Merge branch 'akpm' (incoming from Andrew)

Merge first patch-bomb from Andrew Morton:

 - a couple of misc things

 - inotify/fsnotify work from Jan

 - ocfs2 updates (partial)

 - about half of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (117 commits)
  mm/migrate: remove unused function, fail_migrate_page()
  mm/migrate: remove putback_lru_pages, fix comment on putback_movable_pages
  mm/migrate: correct failure handling if !hugepage_migration_support()
  mm/migrate: add comment about permanent failure path
  mm, page_alloc: warn for non-blockable __GFP_NOFAIL allocation failure
  mm: compaction: reset scanner positions immediately when they meet
  mm: compaction: do not mark unmovable pageblocks as skipped in async compaction
  mm: compaction: detect when scanners meet in isolate_freepages
  mm: compaction: reset cached scanner pfn's before reading them
  mm: compaction: encapsulate defer reset logic
  mm: compaction: trace compaction begin and end
  memcg, oom: lock mem_cgroup_print_oom_info
  sched: add tracepoints related to NUMA task migration
  mm: numa: do not automatically migrate KSM pages
  mm: numa: trace tasks that fail migration due to rate limiting
  mm: numa: limit scope of lock for NUMA migrate rate limiting
  mm: numa: make NUMA-migrate related functions static
  lib/show_mem.c: show num_poisoned_pages when oom
  mm/hwpoison: add '#' to hwpoison_inject
  mm/memblock: use WARN_ONCE when MAX_NUMNODES passed as input parameter
  ...

26 files changed, 1145 insertions, 820 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index f58bcd016f4..3a91a2ea3d3 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -459,6 +459,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	unsigned long flags;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
+	bool skipped_async_unsuitable = false;
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -534,6 +535,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
 		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
 			cc->finished_update_migrate = true;
+			skipped_async_unsuitable = true;
 			goto next_pageblock;
 		}
 
@@ -627,8 +629,13 @@ 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 +667,7 @@ 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 +683,7 @@ 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 +745,14 @@ 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 +851,10 @@ 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 +965,14 @@ 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 +988,7 @@ 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 +1023,11 @@ 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 +1039,8 @@ out:
 	cc->nr_freepages -= release_freepages(&cc->freepages);
 	VM_BUG_ON(cc->nr_freepages != 0);
 
+	trace_mm_compaction_end(ret);
+
 	return ret;
 }
 
@@ -1120,12 +1146,11 @@ 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);
 		}
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index dee6cf4e6d3..04306b9de90 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -690,15 +690,11 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
  */
 int PageHuge(struct page *page)
 {
-	compound_page_dtor *dtor;
-
 	if (!PageCompound(page))
 		return 0;
 
 	page = compound_head(page);
-	dtor = get_compound_page_dtor(page);
-
-	return dtor == free_huge_page;
+	return get_compound_page_dtor(page) == free_huge_page;
 }
 EXPORT_SYMBOL_GPL(PageHuge);
 
@@ -708,16 +704,11 @@ EXPORT_SYMBOL_GPL(PageHuge);
  */
 int PageHeadHuge(struct page *page_head)
 {
-	compound_page_dtor *dtor;
-
 	if (!PageHead(page_head))
 		return 0;
 
-	dtor = get_compound_page_dtor(page_head);
-
-	return dtor == free_huge_page;
+	return get_compound_page_dtor(page_head) == free_huge_page;
 }
-EXPORT_SYMBOL_GPL(PageHeadHuge);
 
 pgoff_t __basepage_index(struct page *page)
 {
@@ -1280,9 +1271,9 @@ int __weak alloc_bootmem_huge_page(struct hstate *h)
 	for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
 		void *addr;
 
-		addr = __alloc_bootmem_node_nopanic(NODE_DATA(node),
-				huge_page_size(h), huge_page_size(h), 0);
-
+		addr = memblock_virt_alloc_try_nid_nopanic(
+				huge_page_size(h), huge_page_size(h),
+				0, BOOTMEM_ALLOC_ACCESSIBLE, node);
 		if (addr) {
 			/*
 			 * Use the beginning of the huge page to store the
@@ -1322,8 +1313,8 @@ static void __init gather_bootmem_prealloc(void)
 
 #ifdef CONFIG_HIGHMEM
 		page = pfn_to_page(m->phys >> PAGE_SHIFT);
-		free_bootmem_late((unsigned long)m,
-				  sizeof(struct huge_bootmem_page));
+		memblock_free_late(__pa(m),
+				   sizeof(struct huge_bootmem_page));
 #else
 		page = virt_to_page(m);
 #endif
@@ -2355,17 +2346,27 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	int cow;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
+	unsigned long mmun_start;	/* For mmu_notifiers */
+	unsigned long mmun_end;		/* For mmu_notifiers */
+	int ret = 0;
 
 	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
+	mmun_start = vma->vm_start;
+	mmun_end = vma->vm_end;
+	if (cow)
+		mmu_notifier_invalidate_range_start(src, mmun_start, mmun_end);
+
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
 		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr);
 		if (!src_pte)
 			continue;
 		dst_pte = huge_pte_alloc(dst, addr, sz);
-		if (!dst_pte)
-			goto nomem;
+		if (!dst_pte) {
+			ret = -ENOMEM;
+			break;
+		}
 
 		/* If the pagetables are shared don't copy or take references */
 		if (dst_pte == src_pte)
@@ -2386,10 +2387,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
 	}
-	return 0;
 
-nomem:
-	return -ENOMEM;
+	if (cow)
+		mmu_notifier_invalidate_range_end(src, mmun_start, mmun_end);
+
+	return ret;
 }
 
 static int is_hugetlb_entry_migration(pte_t pte)
@@ -3079,7 +3081,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 same_page:
 		if (pages) {
 			pages[i] = mem_map_offset(page, pfn_offset);
-			get_page(pages[i]);
+			get_page_foll(pages[i]);
 		}
 
 		if (vmas)
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index 4c84678371e..95487c71cad 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -55,7 +55,7 @@ static int hwpoison_inject(void *data, u64 val)
 		return 0;
 
 inject:
-	printk(KERN_INFO "Injecting memory failure at pfn %lx\n", pfn);
+	pr_info("Injecting memory failure at pfn %#lx\n", pfn);
 	return memory_failure(pfn, 18, MF_COUNT_INCREASED);
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index 684f7aa9692..a346ba120e4 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -47,11 +47,9 @@ static inline void __get_page_tail_foll(struct page *page,
 	 * page_cache_get_speculative()) on tail pages.
 	 */
 	VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
-	VM_BUG_ON(atomic_read(&page->_count) != 0);
-	VM_BUG_ON(page_mapcount(page) < 0);
 	if (get_page_head)
 		atomic_inc(&page->first_page->_count);
-	atomic_inc(&page->_mapcount);
+	get_huge_page_tail(page);
 }
 
 /*
diff --git a/mm/ksm.c b/mm/ksm.c
index 175fff79dc9..3df141e5f3e 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1891,21 +1891,24 @@ struct page *ksm_might_need_to_copy(struct page *page,
 	return new_page;
 }
 
-int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg,
-			unsigned long *vm_flags)
+int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc)
 {
 	struct stable_node *stable_node;
 	struct rmap_item *rmap_item;
-	unsigned int mapcount = page_mapcount(page);
-	int referenced = 0;
+	int ret = SWAP_AGAIN;
 	int search_new_forks = 0;
 
 	VM_BUG_ON(!PageKsm(page));
+
+	/*
+	 * Rely on the page lock to protect against concurrent modifications
+	 * to that page's node of the stable tree.
+	 */
 	VM_BUG_ON(!PageLocked(page));
 
 	stable_node = page_stable_node(page);
 	if (!stable_node)
-		return 0;
+		return ret;
 again:
 	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
 		struct anon_vma *anon_vma = rmap_item->anon_vma;
@@ -1928,113 +1931,16 @@ again:
 			if ((rmap_item->mm == vma->vm_mm) == search_new_forks)
 				continue;
 
-			if (memcg && !mm_match_cgroup(vma->vm_mm, memcg))
-				continue;
-
-			referenced += page_referenced_one(page, vma,
-				rmap_item->address, &mapcount, vm_flags);
-			if (!search_new_forks || !mapcount)
-				break;
-		}
-		anon_vma_unlock_read(anon_vma);
-		if (!mapcount)
-			goto out;
-	}
-	if (!search_new_forks++)
-		goto again;
-out:
-	return referenced;
-}
-
-int try_to_unmap_ksm(struct page *page, enum ttu_flags flags)
-{
-	struct stable_node *stable_node;
-	struct rmap_item *rmap_item;
-	int ret = SWAP_AGAIN;
-	int search_new_forks = 0;
-
-	VM_BUG_ON(!PageKsm(page));
-	VM_BUG_ON(!PageLocked(page));
-
-	stable_node = page_stable_node(page);
-	if (!stable_node)
-		return SWAP_FAIL;
-again:
-	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
-		struct anon_vma *anon_vma = rmap_item->anon_vma;
-		struct anon_vma_chain *vmac;
-		struct vm_area_struct *vma;
-
-		anon_vma_lock_read(anon_vma);
-		anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
-					       0, ULONG_MAX) {
-			vma = vmac->vma;
-			if (rmap_item->address < vma->vm_start ||
-			    rmap_item->address >= vma->vm_end)
-				continue;
-			/*
-			 * Initially we examine only the vma which covers this
-			 * rmap_item; but later, if there is still work to do,
-			 * we examine covering vmas in other mms: in case they
-			 * were forked from the original since ksmd passed.
-			 */
-			if ((rmap_item->mm == vma->vm_mm) == search_new_forks)
+			if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
 				continue;
 
-			ret = try_to_unmap_one(page, vma,
-					rmap_item->address, flags);
-			if (ret != SWAP_AGAIN || !page_mapped(page)) {
+			ret = rwc->rmap_one(page, vma,
+					rmap_item->address, rwc->arg);
+			if (ret != SWAP_AGAIN) {
 				anon_vma_unlock_read(anon_vma);
 				goto out;
 			}
-		}
-		anon_vma_unlock_read(anon_vma);
-	}
-	if (!search_new_forks++)
-		goto again;
-out:
-	return ret;
-}
-
-#ifdef CONFIG_MIGRATION
-int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *,
-		  struct vm_area_struct *, unsigned long, void *), void *arg)
-{
-	struct stable_node *stable_node;
-	struct rmap_item *rmap_item;
-	int ret = SWAP_AGAIN;
-	int search_new_forks = 0;
-
-	VM_BUG_ON(!PageKsm(page));
-	VM_BUG_ON(!PageLocked(page));
-
-	stable_node = page_stable_node(page);
-	if (!stable_node)
-		return ret;
-again:
-	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
-		struct anon_vma *anon_vma = rmap_item->anon_vma;
-		struct anon_vma_chain *vmac;
-		struct vm_area_struct *vma;
-
-		anon_vma_lock_read(anon_vma);
-		anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
-					       0, ULONG_MAX) {
-			vma = vmac->vma;
-			if (rmap_item->address < vma->vm_start ||
-			    rmap_item->address >= vma->vm_end)
-				continue;
-			/*
-			 * Initially we examine only the vma which covers this
-			 * rmap_item; but later, if there is still work to do,
-			 * we examine covering vmas in other mms: in case they
-			 * were forked from the original since ksmd passed.
-			 */
-			if ((rmap_item->mm == vma->vm_mm) == search_new_forks)
-				continue;
-
-			ret = rmap_one(page, vma, rmap_item->address, arg);
-			if (ret != SWAP_AGAIN) {
+			if (rwc->done && rwc->done(page)) {
 				anon_vma_unlock_read(anon_vma);
 				goto out;
 			}
@@ -2047,6 +1953,7 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_MIGRATION
 void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 {
 	struct stable_node *stable_node;
diff --git a/mm/memblock.c b/mm/memblock.c
index 53e477bb555..1c2ef2c7eda 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -21,6 +21,9 @@
 #include <linux/memblock.h>
 
 #include <asm-generic/sections.h>
+#include <linux/io.h>
+
+#include "internal.h"
 
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
@@ -39,6 +42,9 @@ struct memblock memblock __initdata_memblock = {
 };
 
 int memblock_debug __initdata_memblock;
+#ifdef CONFIG_MOVABLE_NODE
+bool movable_node_enabled __initdata_memblock = false;
+#endif
 static int memblock_can_resize __initdata_memblock;
 static int memblock_memory_in_slab __initdata_memblock = 0;
 static int memblock_reserved_in_slab __initdata_memblock = 0;
@@ -91,7 +97,7 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
  * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
  * @size: size of free area to find
  * @align: alignment of free area to find
- * @nid: nid of the free area to find, %MAX_NUMNODES for any node
+ * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
  *
  * Utility called from memblock_find_in_range_node(), find free area bottom-up.
  *
@@ -123,7 +129,7 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
  * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
  * @size: size of free area to find
  * @align: alignment of free area to find
- * @nid: nid of the free area to find, %MAX_NUMNODES for any node
+ * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
  *
  * Utility called from memblock_find_in_range_node(), find free area top-down.
  *
@@ -154,11 +160,11 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
 
