Merge branch 'perf/core' into perf/uprobes

Merge in latest upstream (and the latest perf development tree),
to prepare for tooling changes, and also to pick up v3.4 MM
changes that the uprobes code needs to take care of.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 98 insertions, 54 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index c52b23552659..33c332bbab73 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1138,7 +1138,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
  * @mz:		The mem_cgroup_zone to pull pages from.
  * @dst:	The temp list to put pages on to.
  * @nr_scanned:	The number of pages that were scanned.
- * @order:	The caller's attempted allocation order
+ * @sc:		The scan_control struct for this reclaim session
  * @mode:	One of the LRU isolation modes
  * @active:	True [1] if isolating active pages
  * @file:	True [1] if isolating file [!anon] pages
@@ -1147,8 +1147,8 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
  */
 static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		struct mem_cgroup_zone *mz, struct list_head *dst,
-		unsigned long *nr_scanned, int order, isolate_mode_t mode,
-		int active, int file)
+		unsigned long *nr_scanned, struct scan_control *sc,
+		isolate_mode_t mode, int active, int file)
 {
 	struct lruvec *lruvec;
 	struct list_head *src;
@@ -1194,7 +1194,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			BUG();
 		}
 
-		if (!order)
+		if (!sc->order || !(sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM))
 			continue;
 
 		/*
@@ -1208,8 +1208,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 */
 		zone_id = page_zone_id(page);
 		page_pfn = page_to_pfn(page);
-		pfn = page_pfn & ~((1 << order) - 1);
-		end_pfn = pfn + (1 << order);
+		pfn = page_pfn & ~((1 << sc->order) - 1);
+		end_pfn = pfn + (1 << sc->order);
 		for (; pfn < end_pfn; pfn++) {
 			struct page *cursor_page;
 
@@ -1275,7 +1275,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 	*nr_scanned = scan;
 
-	trace_mm_vmscan_lru_isolate(order,
+	trace_mm_vmscan_lru_isolate(sc->order,
 			nr_to_scan, scan,
 			nr_taken,
 			nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed,
@@ -1413,7 +1413,6 @@ update_isolated_counts(struct mem_cgroup_zone *mz,
 		       unsigned long *nr_anon,
 		       unsigned long *nr_file)
 {
-	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
 	struct zone *zone = mz->zone;
 	unsigned int count[NR_LRU_LISTS] = { 0, };
 	unsigned long nr_active = 0;
@@ -1434,6 +1433,7 @@ update_isolated_counts(struct mem_cgroup_zone *mz,
 		count[lru] += numpages;
 	}
 
+	preempt_disable();
 	__count_vm_events(PGDEACTIVATE, nr_active);
 
 	__mod_zone_page_state(zone, NR_ACTIVE_FILE,
@@ -1448,8 +1448,9 @@ update_isolated_counts(struct mem_cgroup_zone *mz,
 	*nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
 	*nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
 
-	reclaim_stat->recent_scanned[0] += *nr_anon;
-	reclaim_stat->recent_scanned[1] += *nr_file;
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON, *nr_anon);
+	__mod_zone_page_state(zone, NR_ISOLATED_FILE, *nr_file);
+	preempt_enable();
 }
 
 /*
@@ -1509,8 +1510,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 	unsigned long nr_file;
 	unsigned long nr_dirty = 0;
 	unsigned long nr_writeback = 0;
-	isolate_mode_t reclaim_mode = ISOLATE_INACTIVE;
+	isolate_mode_t isolate_mode = ISOLATE_INACTIVE;
 	struct zone *zone = mz->zone;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
 
 	while (unlikely(too_many_isolated(zone, file, sc))) {
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -1522,20 +1524,19 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 
 	set_reclaim_mode(priority, sc, false);
 	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
-		reclaim_mode |= ISOLATE_ACTIVE;
+		isolate_mode |= ISOLATE_ACTIVE;
 
 	lru_add_drain();
 
 	if (!sc->may_unmap)
-		reclaim_mode |= ISOLATE_UNMAPPED;
+		isolate_mode |= ISOLATE_UNMAPPED;
 	if (!sc->may_writepage)
-		reclaim_mode |= ISOLATE_CLEAN;
+		isolate_mode |= ISOLATE_CLEAN;
 
 	spin_lock_irq(&zone->lru_lock);
 
