Merge branch 'akpm' (more incoming from Andrew)

Merge second patch-bomb from Andrew Morton: - A little DM fix - the MM queue * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (154 commits) ksm: allocate roots when needed mm: cleanup "swapcache" in do_swap_page mm,ksm: swapoff might need to copy mm,ksm: FOLL_MIGRATION do migration_entry_wait ksm: shrink 32-bit rmap_item back to 32 bytes ksm: treat unstable nid like in stable tree ksm: add some comments tmpfs: fix mempolicy object leaks tmpfs: fix use-after-free of mempolicy object mm/fadvise.c: drain all pagevecs if POSIX_FADV_DONTNEED fails to discard all pages mm: export mmu notifier invalidates mm: accelerate mm_populate() treatment of THP pages mm: use long type for page counts in mm_populate() and get_user_pages() mm: accurately document nr_free_*_pages functions with code comments HWPOISON: change order of error_states[]'s elements HWPOISON: fix misjudgement of page_action() for errors on mlocked pages memcg: stop warning on memcg_propagate_kmem net: change type of virtio_chan->p9_max_pages vmscan: change type of vm_total_pages to unsigned long fs/nfsd: change type of max_delegations, nfsd_drc_max_mem and nfsd_drc_mem_used ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2013-02-23 17:50:35 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2013-02-23 17:50:35 -0800
commit: 5ce1a70e2f00f0bce0cab57f798ca354b9496169 (patch)
tree: 6e80200536b7a3576fd71ff2c7135ffe87dc858e /mm
parent: 9d3cae26acb471d5954cfdc25d1438b32060babe (diff)
parent: ef53d16cded7f89b3843b7a96970dab897843ea5 (diff)
40 files changed, 2895 insertions, 1346 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 0b23db9a879..2c7aea7106f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -162,10 +162,16 @@ config MOVABLE_NODE
 	  Say Y here if you want to hotplug a whole node.
 	  Say N here if you want kernel to use memory on all nodes evenly.
 
+#
+# Only be set on architectures that have completely implemented memory hotplug
+# feature. If you are not sure, don't touch it.
+#
+config HAVE_BOOTMEM_INFO_NODE
+	def_bool n
+
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
-	select MEMORY_ISOLATION
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
 	depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
 	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
@@ -176,6 +182,8 @@ config MEMORY_HOTPLUG_SPARSE
 
 config MEMORY_HOTREMOVE
 	bool "Allow for memory hot remove"
+	select MEMORY_ISOLATION
+	select HAVE_BOOTMEM_INFO_NODE if X86_64
 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
 	depends on MIGRATION
 
diff --git a/mm/compaction.c b/mm/compaction.c
index c62bd063d76..05ccb4cc0bd 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -15,6 +15,7 @@
 #include <linux/sysctl.h>
 #include <linux/sysfs.h>
 #include <linux/balloon_compaction.h>
+#include <linux/page-isolation.h>
 #include "internal.h"
 
 #ifdef CONFIG_COMPACTION
@@ -85,7 +86,7 @@ static inline bool isolation_suitable(struct compact_control *cc,
 static void __reset_isolation_suitable(struct zone *zone)
 {
 	unsigned long start_pfn = zone->zone_start_pfn;
-	unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long pfn;
 
 	zone->compact_cached_migrate_pfn = start_pfn;
@@ -215,7 +216,10 @@ static bool suitable_migration_target(struct page *page)
 	int migratetype = get_pageblock_migratetype(page);
 
 	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
-	if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
+	if (migratetype == MIGRATE_RESERVE)
+		return false;
+
+	if (is_migrate_isolate(migratetype))
 		return false;
 
 	/* If the page is a large free page, then allow migration */
@@ -611,8 +615,7 @@ check_compact_cluster:
 		continue;
 
 next_pageblock:
-		low_pfn += pageblock_nr_pages;
-		low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
+		low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
 		last_pageblock_nr = pageblock_nr;
 	}
 
@@ -644,7 +647,7 @@ static void isolate_freepages(struct zone *zone,
 				struct compact_control *cc)
 {
 	struct page *page;
-	unsigned long high_pfn, low_pfn, pfn, zone_end_pfn, end_pfn;
+	unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
 	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
@@ -663,7 +666,7 @@ static void isolate_freepages(struct zone *zone,
 	 */
 	high_pfn = min(low_pfn, pfn);
 
-	zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	z_end_pfn = zone_end_pfn(zone);
 
 	/*
 	 * Isolate free pages until enough are available to migrate the
@@ -706,7 +709,7 @@ static void isolate_freepages(struct zone *zone,
 		 * only scans within a pageblock
 		 */
 		end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
-		end_pfn = min(end_pfn, zone_end_pfn);
+		end_pfn = min(end_pfn, z_end_pfn);
 		isolated = isolate_freepages_block(cc, pfn, end_pfn,
 						   freelist, false);
 		nr_freepages += isolated;
@@ -795,7 +798,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
 
 	/* Only scan within a pageblock boundary */
-	end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages);
+	end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
 
 	/* Do not cross the free scanner or scan within a memory hole */
 	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
@@ -920,7 +923,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 {
 	int ret;
 	unsigned long start_pfn = zone->zone_start_pfn;
-	unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	unsigned long end_pfn = zone_end_pfn(zone);
 
 	ret = compaction_suitable(zone, cc->order);
 	switch (ret) {
@@ -977,7 +980,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
-				(unsigned long)cc, false,
+				(unsigned long)cc,
 				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
 				MR_COMPACTION);
 		update_nr_listpages(cc);
@@ -1086,7 +1089,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 
 
 /* Compact all zones within a node */
-static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
+static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 {
 	int zoneid;
 	struct zone *zone;
@@ -1119,28 +1122,26 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 		VM_BUG_ON(!list_empty(&cc->freepages));
 		VM_BUG_ON(!list_empty(&cc->migratepages));
 	}
-
-	return 0;
 }
 
-int compact_pgdat(pg_data_t *pgdat, int order)
+void compact_pgdat(pg_data_t *pgdat, int order)
 {
 	struct compact_control cc = {
 		.order = order,
 		.sync = false,
 	};
 
-	return __compact_pgdat(pgdat, &cc);
+	__compact_pgdat(pgdat, &cc);
 }
 
-static int compact_node(int nid)
+static void compact_node(int nid)
 {
 	struct compact_control cc = {
 		.order = -1,
 		.sync = true,
 	};
 
-	return __compact_pgdat(NODE_DATA(nid), &cc);
+	__compact_pgdat(NODE_DATA(nid), &cc);
 }
 
 /* Compact all nodes in the system */
diff --git a/mm/fadvise.c b/mm/fadvise.c
index a47f0f50c89..909ec558625 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -17,6 +17,7 @@
 #include <linux/fadvise.h>
 #include <linux/writeback.h>
 #include <linux/syscalls.h>
+#include <linux/swap.h>
 
 #include <asm/unistd.h>
 
@@ -120,9 +121,22 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
 		end_index = (endbyte >> PAGE_CACHE_SHIFT);
 
-		if (end_index >= start_index)
-			invalidate_mapping_pages(mapping, start_index,
+		if (end_index >= start_index) {
+			unsigned long count = invalidate_mapping_pages(mapping,
+						start_index, end_index);
+
+			/*
+			 * If fewer pages were invalidated than expected then
+			 * it is possible that some of the pages were on
+			 * a per-cpu pagevec for a remote CPU. Drain all
+			 * pagevecs and try again.
+			 */
+			if (count < (end_index - start_index + 1)) {
+				lru_add_drain_all();
+				invalidate_mapping_pages(mapping, start_index,
 						end_index);
+			}
+		}
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/mm/fremap.c b/mm/fremap.c
index a0aaf0e5680..0cd4c11488e 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -129,6 +129,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	struct vm_area_struct *vma;
 	int err = -EINVAL;
 	int has_write_lock = 0;
+	vm_flags_t vm_flags;
 
 	if (prot)
 		return err;
@@ -160,15 +161,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	/*
 	 * Make sure the vma is shared, that it supports prefaulting,
 	 * and that the remapped range is valid and fully within
-	 * the single existing vma.  vm_private_data is used as a
-	 * swapout cursor in a VM_NONLINEAR vma.
+	 * the single existing vma.
 	 */
 	if (!vma || !(vma->vm_flags & VM_SHARED))
 		goto out;
 
-	if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
-		goto out;
-
 	if (!vma->vm_ops || !vma->vm_ops->remap_pages)
 		goto out;
 
@@ -177,6 +174,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 
 	/* Must set VM_NONLINEAR before any pages are populated. */
 	if (!(vma->vm_flags & VM_NONLINEAR)) {
+		/*
+		 * vm_private_data is used as a swapout cursor
+		 * in a VM_NONLINEAR vma.
+		 */
+		if (vma->vm_private_data)
+			goto out;
+
 		/* Don't need a nonlinear mapping, exit success */
 		if (pgoff == linear_page_index(vma, start)) {
 			err = 0;
@@ -184,6 +188,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 		}
 
 		if (!has_write_lock) {
+get_write_lock:
 			up_read(&mm->mmap_sem);
 			down_write(&mm->mmap_sem);
 			has_write_lock = 1;
@@ -199,9 +204,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
 
-			flags &= MAP_NONBLOCK;
-			addr = mmap_region(file, start, size,
-					flags, vma->vm_flags, pgoff);
+			vm_flags = vma->vm_flags;
+			if (!(flags & MAP_NONBLOCK))
+				vm_flags |= VM_POPULATE;
+			addr = mmap_region(file, start, size, vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -220,32 +226,26 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 		mutex_unlock(&mapping->i_mmap_mutex);
 	}
 
+	if (!(flags & MAP_NONBLOCK) && !(vma->vm_flags & VM_POPULATE)) {
+		if (!has_write_lock)
+			goto get_write_lock;
+		vma->vm_flags |= VM_POPULATE;
+	}
+
 	if (vma->vm_flags & VM_LOCKED) {
 		/*
 		 * drop PG_Mlocked flag for over-mapped range
 		 */
-		vm_flags_t saved_flags = vma->vm_flags;
+		if (!has_write_lock)
+			goto get_write_lock;
+		vm_flags = vma->vm_flags;
 		munlock_vma_pages_range(vma, start, start + size);
-		vma->vm_flags = saved_flags;
+		vma->vm_flags = vm_flags;
 	}
 
 	mmu_notifier_invalidate_range_start(mm, start, start + size);
 	err = vma->vm_ops->remap_pages(vma, start, size, pgoff);
 	mmu_notifier_invalidate_range_end(mm, start, start + size);
-	if (!err && !(flags & MAP_NONBLOCK)) {
-		if (vma->vm_flags & VM_LOCKED) {
-			/*
-			 * might be mapping previously unmapped range of file
-			 */
-			mlock_vma_pages_range(vma, start, start + size);
-		} else {
-			if (unlikely(has_write_lock)) {
-				downgrade_write(&mm->mmap_sem);
-				has_write_lock = 0;
-			}
-			make_pages_present(start, start+size);
-		}
-	}
 
 	/*
 	 * We can't clear VM_NONLINEAR because we'd have to do
@@ -254,10 +254,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	 */
 
 out:
+	vm_flags = vma->vm_flags;
 	if (likely(!has_write_lock))
 		up_read(&mm->mmap_sem);
 	else
 		up_write(&mm->mmap_sem);
+	if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK)))
+		mm_populate(start, size);
 
 	return err;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b5783d81eda..bfa142e67b1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -20,6 +20,7 @@
 #include <linux/mman.h>
 #include <linux/pagemap.h>
 #include <linux/migrate.h>
+#include <linux/hashtable.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -62,12 +63,11 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
 static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
 
 static int khugepaged(void *none);
-static int mm_slots_hash_init(void);
 static int khugepaged_slab_init(void);
-static void khugepaged_slab_free(void);
 
-#define MM_SLOTS_HASH_HEADS 1024
-static struct hlist_head *mm_slots_hash __read_mostly;
+#define MM_SLOTS_HASH_BITS 10
+static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
+
 static struct kmem_cache *mm_slot_cache __read_mostly;
 
 /**
@@ -105,7 +105,6 @@ static int set_recommended_min_free_kbytes(void)
 	struct zone *zone;
 	int nr_zones = 0;
 	unsigned long recommended_min;
-	extern int min_free_kbytes;
 
 	if (!khugepaged_enabled())
 		return 0;
@@ -634,12 +633,6 @@ static int __init hugepage_init(void)
 	if (err)
 		goto out;
 
-	err = mm_slots_hash_init();
-	if (err) {
-		khugepaged_slab_free();
-		goto out;
-	}
-
 	register_shrinker(&huge_zero_page_shrinker);
 
 	/*
@@ -1302,7 +1295,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	int target_nid;
 	int current_nid = -1;
 	bool migrated;
-	bool page_locked = false;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
@@ -1324,7 +1316,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Acquire the page lock to serialise THP migrations */
 	spin_unlock(&mm->page_table_lock);
 	lock_page(page);
-	page_locked = true;
 
 	/* Confirm the PTE did not while locked */
 	spin_lock(&mm->page_table_lock);
@@ -1337,34 +1328,26 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Migrate the THP to the requested node */
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
-				pmdp, pmd, addr,
-				page, target_nid);
-	if (migrated)
-		current_nid = target_nid;
-	else {
-		spin_lock(&mm->page_table_lock);
-		if (unlikely(!pmd_same(pmd, *pmdp))) {
-			unlock_page(page);
-			goto out_unlock;
-		}
-		goto clear_pmdnuma;
-	}
+				pmdp, pmd, addr, page, target_nid);
+	if (!migrated)
+		goto check_same;
 
-	task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
+	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
 	return 0;
 
+check_same:
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(pmd, *pmdp)))
+		goto out_unlock;
 clear_pmdnuma:
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
-	if (page_locked)
-		unlock_page(page);
-
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
 	if (current_nid != -1)
-		task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
+		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
 	return 0;
 }
 
@@ -1656,7 +1639,7 @@ static void __split_huge_page_refcount(struct page *page)
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
-		page_xchg_last_nid(page_tail, page_last_nid(page));
+		page_nid_xchg_last(page_tail, page_nid_last(page));
 
 		BUG_ON(!PageAnon(page_tail));
 		BUG_ON(!PageUptodate(page_tail));
@@ -1846,7 +1829,7 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(PageCompound(page));
 out_unlock:
-	anon_vma_unlock(anon_vma);
+	anon_vma_unlock_write(anon_vma);
 	put_anon_vma(anon_vma);
 out:
 	return ret;
@@ -1908,12 +1891,6 @@ static int __init khugepaged_slab_init(void)
 	return 0;
 }
 
-static void __init khugepaged_slab_free(void)
-{
-	kmem_cache_destroy(mm_slot_cache);
-	mm_slot_cache = NULL;
-}
-
 static inline struct mm_slot *alloc_mm_slot(void)
 {
 	if (!mm_slot_cache)	/* initialization failed */
@@ -1926,47 +1903,23 @@ static inline void free_mm_slot(struct mm_slot *mm_slot)
 	kmem_cache_free(mm_slot_cache, mm_slot);
 }
 
-static int __init mm_slots_hash_init(void)
-{
-	mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head),
-				GFP_KERNEL);
-	if (!mm_slots_hash)
-		return -ENOMEM;
-	return 0;
-}
-
-#if 0
-static void __init mm_slots_hash_free(void)
-{
-	kfree(mm_slots_hash);
-	mm_slots_hash = NULL;
-}
-#endif
-
 static struct mm_slot *get_mm_slot(struct mm_struct *mm)
 {
 	struct mm_slot *mm_slot;
-	struct hlist_head *bucket;
 	struct hlist_node *node;
 
-	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
-				% MM_SLOTS_HASH_HEADS];
-	hlist_for_each_entry(mm_slot, node, bucket, hash) {
+	hash_for_each_possible(mm_slots_hash, mm_slot, node, hash, (unsigned long)mm)
 		if (mm == mm_slot->mm)
 			return mm_slot;
-	}
+
 	return NULL;
 }
 
 static void insert_to_mm_slots_hash(struct mm_struct *mm,
 				    struct mm_slot *mm_slot)
 {
-	struct hlist_head *bucket;
-
-	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
-				% MM_SLOTS_HASH_HEADS];
 	mm_slot->mm = mm;
-	hlist_add_head(&mm_slot->hash, bucket);
+	hash_add(mm_slots_hash, &mm_slot->hash, (long)mm);
 }
 
 static inline int khugepaged_test_exit(struct mm_struct *mm)
@@ -2035,7 +1988,7 @@ void __khugepaged_exit(struct mm_struct *mm)
 	spin_lock(&khugepaged_mm_lock);
 	mm_slot = get_mm_slot(mm);
 	if (mm_slot && khugepaged_scan.mm_slot != mm_slot) {
-		hlist_del(&mm_slot->hash);
+		hash_del(&mm_slot->hash);
 		list_del(&mm_slot->mm_node);
 		free = 1;
 	}
@@ -2368,7 +2321,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 		BUG_ON(!pmd_none(*pmd));
 		set_pmd_at(mm, address, pmd, _pmd);
 		spin_unlock(&mm->page_table_lock);
-		anon_vma_unlock(vma->anon_vma);
+		anon_vma_unlock_write(vma->anon_vma);
 		goto out;
 	}
 
@@ -2376,7 +2329,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * All pages are isolated and locked so anon_vma rmap
 	 * can't run anymore.
 	 */
-	anon_vma_unlock(vma->anon_vma);
+	anon_vma_unlock_write(vma->anon_vma);
 
 	__collapse_huge_page_copy(pte, new_page, vma, address, ptl);
 	pte_unmap(pte);
@@ -2423,7 +2376,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	struct page *page;
 	unsigned long _address;
 	spinlock_t *ptl;
-	int node = -1;
+	int node = NUMA_NO_NODE;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
@@ -2453,7 +2406,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		 * be more sophisticated and look at more pages,
 		 * but isn't for now.
 		 */
-		if (node == -1)
+		if (node == NUMA_NO_NODE)
 			node = page_to_nid(page);
 		VM_BUG_ON(PageCompound(page));
 		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
@@ -2484,7 +2437,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot)
 
 	if (khugepaged_test_exit(mm)) {
 		/* free mm_slot */
-		hlist_del(&mm_slot->hash);
+		hash_del(&mm_slot->hash);
 		list_del(&mm_slot->mm_node);
 
 		/*
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 546db81820e..cdb64e4d238 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1293,8 +1293,7 @@ static void __init report_hugepages(void)
 
 	for_each_hstate(h) {
 		char buf[32];
-		printk(KERN_INFO "HugeTLB registered %s page size, "
-				 "pre-allocated %ld pages\n",
+		pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n",
 			memfmt(buf, huge_page_size(h)),
 			h->free_huge_pages);
 	}
@@ -1702,8 +1701,7 @@ static void __init hugetlb_sysfs_init(void)
 		err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
 					 hstate_kobjs, &hstate_attr_group);
 		if (err)
-			printk(KERN_ERR "Hugetlb: Unable to add hstate %s",
-								h->name);
+			pr_err("Hugetlb: Unable to add hstate %s", h->name);
 	}
 }
 
@@ -1826,9 +1824,8 @@ void hugetlb_register_node(struct node *node)
 						nhs->hstate_kobjs,
 						&per_node_hstate_attr_group);
 		if (err) {
-			printk(KERN_ERR "Hugetlb: Unable to add hstate %s"
-					" for node %d\n",
-						h->name, node->dev.id);
+			pr_err("Hugetlb: Unable to add hstate %s for node %d\n",
+				h->name, node->dev.id);
 			hugetlb_unregister_node(node);
 			break;
 		}
@@ -1924,7 +1921,7 @@ void __init hugetlb_add_hstate(unsigned order)
 	unsigned long i;
 
 	if (size_to_hstate(PAGE_SIZE << order)) {
-		printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
+		pr_warning("hugepagesz= specified twice, ignoring\n");
 		return;
 	}
 	BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
@@ -1960,8 +1957,8 @@ static int __init hugetlb_nrpages_setup(char *s)
 		mhp = &parsed_hstate->max_huge_pages;
 
 	if (mhp == last_mhp) {
-		printk(KERN_WARNING "hugepages= specified twice without "
-			"interleaving hugepagesz=, ignoring\n");
+		pr_warning("hugepages= specified twice without "
+			   "interleaving hugepagesz=, ignoring\n");
 		return 1;
 	}
 
@@ -2692,9 +2689,8 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * COW. Warn that such a situation has occurred as it may not be obvious
 	 */
 	if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
-		printk(KERN_WARNING
-			"PID %d killed due to inadequate hugepage pool\n",
-			current->pid);
+		pr_warning("PID %d killed due to inadequate hugepage pool\n",
+			   current->pid);
 		return ret;
 	}
 
@@ -2924,14 +2920,14 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
-int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
-			struct page **pages, struct vm_area_struct **vmas,
-			unsigned long *position, int *length, int i,
-			unsigned int flags)
+long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
+			 struct page **pages, struct vm_area_struct **vmas,
+			 unsigned long *position, unsigned long *nr_pages,
+			 long i, unsigned int flags)
 {
 	unsigned long pfn_offset;
 	unsigned long vaddr = *position;
-	int remainder = *length;
+	unsigned long remainder = *nr_pages;
 	struct hstate *h = hstate_vma(vma);
 
 	spin_lock(&mm->page_table_lock);
@@ -3001,7 +2997,7 @@ same_page:
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
-	*length = remainder;
+	*nr_pages = remainder;
 	*position = vaddr;
 
 	return i ? i : -EFAULT;
diff --git a/mm/internal.h b/mm/internal.h
index 9ba21100ebf..1c0c4cc0fcf 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -162,8 +162,8 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct rb_node *rb_parent);
 
 #ifdef CONFIG_MMU
-extern long mlock_vma_pages_range(struct vm_area_struct *vma,
-			unsigned long start, unsigned long end);
+extern long __mlock_vma_pages_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end, int *nonblocking);
 extern void munlock_vma_pages_range(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end);
 static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 752a705c77c..83dd5fbf5e6 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1300,9 +1300,8 @@ static void kmemleak_scan(void)
 	 */
 	lock_memory_hotplug();
 	for_each_online_node(i) {
-		pg_data_t *pgdat = NODE_DATA(i);
-		unsigned long start_pfn = pgdat->node_start_pfn;
-		unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
+		unsigned long start_pfn = node_start_pfn(i);
+		unsigned long end_pfn = node_end_pfn(i);
 		unsigned long pfn;
 
 		for (pfn = start_pfn; pfn < end_pfn; pfn++) {
diff --git a/mm/ksm.c b/mm/ksm.c
index 51573858938..ab2ba9ad3c5 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -33,13 +33,22 @@
 #include <linux/mmu_notifier.h>
 #include <linux/swap.h>
 #include <linux/ksm.h>
-#include <linux/hash.h>
+#include <linux/hashtable.h>
 #include <linux/freezer.h>
 #include <linux/oom.h>
+#include <linux/numa.h>
 
 #include <asm/tlbflush.h>
 #include "internal.h"
 
+#ifdef CONFIG_NUMA
+#define NUMA(x)		(x)
+#define DO_NUMA(x)	do { (x); } while (0)
+#else
+#define NUMA(x)		(0)
+#define DO_NUMA(x)	do { } while (0)
+#endif
+
 /*
  * A few notes about the KSM scanning process,
  * to make it easier to understand the data structures below:
@@ -78,6 +87,9 @@
  *    take 10 attempts to find a page in the unstable tree, once it is found,
  *    it is secured in the stable tree.  (When we scan a new page, we first
  *    compare it against the stable tree, and then against the unstable tree.)
+ *
+ * If the merge_across_nodes tunable is unset, then KSM maintains multiple
+ * stable trees and multiple unstable trees: one of each for each NUMA node.
  */
 