 /**
  * memblock_find_in_range_node - find free area in given range and node
- * @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
  * @size: size of free area to find
  * @align: alignment of free area to find
- * @nid: nid of the free area to find, %MAX_NUMNODES for any node
+ * @start: start of candidate range
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
  *
  * Find @size free area aligned to @align in the specified range and node.
  *
@@ -173,9 +179,9 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
  * RETURNS:
  * Found address on success, 0 on failure.
  */
-phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
-					phys_addr_t end, phys_addr_t size,
-					phys_addr_t align, int nid)
+phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
+					phys_addr_t align, phys_addr_t start,
+					phys_addr_t end, int nid)
 {
 	int ret;
 	phys_addr_t kernel_end;
@@ -238,8 +244,8 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					phys_addr_t end, phys_addr_t size,
 					phys_addr_t align)
 {
-	return memblock_find_in_range_node(start, end, size, align,
-					   MAX_NUMNODES);
+	return memblock_find_in_range_node(size, align, start, end,
+					    NUMA_NO_NODE);
 }
 
 static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
@@ -255,6 +261,7 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 		type->cnt = 1;
 		type->regions[0].base = 0;
 		type->regions[0].size = 0;
+		type->regions[0].flags = 0;
 		memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
 	}
 }
@@ -265,6 +272,19 @@ phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
 	if (memblock.reserved.regions == memblock_reserved_init_regions)
 		return 0;
 
+	/*
+	 * Don't allow nobootmem allocator to free reserved memory regions
+	 * array if
+	 *  - CONFIG_DEBUG_FS is enabled;
+	 *  - CONFIG_ARCH_DISCARD_MEMBLOCK is not enabled;
+	 *  - reserved memory regions array have been resized during boot.
+	 * Otherwise debug_fs entry "sys/kernel/debug/memblock/reserved"
+	 * will show garbage instead of state of memory reservations.
+	 */
+	if (IS_ENABLED(CONFIG_DEBUG_FS) &&
+	    !IS_ENABLED(CONFIG_ARCH_DISCARD_MEMBLOCK))
+		return 0;
+
 	*addr = __pa(memblock.reserved.regions);
 
 	return PAGE_ALIGN(sizeof(struct memblock_region) *
@@ -405,7 +425,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
 
 		if (this->base + this->size != next->base ||
 		    memblock_get_region_node(this) !=
-		    memblock_get_region_node(next)) {
+		    memblock_get_region_node(next) ||
+		    this->flags != next->flags) {
 			BUG_ON(this->base + this->size > next->base);
 			i++;
 			continue;
@@ -425,13 +446,15 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
  * @base:	base address of the new region
  * @size:	size of the new region
  * @nid:	node id of the new region
+ * @flags:	flags of the new region
  *
  * Insert new memblock region [@base,@base+@size) into @type at @idx.
  * @type must already have extra room to accomodate the new region.
  */
 static void __init_memblock memblock_insert_region(struct memblock_type *type,
 						   int idx, phys_addr_t base,
-						   phys_addr_t size, int nid)
+						   phys_addr_t size,
+						   int nid, unsigned long flags)
 {
 	struct memblock_region *rgn = &type->regions[idx];
 
@@ -439,6 +462,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
 	memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn));
 	rgn->base = base;
 	rgn->size = size;
+	rgn->flags = flags;
 	memblock_set_region_node(rgn, nid);
 	type->cnt++;
 	type->total_size += size;
@@ -450,6 +474,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
  * @base: base address of the new region
  * @size: size of the new region
  * @nid: nid of the new region
+ * @flags: flags of the new region
  *
  * Add new memblock region [@base,@base+@size) into @type.  The new region
  * is allowed to overlap with existing ones - overlaps don't affect already
@@ -460,7 +485,8 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
  * 0 on success, -errno on failure.
  */
 static int __init_memblock memblock_add_region(struct memblock_type *type,
-				phys_addr_t base, phys_addr_t size, int nid)
+				phys_addr_t base, phys_addr_t size,
+				int nid, unsigned long flags)
 {
 	bool insert = false;
 	phys_addr_t obase = base;
@@ -475,6 +501,7 @@ static int __init_memblock memblock_add_region(struct memblock_type *type,
 		WARN_ON(type->cnt != 1 || type->total_size);
 		type->regions[0].base = base;
 		type->regions[0].size = size;
+		type->regions[0].flags = flags;
 		memblock_set_region_node(&type->regions[0], nid);
 		type->total_size = size;
 		return 0;
@@ -505,7 +532,8 @@ repeat:
 			nr_new++;
 			if (insert)
 				memblock_insert_region(type, i++, base,
-						       rbase - base, nid);
+						       rbase - base, nid,
+						       flags);
 		}
 		/* area below @rend is dealt with, forget about it */
 		base = min(rend, end);
@@ -515,7 +543,8 @@ repeat:
 	if (base < end) {
 		nr_new++;
 		if (insert)
-			memblock_insert_region(type, i, base, end - base, nid);
+			memblock_insert_region(type, i, base, end - base,
+					       nid, flags);
 	}
 
 	/*
@@ -537,12 +566,13 @@ repeat:
 int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
 				       int nid)
 {
-	return memblock_add_region(&memblock.memory, base, size, nid);
+	return memblock_add_region(&memblock.memory, base, size, nid, 0);
 }
 
 int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
-	return memblock_add_region(&memblock.memory, base, size, MAX_NUMNODES);
+	return memblock_add_region(&memblock.memory, base, size,
+				   MAX_NUMNODES, 0);
 }
 
 /**
@@ -597,7 +627,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
 			rgn->size -= base - rbase;
 			type->total_size -= base - rbase;
 			memblock_insert_region(type, i, rbase, base - rbase,
-					       memblock_get_region_node(rgn));
+					       memblock_get_region_node(rgn),
+					       rgn->flags);
 		} else if (rend > end) {
 			/*
 			 * @rgn intersects from above.  Split and redo the
@@ -607,7 +638,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
 			rgn->size -= end - rbase;
 			type->total_size -= end - rbase;
 			memblock_insert_region(type, i--, rbase, end - rbase,
-					       memblock_get_region_node(rgn));
+					       memblock_get_region_node(rgn),
+					       rgn->flags);
 		} else {
 			/* @rgn is fully contained, record it */
 			if (!*end_rgn)
@@ -643,28 +675,89 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
 {
 	memblock_dbg("   memblock_free: [%#016llx-%#016llx] %pF\n",
 		     (unsigned long long)base,
-		     (unsigned long long)base + size,
+		     (unsigned long long)base + size - 1,
 		     (void *)_RET_IP_);
 
 	return __memblock_remove(&memblock.reserved, base, size);
 }
 
-int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
+static int __init_memblock memblock_reserve_region(phys_addr_t base,
+						   phys_addr_t size,
+						   int nid,
+						   unsigned long flags)
 {
 	struct memblock_type *_rgn = &memblock.reserved;
 
-	memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n",
+	memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n",
 		     (unsigned long long)base,
-		     (unsigned long long)base + size,
-		     (void *)_RET_IP_);
+		     (unsigned long long)base + size - 1,
+		     flags, (void *)_RET_IP_);
 
-	return memblock_add_region(_rgn, base, size, MAX_NUMNODES);
+	return memblock_add_region(_rgn, base, size, nid, flags);
+}
+
+int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_reserve_region(base, size, MAX_NUMNODES, 0);
+}
+
+/**
+ * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * This function isolates region [@base, @base + @size), and mark it with flag
+ * MEMBLOCK_HOTPLUG.
+ *
+ * Return 0 on succees, -errno on failure.
+ */
+int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
+{
+	struct memblock_type *type = &memblock.memory;
+	int i, ret, start_rgn, end_rgn;
+
+	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
+	if (ret)
+		return ret;
+
+	for (i = start_rgn; i < end_rgn; i++)
+		memblock_set_region_flags(&type->regions[i], MEMBLOCK_HOTPLUG);
+
+	memblock_merge_regions(type);
+	return 0;
+}
+
+/**
+ * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * This function isolates region [@base, @base + @size), and clear flag
+ * MEMBLOCK_HOTPLUG for the isolated regions.
+ *
+ * Return 0 on succees, -errno on failure.
+ */
+int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
+{
+	struct memblock_type *type = &memblock.memory;
+	int i, ret, start_rgn, end_rgn;
+
+	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
+	if (ret)
+		return ret;
+
+	for (i = start_rgn; i < end_rgn; i++)
+		memblock_clear_region_flags(&type->regions[i],
+					    MEMBLOCK_HOTPLUG);
+
+	memblock_merge_regions(type);
+	return 0;
 }
 
 /**
  * __next_free_mem_range - next function for for_each_free_mem_range()
  * @idx: pointer to u64 loop variable
- * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @nid: node selector, %NUMA_NO_NODE for all nodes
  * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @out_nid: ptr to int for nid of the range, can be %NULL
@@ -693,13 +786,16 @@ void __init_memblock __next_free_mem_range(u64 *idx, int nid,
 	int mi = *idx & 0xffffffff;
 	int ri = *idx >> 32;
 
+	if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
+		nid = NUMA_NO_NODE;
+
 	for ( ; mi < mem->cnt; mi++) {
 		struct memblock_region *m = &mem->regions[mi];
 		phys_addr_t m_start = m->base;
 		phys_addr_t m_end = m->base + m->size;
 
 		/* only memory regions are associated with nodes, check it */
-		if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m))
+		if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m))
 			continue;
 
 		/* scan areas before each reservation for intersection */
@@ -740,12 +836,17 @@ void __init_memblock __next_free_mem_range(u64 *idx, int nid,
 /**
  * __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse()
  * @idx: pointer to u64 loop variable
- * @nid: nid: node selector, %MAX_NUMNODES for all nodes
+ * @nid: nid: node selector, %NUMA_NO_NODE for all nodes
  * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @out_nid: ptr to int for nid of the range, can be %NULL
  *
  * Reverse of __next_free_mem_range().
+ *
+ * Linux kernel cannot migrate pages used by itself. Memory hotplug users won't
+ * be able to hot-remove hotpluggable memory used by the kernel. So this
+ * function skip hotpluggable regions if needed when allocating memory for the
+ * kernel.
  */
 void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid,
 					   phys_addr_t *out_start,
@@ -756,6 +857,9 @@ void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid,
 	int mi = *idx & 0xffffffff;
 	int ri = *idx >> 32;
 
+	if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
+		nid = NUMA_NO_NODE;
+
 	if (*idx == (u64)ULLONG_MAX) {
 		mi = mem->cnt - 1;
 		ri = rsv->cnt;
@@ -767,7 +871,11 @@ void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid,
 		phys_addr_t m_end = m->base + m->size;
 
 		/* only memory regions are associated with nodes, check it */
-		if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m))
+		if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m))
+			continue;
+
+		/* skip hotpluggable memory regions if needed */
+		if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
 			continue;
 
 		/* scan areas before each reservation for intersection */
@@ -837,18 +945,18 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid,
  * memblock_set_node - set node ID on memblock regions
  * @base: base of area to set node ID for
  * @size: size of area to set node ID for
+ * @type: memblock type to set node ID for
  * @nid: node ID to set
  *
- * Set the nid of memblock memory regions in [@base,@base+@size) to @nid.
+ * Set the nid of memblock @type regions in [@base,@base+@size) to @nid.
  * Regions which cross the area boundaries are split as necessary.
  *
  * RETURNS:
  * 0 on success, -errno on failure.
  */
 int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
-				      int nid)
+				      struct memblock_type *type, int nid)
 {
-	struct memblock_type *type = &memblock.memory;
 	int start_rgn, end_rgn;
 	int i, ret;
 
@@ -870,13 +978,13 @@ static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
 {
 	phys_addr_t found;
 
-	if (WARN_ON(!align))
-		align = __alignof__(long long);
+	if (!align)
+		align = SMP_CACHE_BYTES;
 
 	/* align @size to avoid excessive fragmentation on reserved array */
 	size = round_up(size, align);
 
-	found = memblock_find_in_range_node(0, max_addr, size, align, nid);
+	found = memblock_find_in_range_node(size, align, 0, max_addr, nid);
 	if (found && !memblock_reserve(found, size))
 		return found;
 
