36 files changed, 2033 insertions, 2847 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 8405eb0023a9..b3c6ce932c64 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -55,7 +55,9 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o
-obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o vmpressure.o
+obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
+obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
+obj-$(CONFIG_MEMCG_SWAP) += swap_cgroup.o
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index b3cbe19f71b5..fcad8322ef36 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -68,11 +68,13 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
 		 * to be released by the balloon driver.
 		 */
 		if (trylock_page(page)) {
+#ifdef CONFIG_BALLOON_COMPACTION
 			if (!PagePrivate(page)) {
 				/* raced with isolation */
 				unlock_page(page);
 				continue;
 			}
+#endif
 			spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 			balloon_page_delete(page);
 			__count_vm_event(BALLOON_DEFLATE);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 8a000cebb0d7..477be696511d 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -243,13 +243,10 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 
 static int reset_managed_pages_done __initdata;
 
-static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
+void reset_node_managed_pages(pg_data_t *pgdat)
 {
 	struct zone *z;
 
-	if (reset_managed_pages_done)
-		return;
-
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
 		z->managed_pages = 0;
 }
@@ -258,8 +255,12 @@ void __init reset_all_zones_managed_pages(void)
 {
 	struct pglist_data *pgdat;
 
+	if (reset_managed_pages_done)
+		return;
+
 	for_each_online_pgdat(pgdat)
 		reset_node_managed_pages(pgdat);
+
 	reset_managed_pages_done = 1;
 }
 
diff --git a/mm/cma.c b/mm/cma.c
index 963bc4add9af..8e9ec13d31db 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -124,6 +124,7 @@ static int __init cma_activate_area(struct cma *cma)
 
 err:
 	kfree(cma->bitmap);
+	cma->count = 0;
 	return -EINVAL;
 }
 
@@ -214,12 +215,23 @@ int __init cma_declare_contiguous(phys_addr_t base,
 			bool fixed, struct cma **res_cma)
 {
 	phys_addr_t memblock_end = memblock_end_of_DRAM();
-	phys_addr_t highmem_start = __pa(high_memory);
+	phys_addr_t highmem_start;
 	int ret = 0;
 
-	pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n",
-		__func__, (unsigned long)size, (unsigned long)base,
-		(unsigned long)limit, (unsigned long)alignment);
+#ifdef CONFIG_X86
+	/*
+	 * high_memory isn't direct mapped memory so retrieving its physical
+	 * address isn't appropriate.  But it would be useful to check the
+	 * physical address of the highmem boundary so it's justfiable to get
+	 * the physical address from it.  On x86 there is a validation check for
+	 * this case, so the following workaround is needed to avoid it.
+	 */
+	highmem_start = __pa_nodebug(high_memory);
+#else
+	highmem_start = __pa(high_memory);
+#endif
+	pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n",
+		__func__, &size, &base, &limit, &alignment);
 
 	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
 		pr_err("Not enough slots for CMA reserved regions!\n");
@@ -244,52 +256,72 @@ int __init cma_declare_contiguous(phys_addr_t base,
 	size = ALIGN(size, alignment);
 	limit &= ~(alignment - 1);
 
+	if (!base)
+		fixed = false;
+
 	/* size should be aligned with order_per_bit */
 	if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit))
 		return -EINVAL;
 
 	/*
-	 * adjust limit to avoid crossing low/high memory boundary for
-	 * automatically allocated regions
+	 * If allocating at a fixed base the request region must not cross the
+	 * low/high memory boundary.
 	 */
-	if (((limit == 0 || limit > memblock_end) &&
-	     (memblock_end - size < highmem_start &&
-	      memblock_end > highmem_start)) ||
-	    (!fixed && limit > highmem_start && limit - size < highmem_start)) {
-		limit = highmem_start;
-	}
-
-	if (fixed && base < highmem_start && base+size > highmem_start) {
+	if (fixed && base < highmem_start && base + size > highmem_start) {
 		ret = -EINVAL;
-		pr_err("Region at %08lx defined on low/high memory boundary (%08lx)\n",
-			(unsigned long)base, (unsigned long)highmem_start);
+		pr_err("Region at %pa defined on low/high memory boundary (%pa)\n",
+			&base, &highmem_start);
 		goto err;
 	}
 
