Merge tag 'v4.6-rc3' into drm-intel-next-queued

Linux 4.6-rc3

Backmerge requested by Chris Wilson to make his patches apply cleanly.
Tiny conflict in vmalloc.c with the (properly acked and all) patch in
drm-intel-next:

commit 4da56b99d99e5a7df2b7f11e87bfea935f909732
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Mon Apr 4 14:46:42 2016 +0100

    mm/vmap: Add a notifier for when we run out of vmap address space

and Linus' tree.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

1 files changed, 78 insertions, 138 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 71b1c29..b934223e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -195,25 +195,25 @@ static unsigned long zone_reclaimable_pages(struct zone *zone)
 {
 	unsigned long nr;
 
-	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
-	     zone_page_state(zone, NR_INACTIVE_FILE) +
-	     zone_page_state(zone, NR_ISOLATED_FILE);
+	nr = zone_page_state_snapshot(zone, NR_ACTIVE_FILE) +
+	     zone_page_state_snapshot(zone, NR_INACTIVE_FILE) +
+	     zone_page_state_snapshot(zone, NR_ISOLATED_FILE);
 
 	if (get_nr_swap_pages() > 0)
-		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
-		      zone_page_state(zone, NR_INACTIVE_ANON) +
-		      zone_page_state(zone, NR_ISOLATED_ANON);
+		nr += zone_page_state_snapshot(zone, NR_ACTIVE_ANON) +
+		      zone_page_state_snapshot(zone, NR_INACTIVE_ANON) +
+		      zone_page_state_snapshot(zone, NR_ISOLATED_ANON);
 
 	return nr;
 }
 
 bool zone_reclaimable(struct zone *zone)
 {
-	return zone_page_state(zone, NR_PAGES_SCANNED) <
+	return zone_page_state_snapshot(zone, NR_PAGES_SCANNED) <
 		zone_reclaimable_pages(zone) * 6;
 }
 
-static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
+unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
 	if (!mem_cgroup_disabled())
 		return mem_cgroup_get_lru_size(lruvec, lru);
@@ -228,14 +228,6 @@ int register_shrinker(struct shrinker *shrinker)
 {
 	size_t size = sizeof(*shrinker->nr_deferred);
 
-	/*
-	 * If we only have one possible node in the system anyway, save
-	 * ourselves the trouble and disable NUMA aware behavior. This way we
-	 * will save memory and some small loop time later.
-	 */
-	if (nr_node_ids == 1)
-		shrinker->flags &= ~SHRINKER_NUMA_AWARE;
-
 	if (shrinker->flags & SHRINKER_NUMA_AWARE)
 		size *= nr_node_ids;
 
@@ -390,9 +382,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
  *
  * @memcg specifies the memory cgroup to target. If it is not NULL,
  * only shrinkers with SHRINKER_MEMCG_AWARE set will be called to scan
- * objects from the memory cgroup specified. Otherwise all shrinkers
- * are called, and memcg aware shrinkers are supposed to scan the
- * global list then.
+ * objects from the memory cgroup specified. Otherwise, only unaware
+ * shrinkers are called.
  *
  * @nr_scanned and @nr_eligible form a ratio that indicate how much of
  * the available objects should be scanned.  Page reclaim for example
@@ -412,7 +403,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 	struct shrinker *shrinker;
 	unsigned long freed = 0;
 
-	if (memcg && !memcg_kmem_online(memcg))
+	if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
 		return 0;
 
 	if (nr_scanned == 0)
@@ -436,7 +427,13 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 			.memcg = memcg,
 		};
 
-		if (memcg && !(shrinker->flags & SHRINKER_MEMCG_AWARE))
+		/*
+		 * If kernel memory accounting is disabled, we ignore
+		 * SHRINKER_MEMCG_AWARE flag and call all shrinkers
+		 * passing NULL for memcg.
+		 */
+		if (memcg_kmem_enabled() &&
+		    !!memcg != !!(shrinker->flags & SHRINKER_MEMCG_AWARE))
 			continue;
 
 		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
@@ -611,12 +608,10 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 			    bool reclaimed)
 {
 	unsigned long flags;
-	struct mem_cgroup *memcg;
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
 
-	memcg = mem_cgroup_begin_page_stat(page);
 	spin_lock_irqsave(&mapping->tree_lock, flags);
 	/*
 	 * The non racy check for a busy page.
@@ -643,11 +638,11 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	 * Note that if SetPageDirty is always performed via set_page_dirty,
 	 * and thus under tree_lock, then this ordering is not required.
 	 */
-	if (!page_freeze_refs(page, 2))
+	if (!page_ref_freeze(page, 2))
 		goto cannot_free;
 	/* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
 	if (unlikely(PageDirty(page))) {
-		page_unfreeze_refs(page, 2);
+		page_ref_unfreeze(page, 2);
 		goto cannot_free;
 	}
 