@@ -890,7 +998,7 @@ phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int n
 
 phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	return memblock_alloc_base_nid(size, align, max_addr, MAX_NUMNODES);
+	return memblock_alloc_base_nid(size, align, max_addr, NUMA_NO_NODE);
 }
 
 phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
@@ -920,6 +1028,207 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
 	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
+/**
+ * memblock_virt_alloc_internal - allocate boot memory block
+ * @size: size of memory block to be allocated in bytes
+ * @align: alignment of the region and block's size
+ * @min_addr: the lower bound of the memory region to allocate (phys address)
+ * @max_addr: the upper bound of the memory region to allocate (phys address)
+ * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
+ *
+ * The @min_addr limit is dropped if it can not be satisfied and the allocation
+ * will fall back to memory below @min_addr. Also, allocation may fall back
+ * to any node in the system if the specified node can not
+ * hold the requested memory.
+ *
+ * The allocation is performed from memory region limited by
+ * memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE.
+ *
+ * The memory block is aligned on SMP_CACHE_BYTES if @align == 0.
+ *
+ * The phys address of allocated boot memory block is converted to virtual and
+ * allocated memory is reset to 0.
+ *
+ * In addition, function sets the min_count to 0 using kmemleak_alloc for
+ * allocated boot memory block, so that it is never reported as leaks.
+ *
+ * RETURNS:
+ * Virtual address of allocated memory block on success, NULL on failure.
+ */
+static void * __init memblock_virt_alloc_internal(
+				phys_addr_t size, phys_addr_t align,
+				phys_addr_t min_addr, phys_addr_t max_addr,
+				int nid)
+{
+	phys_addr_t alloc;
+	void *ptr;
+
+	if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
+		nid = NUMA_NO_NODE;
+
+	/*
+	 * Detect any accidental use of these APIs after slab is ready, as at
+	 * this moment memblock may be deinitialized already and its
+	 * internal data may be destroyed (after execution of free_all_bootmem)
+	 */
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, nid);
+
+	if (!align)
+		align = SMP_CACHE_BYTES;
+
+	/* align @size to avoid excessive fragmentation on reserved array */
+	size = round_up(size, align);
+
+again:
+	alloc = memblock_find_in_range_node(size, align, min_addr, max_addr,
+					    nid);
+	if (alloc)
+		goto done;
+
+	if (nid != NUMA_NO_NODE) {
+		alloc = memblock_find_in_range_node(size, align, min_addr,
+						    max_addr,  NUMA_NO_NODE);
+		if (alloc)
+			goto done;
+	}
+
+	if (min_addr) {
+		min_addr = 0;
+		goto again;
+	} else {
+		goto error;
+	}
+
+done:
+	memblock_reserve(alloc, size);
+	ptr = phys_to_virt(alloc);
+	memset(ptr, 0, size);
+
+	/*
+	 * The min_count is set to 0 so that bootmem allocated blocks
+	 * are never reported as leaks. This is because many of these blocks
+	 * are only referred via the physical address which is not
+	 * looked up by kmemleak.
+	 */
+	kmemleak_alloc(ptr, size, 0, 0);
+
+	return ptr;
+
+error:
+	return NULL;
+}
+
+/**
+ * memblock_virt_alloc_try_nid_nopanic - allocate boot memory block
+ * @size: size of memory block to be allocated in bytes
+ * @align: alignment of the region and block's size
+ * @min_addr: the lower bound of the memory region from where the allocation
+ *	  is preferred (phys address)
+ * @max_addr: the upper bound of the memory region from where the allocation
+ *	      is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to
+ *	      allocate only from memory limited by memblock.current_limit value
+ * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
+ *
+ * Public version of _memblock_virt_alloc_try_nid_nopanic() which provides
+ * additional debug information (including caller info), if enabled.
+ *
+ * RETURNS:
+ * Virtual address of allocated memory block on success, NULL on failure.
+ */
+void * __init memblock_virt_alloc_try_nid_nopanic(
+				phys_addr_t size, phys_addr_t align,
+				phys_addr_t min_addr, phys_addr_t max_addr,
+				int nid)
+{
+	memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx %pF\n",
+		     __func__, (u64)size, (u64)align, nid, (u64)min_addr,
+		     (u64)max_addr, (void *)_RET_IP_);
+	return memblock_virt_alloc_internal(size, align, min_addr,
+					     max_addr, nid);
+}
+
+/**
+ * memblock_virt_alloc_try_nid - allocate boot memory block with panicking
+ * @size: size of memory block to be allocated in bytes
+ * @align: alignment of the region and block's size
+ * @min_addr: the lower bound of the memory region from where the allocation
+ *	  is preferred (phys address)
+ * @max_addr: the upper bound of the memory region from where the allocation
+ *	      is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to
+ *	      allocate only from memory limited by memblock.current_limit value
+ * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
+ *
+ * Public panicking version of _memblock_virt_alloc_try_nid_nopanic()
+ * which provides debug information (including caller info), if enabled,
+ * and panics if the request can not be satisfied.
+ *
+ * RETURNS:
+ * Virtual address of allocated memory block on success, NULL on failure.
+ */
+void * __init memblock_virt_alloc_try_nid(
+			phys_addr_t size, phys_addr_t align,
+			phys_addr_t min_addr, phys_addr_t max_addr,
+			int nid)
+{
+	void *ptr;
+
+	memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx %pF\n",
+		     __func__, (u64)size, (u64)align, nid, (u64)min_addr,
+		     (u64)max_addr, (void *)_RET_IP_);
+	ptr = memblock_virt_alloc_internal(size, align,
+					   min_addr, max_addr, nid);
+	if (ptr)
+		return ptr;
+
+	panic("%s: Failed to allocate %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx\n",
+	      __func__, (u64)size, (u64)align, nid, (u64)min_addr,
+	      (u64)max_addr);
+	return NULL;
+}
+
+/**
+ * __memblock_free_early - free boot memory block
+ * @base: phys starting address of the  boot memory block
+ * @size: size of the boot memory block in bytes
+ *
+ * Free boot memory block previously allocated by memblock_virt_alloc_xx() API.
+ * The freeing memory will not be released to the buddy allocator.
+ */
+void __init __memblock_free_early(phys_addr_t base, phys_addr_t size)
+{
+	memblock_dbg("%s: [%#016llx-%#016llx] %pF\n",
+		     __func__, (u64)base, (u64)base + size - 1,
+		     (void *)_RET_IP_);
+	kmemleak_free_part(__va(base), size);
+	__memblock_remove(&memblock.reserved, base, size);
+}
+
+/*
+ * __memblock_free_late - free bootmem block pages directly to buddy allocator
+ * @addr: phys starting address of the  boot memory block
+ * @size: size of the boot memory block in bytes
+ *
+ * This is only useful when the bootmem allocator has already been torn
+ * down, but we are still initializing the system.  Pages are released directly
+ * to the buddy allocator, no bootmem metadata is updated because it is gone.
+ */
+void __init __memblock_free_late(phys_addr_t base, phys_addr_t size)
+{
+	u64 cursor, end;
+
+	memblock_dbg("%s: [%#016llx-%#016llx] %pF\n",
+		     __func__, (u64)base, (u64)base + size - 1,
+		     (void *)_RET_IP_);
+	kmemleak_free_part(__va(base), size);
+	cursor = PFN_UP(base);
+	end = PFN_DOWN(base + size);
+
+	for (; cursor < end; cursor++) {
+		__free_pages_bootmem(pfn_to_page(cursor), 0);
+		totalram_pages++;
+	}
+}
 
 /*
  * Remaining API functions
@@ -1101,6 +1410,7 @@ void __init_memblock memblock_set_current_limit(phys_addr_t limit)
 static void __init_memblock memblock_dump(struct memblock_type *type, char *name)
 {
 	unsigned long long base, size;
+	unsigned long flags;
 	int i;
 
 	pr_info(" %s.cnt  = 0x%lx\n", name, type->cnt);
@@ -1111,13 +1421,14 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name
 
 		base = rgn->base;
 		size = rgn->size;
+		flags = rgn->flags;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 		if (memblock_get_region_node(rgn) != MAX_NUMNODES)
 			snprintf(nid_buf, sizeof(nid_buf), " on node %d",
 				 memblock_get_region_node(rgn));
 #endif
-		pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s\n",
-			name, i, base, base + size - 1, size, nid_buf);
+		pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s flags: %#lx\n",
+			name, i, base, base + size - 1, size, nid_buf, flags);
 	}
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7caff36180c..67dd2a88143 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1688,13 +1688,13 @@ static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
  */
 void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
-	struct cgroup *task_cgrp;
-	struct cgroup *mem_cgrp;
 	/*
-	 * Need a buffer in BSS, can't rely on allocations. The code relies
-	 * on the assumption that OOM is serialized for memory controller.
-	 * If this assumption is broken, revisit this code.
+	 * protects memcg_name and makes sure that parallel ooms do not
+	 * interleave
 	 */
+	static DEFINE_SPINLOCK(oom_info_lock);
+	struct cgroup *task_cgrp;
+	struct cgroup *mem_cgrp;
 	static char memcg_name[PATH_MAX];
 	int ret;
 	struct mem_cgroup *iter;
@@ -1703,6 +1703,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	if (!p)
 		return;
 
+	spin_lock(&oom_info_lock);
 	rcu_read_lock();
 
 	mem_cgrp = memcg->css.cgroup;
@@ -1771,6 +1772,7 @@ done:
 
 		pr_cont("\n");
 	}
+	spin_unlock(&oom_info_lock);
 }
 
 /*
@@ -3000,7 +3002,8 @@ static DEFINE_MUTEX(set_limit_mutex);
 static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
 {
 	return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) &&
-		(memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK);
+		(memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK) ==
+							KMEM_ACCOUNTED_MASK;
 }
 
 /*
@@ -3126,7 +3129,7 @@ int memcg_cache_id(struct mem_cgroup *memcg)
  * But when we create a new cache, we can call this as well if its parent
  * is kmem-limited. That will have to hold set_limit_mutex as well.
  */
-int memcg_update_cache_sizes(struct mem_cgroup *memcg)
+static int memcg_update_cache_sizes(struct mem_cgroup *memcg)
 {
 	int num, ret;
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index fabe55046c1..b25ed321e66 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -611,7 +611,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn)
 }
 
 /*
- * Dirty cache page page
+ * Dirty pagecache page
  * Issues: when the error hit a hole page the error is not properly
  * propagated.
  */
@@ -1585,7 +1585,13 @@ static int __soft_offline_page(struct page *page, int flags)
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
-			putback_lru_pages(&pagelist);
+			if (!list_empty(&pagelist)) {
+				list_del(&page->lru);
+				dec_zone_page_state(page, NR_ISOLATED_ANON +
+						page_is_file_cache(page));
+				putback_lru_page(page);
+			}
+
 			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 				pfn, ret, page->flags);
 			if (ret > 0)
diff --git a/mm/memory.c b/mm/memory.c
index 6768ce9e57d..86487dfa5e5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -59,6 +59,7 @@
 #include <linux/gfp.h>
 #include <linux/migrate.h>
 #include <linux/string.h>
+#include <linux/dma-debug.h>
 
 #include <asm/io.h>
 #include <asm/pgalloc.h>
@@ -2559,6 +2560,8 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
 
 static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
 {
+	debug_dma_assert_idle(src);
+
 	/*
 	 * If the source page was a PFN mapping, we don't have
 	 * a "struct page" for it. We do a best-effort copy by
@@ -4272,11 +4275,20 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
 #if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS
+
+static struct kmem_cache *page_ptl_cachep;
+
+void __init ptlock_cache_init(void)
+{
+	page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
+			SLAB_PANIC, NULL);
+}
+
 bool ptlock_alloc(struct page *page)
 {
 	spinlock_t *ptl;
 
-	ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
+	ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
 	if (!ptl)
 		return false;
 	page->ptl = ptl;
@@ -4285,6 +4297,6 @@ bool ptlock_alloc(struct page *page)
 
 void ptlock_free(struct page *page)
 {
-	kfree(page->ptl);
+	kmem_cache_free(page_ptl_cachep, page->ptl);
 }
 #endif
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 489f235502d..cc2ab37220b 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -9,7 +9,6 @@
 #include <linux/swap.h>
 #include <linux/interrupt.h>
 #include <linux/pagemap.h>
-#include <linux/bootmem.h>
 #include <linux/compiler.h>
 #include <linux/export.h>
 #include <linux/pagevec.h>
@@ -269,7 +268,7 @@ static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
 }
 
 /* Can fail with -ENOMEM from allocating a wait table with vmalloc() or
- * alloc_bootmem_node_nopanic() */
+ * alloc_bootmem_node_nopanic()/memblock_virt_alloc_node_nopanic() */
 static int __ref ensure_zone_is_initialized(struct zone *zone,
 			unsigned long start_pfn, unsigned long num_pages)
 {
@@ -1446,6 +1445,7 @@ static int __init cmdline_parse_movable_node(char *p)
 	 * the kernel away from hotpluggable memory.
 	 */
 	memblock_set_bottom_up(true);
+	movable_node_enabled = true;
 #else
 	pr_warn("movable_node option not supported\n");
 #endif
diff --git a/mm/migrate.c b/mm/migrate.c
index 9194375b230..a8025befc32 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -72,28 +72,12 @@ int migrate_prep_local(void)
 }
 
 /*
- * Add isolated pages on the list back to the LRU under page lock
- * to avoid leaking evictable pages back onto unevictable list.
- */
-void putback_lru_pages(struct list_head *l)
-{
-	struct page *page;
-	struct page *page2;
-
-	list_for_each_entry_safe(page, page2, l, lru) {
-		list_del(&page->lru);
-		dec_zone_page_state(page, NR_ISOLATED_ANON +
-				page_is_file_cache(page));
-			putback_lru_page(page);
-	}
-}
-
-/*
  * Put previously isolated pages back onto the appropriate lists
  * from where they were once taken off for compaction/migration.
  *
- * This function shall be used instead of putback_lru_pages(),
- * whenever the isolated pageset has been built by isolate_migratepages_range()
+ * This function shall be used whenever the isolated pageset has been
+ * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range()
+ * and isolate_huge_page().
  */
 void putback_movable_pages(struct list_head *l)
 {
@@ -199,7 +183,12 @@ out:
  */
 static void remove_migration_ptes(struct page *old, struct page *new)
 {
-	rmap_walk(new, remove_migration_pte, old);
+	struct rmap_walk_control rwc = {
+		.rmap_one = remove_migration_pte,
+		.arg = old,
+	};
+
+	rmap_walk(new, &rwc);
 }
 
 /*
@@ -563,14 +552,6 @@ void migrate_page_copy(struct page *newpage, struct page *page)
  *                    Migration functions
  ***********************************************************/
 
-/* Always fail migration. Used for mappings that are not movable */
-int fail_migrate_page(struct address_space *mapping,
-			struct page *newpage, struct page *page)
-{
-	return -EIO;
-}
-EXPORT_SYMBOL(fail_migrate_page);
-
 /*
  * Common logic to directly migrate a single page suitable for
  * pages that do not use PagePrivate/PagePrivate2.
@@ -1008,7 +989,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 {
 	int rc = 0;
 	int *result = NULL;
-	struct page *new_hpage = get_new_page(hpage, private, &result);
+	struct page *new_hpage;
 	struct anon_vma *anon_vma = NULL;
 
