Merge tag 'v4.9.79' into linux-linaro-lsk-v4.9lsk-v4.9-18.02

 This is the 4.9.79 stable release

8 files changed, 62 insertions, 38 deletions

diff --git a/mm/cma.c b/mm/cma.c
index c960459eda7e..397687fc51f9 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -54,7 +54,7 @@ unsigned long cma_get_size(const struct cma *cma)
 }
 
 static unsigned long cma_bitmap_aligned_mask(const struct cma *cma,
-					     int align_order)
+					     unsigned int align_order)
 {
 	if (align_order <= cma->order_per_bit)
 		return 0;
@@ -62,17 +62,14 @@ static unsigned long cma_bitmap_aligned_mask(const struct cma *cma,
 }
 
 /*
- * Find a PFN aligned to the specified order and return an offset represented in
- * order_per_bits.
+ * Find the offset of the base PFN from the specified align_order.
+ * The value returned is represented in order_per_bits.
  */
 static unsigned long cma_bitmap_aligned_offset(const struct cma *cma,
-					       int align_order)
+					       unsigned int align_order)
 {
-	if (align_order <= cma->order_per_bit)
-		return 0;
-
-	return (ALIGN(cma->base_pfn, (1UL << align_order))
-		- cma->base_pfn) >> cma->order_per_bit;
+	return (cma->base_pfn & ((1UL << align_order) - 1))
+		>> cma->order_per_bit;
 }
 
 static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma,
diff --git a/mm/internal.h b/mm/internal.h
index 34a5459e5989..3e2d01694747 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -74,6 +74,12 @@ static inline void set_page_refcounted(struct page *page)
 extern unsigned long highest_memmap_pfn;
 
 /*
+ * Maximum number of reclaim retries without progress before the OOM
+ * killer is consider the only way forward.
+ */
+#define MAX_RECLAIM_RETRIES 16
+
+/*
  * in mm/vmscan.c:
  */
 extern int isolate_lru_page(struct page *page);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2a800c4a39bd..50088150fc17 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5531,7 +5531,7 @@ static void uncharge_list(struct list_head *page_list)
 		next = page->lru.next;
 
 		VM_BUG_ON_PAGE(PageLRU(page), page);
-		VM_BUG_ON_PAGE(page_count(page), page);
+		VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);
 
 		if (!page->mem_cgroup)
 			continue;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ce7d416edab7..5aa71a82ca73 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -535,6 +535,13 @@ static int delete_from_lru_cache(struct page *p)
 		 */
 		ClearPageActive(p);
 		ClearPageUnevictable(p);
+
+		/*
+		 * Poisoned page might never drop its ref count to 0 so we have
+		 * to uncharge it manually from its memcg.
+		 */
+		mem_cgroup_uncharge(p);
+
 		/*
 		 * drop the page count elevated by isolate_lru_page()
 		 */
diff --git a/mm/mmap.c b/mm/mmap.c
index 5b48adb4aa56..45ac5b973459 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2240,7 +2240,8 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 		gap_addr = TASK_SIZE;
 
 	next = vma->vm_next;
-	if (next && next->vm_start < gap_addr) {
+	if (next && next->vm_start < gap_addr &&
+			(next->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) {
 		if (!(next->vm_flags & VM_GROWSUP))
 			return -ENOMEM;
 		/* Check that both stack segments have the same anon_vma? */
@@ -2324,7 +2325,8 @@ int expand_downwards(struct vm_area_struct *vma,
 	if (gap_addr > address)
 		return -ENOMEM;
 	prev = vma->vm_prev;
-	if (prev && prev->vm_end > gap_addr) {
+	if (prev && prev->vm_end > gap_addr &&
+			(prev->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) {
 		if (!(prev->vm_flags & VM_GROWSDOWN))
 			return -ENOMEM;
 		/* Check that both stack segments have the same anon_vma? */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fbc38888252b..94018ea5f935 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2821,9 +2821,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 		if (!area->nr_free)
 			continue;
 
-		if (alloc_harder)
-			return true;
-
 		for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
 			if (!list_empty(&area->free_list[mt]))
 				return true;
@@ -2835,6 +2832,9 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 			return true;
 		}
 #endif
+		if (alloc_harder &&
+			!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+			return true;
 	}
 	return false;
 }
@@ -3422,12 +3422,6 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
 }
 
 /*
- * Maximum number of reclaim retries without any progress before OOM killer
- * is consider as the only way to move forward.
- */
-#define MAX_RECLAIM_RETRIES 16
-
-/*
  * Checks whether it makes sense to retry the reclaim to make a forward progress
  * for the given allocation request.
  * The reclaim feedback represented by did_some_progress (any progress during
@@ -4385,7 +4379,8 @@ void show_free_areas(unsigned int filter)
 			K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
 			K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 			node_page_state(pgdat, NR_PAGES_SCANNED),
-			!pgdat_reclaimable(pgdat) ? "yes" : "no");
+			pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
+				"yes" : "no");
 	}
 
 	for_each_populated_zone(zone) {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 30a88b945a44..f118dc23f662 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2606,6 +2606,15 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	} while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
 