 /**
@@ -113,19 +125,32 @@ struct ksm_scan {
 /**
  * struct stable_node - node of the stable rbtree
  * @node: rb node of this ksm page in the stable tree
+ * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list
+ * @list: linked into migrate_nodes, pending placement in the proper node tree
  * @hlist: hlist head of rmap_items using this ksm page
- * @kpfn: page frame number of this ksm page
+ * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid)
+ * @nid: NUMA node id of stable tree in which linked (may not match kpfn)
  */
 struct stable_node {
-	struct rb_node node;
+	union {
+		struct rb_node node;	/* when node of stable tree */
+		struct {		/* when listed for migration */
+			struct list_head *head;
+			struct list_head list;
+		};
+	};
 	struct hlist_head hlist;
 	unsigned long kpfn;
+#ifdef CONFIG_NUMA
+	int nid;
+#endif
 };
 
 /**
  * struct rmap_item - reverse mapping item for virtual addresses
  * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list
  * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree
+ * @nid: NUMA node id of unstable tree in which linked (may not match page)
  * @mm: the memory structure this rmap_item is pointing into
  * @address: the virtual address this rmap_item tracks (+ flags in low bits)
  * @oldchecksum: previous checksum of the page at that virtual address
@@ -135,7 +160,12 @@ struct stable_node {
  */
 struct rmap_item {
 	struct rmap_item *rmap_list;
-	struct anon_vma *anon_vma;	/* when stable */
+	union {
+		struct anon_vma *anon_vma;	/* when stable */
+#ifdef CONFIG_NUMA
+		int nid;		/* when node of unstable tree */
+#endif
+	};
 	struct mm_struct *mm;
 	unsigned long address;		/* + low bits used for flags below */
 	unsigned int oldchecksum;	/* when unstable */
@@ -153,12 +183,16 @@ struct rmap_item {
 #define STABLE_FLAG	0x200	/* is listed from the stable tree */
 
 /* The stable and unstable tree heads */
-static struct rb_root root_stable_tree = RB_ROOT;
-static struct rb_root root_unstable_tree = RB_ROOT;
+static struct rb_root one_stable_tree[1] = { RB_ROOT };
+static struct rb_root one_unstable_tree[1] = { RB_ROOT };
+static struct rb_root *root_stable_tree = one_stable_tree;
+static struct rb_root *root_unstable_tree = one_unstable_tree;
 
-#define MM_SLOTS_HASH_SHIFT 10
-#define MM_SLOTS_HASH_HEADS (1 << MM_SLOTS_HASH_SHIFT)
-static struct hlist_head mm_slots_hash[MM_SLOTS_HASH_HEADS];
+/* Recently migrated nodes of stable tree, pending proper placement */
+static LIST_HEAD(migrate_nodes);
+
+#define MM_SLOTS_HASH_BITS 10
+static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
 
 static struct mm_slot ksm_mm_head = {
 	.mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list),
@@ -189,10 +223,21 @@ static unsigned int ksm_thread_pages_to_scan = 100;
 /* Milliseconds ksmd should sleep between batches */
 static unsigned int ksm_thread_sleep_millisecs = 20;
 
+#ifdef CONFIG_NUMA
+/* Zeroed when merging across nodes is not allowed */
+static unsigned int ksm_merge_across_nodes = 1;
+static int ksm_nr_node_ids = 1;
+#else
+#define ksm_merge_across_nodes	1U
+#define ksm_nr_node_ids		1
+#endif
+
 #define KSM_RUN_STOP	0
 #define KSM_RUN_MERGE	1
 #define KSM_RUN_UNMERGE	2
-static unsigned int ksm_run = KSM_RUN_STOP;
+#define KSM_RUN_OFFLINE	4
+static unsigned long ksm_run = KSM_RUN_STOP;
+static void wait_while_offlining(void);
 
 static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait);
 static DEFINE_MUTEX(ksm_thread_mutex);
@@ -275,31 +320,21 @@ static inline void free_mm_slot(struct mm_slot *mm_slot)
 
 static struct mm_slot *get_mm_slot(struct mm_struct *mm)
 {
-	struct mm_slot *mm_slot;
-	struct hlist_head *bucket;
 	struct hlist_node *node;
+	struct mm_slot *slot;
+
+	hash_for_each_possible(mm_slots_hash, slot, node, link, (unsigned long)mm)
+		if (slot->mm == mm)
+			return slot;
 
-	bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)];
-	hlist_for_each_entry(mm_slot, node, bucket, link) {
-		if (mm == mm_slot->mm)
-			return mm_slot;
-	}
 	return NULL;
 }
 
 static void insert_to_mm_slots_hash(struct mm_struct *mm,
 				    struct mm_slot *mm_slot)
 {
-	struct hlist_head *bucket;
-
-	bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)];
 	mm_slot->mm = mm;
-	hlist_add_head(&mm_slot->link, bucket);
-}
-
-static inline int in_stable_tree(struct rmap_item *rmap_item)
-{
-	return rmap_item->address & STABLE_FLAG;
+	hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm);
 }
 
 /*
@@ -333,7 +368,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 
 	do {
 		cond_resched();
-		page = follow_page(vma, addr, FOLL_GET);
+		page = follow_page(vma, addr, FOLL_GET | FOLL_MIGRATION);
 		if (IS_ERR_OR_NULL(page))
 			break;
 		if (PageKsm(page))
@@ -447,6 +482,17 @@ out:		page = NULL;
 	return page;
 }
 
+/*
+ * This helper is used for getting right index into array of tree roots.
+ * When merge_across_nodes knob is set to 1, there are only two rb-trees for
+ * stable and unstable pages from all nodes with roots in index 0. Otherwise,
+ * every node has its own stable and unstable tree.
+ */
+static inline int get_kpfn_nid(unsigned long kpfn)
+{
+	return ksm_merge_across_nodes ? 0 : pfn_to_nid(kpfn);
+}
+
 static void remove_node_from_stable_tree(struct stable_node *stable_node)
 {
 	struct rmap_item *rmap_item;
@@ -462,7 +508,11 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node)
 		cond_resched();
 	}
 
-	rb_erase(&stable_node->node, &root_stable_tree);
+	if (stable_node->head == &migrate_nodes)
+		list_del(&stable_node->list);
+	else
+		rb_erase(&stable_node->node,
+			 root_stable_tree + NUMA(stable_node->nid));
 	free_stable_node(stable_node);
 }
 
@@ -472,6 +522,7 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node)
  * In which case we can trust the content of the page, and it
  * returns the gotten page; but if the page has now been zapped,
  * remove the stale node from the stable tree and return NULL.
+ * But beware, the stable node's page might be being migrated.
  *
  * You would expect the stable_node to hold a reference to the ksm page.
  * But if it increments the page's count, swapping out has to wait for
@@ -482,40 +533,77 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node)
  * pointing back to this stable node.  This relies on freeing a PageAnon
  * page to reset its page->mapping to NULL, and relies on no other use of
  * a page to put something that might look like our key in page->mapping.
- *
- * include/linux/pagemap.h page_cache_get_speculative() is a good reference,
- * but this is different - made simpler by ksm_thread_mutex being held, but
- * interesting for assuming that no other use of the struct page could ever
- * put our expected_mapping into page->mapping (or a field of the union which
- * coincides with page->mapping).  The RCU calls are not for KSM at all, but
- * to keep the page_count protocol described with page_cache_get_speculative.
- *
- * Note: it is possible that get_ksm_page() will return NULL one moment,
- * then page the next, if the page is in between page_freeze_refs() and
- * page_unfreeze_refs(): this shouldn't be a problem anywhere, the page
  * is on its way to being freed; but it is an anomaly to bear in mind.
  */
-static struct page *get_ksm_page(struct stable_node *stable_node)
+static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it)
 {
 	struct page *page;
 	void *expected_mapping;
+	unsigned long kpfn;
 
-	page = pfn_to_page(stable_node->kpfn);
 	expected_mapping = (void *)stable_node +
 				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
-	rcu_read_lock();
-	if (page->mapping != expected_mapping)
-		goto stale;
-	if (!get_page_unless_zero(page))
+again:
+	kpfn = ACCESS_ONCE(stable_node->kpfn);
+	page = pfn_to_page(kpfn);
+
+	/*
+	 * page is computed from kpfn, so on most architectures reading
+	 * page->mapping is naturally ordered after reading node->kpfn,
+	 * but on Alpha we need to be more careful.
+	 */
+	smp_read_barrier_depends();
+	if (ACCESS_ONCE(page->mapping) != expected_mapping)
 		goto stale;
-	if (page->mapping != expected_mapping) {
+
+	/*
+	 * We cannot do anything with the page while its refcount is 0.
+	 * Usually 0 means free, or tail of a higher-order page: in which
+	 * case this node is no longer referenced, and should be freed;
+	 * however, it might mean that the page is under page_freeze_refs().
+	 * The __remove_mapping() case is easy, again the node is now stale;
+	 * but if page is swapcache in migrate_page_move_mapping(), it might
+	 * still be our page, in which case it's essential to keep the node.
+	 */
+	while (!get_page_unless_zero(page)) {
+		/*
+		 * Another check for page->mapping != expected_mapping would
+		 * work here too.  We have chosen the !PageSwapCache test to
+		 * optimize the common case, when the page is or is about to
+		 * be freed: PageSwapCache is cleared (under spin_lock_irq)
+		 * in the freeze_refs section of __remove_mapping(); but Anon
+		 * page->mapping reset to NULL later, in free_pages_prepare().
+		 */
+		if (!PageSwapCache(page))
+			goto stale;
+		cpu_relax();
+	}
+
+	if (ACCESS_ONCE(page->mapping) != expected_mapping) {
 		put_page(page);
 		goto stale;
 	}
-	rcu_read_unlock();
+
+	if (lock_it) {
+		lock_page(page);
+		if (ACCESS_ONCE(page->mapping) != expected_mapping) {
+			unlock_page(page);
+			put_page(page);
+			goto stale;
+		}
+	}
 	return page;
+
 stale:
-	rcu_read_unlock();
+	/*
+	 * We come here from above when page->mapping or !PageSwapCache
+	 * suggests that the node is stale; but it might be under migration.
+	 * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(),
+	 * before checking whether node->kpfn has been changed.
+	 */
+	smp_rmb();
+	if (ACCESS_ONCE(stable_node->kpfn) != kpfn)
+		goto again;
 	remove_node_from_stable_tree(stable_node);
 	return NULL;
 }
@@ -531,11 +619,10 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item)
 		struct page *page;
 
 		stable_node = rmap_item->head;
-		page = get_ksm_page(stable_node);
+		page = get_ksm_page(stable_node, true);
 		if (!page)
 			goto out;
 
-		lock_page(page);
 		hlist_del(&rmap_item->hlist);
 		unlock_page(page);
 		put_page(page);
@@ -560,8 +647,8 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item)
 		age = (unsigned char)(ksm_scan.seqnr - rmap_item->address);
 		BUG_ON(age > 1);
 		if (!age)
-			rb_erase(&rmap_item->node, &root_unstable_tree);
-
+			rb_erase(&rmap_item->node,
+				 root_unstable_tree + NUMA(rmap_item->nid));
 		ksm_pages_unshared--;
 		rmap_item->address &= PAGE_MASK;
 	}
@@ -581,7 +668,7 @@ static void remove_trailing_rmap_items(struct mm_slot *mm_slot,
 }
 
 /*
- * Though it's very tempting to unmerge in_stable_tree(rmap_item)s rather
+ * Though it's very tempting to unmerge rmap_items from stable tree rather
  * than check every pte of a given vma, the locking doesn't quite work for
  * that - an rmap_item is assigned to the stable tree after inserting ksm
  * page and upping mmap_sem.  Nor does it fit with the way we skip dup'ing
@@ -614,6 +701,71 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma,
 /*
  * Only called through the sysfs control interface:
  */
+static int remove_stable_node(struct stable_node *stable_node)
+{
+	struct page *page;
+	int err;
+
+	page = get_ksm_page(stable_node, true);
+	if (!page) {
+		/*
+		 * get_ksm_page did remove_node_from_stable_tree itself.
+		 */
+		return 0;
+	}
+
+	if (WARN_ON_ONCE(page_mapped(page))) {
+		/*
+		 * This should not happen: but if it does, just refuse to let
+		 * merge_across_nodes be switched - there is no need to panic.
+		 */
+		err = -EBUSY;
+	} else {
+		/*
+		 * The stable node did not yet appear stale to get_ksm_page(),
+		 * since that allows for an unmapped ksm page to be recognized
+		 * right up until it is freed; but the node is safe to remove.
+		 * This page might be in a pagevec waiting to be freed,
+		 * or it might be PageSwapCache (perhaps under writeback),
+		 * or it might have been removed from swapcache a moment ago.
+		 */
+		set_page_stable_node(page, NULL);
+		remove_node_from_stable_tree(stable_node);
+		err = 0;
+	}
+
+	unlock_page(page);
+	put_page(page);
+	return err;
+}
+
+static int remove_all_stable_nodes(void)
+{
+	struct stable_node *stable_node;
+	struct list_head *this, *next;
+	int nid;
+	int err = 0;
+
+	for (nid = 0; nid < ksm_nr_node_ids; nid++) {
+		while (root_stable_tree[nid].rb_node) {
+			stable_node = rb_entry(root_stable_tree[nid].rb_node,
+						struct stable_node, node);
+			if (remove_stable_node(stable_node)) {
+				err = -EBUSY;
+				break;	/* proceed to next nid */
+			}
+			cond_resched();
+		}
+	}
+	list_for_each_safe(this, next, &migrate_nodes) {
+		stable_node = list_entry(this, struct stable_node, list);
+		if (remove_stable_node(stable_node))
+			err = -EBUSY;
+		cond_resched();
+	}
+	return err;
+}
+
 static int unmerge_and_remove_all_rmap_items(void)
 {
 	struct mm_slot *mm_slot;
@@ -647,7 +799,7 @@ static int unmerge_and_remove_all_rmap_items(void)
 		ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next,
 						struct mm_slot, mm_list);
 		if (ksm_test_exit(mm)) {
-			hlist_del(&mm_slot->link);
+			hash_del(&mm_slot->link);
 			list_del(&mm_slot->mm_list);
 			spin_unlock(&ksm_mmlist_lock);
 
@@ -661,6 +813,8 @@ static int unmerge_and_remove_all_rmap_items(void)
 		}
 	}
 
+	/* Clean up stable nodes, but don't worry if some are still busy */
+	remove_all_stable_nodes();
 	ksm_scan.seqnr = 0;
 	return 0;
 
@@ -946,6 +1100,9 @@ static int try_to_merge_with_ksm_page(struct rmap_item *rmap_item,
 	if (err)
 		goto out;
 
+	/* Unstable nid is in union with stable anon_vma: remove first */
+	remove_rmap_item_from_tree(rmap_item);
+
 	/* Must get reference to anon_vma while still holding mmap_sem */
 	rmap_item->anon_vma = vma->anon_vma;
 	get_anon_vma(vma->anon_vma);
@@ -996,42 +1153,99 @@ static struct page *try_to_merge_two_pages(struct rmap_item *rmap_item,
  */
 static struct page *stable_tree_search(struct page *page)
 {
-	struct rb_node *node = root_stable_tree.rb_node;
+	int nid;
+	struct rb_root *root;
+	struct rb_node **new;
+	struct rb_node *parent;
 	struct stable_node *stable_node;
+	struct stable_node *page_node;
 
-	stable_node = page_stable_node(page);
-	if (stable_node) {			/* ksm page forked */
+	page_node = page_stable_node(page);
+	if (page_node && page_node->head != &migrate_nodes) {
+		/* ksm page forked */
 		get_page(page);
 		return page;
 	}
 
-	while (node) {
+	nid = get_kpfn_nid(page_to_pfn(page));
+	root = root_stable_tree + nid;
+again:
+	new = &root->rb_node;
+	parent = NULL;
+
+	while (*new) {
 		struct page *tree_page;
 		int ret;
 
 		cond_resched();
-		stable_node = rb_entry(node, struct stable_node, node);
-		tree_page = get_ksm_page(stable_node);
+		stable_node = rb_entry(*new, struct stable_node, node);
+		tree_page = get_ksm_page(stable_node, false);
 		if (!tree_page)
 			return NULL;
 
 		ret = memcmp_pages(page, tree_page);
+		put_page(tree_page);
 
-		if (ret < 0) {
-			put_page(tree_page);
-			node = node->rb_left;
-		} else if (ret > 0) {
-			put_page(tree_page);
-			node = node->rb_right;
-		} else
-			return tree_page;
+		parent = *new;
+		if (ret < 0)
+			new = &parent->rb_left;
+		else if (ret > 0)
+			new = &parent->rb_right;
+		else {
+			/*
+			 * Lock and unlock the stable_node's page (which
+			 * might already have been migrated) so that page
+			 * migration is sure to notice its raised count.
+			 * It would be more elegant to return stable_node
+			 * than kpage, but that involves more changes.
+			 */
+			tree_page = get_ksm_page(stable_node, true);
+			if (tree_page) {
+				unlock_page(tree_page);
+				if (get_kpfn_nid(stable_node->kpfn) !=
+						NUMA(stable_node->nid)) {
+					put_page(tree_page);
+					goto replace;
+				}
+				return tree_page;
+			}
+			/*
+			 * There is now a place for page_node, but the tree may
+			 * have been rebalanced, so re-evaluate parent and new.
+			 */
+			if (page_node)
+				goto again;
+			return NULL;
+		}
 	}
 
-	return NULL;
+	if (!page_node)
+		return NULL;
+
+	list_del(&page_node->list);
+	DO_NUMA(page_node->nid = nid);
+	rb_link_node(&page_node->node, parent, new);
+	rb_insert_color(&page_node->node, root);
+	get_page(page);
+	return page;
+
+replace:
+	if (page_node) {
+		list_del(&page_node->list);
+		DO_NUMA(page_node->nid = nid);
+		rb_replace_node(&stable_node->node, &page_node->node, root);
+		get_page(page);
+	} else {
+		rb_erase(&stable_node->node, root);
+		page = NULL;
+	}
+	stable_node->head = &migrate_nodes;
+	list_add(&stable_node->list, stable_node->head);
+	return page;
 }
 
 /*
- * stable_tree_insert - insert rmap_item pointing to new ksm page
+ * stable_tree_insert - insert stable tree node pointing to new ksm page
  * into the stable tree.
  *
  * This function returns the stable tree node just allocated on success,
@@ -1039,17 +1253,25 @@ static struct page *stable_tree_search(struct page *page)
  */
 static struct stable_node *stable_tree_insert(struct page *kpage)
 {
-	struct rb_node **new = &root_stable_tree.rb_node;
+	int nid;
+	unsigned long kpfn;
+	struct rb_root *root;
+	struct rb_node **new;
 	struct rb_node *parent = NULL;
 	struct stable_node *stable_node;
 
+	kpfn = page_to_pfn(kpage);
+	nid = get_kpfn_nid(kpfn);
+	root = root_stable_tree + nid;
+	new = &root->rb_node;
+
 	while (*new) {
 		struct page *tree_page;
 		int ret;
 
 		cond_resched();
 		stable_node = rb_entry(*new, struct stable_node, node);
-		tree_page = get_ksm_page(stable_node);
+		tree_page = get_ksm_page(stable_node, false);
 		if (!tree_page)
 			return NULL;
 
@@ -1075,13 +1297,12 @@ static struct stable_node *stable_tree_insert(struct page *kpage)
 	if (!stable_node)
 		return NULL;
 
-	rb_link_node(&stable_node->node, parent, new);
-	rb_insert_color(&stable_node->node, &root_stable_tree);
-
 	INIT_HLIST_HEAD(&stable_node->hlist);
-
-	stable_node->kpfn = page_to_pfn(kpage);
+	stable_node->kpfn = kpfn;
 	set_page_stable_node(kpage, stable_node);
+	DO_NUMA(stable_node->nid = nid);
+	rb_link_node(&stable_node->node, parent, new);
+	rb_insert_color(&stable_node->node, root);
 
 	return stable_node;
 }
@@ -1104,10 +1325,15 @@ static
 struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item,
 					      struct page *page,
 					      struct page **tree_pagep)
-
 {
-	struct rb_node **new = &root_unstable_tree.rb_node;
+	struct rb_node **new;
+	struct rb_root *root;
 	struct rb_node *parent = NULL;
+	int nid;
+
+	nid = get_kpfn_nid(page_to_pfn(page));
+	root = root_unstable_tree + nid;
+	new = &root->rb_node;
 
 	while (*new) {
 		struct rmap_item *tree_rmap_item;
@@ -1137,6 +1363,15 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item,
 		} else if (ret > 0) {
 			put_page(tree_page);
 			new = &parent->rb_right;
+		} else if (!ksm_merge_across_nodes &&
+			   page_to_nid(tree_page) != nid) {
+			/*
+			 * If tree_page has been migrated to another NUMA node,
+			 * it will be flushed out and put in the right unstable
+			 * tree next time: only merge with it when across_nodes.
+			 */
+			put_page(tree_page);
+			return NULL;
 		} else {
 			*tree_pagep = tree_page;
 			return tree_rmap_item;
@@ -1145,8 +1380,9 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item,
 
 	rmap_item->address |= UNSTABLE_FLAG;
 	rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK);
+	DO_NUMA(rmap_item->nid = nid);
 	rb_link_node(&rmap_item->node, parent, new);
-	rb_insert_color(&rmap_item->node, &root_unstable_tree);
+	rb_insert_color(&rmap_item->node, root);
 
 	ksm_pages_unshared++;
 	return NULL;
@@ -1188,10 +1424,29 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 	unsigned int checksum;
 	int err;
 
-	remove_rmap_item_from_tree(rmap_item);
+	stable_node = page_stable_node(page);
+	if (stable_node) {
+		if (stable_node->head != &migrate_nodes &&
+		    get_kpfn_nid(stable_node->kpfn) != NUMA(stable_node->nid)) {
+			rb_erase(&stable_node->node,
+				 root_stable_tree + NUMA(stable_node->nid));
+			stable_node->head = &migrate_nodes;
+			list_add(&stable_node->list, stable_node->head);
+		}
+		if (stable_node->head != &migrate_nodes &&
+		    rmap_item->head == stable_node)
+			return;
+	}
 
 	/* We first start with searching the page inside the stable tree */
 	kpage = stable_tree_search(page);
+	if (kpage == page && rmap_item->head == stable_node) {
+		put_page(kpage);
+		return;
+	}
+
+	remove_rmap_item_from_tree(rmap_item);
+
 	if (kpage) {
 		err = try_to_merge_with_ksm_page(rmap_item, page, kpage);
 		if (!err) {
@@ -1225,14 +1480,11 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 		kpage = try_to_merge_two_pages(rmap_item, page,
 						tree_rmap_item, tree_page);
 		put_page(tree_page);
-		/*
-		 * As soon as we merge this page, we want to remove the
-		 * rmap_item of the page we have merged with from the unstable
-		 * tree, and insert it instead as new node in the stable tree.
-		 */
 		if (kpage) {
-			remove_rmap_item_from_tree(tree_rmap_item);
-
+			/*
+			 * The pages were successfully merged: insert new
+			 * node in the stable tree and add both rmap_items.
+			 */
 			lock_page(kpage);
 			stable_node = stable_tree_insert(kpage);
 			if (stable_node) {
@@ -1289,6 +1541,7 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page)
 	struct mm_slot *slot;
 	struct vm_area_struct *vma;
 	struct rmap_item *rmap_item;
+	int nid;
 
 	if (list_empty(&ksm_mm_head.mm_list))
 		return NULL;
@@ -1307,7 +1560,29 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page)
 		 */
 		lru_add_drain_all();
 
