1 files changed, 152 insertions, 172 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 777af57fd8c8..c26986c85ce0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -55,6 +55,11 @@ struct scan_control {
 	/* Number of pages freed so far during a call to shrink_zones() */
 	unsigned long nr_reclaimed;
 
+	/* How many pages shrink_list() should reclaim */
+	unsigned long nr_to_reclaim;
+
+	unsigned long hibernation_mode;
+
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -66,12 +71,6 @@ struct scan_control {
 	/* Can pages be swapped as part of reclaim? */
 	int may_swap;
 
-	/* This context's SWAP_CLUSTER_MAX. If freeing memory for
-	 * suspend, we effectively ignore SWAP_CLUSTER_MAX.
-	 * In this context, it doesn't matter that we scan the
-	 * whole list at once. */
-	int swap_cluster_max;
-
 	int swappiness;
 
 	int all_unreclaimable;
@@ -358,7 +357,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 	 * stalls if we need to run get_block().  We could test
 	 * PagePrivate for that.
 	 *
-	 * If this process is currently in generic_file_write() against
+	 * If this process is currently in __generic_file_aio_write() against
 	 * this page's queue, we can perform writeback even if that
 	 * will block.
 	 *
@@ -1132,7 +1131,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		unsigned long nr_anon;
 		unsigned long nr_file;
 
-		nr_taken = sc->isolate_pages(sc->swap_cluster_max,
+		nr_taken = sc->isolate_pages(SWAP_CLUSTER_MAX,
 			     &page_list, &nr_scan, sc->order, mode,
 				zone, sc->mem_cgroup, 0, file);
 
@@ -1166,10 +1165,8 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		__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];
-		reclaim_stat->recent_scanned[1] += count[LRU_INACTIVE_FILE];
-		reclaim_stat->recent_scanned[1] += count[LRU_ACTIVE_FILE];
+		reclaim_stat->recent_scanned[0] += nr_anon;
+		reclaim_stat->recent_scanned[1] += nr_file;
 
 		spin_unlock_irq(&zone->lru_lock);
 
@@ -1464,20 +1461,26 @@ static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
 	return low;
 }
 
+static int inactive_list_is_low(struct zone *zone, struct scan_control *sc,
+				int file)
+{
+	if (file)
+		return inactive_file_is_low(zone, sc);
+	else
+		return inactive_anon_is_low(zone, sc);
+}
+
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 	struct zone *zone, struct scan_control *sc, int priority)
 {
 	int file = is_file_lru(lru);
 
-	if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) {
-		shrink_active_list(nr_to_scan, zone, sc, priority, file);
+	if (is_active_lru(lru)) {
+		if (inactive_list_is_low(zone, sc, file))
+		    shrink_active_list(nr_to_scan, zone, sc, priority, file);
 		return 0;
 	}
 
-	if (lru == LRU_ACTIVE_ANON && inactive_anon_is_low(zone, sc)) {
-		shrink_active_list(nr_to_scan, zone, sc, priority, file);
-		return 0;
-	}
 	return shrink_inactive_list(nr_to_scan, zone, sc, priority, file);
 }
 
@@ -1567,15 +1570,14 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
  * until we collected @swap_cluster_max pages to scan.
  */
 static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
-				       unsigned long *nr_saved_scan,
-				       unsigned long swap_cluster_max)
+				       unsigned long *nr_saved_scan)
 {
 	unsigned long nr;
 
 	*nr_saved_scan += nr_to_scan;
 	nr = *nr_saved_scan;
 
-	if (nr >= swap_cluster_max)
+	if (nr >= SWAP_CLUSTER_MAX)
 		*nr_saved_scan = 0;
 	else
 		nr = 0;
@@ -1594,7 +1596,7 @@ static void shrink_zone(int priority, struct zone *zone,
 	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;
+	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	int noswap = 0;
 
@@ -1616,15 +1618,15 @@ static void shrink_zone(int priority, struct zone *zone,
 			scan = (scan * percent[file]) / 100;
 		}
 		nr[l] = nr_scan_try_batch(scan,
-					  &reclaim_stat->nr_saved_scan[l],
-					  swap_cluster_max);
+					  &reclaim_stat->nr_saved_scan[l]);
 	}
 
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
 		for_each_evictable_lru(l) {
 			if (nr[l]) {
-				nr_to_scan = min(nr[l], swap_cluster_max);
+				nr_to_scan = min_t(unsigned long,
+						   nr[l], SWAP_CLUSTER_MAX);
 				nr[l] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(l, nr_to_scan,
@@ -1639,8 +1641,7 @@ static void shrink_zone(int priority, struct zone *zone,
 		 * 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())
+		if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 
@@ -1738,6 +1739,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
+	unsigned long writeback_threshold;
 
 	delayacct_freepages_start();
 
