1 files changed, 244 insertions, 61 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6072d74..5326f98 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -248,35 +248,66 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
 		unsigned long long delta;
-		unsigned long total_scan;
-		unsigned long max_pass;
+		long total_scan;
+		long max_pass;
+		int shrink_ret = 0;
+		long nr;
+		long new_nr;
 
 		max_pass = do_shrinker_shrink(shrinker, shrink, 0);
+		if (max_pass <= 0)
+			continue;
+
+		/*
+		 * copy the current shrinker scan count into a local variable
+		 * and zero it so that other concurrent shrinker invocations
+		 * don't also do this scanning work.
+		 */
+		do {
+			nr = shrinker->nr;
+		} while (cmpxchg(&shrinker->nr, nr, 0) != nr);
+
+		total_scan = nr;
 		delta = (4 * nr_pages_scanned) / shrinker->seeks;
 		delta *= max_pass;
 		do_div(delta, lru_pages + 1);
-		shrinker->nr += delta;
-		if (shrinker->nr < 0) {
+		total_scan += delta;
+		if (total_scan < 0) {
 			printk(KERN_ERR "shrink_slab: %pF negative objects to "
 			       "delete nr=%ld\n",
-			       shrinker->shrink, shrinker->nr);
-			shrinker->nr = max_pass;
+			       shrinker->shrink, total_scan);
+			total_scan = max_pass;
 		}
 
 		/*
+		 * We need to avoid excessive windup on filesystem shrinkers
+		 * due to large numbers of GFP_NOFS allocations causing the
+		 * shrinkers to return -1 all the time. This results in a large
+		 * nr being built up so when a shrink that can do some work
+		 * comes along it empties the entire cache due to nr >>>
+		 * max_pass.  This is bad for sustaining a working set in
+		 * memory.
+		 *
+		 * Hence only allow the shrinker to scan the entire cache when
+		 * a large delta change is calculated directly.
+		 */
+		if (delta < max_pass / 4)
+			total_scan = min(total_scan, max_pass / 2);
+
+		/*
 		 * Avoid risking looping forever due to too large nr value:
 		 * never try to free more than twice the estimate number of
 		 * freeable entries.
 		 */
-		if (shrinker->nr > max_pass * 2)
-			shrinker->nr = max_pass * 2;
+		if (total_scan > max_pass * 2)
+			total_scan = max_pass * 2;
 
-		total_scan = shrinker->nr;
-		shrinker->nr = 0;
+		trace_mm_shrink_slab_start(shrinker, shrink, nr,
+					nr_pages_scanned, lru_pages,
+					max_pass, delta, total_scan);
 
 		while (total_scan >= SHRINK_BATCH) {
 			long this_scan = SHRINK_BATCH;
-			int shrink_ret;
 			int nr_before;
 
 			nr_before = do_shrinker_shrink(shrinker, shrink, 0);
@@ -292,7 +323,19 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 			cond_resched();
 		}
 
-		shrinker->nr += total_scan;
+		/*
+		 * move the unused scan count back into the shrinker in a
+		 * manner that handles concurrent updates. If we exhausted the
+		 * scan, there is no need to do an update.
+		 */
+		do {
+			nr = shrinker->nr;
+			new_nr = total_scan + nr;
+			if (total_scan <= 0)
+				break;
+		} while (cmpxchg(&shrinker->nr, nr, new_nr) != nr);
+
+		trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
 	}
 	up_read(&shrinker_rwsem);
 out:
@@ -665,7 +708,7 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_RECLAIM;
 
 	if (referenced_ptes) {
-		if (PageAnon(page))
+		if (PageSwapBacked(page))
 			return PAGEREF_ACTIVATE;
 		/*
 		 * All mapped pages start out with page table
@@ -683,7 +726,13 @@ static enum page_references page_check_references(struct page *page,
 		 */
 		SetPageReferenced(page);
 