-	nr_taken = isolate_lru_pages(nr_to_scan, mz, &page_list,
-				     &nr_scanned, sc->order,
-				     reclaim_mode, 0, file);
+	nr_taken = isolate_lru_pages(nr_to_scan, mz, &page_list, &nr_scanned,
+				     sc, isolate_mode, 0, file);
 	if (global_reclaim(sc)) {
 		zone->pages_scanned += nr_scanned;
 		if (current_is_kswapd())
@@ -1545,19 +1546,13 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 			__count_zone_vm_events(PGSCAN_DIRECT, zone,
 					       nr_scanned);
 	}
+	spin_unlock_irq(&zone->lru_lock);
 
-	if (nr_taken == 0) {
-		spin_unlock_irq(&zone->lru_lock);
+	if (nr_taken == 0)
 		return 0;
-	}
 
 	update_isolated_counts(mz, &page_list, &nr_anon, &nr_file);
 
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file);
-
-	spin_unlock_irq(&zone->lru_lock);
-
 	nr_reclaimed = shrink_page_list(&page_list, mz, sc, priority,
 						&nr_dirty, &nr_writeback);
 
@@ -1570,6 +1565,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 
 	spin_lock_irq(&zone->lru_lock);
 
+	reclaim_stat->recent_scanned[0] += nr_anon;
+	reclaim_stat->recent_scanned[1] += nr_file;
+
 	if (current_is_kswapd())
 		__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
 	__count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
@@ -1643,18 +1641,6 @@ static void move_active_pages_to_lru(struct zone *zone,
 	unsigned long pgmoved = 0;
 	struct page *page;
 
-	if (buffer_heads_over_limit) {
-		spin_unlock_irq(&zone->lru_lock);
-		list_for_each_entry(page, list, lru) {
-			if (page_has_private(page) && trylock_page(page)) {
-				if (page_has_private(page))
-					try_to_release_page(page, 0);
-				unlock_page(page);
-			}
-		}
-		spin_lock_irq(&zone->lru_lock);
-	}
-
 	while (!list_empty(list)) {
 		struct lruvec *lruvec;
 
@@ -1699,21 +1685,22 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	struct page *page;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
 	unsigned long nr_rotated = 0;
-	isolate_mode_t reclaim_mode = ISOLATE_ACTIVE;
+	isolate_mode_t isolate_mode = ISOLATE_ACTIVE;
 	struct zone *zone = mz->zone;
 
 	lru_add_drain();
 
+	reset_reclaim_mode(sc);
+
 	if (!sc->may_unmap)
-		reclaim_mode |= ISOLATE_UNMAPPED;
+		isolate_mode |= ISOLATE_UNMAPPED;
 	if (!sc->may_writepage)
-		reclaim_mode |= ISOLATE_CLEAN;
+		isolate_mode |= ISOLATE_CLEAN;
 
 	spin_lock_irq(&zone->lru_lock);
 
-	nr_taken = isolate_lru_pages(nr_to_scan, mz, &l_hold,
-				     &nr_scanned, sc->order,
-				     reclaim_mode, 1, file);
+	nr_taken = isolate_lru_pages(nr_to_scan, mz, &l_hold, &nr_scanned, sc,
+				     isolate_mode, 1, file);
 	if (global_reclaim(sc))
 		zone->pages_scanned += nr_scanned;
 
@@ -1737,6 +1724,14 @@ static void shrink_active_list(unsigned long nr_to_scan,
 			continue;
 		}
 
+		if (unlikely(buffer_heads_over_limit)) {
+			if (page_has_private(page) && trylock_page(page)) {
+				if (page_has_private(page))
+					try_to_release_page(page, 0);
+				unlock_page(page);
+			}
+		}
+
 		if (page_referenced(page, 0, mz->mem_cgroup, &vm_flags)) {
 			nr_rotated += hpage_nr_pages(page);
 			/*
@@ -2112,7 +2107,12 @@ restart:
 		 * with multiple processes reclaiming pages, the total
 		 * freeing target can get unreasonably large.
 		 */
-		if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY)
+		if (nr_reclaimed >= nr_to_reclaim)
+			nr_to_reclaim = 0;
+		else
+			nr_to_reclaim -= nr_reclaimed;
+
+		if (!nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 	blk_finish_plug(&plug);
@@ -2195,7 +2195,7 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
 	 * If compaction is deferred, reclaim up to a point where
 	 * compaction will have a chance of success when re-enabled
 	 */
-	if (compaction_deferred(zone))
+	if (compaction_deferred(zone, sc->order))
 		return watermark_ok;
 