@@ -1773,7 +1775,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			}
 		}
 		total_scanned += sc->nr_scanned;
-		if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+		if (sc->nr_reclaimed >= sc->nr_to_reclaim) {
 			ret = sc->nr_reclaimed;
 			goto out;
 		}
@@ -1785,14 +1787,15 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		 * that's undesirable in laptop mode, where we *want* lumpy
 		 * writeout.  So in laptop mode, write out the whole world.
 		 */
-		if (total_scanned > sc->swap_cluster_max +
-					sc->swap_cluster_max / 2) {
+		writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
+		if (total_scanned > writeback_threshold) {
 			wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
 			sc->may_writepage = 1;
 		}
 
 		/* Take a nap, wait for some writeback to complete */
-		if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
+		if (!sc->hibernation_mode && sc->nr_scanned &&
+		    priority < DEF_PRIORITY - 2)
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
@@ -1831,7 +1834,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	struct scan_control sc = {
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.may_unmap = 1,
 		.may_swap = 1,
 		.swappiness = vm_swappiness,
@@ -1855,7 +1858,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = !noswap,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem,
@@ -1889,7 +1891,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = !noswap,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem_cont,
@@ -1904,6 +1906,33 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 }
 #endif
 
+/* is kswapd sleeping prematurely? */
+static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
+{
+	int i;
+
+	/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
+	if (remaining)
+		return 1;
+
+	/* If after HZ/10, a zone is below the high mark, it's premature */
+	for (i = 0; i < pgdat->nr_zones; i++) {
+		struct zone *zone = pgdat->node_zones + i;
+
+		if (!populated_zone(zone))
+			continue;
+
+		if (zone_is_all_unreclaimable(zone))
+			continue;
+
+		if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
+								0, 0))
+			return 1;
+	}
+
+	return 0;
+}
+
 /*
  * For kswapd, balance_pgdat() will work across all this node's zones until
  * they are all at high_wmark_pages(zone).
@@ -1936,7 +1965,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.gfp_mask = GFP_KERNEL,
 		.may_unmap = 1,
 		.may_swap = 1,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		/*
+		 * kswapd doesn't want to be bailed out while reclaim. because
+		 * we want to put equal scanning pressure on each zone.
+		 */
+		.nr_to_reclaim = ULONG_MAX,
 		.swappiness = vm_swappiness,
 		.order = order,
 		.mem_cgroup = NULL,
@@ -1961,6 +1994,7 @@ loop_again:
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 		unsigned long lru_pages = 0;
+		int has_under_min_watermark_zone = 0;
 
 		/* The swap token gets in the way of swapout... */
 		if (!priority)
@@ -2067,6 +2101,15 @@ loop_again:
 			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
 			    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 (all_zones_ok)
 			break;		/* kswapd: all done */
@@ -2074,8 +2117,12 @@ loop_again:
 		 * OK, kswapd is getting into trouble.  Take a nap, then take
 		 * another pass across the zones.
 		 */
-		if (total_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(BLK_RW_ASYNC, HZ/10);
+		if (total_scanned && (priority < DEF_PRIORITY - 2)) {
+			if (has_under_min_watermark_zone)
+				count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
+			else
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
+		}
 
 		/*
 		 * We do this so kswapd doesn't build up large priorities for
@@ -2173,6 +2220,7 @@ static int kswapd(void *p)
 	order = 0;
 	for ( ; ; ) {
 		unsigned long new_order;
+		int ret;
 
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 		new_order = pgdat->kswapd_max_order;
@@ -2184,19 +2232,45 @@ static int kswapd(void *p)
 			 */
 			order = new_order;
 		} else {
-			if (!freezing(current))
-				schedule();
+			if (!freezing(current) && !kthread_should_stop()) {
+				long remaining = 0;
+
+				/* Try to sleep for a short interval */
+				if (!sleeping_prematurely(pgdat, order, remaining)) {
+					remaining = schedule_timeout(HZ/10);
+					finish_wait(&pgdat->kswapd_wait, &wait);
+					prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
+				}
+
+				/*
+				 * After a short sleep, check if it was a
+				 * premature sleep. If not, then go fully
+				 * to sleep until explicitly woken up
+				 */
+				if (!sleeping_prematurely(pgdat, order, remaining))
+					schedule();
+				else {
+					if (remaining)
+						count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
+					else
+						count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
+				}
+			}
 
 			order = pgdat->kswapd_max_order;
 		}
 		finish_wait(&pgdat->kswapd_wait, &wait);
 