+	/*
+	 * If the limit is unspecified or above the memblock end, its effective
+	 * value will be the memblock end. Set it explicitly to simplify further
+	 * checks.
+	 */
+	if (limit == 0 || limit > memblock_end)
+		limit = memblock_end;
+
 	/* Reserve memory */
-	if (base && fixed) {
+	if (fixed) {
 		if (memblock_is_region_reserved(base, size) ||
 		    memblock_reserve(base, size) < 0) {
 			ret = -EBUSY;
 			goto err;
 		}
 	} else {
-		phys_addr_t addr = memblock_alloc_range(size, alignment, base,
-							limit);
+		phys_addr_t addr = 0;
+
+		/*
+		 * All pages in the reserved area must come from the same zone.
+		 * If the requested region crosses the low/high memory boundary,
+		 * try allocating from high memory first and fall back to low
+		 * memory in case of failure.
+		 */
+		if (base < highmem_start && limit > highmem_start) {
+			addr = memblock_alloc_range(size, alignment,
+						    highmem_start, limit);
+			limit = highmem_start;
+		}
+
 		if (!addr) {
-			ret = -ENOMEM;
-			goto err;
-		} else {
-			base = addr;
+			addr = memblock_alloc_range(size, alignment, base,
+						    limit);
+			if (!addr) {
+				ret = -ENOMEM;
+				goto err;
+			}
 		}
+
+		base = addr;
 	}
 
 	ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma);
 	if (ret)
 		goto err;
 
-	pr_info("Reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
-		(unsigned long)base);
+	pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M,
+		&base);
 	return 0;
 
 err:
diff --git a/mm/compaction.c b/mm/compaction.c
index edba18aed173..546e571e9d60 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -41,15 +41,17 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 static unsigned long release_freepages(struct list_head *freelist)
 {
 	struct page *page, *next;
-	unsigned long count = 0;
+	unsigned long high_pfn = 0;
 
 	list_for_each_entry_safe(page, next, freelist, lru) {
+		unsigned long pfn = page_to_pfn(page);
 		list_del(&page->lru);
 		__free_page(page);
-		count++;
+		if (pfn > high_pfn)
+			high_pfn = pfn;
 	}
 
-	return count;
+	return high_pfn;
 }
 
 static void map_pages(struct list_head *list)
@@ -195,16 +197,12 @@ static void update_pageblock_skip(struct compact_control *cc,
 
 	/* Update where async and sync compaction should restart */
 	if (migrate_scanner) {
-		if (cc->finished_update_migrate)
-			return;
 		if (pfn > zone->compact_cached_migrate_pfn[0])
 			zone->compact_cached_migrate_pfn[0] = pfn;
 		if (cc->mode != MIGRATE_ASYNC &&
 		    pfn > zone->compact_cached_migrate_pfn[1])
 			zone->compact_cached_migrate_pfn[1] = pfn;
 	} else {
-		if (cc->finished_update_free)
-			return;
 		if (pfn < zone->compact_cached_free_pfn)
 			zone->compact_cached_free_pfn = pfn;
 	}
@@ -479,6 +477,16 @@ isolate_freepages_range(struct compact_control *cc,
 
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
+		/*
+		 * pfn could pass the block_end_pfn if isolated freepage
+		 * is more than pageblock order. In this case, we adjust
+		 * scanning range to right one.
+		 */
+		if (pfn >= block_end_pfn) {
+			block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+			block_end_pfn = min(block_end_pfn, end_pfn);
+		}
+
 		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
 			break;
 
@@ -705,7 +713,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		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++;
@@ -784,6 +791,9 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 			cc->nr_migratepages = 0;
 			break;
 		}
+
+		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+			break;
 	}
 	acct_isolated(cc->zone, cc);
 
@@ -876,15 +886,6 @@ static void isolate_freepages(struct compact_control *cc)
 				block_start_pfn - pageblock_nr_pages;
 
 		/*
-		 * Set a flag that we successfully isolated in this pageblock.
-		 * In the next loop iteration, zone->compact_cached_free_pfn
-		 * will not be updated and thus it will effectively contain the
-		 * highest pageblock we isolated pages from.
-		 */
-		if (isolated)
-			cc->finished_update_free = true;
-
-		/*
 		 * isolate_freepages_block() might have aborted due to async
 		 * compaction being contended
 		 */
@@ -1026,8 +1027,12 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	}
 
 	acct_isolated(zone, cc);
-	/* Record where migration scanner will be restarted */
-	cc->migrate_pfn = low_pfn;
+	/*
+	 * Record where migration scanner will be restarted. If we end up in
+	 * the same pageblock as the free scanner, make the scanners fully
+	 * meet so that compact_finished() terminates compaction.
+	 */
+	cc->migrate_pfn = (end_pfn <= cc->free_pfn) ? low_pfn : cc->free_pfn;
 