@@ -656,7 +651,6 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		mem_cgroup_swapout(page, swap);
 		__delete_from_swap_cache(page);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
-		mem_cgroup_end_page_stat(memcg);
 		swapcache_free(swap);
 	} else {
 		void (*freepage)(struct page *);
@@ -682,9 +676,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		if (reclaimed && page_is_file_cache(page) &&
 		    !mapping_exiting(mapping) && !dax_mapping(mapping))
 			shadow = workingset_eviction(mapping, page);
-		__delete_from_page_cache(page, shadow, memcg);
+		__delete_from_page_cache(page, shadow);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
-		mem_cgroup_end_page_stat(memcg);
 
 		if (freepage != NULL)
 			freepage(page);
@@ -694,7 +687,6 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 
 cannot_free:
 	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-	mem_cgroup_end_page_stat(memcg);
 	return 0;
 }
 
@@ -712,7 +704,7 @@ int remove_mapping(struct address_space *mapping, struct page *page)
 		 * drops the pagecache ref for us without requiring another
 		 * atomic operation.
 		 */
-		page_unfreeze_refs(page, 1);
+		page_ref_unfreeze(page, 1);
 		return 1;
 	}
 	return 0;
@@ -1931,8 +1923,8 @@ static bool inactive_file_is_low(struct lruvec *lruvec)
 	unsigned long inactive;
 	unsigned long active;
 
-	inactive = get_lru_size(lruvec, LRU_INACTIVE_FILE);
-	active = get_lru_size(lruvec, LRU_ACTIVE_FILE);
+	inactive = lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
+	active = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
 
 	return active > inactive;
 }
@@ -2071,7 +2063,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * system is under heavy pressure.
 	 */
 	if (!inactive_file_is_low(lruvec) &&
-	    get_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
+	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -2097,10 +2089,10 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * anon in [0], file in [1]
 	 */
 
-	anon  = get_lru_size(lruvec, LRU_ACTIVE_ANON) +
-		get_lru_size(lruvec, LRU_INACTIVE_ANON);
-	file  = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
-		get_lru_size(lruvec, LRU_INACTIVE_FILE);
+	anon  = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON) +
+		lruvec_lru_size(lruvec, LRU_INACTIVE_ANON);
+	file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
+		lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
 
 	spin_lock_irq(&zone->lru_lock);
 	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
@@ -2138,7 +2130,7 @@ out:
 			unsigned long size;
 			unsigned long scan;
 
-			size = get_lru_size(lruvec, lru);
+			size = lruvec_lru_size(lruvec, lru);
 			scan = size >> sc->priority;
 
 			if (!scan && pass && force_scan)
@@ -2981,18 +2973,23 @@ static void age_active_anon(struct zone *zone, struct scan_control *sc)
 	} while (memcg);
 }
 
-static bool zone_balanced(struct zone *zone, int order,
-			  unsigned long balance_gap, int classzone_idx)
+static bool zone_balanced(struct zone *zone, int order, bool highorder,
+			unsigned long balance_gap, int classzone_idx)
 {
-	if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone) +
-				    balance_gap, classzone_idx))
-		return false;
+	unsigned long mark = high_wmark_pages(zone) + balance_gap;
 
-	if (IS_ENABLED(CONFIG_COMPACTION) && order && compaction_suitable(zone,
-				order, 0, classzone_idx) == COMPACT_SKIPPED)
-		return false;
+	/*
+	 * When checking from pgdat_balanced(), kswapd should stop and sleep
+	 * when it reaches the high order-0 watermark and let kcompactd take
+	 * over. Other callers such as wakeup_kswapd() want to determine the
+	 * true high-order watermark.
+	 */
+	if (IS_ENABLED(CONFIG_COMPACTION) && !highorder) {
+		mark += (1UL << order);
+		order = 0;
+	}
 
-	return true;
+	return zone_watermark_ok_safe(zone, order, mark, classzone_idx);
 }
 
 /*
@@ -3042,7 +3039,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
 			continue;
 		}
 
