slab shrink if the zone is out of memory */
 
 /*
- * Mininum time between zone reclaim scans
- */
-int zone_reclaim_interval __read_mostly = 30*HZ;
-
-/*
  * Priority for ZONE_RECLAIM. This determines the fraction of pages
  * of a node considered for each zone_reclaim. 4 scans 1/16th of
  * a zone.
@@ -1412,10 +1537,10 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	struct scan_control sc = {
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
 		.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
-		.nr_mapped = read_page_state(nr_mapped),
 		.swap_cluster_max = max_t(unsigned long, nr_pages,
 					SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
+		.swappiness = vm_swappiness,
 	};
 
 	disable_swap_token();
@@ -1456,16 +1581,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 
 	p->reclaim_state = NULL;
 	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
-
-	if (nr_reclaimed == 0) {
-		/*
-		 * We were unable to reclaim enough pages to stay on node.  We
-		 * now allow off node accesses for a certain time period before
-		 * trying again to reclaim pages from the local zone.
-		 */
-		zone->last_unsuccessful_zone_reclaim = jiffies;
-	}
-
 	return nr_reclaimed >= nr_pages;
 }
 
@@ -1475,13 +1590,17 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	int node_id;
 
 	/*
-	 * Do not reclaim if there was a recent unsuccessful attempt at zone
-	 * reclaim.  In that case we let allocations go off node for the
-	 * zone_reclaim_interval.  Otherwise we would scan for each off-node
-	 * page allocation.
+	 * Do not reclaim if there are not enough reclaimable pages in this
+	 * zone that would satify this allocations.
+	 *
+	 * All unmapped pagecache pages are reclaimable.
+	 *
+	 * Both counters may be temporarily off a bit so we use
+	 * SWAP_CLUSTER_MAX as the boundary. It may also be good to
+	 * leave a few frequently used unmapped pagecache pages around.
 	 */
-	if (time_before(jiffies,
-		zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
+	if (zone_page_state(zone, NR_FILE_PAGES) -
+		zone_page_state(zone, NR_FILE_MAPPED) < SWAP_CLUSTER_MAX)
 			return 0;
 
 	/*