-		if (!try_to_freeze()) {
-			/* We can speed up thawing tasks if we don't call
-			 * balance_pgdat after returning from the refrigerator
-			 */
+		ret = try_to_freeze();
+		if (kthread_should_stop())
+			break;
+
+		/*
+		 * We can speed up thawing tasks if we don't call balance_pgdat
+		 * after returning from the refrigerator
+		 */
+		if (!ret)
 			balance_pgdat(pgdat, order);
-		}
 	}
 	return 0;
 }
@@ -2260,148 +2334,43 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 
 #ifdef CONFIG_HIBERNATION
 /*
- * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
- * from LRU lists system-wide, for given pass and priority.
- *
- * For pass > 3 we also try to shrink the LRU lists that contain a few pages
- */
-static void shrink_all_zones(unsigned long nr_pages, int prio,
-				      int pass, struct scan_control *sc)
-{
-	struct zone *zone;
-	unsigned long nr_reclaimed = 0;
-	struct zone_reclaim_stat *reclaim_stat;
-
-	for_each_populated_zone(zone) {
-		enum lru_list l;
-
-		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
-			continue;
-
-		for_each_evictable_lru(l) {
-			enum zone_stat_item ls = NR_LRU_BASE + l;
-			unsigned long lru_pages = zone_page_state(zone, ls);
-
-			/* For pass = 0, we don't shrink the active list */
-			if (pass == 0 && (l == LRU_ACTIVE_ANON ||
-						l == LRU_ACTIVE_FILE))
-				continue;
-
-			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;
-
-				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);
-				if (nr_reclaimed >= nr_pages) {
-					sc->nr_reclaimed += nr_reclaimed;
-					return;
-				}
-			}
-		}
-	}
-	sc->nr_reclaimed += nr_reclaimed;
-}
-
-/*
- * Try to free `nr_pages' of memory, system-wide, and return the number of
+ * Try to free `nr_to_reclaim' 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)
+unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 {
-	unsigned long lru_pages, nr_slab;
-	int pass;
 	struct reclaim_state reclaim_state;
 	struct scan_control sc = {
-		.gfp_mask = GFP_KERNEL,
-		.may_unmap = 0,
+		.gfp_mask = GFP_HIGHUSER_MOVABLE,
+		.may_swap = 1,
+		.may_unmap = 1,
 		.may_writepage = 1,
+		.nr_to_reclaim = nr_to_reclaim,
+		.hibernation_mode = 1,
+		.swappiness = vm_swappiness,
+		.order = 0,
 		.isolate_pages = isolate_pages_global,
-		.nr_reclaimed = 0,
 	};
+	struct zonelist * zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
+	struct task_struct *p = current;
+	unsigned long nr_reclaimed;
 
-	current->reclaim_state = &reclaim_state;
-
-	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) {
-		reclaim_state.reclaimed_slab = 0;
-		shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
-		if (!reclaim_state.reclaimed_slab)
-			break;
-
-		sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-		if (sc.nr_reclaimed >= nr_pages)
-			goto out;
-
-		nr_slab -= reclaim_state.reclaimed_slab;
-	}
-
-	/*
-	 * 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;
-
-		/* Force reclaiming mapped pages in the passes #3 and #4 */
-		if (pass > 2)
-			sc.may_unmap = 1;
-
-		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
-			unsigned long nr_to_scan = nr_pages - sc.nr_reclaimed;
-
-			sc.nr_scanned = 0;
-			sc.swap_cluster_max = nr_to_scan;
-			shrink_all_zones(nr_to_scan, prio, pass, &sc);
-			if (sc.nr_reclaimed >= nr_pages)
-				goto out;
-
-			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(sc.nr_scanned, sc.gfp_mask,
-				    global_reclaimable_pages());
-			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-			if (sc.nr_reclaimed >= nr_pages)
-				goto out;
-
-			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				congestion_wait(BLK_RW_ASYNC, HZ / 10);
-		}
-	}
-
-	/*
-	 * If sc.nr_reclaimed = 0, we could not shrink LRUs, but there may be
-	 * something in slab caches
-	 */
-	if (!sc.nr_reclaimed) {
-		do {
-			reclaim_state.reclaimed_slab = 0;
-			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);
-	}
+	p->flags |= PF_MEMALLOC;
+	lockdep_set_current_reclaim_state(sc.gfp_mask);
+	reclaim_state.reclaimed_slab = 0;
+	p->reclaim_state = &reclaim_state;
 
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
-out:
-	current->reclaim_state = NULL;
+	p->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+	p->flags &= ~PF_MEMALLOC;
 
-	return sc.nr_reclaimed;
+	return nr_reclaimed;
 }
 #endif /* CONFIG_HIBERNATION */
 
@@ -2451,6 +2420,17 @@ int kswapd_run(int nid)
 	return ret;
 }
 
+/*
+ * Called by memory hotplug when all memory in a node is offlined.
+ */
+void kswapd_stop(int nid)
+{
+	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
+
+	if (kswapd)
+		kthread_stop(kswapd);
+}
+
 static int __init kswapd_init(void)
 {
 	int nid;
@@ -2553,8 +2533,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
 		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
 		.may_swap = 1,
-		.swap_cluster_max = max_t(unsigned long, nr_pages,
-					SWAP_CLUSTER_MAX),
+		.nr_to_reclaim = max_t(unsigned long, nr_pages,
+				       SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
 		.swappiness = vm_swappiness,
 		.order = order,