-		if (zone_balanced(zone, order, 0, i))
+		if (zone_balanced(zone, order, false, 0, i))
 			balanced_pages += zone->managed_pages;
 		else if (!order)
 			return false;
@@ -3096,10 +3093,8 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
  */
 static bool kswapd_shrink_zone(struct zone *zone,
 			       int classzone_idx,
-			       struct scan_control *sc,
-			       unsigned long *nr_attempted)
+			       struct scan_control *sc)
 {
-	int testorder = sc->order;
 	unsigned long balance_gap;
 	bool lowmem_pressure;
 
@@ -3107,17 +3102,6 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone));
 
 	/*
-	 * 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.
-	 */
-	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
-			compaction_suitable(zone, sc->order, 0, classzone_idx)
-							!= COMPACT_SKIPPED)
-		testorder = 0;
-
-	/*
 	 * We put equal pressure on every zone, unless one zone has way too
 	 * many pages free already. The "too many pages" is defined as the
 	 * high wmark plus a "gap" where the gap is either the low
@@ -3131,15 +3115,12 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	 * reclaim is necessary
 	 */
 	lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone));
-	if (!lowmem_pressure && zone_balanced(zone, testorder,
+	if (!lowmem_pressure && zone_balanced(zone, sc->order, false,
 						balance_gap, classzone_idx))
 		return true;
 
 	shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
 
-	/* Account for the number of pages attempted to reclaim */
-	*nr_attempted += sc->nr_to_reclaim;
-
 	clear_bit(ZONE_WRITEBACK, &zone->flags);
 
 	/*
@@ -3149,7 +3130,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	 * waits.
 	 */
 	if (zone_reclaimable(zone) &&
-	    zone_balanced(zone, testorder, 0, classzone_idx)) {
+	    zone_balanced(zone, sc->order, false, 0, classzone_idx)) {
 		clear_bit(ZONE_CONGESTED, &zone->flags);
 		clear_bit(ZONE_DIRTY, &zone->flags);
 	}
@@ -3161,7 +3142,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
  * For kswapd, balance_pgdat() will work across all this node's zones until
  * they are all at high_wmark_pages(zone).
  *
- * Returns the final order kswapd was reclaiming at
+ * Returns the highest zone idx kswapd was reclaiming at
  *
  * There is special handling here for zones which are full of pinned pages.
  * This can happen if the pages are all mlocked, or if they are all used by
@@ -3178,8 +3159,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
  * interoperates with 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, int order,
-							int *classzone_idx)
+static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 {
 	int i;
 	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
@@ -3196,9 +3176,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 	count_vm_event(PAGEOUTRUN);
 
 	do {
-		unsigned long nr_attempted = 0;
 		bool raise_priority = true;
-		bool pgdat_needs_compaction = (order > 0);
 
 		sc.nr_reclaimed = 0;
 
@@ -3233,7 +3211,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 				break;
 			}
 
-			if (!zone_balanced(zone, order, 0, 0)) {
+			if (!zone_balanced(zone, order, false, 0, 0)) {
 				end_zone = i;
 				break;
 			} else {
@@ -3249,24 +3227,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 		if (i < 0)
 			goto out;
 
-		for (i = 0; i <= end_zone; i++) {
-			struct zone *zone = pgdat->node_zones + i;
-
-			if (!populated_zone(zone))
-				continue;
-
-			/*
-			 * If any zone is currently balanced then kswapd will
-			 * not call compaction as it is expected that the
-			 * necessary pages are already available.
-			 */
-			if (pgdat_needs_compaction &&
-					zone_watermark_ok(zone, order,
-						low_wmark_pages(zone),
-						*classzone_idx, 0))
-				pgdat_needs_compaction = false;
-		}
-
 		/*
 		 * If we're getting trouble reclaiming, start doing writepage
 		 * even in laptop mode.
@@ -3310,8 +3270,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 			 * that that high watermark would be met at 100%
 			 * efficiency.
 			 */
-			if (kswapd_shrink_zone(zone, end_zone,
-					       &sc, &nr_attempted))
+			if (kswapd_shrink_zone(zone, end_zone, &sc))
 				raise_priority = false;
 		}
 
@@ -3324,49 +3283,29 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 				pfmemalloc_watermark_ok(pgdat))
 			wake_up_all(&pgdat->pfmemalloc_wait);
 
-		/*
-		 * Fragmentation may mean that the system cannot be rebalanced
-		 * for high-order allocations in all zones. If twice the
-		 * allocation size has been reclaimed and the zones are still
-		 * not balanced then recheck the watermarks at order-0 to
-		 * prevent kswapd reclaiming excessively. Assume that a
-		 * process requested a high-order can direct reclaim/compact.
-		 */
-		if (order && sc.nr_reclaimed >= 2UL << order)
-			order = sc.order = 0;
-
 		/* Check if kswapd should be suspending */
 		if (try_to_freeze() || kthread_should_stop())
 			break;
 