-		if (referenced_page)
+		if (referenced_page || referenced_ptes > 1)
+			return PAGEREF_ACTIVATE;
+
+		/*
+		 * Activate file-backed executable pages after first usage.
+		 */
+		if (vm_flags & VM_EXEC)
 			return PAGEREF_ACTIVATE;
 
 		return PAGEREF_KEEP;
@@ -972,23 +1021,27 @@ keep_lumpy:
  *
  * returns 0 on success, -ve errno on failure.
  */
-int __isolate_lru_page(struct page *page, int mode, int file)
+int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
 {
+	bool all_lru_mode;
 	int ret = -EINVAL;
 
 	/* Only take pages on the LRU. */
 	if (!PageLRU(page))
 		return ret;
 
+	all_lru_mode = (mode & (ISOLATE_ACTIVE|ISOLATE_INACTIVE)) ==
+		(ISOLATE_ACTIVE|ISOLATE_INACTIVE);
+
 	/*
 	 * When checking the active state, we need to be sure we are
 	 * dealing with comparible boolean values.  Take the logical not
 	 * of each.
 	 */
-	if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
+	if (!all_lru_mode && !PageActive(page) != !(mode & ISOLATE_ACTIVE))
 		return ret;
 
-	if (mode != ISOLATE_BOTH && page_is_file_cache(page) != file)
+	if (!all_lru_mode && !!page_is_file_cache(page) != file)
 		return ret;
 
 	/*
@@ -1001,6 +1054,43 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 
 	ret = -EBUSY;
 
+	/*
+	 * To minimise LRU disruption, the caller can indicate that it only
+	 * wants to isolate pages it will be able to operate on without
+	 * blocking - clean pages for the most part.
+	 *
+	 * ISOLATE_CLEAN means that only clean pages should be isolated. This
+	 * is used by reclaim when it is cannot write to backing storage
+	 *
+	 * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
+	 * that it is possible to migrate without blocking
+	 */
+	if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) {
+		/* All the caller can do on PageWriteback is block */
+		if (PageWriteback(page))
+			return ret;
+
+		if (PageDirty(page)) {
+			struct address_space *mapping;
+
+			/* ISOLATE_CLEAN means only clean pages */
+			if (mode & ISOLATE_CLEAN)
+				return ret;
+
+			/*
+			 * Only pages without mappings or that have a
+			 * ->migratepage callback are possible to migrate
+			 * without blocking
+			 */
+			mapping = page_mapping(page);
+			if (mapping && !mapping->a_ops->migratepage)
+				return ret;
+		}
+	}
+
+	if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
+		return ret;
+
 	if (likely(get_page_unless_zero(page))) {
 		/*
 		 * Be careful not to clear PageLRU until after we're
@@ -1036,7 +1126,8 @@ int __isolate_lru_page(struct page *page, int mode, int file)
  */
 static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		struct list_head *src, struct list_head *dst,
-		unsigned long *scanned, int order, int mode, int file)
+		unsigned long *scanned, int order, isolate_mode_t mode,
+		int file)
 {
 	unsigned long nr_taken = 0;
 	unsigned long nr_lumpy_taken = 0;
@@ -1111,7 +1202,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			 * anon page which don't already have a swap slot is
 			 * pointless.
 			 */
-			if (nr_swap_pages <= 0 && PageAnon(cursor_page) &&
+			if (nr_swap_pages <= 0 && PageSwapBacked(cursor_page) &&
 			    !PageSwapCache(cursor_page))
 				break;
 