 	/*
@@ -1018,9 +999,12 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	 * tables or check whether the hugepage is pmd-based or not before
 	 * kicking migration.
 	 */
-	if (!hugepage_migration_support(page_hstate(hpage)))
+	if (!hugepage_migration_support(page_hstate(hpage))) {
+		putback_active_hugepage(hpage);
 		return -ENOSYS;
+	}
 
+	new_hpage = get_new_page(hpage, private, &result);
 	if (!new_hpage)
 		return -ENOMEM;
 
@@ -1120,7 +1104,12 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 				nr_succeeded++;
 				break;
 			default:
-				/* Permanent failure */
+				/*
+				 * Permanent failure (-EBUSY, -ENOSYS, etc.):
+				 * unlike -EAGAIN case, the failed page is
+				 * removed from migration page list and not
+				 * retried in the next outer loop.
+				 */
 				nr_failed++;
 				break;
 			}
@@ -1594,31 +1583,38 @@ bool migrate_ratelimited(int node)
 }
 
 /* Returns true if the node is migrate rate-limited after the update */
-bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages)
+static bool numamigrate_update_ratelimit(pg_data_t *pgdat,
+					unsigned long nr_pages)
 {
-	bool rate_limited = false;
-
 	/*
 	 * Rate-limit the amount of data that is being migrated to a node.
 	 * Optimal placement is no good if the memory bus is saturated and
 	 * all the time is being spent migrating!
 	 */
-	spin_lock(&pgdat->numabalancing_migrate_lock);
 	if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) {
+		spin_lock(&pgdat->numabalancing_migrate_lock);
 		pgdat->numabalancing_migrate_nr_pages = 0;
 		pgdat->numabalancing_migrate_next_window = jiffies +
 			msecs_to_jiffies(migrate_interval_millisecs);
+		spin_unlock(&pgdat->numabalancing_migrate_lock);
 	}
-	if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages)
-		rate_limited = true;
-	else
-		pgdat->numabalancing_migrate_nr_pages += nr_pages;
-	spin_unlock(&pgdat->numabalancing_migrate_lock);
-	
-	return rate_limited;
+	if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) {
+		trace_mm_numa_migrate_ratelimit(current, pgdat->node_id,
+								nr_pages);
+		return true;
+	}
+
+	/*
+	 * This is an unlocked non-atomic update so errors are possible.
+	 * The consequences are failing to migrate when we potentiall should
+	 * have which is not severe enough to warrant locking. If it is ever
+	 * a problem, it can be converted to a per-cpu counter.
+	 */
+	pgdat->numabalancing_migrate_nr_pages += nr_pages;
+	return false;
 }
 
-int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
+static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 {
 	int page_lru;
 
@@ -1705,7 +1701,12 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 	nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
 				     node, MIGRATE_ASYNC, MR_NUMA_MISPLACED);
 	if (nr_remaining) {
-		putback_lru_pages(&migratepages);
+		if (!list_empty(&migratepages)) {
+			list_del(&page->lru);
+			dec_zone_page_state(page, NR_ISOLATED_ANON +
+					page_is_file_cache(page));
+			putback_lru_page(page);
+		}
 		isolated = 0;
 	} else
 		count_vm_numa_event(NUMA_PAGE_MIGRATE);
diff --git a/mm/mlock.c b/mm/mlock.c
index 192e6eebe4f..10819ed4df3 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -709,19 +709,21 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 
 	lru_add_drain_all();	/* flush pagevec */
 
-	down_write(&current->mm->mmap_sem);
 	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
 	start &= PAGE_MASK;
 
-	locked = len >> PAGE_SHIFT;
-	locked += current->mm->locked_vm;
-
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
+	locked = len >> PAGE_SHIFT;
+
+	down_write(&current->mm->mmap_sem);
+
+	locked += current->mm->locked_vm;
 
 	/* check against resource limits */
 	if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
 		error = do_mlock(start, len, 1);
+
 	up_write(&current->mm->mmap_sem);
 	if (!error)
 		error = __mm_populate(start, len, 0);
@@ -732,11 +734,13 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
-	down_write(&current->mm->mmap_sem);
 	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
 	start &= PAGE_MASK;
+
+	down_write(&current->mm->mmap_sem);
 	ret = do_mlock(start, len, 0);
 	up_write(&current->mm->mmap_sem);
+
 	return ret;
 }
 
@@ -781,12 +785,12 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 	if (flags & MCL_CURRENT)
 		lru_add_drain_all();	/* flush pagevec */
 
-	down_write(&current->mm->mmap_sem);
-
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
 
 	ret = -ENOMEM;
+	down_write(&current->mm->mmap_sem);
+
 	if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
 	    capable(CAP_IPC_LOCK))
 		ret = do_mlockall(flags);
diff --git a/mm/mmap.c b/mm/mmap.c
index 834b2d785f1..a0e7153a79e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -86,6 +86,7 @@ EXPORT_SYMBOL(vm_get_page_prot);
 
 int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;  /* heuristic overcommit */
 int sysctl_overcommit_ratio __read_mostly = 50;	/* default is 50% */
+unsigned long sysctl_overcommit_kbytes __read_mostly;
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
 unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
 unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
@@ -1190,6 +1191,24 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
 	return hint;
 }
 
+static inline int mlock_future_check(struct mm_struct *mm,
+				     unsigned long flags,
+				     unsigned long len)
+{
+	unsigned long locked, lock_limit;
+
+	/*  mlock MCL_FUTURE? */
+	if (flags & VM_LOCKED) {
+		locked = len >> PAGE_SHIFT;
+		locked += mm->locked_vm;
+		lock_limit = rlimit(RLIMIT_MEMLOCK);
+		lock_limit >>= PAGE_SHIFT;
+		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+			return -EAGAIN;
+	}
+	return 0;
+}
+
 /*
  * The caller must hold down_write(&current->mm->mmap_sem).
  */
@@ -1251,16 +1270,8 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 		if (!can_do_mlock())
 			return -EPERM;
 
-	/* mlock MCL_FUTURE? */
-	if (vm_flags & VM_LOCKED) {
-		unsigned long locked, lock_limit;
-		locked = len >> PAGE_SHIFT;
-		locked += mm->locked_vm;
-		lock_limit = rlimit(RLIMIT_MEMLOCK);
-		lock_limit >>= PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			return -EAGAIN;
-	}
+	if (mlock_future_check(mm, vm_flags, len))
+		return -EAGAIN;
 
 	if (file) {
 		struct inode *inode = file_inode(file);
@@ -2591,18 +2602,9 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 	if (error & ~PAGE_MASK)
 		return error;
 
-	/*
-	 * mlock MCL_FUTURE?
-	 */
-	if (mm->def_flags & VM_LOCKED) {
-		unsigned long locked, lock_limit;
-		locked = len >> PAGE_SHIFT;
-		locked += mm->locked_vm;
-		lock_limit = rlimit(RLIMIT_MEMLOCK);
-		lock_limit >>= PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			return -EAGAIN;
-	}
+	error = mlock_future_check(mm, mm->def_flags, len);
+	if (error)
+		return error;
 
 	/*
 	 * mm->mmap_sem is required to protect against another thread
diff --git a/mm/mprotect.c b/mm/mprotect.c
index bb53a6591ae..7332c178574 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -23,6 +23,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
 #include <linux/perf_event.h>
+#include <linux/ksm.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
@@ -63,7 +64,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 				ptent = *pte;
 				page = vm_normal_page(vma, addr, oldpte);
-				if (page) {
+				if (page && !PageKsm(page)) {
 					if (!pte_numa(oldpte)) {
 						ptent = pte_mknuma(ptent);
 						set_pte_at(mm, addr, pte, ptent);
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 2c254d37465..19121ceb887 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -41,7 +41,7 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 	if (limit > memblock.current_limit)
 		limit = memblock.current_limit;
 
-	addr = memblock_find_in_range_node(goal, limit, size, align, nid);
+	addr = memblock_find_in_range_node(size, align, goal, limit, nid);
 	if (!addr)
 		return NULL;
 
@@ -117,7 +117,7 @@ static unsigned long __init free_low_memory_core_early(void)
 	phys_addr_t start, end, size;
 	u64 i;
 
-	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
+	for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL)
 		count += __free_memory_core(start, end);
 
 	/* free range that is used for reserved array if we allocate it */
@@ -161,7 +161,7 @@ unsigned long __init free_all_bootmem(void)
 	reset_all_zones_managed_pages();
 
 	/*
-	 * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id
+	 * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id
 	 *  because in some case like Node0 doesn't have RAM installed
 	 *  low ram will be on Node1
 	 */
@@ -215,7 +215,7 @@ static void * __init ___alloc_bootmem_nopanic(unsigned long size,
 
 restart:
 
-	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit);
+	ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit);
 
 	if (ptr)
 		return ptr;
@@ -299,7 +299,7 @@ again:
 	if (ptr)
 		return ptr;
 
-	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align,
+	ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align,
 					goal, limit);
 	if (ptr)
 		return ptr;
diff --git a/mm/nommu.c b/mm/nommu.c
index fec093adad9..8740213b164 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -60,6 +60,7 @@ unsigned long highest_memmap_pfn;
 struct percpu_counter vm_committed_as;
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50; /* default is 50% */
+unsigned long sysctl_overcommit_kbytes __read_mostly;
 int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
 int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
 unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 1e4a600a616..054ff47c447 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -47,19 +47,21 @@ static DEFINE_SPINLOCK(zone_scan_lock);
 #ifdef CONFIG_NUMA
 /**
  * has_intersects_mems_allowed() - check task eligiblity for kill
- * @tsk: task struct of which task to consider
+ * @start: task struct of which task to consider
  * @mask: nodemask passed to page allocator for mempolicy ooms
  *
  * Task eligibility is determined by whether or not a candidate task, @tsk,
  * shares the same mempolicy nodes as current if it is bound by such a policy
  * and whether or not it has the same set of allowed cpuset nodes.
  */
-static bool has_intersects_mems_allowed(struct task_struct *tsk,
+static bool has_intersects_mems_allowed(struct task_struct *start,
 					const nodemask_t *mask)
 {
-	struct task_struct *start = tsk;
+	struct task_struct *tsk;
+	bool ret = false;
 
-	do {
+	rcu_read_lock();
+	for_each_thread(start, tsk) {
 		if (mask) {
 			/*
 			 * If this is a mempolicy constrained oom, tsk's
@@ -67,19 +69,20 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
 			 * mempolicy intersects current, otherwise it may be
 			 * needlessly killed.
 			 */
-			if (mempolicy_nodemask_intersects(tsk, mask))
-				return true;
+			ret = mempolicy_nodemask_intersects(tsk, mask);
 		} else {
 			/*
 			 * This is not a mempolicy constrained oom, so only
 			 * check the mems of tsk's cpuset.
 			 */
-			if (cpuset_mems_allowed_intersects(current, tsk))
-				return true;
+			ret = cpuset_mems_allowed_intersects(current, tsk);
 		}
-	} while_each_thread(start, tsk);
+		if (ret)
+			break;
+	}
+	rcu_read_unlock();
 
-	return false;
+	return ret;
 }
 #else
 static bool has_intersects_mems_allowed(struct task_struct *tsk,
@@ -97,16 +100,21 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
  */
 struct task_struct *find_lock_task_mm(struct task_struct *p)
 {
-	struct task_struct *t = p;
+	struct task_struct *t;
 
-	do {
+	rcu_read_lock();
+
+	for_each_thread(p, t) {
 		task_lock(t);
 		if (likely(t->mm))
-			return t;
+			goto found;
 		task_unlock(t);
-	} while_each_thread(p, t);
+	}
+	t = NULL;
+found:
+	rcu_read_unlock();
 
-	return NULL;
+	return t;
 }
 
 /* return true if the task is not adequate as candidate victim task. */
@@ -301,7 +309,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 	unsigned long chosen_points = 0;
 
 	rcu_read_lock();
-	do_each_thread(g, p) {
+	for_each_process_thread(g, p) {
 		unsigned int points;
 
 		switch (oom_scan_process_thread(p, totalpages, nodemask,
@@ -323,7 +331,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 			chosen = p;
 			chosen_points = points;
 		}
-	} while_each_thread(g, p);
+	}
 	if (chosen)
 		get_task_struct(chosen);
 	rcu_read_unlock();
@@ -406,7 +414,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 {
 	struct task_struct *victim = p;
 	struct task_struct *child;
-	struct task_struct *t = p;
+	struct task_struct *t;
 	struct mm_struct *mm;
 	unsigned int victim_points = 0;
 	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
@@ -437,7 +445,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * still freeing memory.
 	 */
 	read_lock(&tasklist_lock);
-	do {
+	for_each_thread(p, t) {
 		list_for_each_entry(child, &t->children, sibling) {
 			unsigned int child_points;
 
@@ -455,13 +463,11 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 				get_task_struct(victim);
 			}
 		}
-	} while_each_thread(p, t);
+	}
 	read_unlock(&tasklist_lock);
 
-	rcu_read_lock();
 	p = find_lock_task_mm(victim);
 	if (!p) {
-		rcu_read_unlock();
 		put_task_struct(victim);
 		return;
 	} else if (victim != p) {
@@ -487,6 +493,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * That thread will now get access to memory reserves since it has a
 	 * pending fatal signal.
 	 */
+	rcu_read_lock();
 	for_each_process(p)
 		if (p->mm == mm && !same_thread_group(p, victim) &&
 		    !(p->flags & PF_KTHREAD)) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5248fe070aa..533e2147d14 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2072,13 +2072,6 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 		return;
 