-		root_unstable_tree = RB_ROOT;
+		/*
+		 * Whereas stale stable_nodes on the stable_tree itself
+		 * get pruned in the regular course of stable_tree_search(),
+		 * those moved out to the migrate_nodes list can accumulate:
+		 * so prune them once before each full scan.
+		 */
+		if (!ksm_merge_across_nodes) {
+			struct stable_node *stable_node;
+			struct list_head *this, *next;
+			struct page *page;
+
+			list_for_each_safe(this, next, &migrate_nodes) {
+				stable_node = list_entry(this,
+						struct stable_node, list);
+				page = get_ksm_page(stable_node, false);
+				if (page)
+					put_page(page);
+				cond_resched();
+			}
+		}
+
+		for (nid = 0; nid < ksm_nr_node_ids; nid++)
+			root_unstable_tree[nid] = RB_ROOT;
 
 		spin_lock(&ksm_mmlist_lock);
 		slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list);
@@ -1392,7 +1667,7 @@ next_mm:
 		 * or when all VM_MERGEABLE areas have been unmapped (and
 		 * mmap_sem then protects against race with MADV_MERGEABLE).
 		 */
-		hlist_del(&slot->link);
+		hash_del(&slot->link);
 		list_del(&slot->mm_list);
 		spin_unlock(&ksm_mmlist_lock);
 
@@ -1428,8 +1703,7 @@ static void ksm_do_scan(unsigned int scan_npages)
 		rmap_item = scan_get_next_rmap_item(&page);
 		if (!rmap_item)
 			return;
-		if (!PageKsm(page) || !in_stable_tree(rmap_item))
-			cmp_and_merge_page(page, rmap_item);
+		cmp_and_merge_page(page, rmap_item);
 		put_page(page);
 	}
 }
@@ -1446,6 +1720,7 @@ static int ksm_scan_thread(void *nothing)
 
 	while (!kthread_should_stop()) {
 		mutex_lock(&ksm_thread_mutex);
+		wait_while_offlining();
 		if (ksmd_should_run())
 			ksm_do_scan(ksm_thread_pages_to_scan);
 		mutex_unlock(&ksm_thread_mutex);
@@ -1525,11 +1800,19 @@ int __ksm_enter(struct mm_struct *mm)
 	spin_lock(&ksm_mmlist_lock);
 	insert_to_mm_slots_hash(mm, mm_slot);
 	/*
-	 * Insert just behind the scanning cursor, to let the area settle
+	 * When KSM_RUN_MERGE (or KSM_RUN_STOP),
+	 * insert just behind the scanning cursor, to let the area settle
 	 * down a little; when fork is followed by immediate exec, we don't
 	 * want ksmd to waste time setting up and tearing down an rmap_list.
+	 *
+	 * But when KSM_RUN_UNMERGE, it's important to insert ahead of its
+	 * scanning cursor, otherwise KSM pages in newly forked mms will be
+	 * missed: then we might as well insert at the end of the list.
 	 */
-	list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list);
+	if (ksm_run & KSM_RUN_UNMERGE)
+		list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list);
+	else
+		list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list);
 	spin_unlock(&ksm_mmlist_lock);
 
 	set_bit(MMF_VM_MERGEABLE, &mm->flags);
@@ -1559,7 +1842,7 @@ void __ksm_exit(struct mm_struct *mm)
 	mm_slot = get_mm_slot(mm);
 	if (mm_slot && ksm_scan.mm_slot != mm_slot) {
 		if (!mm_slot->rmap_list) {
-			hlist_del(&mm_slot->link);
+			hash_del(&mm_slot->link);
 			list_del(&mm_slot->mm_list);
 			easy_to_free = 1;
 		} else {
@@ -1579,24 +1862,32 @@ void __ksm_exit(struct mm_struct *mm)
 	}
 }
 
-struct page *ksm_does_need_to_copy(struct page *page,
+struct page *ksm_might_need_to_copy(struct page *page,
 			struct vm_area_struct *vma, unsigned long address)
 {
+	struct anon_vma *anon_vma = page_anon_vma(page);
 	struct page *new_page;
 
+	if (PageKsm(page)) {
+		if (page_stable_node(page) &&
+		    !(ksm_run & KSM_RUN_UNMERGE))
+			return page;	/* no need to copy it */
+	} else if (!anon_vma) {
+		return page;		/* no need to copy it */
+	} else if (anon_vma->root == vma->anon_vma->root &&
+		 page->index == linear_page_index(vma, address)) {
+		return page;		/* still no need to copy it */
+	}
+	if (!PageUptodate(page))
+		return page;		/* let do_swap_page report the error */
+
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 	if (new_page) {
 		copy_user_highpage(new_page, page, address, vma);
 
 		SetPageDirty(new_page);
 		__SetPageUptodate(new_page);
-		SetPageSwapBacked(new_page);
 		__set_page_locked(new_page);
-
-		if (!mlocked_vma_newpage(vma, new_page))
-			lru_cache_add_lru(new_page, LRU_ACTIVE_ANON);
-		else
-			add_page_to_unevictable_list(new_page);
 	}
 
 	return new_page;
@@ -1773,64 +2064,115 @@ void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 	if (stable_node) {
 		VM_BUG_ON(stable_node->kpfn != page_to_pfn(oldpage));
 		stable_node->kpfn = page_to_pfn(newpage);
+		/*
+		 * newpage->mapping was set in advance; now we need smp_wmb()
+		 * to make sure that the new stable_node->kpfn is visible
+		 * to get_ksm_page() before it can see that oldpage->mapping
+		 * has gone stale (or that PageSwapCache has been cleared).
+		 */
+		smp_wmb();
+		set_page_stable_node(oldpage, NULL);
 	}
 }
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static struct stable_node *ksm_check_stable_tree(unsigned long start_pfn,
-						 unsigned long end_pfn)
+static int just_wait(void *word)
 {
-	struct rb_node *node;
+	schedule();
+	return 0;
+}
 
-	for (node = rb_first(&root_stable_tree); node; node = rb_next(node)) {
-		struct stable_node *stable_node;
+static void wait_while_offlining(void)
+{
+	while (ksm_run & KSM_RUN_OFFLINE) {
+		mutex_unlock(&ksm_thread_mutex);
+		wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE),
+				just_wait, TASK_UNINTERRUPTIBLE);
+		mutex_lock(&ksm_thread_mutex);
+	}
+}
 
-		stable_node = rb_entry(node, struct stable_node, node);
+static void ksm_check_stable_tree(unsigned long start_pfn,
+				  unsigned long end_pfn)
+{
+	struct stable_node *stable_node;
+	struct list_head *this, *next;
+	struct rb_node *node;
+	int nid;
+
+	for (nid = 0; nid < ksm_nr_node_ids; nid++) {
+		node = rb_first(root_stable_tree + nid);
+		while (node) {
+			stable_node = rb_entry(node, struct stable_node, node);
+			if (stable_node->kpfn >= start_pfn &&
+			    stable_node->kpfn < end_pfn) {
+				/*
+				 * Don't get_ksm_page, page has already gone:
+				 * which is why we keep kpfn instead of page*
+				 */
+				remove_node_from_stable_tree(stable_node);
+				node = rb_first(root_stable_tree + nid);
+			} else
+				node = rb_next(node);
+			cond_resched();
+		}
+	}
+	list_for_each_safe(this, next, &migrate_nodes) {
+		stable_node = list_entry(this, struct stable_node, list);
 		if (stable_node->kpfn >= start_pfn &&
 		    stable_node->kpfn < end_pfn)
-			return stable_node;
+			remove_node_from_stable_tree(stable_node);
+		cond_resched();
 	}
-	return NULL;
 }
 
 static int ksm_memory_callback(struct notifier_block *self,
 			       unsigned long action, void *arg)
 {
 	struct memory_notify *mn = arg;
-	struct stable_node *stable_node;
 
 	switch (action) {
 	case MEM_GOING_OFFLINE:
 		/*
-		 * Keep it very simple for now: just lock out ksmd and
-		 * MADV_UNMERGEABLE while any memory is going offline.
-		 * mutex_lock_nested() is necessary because lockdep was alarmed
-		 * that here we take ksm_thread_mutex inside notifier chain
-		 * mutex, and later take notifier chain mutex inside
-		 * ksm_thread_mutex to unlock it.   But that's safe because both
-		 * are inside mem_hotplug_mutex.
+		 * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items()
+		 * and remove_all_stable_nodes() while memory is going offline:
+		 * it is unsafe for them to touch the stable tree at this time.
+		 * But unmerge_ksm_pages(), rmap lookups and other entry points
+		 * which do not need the ksm_thread_mutex are all safe.
 		 */
-		mutex_lock_nested(&ksm_thread_mutex, SINGLE_DEPTH_NESTING);
+		mutex_lock(&ksm_thread_mutex);
+		ksm_run |= KSM_RUN_OFFLINE;
+		mutex_unlock(&ksm_thread_mutex);
 		break;
 
 	case MEM_OFFLINE:
 		/*
 		 * Most of the work is done by page migration; but there might
 		 * be a few stable_nodes left over, still pointing to struct
-		 * pages which have been offlined: prune those from the tree.
+		 * pages which have been offlined: prune those from the tree,
+		 * otherwise get_ksm_page() might later try to access a
+		 * non-existent struct page.
 		 */
-		while ((stable_node = ksm_check_stable_tree(mn->start_pfn,
-					mn->start_pfn + mn->nr_pages)) != NULL)
-			remove_node_from_stable_tree(stable_node);
+		ksm_check_stable_tree(mn->start_pfn,
+				      mn->start_pfn + mn->nr_pages);
 		/* fallthrough */
 
 	case MEM_CANCEL_OFFLINE:
+		mutex_lock(&ksm_thread_mutex);
+		ksm_run &= ~KSM_RUN_OFFLINE;
 		mutex_unlock(&ksm_thread_mutex);
+
+		smp_mb();	/* wake_up_bit advises this */
+		wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE));
 		break;
 	}
 	return NOTIFY_OK;
 }
+#else
+static void wait_while_offlining(void)
+{
+}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 #ifdef CONFIG_SYSFS
@@ -1893,7 +2235,7 @@ KSM_ATTR(pages_to_scan);
 static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr,
 			char *buf)
 {
-	return sprintf(buf, "%u\n", ksm_run);
+	return sprintf(buf, "%lu\n", ksm_run);
 }
 
 static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
@@ -1916,6 +2258,7 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
 	 */
 
 	mutex_lock(&ksm_thread_mutex);
+	wait_while_offlining();
 	if (ksm_run != flags) {
 		ksm_run = flags;
 		if (flags & KSM_RUN_UNMERGE) {
@@ -1937,6 +2280,64 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
 }
 KSM_ATTR(run);
 
+#ifdef CONFIG_NUMA
+static ssize_t merge_across_nodes_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", ksm_merge_across_nodes);
+}
+
+static ssize_t merge_across_nodes_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t count)
+{
+	int err;
+	unsigned long knob;
+
+	err = kstrtoul(buf, 10, &knob);
+	if (err)
+		return err;
+	if (knob > 1)
+		return -EINVAL;
+
+	mutex_lock(&ksm_thread_mutex);
+	wait_while_offlining();
+	if (ksm_merge_across_nodes != knob) {
+		if (ksm_pages_shared || remove_all_stable_nodes())
+			err = -EBUSY;
+		else if (root_stable_tree == one_stable_tree) {
+			struct rb_root *buf;
+			/*
+			 * This is the first time that we switch away from the
+			 * default of merging across nodes: must now allocate
+			 * a buffer to hold as many roots as may be needed.
+			 * Allocate stable and unstable together:
+			 * MAXSMP NODES_SHIFT 10 will use 16kB.
+			 */
+			buf = kcalloc(nr_node_ids + nr_node_ids,
+				sizeof(*buf), GFP_KERNEL | __GFP_ZERO);
+			/* Let us assume that RB_ROOT is NULL is zero */
+			if (!buf)
+				err = -ENOMEM;
+			else {
+				root_stable_tree = buf;
+				root_unstable_tree = buf + nr_node_ids;
+				/* Stable tree is empty but not the unstable */
+				root_unstable_tree[0] = one_unstable_tree[0];
+			}
+		}
+		if (!err) {
+			ksm_merge_across_nodes = knob;
+			ksm_nr_node_ids = knob ? 1 : nr_node_ids;
+		}
+	}
+	mutex_unlock(&ksm_thread_mutex);
+
+	return err ? err : count;
+}
+KSM_ATTR(merge_across_nodes);
+#endif
+
 static ssize_t pages_shared_show(struct kobject *kobj,
 				 struct kobj_attribute *attr, char *buf)
 {
@@ -1991,6 +2392,9 @@ static struct attribute *ksm_attrs[] = {
 	&pages_unshared_attr.attr,
 	&pages_volatile_attr.attr,
 	&full_scans_attr.attr,
+#ifdef CONFIG_NUMA
+	&merge_across_nodes_attr.attr,
+#endif
 	NULL,
 };
 
@@ -2029,10 +2433,7 @@ static int __init ksm_init(void)
 #endif /* CONFIG_SYSFS */
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-	/*
-	 * Choose a high priority since the callback takes ksm_thread_mutex:
-	 * later callbacks could only be taking locks which nest within that.
-	 */
+	/* There is no significance to this priority 100 */
 	hotplug_memory_notifier(ksm_memory_callback, 100);
 #endif
 	return 0;
diff --git a/mm/madvise.c b/mm/madvise.c
index 03dfa5c7adb..c58c94b56c3 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -16,6 +16,9 @@
 #include <linux/ksm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
+#include <linux/blkdev.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -131,6 +134,84 @@ out:
 	return error;
 }
 
+#ifdef CONFIG_SWAP
+static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
+	unsigned long end, struct mm_walk *walk)
+{
+	pte_t *orig_pte;
+	struct vm_area_struct *vma = walk->private;
+	unsigned long index;
+
+	if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+		return 0;
+
+	for (index = start; index != end; index += PAGE_SIZE) {
+		pte_t pte;
+		swp_entry_t entry;
+		struct page *page;
+		spinlock_t *ptl;
+
+		orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
+		pte = *(orig_pte + ((index - start) / PAGE_SIZE));
+		pte_unmap_unlock(orig_pte, ptl);
+
+		if (pte_present(pte) || pte_none(pte) || pte_file(pte))
+			continue;
+		entry = pte_to_swp_entry(pte);
+		if (unlikely(non_swap_entry(entry)))
+			continue;
+
+		page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
+								vma, index);
+		if (page)
+			page_cache_release(page);
+	}
+
+	return 0;
+}
+
+static void force_swapin_readahead(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	struct mm_walk walk = {
+		.mm = vma->vm_mm,
+		.pmd_entry = swapin_walk_pmd_entry,
+		.private = vma,
+	};
+
+	walk_page_range(start, end, &walk);
+
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+}
+
+static void force_shm_swapin_readahead(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end,
+		struct address_space *mapping)
+{
+	pgoff_t index;
+	struct page *page;
+	swp_entry_t swap;
+
+	for (; start < end; start += PAGE_SIZE) {
+		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+
+		page = find_get_page(mapping, index);
+		if (!radix_tree_exceptional_entry(page)) {
+			if (page)
+				page_cache_release(page);
+			continue;
+		}
+		swap = radix_to_swp_entry(page);
+		page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
+								NULL, 0);
+		if (page)
+			page_cache_release(page);
+	}
+
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+}
+#endif		/* CONFIG_SWAP */
+
 /*
  * Schedule all required I/O operations.  Do not wait for completion.
  */
@@ -140,6 +221,18 @@ static long madvise_willneed(struct vm_area_struct * vma,
 {
 	struct file *file = vma->vm_file;
 
+#ifdef CONFIG_SWAP
+	if (!file || mapping_cap_swap_backed(file->f_mapping)) {
+		*prev = vma;
+		if (!file)
+			force_swapin_readahead(vma, start, end);
+		else
+			force_shm_swapin_readahead(vma, start, end,
+						file->f_mapping);
+		return 0;
+	}
+#endif
+
 	if (!file)
 		return -EBADF;
 
@@ -371,6 +464,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	int error = -EINVAL;
 	int write;
 	size_t len;
+	struct blk_plug plug;
 
 #ifdef CONFIG_MEMORY_FAILURE
 	if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
@@ -410,18 +504,19 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	if (vma && start > vma->vm_start)
 		prev = vma;
 
+	blk_start_plug(&plug);
 	for (;;) {
 		/* Still start < end. */
 		error = -ENOMEM;
 		if (!vma)
-			goto out;
+			goto out_plug;
 
 		/* Here start < (end|vma->vm_end). */
 		if (start < vma->vm_start) {
 			unmapped_error = -ENOMEM;
 			start = vma->vm_start;
 			if (start >= end)
-				goto out;
+				goto out_plug;
 		}
 
 		/* Here vma->vm_start <= start < (end|vma->vm_end) */
@@ -432,18 +527,20 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
 		error = madvise_vma(vma, &prev, start, tmp, behavior);
 		if (error)
-			goto out;
+			goto out_plug;
 		start = tmp;
 		if (prev && start < prev->vm_end)
 			start = prev->vm_end;
 		error = unmapped_error;
 		if (start >= end)
-			goto out;
+			goto out_plug;
 		if (prev)
 			vma = prev->vm_next;
 		else	/* madvise_remove dropped mmap_sem */
 			vma = find_vma(current->mm, start);
 	}
+out_plug:
+	blk_finish_plug(&plug);
 out:
 	if (write)
 		up_write(&current->mm->mmap_sem);
diff --git a/mm/memblock.c b/mm/memblock.c
index b8d9147e5c0..1bcd9b97056 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -92,9 +92,58 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
  *
  * Find @size free area aligned to @align in the specified range and node.
  *
+ * If we have CONFIG_HAVE_MEMBLOCK_NODE_MAP defined, we need to check if the
+ * memory we found if not in hotpluggable ranges.
+ *
  * RETURNS:
  * Found address on success, %0 on failure.
  */
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+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 this_start, this_end, cand;
+	u64 i;
+	int curr = movablemem_map.nr_map - 1;
+
+	/* pump up @end */
+	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
+		end = memblock.current_limit;
+
+	/* avoid allocating the first page */
+	start = max_t(phys_addr_t, start, PAGE_SIZE);
+	end = max(start, end);
+
+	for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) {
+		this_start = clamp(this_start, start, end);
+		this_end = clamp(this_end, start, end);
+
+restart:
+		if (this_end <= this_start || this_end < size)
+			continue;
+
+		for (; curr >= 0; curr--) {
+			if ((movablemem_map.map[curr].start_pfn << PAGE_SHIFT)
+			    < this_end)
+				break;
+		}
+
+		cand = round_down(this_end - size, align);
+		if (curr >= 0 &&
+		    cand < movablemem_map.map[curr].end_pfn << PAGE_SHIFT) {
+			this_end = movablemem_map.map[curr].start_pfn
+				   << PAGE_SHIFT;
+			goto restart;
+		}
+
+		if (cand >= this_start)
+			return cand;
+	}
+
+	return 0;
+}
+#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 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)
@@ -123,6 +172,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 	}
 	return 0;
 }
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 /**
  * memblock_find_in_range - find free area in given range
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index fbb60b103e6..53b8201b31e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -120,6 +120,14 @@ static const char * const mem_cgroup_events_names[] = {
 	"pgmajfault",
 };
 
+static const char * const mem_cgroup_lru_names[] = {
+	"inactive_anon",
+	"active_anon",
+	"inactive_file",
+	"active_file",
+	"unevictable",
+};
+
 /*
  * Per memcg event counter is incremented at every pagein/pageout. With THP,
  * it will be incremated by the number of pages. This counter is used for
@@ -172,7 +180,7 @@ struct mem_cgroup_per_node {
 };
 
 struct mem_cgroup_lru_info {
-	struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
+	struct mem_cgroup_per_node *nodeinfo[0];
 };
 
 /*
@@ -276,17 +284,6 @@ struct mem_cgroup {
 	 */
 	struct res_counter kmem;
 	/*
-	 * Per cgroup active and inactive list, similar to the
-	 * per zone LRU lists.
-	 */
-	struct mem_cgroup_lru_info info;
-	int last_scanned_node;
-#if MAX_NUMNODES > 1
-	nodemask_t	scan_nodes;
-	atomic_t	numainfo_events;
-	atomic_t	numainfo_updating;
-#endif
-	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
 	bool use_hierarchy;
@@ -349,8 +346,29 @@ struct mem_cgroup {
         /* Index in the kmem_cache->memcg_params->memcg_caches array */
 	int kmemcg_id;
 #endif
+
+	int last_scanned_node;
+#if MAX_NUMNODES > 1
+	nodemask_t	scan_nodes;
+	atomic_t	numainfo_events;
+	atomic_t	numainfo_updating;
+#endif
+	/*
+	 * Per cgroup active and inactive list, similar to the
+	 * per zone LRU lists.
+	 *
+	 * WARNING: This has to be the last element of the struct. Don't
+	 * add new fields after this point.
+	 */
+	struct mem_cgroup_lru_info info;
 };
 
+static size_t memcg_size(void)
+{
+	return sizeof(struct mem_cgroup) +
+		nr_node_ids * sizeof(struct mem_cgroup_per_node);
+}
+
 /* internal only representation about the status of kmem accounting. */
 enum {
 	KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
@@ -398,8 +416,8 @@ static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
 
 /* Stuffs for move charges at task migration. */
 /*
- * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a
- * left-shifted bitmap of these types.
+ * Types of charges to be moved. "move_charge_at_immitgrate" and
+ * "immigrate_flags" are treated as a left-shifted bitmap of these types.
  */
 enum move_type {
 	MOVE_CHARGE_TYPE_ANON,	/* private anonymous page and swap of it */
@@ -412,6 +430,7 @@ static struct move_charge_struct {
 	spinlock_t	  lock; /* for from, to */
 	struct mem_cgroup *from;
 	struct mem_cgroup *to;
+	unsigned long immigrate_flags;
 	unsigned long precharge;
 	unsigned long moved_charge;
 	unsigned long moved_swap;
@@ -424,14 +443,12 @@ static struct move_charge_struct {
 
 static bool move_anon(void)
 {
-	return test_bit(MOVE_CHARGE_TYPE_ANON,
-					&mc.to->move_charge_at_immigrate);
+	return test_bit(MOVE_CHARGE_TYPE_ANON, &mc.immigrate_flags);
 }
 
 static bool move_file(void)
 {
-	return test_bit(MOVE_CHARGE_TYPE_FILE,
-					&mc.to->move_charge_at_immigrate);
+	return test_bit(MOVE_CHARGE_TYPE_FILE, &mc.immigrate_flags);
 }
 
 /*
@@ -471,6 +488,13 @@ enum res_type {
 #define MEM_CGROUP_RECLAIM_SHRINK_BIT	0x1
 #define MEM_CGROUP_RECLAIM_SHRINK	(1 << MEM_CGROUP_RECLAIM_SHRINK_BIT)
 
+/*
+ * The memcg_create_mutex will be held whenever a new cgroup is created.
+ * As a consequence, any change that needs to protect against new child cgroups
+ * appearing has to hold it as well.
+ */
+static DEFINE_MUTEX(memcg_create_mutex);
+
 static void mem_cgroup_get(struct mem_cgroup *memcg);
 static void mem_cgroup_put(struct mem_cgroup *memcg);
 
@@ -627,6 +651,7 @@ static void drain_all_stock_async(struct mem_cgroup *memcg);
 static struct mem_cgroup_per_zone *
 mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid)
 {
+	VM_BUG_ON((unsigned)nid >= nr_node_ids);
 	return &memcg->info.nodeinfo[nid]->zoneinfo[zid];
 }
 
@@ -1371,17 +1396,6 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return inactive * inactive_ratio < active;
 }
 
