1 files changed, 110 insertions, 70 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index f58bcd016f43..37f976287068 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -217,21 +217,12 @@ static inline bool compact_trylock_irqsave(spinlock_t *lock,
 /* Returns true if the page is within a block suitable for migration to */
 static bool suitable_migration_target(struct page *page)
 {
-	int migratetype = get_pageblock_migratetype(page);
-
-	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
-	if (migratetype == MIGRATE_RESERVE)
-		return false;
-
-	if (is_migrate_isolate(migratetype))
-		return false;
-
-	/* If the page is a large free page, then allow migration */
+	/* If the page is a large free page, then disallow migration */
 	if (PageBuddy(page) && page_order(page) >= pageblock_order)
-		return true;
+		return false;
 
 	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
-	if (migrate_async_suitable(migratetype))
+	if (migrate_async_suitable(get_pageblock_migratetype(page)))
 		return true;
 
 	/* Otherwise skip the block */
@@ -251,9 +242,9 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 {
 	int nr_scanned = 0, total_isolated = 0;
 	struct page *cursor, *valid_page = NULL;
-	unsigned long nr_strict_required = end_pfn - blockpfn;
 	unsigned long flags;
 	bool locked = false;
+	bool checked_pageblock = false;
 
 	cursor = pfn_to_page(blockpfn);
 
@@ -264,11 +255,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		nr_scanned++;
 		if (!pfn_valid_within(blockpfn))
-			continue;
+			goto isolate_fail;
+
 		if (!valid_page)
 			valid_page = page;
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/*
 		 * The zone lock must be held to isolate freepages.
@@ -284,17 +276,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 			break;
 
 		/* Recheck this is a suitable migration target under lock */
-		if (!strict && !suitable_migration_target(page))
-			break;
+		if (!strict && !checked_pageblock) {
+			/*
+			 * We need to check suitability of pageblock only once
+			 * and this isolate_freepages_block() is called with
+			 * pageblock range, so just check once is sufficient.
+			 */
+			checked_pageblock = true;
+			if (!suitable_migration_target(page))
+				break;
+		}
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
-		if (!isolated && strict)
-			break;
 		total_isolated += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
@@ -305,7 +303,15 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		if (isolated) {
 			blockpfn += isolated - 1;
 			cursor += isolated - 1;
+			continue;
 		}
+
+isolate_fail:
+		if (strict)
+			break;
+		else
+			continue;
+
 	}
 
 	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -315,7 +321,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	 * pages requested were isolated. If there were any failures, 0 is
 	 * returned and CMA will fail.
 	 */
-	if (strict && nr_strict_required > total_isolated)
+	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
 	if (locked)
@@ -454,11 +460,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	unsigned long last_pageblock_nr = 0, pageblock_nr;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
-	isolate_mode_t mode = 0;
 	struct lruvec *lruvec;
 	unsigned long flags;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
+	bool skipped_async_unsuitable = false;
+	const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) |
+				    (unevictable ? ISOLATE_UNEVICTABLE : 0);
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -480,7 +488,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	cond_resched();
 	for (; low_pfn < end_pfn; low_pfn++) {
 		/* give a chance to irqs before checking need_resched() */
-		if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) {
+		if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) {
 			if (should_release_lock(&zone->lru_lock)) {
 				spin_unlock_irqrestore(&zone->lru_lock, flags);
 				locked = false;
@@ -519,23 +527,32 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 		/* If isolation recently failed, do not retry */
 		pageblock_nr = low_pfn >> pageblock_order;
-		if (!isolation_suitable(cc, page))
-			goto next_pageblock;
+		if (last_pageblock_nr != pageblock_nr) {
+			int mt;
 
-		/* Skip if free */
-		if (PageBuddy(page))
-			continue;
+			last_pageblock_nr = pageblock_nr;
+			if (!isolation_suitable(cc, page))
+				goto next_pageblock;
+
+			/*
+			 * For async migration, also only scan in MOVABLE
+			 * blocks. Async migration is optimistic to see if
+			 * the minimum amount of work satisfies the allocation
+			 */
+			mt = get_pageblock_migratetype(page);
+			if (!cc->sync && !migrate_async_suitable(mt)) {
+				cc->finished_update_migrate = true;
+				skipped_async_unsuitable = true;
+				goto next_pageblock;
+			}
+		}
 