 	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
 }
@@ -1069,9 +1074,9 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
 
 	/* Compaction run is not finished if the watermark is not met */
 	watermark = low_wmark_pages(zone);
-	watermark += (1 << cc->order);
 
-	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
+	if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx,
+							cc->alloc_flags))
 		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
@@ -1097,7 +1102,8 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
  *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
  *   COMPACT_CONTINUE - If compaction should run now
  */
-unsigned long compaction_suitable(struct zone *zone, int order)
+unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	int fragindex;
 	unsigned long watermark;
@@ -1109,21 +1115,30 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	if (order == -1)
 		return COMPACT_CONTINUE;
 
+	watermark = low_wmark_pages(zone);
+	/*
+	 * If watermarks for high-order allocation are already met, there
+	 * should be no need for compaction at all.
+	 */
+	if (zone_watermark_ok(zone, order, watermark, classzone_idx,
+								alloc_flags))
+		return COMPACT_PARTIAL;
+
 	/*
 	 * Watermarks for order-0 must be met for compaction. Note the 2UL.
 	 * This is because during migration, copies of pages need to be
 	 * allocated and for a short time, the footprint is higher
 	 */
-	watermark = low_wmark_pages(zone) + (2UL << order);
-	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+	watermark += (2UL << order);
+	if (!zone_watermark_ok(zone, 0, watermark, classzone_idx, alloc_flags))
 		return COMPACT_SKIPPED;
 
 	/*
 	 * fragmentation index determines if allocation failures are due to
 	 * low memory or external fragmentation
 	 *
-	 * index of -1000 implies allocations might succeed depending on
-	 * watermarks
+	 * index of -1000 would imply allocations might succeed depending on
+	 * watermarks, but we already failed the high-order watermark check
 	 * index towards 0 implies failure is due to lack of memory
 	 * index towards 1000 implies failure is due to fragmentation
 	 *
@@ -1133,10 +1148,6 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
 		return COMPACT_SKIPPED;
 
-	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
-	    0, 0))
-		return COMPACT_PARTIAL;
-
 	return COMPACT_CONTINUE;
 }
 
@@ -1147,8 +1158,10 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	unsigned long end_pfn = zone_end_pfn(zone);
 	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
+	unsigned long last_migrated_pfn = 0;
 
-	ret = compaction_suitable(zone, cc->order);
+	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
+							cc->classzone_idx);
 	switch (ret) {
 	case COMPACT_PARTIAL:
 	case COMPACT_SKIPPED:
@@ -1191,6 +1204,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	while ((ret = compact_finished(zone, cc, migratetype)) ==
 						COMPACT_CONTINUE) {
 		int err;
+		unsigned long isolate_start_pfn = cc->migrate_pfn;
 
 		switch (isolate_migratepages(zone, cc)) {
 		case ISOLATE_ABORT:
@@ -1199,7 +1213,12 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 			cc->nr_migratepages = 0;
 			goto out;
 		case ISOLATE_NONE:
-			continue;
+			/*
+			 * We haven't isolated and migrated anything, but
+			 * there might still be unflushed migrations from
+			 * previous cc->order aligned block.
+			 */
+			goto check_drain;
 		case ISOLATE_SUCCESS:
 			;
 		}
@@ -1224,12 +1243,61 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 				goto out;
 			}
 		}
+
+		/*
+		 * Record where we could have freed pages by migration and not
+		 * yet flushed them to buddy allocator. We use the pfn that
+		 * isolate_migratepages() started from in this loop iteration
+		 * - this is the lowest page that could have been isolated and
+		 * then freed by migration.
+		 */
+		if (!last_migrated_pfn)
+			last_migrated_pfn = isolate_start_pfn;
+
+check_drain:
+		/*
+		 * Has the migration scanner moved away from the previous
+		 * cc->order aligned block where we migrated from? If yes,
+		 * flush the pages that were freed, so that they can merge and
+		 * compact_finished() can detect immediately if allocation
+		 * would succeed.
+		 */
+		if (cc->order > 0 && last_migrated_pfn) {
+			int cpu;
+			unsigned long current_block_start =
+				cc->migrate_pfn & ~((1UL << cc->order) - 1);
+
+			if (last_migrated_pfn < current_block_start) {
+				cpu = get_cpu();
+				lru_add_drain_cpu(cpu);
+				drain_local_pages(zone);
+				put_cpu();
+				/* No more flushing until we migrate again */
+				last_migrated_pfn = 0;
+			}
+		}
+
 	}
 