-int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec)
-{
-	unsigned long active;
-	unsigned long inactive;
-
-	inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_FILE);
-	active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_FILE);
-
-	return (active > inactive);
-}
-
 #define mem_cgroup_from_res_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
@@ -1524,8 +1538,9 @@ static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
 	spin_unlock_irqrestore(&memcg->move_lock, *flags);
 }
 
+#define K(x) ((x) << (PAGE_SHIFT-10))
 /**
- * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode.
+ * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller.
  * @memcg: The memory cgroup that went over limit
  * @p: Task that is going to be killed
  *
@@ -1543,8 +1558,10 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	 */
 	static char memcg_name[PATH_MAX];
 	int ret;
+	struct mem_cgroup *iter;
+	unsigned int i;
 
-	if (!memcg || !p)
+	if (!p)
 		return;
 
 	rcu_read_lock();
@@ -1563,7 +1580,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	}
 	rcu_read_unlock();
 
-	printk(KERN_INFO "Task in %s killed", memcg_name);
+	pr_info("Task in %s killed", memcg_name);
 
 	rcu_read_lock();
 	ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
@@ -1576,22 +1593,45 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	/*
 	 * Continues from above, so we don't need an KERN_ level
 	 */
-	printk(KERN_CONT " as a result of limit of %s\n", memcg_name);
+	pr_cont(" as a result of limit of %s\n", memcg_name);
 done:
 
-	printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n",
+	pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n",
 		res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
 		res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
 		res_counter_read_u64(&memcg->res, RES_FAILCNT));
-	printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, "
-		"failcnt %llu\n",
+	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %llu\n",
 		res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
 		res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
 		res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
-	printk(KERN_INFO "kmem: usage %llukB, limit %llukB, failcnt %llu\n",
+	pr_info("kmem: usage %llukB, limit %llukB, failcnt %llu\n",
 		res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10,
 		res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10,
 		res_counter_read_u64(&memcg->kmem, RES_FAILCNT));
+
+	for_each_mem_cgroup_tree(iter, memcg) {
+		pr_info("Memory cgroup stats");
+
+		rcu_read_lock();
+		ret = cgroup_path(iter->css.cgroup, memcg_name, PATH_MAX);
+		if (!ret)
+			pr_cont(" for %s", memcg_name);
+		rcu_read_unlock();
+		pr_cont(":");
+
+		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
+			if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
+				continue;
+			pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+				K(mem_cgroup_read_stat(iter, i)));
+		}
+
+		for (i = 0; i < NR_LRU_LISTS; i++)
+			pr_cont(" %s:%luKB", mem_cgroup_lru_names[i],
+				K(mem_cgroup_nr_lru_pages(iter, BIT(i))));
+
+		pr_cont("\n");
+	}
 }
 
 /*
@@ -2256,6 +2296,17 @@ static void drain_local_stock(struct work_struct *dummy)
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 }
 
+static void __init memcg_stock_init(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct memcg_stock_pcp *stock =
+					&per_cpu(memcg_stock, cpu);
+		INIT_WORK(&stock->work, drain_local_stock);
+	}
+}
+
 /*
  * Cache charges(val) which is from res_counter, to local per_cpu area.
  * This will be consumed by consume_stock() function, later.
@@ -4391,8 +4442,8 @@ void mem_cgroup_print_bad_page(struct page *page)
 
 	pc = lookup_page_cgroup_used(page);
 	if (pc) {
-		printk(KERN_ALERT "pc:%p pc->flags:%lx pc->mem_cgroup:%p\n",
-		       pc, pc->flags, pc->mem_cgroup);
+		pr_alert("pc:%p pc->flags:%lx pc->mem_cgroup:%p\n",
+			 pc, pc->flags, pc->mem_cgroup);
 	}
 }
 #endif
@@ -4719,6 +4770,33 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 }
 
 /*
+ * This mainly exists for tests during the setting of set of use_hierarchy.
+ * Since this is the very setting we are changing, the current hierarchy value
+ * is meaningless
+ */
+static inline bool __memcg_has_children(struct mem_cgroup *memcg)
+{
+	struct cgroup *pos;
+
+	/* bounce at first found */
+	cgroup_for_each_child(pos, memcg->css.cgroup)
+		return true;
+	return false;
+}
+
+/*
+ * Must be called with memcg_create_mutex held, unless the cgroup is guaranteed
+ * to be already dead (as in mem_cgroup_force_empty, for instance).  This is
+ * from mem_cgroup_count_children(), in the sense that we don't really care how
+ * many children we have; we only need to know if we have any.  It also counts
+ * any memcg without hierarchy as infertile.
+ */
+static inline bool memcg_has_children(struct mem_cgroup *memcg)
+{
+	return memcg->use_hierarchy && __memcg_has_children(memcg);
+}
+
+/*
  * Reclaims as many pages from the given memcg as possible and moves
  * the rest to the parent.
  *
@@ -4788,7 +4866,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 	if (parent)
 		parent_memcg = mem_cgroup_from_cont(parent);
 
-	cgroup_lock();
+	mutex_lock(&memcg_create_mutex);
 
 	if (memcg->use_hierarchy == val)
 		goto out;
@@ -4803,7 +4881,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 	 */
 	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
 				(val == 1 || val == 0)) {
-		if (list_empty(&cont->children))
+		if (!__memcg_has_children(memcg))
 			memcg->use_hierarchy = val;
 		else
 			retval = -EBUSY;
@@ -4811,7 +4889,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 		retval = -EINVAL;
 
 out:
-	cgroup_unlock();
+	mutex_unlock(&memcg_create_mutex);
 
 	return retval;
 }
@@ -4896,8 +4974,6 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
 {
 	int ret = -EINVAL;
 #ifdef CONFIG_MEMCG_KMEM
-	bool must_inc_static_branch = false;
-
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 	/*
 	 * For simplicity, we won't allow this to be disabled.  It also can't
@@ -4910,18 +4986,11 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
 	 *
 	 * After it first became limited, changes in the value of the limit are
 	 * of course permitted.
-	 *
-	 * Taking the cgroup_lock is really offensive, but it is so far the only
-	 * way to guarantee that no children will appear. There are plenty of
-	 * other offenders, and they should all go away. Fine grained locking
-	 * is probably the way to go here. When we are fully hierarchical, we
-	 * can also get rid of the use_hierarchy check.
 	 */
-	cgroup_lock();
+	mutex_lock(&memcg_create_mutex);
 	mutex_lock(&set_limit_mutex);
 	if (!memcg->kmem_account_flags && val != RESOURCE_MAX) {
-		if (cgroup_task_count(cont) || (memcg->use_hierarchy &&
-						!list_empty(&cont->children))) {
+		if (cgroup_task_count(cont) || memcg_has_children(memcg)) {
 			ret = -EBUSY;
 			goto out;
 		}
@@ -4933,7 +5002,13 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
 			res_counter_set_limit(&memcg->kmem, RESOURCE_MAX);
 			goto out;
 		}
-		must_inc_static_branch = true;
+		static_key_slow_inc(&memcg_kmem_enabled_key);
+		/*
+		 * setting the active bit after the inc will guarantee no one
+		 * starts accounting before all call sites are patched
+		 */
+		memcg_kmem_set_active(memcg);
+
 		/*
 		 * kmem charges can outlive the cgroup. In the case of slab
 		 * pages, for instance, a page contain objects from various
@@ -4945,32 +5020,12 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
 		ret = res_counter_set_limit(&memcg->kmem, val);
 out:
 	mutex_unlock(&set_limit_mutex);
-	cgroup_unlock();
-
-	/*
-	 * We are by now familiar with the fact that we can't inc the static
-	 * branch inside cgroup_lock. See disarm functions for details. A
-	 * worker here is overkill, but also wrong: After the limit is set, we
-	 * must start accounting right away. Since this operation can't fail,
-	 * we can safely defer it to here - no rollback will be needed.
-	 *
-	 * The boolean used to control this is also safe, because
-	 * KMEM_ACCOUNTED_ACTIVATED guarantees that only one process will be
-	 * able to set it to true;
-	 */
-	if (must_inc_static_branch) {
-		static_key_slow_inc(&memcg_kmem_enabled_key);
-		/*
-		 * setting the active bit after the inc will guarantee no one
-		 * starts accounting before all call sites are patched
-		 */
-		memcg_kmem_set_active(memcg);
-	}
-
+	mutex_unlock(&memcg_create_mutex);
 #endif
 	return ret;
 }
 
+#ifdef CONFIG_MEMCG_KMEM
 static int memcg_propagate_kmem(struct mem_cgroup *memcg)
 {
 	int ret = 0;
@@ -4979,7 +5034,6 @@ static int memcg_propagate_kmem(struct mem_cgroup *memcg)
 		goto out;
 
 	memcg->kmem_account_flags = parent->kmem_account_flags;
-#ifdef CONFIG_MEMCG_KMEM
 	/*
 	 * When that happen, we need to disable the static branch only on those
 	 * memcgs that enabled it. To achieve this, we would be forced to
@@ -5005,10 +5059,10 @@ static int memcg_propagate_kmem(struct mem_cgroup *memcg)
 	mutex_lock(&set_limit_mutex);
 	ret = memcg_update_cache_sizes(memcg);
 	mutex_unlock(&set_limit_mutex);
-#endif
 out:
 	return ret;
 }
+#endif /* CONFIG_MEMCG_KMEM */
 
 /*
  * The user of this function is...
@@ -5148,15 +5202,14 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
 
 	if (val >= (1 << NR_MOVE_TYPE))
 		return -EINVAL;
+
 	/*
-	 * We check this value several times in both in can_attach() and
-	 * attach(), so we need cgroup lock to prevent this value from being
-	 * inconsistent.
+	 * No kind of locking is needed in here, because ->can_attach() will
+	 * check this value once in the beginning of the process, and then carry
+	 * on with stale data. This means that changes to this value will only
+	 * affect task migrations starting after the change.
 	 */
-	cgroup_lock();
 	memcg->move_charge_at_immigrate = val;
-	cgroup_unlock();
-
 	return 0;
 }
 #else
@@ -5214,14 +5267,6 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 }
 #endif /* CONFIG_NUMA */
 
-static const char * const mem_cgroup_lru_names[] = {
-	"inactive_anon",
-	"active_anon",
-	"inactive_file",
-	"active_file",
-	"unevictable",
-};
-
 static inline void mem_cgroup_lru_names_not_uptodate(void)
 {
 	BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
@@ -5335,18 +5380,17 @@ static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft,
 
 	parent = mem_cgroup_from_cont(cgrp->parent);
 
-	cgroup_lock();
+	mutex_lock(&memcg_create_mutex);
 
 	/* If under hierarchy, only empty-root can set this value */
-	if ((parent->use_hierarchy) ||
-	    (memcg->use_hierarchy && !list_empty(&cgrp->children))) {
-		cgroup_unlock();
+	if ((parent->use_hierarchy) || memcg_has_children(memcg)) {
+		mutex_unlock(&memcg_create_mutex);
 		return -EINVAL;
 	}
 
 	memcg->swappiness = val;
 
-	cgroup_unlock();
+	mutex_unlock(&memcg_create_mutex);
 
 	return 0;
 }
@@ -5672,17 +5716,16 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
 
 	parent = mem_cgroup_from_cont(cgrp->parent);
 
-	cgroup_lock();
+	mutex_lock(&memcg_create_mutex);
 	/* oom-kill-disable is a flag for subhierarchy. */
-	if ((parent->use_hierarchy) ||
-	    (memcg->use_hierarchy && !list_empty(&cgrp->children))) {
-		cgroup_unlock();
+	if ((parent->use_hierarchy) || memcg_has_children(memcg)) {
+		mutex_unlock(&memcg_create_mutex);
 		return -EINVAL;
 	}
 	memcg->oom_kill_disable = val;
 	if (!val)
 		memcg_oom_recover(memcg);
-	cgroup_unlock();
+	mutex_unlock(&memcg_create_mutex);
 	return 0;
 }
 
@@ -5797,33 +5840,6 @@ static struct cftype mem_cgroup_files[] = {
 		.read_seq_string = memcg_numa_stat_show,
 	},
 #endif
-#ifdef CONFIG_MEMCG_SWAP
-	{
-		.name = "memsw.usage_in_bytes",
-		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
-		.read = mem_cgroup_read,
-		.register_event = mem_cgroup_usage_register_event,
-		.unregister_event = mem_cgroup_usage_unregister_event,
-	},
-	{
-		.name = "memsw.max_usage_in_bytes",
-		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
-		.trigger = mem_cgroup_reset,
-		.read = mem_cgroup_read,
-	},
-	{
-		.name = "memsw.limit_in_bytes",
-		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
-		.write_string = mem_cgroup_write,
-		.read = mem_cgroup_read,
-	},
-	{
-		.name = "memsw.failcnt",
-		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
-		.trigger = mem_cgroup_reset,
-		.read = mem_cgroup_read,
-	},
-#endif
 #ifdef CONFIG_MEMCG_KMEM
 	{
 		.name = "kmem.limit_in_bytes",
@@ -5858,6 +5874,36 @@ static struct cftype mem_cgroup_files[] = {
 	{ },	/* terminate */
 };
 
+#ifdef CONFIG_MEMCG_SWAP
+static struct cftype memsw_cgroup_files[] = {
+	{
+		.name = "memsw.usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
+		.read = mem_cgroup_read,
+		.register_event = mem_cgroup_usage_register_event,
+		.unregister_event = mem_cgroup_usage_unregister_event,
+	},
+	{
+		.name = "memsw.max_usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
+		.trigger = mem_cgroup_reset,
+		.read = mem_cgroup_read,
+	},
+	{
+		.name = "memsw.limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
+		.write_string = mem_cgroup_write,
+		.read = mem_cgroup_read,
+	},
+	{
+		.name = "memsw.failcnt",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
+		.trigger = mem_cgroup_reset,
+		.read = mem_cgroup_read,
+	},
+	{ },	/* terminate */
+};
+#endif
 static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
@@ -5896,9 +5942,9 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *memcg;
-	int size = sizeof(struct mem_cgroup);
+	size_t size = memcg_size();
 
-	/* Can be very big if MAX_NUMNODES is very big */
+	/* Can be very big if nr_node_ids is very big */
 	if (size < PAGE_SIZE)
 		memcg = kzalloc(size, GFP_KERNEL);
 	else
@@ -5935,7 +5981,7 @@ out_free:
 static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
-	int size = sizeof(struct mem_cgroup);
+	size_t size = memcg_size();
 
 	mem_cgroup_remove_from_trees(memcg);
 	free_css_id(&mem_cgroup_subsys, &memcg->css);
@@ -6017,19 +6063,7 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
-#ifdef CONFIG_MEMCG_SWAP
-static void __init enable_swap_cgroup(void)
-{
-	if (!mem_cgroup_disabled() && really_do_swap_account)
-		do_swap_account = 1;
-}
-#else
-static void __init enable_swap_cgroup(void)
-{
-}
-#endif
-
-static int mem_cgroup_soft_limit_tree_init(void)
+static void __init mem_cgroup_soft_limit_tree_init(void)
 {
 	struct mem_cgroup_tree_per_node *rtpn;
 	struct mem_cgroup_tree_per_zone *rtpz;
@@ -6040,8 +6074,7 @@ static int mem_cgroup_soft_limit_tree_init(void)
 		if (!node_state(node, N_NORMAL_MEMORY))
 			tmp = -1;
 		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
-		if (!rtpn)
-			goto err_cleanup;
+		BUG_ON(!rtpn);
 
 		soft_limit_tree.rb_tree_per_node[node] = rtpn;
 
@@ -6051,23 +6084,12 @@ static int mem_cgroup_soft_limit_tree_init(void)
 			spin_lock_init(&rtpz->lock);
 		}
 	}
-	return 0;
-
-err_cleanup:
-	for_each_node(node) {
-		if (!soft_limit_tree.rb_tree_per_node[node])
-			break;
-		kfree(soft_limit_tree.rb_tree_per_node[node]);
-		soft_limit_tree.rb_tree_per_node[node] = NULL;
-	}
-	return 1;
-
 }
 
 static struct cgroup_subsys_state * __ref
 mem_cgroup_css_alloc(struct cgroup *cont)
 {
-	struct mem_cgroup *memcg, *parent;
+	struct mem_cgroup *memcg;
 	long error = -ENOMEM;
 	int node;
 
@@ -6081,24 +6103,44 @@ mem_cgroup_css_alloc(struct cgroup *cont)
 
 	/* root ? */
 	if (cont->parent == NULL) {
-		int cpu;
-		enable_swap_cgroup();
-		parent = NULL;
-		if (mem_cgroup_soft_limit_tree_init())
-			goto free_out;
 		root_mem_cgroup = memcg;
-		for_each_possible_cpu(cpu) {
-			struct memcg_stock_pcp *stock =
-						&per_cpu(memcg_stock, cpu);
-			INIT_WORK(&stock->work, drain_local_stock);
-		}
-	} else {
-		parent = mem_cgroup_from_cont(cont->parent);
-		memcg->use_hierarchy = parent->use_hierarchy;
-		memcg->oom_kill_disable = parent->oom_kill_disable;
+		res_counter_init(&memcg->res, NULL);
+		res_counter_init(&memcg->memsw, NULL);
+		res_counter_init(&memcg->kmem, NULL);
 	}
 
-	if (parent && parent->use_hierarchy) {
+	memcg->last_scanned_node = MAX_NUMNODES;
+	INIT_LIST_HEAD(&memcg->oom_notify);
+	atomic_set(&memcg->refcnt, 1);
+	memcg->move_charge_at_immigrate = 0;
+	mutex_init(&memcg->thresholds_lock);
+	spin_lock_init(&memcg->move_lock);
+
+	return &memcg->css;
+
+free_out:
+	__mem_cgroup_free(memcg);
+	return ERR_PTR(error);
+}
+
+static int
+mem_cgroup_css_online(struct cgroup *cont)
+{
+	struct mem_cgroup *memcg, *parent;
+	int error = 0;
+
+	if (!cont->parent)
+		return 0;
+
+	mutex_lock(&memcg_create_mutex);
+	memcg = mem_cgroup_from_cont(cont);
+	parent = mem_cgroup_from_cont(cont->parent);
+
+	memcg->use_hierarchy = parent->use_hierarchy;
+	memcg->oom_kill_disable = parent->oom_kill_disable;
+	memcg->swappiness = mem_cgroup_swappiness(parent);
+
+	if (parent->use_hierarchy) {
 		res_counter_init(&memcg->res, &parent->res);
 		res_counter_init(&memcg->memsw, &parent->memsw);
 		res_counter_init(&memcg->kmem, &parent->kmem);
@@ -6119,20 +6161,12 @@ mem_cgroup_css_alloc(struct cgroup *cont)
 		 * much sense so let cgroup subsystem know about this
 		 * unfortunate state in our controller.
 		 */
-		if (parent && parent != root_mem_cgroup)
+		if (parent != root_mem_cgroup)
 			mem_cgroup_subsys.broken_hierarchy = true;
 	}
-	memcg->last_scanned_node = MAX_NUMNODES;
-	INIT_LIST_HEAD(&memcg->oom_notify);
-
-	if (parent)
-		memcg->swappiness = mem_cgroup_swappiness(parent);
-	atomic_set(&memcg->refcnt, 1);
-	memcg->move_charge_at_immigrate = 0;
-	mutex_init(&memcg->thresholds_lock);
-	spin_lock_init(&memcg->move_lock);
 
 	error = memcg_init_kmem(memcg, &mem_cgroup_subsys);
+	mutex_unlock(&memcg_create_mutex);
 	if (error) {
 		/*
 		 * We call put now because our (and parent's) refcnts
@@ -6140,12 +6174,10 @@ mem_cgroup_css_alloc(struct cgroup *cont)
 		 * call __mem_cgroup_free, so return directly
 		 */
 		mem_cgroup_put(memcg);
-		return ERR_PTR(error);
+		if (parent->use_hierarchy)
+			mem_cgroup_put(parent);
 	}
-	return &memcg->css;
-free_out:
-	__mem_cgroup_free(memcg);
-	return ERR_PTR(error);
+	return error;
 }
 
 static void mem_cgroup_css_offline(struct cgroup *cont)
@@ -6281,7 +6313,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
 	 * Because lookup_swap_cache() updates some statistics counter,
 	 * we call find_get_page() with swapper_space directly.
 	 */
-	page = find_get_page(&swapper_space, ent.val);
+	page = find_get_page(swap_address_space(ent), ent.val);
 	if (do_swap_account)
 		entry->val = ent.val;
 
@@ -6322,7 +6354,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 		swp_entry_t swap = radix_to_swp_entry(page);
 		if (do_swap_account)
 			*entry = swap;
-		page = find_get_page(&swapper_space, swap.val);
+		page = find_get_page(swap_address_space(swap), swap.val);
 	}
 #endif
 	return page;
@@ -6532,8 +6564,15 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup,
 	struct task_struct *p = cgroup_taskset_first(tset);
 	int ret = 0;
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);
+	unsigned long move_charge_at_immigrate;
 
-	if (memcg->move_charge_at_immigrate) {
+	/*
+	 * We are now commited to this value whatever it is. Changes in this
+	 * tunable will only affect upcoming migrations, not the current one.
+	 * So we need to save it, and keep it going.
+	 */
+	move_charge_at_immigrate  = memcg->move_charge_at_immigrate;
+	if (move_charge_at_immigrate) {
 		struct mm_struct *mm;
 		struct mem_cgroup *from = mem_cgroup_from_task(p);
 
@@ -6553,6 +6592,7 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup,
 			spin_lock(&mc.lock);
 			mc.from = from;
 			mc.to = memcg;
+			mc.immigrate_flags = move_charge_at_immigrate;
 			spin_unlock(&mc.lock);
 			/* We set mc.moving_task later */
 
@@ -6747,6 +6787,7 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.name = "memory",
 	.subsys_id = mem_cgroup_subsys_id,
 	.css_alloc = mem_cgroup_css_alloc,
+	.css_online = mem_cgroup_css_online,
 	.css_offline = mem_cgroup_css_offline,
 	.css_free = mem_cgroup_css_free,
 	.can_attach = mem_cgroup_can_attach,
@@ -6757,19 +6798,6 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.use_id = 1,
 };
 
-/*
- * The rest of init is performed during ->css_alloc() for root css which
- * happens before initcalls.  hotcpu_notifier() can't be done together as
- * it would introduce circular locking by adding cgroup_lock -> cpu hotplug
- * dependency.  Do it from a subsys_initcall().
- */
-static int __init mem_cgroup_init(void)
-{
-	hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
-	return 0;
-}
-subsys_initcall(mem_cgroup_init);
-
 #ifdef CONFIG_MEMCG_SWAP
 static int __init enable_swap_account(char *s)
 {
@@ -6782,4 +6810,39 @@ static int __init enable_swap_account(char *s)
 }
 __setup("swapaccount=", enable_swap_account);
 
+static void __init memsw_file_init(void)
+{
+	WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, memsw_cgroup_files));
+}
+
+static void __init enable_swap_cgroup(void)
+{
+	if (!mem_cgroup_disabled() && really_do_swap_account) {
+		do_swap_account = 1;
+		memsw_file_init();
+	}
+}
+
+#else
+static void __init enable_swap_cgroup(void)
+{
+}
 #endif
+
+/*
+ * subsys_initcall() for memory controller.
+ *
+ * Some parts like hotcpu_notifier() have to be initialized from this context
+ * because of lock dependencies (cgroup_lock -> cpu hotplug) but basically
+ * everything that doesn't depend on a specific mem_cgroup structure should
+ * be initialized from here.
+ */
+static int __init mem_cgroup_init(void)
+{
+	hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
+	enable_swap_cgroup();
+	mem_cgroup_soft_limit_tree_init();
+	memcg_stock_init();
+	return 0;
+}
+subsys_initcall(mem_cgroup_init);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c6e4dd3e1c0..df0694c6ade 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -61,7 +61,7 @@ int sysctl_memory_failure_early_kill __read_mostly = 0;
 
 int sysctl_memory_failure_recovery __read_mostly = 1;
 