 		/*
-		 * For async migration, also only scan in MOVABLE blocks. Async
-		 * migration is optimistic to see if the minimum amount of work
-		 * satisfies the allocation
+		 * Skip if free. page_order cannot be used without zone->lock
+		 * as nothing prevents parallel allocations or buddy merging.
 		 */
-		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
-		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
-			cc->finished_update_migrate = true;
-			goto next_pageblock;
-		}
+		if (PageBuddy(page))
+			continue;
 
 		/*
 		 * Check may be lockless but that's ok as we recheck later.
@@ -546,11 +563,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			if (unlikely(balloon_page_movable(page))) {
 				if (locked && balloon_page_isolate(page)) {
 					/* Successfully isolated */
-					cc->finished_update_migrate = true;
-					list_add(&page->lru, migratelist);
-					cc->nr_migratepages++;
-					nr_isolated++;
-					goto check_compact_cluster;
+					goto isolate_success;
 				}
 			}
 			continue;
@@ -573,6 +586,15 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
+		/*
+		 * Migration will fail if an anonymous page is pinned in memory,
+		 * so avoid taking lru_lock and isolating it unnecessarily in an
+		 * admittedly racy check.
+		 */
+		if (!page_mapping(page) &&
+		    page_count(page) > page_mapcount(page))
+			continue;
+
 		/* Check if it is ok to still hold the lock */
 		locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
 								locked, cc);
@@ -587,28 +609,23 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
-		if (!cc->sync)
-			mode |= ISOLATE_ASYNC_MIGRATE;
-
-		if (unevictable)
-			mode |= ISOLATE_UNEVICTABLE;
-
 		lruvec = mem_cgroup_page_lruvec(page, zone);
 
 		/* Try isolate the page */
 		if (__isolate_lru_page(page, mode) != 0)
 			continue;
 
-		VM_BUG_ON(PageTransCompound(page));
+		VM_BUG_ON_PAGE(PageTransCompound(page), page);
 
 		/* Successfully isolated */
-		cc->finished_update_migrate = true;
 		del_page_from_lru_list(page, lruvec, page_lru(page));
+
+isolate_success:
+		cc->finished_update_migrate = true;
 		list_add(&page->lru, migratelist);
 		cc->nr_migratepages++;
 		nr_isolated++;
 
-check_compact_cluster:
 		/* Avoid isolating too much */
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
 			++low_pfn;
@@ -619,7 +636,6 @@ check_compact_cluster:
 
 next_pageblock:
 		low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
-		last_pageblock_nr = pageblock_nr;
 	}
 
 	acct_isolated(zone, locked, cc);
@@ -627,8 +643,13 @@ next_pageblock:
 	if (locked)
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
 
-	/* Update the pageblock-skip if the whole pageblock was scanned */
-	if (low_pfn == end_pfn)
+	/*
+	 * Update the pageblock-skip information and cached scanner pfn,
+	 * if the whole pageblock was scanned without isolating any page.
+	 * This is not done when pageblock was skipped due to being unsuitable
+	 * for async compaction, so that eventual sync compaction can try.
+	 */
+	if (low_pfn == end_pfn && !skipped_async_unsuitable)
 		update_pageblock_skip(cc, valid_page, nr_isolated, true);
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
@@ -660,7 +681,7 @@ static void isolate_freepages(struct zone *zone,
 	 * is the end of the pageblock the migration scanner is using.
 	 */
 	pfn = cc->free_pfn;
-	low_pfn = cc->migrate_pfn + pageblock_nr_pages;
+	low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
 
 	/*
 	 * Take care that if the migration scanner is at the end of the zone
@@ -676,7 +697,7 @@ static void isolate_freepages(struct zone *zone,
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
 	 */
-	for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
+	for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
 
@@ -738,7 +759,14 @@ static void isolate_freepages(struct zone *zone,
 	/* split_free_page does not map the pages */
 	map_pages(freelist);
 