 out:
-	/* Release free pages and check accounting */
-	cc->nr_freepages -= release_freepages(&cc->freepages);
-	VM_BUG_ON(cc->nr_freepages != 0);
+	/*
+	 * Release free pages and update where the free scanner should restart,
+	 * so we don't leave any returned pages behind in the next attempt.
+	 */
+	if (cc->nr_freepages > 0) {
+		unsigned long free_pfn = release_freepages(&cc->freepages);
+
+		cc->nr_freepages = 0;
+		VM_BUG_ON(free_pfn == 0);
+		/* The cached pfn is always the first in a pageblock */
+		free_pfn &= ~(pageblock_nr_pages-1);
+		/*
+		 * Only go back, not forward. The cached pfn might have been
+		 * already reset to zone end in compact_finished()
+		 */
+		if (free_pfn > zone->compact_cached_free_pfn)
+			zone->compact_cached_free_pfn = free_pfn;
+	}
 
 	trace_mm_compaction_end(ret);
 
@@ -1237,7 +1305,8 @@ out:
 }
 
 static unsigned long compact_zone_order(struct zone *zone, int order,
-		gfp_t gfp_mask, enum migrate_mode mode, int *contended)
+		gfp_t gfp_mask, enum migrate_mode mode, int *contended,
+		int alloc_flags, int classzone_idx)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1247,6 +1316,8 @@ static unsigned long compact_zone_order(struct zone *zone, int order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
 		.mode = mode,
+		.alloc_flags = alloc_flags,
+		.classzone_idx = classzone_idx,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1271,14 +1342,13 @@ int sysctl_extfrag_threshold = 500;
  * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that determines if compaction was aborted due to
  *	       need_resched() or lock contention
- * @candidate_zone: Return the zone where we think allocation should succeed
  *
  * This is the main entry point for direct page compaction.
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone)
+			int alloc_flags, int classzone_idx)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1286,7 +1356,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_DEFERRED;
-	int alloc_flags = 0;
 	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
 
 	*contended = COMPACT_CONTENDED_NONE;
@@ -1295,10 +1364,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	if (!order || !may_enter_fs || !may_perform_io)
 		return COMPACT_SKIPPED;
 
-#ifdef CONFIG_CMA
-	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
@@ -1309,7 +1374,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			continue;
 
 		status = compact_zone_order(zone, order, gfp_mask, mode,
-							&zone_contended);
+				&zone_contended, alloc_flags, classzone_idx);
 		rc = max(status, rc);
 		/*
 		 * It takes at least one zone that wasn't lock contended
@@ -1318,9 +1383,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		all_zones_contended &= zone_contended;
 
 		/* If a normal allocation would succeed, stop compacting */
-		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
-				      alloc_flags)) {
-			*candidate_zone = zone;
+		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
+					classzone_idx, alloc_flags)) {
 			/*
 			 * We think the allocation will succeed in this zone,
 			 * but it is not certain, hence the false. The caller
@@ -1342,7 +1406,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			goto break_loop;
 		}
 
-		if (mode != MIGRATE_ASYNC) {
+		if (mode != MIGRATE_ASYNC && status == COMPACT_COMPLETE) {
 			/*
 			 * We think that allocation won't succeed in this zone
 			 * so we defer compaction there. If it ends up
diff --git a/mm/debug.c b/mm/debug.c
index 5ce45c9a29b5..0e58f3211f89 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -95,7 +95,10 @@ void dump_page_badflags(struct page *page, const char *reason,
 		dump_flags(page->flags & badflags,
 				pageflag_names, ARRAY_SIZE(pageflag_names));
 	}
-	mem_cgroup_print_bad_page(page);
+#ifdef CONFIG_MEMCG
+	if (page->mem_cgroup)
+		pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
+#endif
 }
 