-atomic_long_t mce_bad_pages __read_mostly = ATOMIC_LONG_INIT(0);
+atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
 #if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
 
@@ -784,12 +784,12 @@ static struct page_state {
 	{ sc|dirty,	sc|dirty,	"dirty swapcache",	me_swapcache_dirty },
 	{ sc|dirty,	sc,		"clean swapcache",	me_swapcache_clean },
 
-	{ unevict|dirty, unevict|dirty,	"dirty unevictable LRU", me_pagecache_dirty },
-	{ unevict,	unevict,	"clean unevictable LRU", me_pagecache_clean },
-
 	{ mlock|dirty,	mlock|dirty,	"dirty mlocked LRU",	me_pagecache_dirty },
 	{ mlock,	mlock,		"clean mlocked LRU",	me_pagecache_clean },
 
+	{ unevict|dirty, unevict|dirty,	"dirty unevictable LRU", me_pagecache_dirty },
+	{ unevict,	unevict,	"clean unevictable LRU", me_pagecache_clean },
+
 	{ lru|dirty,	lru|dirty,	"dirty LRU",	me_pagecache_dirty },
 	{ lru|dirty,	lru,		"clean LRU",	me_pagecache_clean },
 
@@ -1021,6 +1021,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	struct page *hpage;
 	int res;
 	unsigned int nr_pages;
+	unsigned long page_flags;
 
 	if (!sysctl_memory_failure_recovery)
 		panic("Memory failure from trap %d on page %lx", trapno, pfn);
@@ -1039,8 +1040,18 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 		return 0;
 	}
 
-	nr_pages = 1 << compound_trans_order(hpage);
-	atomic_long_add(nr_pages, &mce_bad_pages);
+	/*
+	 * Currently errors on hugetlbfs pages are measured in hugepage units,
+	 * so nr_pages should be 1 << compound_order.  OTOH when errors are on
+	 * transparent hugepages, they are supposed to be split and error
+	 * measurement is done in normal page units.  So nr_pages should be one
+	 * in this case.
+	 */
+	if (PageHuge(p))
+		nr_pages = 1 << compound_order(hpage);
+	else /* normal page or thp */
+		nr_pages = 1;
+	atomic_long_add(nr_pages, &num_poisoned_pages);
 
 	/*
 	 * We need/can do nothing about count=0 pages.
@@ -1070,7 +1081,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			if (!PageHWPoison(hpage)
 			    || (hwpoison_filter(p) && TestClearPageHWPoison(p))
 			    || (p != hpage && TestSetPageHWPoison(hpage))) {
-				atomic_long_sub(nr_pages, &mce_bad_pages);
+				atomic_long_sub(nr_pages, &num_poisoned_pages);
 				return 0;
 			}
 			set_page_hwpoison_huge_page(hpage);
@@ -1119,6 +1130,15 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	lock_page(hpage);
 
 	/*
+	 * We use page flags to determine what action should be taken, but
+	 * the flags can be modified by the error containment action.  One
+	 * example is an mlocked page, where PG_mlocked is cleared by
+	 * page_remove_rmap() in try_to_unmap_one(). So to determine page status
+	 * correctly, we save a copy of the page flags at this time.
+	 */
+	page_flags = p->flags;
+
+	/*
 	 * unpoison always clear PG_hwpoison inside page lock
 	 */
 	if (!PageHWPoison(p)) {
@@ -1128,7 +1148,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
-			atomic_long_sub(nr_pages, &mce_bad_pages);
+			atomic_long_sub(nr_pages, &num_poisoned_pages);
 		unlock_page(hpage);
 		put_page(hpage);
 		return 0;
@@ -1176,12 +1196,19 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	}
 
 	res = -EBUSY;
-	for (ps = error_states;; ps++) {
-		if ((p->flags & ps->mask) == ps->res) {
-			res = page_action(ps, p, pfn);
+	/*
+	 * The first check uses the current page flags which may not have any
+	 * relevant information. The second check with the saved page flagss is
+	 * carried out only if the first check can't determine the page status.
+	 */
+	for (ps = error_states;; ps++)
+		if ((p->flags & ps->mask) == ps->res)
 			break;
-		}
-	}
+	if (!ps->mask)
+		for (ps = error_states;; ps++)
+			if ((page_flags & ps->mask) == ps->res)
+				break;
+	res = page_action(ps, p, pfn);
 out:
 	unlock_page(hpage);
 	return res;
@@ -1323,7 +1350,7 @@ int unpoison_memory(unsigned long pfn)
 			return 0;
 		}
 		if (TestClearPageHWPoison(p))
-			atomic_long_sub(nr_pages, &mce_bad_pages);
+			atomic_long_sub(nr_pages, &num_poisoned_pages);
 		pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn);
 		return 0;
 	}
@@ -1337,7 +1364,7 @@ int unpoison_memory(unsigned long pfn)
 	 */
 	if (TestClearPageHWPoison(page)) {
 		pr_info("MCE: Software-unpoisoned page %#lx\n", pfn);
-		atomic_long_sub(nr_pages, &mce_bad_pages);
+		atomic_long_sub(nr_pages, &num_poisoned_pages);
 		freeit = 1;
 		if (PageHuge(page))
 			clear_page_hwpoison_huge_page(page);
@@ -1368,7 +1395,7 @@ static struct page *new_page(struct page *p, unsigned long private, int **x)
  * that is not free, and 1 for any other page type.
  * For 1 the page is returned with increased page count, otherwise not.
  */
-static int get_any_page(struct page *p, unsigned long pfn, int flags)
+static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 {
 	int ret;
 
@@ -1393,11 +1420,9 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags)
 	if (!get_page_unless_zero(compound_head(p))) {
 		if (PageHuge(p)) {
 			pr_info("%s: %#lx free huge page\n", __func__, pfn);
-			ret = dequeue_hwpoisoned_huge_page(compound_head(p));
+			ret = 0;
 		} else if (is_free_buddy_page(p)) {
 			pr_info("%s: %#lx free buddy page\n", __func__, pfn);
-			/* Set hwpoison bit while page is still isolated */
-			SetPageHWPoison(p);
 			ret = 0;
 		} else {
 			pr_info("%s: %#lx: unknown zero refcount page type %lx\n",
@@ -1413,43 +1438,68 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags)
 	return ret;
 }
 
+static int get_any_page(struct page *page, unsigned long pfn, int flags)
+{
+	int ret = __get_any_page(page, pfn, flags);
+
+	if (ret == 1 && !PageHuge(page) && !PageLRU(page)) {
+		/*
+		 * Try to free it.
+		 */
+		put_page(page);
+		shake_page(page, 1);
+
+		/*
+		 * Did it turn free?
+		 */
+		ret = __get_any_page(page, pfn, 0);
+		if (!PageLRU(page)) {
+			pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
+				pfn, page->flags);
+			return -EIO;
+		}
+	}
+	return ret;
+}
+
 static int soft_offline_huge_page(struct page *page, int flags)
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
 	struct page *hpage = compound_head(page);
 
-	ret = get_any_page(page, pfn, flags);
-	if (ret < 0)
-		return ret;
-	if (ret == 0)
-		goto done;
-
+	/*
+	 * This double-check of PageHWPoison is to avoid the race with
+	 * memory_failure(). See also comment in __soft_offline_page().
+	 */
+	lock_page(hpage);
 	if (PageHWPoison(hpage)) {
+		unlock_page(hpage);
 		put_page(hpage);
 		pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
 		return -EBUSY;
 	}
+	unlock_page(hpage);
 
 	/* Keep page count to indicate a given hugepage is isolated. */
-	ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL, false,
+	ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL,
 				MIGRATE_SYNC);
 	put_page(hpage);
 	if (ret) {
 		pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 			pfn, ret, page->flags);
-		return ret;
-	}
-done:
-	if (!PageHWPoison(hpage))
+	} else {
+		set_page_hwpoison_huge_page(hpage);
+		dequeue_hwpoisoned_huge_page(hpage);
 		atomic_long_add(1 << compound_trans_order(hpage),
-				&mce_bad_pages);
-	set_page_hwpoison_huge_page(hpage);
-	dequeue_hwpoisoned_huge_page(hpage);
+				&num_poisoned_pages);
+	}
 	/* keep elevated page count for bad page */
 	return ret;
 }
 
+static int __soft_offline_page(struct page *page, int flags);
+
 /**
  * soft_offline_page - Soft offline a page.
  * @page: page to offline
@@ -1478,9 +1528,11 @@ int soft_offline_page(struct page *page, int flags)
 	unsigned long pfn = page_to_pfn(page);
 	struct page *hpage = compound_trans_head(page);
 
-	if (PageHuge(page))
-		return soft_offline_huge_page(page, flags);
-	if (PageTransHuge(hpage)) {
+	if (PageHWPoison(page)) {
+		pr_info("soft offline: %#lx page already poisoned\n", pfn);
+		return -EBUSY;
+	}
+	if (!PageHuge(page) && PageTransHuge(hpage)) {
 		if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
 			pr_info("soft offline: %#lx: failed to split THP\n",
 				pfn);
@@ -1491,47 +1543,45 @@ int soft_offline_page(struct page *page, int flags)
 	ret = get_any_page(page, pfn, flags);
 	if (ret < 0)
 		return ret;
-	if (ret == 0)
-		goto done;
-
-	/*
-	 * Page cache page we can handle?
-	 */
-	if (!PageLRU(page)) {
-		/*
-		 * Try to free it.
-		 */
-		put_page(page);
-		shake_page(page, 1);
-
-		/*
-		 * Did it turn free?
-		 */
-		ret = get_any_page(page, pfn, 0);
-		if (ret < 0)
-			return ret;
-		if (ret == 0)
-			goto done;
-	}
-	if (!PageLRU(page)) {
-		pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
-			pfn, page->flags);
-		return -EIO;
+	if (ret) { /* for in-use pages */
+		if (PageHuge(page))
+			ret = soft_offline_huge_page(page, flags);
+		else
+			ret = __soft_offline_page(page, flags);
+	} else { /* for free pages */
+		if (PageHuge(page)) {
+			set_page_hwpoison_huge_page(hpage);
+			dequeue_hwpoisoned_huge_page(hpage);
+			atomic_long_add(1 << compound_trans_order(hpage),
+					&num_poisoned_pages);
+		} else {
+			SetPageHWPoison(page);
+			atomic_long_inc(&num_poisoned_pages);
+		}
 	}
+	/* keep elevated page count for bad page */
+	return ret;
+}
 
-	lock_page(page);
-	wait_on_page_writeback(page);
+static int __soft_offline_page(struct page *page, int flags)
+{
+	int ret;
+	unsigned long pfn = page_to_pfn(page);
 
 	/*
-	 * Synchronized using the page lock with memory_failure()
+	 * Check PageHWPoison again inside page lock because PageHWPoison
+	 * is set by memory_failure() outside page lock. Note that
+	 * memory_failure() also double-checks PageHWPoison inside page lock,
+	 * so there's no race between soft_offline_page() and memory_failure().
 	 */
+	lock_page(page);
+	wait_on_page_writeback(page);
 	if (PageHWPoison(page)) {
 		unlock_page(page);
 		put_page(page);
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
 		return -EBUSY;
 	}
-
 	/*
 	 * Try to invalidate first. This should work for
 	 * non dirty unmapped page cache pages.
@@ -1544,9 +1594,10 @@ int soft_offline_page(struct page *page, int flags)
 	 */
 	if (ret == 1) {
 		put_page(page);
-		ret = 0;
 		pr_info("soft_offline: %#lx: invalidated\n", pfn);
-		goto done;
+		SetPageHWPoison(page);
+		atomic_long_inc(&num_poisoned_pages);
+		return 0;
 	}
 
 	/*
@@ -1563,28 +1614,23 @@ int soft_offline_page(struct page *page, int flags)
 	if (!ret) {
 		LIST_HEAD(pagelist);
 		inc_zone_page_state(page, NR_ISOLATED_ANON +
-					    page_is_file_cache(page));
+					page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
-							false, MIGRATE_SYNC,
-							MR_MEMORY_FAILURE);
+					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
 			putback_lru_pages(&pagelist);
 			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 				pfn, ret, page->flags);
 			if (ret > 0)
 				ret = -EIO;
+		} else {
+			SetPageHWPoison(page);
+			atomic_long_inc(&num_poisoned_pages);
 		}
 	} else {
 		pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
 			pfn, ret, page_count(page), page->flags);
 	}
-	if (ret)
-		return ret;
-
-done:
-	atomic_long_add(1, &mce_bad_pages);
-	SetPageHWPoison(page);
-	/* keep elevated page count for bad page */
 	return ret;
 }
diff --git a/mm/memory.c b/mm/memory.c
index bb1369f7b9b..705473afc1f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -69,6 +69,10 @@
 
 #include "internal.h"
 
+#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nid.
+#endif
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 /* use the per-pgdat data instead for discontigmem - mbligh */
 unsigned long max_mapnr;
@@ -1458,10 +1462,11 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 EXPORT_SYMBOL_GPL(zap_vma_ptes);
 
 /**
- * follow_page - look up a page descriptor from a user-virtual address
+ * follow_page_mask - look up a page descriptor from a user-virtual address
  * @vma: vm_area_struct mapping @address
  * @address: virtual address to look up
  * @flags: flags modifying lookup behaviour
+ * @page_mask: on output, *page_mask is set according to the size of the page
  *
  * @flags can have FOLL_ flags set, defined in <linux/mm.h>
  *
@@ -1469,8 +1474,9 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
  * an error pointer if there is a mapping to something not represented
  * by a page descriptor (see also vm_normal_page()).
  */
-struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
-			unsigned int flags)
+struct page *follow_page_mask(struct vm_area_struct *vma,
+			      unsigned long address, unsigned int flags,
+			      unsigned int *page_mask)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -1480,6 +1486,8 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	struct page *page;
 	struct mm_struct *mm = vma->vm_mm;
 
+	*page_mask = 0;
+
 	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
 	if (!IS_ERR(page)) {
 		BUG_ON(flags & FOLL_GET);
@@ -1526,6 +1534,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 				page = follow_trans_huge_pmd(vma, address,
 							     pmd, flags);
 				spin_unlock(&mm->page_table_lock);
+				*page_mask = HPAGE_PMD_NR - 1;
 				goto out;
 			}
 		} else
@@ -1539,8 +1548,24 @@ split_fallthrough:
 	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
 
 	pte = *ptep;
-	if (!pte_present(pte))
-		goto no_page;
+	if (!pte_present(pte)) {
+		swp_entry_t entry;
+		/*
+		 * KSM's break_ksm() relies upon recognizing a ksm page
+		 * even while it is being migrated, so for that case we
+		 * need migration_entry_wait().
+		 */
+		if (likely(!(flags & FOLL_MIGRATION)))
+			goto no_page;
+		if (pte_none(pte) || pte_file(pte))
+			goto no_page;
+		entry = pte_to_swp_entry(pte);
+		if (!is_migration_entry(entry))
+			goto no_page;
+		pte_unmap_unlock(ptep, ptl);
+		migration_entry_wait(mm, pmd, address);
+		goto split_fallthrough;
+	}
 	if ((flags & FOLL_NUMA) && pte_numa(pte))
 		goto no_page;
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
@@ -1673,15 +1698,16 @@ static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long add
  * instead of __get_user_pages. __get_user_pages should be used only if
  * you need some special @gup_flags.
  */
-int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		     unsigned long start, int nr_pages, unsigned int gup_flags,
-		     struct page **pages, struct vm_area_struct **vmas,
-		     int *nonblocking)
+long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long start, unsigned long nr_pages,
+		unsigned int gup_flags, struct page **pages,
+		struct vm_area_struct **vmas, int *nonblocking)
 {
-	int i;
+	long i;
 	unsigned long vm_flags;
+	unsigned int page_mask;
 
-	if (nr_pages <= 0)
+	if (!nr_pages)
 		return 0;
 
 	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
@@ -1757,6 +1783,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				get_page(page);
 			}
 			pte_unmap(pte);
+			page_mask = 0;
 			goto next_page;
 		}
 
@@ -1774,6 +1801,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		do {
 			struct page *page;
 			unsigned int foll_flags = gup_flags;
+			unsigned int page_increm;
 
 			/*
 			 * If we have a pending SIGKILL, don't keep faulting
@@ -1783,7 +1811,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				return i ? i : -ERESTARTSYS;
 
 			cond_resched();
-			while (!(page = follow_page(vma, start, foll_flags))) {
+			while (!(page = follow_page_mask(vma, start,
+						foll_flags, &page_mask))) {
 				int ret;
 				unsigned int fault_flags = 0;
 
@@ -1857,13 +1886,19 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 				flush_anon_page(vma, page, start);
 				flush_dcache_page(page);
+				page_mask = 0;
 			}
 next_page:
-			if (vmas)
+			if (vmas) {
 				vmas[i] = vma;
-			i++;
-			start += PAGE_SIZE;
-			nr_pages--;
+				page_mask = 0;
+			}
+			page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+			if (page_increm > nr_pages)
+				page_increm = nr_pages;
+			i += page_increm;
+			start += page_increm * PAGE_SIZE;
+			nr_pages -= page_increm;
 		} while (nr_pages && start < vma->vm_end);
 	} while (nr_pages);
 	return i;
@@ -1977,9 +2012,9 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
  *
  * See also get_user_pages_fast, for performance critical applications.
  */
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, int nr_pages, int write, int force,
-		struct page **pages, struct vm_area_struct **vmas)
+long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long start, unsigned long nr_pages, int write,
+		int force, struct page **pages, struct vm_area_struct **vmas)
 {
 	int flags = FOLL_TOUCH;
 
@@ -2919,7 +2954,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned int flags, pte_t orig_pte)
 {
 	spinlock_t *ptl;
-	struct page *page, *swapcache = NULL;
+	struct page *page, *swapcache;
 	swp_entry_t entry;
 	pte_t pte;
 	int locked;
@@ -2970,9 +3005,11 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		ret = VM_FAULT_HWPOISON;
 		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+		swapcache = page;
 		goto out_release;
 	}
 
+	swapcache = page;
 	locked = lock_page_or_retry(page, mm, flags);
 
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
@@ -2990,16 +3027,11 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val))
 		goto out_page;
 
-	if (ksm_might_need_to_copy(page, vma, address)) {
-		swapcache = page;
-		page = ksm_does_need_to_copy(page, vma, address);
-
-		if (unlikely(!page)) {
-			ret = VM_FAULT_OOM;
-			page = swapcache;
-			swapcache = NULL;
-			goto out_page;
-		}
+	page = ksm_might_need_to_copy(page, vma, address);
+	if (unlikely(!page)) {
+		ret = VM_FAULT_OOM;
+		page = swapcache;
+		goto out_page;
 	}
 
 	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
@@ -3044,7 +3076,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	flush_icache_page(vma, page);
 	set_pte_at(mm, address, page_table, pte);
-	do_page_add_anon_rmap(page, vma, address, exclusive);
+	if (page == swapcache)
+		do_page_add_anon_rmap(page, vma, address, exclusive);
+	else /* ksm created a completely new copy */
+		page_add_new_anon_rmap(page, vma, address);
 	/* It's better to call commit-charge after rmap is established */
 	mem_cgroup_commit_charge_swapin(page, ptr);
 
@@ -3052,7 +3087,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
 		try_to_free_swap(page);
 	unlock_page(page);
-	if (swapcache) {
+	if (page != swapcache) {
 		/*
 		 * Hold the lock to avoid the swap entry to be reused
 		 * until we take the PT lock for the pte_same() check
@@ -3085,7 +3120,7 @@ out_page:
 	unlock_page(page);
 out_release:
 	page_cache_release(page);
-	if (swapcache) {
+	if (page != swapcache) {
 		unlock_page(swapcache);
 		page_cache_release(swapcache);
 	}
@@ -3821,30 +3856,6 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-int make_pages_present(unsigned long addr, unsigned long end)
-{
-	int ret, len, write;
-	struct vm_area_struct * vma;
-
-	vma = find_vma(current->mm, addr);
-	if (!vma)
-		return -ENOMEM;
-	/*
-	 * We want to touch writable mappings with a write fault in order
-	 * to break COW, except for shared mappings because these don't COW
-	 * and we would not want to dirty them for nothing.
-	 */
-	write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE;
-	BUG_ON(addr >= end);
-	BUG_ON(end > vma->vm_end);
-	len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
-	ret = get_user_pages(current, current->mm, addr,
-			len, write, 0, NULL, NULL);
-	if (ret < 0)
-		return ret;
-	return ret == len ? 0 : -EFAULT;
-}
-
 #if !defined(__HAVE_ARCH_GATE_AREA)
 
 #if defined(AT_SYSINFO_EHDR)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index d04ed87bfac..b81a367b9f3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -29,6 +29,7 @@
 #include <linux/suspend.h>
 #include <linux/mm_inline.h>
 #include <linux/firmware-map.h>
+#include <linux/stop_machine.h>
 
 #include <asm/tlbflush.h>
 
@@ -91,9 +92,8 @@ static void release_memory_resource(struct resource *res)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void get_page_bootmem(unsigned long info,  struct page *page,
-			     unsigned long type)
+void get_page_bootmem(unsigned long info,  struct page *page,
+		      unsigned long type)
 {
 	page->lru.next = (struct list_head *) type;
 	SetPagePrivate(page);
@@ -124,10 +124,13 @@ void __ref put_page_bootmem(struct page *page)
 		mutex_lock(&ppb_lock);
 		__free_pages_bootmem(page, 0);
 		mutex_unlock(&ppb_lock);
+		totalram_pages++;
 	}
 
 }
 
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
 static void register_page_bootmem_info_section(unsigned long start_pfn)
 {
 	unsigned long *usemap, mapsize, section_nr, i;
@@ -161,6 +164,32 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
 
 }
+#else /* CONFIG_SPARSEMEM_VMEMMAP */
+static void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+	unsigned long *usemap, mapsize, section_nr, i;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+
+	if (!pfn_valid(start_pfn))
+		return;
+
+	section_nr = pfn_to_section_nr(start_pfn);
+	ms = __nr_to_section(section_nr);
+
+	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
+
+	usemap = __nr_to_section(section_nr)->pageblock_flags;
+	page = virt_to_page(usemap);
+
+	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
 
 void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
@@ -189,7 +218,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 	}
 
 	pfn = pgdat->node_start_pfn;
-	end_pfn = pfn + pgdat->node_spanned_pages;
+	end_pfn = pgdat_end_pfn(pgdat);
 
 	/* register_section info */
 	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
@@ -203,7 +232,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 			register_page_bootmem_info_section(pfn);
 	}
 }
-#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
 
 static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
 			   unsigned long end_pfn)
@@ -253,6 +282,17 @@ static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
 		set_page_links(pfn_to_page(pfn), zid, nid, pfn);
 }
 
+/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or
+ * alloc_bootmem_node_nopanic() */
+static int __ref ensure_zone_is_initialized(struct zone *zone,
+			unsigned long start_pfn, unsigned long num_pages)
+{
+	if (!zone_is_initialized(zone))
+		return init_currently_empty_zone(zone, start_pfn, num_pages,
+						 MEMMAP_HOTPLUG);
+	return 0;
+}
+
 static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
 		unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -260,17 +300,14 @@ static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
 	unsigned long flags;
 	unsigned long z1_start_pfn;
 