-	cc->free_pfn = high_pfn;
+	/*
+	 * If we crossed the migrate scanner, we want to keep it that way
+	 * so that compact_finished() may detect this
+	 */
+	if (pfn < low_pfn)
+		cc->free_pfn = max(pfn, zone->zone_start_pfn);
+	else
+		cc->free_pfn = high_pfn;
 	cc->nr_freepages = nr_freepages;
 }
 
@@ -837,6 +865,10 @@ static int compact_finished(struct zone *zone,
 
 	/* Compaction run completes if the migrate and free scanner meet */
 	if (cc->free_pfn <= cc->migrate_pfn) {
+		/* Let the next compaction start anew. */
+		zone->compact_cached_migrate_pfn = zone->zone_start_pfn;
+		zone->compact_cached_free_pfn = zone_end_pfn(zone);
+
 		/*
 		 * Mark that the PG_migrate_skip information should be cleared
 		 * by kswapd when it goes to sleep. kswapd does not set the
@@ -947,6 +979,14 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	}
 
 	/*
+	 * Clear pageblock skip if there were failures recently and compaction
+	 * is about to be retried after being deferred. kswapd does not do
+	 * this reset as it'll reset the cached information when going to sleep.
+	 */
+	if (compaction_restarting(zone, cc->order) && !current_is_kswapd())
+		__reset_isolation_suitable(zone);
+
+	/*
 	 * Setup to move all movable pages to the end of the zone. Used cached
 	 * information on where the scanners should start but check that it
 	 * is initialised by ensuring the values are within zone boundaries.
@@ -962,13 +1002,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		zone->compact_cached_migrate_pfn = cc->migrate_pfn;
 	}
 
-	/*
-	 * Clear pageblock skip if there were failures recently and compaction
-	 * is about to be retried after being deferred. kswapd does not do
-	 * this reset as it'll reset the cached information when going to sleep.
-	 */
-	if (compaction_restarting(zone, cc->order) && !current_is_kswapd())
-		__reset_isolation_suitable(zone);
+	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn);
 
 	migrate_prep_local();
 
@@ -1003,7 +1037,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		if (err) {
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
-			if (err == -ENOMEM) {
+			/*
+			 * migrate_pages() may return -ENOMEM when scanners meet
+			 * and we want compact_finished() to detect it
+			 */
+			if (err == -ENOMEM && cc->free_pfn > cc->migrate_pfn) {
 				ret = COMPACT_PARTIAL;
 				goto out;
 			}
@@ -1015,6 +1053,8 @@ out:
 	cc->nr_freepages -= release_freepages(&cc->freepages);
 	VM_BUG_ON(cc->nr_freepages != 0);
 
+	trace_mm_compaction_end(ret);
+
 	return ret;
 }
 
@@ -1120,12 +1160,11 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 			compact_zone(zone, cc);
 
 		if (cc->order > 0) {
-			int ok = zone_watermark_ok(zone, cc->order,
-						low_wmark_pages(zone), 0, 0);
-			if (ok && cc->order >= zone->compact_order_failed)
-				zone->compact_order_failed = cc->order + 1;
+			if (zone_watermark_ok(zone, cc->order,
+						low_wmark_pages(zone), 0, 0))
+				compaction_defer_reset(zone, cc->order, false);
 			/* Currently async compaction is never deferred. */
-			else if (!ok && cc->sync)
+			else if (cc->sync)
 				defer_compaction(zone, cc->order);
 		}
 
@@ -1152,6 +1191,7 @@ static void compact_node(int nid)
 	struct compact_control cc = {
 		.order = -1,
 		.sync = true,
+		.ignore_skip_hint = true,
 	};
 
 	__compact_pgdat(NODE_DATA(nid), &cc);
@@ -1191,7 +1231,7 @@ int sysctl_extfrag_handler(struct ctl_table *table, int write,
 }
 
 #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
-ssize_t sysfs_compact_node(struct device *dev,
+static ssize_t sysfs_compact_node(struct device *dev,
 			struct device_attribute *attr,
 			const char *buf, size_t count)
 {