 	/*
-	 * Walking all memory to count page types is very expensive and should
-	 * be inhibited in non-blockable contexts.
-	 */
-	if (!(gfp_mask & __GFP_WAIT))
-		filter |= SHOW_MEM_FILTER_PAGE_COUNT;
-
-	/*
 	 * This documents exceptions given to allocations in certain
 	 * contexts that are allowed to allocate outside current's set
 	 * of allowed nodes.
@@ -2242,10 +2235,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 				preferred_zone, migratetype);
 		if (page) {
 			preferred_zone->compact_blockskip_flush = false;
-			preferred_zone->compact_considered = 0;
-			preferred_zone->compact_defer_shift = 0;
-			if (order >= preferred_zone->compact_order_failed)
-				preferred_zone->compact_order_failed = order + 1;
+			compaction_defer_reset(preferred_zone, order, true);
 			count_vm_event(COMPACTSUCCESS);
 			return page;
 		}
@@ -2535,8 +2525,15 @@ rebalance:
 	}
 
 	/* Atomic allocations - we can't balance anything */
-	if (!wait)
+	if (!wait) {
+		/*
+		 * All existing users of the deprecated __GFP_NOFAIL are
+		 * blockable, so warn of any new users that actually allow this
+		 * type of allocation to fail.
+		 */
+		WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL);
 		goto nopage;
+	}
 
 	/* Avoid recursion of direct reclaim */
 	if (current->flags & PF_MEMALLOC)
@@ -3901,6 +3898,7 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 	struct page *page;
 	unsigned long block_migratetype;
 	int reserve;
+	int old_reserve;
 
 	/*
 	 * Get the start pfn, end pfn and the number of blocks to reserve
@@ -3922,6 +3920,12 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 	 * future allocation of hugepages at runtime.
 	 */
 	reserve = min(2, reserve);
+	old_reserve = zone->nr_migrate_reserve_block;
+
+	/* When memory hot-add, we almost always need to do nothing */
+	if (reserve == old_reserve)
+		return;
+	zone->nr_migrate_reserve_block = reserve;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
 		if (!pfn_valid(pfn))
@@ -3959,6 +3963,12 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 				reserve--;
 				continue;
 			}
+		} else if (!old_reserve) {
+			/*
+			 * At boot time we don't need to scan the whole zone
+			 * for turning off MIGRATE_RESERVE.
+			 */
+			break;
 		}
 
 		/*
@@ -4209,7 +4219,6 @@ static noinline __init_refok
 int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
 {
 	int i;
-	struct pglist_data *pgdat = zone->zone_pgdat;
 	size_t alloc_size;
 
 	/*
@@ -4225,7 +4234,8 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
 
 	if (!slab_is_available()) {
 		zone->wait_table = (wait_queue_head_t *)
-			alloc_bootmem_node_nopanic(pgdat, alloc_size);
+			memblock_virt_alloc_node_nopanic(
+				alloc_size, zone->zone_pgdat->node_id);
 	} else {
 		/*
 		 * This case means that a zone whose size was 0 gets new memory
@@ -4345,13 +4355,14 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
 #endif
 
 /**
- * free_bootmem_with_active_regions - Call free_bootmem_node for each active range
+ * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range
  * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
- * @max_low_pfn: The highest PFN that will be passed to free_bootmem_node
+ * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid
  *
  * If an architecture guarantees that all ranges registered with
  * add_active_ranges() contain no holes and may be freed, this
- * this function may be used instead of calling free_bootmem() manually.
+ * this function may be used instead of calling memblock_free_early_nid()
+ * manually.
  */
 void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
 {
@@ -4363,9 +4374,9 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
 		end_pfn = min(end_pfn, max_low_pfn);
 
 		if (start_pfn < end_pfn)
-			free_bootmem_node(NODE_DATA(this_nid),
-					  PFN_PHYS(start_pfn),
-					  (end_pfn - start_pfn) << PAGE_SHIFT);
+			memblock_free_early_nid(PFN_PHYS(start_pfn),
+					(end_pfn - start_pfn) << PAGE_SHIFT,
+					this_nid);
 	}
 }
 
@@ -4636,8 +4647,9 @@ static void __init setup_usemap(struct pglist_data *pgdat,
 	unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
 	zone->pageblock_flags = NULL;
 	if (usemapsize)
-		zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat,
-								   usemapsize);
+		zone->pageblock_flags =
+			memblock_virt_alloc_node_nopanic(usemapsize,
+							 pgdat->node_id);
 }
 #else
 static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
@@ -4831,7 +4843,8 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 		size =  (end - start) * sizeof(struct page);
 		map = alloc_remap(pgdat->node_id, size);
 		if (!map)
-			map = alloc_bootmem_node_nopanic(pgdat, size);
+			map = memblock_virt_alloc_node_nopanic(size,
+							       pgdat->node_id);
 		pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
 	}
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -5012,9 +5025,33 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	nodemask_t saved_node_state = node_states[N_MEMORY];
 	unsigned long totalpages = early_calculate_totalpages();
 	int usable_nodes = nodes_weight(node_states[N_MEMORY]);
+	struct memblock_type *type = &memblock.memory;
+
+	/* Need to find movable_zone earlier when movable_node is specified. */
+	find_usable_zone_for_movable();
+
+	/*
+	 * If movable_node is specified, ignore kernelcore and movablecore
+	 * options.
+	 */
+	if (movable_node_is_enabled()) {
+		for (i = 0; i < type->cnt; i++) {
+			if (!memblock_is_hotpluggable(&type->regions[i]))
+				continue;
+
+			nid = type->regions[i].nid;
+
+			usable_startpfn = PFN_DOWN(type->regions[i].base);
+			zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
+				min(usable_startpfn, zone_movable_pfn[nid]) :
+				usable_startpfn;
+		}
+
+		goto out2;
+	}
 
 	/*
-	 * If movablecore was specified, calculate what size of
+	 * If movablecore=nn[KMG] was specified, calculate what size of
 	 * kernelcore that corresponds so that memory usable for
 	 * any allocation type is evenly spread. If both kernelcore
 	 * and movablecore are specified, then the value of kernelcore
@@ -5040,7 +5077,6 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 		goto out;
 
 	/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
-	find_usable_zone_for_movable();
 	usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];
 
 restart:
@@ -5131,6 +5167,7 @@ restart:
 	if (usable_nodes && required_kernelcore > usable_nodes)
 		goto restart;
 
+out2:
 	/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
 	for (nid = 0; nid < MAX_NUMNODES; nid++)
 		zone_movable_pfn[nid] =
@@ -5857,7 +5894,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 	do {
 		size = bucketsize << log2qty;
 		if (flags & HASH_EARLY)
-			table = alloc_bootmem_nopanic(size);
+			table = memblock_virt_alloc_nopanic(size, 0);
 		else if (hashdist)
 			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
 		else {
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 3bd0b8e6ab1..cfd162882c0 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -54,8 +54,9 @@ static int __init alloc_node_page_cgroup(int nid)
 
 	table_size = sizeof(struct page_cgroup) * nr_pages;
 
-	base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
-			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	base = memblock_virt_alloc_try_nid_nopanic(
+			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
+			BOOTMEM_ALLOC_ACCESSIBLE, nid);
 	if (!base)
 		return -ENOMEM;
 	NODE_DATA(nid)->node_page_cgroup = base;
diff --git a/mm/percpu.c b/mm/percpu.c
index afbf352ae58..036cfe07050 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1063,7 +1063,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
 			  __alignof__(ai->groups[0].cpu_map[0]));
 	ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]);
 
-	ptr = alloc_bootmem_nopanic(PFN_ALIGN(ai_size));
+	ptr = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), 0);
 	if (!ptr)
 		return NULL;
 	ai = ptr;
@@ -1088,7 +1088,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
  */
 void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
 {
-	free_bootmem(__pa(ai), ai->__ai_size);
+	memblock_free_early(__pa(ai), ai->__ai_size);
 }
 
 /**
@@ -1246,10 +1246,12 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
 
 	/* process group information and build config tables accordingly */
-	group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));
-	group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0]));
-	unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0]));
-	unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0]));
+	group_offsets = memblock_virt_alloc(ai->nr_groups *
+					     sizeof(group_offsets[0]), 0);
+	group_sizes = memblock_virt_alloc(ai->nr_groups *
+					   sizeof(group_sizes[0]), 0);
+	unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0);
+	unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0);
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
 		unit_map[cpu] = UINT_MAX;
@@ -1311,7 +1313,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 * empty chunks.
 	 */
 	pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
-	pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0]));
+	pcpu_slot = memblock_virt_alloc(
+			pcpu_nr_slots * sizeof(pcpu_slot[0]), 0);
 	for (i = 0; i < pcpu_nr_slots; i++)
 		INIT_LIST_HEAD(&pcpu_slot[i]);
 
@@ -1322,7 +1325,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 * covers static area + reserved area (mostly used for module
 	 * static percpu allocation).
 	 */
-	schunk = alloc_bootmem(pcpu_chunk_struct_size);
+	schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 	INIT_LIST_HEAD(&schunk->list);
 	schunk->base_addr = base_addr;
 	schunk->map = smap;
@@ -1346,7 +1349,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 	/* init dynamic chunk if necessary */
 	if (dyn_size) {
-		dchunk = alloc_bootmem(pcpu_chunk_struct_size);
+		dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 		INIT_LIST_HEAD(&dchunk->list);
 		dchunk->base_addr = base_addr;
 		dchunk->map = dmap;
@@ -1626,7 +1629,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 	size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
 	areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *));
 
-	areas = alloc_bootmem_nopanic(areas_size);
+	areas = memblock_virt_alloc_nopanic(areas_size, 0);
 	if (!areas) {
 		rc = -ENOMEM;
 		goto out_free;
@@ -1712,7 +1715,7 @@ out_free_areas:
 out_free:
 	pcpu_free_alloc_info(ai);
 	if (areas)
-		free_bootmem(__pa(areas), areas_size);
+		memblock_free_early(__pa(areas), areas_size);
 	return rc;
 }
 #endif /* BUILD_EMBED_FIRST_CHUNK */
@@ -1760,7 +1763,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
 	/* unaligned allocations can't be freed, round up to page size */
 	pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() *
 			       sizeof(pages[0]));
-	pages = alloc_bootmem(pages_size);
+	pages = memblock_virt_alloc(pages_size, 0);
 
 	/* allocate pages */
 	j = 0;
@@ -1823,7 +1826,7 @@ enomem:
 		free_fn(page_address(pages[j]), PAGE_SIZE);
 	rc = -ENOMEM;
 out_free_ar:
-	free_bootmem(__pa(pages), pages_size);
+	memblock_free_early(__pa(pages), pages_size);
 	pcpu_free_alloc_info(ai);
 	return rc;
 }
@@ -1848,12 +1851,13 @@ EXPORT_SYMBOL(__per_cpu_offset);
 static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size,
 				       size_t align)
 {
-	return __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
+	return  memblock_virt_alloc_from_nopanic(
+			size, align, __pa(MAX_DMA_ADDRESS));
 }
 
 static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
 {
-	free_bootmem(__pa(ptr), size);
+	memblock_free_early(__pa(ptr), size);
 }
 
 void __init setup_per_cpu_areas(void)
@@ -1896,7 +1900,9 @@ void __init setup_per_cpu_areas(void)
 	void *fc;
 
 	ai = pcpu_alloc_alloc_info(1, 1);
-	fc = __alloc_bootmem(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	fc = memblock_virt_alloc_from_nopanic(unit_size,
+					      PAGE_SIZE,
+					      __pa(MAX_DMA_ADDRESS));
 	if (!ai || !fc)
 		panic("Failed to allocate memory for percpu areas.");
 	/* kmemleak tracks the percpu allocations separately */
diff --git a/mm/rmap.c b/mm/rmap.c
index 068522d8502..962e2a1e13a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -660,17 +660,22 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
 	return 1;
 }
 
+struct page_referenced_arg {
+	int mapcount;
+	int referenced;
+	unsigned long vm_flags;
+	struct mem_cgroup *memcg;
+};
 /*
- * Subfunctions of page_referenced: page_referenced_one called
- * repeatedly from either page_referenced_anon or page_referenced_file.
+ * arg: page_referenced_arg will be passed
  */
 int page_referenced_one(struct page *page, struct vm_area_struct *vma,
-			unsigned long address, unsigned int *mapcount,
-			unsigned long *vm_flags)
+			unsigned long address, void *arg)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
 	int referenced = 0;
+	struct page_referenced_arg *pra = arg;
 
 	if (unlikely(PageTransHuge(page))) {
 		pmd_t *pmd;
@@ -682,13 +687,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		pmd = page_check_address_pmd(page, mm, address,
 					     PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl);
 		if (!pmd)
-			goto out;
+			return SWAP_AGAIN;
 
 		if (vma->vm_flags & VM_LOCKED) {
 			spin_unlock(ptl);
-			*mapcount = 0;	/* break early from loop */
-			*vm_flags |= VM_LOCKED;
-			goto out;
+			pra->vm_flags |= VM_LOCKED;
+			return SWAP_FAIL; /* To break the loop */
 		}
 