-	if (!z1->wait_table) {
-		ret = init_currently_empty_zone(z1, start_pfn,
-			end_pfn - start_pfn, MEMMAP_HOTPLUG);
-		if (ret)
-			return ret;
-	}
+	ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn);
+	if (ret)
+		return ret;
 
 	pgdat_resize_lock(z1->zone_pgdat, &flags);
 
 	/* can't move pfns which are higher than @z2 */
-	if (end_pfn > z2->zone_start_pfn + z2->spanned_pages)
+	if (end_pfn > zone_end_pfn(z2))
 		goto out_fail;
 	/* the move out part mast at the left most of @z2 */
 	if (start_pfn > z2->zone_start_pfn)
@@ -286,7 +323,7 @@ static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
 		z1_start_pfn = start_pfn;
 
 	resize_zone(z1, z1_start_pfn, end_pfn);
-	resize_zone(z2, end_pfn, z2->zone_start_pfn + z2->spanned_pages);
+	resize_zone(z2, end_pfn, zone_end_pfn(z2));
 
 	pgdat_resize_unlock(z1->zone_pgdat, &flags);
 
@@ -305,12 +342,9 @@ static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2,
 	unsigned long flags;
 	unsigned long z2_end_pfn;
 
-	if (!z2->wait_table) {
-		ret = init_currently_empty_zone(z2, start_pfn,
-			end_pfn - start_pfn, MEMMAP_HOTPLUG);
-		if (ret)
-			return ret;
-	}
+	ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn);
+	if (ret)
+		return ret;
 
 	pgdat_resize_lock(z1->zone_pgdat, &flags);
 
@@ -318,15 +352,15 @@ static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2,
 	if (z1->zone_start_pfn > start_pfn)
 		goto out_fail;
 	/* the move out part mast at the right most of @z1 */
-	if (z1->zone_start_pfn + z1->spanned_pages >  end_pfn)
+	if (zone_end_pfn(z1) >  end_pfn)
 		goto out_fail;
 	/* must included/overlap */
-	if (start_pfn >= z1->zone_start_pfn + z1->spanned_pages)
+	if (start_pfn >= zone_end_pfn(z1))
 		goto out_fail;
 
 	/* use end_pfn for z2's end_pfn if z2 is empty */
 	if (z2->spanned_pages)
-		z2_end_pfn = z2->zone_start_pfn + z2->spanned_pages;
+		z2_end_pfn = zone_end_pfn(z2);
 	else
 		z2_end_pfn = end_pfn;
 
@@ -363,16 +397,13 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 	int nid = pgdat->node_id;
 	int zone_type;
 	unsigned long flags;
+	int ret;
 
 	zone_type = zone - pgdat->node_zones;
-	if (!zone->wait_table) {
-		int ret;
+	ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages);
+	if (ret)
+		return ret;
 
-		ret = init_currently_empty_zone(zone, phys_start_pfn,
-						nr_pages, MEMMAP_HOTPLUG);
-		if (ret)
-			return ret;
-	}
 	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages);
 	grow_pgdat_span(zone->zone_pgdat, phys_start_pfn,
@@ -405,20 +436,211 @@ static int __meminit __add_section(int nid, struct zone *zone,
 	return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
 }
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-static int __remove_section(struct zone *zone, struct mem_section *ms)
+/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
+static int find_smallest_section_pfn(int nid, struct zone *zone,
+				     unsigned long start_pfn,
+				     unsigned long end_pfn)
+{
+	struct mem_section *ms;
+
+	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) {
+		ms = __pfn_to_section(start_pfn);
+
+		if (unlikely(!valid_section(ms)))
+			continue;
+
+		if (unlikely(pfn_to_nid(start_pfn) != nid))
+			continue;
+
+		if (zone && zone != page_zone(pfn_to_page(start_pfn)))
+			continue;
+
+		return start_pfn;
+	}
+
+	return 0;
+}
+
+/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
+static int find_biggest_section_pfn(int nid, struct zone *zone,
+				    unsigned long start_pfn,
+				    unsigned long end_pfn)
+{
+	struct mem_section *ms;
+	unsigned long pfn;
+
+	/* pfn is the end pfn of a memory section. */
+	pfn = end_pfn - 1;
+	for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) {
+		ms = __pfn_to_section(pfn);
+
+		if (unlikely(!valid_section(ms)))
+			continue;
+
+		if (unlikely(pfn_to_nid(pfn) != nid))
+			continue;
+
+		if (zone && zone != page_zone(pfn_to_page(pfn)))
+			continue;
+
+		return pfn;
+	}
+
+	return 0;
+}
+
+static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
+			     unsigned long end_pfn)
 {
+	unsigned long zone_start_pfn =  zone->zone_start_pfn;
+	unsigned long zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	unsigned long pfn;
+	struct mem_section *ms;
+	int nid = zone_to_nid(zone);
+
+	zone_span_writelock(zone);
+	if (zone_start_pfn == start_pfn) {
+		/*
+		 * If the section is smallest section in the zone, it need
+		 * shrink zone->zone_start_pfn and zone->zone_spanned_pages.
+		 * In this case, we find second smallest valid mem_section
+		 * for shrinking zone.
+		 */
+		pfn = find_smallest_section_pfn(nid, zone, end_pfn,
+						zone_end_pfn);
+		if (pfn) {
+			zone->zone_start_pfn = pfn;
+			zone->spanned_pages = zone_end_pfn - pfn;
+		}
+	} else if (zone_end_pfn == end_pfn) {
+		/*
+		 * If the section is biggest section in the zone, it need
+		 * shrink zone->spanned_pages.
+		 * In this case, we find second biggest valid mem_section for
+		 * shrinking zone.
+		 */
+		pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn,
+					       start_pfn);
+		if (pfn)
+			zone->spanned_pages = pfn - zone_start_pfn + 1;
+	}
+
 	/*
-	 * XXX: Freeing memmap with vmemmap is not implement yet.
-	 *      This should be removed later.
+	 * The section is not biggest or smallest mem_section in the zone, it
+	 * only creates a hole in the zone. So in this case, we need not
+	 * change the zone. But perhaps, the zone has only hole data. Thus
+	 * it check the zone has only hole or not.
 	 */
-	return -EBUSY;
+	pfn = zone_start_pfn;
+	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) {
+		ms = __pfn_to_section(pfn);
+
+		if (unlikely(!valid_section(ms)))
+			continue;
+
+		if (page_zone(pfn_to_page(pfn)) != zone)
+			continue;
+
+		 /* If the section is current section, it continues the loop */
+		if (start_pfn == pfn)
+			continue;
+
+		/* If we find valid section, we have nothing to do */
+		zone_span_writeunlock(zone);
+		return;
+	}
+
+	/* The zone has no valid section */
+	zone->zone_start_pfn = 0;
+	zone->spanned_pages = 0;
+	zone_span_writeunlock(zone);
 }
-#else
-static int __remove_section(struct zone *zone, struct mem_section *ms)
+
+static void shrink_pgdat_span(struct pglist_data *pgdat,
+			      unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long pgdat_start_pfn =  pgdat->node_start_pfn;
+	unsigned long pgdat_end_pfn =
+		pgdat->node_start_pfn + pgdat->node_spanned_pages;
+	unsigned long pfn;
+	struct mem_section *ms;
+	int nid = pgdat->node_id;
+
+	if (pgdat_start_pfn == start_pfn) {
+		/*
+		 * If the section is smallest section in the pgdat, it need
+		 * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
+		 * In this case, we find second smallest valid mem_section
+		 * for shrinking zone.
+		 */
+		pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
+						pgdat_end_pfn);
+		if (pfn) {
+			pgdat->node_start_pfn = pfn;
+			pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
+		}
+	} else if (pgdat_end_pfn == end_pfn) {
+		/*
+		 * If the section is biggest section in the pgdat, it need
+		 * shrink pgdat->node_spanned_pages.
+		 * In this case, we find second biggest valid mem_section for
+		 * shrinking zone.
+		 */
+		pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
+					       start_pfn);
+		if (pfn)
+			pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
+	}
+
+	/*
+	 * If the section is not biggest or smallest mem_section in the pgdat,
+	 * it only creates a hole in the pgdat. So in this case, we need not
+	 * change the pgdat.
+	 * But perhaps, the pgdat has only hole data. Thus it check the pgdat
+	 * has only hole or not.
+	 */
+	pfn = pgdat_start_pfn;
+	for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) {
+		ms = __pfn_to_section(pfn);
+
+		if (unlikely(!valid_section(ms)))
+			continue;
+
+		if (pfn_to_nid(pfn) != nid)
+			continue;
+
+		 /* If the section is current section, it continues the loop */
+		if (start_pfn == pfn)
+			continue;
+
+		/* If we find valid section, we have nothing to do */
+		return;
+	}
+
+	/* The pgdat has no valid section */
+	pgdat->node_start_pfn = 0;
+	pgdat->node_spanned_pages = 0;
+}
+
+static void __remove_zone(struct zone *zone, unsigned long start_pfn)
 {
-	unsigned long flags;
 	struct pglist_data *pgdat = zone->zone_pgdat;
+	int nr_pages = PAGES_PER_SECTION;
+	int zone_type;
+	unsigned long flags;
+
+	zone_type = zone - pgdat->node_zones;
+
+	pgdat_resize_lock(zone->zone_pgdat, &flags);
+	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
+	shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
+	pgdat_resize_unlock(zone->zone_pgdat, &flags);
+}
+
+static int __remove_section(struct zone *zone, struct mem_section *ms)
+{
+	unsigned long start_pfn;
+	int scn_nr;
 	int ret = -EINVAL;
 
 	if (!valid_section(ms))
@@ -428,12 +650,13 @@ static int __remove_section(struct zone *zone, struct mem_section *ms)
 	if (ret)
 		return ret;
 
-	pgdat_resize_lock(pgdat, &flags);
+	scn_nr = __section_nr(ms);
+	start_pfn = section_nr_to_pfn(scn_nr);
+	__remove_zone(zone, start_pfn);
+
 	sparse_remove_one_section(zone, ms);
-	pgdat_resize_unlock(pgdat, &flags);
 	return 0;
 }
-#endif
 
 /*
  * Reasonably generic function for adding memory.  It is
@@ -797,11 +1020,14 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	unsigned long zholes_size[MAX_NR_ZONES] = {0};
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 
-	pgdat = arch_alloc_nodedata(nid);
-	if (!pgdat)
-		return NULL;
+	pgdat = NODE_DATA(nid);
+	if (!pgdat) {
+		pgdat = arch_alloc_nodedata(nid);
+		if (!pgdat)
+			return NULL;
 
-	arch_refresh_nodedata(nid, pgdat);
+		arch_refresh_nodedata(nid, pgdat);
+	}
 
 	/* we can use NODE_DATA(nid) from here */
 
@@ -854,7 +1080,8 @@ out:
 int __ref add_memory(int nid, u64 start, u64 size)
 {
 	pg_data_t *pgdat = NULL;
-	int new_pgdat = 0;
+	bool new_pgdat;
+	bool new_node;
 	struct resource *res;
 	int ret;
 
@@ -865,12 +1092,16 @@ int __ref add_memory(int nid, u64 start, u64 size)
 	if (!res)
 		goto out;
 
-	if (!node_online(nid)) {
+	{	/* Stupid hack to suppress address-never-null warning */
+		void *p = NODE_DATA(nid);
+		new_pgdat = !p;
+	}
+	new_node = !node_online(nid);
+	if (new_node) {
 		pgdat = hotadd_new_pgdat(nid, start);
 		ret = -ENOMEM;
 		if (!pgdat)
 			goto error;
-		new_pgdat = 1;
 	}
 
 	/* call arch's memory hotadd */
@@ -882,7 +1113,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
 	/* we online node here. we can't roll back from here. */
 	node_set_online(nid);
 
-	if (new_pgdat) {
+	if (new_node) {
 		ret = register_one_node(nid);
 		/*
 		 * If sysfs file of new node can't create, cpu on the node
@@ -901,8 +1132,7 @@ error:
 	/* rollback pgdat allocation and others */
 	if (new_pgdat)
 		rollback_node_hotadd(nid, pgdat);
-	if (res)
-		release_memory_resource(res);
+	release_memory_resource(res);
 
 out:
 	unlock_memory_hotplug();
@@ -1058,8 +1288,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		 * migrate_pages returns # of failed pages.
 		 */
 		ret = migrate_pages(&source, alloc_migrate_target, 0,
-							true, MIGRATE_SYNC,
-							MR_MEMORY_HOTPLUG);
+					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
 		if (ret)
 			putback_lru_pages(&source);
 	}
@@ -1381,17 +1610,26 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 	return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ);
 }
 
-int remove_memory(u64 start, u64 size)
+/**
+ * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn)
+ * @start_pfn: start pfn of the memory range
+ * @end_pfn: end pft of the memory range
+ * @arg: argument passed to func
+ * @func: callback for each memory section walked
+ *
+ * This function walks through all present mem sections in range
+ * [start_pfn, end_pfn) and call func on each mem section.
+ *
+ * Returns the return value of func.
+ */
+static int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
+		void *arg, int (*func)(struct memory_block *, void *))
 {
 	struct memory_block *mem = NULL;
 	struct mem_section *section;
-	unsigned long start_pfn, end_pfn;
 	unsigned long pfn, section_nr;
 	int ret;
 
-	start_pfn = PFN_DOWN(start);
-	end_pfn = start_pfn + PFN_DOWN(size);
-
 	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
 		section_nr = pfn_to_section_nr(pfn);
 		if (!present_section_nr(section_nr))
@@ -1408,7 +1646,7 @@ int remove_memory(u64 start, u64 size)
 		if (!mem)
 			continue;
 
-		ret = offline_memory_block(mem);
+		ret = func(mem, arg);
 		if (ret) {
 			kobject_put(&mem->dev.kobj);
 			return ret;
@@ -1420,12 +1658,209 @@ int remove_memory(u64 start, u64 size)
 
 	return 0;
 }
+
+/**
+ * offline_memory_block_cb - callback function for offlining memory block
+ * @mem: the memory block to be offlined
+ * @arg: buffer to hold error msg
+ *
+ * Always return 0, and put the error msg in arg if any.
+ */
+static int offline_memory_block_cb(struct memory_block *mem, void *arg)
+{
+	int *ret = arg;
+	int error = offline_memory_block(mem);
+
+	if (error != 0 && *ret == 0)
+		*ret = error;
+
+	return 0;
+}
+
+static int is_memblock_offlined_cb(struct memory_block *mem, void *arg)
+{
+	int ret = !is_memblock_offlined(mem);
+
+	if (unlikely(ret))
+		pr_warn("removing memory fails, because memory "
+			"[%#010llx-%#010llx] is onlined\n",
+			PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)),
+			PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1);
+
+	return ret;
+}
+
+static int check_cpu_on_node(void *data)
+{
+	struct pglist_data *pgdat = data;
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		if (cpu_to_node(cpu) == pgdat->node_id)
+			/*
+			 * the cpu on this node isn't removed, and we can't
+			 * offline this node.
+			 */
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void unmap_cpu_on_node(void *data)
+{
+#ifdef CONFIG_ACPI_NUMA
+	struct pglist_data *pgdat = data;
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		if (cpu_to_node(cpu) == pgdat->node_id)
+			numa_clear_node(cpu);
+#endif
+}
+
+static int check_and_unmap_cpu_on_node(void *data)
+{
+	int ret = check_cpu_on_node(data);
+
+	if (ret)
+		return ret;
+
+	/*
+	 * the node will be offlined when we come here, so we can clear
+	 * the cpu_to_node() now.
+	 */
+
+	unmap_cpu_on_node(data);
+	return 0;
+}
+
+/* offline the node if all memory sections of this node are removed */
+void try_offline_node(int nid)
+{
+	pg_data_t *pgdat = NODE_DATA(nid);
+	unsigned long start_pfn = pgdat->node_start_pfn;
+	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
+	unsigned long pfn;
+	struct page *pgdat_page = virt_to_page(pgdat);
+	int i;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		unsigned long section_nr = pfn_to_section_nr(pfn);
+
+		if (!present_section_nr(section_nr))
+			continue;
+
+		if (pfn_to_nid(pfn) != nid)
+			continue;
+
+		/*
+		 * some memory sections of this node are not removed, and we
+		 * can't offline node now.
+		 */
+		return;
+	}
+
+	if (stop_machine(check_and_unmap_cpu_on_node, pgdat, NULL))
+		return;
+
+	/*
+	 * all memory/cpu of this node are removed, we can offline this
+	 * node now.
+	 */
+	node_set_offline(nid);
+	unregister_one_node(nid);
+
+	if (!PageSlab(pgdat_page) && !PageCompound(pgdat_page))
+		/* node data is allocated from boot memory */
+		return;
+
+	/* free waittable in each zone */
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		struct zone *zone = pgdat->node_zones + i;
+
+		if (zone->wait_table)
+			vfree(zone->wait_table);
+	}
+
+	/*
+	 * Since there is no way to guarentee the address of pgdat/zone is not
+	 * on stack of any kernel threads or used by other kernel objects
+	 * without reference counting or other symchronizing method, do not
+	 * reset node_data and free pgdat here. Just reset it to 0 and reuse
+	 * the memory when the node is online again.
+	 */
+	memset(pgdat, 0, sizeof(*pgdat));
+}
+EXPORT_SYMBOL(try_offline_node);
+
+int __ref remove_memory(int nid, u64 start, u64 size)
+{
+	unsigned long start_pfn, end_pfn;
+	int ret = 0;
+	int retry = 1;
+
+	start_pfn = PFN_DOWN(start);
+	end_pfn = start_pfn + PFN_DOWN(size);
+
+	/*
+	 * When CONFIG_MEMCG is on, one memory block may be used by other
+	 * blocks to store page cgroup when onlining pages. But we don't know
+	 * in what order pages are onlined. So we iterate twice to offline
+	 * memory:
+	 * 1st iterate: offline every non primary memory block.
+	 * 2nd iterate: offline primary (i.e. first added) memory block.
+	 */
+repeat:
+	walk_memory_range(start_pfn, end_pfn, &ret,
+			  offline_memory_block_cb);
+	if (ret) {
+		if (!retry)
+			return ret;
+
+		retry = 0;
+		ret = 0;
+		goto repeat;
+	}
+
+	lock_memory_hotplug();
+
+	/*
+	 * we have offlined all memory blocks like this:
+	 *   1. lock memory hotplug
+	 *   2. offline a memory block
+	 *   3. unlock memory hotplug
+	 *
+	 * repeat step1-3 to offline the memory block. All memory blocks
+	 * must be offlined before removing memory. But we don't hold the
+	 * lock in the whole operation. So we should check whether all
+	 * memory blocks are offlined.
+	 */
+
+	ret = walk_memory_range(start_pfn, end_pfn, NULL,
+				is_memblock_offlined_cb);
+	if (ret) {
+		unlock_memory_hotplug();
+		return ret;
+	}
+
+	/* remove memmap entry */
+	firmware_map_remove(start, start + size, "System RAM");
+
+	arch_remove_memory(start, size);
+
+	try_offline_node(nid);
+
+	unlock_memory_hotplug();
+
+	return 0;
+}
 #else
 int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 {
 	return -EINVAL;
 }
-int remove_memory(u64 start, u64 size)
+int remove_memory(int nid, u64 start, u64 size)
 {
 	return -EINVAL;
 }
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e2df1c1fb41..31d26637b65 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -26,7 +26,7 @@
  *                the allocation to memory nodes instead
  *
  * preferred       Try a specific node first before normal fallback.
- *                As a special case node -1 here means do the allocation
+ *                As a special case NUMA_NO_NODE here means do the allocation
  *                on the local CPU. This is normally identical to default,
  *                but useful to set in a VMA when you have a non default
  *                process policy.
@@ -127,7 +127,7 @@ static struct mempolicy *get_task_policy(struct task_struct *p)
 
 	if (!pol) {
 		node = numa_node_id();
-		if (node != -1)
+		if (node != NUMA_NO_NODE)
 			pol = &preferred_node_policy[node];
 
 		/* preferred_node_policy is not initialised early in boot */
@@ -161,19 +161,7 @@ static const struct mempolicy_operations {
 /* Check that the nodemask contains at least one populated zone */
 static int is_valid_nodemask(const nodemask_t *nodemask)
 {
-	int nd, k;
-
-	for_each_node_mask(nd, *nodemask) {
-		struct zone *z;
-
-		for (k = 0; k <= policy_zone; k++) {
-			z = &NODE_DATA(nd)->node_zones[k];
-			if (z->present_pages > 0)
-				return 1;
-		}
-	}
-
-	return 0;
+	return nodes_intersects(*nodemask, node_states[N_MEMORY]);
 }
 
 static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
@@ -270,7 +258,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 	struct mempolicy *policy;
 
 	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
-		 mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
+		 mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE);
 
 	if (mode == MPOL_DEFAULT) {
 		if (nodes && !nodes_empty(*nodes))
@@ -508,9 +496,8 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		/*
 		 * vm_normal_page() filters out zero pages, but there might
 		 * still be PageReserved pages to skip, perhaps in a VDSO.
-		 * And we cannot move PageKsm pages sensibly or safely yet.
 		 */
-		if (PageReserved(page) || PageKsm(page))
+		if (PageReserved(page))
 			continue;
 		nid = page_to_nid(page);
 		if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
@@ -1027,8 +1014,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_node_page, dest,
-							false, MIGRATE_SYNC,
-							MR_SYSCALL);
+					MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
 			putback_lru_pages(&pagelist);
 	}
@@ -1235,7 +1221,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 	pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n",
 		 start, start + len, mode, mode_flags,
-		 nmask ? nodes_addr(*nmask)[0] : -1);
+		 nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE);
 
 	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
 
@@ -1272,9 +1258,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 		if (!list_empty(&pagelist)) {
 			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
 			nr_failed = migrate_pages(&pagelist, new_vma_page,
-						(unsigned long)vma,
-						false, MIGRATE_SYNC,
-						MR_MEMPOLICY_MBIND);
+					(unsigned long)vma,
+					MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
 			if (nr_failed)
 				putback_lru_pages(&pagelist);
 		}
@@ -1644,6 +1629,26 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 	return pol;
 }
 
+static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
+{
+	enum zone_type dynamic_policy_zone = policy_zone;
+
+	BUG_ON(dynamic_policy_zone == ZONE_MOVABLE);
+
+	/*
+	 * if policy->v.nodes has movable memory only,
+	 * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only.
+	 *
+	 * policy->v.nodes is intersect with node_states[N_MEMORY].
+	 * so if the following test faile, it implies
+	 * policy->v.nodes has movable memory only.
+	 */
+	if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY]))
+		dynamic_policy_zone = ZONE_MOVABLE;
+
+	return zone >= dynamic_policy_zone;
+}
+
 /*
  * Return a nodemask representing a mempolicy for filtering nodes for
  * page allocation
@@ -1652,7 +1657,7 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
 {
 	/* Lower zones don't get a nodemask applied for MPOL_BIND */
 	if (unlikely(policy->mode == MPOL_BIND) &&
-			gfp_zone(gfp) >= policy_zone &&
+			apply_policy_zone(policy, gfp_zone(gfp)) &&
 			cpuset_nodemask_valid_mems_allowed(&policy->v.nodes))
 		return &policy->v.nodes;
 