 		/*
-		 * Compact if necessary and kswapd is reclaiming at least the
-		 * high watermark number of pages as requsted
-		 */
-		if (pgdat_needs_compaction && sc.nr_reclaimed > nr_attempted)
-			compact_pgdat(pgdat, order);
-
-		/*
 		 * Raise priority if scanning rate is too low or there was no
 		 * progress in reclaiming pages
 		 */
 		if (raise_priority || !sc.nr_reclaimed)
 			sc.priority--;
 	} while (sc.priority >= 1 &&
-		 !pgdat_balanced(pgdat, order, *classzone_idx));
+			!pgdat_balanced(pgdat, order, classzone_idx));
 
 out:
 	/*
-	 * Return the order we were reclaiming at so prepare_kswapd_sleep()
-	 * makes a decision on the order we were last reclaiming at. However,
-	 * if another caller entered the allocator slow path while kswapd
-	 * was awake, order will remain at the higher level
+	 * Return the highest zone idx we were reclaiming at so
+	 * prepare_kswapd_sleep() makes the same decisions as here.
 	 */
-	*classzone_idx = end_zone;
-	return order;
+	return end_zone;
 }
 
-static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
+static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
+				int classzone_idx, int balanced_classzone_idx)
 {
 	long remaining = 0;
 	DEFINE_WAIT(wait);
@@ -3377,7 +3316,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 	prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 
 	/* Try to sleep for a short interval */
-	if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
+	if (prepare_kswapd_sleep(pgdat, order, remaining,
+						balanced_classzone_idx)) {
 		remaining = schedule_timeout(HZ/10);
 		finish_wait(&pgdat->kswapd_wait, &wait);
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
@@ -3387,7 +3327,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 	 * After a short sleep, check if it was a premature sleep. If not, then
 	 * go fully to sleep until explicitly woken up.
 	 */
-	if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
+	if (prepare_kswapd_sleep(pgdat, order, remaining,
+						balanced_classzone_idx)) {
 		trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
 
 		/*
@@ -3408,6 +3349,12 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 		 */
 		reset_isolation_suitable(pgdat);
 
+		/*
+		 * We have freed the memory, now we should compact it to make
+		 * allocation of the requested order possible.
+		 */
+		wakeup_kcompactd(pgdat, order, classzone_idx);
+
 		if (!kthread_should_stop())
 			schedule();
 
@@ -3437,7 +3384,6 @@ 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;
@@ -3470,24 +3416,19 @@ 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 ( ; ; ) {
 		bool ret;
 
 		/*
-		 * If the last balance_pgdat was unsuccessful it's unlikely a
-		 * new request of a similar or harder type will succeed soon
-		 * so consider going to sleep on the basis we reclaimed at
+		 * While we were reclaiming, there might have been another
+		 * wakeup, so check the values.
 		 */
-		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;
-			pgdat->classzone_idx = pgdat->nr_zones - 1;
-		}
+		new_order = pgdat->kswapd_max_order;
+		new_classzone_idx = pgdat->classzone_idx;
+		pgdat->kswapd_max_order =  0;
+		pgdat->classzone_idx = pgdat->nr_zones - 1;
 
 		if (order < new_order || classzone_idx > new_classzone_idx) {
 			/*
@@ -3497,7 +3438,7 @@ static int kswapd(void *p)
 			order = new_order;
 			classzone_idx = new_classzone_idx;
 		} else {
-			kswapd_try_to_sleep(pgdat, balanced_order,
+			kswapd_try_to_sleep(pgdat, order, classzone_idx,
 						balanced_classzone_idx);
 			order = pgdat->kswapd_max_order;
 			classzone_idx = pgdat->classzone_idx;
@@ -3517,9 +3458,8 @@ static int kswapd(void *p)
 		 */
 		if (!ret) {
 			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
-			balanced_classzone_idx = classzone_idx;
-			balanced_order = balance_pgdat(pgdat, order,
-						&balanced_classzone_idx);
+			balanced_classzone_idx = balance_pgdat(pgdat, order,
+								classzone_idx);
 		}
 	}
 
@@ -3549,7 +3489,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	}
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
-	if (zone_balanced(zone, order, 0, 0))
+	if (zone_balanced(zone, order, true, 0, 0))
 		return;
 
 	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);