@@ -1161,8 +1252,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 static unsigned long isolate_pages_global(unsigned long nr,
 					struct list_head *dst,
 					unsigned long *scanned, int order,
-					int mode, struct zone *z,
-					int active, int file)
+					isolate_mode_t mode,
+					struct zone *z,	int active, int file)
 {
 	int lru = LRU_BASE;
 	if (active)
@@ -1408,6 +1499,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	unsigned long nr_taken;
 	unsigned long nr_anon;
 	unsigned long nr_file;
+	isolate_mode_t reclaim_mode = ISOLATE_INACTIVE;
 
 	while (unlikely(too_many_isolated(zone, file, sc))) {
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -1418,15 +1510,21 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	}
 
 	set_reclaim_mode(priority, sc, false);
+	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
+		reclaim_mode |= ISOLATE_ACTIVE;
+
 	lru_add_drain();
+
+	if (!sc->may_unmap)
+		reclaim_mode |= ISOLATE_UNMAPPED;
+	if (!sc->may_writepage)
+		reclaim_mode |= ISOLATE_CLEAN;
+
 	spin_lock_irq(&zone->lru_lock);
 
 	if (scanning_global_lru(sc)) {
-		nr_taken = isolate_pages_global(nr_to_scan,
-			&page_list, &nr_scanned, sc->order,
-			sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ?
-					ISOLATE_BOTH : ISOLATE_INACTIVE,
-			zone, 0, file);
+		nr_taken = isolate_pages_global(nr_to_scan, &page_list,
+			&nr_scanned, sc->order, reclaim_mode, zone, 0, file);
 		zone->pages_scanned += nr_scanned;
 		if (current_is_kswapd())
 			__count_zone_vm_events(PGSCAN_KSWAPD, zone,
@@ -1435,12 +1533,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 			__count_zone_vm_events(PGSCAN_DIRECT, zone,
 					       nr_scanned);
 	} else {
-		nr_taken = mem_cgroup_isolate_pages(nr_to_scan,
-			&page_list, &nr_scanned, sc->order,
-			sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ?
-					ISOLATE_BOTH : ISOLATE_INACTIVE,
-			zone, sc->mem_cgroup,
-			0, file);
+		nr_taken = mem_cgroup_isolate_pages(nr_to_scan, &page_list,
+			&nr_scanned, sc->order, reclaim_mode, zone,
+			sc->mem_cgroup, 0, file);
 		/*
 		 * mem_cgroup_isolate_pages() keeps track of
 		 * scanned pages on its own.
@@ -1542,19 +1637,26 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	struct page *page;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	unsigned long nr_rotated = 0;
+	isolate_mode_t reclaim_mode = ISOLATE_ACTIVE;
 
 	lru_add_drain();
+
+	if (!sc->may_unmap)
+		reclaim_mode |= ISOLATE_UNMAPPED;
+	if (!sc->may_writepage)
+		reclaim_mode |= ISOLATE_CLEAN;
+
 	spin_lock_irq(&zone->lru_lock);
 	if (scanning_global_lru(sc)) {
 		nr_taken = isolate_pages_global(nr_pages, &l_hold,
 						&pgscanned, sc->order,
-						ISOLATE_ACTIVE, zone,
+						reclaim_mode, zone,
 						1, file);
 		zone->pages_scanned += pgscanned;
 	} else {
 		nr_taken = mem_cgroup_isolate_pages(nr_pages, &l_hold,
 						&pgscanned, sc->order,
-						ISOLATE_ACTIVE, zone,
+						reclaim_mode, zone,
 						sc->mem_cgroup, 1, file);
 		/*
 		 * mem_cgroup_isolate_pages() keeps track of
@@ -1747,23 +1849,16 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 	u64 fraction[2], denominator;
 	enum lru_list l;
 	int noswap = 0;
-	int force_scan = 0;
+	bool force_scan = false;
 	unsigned long nr_force_scan[2];
 
-
-	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) +
-		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
-
-	if (((anon + file) >> priority) < SWAP_CLUSTER_MAX) {
-		/* kswapd does zone balancing and need to scan this zone */
-		if (scanning_global_lru(sc) && current_is_kswapd())
-			force_scan = 1;
-		/* memcg may have small limit and need to avoid priority drop */
-		if (!scanning_global_lru(sc))
-			force_scan = 1;
-	}
+	/* kswapd does zone balancing and needs to scan this zone */
+	if (scanning_global_lru(sc) && current_is_kswapd() &&
+	    zone->all_unreclaimable)
+		force_scan = true;
+	/* memcg may have small limit and need to avoid priority drop */
+	if (!scanning_global_lru(sc))
+		force_scan = true;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
 	if (!sc->may_swap || (nr_swap_pages <= 0)) {
@@ -1776,6 +1871,11 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 		goto out;
 	}
 