 	/* If compaction is not ready to start, keep reclaiming */
@@ -2235,6 +2235,14 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
 	unsigned long nr_soft_scanned;
 	bool aborted_reclaim = false;
 
+	/*
+	 * If the number of buffer_heads in the machine exceeds the maximum
+	 * allowed level, force direct reclaim to scan the highmem zone as
+	 * highmem pages could be pinning lowmem pages storing buffer_heads
+	 */
+	if (buffer_heads_over_limit)
+		sc->gfp_mask |= __GFP_HIGHMEM;
+
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
 		if (!populated_zone(zone))
@@ -2255,8 +2263,8 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
 				 * 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.
+				 * noticeable problem, like transparent huge
+				 * page allocations.
 				 */
 				if (compaction_ready(zone, sc)) {
 					aborted_reclaim = true;
@@ -2337,7 +2345,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	unsigned long writeback_threshold;
 	bool aborted_reclaim;
 
-	get_mems_allowed();
 	delayacct_freepages_start();
 
 	if (global_reclaim(sc))
@@ -2401,7 +2408,6 @@ 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;
@@ -2724,6 +2730,17 @@ loop_again:
 			 */
 			age_active_anon(zone, &sc, priority);
 
+			/*
+			 * If the number of buffer_heads in the machine
+			 * exceeds the maximum allowed level and this node
+			 * has a highmem zone, force kswapd to reclaim from
+			 * it to relieve lowmem pressure.
+			 */
+			if (buffer_heads_over_limit && is_highmem_idx(i)) {
+				end_zone = i;
+				break;
+			}
+
 			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
@@ -2753,7 +2770,7 @@ loop_again:
 		 */
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
-			int nr_slab;
+			int nr_slab, testorder;
 			unsigned long balance_gap;
 
 			if (!populated_zone(zone))
@@ -2786,7 +2803,21 @@ loop_again:
 				(zone->present_pages +
 					KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
 				KSWAPD_ZONE_BALANCE_GAP_RATIO);
-			if (!zone_watermark_ok_safe(zone, order,
+			/*
+			 * Kswapd reclaims only single pages with compaction
+			 * enabled. Trying too hard to reclaim until contiguous
+			 * free pages have become available can hurt performance
+			 * by evicting too much useful data from memory.
+			 * Do not reclaim more than needed for compaction.
+			 */
+			testorder = order;
+			if (COMPACTION_BUILD && order &&
+					compaction_suitable(zone, order) !=
+						COMPACT_SKIPPED)
+				testorder = 0;
+
+			if ((buffer_heads_over_limit && is_highmem_idx(i)) ||
+				    !zone_watermark_ok_safe(zone, testorder,
 					high_wmark_pages(zone) + balance_gap,
 					end_zone, 0)) {
 				shrink_zone(priority, zone, &sc);
@@ -2815,7 +2846,7 @@ loop_again:
 				continue;
 			}
 
-			if (!zone_watermark_ok_safe(zone, order,
+			if (!zone_watermark_ok_safe(zone, testorder,
 					high_wmark_pages(zone), end_zone, 0)) {
 				all_zones_ok = 0;
 				/*
@@ -2903,6 +2934,8 @@ out:
 	 * and it is potentially going to sleep here.
 	 */
 	if (order) {
+		int zones_need_compaction = 1;
+
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
@@ -2912,6 +2945,11 @@ out:
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;
 
+			/* Would compaction fail due to lack of free memory? */
+			if (COMPACTION_BUILD &&
+			    compaction_suitable(zone, order) == COMPACT_SKIPPED)
+				goto loop_again;
+
 			/* Confirm the zone is balanced for order-0 */
 			if (!zone_watermark_ok(zone, 0,
 					high_wmark_pages(zone), 0, 0)) {
@@ -2919,11 +2957,17 @@ out:
 				goto loop_again;
 			}
 
+			/* Check if the memory needs to be defragmented. */
+			if (zone_watermark_ok(zone, order,
+				    low_wmark_pages(zone), *classzone_idx, 0))
+				zones_need_compaction = 0;
+
 			/* If balanced, clear the congested flag */
 			zone_clear_flag(zone, ZONE_CONGESTED);
-			if (i <= *classzone_idx)
-				balanced += zone->present_pages;
 		}
+
+		if (zones_need_compaction)
+			compact_pgdat(pgdat, order);
 	}
 
 	/*