 		/* go ahead even if the pmd is pmd_trans_splitting() */
@@ -704,13 +708,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		 */
 		pte = page_check_address(page, mm, address, &ptl, 0);
 		if (!pte)
-			goto out;
+			return SWAP_AGAIN;
 
 		if (vma->vm_flags & VM_LOCKED) {
 			pte_unmap_unlock(pte, ptl);
-			*mapcount = 0;	/* break early from loop */
-			*vm_flags |= VM_LOCKED;
-			goto out;
+			pra->vm_flags |= VM_LOCKED;
+			return SWAP_FAIL; /* To break the loop */
 		}
 
 		if (ptep_clear_flush_young_notify(vma, address, pte)) {
@@ -727,113 +730,27 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		pte_unmap_unlock(pte, ptl);
 	}
 
-	(*mapcount)--;
-
-	if (referenced)
-		*vm_flags |= vma->vm_flags;
-out:
-	return referenced;
-}
-
-static int page_referenced_anon(struct page *page,
-				struct mem_cgroup *memcg,
-				unsigned long *vm_flags)
-{
-	unsigned int mapcount;
-	struct anon_vma *anon_vma;
-	pgoff_t pgoff;
-	struct anon_vma_chain *avc;
-	int referenced = 0;
-
-	anon_vma = page_lock_anon_vma_read(page);
-	if (!anon_vma)
-		return referenced;
-
-	mapcount = page_mapcount(page);
-	pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
-		struct vm_area_struct *vma = avc->vma;
-		unsigned long address = vma_address(page, vma);
-		/*
-		 * If we are reclaiming on behalf of a cgroup, skip
-		 * counting on behalf of references from different
-		 * cgroups
-		 */
-		if (memcg && !mm_match_cgroup(vma->vm_mm, memcg))
-			continue;
-		referenced += page_referenced_one(page, vma, address,
-						  &mapcount, vm_flags);
-		if (!mapcount)
-			break;
+	if (referenced) {
+		pra->referenced++;
+		pra->vm_flags |= vma->vm_flags;
 	}
 
-	page_unlock_anon_vma_read(anon_vma);
-	return referenced;
+	pra->mapcount--;
+	if (!pra->mapcount)
+		return SWAP_SUCCESS; /* To break the loop */
+
+	return SWAP_AGAIN;
 }
 
-/**
- * page_referenced_file - referenced check for object-based rmap
- * @page: the page we're checking references on.
- * @memcg: target memory control group
- * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
- *
- * For an object-based mapped page, find all the places it is mapped and
- * check/clear the referenced flag.  This is done by following the page->mapping
- * pointer, then walking the chain of vmas it holds.  It returns the number
- * of references it found.
- *
- * This function is only called from page_referenced for object-based pages.
- */
-static int page_referenced_file(struct page *page,
-				struct mem_cgroup *memcg,
-				unsigned long *vm_flags)
+static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
 {
-	unsigned int mapcount;
-	struct address_space *mapping = page->mapping;
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-	struct vm_area_struct *vma;
-	int referenced = 0;
-
-	/*
-	 * The caller's checks on page->mapping and !PageAnon have made
-	 * sure that this is a file page: the check for page->mapping
-	 * excludes the case just before it gets set on an anon page.
-	 */
-	BUG_ON(PageAnon(page));
-
-	/*
-	 * The page lock not only makes sure that page->mapping cannot
-	 * suddenly be NULLified by truncation, it makes sure that the
-	 * structure at mapping cannot be freed and reused yet,
-	 * so we can safely take mapping->i_mmap_mutex.
-	 */
-	BUG_ON(!PageLocked(page));
-
-	mutex_lock(&mapping->i_mmap_mutex);
+	struct page_referenced_arg *pra = arg;
+	struct mem_cgroup *memcg = pra->memcg;
 
-	/*
-	 * i_mmap_mutex does not stabilize mapcount at all, but mapcount
-	 * is more likely to be accurate if we note it after spinning.
-	 */
-	mapcount = page_mapcount(page);
-
-	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
-		unsigned long address = vma_address(page, vma);
-		/*
-		 * If we are reclaiming on behalf of a cgroup, skip
-		 * counting on behalf of references from different
-		 * cgroups
-		 */
-		if (memcg && !mm_match_cgroup(vma->vm_mm, memcg))
-			continue;
-		referenced += page_referenced_one(page, vma, address,
-						  &mapcount, vm_flags);
-		if (!mapcount)
-			break;
-	}
+	if (!mm_match_cgroup(vma->vm_mm, memcg))
+		return true;
 
-	mutex_unlock(&mapping->i_mmap_mutex);
-	return referenced;
+	return false;
 }
 
 /**
@@ -851,41 +768,57 @@ int page_referenced(struct page *page,
 		    struct mem_cgroup *memcg,
 		    unsigned long *vm_flags)
 {
-	int referenced = 0;
+	int ret;
 	int we_locked = 0;
+	struct page_referenced_arg pra = {
+		.mapcount = page_mapcount(page),
+		.memcg = memcg,
+	};
+	struct rmap_walk_control rwc = {
+		.rmap_one = page_referenced_one,
+		.arg = (void *)&pra,
+		.anon_lock = page_lock_anon_vma_read,
+	};
 
 	*vm_flags = 0;
-	if (page_mapped(page) && page_rmapping(page)) {
-		if (!is_locked && (!PageAnon(page) || PageKsm(page))) {
-			we_locked = trylock_page(page);
-			if (!we_locked) {
-				referenced++;
-				goto out;
-			}
-		}
-		if (unlikely(PageKsm(page)))
-			referenced += page_referenced_ksm(page, memcg,
-								vm_flags);
-		else if (PageAnon(page))
-			referenced += page_referenced_anon(page, memcg,
-								vm_flags);
-		else if (page->mapping)
-			referenced += page_referenced_file(page, memcg,
-								vm_flags);
-		if (we_locked)
-			unlock_page(page);
+	if (!page_mapped(page))
+		return 0;
+
+	if (!page_rmapping(page))
+		return 0;
+
+	if (!is_locked && (!PageAnon(page) || PageKsm(page))) {
+		we_locked = trylock_page(page);
+		if (!we_locked)
+			return 1;
 	}
-out:
-	return referenced;
+
+	/*
+	 * If we are reclaiming on behalf of a cgroup, skip
+	 * counting on behalf of references from different
+	 * cgroups
+	 */
+	if (memcg) {
+		rwc.invalid_vma = invalid_page_referenced_vma;
+	}
+
+	ret = rmap_walk(page, &rwc);
+	*vm_flags = pra.vm_flags;
+
+	if (we_locked)
+		unlock_page(page);
+
+	return pra.referenced;
 }
 
 static int page_mkclean_one(struct page *page, struct vm_area_struct *vma,
-			    unsigned long address)
+			    unsigned long address, void *arg)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte;
 	spinlock_t *ptl;
 	int ret = 0;
+	int *cleaned = arg;
 
 	pte = page_check_address(page, mm, address, &ptl, 1);
 	if (!pte)
@@ -904,44 +837,44 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 
 	pte_unmap_unlock(pte, ptl);
 
-	if (ret)
+	if (ret) {
 		mmu_notifier_invalidate_page(mm, address);
+		(*cleaned)++;
+	}
 out:
-	return ret;
+	return SWAP_AGAIN;
 }
 
-static int page_mkclean_file(struct address_space *mapping, struct page *page)
+static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg)
 {
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-	struct vm_area_struct *vma;
-	int ret = 0;
-
-	BUG_ON(PageAnon(page));
+	if (vma->vm_flags & VM_SHARED)
+		return 0;
 
-	mutex_lock(&mapping->i_mmap_mutex);
-	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
-		if (vma->vm_flags & VM_SHARED) {
-			unsigned long address = vma_address(page, vma);
-			ret += page_mkclean_one(page, vma, address);
-		}
-	}
-	mutex_unlock(&mapping->i_mmap_mutex);
-	return ret;
+	return 1;
 }
 
 int page_mkclean(struct page *page)
 {
-	int ret = 0;
+	int cleaned = 0;
+	struct address_space *mapping;
+	struct rmap_walk_control rwc = {
+		.arg = (void *)&cleaned,
+		.rmap_one = page_mkclean_one,
+		.invalid_vma = invalid_mkclean_vma,
+	};
 
 	BUG_ON(!PageLocked(page));
 
-	if (page_mapped(page)) {
-		struct address_space *mapping = page_mapping(page);
-		if (mapping)
-			ret = page_mkclean_file(mapping, page);
-	}
+	if (!page_mapped(page))
+		return 0;
 
-	return ret;
+	mapping = page_mapping(page);
+	if (!mapping)
+		return 0;
+
+	rmap_walk(page, &rwc);
+
+	return cleaned;
 }
 EXPORT_SYMBOL_GPL(page_mkclean);
 
@@ -1177,17 +1110,17 @@ out:
 }
 
 /*
- * Subfunctions of try_to_unmap: try_to_unmap_one called
- * repeatedly from try_to_unmap_ksm, try_to_unmap_anon or try_to_unmap_file.
+ * @arg: enum ttu_flags will be passed to this argument
  */
 int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
-		     unsigned long address, enum ttu_flags flags)
+		     unsigned long address, void *arg)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte;
 	pte_t pteval;
 	spinlock_t *ptl;
 	int ret = SWAP_AGAIN;
+	enum ttu_flags flags = (enum ttu_flags)arg;
 
 	pte = page_check_address(page, mm, address, &ptl, 0);
 	if (!pte)
@@ -1426,124 +1359,18 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 	return ret;
 }
 
-bool is_vma_temporary_stack(struct vm_area_struct *vma)
-{
-	int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
-
-	if (!maybe_stack)
-		return false;
-
-	if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) ==
-						VM_STACK_INCOMPLETE_SETUP)
-		return true;
-
-	return false;
-}
-
-/**
- * try_to_unmap_anon - unmap or unlock anonymous page using the object-based
- * rmap method
- * @page: the page to unmap/unlock
- * @flags: action and flags
- *
- * Find all the mappings of a page using the mapping pointer and the vma chains
- * contained in the anon_vma struct it points to.
- *
- * This function is only called from try_to_unmap/try_to_munlock for
- * anonymous pages.
- * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
- * where the page was found will be held for write.  So, we won't recheck
- * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
- * 'LOCKED.
- */
-static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
-{
-	struct anon_vma *anon_vma;
-	pgoff_t pgoff;
-	struct anon_vma_chain *avc;
-	int ret = SWAP_AGAIN;
-
-	anon_vma = page_lock_anon_vma_read(page);
-	if (!anon_vma)
-		return ret;
-
-	pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
-		struct vm_area_struct *vma = avc->vma;
-		unsigned long address;
-
-		/*
-		 * During exec, a temporary VMA is setup and later moved.
-		 * The VMA is moved under the anon_vma lock but not the
-		 * page tables leading to a race where migration cannot
-		 * find the migration ptes. Rather than increasing the
-		 * locking requirements of exec(), migration skips
-		 * temporary VMAs until after exec() completes.
-		 */
-		if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) &&
-				is_vma_temporary_stack(vma))
-			continue;
-
-		address = vma_address(page, vma);
-		ret = try_to_unmap_one(page, vma, address, flags);
-		if (ret != SWAP_AGAIN || !page_mapped(page))
-			break;
-	}
-
-	page_unlock_anon_vma_read(anon_vma);
-	return ret;
-}
-
-/**
- * try_to_unmap_file - unmap/unlock file page using the object-based rmap method
- * @page: the page to unmap/unlock
- * @flags: action and flags
- *
- * Find all the mappings of a page using the mapping pointer and the vma chains
- * contained in the address_space struct it points to.
- *
- * This function is only called from try_to_unmap/try_to_munlock for
- * object-based pages.
- * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
- * where the page was found will be held for write.  So, we won't recheck
- * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
- * 'LOCKED.
- */
-static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
+static int try_to_unmap_nonlinear(struct page *page,
+		struct address_space *mapping, struct vm_area_struct *vma)
 {
-	struct address_space *mapping = page->mapping;
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-	struct vm_area_struct *vma;
 	int ret = SWAP_AGAIN;
 	unsigned long cursor;
 	unsigned long max_nl_cursor = 0;
 	unsigned long max_nl_size = 0;
 	unsigned int mapcount;
 
-	if (PageHuge(page))
-		pgoff = page->index << compound_order(page);
+	list_for_each_entry(vma,
+		&mapping->i_mmap_nonlinear, shared.nonlinear) {
 
-	mutex_lock(&mapping->i_mmap_mutex);
-	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
-		unsigned long address = vma_address(page, vma);
-		ret = try_to_unmap_one(page, vma, address, flags);
-		if (ret != SWAP_AGAIN || !page_mapped(page))
-			goto out;
-	}
-
-	if (list_empty(&mapping->i_mmap_nonlinear))
-		goto out;
-
-	/*
-	 * We don't bother to try to find the munlocked page in nonlinears.
-	 * It's costly. Instead, later, page reclaim logic may call
-	 * try_to_unmap(TTU_MUNLOCK) and recover PG_mlocked lazily.
-	 */
-	if (TTU_ACTION(flags) == TTU_MUNLOCK)
-		goto out;
-
-	list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
-							shared.nonlinear) {
 		cursor = (unsigned long) vma->vm_private_data;
 		if (cursor > max_nl_cursor)
 			max_nl_cursor = cursor;
@@ -1553,8 +1380,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
 	}
 
 	if (max_nl_size == 0) {	/* all nonlinears locked or reserved ? */
-		ret = SWAP_FAIL;
-		goto out;
+		return SWAP_FAIL;
 	}
 