+	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) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+
 	if (scanning_global_lru(sc)) {
 		free  = zone_page_state(zone, NR_FREE_PAGES);
 		/* If we have very few page cache pages,
@@ -1912,8 +2012,9 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	 * inactive lists are large enough, continue reclaiming
 	 */
 	pages_for_compaction = (2UL << sc->order);
-	inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON) +
-				zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+	inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+	if (nr_swap_pages > 0)
+		inactive_lru_pages += zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
 	if (sc->nr_reclaimed < pages_for_compaction &&
 			inactive_lru_pages > pages_for_compaction)
 		return true;
@@ -1985,6 +2086,42 @@ restart:
 	throttle_vm_writeout(sc->gfp_mask);
 }
 
+/* Returns true if compaction should go ahead for a high-order request */
+static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
+{
+	unsigned long balance_gap, watermark;
+	bool watermark_ok;
+
+	/* Do not consider compaction for orders reclaim is meant to satisfy */
+	if (sc->order <= PAGE_ALLOC_COSTLY_ORDER)
+		return false;
+
+	/*
+	 * Compaction takes time to run and there are potentially other
+	 * callers using the pages just freed. Continue reclaiming until
+	 * there is a buffer of free pages available to give compaction
+	 * a reasonable chance of completing and allocating the page
+	 */
+	balance_gap = min(low_wmark_pages(zone),
+		(zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
+			KSWAPD_ZONE_BALANCE_GAP_RATIO);
+	watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order);
+	watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0);
+
+	/*
+	 * If compaction is deferred, reclaim up to a point where
+	 * compaction will have a chance of success when re-enabled
+	 */
+	if (compaction_deferred(zone))
+		return watermark_ok;
+
+	/* If compaction is not ready to start, keep reclaiming */
+	if (!compaction_suitable(zone, sc->order))
+		return false;
+
+	return watermark_ok;
+}
+
 /*
  * This is the direct reclaim path, for page-allocating processes.  We only
  * try to reclaim pages from zones which will satisfy the caller's allocation
@@ -2000,14 +2137,20 @@ restart:
  *
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
+ *
+ * This function returns true if a zone is being reclaimed for a costly
+ * high-order allocation and compaction is ready to begin. This indicates to
+ * the caller that it should consider retrying the allocation instead of
+ * further reclaim.
  */
-static void shrink_zones(int priority, struct zonelist *zonelist,
+static bool shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
+	bool aborted_reclaim = false;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2022,6 +2165,21 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 				continue;
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
+			if (COMPACTION_BUILD) {
+				/*
+				 * If we already have plenty of memory free for
+				 * compaction in this zone, don't free any more.
+				 * Even though compaction is invoked for any
+				 * non-zero order, only frequent costly order
+				 * reclamation is disruptive enough to become a
+				 * noticable problem, like transparent huge page
+				 * allocations.
+				 */
+				if (compaction_ready(zone, sc)) {
+					aborted_reclaim = true;
+					continue;
+				}
+			}
 			/*
 			 * This steals pages from memory cgroups over softlimit
 			 * and returns the number of reclaimed pages and
@@ -2039,6 +2197,8 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 
 		shrink_zone(priority, zone, sc);
 	}
+
+	return aborted_reclaim;
 }
 
 static bool zone_reclaimable(struct zone *zone)
@@ -2092,8 +2252,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	unsigned long writeback_threshold;
+	bool aborted_reclaim;
 