@@ -2308,7 +2313,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		 * it less likely we act on an unlikely task<->page
 		 * relation.
 		 */
-		last_nid = page_xchg_last_nid(page, polnid);
+		last_nid = page_nid_xchg_last(page, polnid);
 		if (last_nid != polnid)
 			goto out;
 	}
@@ -2483,7 +2488,7 @@ int mpol_set_shared_policy(struct shared_policy *info,
 		 vma->vm_pgoff,
 		 sz, npol ? npol->mode : -1,
 		 npol ? npol->flags : -1,
-		 npol ? nodes_addr(npol->v.nodes)[0] : -1);
+		 npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE);
 
 	if (npol) {
 		new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol);
diff --git a/mm/migrate.c b/mm/migrate.c
index 2fd8b4af474..3bbaf5d230b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -464,7 +464,10 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 
 	mlock_migrate_page(newpage, page);
 	ksm_migrate_page(newpage, page);
-
+	/*
+	 * Please do not reorder this without considering how mm/ksm.c's
+	 * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
+	 */
 	ClearPageSwapCache(page);
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
@@ -698,7 +701,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 }
 
 static int __unmap_and_move(struct page *page, struct page *newpage,
-			int force, bool offlining, enum migrate_mode mode)
+				int force, enum migrate_mode mode)
 {
 	int rc = -EAGAIN;
 	int remap_swapcache = 1;
@@ -728,20 +731,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		lock_page(page);
 	}
 
-	/*
-	 * Only memory hotplug's offline_pages() caller has locked out KSM,
-	 * and can safely migrate a KSM page.  The other cases have skipped
-	 * PageKsm along with PageReserved - but it is only now when we have
-	 * the page lock that we can be certain it will not go KSM beneath us
-	 * (KSM will not upgrade a page from PageAnon to PageKsm when it sees
-	 * its pagecount raised, but only here do we take the page lock which
-	 * serializes that).
-	 */
-	if (PageKsm(page) && !offlining) {
-		rc = -EBUSY;
-		goto unlock;
-	}
-
 	/* charge against new page */
 	mem_cgroup_prepare_migration(page, newpage, &mem);
 
@@ -768,7 +757,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 	 * File Caches may use write_page() or lock_page() in migration, then,
 	 * just care Anon page here.
 	 */
-	if (PageAnon(page)) {
+	if (PageAnon(page) && !PageKsm(page)) {
 		/*
 		 * Only page_lock_anon_vma_read() understands the subtleties of
 		 * getting a hold on an anon_vma from outside one of its mms.
@@ -848,7 +837,6 @@ uncharge:
 	mem_cgroup_end_migration(mem, page, newpage,
 				 (rc == MIGRATEPAGE_SUCCESS ||
 				  rc == MIGRATEPAGE_BALLOON_SUCCESS));
-unlock:
 	unlock_page(page);
 out:
 	return rc;
@@ -859,8 +847,7 @@ out:
  * to the newly allocated page in newpage.
  */
 static int unmap_and_move(new_page_t get_new_page, unsigned long private,
-			struct page *page, int force, bool offlining,
-			enum migrate_mode mode)
+			struct page *page, int force, enum migrate_mode mode)
 {
 	int rc = 0;
 	int *result = NULL;
@@ -878,7 +865,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 		if (unlikely(split_huge_page(page)))
 			goto out;
 
-	rc = __unmap_and_move(page, newpage, force, offlining, mode);
+	rc = __unmap_and_move(page, newpage, force, mode);
 
 	if (unlikely(rc == MIGRATEPAGE_BALLOON_SUCCESS)) {
 		/*
@@ -938,8 +925,7 @@ out:
  */
 static int unmap_and_move_huge_page(new_page_t get_new_page,
 				unsigned long private, struct page *hpage,
-				int force, bool offlining,
-				enum migrate_mode mode)
+				int force, enum migrate_mode mode)
 {
 	int rc = 0;
 	int *result = NULL;
@@ -1001,9 +987,8 @@ out:
  *
  * Return: Number of pages not migrated or error code.
  */
-int migrate_pages(struct list_head *from,
-		new_page_t get_new_page, unsigned long private, bool offlining,
-		enum migrate_mode mode, int reason)
+int migrate_pages(struct list_head *from, new_page_t get_new_page,
+		unsigned long private, enum migrate_mode mode, int reason)
 {
 	int retry = 1;
 	int nr_failed = 0;
@@ -1024,8 +1009,7 @@ int migrate_pages(struct list_head *from,
 			cond_resched();
 
 			rc = unmap_and_move(get_new_page, private,
-						page, pass > 2, offlining,
-						mode);
+						page, pass > 2, mode);
 
 			switch(rc) {
 			case -ENOMEM:
@@ -1058,15 +1042,13 @@ out:
 }
 
 int migrate_huge_page(struct page *hpage, new_page_t get_new_page,
-		      unsigned long private, bool offlining,
-		      enum migrate_mode mode)
+		      unsigned long private, enum migrate_mode mode)
 {
 	int pass, rc;
 
 	for (pass = 0; pass < 10; pass++) {
-		rc = unmap_and_move_huge_page(get_new_page,
-					      private, hpage, pass > 2, offlining,
-					      mode);
+		rc = unmap_and_move_huge_page(get_new_page, private,
+						hpage, pass > 2, mode);
 		switch (rc) {
 		case -ENOMEM:
 			goto out;
@@ -1152,7 +1134,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 			goto set_status;
 
 		/* Use PageReserved to check for zero page */
-		if (PageReserved(page) || PageKsm(page))
+		if (PageReserved(page))
 			goto put_and_set;
 
 		pp->page = page;
@@ -1189,8 +1171,7 @@ set_status:
 	err = 0;
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_page_node,
-				(unsigned long)pm, 0, MIGRATE_SYNC,
-				MR_SYSCALL);
+				(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
 			putback_lru_pages(&pagelist);
 	}
@@ -1314,7 +1295,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
 
 		err = -ENOENT;
 		/* Use PageReserved to check for zero page */
-		if (!page || PageReserved(page) || PageKsm(page))
+		if (!page || PageReserved(page))
 			goto set_status;
 
 		err = page_to_nid(page);
@@ -1461,7 +1442,7 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
  * pages. Currently it only checks the watermarks which crude
  */
 static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
-				   int nr_migrate_pages)
+				   unsigned long nr_migrate_pages)
 {
 	int z;
 	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
@@ -1497,7 +1478,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					  __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 	if (newpage)
-		page_xchg_last_nid(newpage, page_last_nid(page));
+		page_nid_xchg_last(newpage, page_nid_last(page));
 
 	return newpage;
 }
@@ -1557,39 +1538,40 @@ bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages)
 
 int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 {
-	int ret = 0;
+	int page_lru;
+
+	VM_BUG_ON(compound_order(page) && !PageTransHuge(page));
 
 	/* Avoid migrating to a node that is nearly full */
-	if (migrate_balanced_pgdat(pgdat, 1)) {
-		int page_lru;
+	if (!migrate_balanced_pgdat(pgdat, 1UL << compound_order(page)))
+		return 0;
 
-		if (isolate_lru_page(page)) {
-			put_page(page);
-			return 0;
-		}
+	if (isolate_lru_page(page))
+		return 0;
 
-		/* Page is isolated */
-		ret = 1;
-		page_lru = page_is_file_cache(page);
-		if (!PageTransHuge(page))
-			inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru);
-		else
-			mod_zone_page_state(page_zone(page),
-					NR_ISOLATED_ANON + page_lru,
-					HPAGE_PMD_NR);
+	/*
+	 * migrate_misplaced_transhuge_page() skips page migration's usual
+	 * check on page_count(), so we must do it here, now that the page
+	 * has been isolated: a GUP pin, or any other pin, prevents migration.
+	 * The expected page count is 3: 1 for page's mapcount and 1 for the
+	 * caller's pin and 1 for the reference taken by isolate_lru_page().
+	 */
+	if (PageTransHuge(page) && page_count(page) != 3) {
+		putback_lru_page(page);
+		return 0;
 	}
 
+	page_lru = page_is_file_cache(page);
+	mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru,
+				hpage_nr_pages(page));
+
 	/*
-	 * Page is either isolated or there is not enough space on the target
-	 * node. If isolated, then it has taken a reference count and the
-	 * callers reference can be safely dropped without the page
-	 * disappearing underneath us during migration. Otherwise the page is
-	 * not to be migrated but the callers reference should still be
-	 * dropped so it does not leak.
+	 * Isolating the page has taken another reference, so the
+	 * caller's reference can be safely dropped without the page
+	 * disappearing underneath us during migration.
 	 */
 	put_page(page);
-
-	return ret;
+	return 1;
 }
 
 /*
@@ -1600,7 +1582,7 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 int migrate_misplaced_page(struct page *page, int node)
 {
 	pg_data_t *pgdat = NODE_DATA(node);
-	int isolated = 0;
+	int isolated;
 	int nr_remaining;
 	LIST_HEAD(migratepages);
 
@@ -1608,42 +1590,43 @@ int migrate_misplaced_page(struct page *page, int node)
 	 * Don't migrate pages that are mapped in multiple processes.
 	 * TODO: Handle false sharing detection instead of this hammer
 	 */
-	if (page_mapcount(page) != 1) {
-		put_page(page);
+	if (page_mapcount(page) != 1)
 		goto out;
-	}
 
 	/*
 	 * 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!
 	 */
-	if (numamigrate_update_ratelimit(pgdat, 1)) {
-		put_page(page);
+	if (numamigrate_update_ratelimit(pgdat, 1))
 		goto out;
-	}
 
 	isolated = numamigrate_isolate_page(pgdat, page);
 	if (!isolated)
 		goto out;
 
 	list_add(&page->lru, &migratepages);
-	nr_remaining = migrate_pages(&migratepages,
-			alloc_misplaced_dst_page,
-			node, false, MIGRATE_ASYNC,
-			MR_NUMA_MISPLACED);
+	nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
+				     node, MIGRATE_ASYNC, MR_NUMA_MISPLACED);
 	if (nr_remaining) {
 		putback_lru_pages(&migratepages);
 		isolated = 0;
 	} else
 		count_vm_numa_event(NUMA_PAGE_MIGRATE);
 	BUG_ON(!list_empty(&migratepages));
-out:
 	return isolated;
+
+out:
+	put_page(page);
+	return 0;
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
 #if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+/*
+ * Migrates a THP to a given target node. page must be locked and is unlocked
+ * before returning.
+ */
 int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 				struct vm_area_struct *vma,
 				pmd_t *pmd, pmd_t entry,
@@ -1674,29 +1657,15 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 
 	new_page = alloc_pages_node(node,
 		(GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
-	if (!new_page) {
-		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-		goto out_dropref;
-	}
-	page_xchg_last_nid(new_page, page_last_nid(page));
+	if (!new_page)
+		goto out_fail;
 
-	isolated = numamigrate_isolate_page(pgdat, page);
+	page_nid_xchg_last(new_page, page_nid_last(page));
 
-	/*
-	 * Failing to isolate or a GUP pin prevents migration. The expected
-	 * page count is 2. 1 for anonymous pages without a mapping and 1
-	 * for the callers pin. If the page was isolated, the page will
-	 * need to be put back on the LRU.
-	 */
-	if (!isolated || page_count(page) != 2) {
-		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
+	isolated = numamigrate_isolate_page(pgdat, page);
+	if (!isolated) {
 		put_page(new_page);
-		if (isolated) {
-			putback_lru_page(page);
-			isolated = 0;
-			goto out;
-		}
-		goto out_keep_locked;
+		goto out_fail;
 	}
 
 	/* Prepare a page as a migration target */
@@ -1728,6 +1697,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		putback_lru_page(page);
 
 		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
+		isolated = 0;
 		goto out;
 	}
 
@@ -1772,9 +1742,11 @@ out:
 			-HPAGE_PMD_NR);
 	return isolated;
 
+out_fail:
+	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
+	unlock_page(page);
 	put_page(page);
-out_keep_locked:
 	return 0;
 }
 #endif /* CONFIG_NUMA_BALANCING */
diff --git a/mm/mincore.c b/mm/mincore.c
index 936b4cee8cb..da2be56a7b8 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -75,7 +75,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	/* shmem/tmpfs may return swap: account for swapcache page too. */
 	if (radix_tree_exceptional_entry(page)) {
 		swp_entry_t swap = radix_to_swp_entry(page);
-		page = find_get_page(&swapper_space, swap.val);
+		page = find_get_page(swap_address_space(swap), swap.val);
 	}
 #endif
 	if (page) {
@@ -135,7 +135,8 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			} else {
 #ifdef CONFIG_SWAP
 				pgoff = entry.val;
-				*vec = mincore_page(&swapper_space, pgoff);
+				*vec = mincore_page(swap_address_space(entry),
+					pgoff);
 #else
 				WARN_ON(1);
 				*vec = 1;
diff --git a/mm/mlock.c b/mm/mlock.c
index c9bd528b01d..e6638f565d4 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -155,13 +155,12 @@ void munlock_vma_page(struct page *page)
  *
  * vma->vm_mm->mmap_sem must be held for at least read.
  */
-static long __mlock_vma_pages_range(struct vm_area_struct *vma,
-				    unsigned long start, unsigned long end,
-				    int *nonblocking)
+long __mlock_vma_pages_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end, int *nonblocking)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long addr = start;
-	int nr_pages = (end - start) / PAGE_SIZE;
+	unsigned long nr_pages = (end - start) / PAGE_SIZE;
 	int gup_flags;
 
 	VM_BUG_ON(start & ~PAGE_MASK);
@@ -186,6 +185,10 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
 	if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
 		gup_flags |= FOLL_FORCE;
 
+	/*
+	 * We made sure addr is within a VMA, so the following will
+	 * not result in a stack expansion that recurses back here.
+	 */
 	return __get_user_pages(current, mm, addr, nr_pages, gup_flags,
 				NULL, NULL, nonblocking);
 }
@@ -202,56 +205,6 @@ static int __mlock_posix_error_return(long retval)
 	return retval;
 }
 
-/**
- * mlock_vma_pages_range() - mlock pages in specified vma range.
- * @vma - the vma containing the specfied address range
- * @start - starting address in @vma to mlock
- * @end   - end address [+1] in @vma to mlock
- *
- * For mmap()/mremap()/expansion of mlocked vma.
- *
- * return 0 on success for "normal" vmas.
- *
- * return number of pages [> 0] to be removed from locked_vm on success
- * of "special" vmas.
- */
-long mlock_vma_pages_range(struct vm_area_struct *vma,
-			unsigned long start, unsigned long end)
-{
-	int nr_pages = (end - start) / PAGE_SIZE;
-	BUG_ON(!(vma->vm_flags & VM_LOCKED));
-
-	/*
-	 * filter unlockable vmas
-	 */
-	if (vma->vm_flags & (VM_IO | VM_PFNMAP))
-		goto no_mlock;
-
-	if (!((vma->vm_flags & VM_DONTEXPAND) ||
-			is_vm_hugetlb_page(vma) ||
-			vma == get_gate_vma(current->mm))) {
-
-		__mlock_vma_pages_range(vma, start, end, NULL);
-
-		/* Hide errors from mmap() and other callers */
-		return 0;
-	}
-
-	/*
-	 * User mapped kernel pages or huge pages:
-	 * make these pages present to populate the ptes, but
-	 * fall thru' to reset VM_LOCKED--no need to unlock, and
-	 * return nr_pages so these don't get counted against task's
-	 * locked limit.  huge pages are already counted against
-	 * locked vm limit.
-	 */
-	make_pages_present(start, end);
-
-no_mlock:
-	vma->vm_flags &= ~VM_LOCKED;	/* and don't come back! */
-	return nr_pages;		/* error or pages NOT mlocked */
-}
-
 /*
  * munlock_vma_pages_range() - munlock all pages in the vma range.'
  * @vma - vma containing range to be munlock()ed.
@@ -303,7 +256,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
  *
  * Filters out "special" vmas -- VM_LOCKED never gets set for these, and
  * munlock is a no-op.  However, for some special vmas, we go ahead and
- * populate the ptes via make_pages_present().
+ * populate the ptes.
  *
  * For vmas that pass the filters, merge/split as appropriate.
  */
@@ -391,9 +344,9 @@ static int do_mlock(unsigned long start, size_t len, int on)
 
 		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
 
-		newflags = vma->vm_flags | VM_LOCKED;
-		if (!on)
-			newflags &= ~VM_LOCKED;
+		newflags = vma->vm_flags & ~VM_LOCKED;
+		if (on)
+			newflags |= VM_LOCKED | VM_POPULATE;
 
 		tmp = vma->vm_end;
 		if (tmp > end)
@@ -416,13 +369,20 @@ static int do_mlock(unsigned long start, size_t len, int on)
 	return error;
 }
 
-static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors)
+/*
+ * __mm_populate - populate and/or mlock pages within a range of address space.
+ *
+ * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
+ * flags. VMAs must be already marked with the desired vm_flags, and
+ * mmap_sem must not be held.
+ */
+int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long end, nstart, nend;
 	struct vm_area_struct *vma = NULL;
 	int locked = 0;
-	int ret = 0;
+	long ret = 0;
 
 	VM_BUG_ON(start & ~PAGE_MASK);
 	VM_BUG_ON(len != PAGE_ALIGN(len));
@@ -446,7 +406,8 @@ static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors)
 		 * range with the first VMA. Also, skip undesirable VMA types.
 		 */
 		nend = min(end, vma->vm_end);
-		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+		if ((vma->vm_flags & (VM_IO | VM_PFNMAP | VM_POPULATE)) !=
+		    VM_POPULATE)
 			continue;
 		if (nstart < vma->vm_start)
 			nstart = vma->vm_start;
@@ -498,7 +459,7 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 		error = do_mlock(start, len, 1);
 	up_write(&current->mm->mmap_sem);
 	if (!error)
-		error = do_mlock_pages(start, len, 0);
+		error = __mm_populate(start, len, 0);
 	return error;
 }
 
@@ -519,18 +480,18 @@ static int do_mlockall(int flags)
 	struct vm_area_struct * vma, * prev = NULL;
 
 	if (flags & MCL_FUTURE)
-		current->mm->def_flags |= VM_LOCKED;
+		current->mm->def_flags |= VM_LOCKED | VM_POPULATE;
 	else
-		current->mm->def_flags &= ~VM_LOCKED;
+		current->mm->def_flags &= ~(VM_LOCKED | VM_POPULATE);
 	if (flags == MCL_FUTURE)
 		goto out;
 
 	for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
 		vm_flags_t newflags;
 
-		newflags = vma->vm_flags | VM_LOCKED;
-		if (!(flags & MCL_CURRENT))
-			newflags &= ~VM_LOCKED;
+		newflags = vma->vm_flags & ~VM_LOCKED;
+		if (flags & MCL_CURRENT)
+			newflags |= VM_LOCKED | VM_POPULATE;
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
@@ -564,10 +525,8 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 	    capable(CAP_IPC_LOCK))
 		ret = do_mlockall(flags);
 	up_write(&current->mm->mmap_sem);
-	if (!ret && (flags & MCL_CURRENT)) {
-		/* Ignore errors */
-		do_mlock_pages(0, TASK_SIZE, 1);
-	}
+	if (!ret && (flags & MCL_CURRENT))
+		mm_populate(0, TASK_SIZE);
 out:
 	return ret;
 }
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 1ffd97ae26d..c280a02ea11 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -69,34 +69,41 @@ void __init mminit_verify_pageflags_layout(void)
 	unsigned long or_mask, add_mask;
 
 	shift = 8 * sizeof(unsigned long);
-	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH;
+	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_NID_SHIFT;
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
-		"Section %d Node %d Zone %d Flags %d\n",
+		"Section %d Node %d Zone %d Lastnid %d Flags %d\n",
 		SECTIONS_WIDTH,
 		NODES_WIDTH,
 		ZONES_WIDTH,
+		LAST_NID_WIDTH,
 		NR_PAGEFLAGS);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
-		"Section %d Node %d Zone %d\n",
+		"Section %d Node %d Zone %d Lastnid %d\n",
 		SECTIONS_SHIFT,
 		NODES_SHIFT,
-		ZONES_SHIFT);
-	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_offsets",
-		"Section %lu Node %lu Zone %lu\n",
+		ZONES_SHIFT,
+		LAST_NID_SHIFT);
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
+		"Section %lu Node %lu Zone %lu Lastnid %lu\n",
 		(unsigned long)SECTIONS_PGSHIFT,
 		(unsigned long)NODES_PGSHIFT,
-		(unsigned long)ZONES_PGSHIFT);
-	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_zoneid",
-		"Zone ID: %lu -> %lu\n",
-		(unsigned long)ZONEID_PGOFF,
-		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT));
+		(unsigned long)ZONES_PGSHIFT,
+		(unsigned long)LAST_NID_PGSHIFT);
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
+		"Node/Zone ID: %lu -> %lu\n",
+		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
+		(unsigned long)ZONEID_PGOFF);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage",
-		"location: %d -> %d unused %d -> %d flags %d -> %d\n",
+		"location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n",
 		shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0);
 #ifdef NODE_NOT_IN_PAGE_FLAGS
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
 		"Node not in page flags");
 #endif
+#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
+		"Last nid not in page flags");
+#endif
 
 	if (SECTIONS_WIDTH) {
 		shift -= SECTIONS_WIDTH;
diff --git a/mm/mmap.c b/mm/mmap.c
index 09da0b26498..318e121affd 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -144,7 +144,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		 */
 		free -= global_page_state(NR_SHMEM);
 
-		free += nr_swap_pages;
+		free += get_nr_swap_pages();
 
 		/*
 		 * Any slabs which are created with the
@@ -256,6 +256,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	unsigned long newbrk, oldbrk;
 	struct mm_struct *mm = current->mm;
 	unsigned long min_brk;
+	bool populate;
 
 	down_write(&mm->mmap_sem);
 
@@ -305,8 +306,15 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	/* Ok, looks good - let it rip. */
 	if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk)
 		goto out;
+
 set_brk:
 	mm->brk = brk;
+	populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
+	up_write(&mm->mmap_sem);
+	if (populate)
+		mm_populate(oldbrk, newbrk - oldbrk);
+	return brk;
+
 out:
 	retval = mm->brk;
 	up_write(&mm->mmap_sem);
@@ -801,7 +809,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 		anon_vma_interval_tree_post_update_vma(vma);
 		if (adjust_next)
 			anon_vma_interval_tree_post_update_vma(next);
-		anon_vma_unlock(anon_vma);
+		anon_vma_unlock_write(anon_vma);
 	}
 	if (mapping)
 		mutex_unlock(&mapping->i_mmap_mutex);
@@ -1154,12 +1162,15 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
 
 unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
-			unsigned long flags, unsigned long pgoff)
+			unsigned long flags, unsigned long pgoff,
+			unsigned long *populate)
 {
 	struct mm_struct * mm = current->mm;
 	struct inode *inode;
 	vm_flags_t vm_flags;
 
+	*populate = 0;
+
 	/*
 	 * Does the application expect PROT_READ to imply PROT_EXEC?
 	 *
@@ -1280,7 +1291,24 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 		}
 	}
 
-	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
+	/*
+	 * Set 'VM_NORESERVE' if we should not account for the
+	 * memory use of this mapping.
+	 */
+	if (flags & MAP_NORESERVE) {
+		/* We honor MAP_NORESERVE if allowed to overcommit */
+		if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
+			vm_flags |= VM_NORESERVE;
+
+		/* hugetlb applies strict overcommit unless MAP_NORESERVE */
+		if (file && is_file_hugepages(file))
+			vm_flags |= VM_NORESERVE;
+	}
+
+	addr = mmap_region(file, addr, len, vm_flags, pgoff);
+	if (!IS_ERR_VALUE(addr) && (vm_flags & VM_POPULATE))
+		*populate = len;
+	return addr;
 }
 
 SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
@@ -1395,8 +1423,7 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags)
 }
 
 unsigned long mmap_region(struct file *file, unsigned long addr,
-			  unsigned long len, unsigned long flags,
-			  vm_flags_t vm_flags, unsigned long pgoff)
+		unsigned long len, vm_flags_t vm_flags, unsigned long pgoff)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
@@ -1420,20 +1447,6 @@ munmap_back:
 		return -ENOMEM;
 