 void dump_page(struct page *page, const char *reason)
diff --git a/mm/frontswap.c b/mm/frontswap.c
index c30eec536f03..8d82809eb085 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -182,7 +182,7 @@ void __frontswap_init(unsigned type, unsigned long *map)
 	if (frontswap_ops)
 		frontswap_ops->init(type);
 	else {
-		BUG_ON(type > MAX_SWAPFILES);
+		BUG_ON(type >= MAX_SWAPFILES);
 		set_bit(type, need_init);
 	}
 }
@@ -244,8 +244,10 @@ int __frontswap_store(struct page *page)
 		  the (older) page from frontswap
 		 */
 		inc_frontswap_failed_stores();
-		if (dup)
+		if (dup) {
 			__frontswap_clear(sis, offset);
+			frontswap_ops->invalidate_page(type, offset);
+		}
 	}
 	if (frontswap_writethrough_enabled)
 		/* report failure so swap also writes to swap device */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6a37f1b2ed1e..46f96c23cc27 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -200,7 +200,7 @@ retry:
 	preempt_disable();
 	if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
 		preempt_enable();
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		goto retry;
 	}
 
@@ -232,7 +232,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
 	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
 		struct page *zero_page = xchg(&huge_zero_page, NULL);
 		BUG_ON(zero_page == NULL);
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		return HPAGE_PMD_NR;
 	}
 
@@ -784,7 +784,6 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 	if (!pmd_none(*pmd))
 		return false;
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
-	entry = pmd_wrprotect(entry);
 	entry = pmd_mkhuge(entry);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
@@ -803,7 +802,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return VM_FAULT_FALLBACK;
 	if (unlikely(anon_vma_prepare(vma)))
 		return VM_FAULT_OOM;
-	if (unlikely(khugepaged_enter(vma)))
+	if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
 		return VM_FAULT_OOM;
 	if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm) &&
 			transparent_hugepage_use_zero_page()) {
@@ -1971,7 +1970,7 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		 * register it here without waiting a page fault that
 		 * may not happen any time soon.
 		 */
-		if (unlikely(khugepaged_enter_vma_merge(vma)))
+		if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags)))
 			return -ENOMEM;
 		break;
 	case MADV_NOHUGEPAGE:
@@ -2072,7 +2071,8 @@ int __khugepaged_enter(struct mm_struct *mm)
 	return 0;
 }
 
-int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+			       unsigned long vm_flags)
 {
 	unsigned long hstart, hend;
 	if (!vma->anon_vma)
@@ -2084,11 +2084,11 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
 	if (vma->vm_ops)
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
-	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
+	VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
-		return khugepaged_enter(vma);
+		return khugepaged_enter(vma, vm_flags);
 	return 0;
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9fd722769927..30cd96879152 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2638,8 +2638,9 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 	tlb_start_vma(tlb, vma);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+	address = start;
 again:
-	for (address = start; address < end; address += sz) {
+	for (; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
@@ -2686,6 +2687,7 @@ again:
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
 		if (force_flush) {
+			address += sz;
 			spin_unlock(ptl);
 			break;
 		}
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index a67c26e0f360..037e1c00a5b7 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/page_counter.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
@@ -23,7 +24,7 @@ struct hugetlb_cgroup {
 	/*
 	 * the counter to account for hugepages from hugetlb.
 	 */
-	struct res_counter hugepage[HUGE_MAX_HSTATE];
+	struct page_counter hugepage[HUGE_MAX_HSTATE];
 };
 
 #define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
@@ -60,7 +61,7 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
 	int idx;
 
 	for (idx = 0; idx < hugetlb_max_hstate; idx++) {
-		if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0)
+		if (page_counter_read(&h_cg->hugepage[idx]))
 			return true;
 	}
 	return false;
@@ -79,12 +80,12 @@ hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	if (parent_h_cgroup) {
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx],
-					 &parent_h_cgroup->hugepage[idx]);
+			page_counter_init(&h_cgroup->hugepage[idx],
+					  &parent_h_cgroup->hugepage[idx]);
 	} else {
 		root_h_cgroup = h_cgroup;
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx], NULL);
+			page_counter_init(&h_cgroup->hugepage[idx], NULL);
 	}
 	return &h_cgroup->css;
 }
@@ -108,9 +109,8 @@ static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
 static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
 				       struct page *page)
 {
-	int csize;
-	struct res_counter *counter;
-	struct res_counter *fail_res;
+	unsigned int nr_pages;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *page_hcg;
 	struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);
 
@@ -123,15 +123,15 @@ static void hugetlb_cgroup_move_parent(int idx, struct