 	/*
@@ -1566,7 +1392,8 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
 	 */
 	mapcount = page_mapcount(page);
 	if (!mapcount)
-		goto out;
+		return ret;
+
 	cond_resched();
 
 	max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK;
@@ -1574,10 +1401,11 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
 		max_nl_cursor = CLUSTER_SIZE;
 
 	do {
-		list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
-							shared.nonlinear) {
+		list_for_each_entry(vma,
+			&mapping->i_mmap_nonlinear, shared.nonlinear) {
+
 			cursor = (unsigned long) vma->vm_private_data;
-			while ( cursor < max_nl_cursor &&
+			while (cursor < max_nl_cursor &&
 				cursor < vma->vm_end - vma->vm_start) {
 				if (try_to_unmap_cluster(cursor, &mapcount,
 						vma, page) == SWAP_MLOCK)
@@ -1585,7 +1413,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
 				cursor += CLUSTER_SIZE;
 				vma->vm_private_data = (void *) cursor;
 				if ((int)mapcount <= 0)
-					goto out;
+					return ret;
 			}
 			vma->vm_private_data = (void *) max_nl_cursor;
 		}
@@ -1600,11 +1428,34 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
 	 */
 	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear)
 		vma->vm_private_data = NULL;
-out:
-	mutex_unlock(&mapping->i_mmap_mutex);
+
 	return ret;
 }
 
+bool is_vma_temporary_stack(struct vm_area_struct *vma)
+{
+	int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
+
+	if (!maybe_stack)
+		return false;
+
+	if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) ==
+						VM_STACK_INCOMPLETE_SETUP)
+		return true;
+
+	return false;
+}
+
+static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg)
+{
+	return is_vma_temporary_stack(vma);
+}
+
+static int page_not_mapped(struct page *page)
+{
+	return !page_mapped(page);
+};
+
 /**
  * try_to_unmap - try to remove all page table mappings to a page
  * @page: the page to get unmapped
@@ -1622,16 +1473,29 @@ out:
 int try_to_unmap(struct page *page, enum ttu_flags flags)
 {
 	int ret;
+	struct rmap_walk_control rwc = {
+		.rmap_one = try_to_unmap_one,
+		.arg = (void *)flags,
+		.done = page_not_mapped,
+		.file_nonlinear = try_to_unmap_nonlinear,
+		.anon_lock = page_lock_anon_vma_read,
+	};
 
-	BUG_ON(!PageLocked(page));
 	VM_BUG_ON(!PageHuge(page) && PageTransHuge(page));
 
-	if (unlikely(PageKsm(page)))
-		ret = try_to_unmap_ksm(page, flags);
-	else if (PageAnon(page))
-		ret = try_to_unmap_anon(page, flags);
-	else
-		ret = try_to_unmap_file(page, flags);
+	/*
+	 * During exec, a temporary VMA is setup and later moved.
+	 * The VMA is moved under the anon_vma lock but not the
+	 * page tables leading to a race where migration cannot
+	 * find the migration ptes. Rather than increasing the
+	 * locking requirements of exec(), migration skips
+	 * temporary VMAs until after exec() completes.
+	 */
+	if (flags & TTU_MIGRATION && !PageKsm(page) && PageAnon(page))
+		rwc.invalid_vma = invalid_migration_vma;
+
+	ret = rmap_walk(page, &rwc);
+
 	if (ret != SWAP_MLOCK && !page_mapped(page))
 		ret = SWAP_SUCCESS;
 	return ret;
@@ -1654,14 +1518,25 @@ int try_to_unmap(struct page *page, enum ttu_flags flags)
  */
 int try_to_munlock(struct page *page)
 {
+	int ret;
+	struct rmap_walk_control rwc = {
+		.rmap_one = try_to_unmap_one,
+		.arg = (void *)TTU_MUNLOCK,
+		.done = page_not_mapped,
+		/*
+		 * We don't bother to try to find the munlocked page in
+		 * nonlinears. It's costly. Instead, later, page reclaim logic
+		 * may call try_to_unmap() and recover PG_mlocked lazily.
+		 */
+		.file_nonlinear = NULL,
+		.anon_lock = page_lock_anon_vma_read,
+
+	};
+
 	VM_BUG_ON(!PageLocked(page) || PageLRU(page));
 
-	if (unlikely(PageKsm(page)))
-		return try_to_unmap_ksm(page, TTU_MUNLOCK);
-	else if (PageAnon(page))
-		return try_to_unmap_anon(page, TTU_MUNLOCK);
-	else
-		return try_to_unmap_file(page, TTU_MUNLOCK);
+	ret = rmap_walk(page, &rwc);
+	return ret;
 }
 
 void __put_anon_vma(struct anon_vma *anon_vma)
@@ -1674,18 +1549,13 @@ void __put_anon_vma(struct anon_vma *anon_vma)
 	anon_vma_free(anon_vma);
 }
 
-#ifdef CONFIG_MIGRATION
-/*
- * rmap_walk() and its helpers rmap_walk_anon() and rmap_walk_file():
- * Called by migrate.c to remove migration ptes, but might be used more later.
- */
-static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
-		struct vm_area_struct *, unsigned long, void *), void *arg)
+static struct anon_vma *rmap_walk_anon_lock(struct page *page,
+					struct rmap_walk_control *rwc)
 {
 	struct anon_vma *anon_vma;
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-	struct anon_vma_chain *avc;
-	int ret = SWAP_AGAIN;
+
+	if (rwc->anon_lock)
+		return rwc->anon_lock(page);
 
 	/*
 	 * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read()
@@ -1695,58 +1565,120 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
 	 */
 	anon_vma = page_anon_vma(page);
 	if (!anon_vma)
-		return ret;
+		return NULL;
+
 	anon_vma_lock_read(anon_vma);
+	return anon_vma;
+}
+
+/*
+ * rmap_walk_anon - do something to anonymous page using the object-based
+ * rmap method
+ * @page: the page to be handled
+ * @rwc: control variable according to each walk type
+ *
+ * Find all the mappings of a page using the mapping pointer and the vma chains
+ * contained in the anon_vma struct it points to.
+ *
+ * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
+ * where the page was found will be held for write.  So, we won't recheck
+ * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
+ * LOCKED.
+ */
+static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc)
+{
+	struct anon_vma *anon_vma;
+	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	struct anon_vma_chain *avc;
+	int ret = SWAP_AGAIN;
+
+	anon_vma = rmap_walk_anon_lock(page, rwc);
+	if (!anon_vma)
+		return ret;
+
 	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
 		struct vm_area_struct *vma = avc->vma;
 		unsigned long address = vma_address(page, vma);
-		ret = rmap_one(page, vma, address, arg);
+
+		if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
+			continue;
+
+		ret = rwc->rmap_one(page, vma, address, rwc->arg);
 		if (ret != SWAP_AGAIN)
 			break;
+		if (rwc->done && rwc->done(page))
+			break;
 	}
 	anon_vma_unlock_read(anon_vma);
 	return ret;
 }
 
-static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *,
-		struct vm_area_struct *, unsigned long, void *), void *arg)
+/*
+ * rmap_walk_file - do something to file page using the object-based rmap method
+ * @page: the page to be handled
+ * @rwc: control variable according to each walk type
+ *
+ * Find all the mappings of a page using the mapping pointer and the vma chains
+ * contained in the address_space struct it points to.
+ *
+ * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
+ * where the page was found will be held for write.  So, we won't recheck
+ * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
+ * LOCKED.
+ */
+static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 {
 	struct address_space *mapping = page->mapping;
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	pgoff_t pgoff = page->index << compound_order(page);
 	struct vm_area_struct *vma;
 	int ret = SWAP_AGAIN;
 
+	/*
+	 * The page lock not only makes sure that page->mapping cannot
+	 * suddenly be NULLified by truncation, it makes sure that the
+	 * structure at mapping cannot be freed and reused yet,
+	 * so we can safely take mapping->i_mmap_mutex.
+	 */
+	VM_BUG_ON(!PageLocked(page));
+
 	if (!mapping)
 		return ret;
 	mutex_lock(&mapping->i_mmap_mutex);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
 		unsigned long address = vma_address(page, vma);
-		ret = rmap_one(page, vma, address, arg);
+
+		if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
+			continue;
+
+		ret = rwc->rmap_one(page, vma, address, rwc->arg);
 		if (ret != SWAP_AGAIN)
-			break;
+			goto done;
+		if (rwc->done && rwc->done(page))
+			goto done;
 	}
-	/*
-	 * No nonlinear handling: being always shared, nonlinear vmas
-	 * never contain migration ptes.  Decide what to do about this
-	 * limitation to linear when we need rmap_walk() on nonlinear.
-	 */
+
+	if (!rwc->file_nonlinear)
+		goto done;
+
+	if (list_empty(&mapping->i_mmap_nonlinear))
+		goto done;
+
+	ret = rwc->file_nonlinear(page, mapping, vma);
+
+done:
 	mutex_unlock(&mapping->i_mmap_mutex);
 	return ret;
 }
 
-int rmap_walk(struct page *page, int (*rmap_one)(struct page *,
-		struct vm_area_struct *, unsigned long, void *), void *arg)
+int rmap_walk(struct page *page, struct rmap_walk_control *rwc)
 {
-	VM_BUG_ON(!PageLocked(page));
-
 	if (unlikely(PageKsm(page)))
-		return rmap_walk_ksm(page, rmap_one, arg);
+		return rmap_walk_ksm(page, rwc);
 	else if (PageAnon(page))
-		return rmap_walk_anon(page, rmap_one, arg);
+		return rmap_walk_anon(page, rwc);
 	else
-		return rmap_walk_file(page, rmap_one, arg);
+		return rmap_walk_file(page, rwc);
 }
-#endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_HUGETLB_PAGE
 /*
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 27eeab3be75..4cba9c2783a 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -40,7 +40,8 @@ static void * __init_refok __earlyonly_bootmem_alloc(int node,
 				unsigned long align,
 				unsigned long goal)
 {
-	return __alloc_bootmem_node_high(NODE_DATA(node), size, align, goal);
+	return memblock_virt_alloc_try_nid(size, align, goal,
+					    BOOTMEM_ALLOC_ACCESSIBLE, node);
 }
 
 static void *vmemmap_buf;
@@ -226,7 +227,8 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 
 	if (vmemmap_buf_start) {
 		/* need to free left buf */
-		free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf);
+		memblock_free_early(__pa(vmemmap_buf),
+				    vmemmap_buf_end - vmemmap_buf);
 		vmemmap_buf = NULL;
 		vmemmap_buf_end = NULL;
 	}
diff --git a/mm/sparse.c b/mm/sparse.c
index 8cc7be0e959..63c3ea5c119 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -69,7 +69,7 @@ static struct mem_section noinline __init_refok *sparse_index_alloc(int nid)
 		else
 			section = kzalloc(array_size, GFP_KERNEL);
 	} else {
-		section = alloc_bootmem_node(NODE_DATA(nid), array_size);
+		section = memblock_virt_alloc_node(array_size, nid);
 	}
 
 	return section;
@@ -279,8 +279,9 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 	limit = goal + (1UL << PA_SECTION_SHIFT);
 	nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
 again:
-	p = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size,
-					  SMP_CACHE_BYTES, goal, limit);
+	p = memblock_virt_alloc_try_nid_nopanic(size,
+						SMP_CACHE_BYTES, goal, limit,
+						nid);
 	if (!p && limit) {
 		limit = 0;
 		goto again;
@@ -331,7 +332,7 @@ static unsigned long * __init
 sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 					 unsigned long size)
 {
-	return alloc_bootmem_node_nopanic(pgdat, size);
+	return memblock_virt_alloc_node_nopanic(size, pgdat->node_id);
 }
 
 static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
@@ -376,8 +377,9 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
 		return map;
 
 	size = PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
-	map = __alloc_bootmem_node_high(NODE_DATA(nid), size,
-					 PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	map = memblock_virt_alloc_try_nid(size,
+					  PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
+					  BOOTMEM_ALLOC_ACCESSIBLE, nid);
 	return map;
 }
 void __init sparse_mem_maps_populate_node(struct page **map_map,
@@ -401,8 +403,9 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 	}
 
 	size = PAGE_ALIGN(size);
-	map = __alloc_bootmem_node_high(NODE_DATA(nodeid), size * map_count,
-					 PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	map = memblock_virt_alloc_try_nid(size * map_count,
+					  PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
+					  BOOTMEM_ALLOC_ACCESSIBLE, nodeid);
 	if (map) {
 		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
 			if (!present_section_nr(pnum))
@@ -545,7 +548,7 @@ void __init sparse_init(void)
 	 * sparse_early_mem_map_alloc, so allocate usemap_map at first.
 	 */
 	size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
-	usemap_map = alloc_bootmem(size);
+	usemap_map = memblock_virt_alloc(size, 0);
 	if (!usemap_map)
 		panic("can not allocate usemap_map\n");
 	alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node,
@@ -553,7 +556,7 @@ void __init sparse_init(void)
 
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 	size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
-	map_map = alloc_bootmem(size2);
+	map_map = memblock_virt_alloc(size2, 0);
 	if (!map_map)
 		panic("can not allocate map_map\n");
 	alloc_usemap_and_memmap(sparse_early_mem_maps_alloc_node,
@@ -583,9 +586,9 @@ void __init sparse_init(void)
 	vmemmap_populate_print_last();
 