+	/*
+	 * Kswapd gives up on balancing particular nodes after too
+	 * many failures to reclaim anything from them and goes to
+	 * sleep. On reclaim progress, reset the failure counter. A
+	 * successful direct reclaim run will revive a dormant kswapd.
+	 */
+	if (reclaimable)
+		pgdat->kswapd_failures = 0;
+
 	return reclaimable;
 }
 
@@ -2680,10 +2689,6 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 						 GFP_KERNEL | __GFP_HARDWALL))
 				continue;
 
-			if (sc->priority != DEF_PRIORITY &&
-			    !pgdat_reclaimable(zone->zone_pgdat))
-				continue;	/* Let kswapd poll it */
-
 			/*
 			 * If we already have plenty of memory free for
 			 * compaction in this zone, don't free any more.
@@ -2820,7 +2825,7 @@ retry:
 	return 0;
 }
 
-static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
+static bool allow_direct_reclaim(pg_data_t *pgdat)
 {
 	struct zone *zone;
 	unsigned long pfmemalloc_reserve = 0;
@@ -2828,6 +2833,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 	int i;
 	bool wmark_ok;
 
+	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+		return true;
+
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
 		if (!managed_zone(zone) ||
@@ -2908,7 +2916,7 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 
 		/* Throttle based on the first usable node */
 		pgdat = zone->zone_pgdat;
-		if (pfmemalloc_watermark_ok(pgdat))
+		if (allow_direct_reclaim(pgdat))
 			goto out;
 		break;
 	}
@@ -2930,14 +2938,14 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	 */
 	if (!(gfp_mask & __GFP_FS)) {
 		wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
-			pfmemalloc_watermark_ok(pgdat), HZ);
+			allow_direct_reclaim(pgdat), HZ);
 
 		goto check_pending;
 	}
 
 	/* Throttle until kswapd wakes the process */
 	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
-		pfmemalloc_watermark_ok(pgdat));
+		allow_direct_reclaim(pgdat));
 
 check_pending:
 	if (fatal_signal_pending(current))
@@ -3116,7 +3124,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 
 	/*
 	 * The throttled processes are normally woken up in balance_pgdat() as
-	 * soon as pfmemalloc_watermark_ok() is true. But there is a potential
+	 * soon as allow_direct_reclaim() is true. But there is a potential
 	 * race between when kswapd checks the watermarks and a process gets
 	 * throttled. There is also a potential race if processes get
 	 * throttled, kswapd wakes, a large process exits thereby balancing the
@@ -3130,6 +3138,10 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 	if (waitqueue_active(&pgdat->pfmemalloc_wait))
 		wake_up_all(&pgdat->pfmemalloc_wait);
 
+	/* Hopeless node, leave it to direct reclaim */
+	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+		return true;
+
 	for (i = 0; i <= classzone_idx; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
@@ -3216,9 +3228,9 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 	count_vm_event(PAGEOUTRUN);
 
 	do {
+		unsigned long nr_reclaimed = sc.nr_reclaimed;
 		bool raise_priority = true;
 
-		sc.nr_reclaimed = 0;
 		sc.reclaim_idx = classzone_idx;
 
 		/*
@@ -3297,7 +3309,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		 * able to safely make forward progress. Wake them
 		 */
 		if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
-				pfmemalloc_watermark_ok(pgdat))
+				allow_direct_reclaim(pgdat))
 			wake_up_all(&pgdat->pfmemalloc_wait);
 
 		/* Check if kswapd should be suspending */
@@ -3308,10 +3320,14 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		 * Raise priority if scanning rate is too low or there was no
 		 * progress in reclaiming pages
 		 */
-		if (raise_priority || !sc.nr_reclaimed)
+		nr_reclaimed = sc.nr_reclaimed - nr_reclaimed;
+		if (raise_priority || !nr_reclaimed)
 			sc.priority--;
 	} while (sc.priority >= 1);
 
+	if (!sc.nr_reclaimed)
+		pgdat->kswapd_failures++;
+
 out:
 	/*
 	 * Return the order kswapd stopped reclaiming at as
@@ -3511,6 +3527,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
 
+	/* Hopeless node, leave it to direct reclaim */
+	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+		return;
+
 	/* Only wake kswapd if all zones are unbalanced */
 	for (z = 0; z <= classzone_idx; z++) {
 		zone = pgdat->node_zones + z;
@@ -3781,9 +3801,6 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 	    sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
 		return NODE_RECLAIM_FULL;
 
-	if (!pgdat_reclaimable(pgdat))
-		return NODE_RECLAIM_FULL;
-
 	/*
 	 * Do not scan if the allocation should not be delayed.
 	 */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6a088df04b29..3863b5d6d598 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1421,7 +1421,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n  node_unreclaimable:  %u"
 		   "\n  start_pfn:           %lu"
 		   "\n  node_inactive_ratio: %u",
-		   !pgdat_reclaimable(zone->zone_pgdat),
+		   pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES,
 		   zone->zone_start_pfn,
 		   zone->zone_pgdat->inactive_ratio);
 	seq_putc(m, '\n');