-	get_mems_allowed();
 	delayacct_freepages_start();
 
 	if (scanning_global_lru(sc))
@@ -2103,7 +2263,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token(sc->mem_cgroup);
-		shrink_zones(priority, zonelist, sc);
+		aborted_reclaim = shrink_zones(priority, zonelist, sc);
+
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -2155,7 +2316,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 out:
 	delayacct_freepages_end();
-	put_mems_allowed();
 
 	if (sc->nr_reclaimed)
 		return sc->nr_reclaimed;
@@ -2168,6 +2328,10 @@ out:
 	if (oom_killer_disabled)
 		return 0;
 
+	/* Aborted reclaim to try compaction? don't OOM, then */
+	if (aborted_reclaim)
+		return 1;
+
 	/* top priority shrink_zones still had more to do? don't OOM, then */
 	if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc))
 		return 1;
@@ -2459,6 +2623,9 @@ loop_again:
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
 				break;
+			} else {
+				/* If balanced, clear the congested flag */
+				zone_clear_flag(zone, ZONE_CONGESTED);
 			}
 		}
 		if (i < 0)
@@ -2695,7 +2862,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 		 * them before going back to sleep.
 		 */
 		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
-		schedule();
+
+		if (!kthread_should_stop())
+			schedule();
+
 		set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
 	} else {
 		if (remaining)
@@ -2722,7 +2892,9 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 static int kswapd(void *p)
 {
 	unsigned long order, new_order;
+	unsigned balanced_order;
 	int classzone_idx, new_classzone_idx;
+	int balanced_classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -2753,7 +2925,9 @@ static int kswapd(void *p)
 	set_freezable();
 
 	order = new_order = 0;
+	balanced_order = 0;
 	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
+	balanced_classzone_idx = classzone_idx;
 	for ( ; ; ) {
 		int ret;
 
@@ -2762,7 +2936,8 @@ static int kswapd(void *p)
 		 * new request of a similar or harder type will succeed soon
 		 * so consider going to sleep on the basis we reclaimed at
 		 */
-		if (classzone_idx >= new_classzone_idx && order == new_order) {
+		if (balanced_classzone_idx >= new_classzone_idx &&
+					balanced_order == new_order) {
 			new_order = pgdat->kswapd_max_order;
 			new_classzone_idx = pgdat->classzone_idx;
 			pgdat->kswapd_max_order =  0;
@@ -2777,9 +2952,12 @@ static int kswapd(void *p)
 			order = new_order;
 			classzone_idx = new_classzone_idx;
 		} else {
-			kswapd_try_to_sleep(pgdat, order, classzone_idx);
+			kswapd_try_to_sleep(pgdat, balanced_order,
+						balanced_classzone_idx);
 			order = pgdat->kswapd_max_order;
 			classzone_idx = pgdat->classzone_idx;
+			new_order = order;
+			new_classzone_idx = classzone_idx;
 			pgdat->kswapd_max_order = 0;
 			pgdat->classzone_idx = pgdat->nr_zones - 1;
 		}
@@ -2794,7 +2972,9 @@ static int kswapd(void *p)
 		 */
 		if (!ret) {
 			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
-			order = balance_pgdat(pgdat, order, &classzone_idx);
+			balanced_classzone_idx = classzone_idx;
+			balanced_order = balance_pgdat(pgdat, order,
+						&balanced_classzone_idx);
 		}
 	}
 	return 0;
@@ -2952,14 +3132,17 @@ int kswapd_run(int nid)
 }
 
 /*
- * Called by memory hotplug when all memory in a node is offlined.
+ * Called by memory hotplug when all memory in a node is offlined.  Caller must
+ * hold lock_memory_hotplug().
  */
 void kswapd_stop(int nid)
 {
 	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
 
-	if (kswapd)
+	if (kswapd) {
 		kthread_stop(kswapd);
+		NODE_DATA(nid)->kswapd = NULL;
+	}
 }
 
 static int __init kswapd_init(void)