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
-	free_bootmem(__pa(map_map), size2);
+	memblock_free_early(__pa(map_map), size2);
 #endif
-	free_bootmem(__pa(usemap_map), size);
+	memblock_free_early(__pa(usemap_map), size);
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/mm/swap.c b/mm/swap.c
index 84b26aaabd0..d1100b619e6 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -31,7 +31,6 @@
 #include <linux/memcontrol.h>
 #include <linux/gfp.h>
 #include <linux/uio.h>
-#include <linux/hugetlb.h>
 
 #include "internal.h"
 
@@ -82,118 +81,150 @@ static void __put_compound_page(struct page *page)
 
 static void put_compound_page(struct page *page)
 {
-	if (unlikely(PageTail(page))) {
-		/* __split_huge_page_refcount can run under us */
-		struct page *page_head = compound_trans_head(page);
-
-		if (likely(page != page_head &&
-			   get_page_unless_zero(page_head))) {
-			unsigned long flags;
+	struct page *page_head;
 
+	if (likely(!PageTail(page))) {
+		if (put_page_testzero(page)) {
 			/*
-			 * THP can not break up slab pages so avoid taking
-			 * compound_lock().  Slab performs non-atomic bit ops
-			 * on page->flags for better performance.  In particular
-			 * slab_unlock() in slub used to be a hot path.  It is
-			 * still hot on arches that do not support
-			 * this_cpu_cmpxchg_double().
+			 * By the time all refcounts have been released
+			 * split_huge_page cannot run anymore from under us.
 			 */
-			if (PageSlab(page_head) || PageHeadHuge(page_head)) {
-				if (likely(PageTail(page))) {
-					/*
-					 * __split_huge_page_refcount
-					 * cannot race here.
-					 */
-					VM_BUG_ON(!PageHead(page_head));
-					atomic_dec(&page->_mapcount);
-					if (put_page_testzero(page_head))
-						VM_BUG_ON(1);
-					if (put_page_testzero(page_head))
-						__put_compound_page(page_head);
-					return;
-				} else
-					/*
-					 * __split_huge_page_refcount
-					 * run before us, "page" was a
-					 * THP tail. The split
-					 * page_head has been freed
-					 * and reallocated as slab or
-					 * hugetlbfs page of smaller
-					 * order (only possible if
-					 * reallocated as slab on
-					 * x86).
-					 */
-					goto skip_lock;
-			}
+			if (PageHead(page))
+				__put_compound_page(page);
+			else
+				__put_single_page(page);
+		}
+		return;
+	}
+
+	/* __split_huge_page_refcount can run under us */
+	page_head = compound_trans_head(page);
+
+	/*
+	 * THP can not break up slab pages so avoid taking
+	 * compound_lock() and skip the tail page refcounting (in
+	 * _mapcount) too. Slab performs non-atomic bit ops on
+	 * page->flags for better performance. In particular
+	 * slab_unlock() in slub used to be a hot path. It is still
+	 * hot on arches that do not support
+	 * this_cpu_cmpxchg_double().
+	 *
+	 * If "page" is part of a slab or hugetlbfs page it cannot be
+	 * splitted and the head page cannot change from under us. And
+	 * if "page" is part of a THP page under splitting, if the
+	 * head page pointed by the THP tail isn't a THP head anymore,
+	 * we'll find PageTail clear after smp_rmb() and we'll treat
+	 * it as a single page.
+	 */
+	if (!__compound_tail_refcounted(page_head)) {
+		/*
+		 * If "page" is a THP tail, we must read the tail page
+		 * flags after the head page flags. The
+		 * split_huge_page side enforces write memory barriers
+		 * between clearing PageTail and before the head page
+		 * can be freed and reallocated.
+		 */
+		smp_rmb();
+		if (likely(PageTail(page))) {
 			/*
-			 * page_head wasn't a dangling pointer but it
-			 * may not be a head page anymore by the time
-			 * we obtain the lock. That is ok as long as it
-			 * can't be freed from under us.
+			 * __split_huge_page_refcount cannot race
+			 * here.
 			 */
-			flags = compound_lock_irqsave(page_head);
-			if (unlikely(!PageTail(page))) {
-				/* __split_huge_page_refcount run before us */
-				compound_unlock_irqrestore(page_head, flags);
-skip_lock:
-				if (put_page_testzero(page_head)) {
-					/*
-					 * The head page may have been
-					 * freed and reallocated as a
-					 * compound page of smaller
-					 * order and then freed again.
-					 * All we know is that it
-					 * cannot have become: a THP
-					 * page, a compound page of
-					 * higher order, a tail page.
-					 * That is because we still
-					 * hold the refcount of the
-					 * split THP tail and
-					 * page_head was the THP head
-					 * before the split.
-					 */
-					if (PageHead(page_head))
-						__put_compound_page(page_head);
-					else
-						__put_single_page(page_head);
-				}
-out_put_single:
-				if (put_page_testzero(page))
-					__put_single_page(page);
-				return;
+			VM_BUG_ON(!PageHead(page_head));
+			VM_BUG_ON(page_mapcount(page) != 0);
+			if (put_page_testzero(page_head)) {
+				/*
+				 * If this is the tail of a slab
+				 * compound page, the tail pin must
+				 * not be the last reference held on
+				 * the page, because the PG_slab
+				 * cannot be cleared before all tail
+				 * pins (which skips the _mapcount
+				 * tail refcounting) have been
+				 * released. For hugetlbfs the tail
+				 * pin may be the last reference on
+				 * the page instead, because
+				 * PageHeadHuge will not go away until
+				 * the compound page enters the buddy
+				 * allocator.
+				 */
+				VM_BUG_ON(PageSlab(page_head));
+				__put_compound_page(page_head);
 			}
-			VM_BUG_ON(page_head != page->first_page);
+			return;
+		} else
 			/*
-			 * We can release the refcount taken by
-			 * get_page_unless_zero() now that
-			 * __split_huge_page_refcount() is blocked on
-			 * the compound_lock.
+			 * __split_huge_page_refcount run before us,
+			 * "page" was a THP tail. The split page_head
+			 * has been freed and reallocated as slab or
+			 * hugetlbfs page of smaller order (only
+			 * possible if reallocated as slab on x86).
 			 */
-			if (put_page_testzero(page_head))
-				VM_BUG_ON(1);
-			/* __split_huge_page_refcount will wait now */
-			VM_BUG_ON(page_mapcount(page) <= 0);
-			atomic_dec(&page->_mapcount);
-			VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
-			VM_BUG_ON(atomic_read(&page->_count) != 0);
-			compound_unlock_irqrestore(page_head, flags);
+			goto out_put_single;
+	}
 
+	if (likely(page != page_head && get_page_unless_zero(page_head))) {
+		unsigned long flags;
+
+		/*
+		 * page_head wasn't a dangling pointer but it may not
+		 * be a head page anymore by the time we obtain the
+		 * lock. That is ok as long as it can't be freed from
+		 * under us.
+		 */
+		flags = compound_lock_irqsave(page_head);
+		if (unlikely(!PageTail(page))) {
+			/* __split_huge_page_refcount run before us */
+			compound_unlock_irqrestore(page_head, flags);
 			if (put_page_testzero(page_head)) {
+				/*
+				 * The head page may have been freed
+				 * and reallocated as a compound page
+				 * of smaller order and then freed
+				 * again.  All we know is that it
+				 * cannot have become: a THP page, a
+				 * compound page of higher order, a
+				 * tail page.  That is because we
+				 * still hold the refcount of the
+				 * split THP tail and page_head was
+				 * the THP head before the split.
+				 */
 				if (PageHead(page_head))
 					__put_compound_page(page_head);
 				else
 					__put_single_page(page_head);
 			}
-		} else {
-			/* page_head is a dangling pointer */
-			VM_BUG_ON(PageTail(page));
-			goto out_put_single;
+out_put_single:
+			if (put_page_testzero(page))
+				__put_single_page(page);
+			return;
 		}
-	} else if (put_page_testzero(page)) {
-		if (PageHead(page))
-			__put_compound_page(page);
-		else
-			__put_single_page(page);
+		VM_BUG_ON(page_head != page->first_page);
+		/*
+		 * We can release the refcount taken by
+		 * get_page_unless_zero() now that
+		 * __split_huge_page_refcount() is blocked on the
+		 * compound_lock.
+		 */
+		if (put_page_testzero(page_head))
+			VM_BUG_ON(1);
+		/* __split_huge_page_refcount will wait now */
+		VM_BUG_ON(page_mapcount(page) <= 0);
+		atomic_dec(&page->_mapcount);
+		VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
+		VM_BUG_ON(atomic_read(&page->_count) != 0);
+		compound_unlock_irqrestore(page_head, flags);
+
+		if (put_page_testzero(page_head)) {
+			if (PageHead(page_head))
+				__put_compound_page(page_head);
+			else
+				__put_single_page(page_head);
+		}
+	} else {
+		/* page_head is a dangling pointer */
+		VM_BUG_ON(PageTail(page));
+		goto out_put_single;
 	}
 }
 
@@ -221,36 +252,37 @@ bool __get_page_tail(struct page *page)
 	 * split_huge_page().
 	 */
 	unsigned long flags;
-	bool got = false;
+	bool got;
 	struct page *page_head = compound_trans_head(page);
 
-	if (likely(page != page_head && get_page_unless_zero(page_head))) {
-		/* Ref to put_compound_page() comment. */
-		if (PageSlab(page_head) || PageHeadHuge(page_head)) {
-			if (likely(PageTail(page))) {
-				/*
-				 * This is a hugetlbfs page or a slab
-				 * page. __split_huge_page_refcount
-				 * cannot race here.
-				 */
-				VM_BUG_ON(!PageHead(page_head));
-				__get_page_tail_foll(page, false);
-				return true;
-			} else {
-				/*
-				 * __split_huge_page_refcount run
-				 * before us, "page" was a THP
-				 * tail. The split page_head has been
-				 * freed and reallocated as slab or
-				 * hugetlbfs page of smaller order
-				 * (only possible if reallocated as
-				 * slab on x86).
-				 */
-				put_page(page_head);
-				return false;
-			}
+	/* Ref to put_compound_page() comment. */
+	if (!__compound_tail_refcounted(page_head)) {
+		smp_rmb();
+		if (likely(PageTail(page))) {
+			/*
+			 * This is a hugetlbfs page or a slab
+			 * page. __split_huge_page_refcount
+			 * cannot race here.
+			 */
+			VM_BUG_ON(!PageHead(page_head));
+			__get_page_tail_foll(page, true);
+			return true;
+		} else {
+			/*
+			 * __split_huge_page_refcount run
+			 * before us, "page" was a THP
+			 * tail. The split page_head has been
+			 * freed and reallocated as slab or
+			 * hugetlbfs page of smaller order
+			 * (only possible if reallocated as
+			 * slab on x86).
+			 */
+			return false;
 		}
+	}
 
+	got = false;
+	if (likely(page != page_head && get_page_unless_zero(page_head))) {
 		/*
 		 * page_head wasn't a dangling pointer but it
 		 * may not be a head page anymore by the time
diff --git a/mm/util.c b/mm/util.c
index 808f375648e..a24aa22f247 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -404,13 +404,45 @@ struct address_space *page_mapping(struct page *page)
 	return mapping;
 }
 
+int overcommit_ratio_handler(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		sysctl_overcommit_kbytes = 0;
+	return ret;
+}
+
+int overcommit_kbytes_handler(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		sysctl_overcommit_ratio = 0;
+	return ret;
+}
+
 /*
  * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
  */
 unsigned long vm_commit_limit(void)
 {
-	return ((totalram_pages - hugetlb_total_pages())
-		* sysctl_overcommit_ratio / 100) + total_swap_pages;
+	unsigned long allowed;
+
+	if (sysctl_overcommit_kbytes)
+		allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
+	else
+		allowed = ((totalram_pages - hugetlb_total_pages())
+			   * sysctl_overcommit_ratio / 100);
+	allowed += total_swap_pages;
+
+	return allowed;
 }
 
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 0fdf96803c5..e4f0db2a3ea 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -220,12 +220,12 @@ int is_vmalloc_or_module_addr(const void *x)
 }
 
 /*
- * Walk a vmap address to the struct page it maps.
+ * Walk a vmap address to the physical pfn it maps to.
  */
-struct page *vmalloc_to_page(const void *vmalloc_addr)
+unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
 {
 	unsigned long addr = (unsigned long) vmalloc_addr;
-	struct page *page = NULL;
+	unsigned long pfn = 0;
 	pgd_t *pgd = pgd_offset_k(addr);
 
 	/*
@@ -244,23 +244,23 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 				ptep = pte_offset_map(pmd, addr);
 				pte = *ptep;
 				if (pte_present(pte))
-					page = pte_page(pte);
+					pfn = pte_pfn(pte);
 				pte_unmap(ptep);
 			}
 		}
 	}
-	return page;
+	return pfn;
 }
-EXPORT_SYMBOL(vmalloc_to_page);
+EXPORT_SYMBOL(vmalloc_to_pfn);
 
 /*
- * Map a vmalloc()-space virtual address to the physical page frame number.
+ * Map a vmalloc()-space virtual address to the struct page.
  */
-unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
+struct page *vmalloc_to_page(const void *vmalloc_addr)
 {
-	return page_to_pfn(vmalloc_to_page(vmalloc_addr));
+	return pfn_to_page(vmalloc_to_pfn(vmalloc_addr));
 }
-EXPORT_SYMBOL(vmalloc_to_pfn);
+EXPORT_SYMBOL(vmalloc_to_page);
 
 
 /*** Global kva allocator ***/