 	/*
-	 * Set 'VM_NORESERVE' if we should not account for the
-	 * memory use of this mapping.
-	 */
-	if ((flags & MAP_NORESERVE)) {
-		/* We honor MAP_NORESERVE if allowed to overcommit */
-		if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
-			vm_flags |= VM_NORESERVE;
-
-		/* hugetlb applies strict overcommit unless MAP_NORESERVE */
-		if (file && is_file_hugepages(file))
-			vm_flags |= VM_NORESERVE;
-	}
-
-	/*
 	 * Private writable mapping: check memory availability
 	 */
 	if (accountable_mapping(file, vm_flags)) {
@@ -1531,10 +1544,12 @@ out:
 
 	vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
 	if (vm_flags & VM_LOCKED) {
-		if (!mlock_vma_pages_range(vma, addr, addr + len))
+		if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) ||
+					vma == get_gate_vma(current->mm)))
 			mm->locked_vm += (len >> PAGE_SHIFT);
-	} else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
-		make_pages_present(addr, addr + len);
+		else
+			vma->vm_flags &= ~VM_LOCKED;
+	}
 
 	if (file)
 		uprobe_mmap(vma);
@@ -2187,9 +2202,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 		return vma;
 	if (!prev || expand_stack(prev, addr))
 		return NULL;
-	if (prev->vm_flags & VM_LOCKED) {
-		mlock_vma_pages_range(prev, addr, prev->vm_end);
-	}
+	if (prev->vm_flags & VM_LOCKED)
+		__mlock_vma_pages_range(prev, addr, prev->vm_end, NULL);
 	return prev;
 }
 #else
@@ -2215,9 +2229,8 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr)
 	start = vma->vm_start;
 	if (expand_stack(vma, addr))
 		return NULL;
-	if (vma->vm_flags & VM_LOCKED) {
-		mlock_vma_pages_range(vma, addr, start);
-	}
+	if (vma->vm_flags & VM_LOCKED)
+		__mlock_vma_pages_range(vma, addr, start, NULL);
 	return vma;
 }
 #endif
@@ -2590,10 +2603,8 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 out:
 	perf_event_mmap(vma);
 	mm->total_vm += len >> PAGE_SHIFT;
-	if (flags & VM_LOCKED) {
-		if (!mlock_vma_pages_range(vma, addr, addr + len))
-			mm->locked_vm += (len >> PAGE_SHIFT);
-	}
+	if (flags & VM_LOCKED)
+		mm->locked_vm += (len >> PAGE_SHIFT);
 	return addr;
 }
 
@@ -2601,10 +2612,14 @@ unsigned long vm_brk(unsigned long addr, unsigned long len)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long ret;
+	bool populate;
 
 	down_write(&mm->mmap_sem);
 	ret = do_brk(addr, len);
+	populate = ((mm->def_flags & VM_LOCKED) != 0);
 	up_write(&mm->mmap_sem);
+	if (populate)
+		mm_populate(addr, len);
 	return ret;
 }
 EXPORT_SYMBOL(vm_brk);
@@ -3002,7 +3017,7 @@ static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
 		if (!__test_and_clear_bit(0, (unsigned long *)
 					  &anon_vma->root->rb_root.rb_node))
 			BUG();
-		anon_vma_unlock(anon_vma);
+		anon_vma_unlock_write(anon_vma);
 	}
 }
 
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 8a5ac8c686b..2175fb0d501 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -37,49 +37,51 @@ static struct srcu_struct srcu;
 void __mmu_notifier_release(struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
 	int id;
 
 	/*
-	 * SRCU here will block mmu_notifier_unregister until
-	 * ->release returns.
+	 * srcu_read_lock() here will block synchronize_srcu() in
+	 * mmu_notifier_unregister() until all registered
+	 * ->release() callouts this function makes have
+	 * returned.
 	 */
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist)
-		/*
-		 * if ->release runs before mmu_notifier_unregister it
-		 * must be handled as it's the only way for the driver
-		 * to flush all existing sptes and stop the driver
-		 * from establishing any more sptes before all the
-		 * pages in the mm are freed.
-		 */
-		if (mn->ops->release)
-			mn->ops->release(mn, mm);
-	srcu_read_unlock(&srcu, id);
-
 	spin_lock(&mm->mmu_notifier_mm->lock);
 	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
 		mn = hlist_entry(mm->mmu_notifier_mm->list.first,
 				 struct mmu_notifier,
 				 hlist);
+
 		/*
-		 * We arrived before mmu_notifier_unregister so
-		 * mmu_notifier_unregister will do nothing other than
-		 * to wait ->release to finish and
-		 * mmu_notifier_unregister to return.
+		 * Unlink.  This will prevent mmu_notifier_unregister()
+		 * from also making the ->release() callout.
 		 */
 		hlist_del_init_rcu(&mn->hlist);
+		spin_unlock(&mm->mmu_notifier_mm->lock);
+
+		/*
+		 * Clear sptes. (see 'release' description in mmu_notifier.h)
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+
+		spin_lock(&mm->mmu_notifier_mm->lock);
 	}
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
 	/*
-	 * synchronize_srcu here prevents mmu_notifier_release to
-	 * return to exit_mmap (which would proceed freeing all pages
-	 * in the mm) until the ->release method returns, if it was
-	 * invoked by mmu_notifier_unregister.
-	 *
-	 * The mmu_notifier_mm can't go away from under us because one
-	 * mm_count is hold by exit_mmap.
+	 * All callouts to ->release() which we have done are complete.
+	 * Allow synchronize_srcu() in mmu_notifier_unregister() to complete
+	 */
+	srcu_read_unlock(&srcu, id);
+
+	/*
+	 * mmu_notifier_unregister() may have unlinked a notifier and may
+	 * still be calling out to it.	Additionally, other notifiers
+	 * may have been active via vmtruncate() et. al. Block here
+	 * to ensure that all notifier callouts for this mm have been
+	 * completed and the sptes are really cleaned up before returning
+	 * to exit_mmap().
 	 */
 	synchronize_srcu(&srcu);
 }
@@ -170,6 +172,7 @@ void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
 	}
 	srcu_read_unlock(&srcu, id);
 }
+EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_start);
 
 void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
@@ -185,6 +188,7 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 	}
 	srcu_read_unlock(&srcu, id);
 }
+EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end);
 
 static int do_mmu_notifier_register(struct mmu_notifier *mn,
 				    struct mm_struct *mm,
@@ -294,31 +298,31 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
+	spin_lock(&mm->mmu_notifier_mm->lock);
 	if (!hlist_unhashed(&mn->hlist)) {
-		/*
-		 * SRCU here will force exit_mmap to wait ->release to finish
-		 * before freeing the pages.
-		 */
 		int id;
 
-		id = srcu_read_lock(&srcu);
 		/*
-		 * exit_mmap will block in mmu_notifier_release to
-		 * guarantee ->release is called before freeing the
-		 * pages.
+		 * Ensure we synchronize up with __mmu_notifier_release().
 		 */
+		id = srcu_read_lock(&srcu);
+
+		hlist_del_rcu(&mn->hlist);
+		spin_unlock(&mm->mmu_notifier_mm->lock);
+
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
-		srcu_read_unlock(&srcu, id);
 
-		spin_lock(&mm->mmu_notifier_mm->lock);
-		hlist_del_rcu(&mn->hlist);
+		/*
+		 * Allow __mmu_notifier_release() to complete.
+		 */
+		srcu_read_unlock(&srcu, id);
+	} else
 		spin_unlock(&mm->mmu_notifier_mm->lock);
-	}
 
 	/*
-	 * Wait any running method to finish, of course including
-	 * ->release if it was run by mmu_notifier_relase instead of us.
+	 * Wait for any running method to finish, including ->release() if it
+	 * was run by __mmu_notifier_release() instead of us.
 	 */
 	synchronize_srcu(&srcu);
 
diff --git a/mm/mmzone.c b/mm/mmzone.c
index 4596d81b89b..2ac0afbd68f 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -1,7 +1,7 @@
 /*
  * linux/mm/mmzone.c
  *
- * management codes for pgdats and zones.
+ * management codes for pgdats, zones and page flags
  */
 
 
@@ -96,3 +96,21 @@ void lruvec_init(struct lruvec *lruvec)
 	for_each_lru(lru)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
 }
+
+#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NID_NOT_IN_PAGE_FLAGS)
+int page_nid_xchg_last(struct page *page, int nid)
+{
+	unsigned long old_flags, flags;
+	int last_nid;
+
+	do {
+		old_flags = flags = page->flags;
+		last_nid = page_nid_last(page);
+
+		flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
+		flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
+	} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));
+
+	return last_nid;
+}
+#endif
diff --git a/mm/mremap.c b/mm/mremap.c
index f9766f46029..463a25705ac 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -135,7 +135,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	pte_unmap(new_pte - 1);
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (anon_vma)
-		anon_vma_unlock(anon_vma);
+		anon_vma_unlock_write(anon_vma);
 	if (mapping)
 		mutex_unlock(&mapping->i_mmap_mutex);
 }
@@ -209,7 +209,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 
 static unsigned long move_vma(struct vm_area_struct *vma,
 		unsigned long old_addr, unsigned long old_len,
-		unsigned long new_len, unsigned long new_addr)
+		unsigned long new_len, unsigned long new_addr, bool *locked)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *new_vma;
@@ -300,9 +300,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 
 	if (vm_flags & VM_LOCKED) {
 		mm->locked_vm += new_len >> PAGE_SHIFT;
-		if (new_len > old_len)
-			mlock_vma_pages_range(new_vma, new_addr + old_len,
-						       new_addr + new_len);
+		*locked = true;
 	}
 
 	return new_addr;
@@ -367,9 +365,8 @@ Eagain:
 	return ERR_PTR(-EAGAIN);
 }
 
-static unsigned long mremap_to(unsigned long addr,
-	unsigned long old_len, unsigned long new_addr,
-	unsigned long new_len)
+static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
+		unsigned long new_addr, unsigned long new_len, bool *locked)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
@@ -419,7 +416,7 @@ static unsigned long mremap_to(unsigned long addr,
 	if (ret & ~PAGE_MASK)
 		goto out1;
 
-	ret = move_vma(vma, addr, old_len, new_len, new_addr);
+	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked);
 	if (!(ret & ~PAGE_MASK))
 		goto out;
 out1:
@@ -457,6 +454,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	struct vm_area_struct *vma;
 	unsigned long ret = -EINVAL;
 	unsigned long charged = 0;
+	bool locked = false;
 
 	down_write(&current->mm->mmap_sem);
 
@@ -479,7 +477,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 
 	if (flags & MREMAP_FIXED) {
 		if (flags & MREMAP_MAYMOVE)
-			ret = mremap_to(addr, old_len, new_addr, new_len);
+			ret = mremap_to(addr, old_len, new_addr, new_len,
+					&locked);
 		goto out;
 	}
 
@@ -521,8 +520,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 			vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages);
 			if (vma->vm_flags & VM_LOCKED) {
 				mm->locked_vm += pages;
-				mlock_vma_pages_range(vma, addr + old_len,
-						   addr + new_len);
+				locked = true;
+				new_addr = addr;
 			}
 			ret = addr;
 			goto out;
@@ -548,11 +547,13 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 			goto out;
 		}
 
-		ret = move_vma(vma, addr, old_len, new_len, new_addr);
+		ret = move_vma(vma, addr, old_len, new_len, new_addr, &locked);
 	}
 out:
 	if (ret & ~PAGE_MASK)
 		vm_unacct_memory(charged);
 	up_write(&current->mm->mmap_sem);
+	if (locked && new_len > old_len)
+		mm_populate(new_addr + old_len, new_len - old_len);
 	return ret;
 }
diff --git a/mm/nommu.c b/mm/nommu.c
index b20db4e2226..da0d210fd40 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -140,10 +140,10 @@ unsigned int kobjsize(const void *objp)
 	return PAGE_SIZE << compound_order(page);
 }
 
-int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		     unsigned long start, int nr_pages, unsigned int foll_flags,
-		     struct page **pages, struct vm_area_struct **vmas,
-		     int *retry)
+long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		      unsigned long start, unsigned long nr_pages,
+		      unsigned int foll_flags, struct page **pages,
+		      struct vm_area_struct **vmas, int *nonblocking)
 {
 	struct vm_area_struct *vma;
 	unsigned long vm_flags;
@@ -190,9 +190,10 @@ finish_or_fault:
  *   slab page or a secondary page from a compound page
  * - don't permit access to VMAs that don't support it, such as I/O mappings
  */
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-	unsigned long start, int nr_pages, int write, int force,
-	struct page **pages, struct vm_area_struct **vmas)
+long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		    unsigned long start, unsigned long nr_pages,
+		    int write, int force, struct page **pages,
+		    struct vm_area_struct **vmas)
 {
 	int flags = 0;
 
@@ -1250,7 +1251,8 @@ unsigned long do_mmap_pgoff(struct file *file,
 			    unsigned long len,
 			    unsigned long prot,
 			    unsigned long flags,
-			    unsigned long pgoff)
+			    unsigned long pgoff,
+			    unsigned long *populate)
 {
 	struct vm_area_struct *vma;
 	struct vm_region *region;
@@ -1260,6 +1262,8 @@ unsigned long do_mmap_pgoff(struct file *file,
 
 	kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
 
+	*populate = 0;
+
 	/* decide whether we should attempt the mapping, and if so what sort of
 	 * mapping */
 	ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
@@ -1815,9 +1819,11 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	return ret;
 }
 
-struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
-			unsigned int foll_flags)
+struct page *follow_page_mask(struct vm_area_struct *vma,
+			      unsigned long address, unsigned int flags,
+			      unsigned int *page_mask)
 {
+	*page_mask = 0;
 	return NULL;
 }
 
@@ -1904,7 +1910,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		 */
 		free -= global_page_state(NR_SHMEM);
 
-		free += nr_swap_pages;
+		free += get_nr_swap_pages();
 
 		/*
 		 * Any slabs which are created with the
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 0399f146ae4..79e451a78c9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -386,8 +386,10 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 	cpuset_print_task_mems_allowed(current);
 	task_unlock(current);
 	dump_stack();
-	mem_cgroup_print_oom_info(memcg, p);
-	show_mem(SHOW_MEM_FILTER_NODES);
+	if (memcg)
+		mem_cgroup_print_oom_info(memcg, p);
+	else
+		show_mem(SHOW_MEM_FILTER_NODES);
 	if (sysctl_oom_dump_tasks)
 		dump_tasks(memcg, nodemask);
 }
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7300c9d5e1d..cdc377c456c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -241,6 +241,9 @@ static unsigned long global_dirtyable_memory(void)
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);
 
+	/* Subtract min_free_kbytes */
+	x -= min_t(unsigned long, x, min_free_kbytes >> (PAGE_SHIFT - 10));
+
 	return x + 1;	/* Ensure that we never return 0 */
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d1107adf174..e9075fdef69 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -202,11 +202,18 @@ static unsigned long __meminitdata nr_all_pages;
 static unsigned long __meminitdata dma_reserve;
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+/* Movable memory ranges, will also be used by memblock subsystem. */
+struct movablemem_map movablemem_map = {
+	.acpi = false,
+	.nr_map = 0,
+};
+
 static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
 static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
 static unsigned long __initdata required_kernelcore;
 static unsigned long __initdata required_movablecore;
 static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
+static unsigned long __meminitdata zone_movable_limit[MAX_NUMNODES];
 
 /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
 int movable_zone;
@@ -240,15 +247,20 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 	int ret = 0;
 	unsigned seq;
 	unsigned long pfn = page_to_pfn(page);
+	unsigned long sp, start_pfn;
 
 	do {
 		seq = zone_span_seqbegin(zone);
-		if (pfn >= zone->zone_start_pfn + zone->spanned_pages)
-			ret = 1;
-		else if (pfn < zone->zone_start_pfn)
+		start_pfn = zone->zone_start_pfn;
+		sp = zone->spanned_pages;
+		if (!zone_spans_pfn(zone, pfn))
 			ret = 1;
 	} while (zone_span_seqretry(zone, seq));
 
+	if (ret)
+		pr_err("page %lu outside zone [ %lu - %lu ]\n",
+			pfn, start_pfn, start_pfn + sp);
+
 	return ret;
 }
 
@@ -288,7 +300,7 @@ static void bad_page(struct page *page)
 
 	/* Don't complain about poisoned pages */
 	if (PageHWPoison(page)) {
-		reset_page_mapcount(page); /* remove PageBuddy */
+		page_mapcount_reset(page); /* remove PageBuddy */
 		return;
 	}
 
@@ -320,7 +332,7 @@ static void bad_page(struct page *page)
 	dump_stack();
 out:
 	/* Leave bad fields for debug, except PageBuddy could make trouble */
-	reset_page_mapcount(page); /* remove PageBuddy */
+	page_mapcount_reset(page); /* remove PageBuddy */
 	add_taint(TAINT_BAD_PAGE);
 }
 
@@ -533,6 +545,8 @@ static inline void __free_one_page(struct page *page,
 	unsigned long uninitialized_var(buddy_idx);
 	struct page *buddy;
 
+	VM_BUG_ON(!zone_is_initialized(zone));
+
 	if (unlikely(PageCompound(page)))
 		if (unlikely(destroy_compound_page(page, order)))
 			return;
@@ -606,7 +620,7 @@ static inline int free_pages_check(struct page *page)
 		bad_page(page);
 		return 1;
 	}
-	reset_page_last_nid(page);
+	page_nid_reset_last(page);
 	if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
 		page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	return 0;
@@ -666,7 +680,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
 			__free_one_page(page, zone, 0, mt);
 			trace_mm_page_pcpu_drain(page, 0, mt);
-			if (likely(get_pageblock_migratetype(page) != MIGRATE_ISOLATE)) {
+			if (likely(!is_migrate_isolate_page(page))) {
 				__mod_zone_page_state(zone, NR_FREE_PAGES, 1);
 				if (is_migrate_cma(mt))
 					__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1);
@@ -684,7 +698,7 @@ static void free_one_page(struct zone *zone, struct page *page, int order,
 	zone->pages_scanned = 0;
 
 	__free_one_page(page, zone, order, migratetype);
-	if (unlikely(migratetype != MIGRATE_ISOLATE))
+	if (unlikely(!is_migrate_isolate(migratetype)))
 		__mod_zone_freepage_state(zone, 1 << order, migratetype);
 	spin_unlock(&zone->lock);
 }
@@ -916,7 +930,9 @@ static int fallbacks[MIGRATE_TYPES][4] = {
 	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE,   MIGRATE_RESERVE },
 #endif
 	[MIGRATE_RESERVE]     = { MIGRATE_RESERVE }, /* Never used */
+#ifdef CONFIG_MEMORY_ISOLATION
 	[MIGRATE_ISOLATE]     = { MIGRATE_RESERVE }, /* Never used */
+#endif
 };
 
 /*
@@ -981,9 +997,9 @@ int move_freepages_block(struct zone *zone, struct page *page,
 	end_pfn = start_pfn + pageblock_nr_pages - 1;
 
 	/* Do not cross zone boundaries */
-	if (start_pfn < zone->zone_start_pfn)
+	if (!zone_spans_pfn(zone, start_pfn))
 		start_page = page;
-	if (end_pfn >= zone->zone_start_pfn + zone->spanned_pages)
+	if (!zone_spans_pfn(zone, end_pfn))
 		return 0;
 
 	return move_freepages(zone, start_page, end_page, migratetype);
@@ -1142,7 +1158,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			list_add_tail(&page->lru, list);
 		if (IS_ENABLED(CONFIG_CMA)) {
 			mt = get_pageblock_migratetype(page);
-			if (!is_migrate_cma(mt) && mt != MIGRATE_ISOLATE)
+			if (!is_migrate_cma(mt) && !is_migrate_isolate(mt))
 				mt = migratetype;
 		}
 		set_freepage_migratetype(page, mt);
@@ -1277,7 +1293,7 @@ void mark_free_pages(struct zone *zone)
 
 	spin_lock_irqsave(&zone->lock, flags);
 
-	max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	max_zone_pfn = zone_end_pfn(zone);
 	for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
 		if (pfn_valid(pfn)) {
 			struct page *page = pfn_to_page(pfn);
@@ -1326,7 +1342,7 @@ void free_hot_cold_page(struct page *page, int cold)
 	 * excessively into the page allocator
 	 */
 	if (migratetype >= MIGRATE_PCPTYPES) {
-		if (unlikely(migratetype == MIGRATE_ISOLATE)) {
+		if (unlikely(is_migrate_isolate(migratetype))) {
 			free_one_page(zone, page, 0, migratetype);
 			goto out;
 		}
@@ -1400,7 +1416,7 @@ static int __isolate_free_page(struct page *page, unsigned int order)
 	zone = page_zone(page);
 	mt = get_pageblock_migratetype(page);
 
-	if (mt != MIGRATE_ISOLATE) {
+	if (!is_migrate_isolate(mt)) {
 		/* Obey watermarks as if the page was being allocated */
 		watermark = low_wmark_pages(zone) + (1 << order);
 		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
@@ -1419,7 +1435,7 @@ static int __isolate_free_page(struct page *page, unsigned int order)
 		struct page *endpage = page + (1 << order) - 1;
 		for (; page < endpage; page += pageblock_nr_pages) {
 			int mt = get_pageblock_migratetype(page);
-			if (mt != MIGRATE_ISOLATE && !is_migrate_cma(mt))
+			if (!is_migrate_isolate(mt) && !is_migrate_cma(mt))
 				set_pageblock_migratetype(page,
 							  MIGRATE_MOVABLE);
 		}
@@ -2615,10 +2631,17 @@ retry_cpuset:
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
 			zonelist, high_zoneidx, alloc_flags,
 			preferred_zone, migratetype);
-	if (unlikely(!page))
+	if (unlikely(!page)) {
+		/*
+		 * Runtime PM, block IO and its error handling path
+		 * can deadlock because I/O on the device might not
+		 * complete.
+		 */
+		gfp_mask = memalloc_noio_flags(gfp_mask);
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
+	}
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
 
@@ -2790,18 +2813,27 @@ void free_pages_exact(void *virt, size_t size)
 }
 EXPORT_SYMBOL(free_pages_exact);
 
-static unsigned int nr_free_zone_pages(int offset)
+/**
+ * nr_free_zone_pages - count number of pages beyond high watermark
+ * @offset: The zone index of the highest zone
+ *
+ * nr_free_zone_pages() counts the number of counts pages which are beyond the
+ * high watermark within all zones at or below a given zone index.  For each
+ * zone, the number of pages is calculated as:
+ *     present_pages - high_pages
+ */
+static unsigned long nr_free_zone_pages(int offset)
 {
 	struct zoneref *z;
 	struct zone *zone;
 
 	/* Just pick one node, since fallback list is circular */
-	unsigned int sum = 0;
+	unsigned long sum = 0;
 
 	struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
 
 	for_each_zone_zonelist(zone, z, zonelist, offset) {
-		unsigned long size = zone->present_pages;
+		unsigned long size = zone->managed_pages;
 		unsigned long high = high_wmark_pages(zone);
 		if (size > high)
 			sum += size - high;
@@ -2810,19 +2842,25 @@ static unsigned int nr_free_zone_pages(int offset)
 	return sum;
 }
 
-/*
- * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL
+/**
+ * nr_free_buffer_pages - count number of pages beyond high watermark
+ *
+ * nr_free_buffer_pages() counts the number of pages which are beyond the high
+ * watermark within ZONE_DMA and ZONE_NORMAL.
  */
-unsigned int nr_free_buffer_pages(void)
+unsigned long nr_free_buffer_pages(void)
 {
 	return nr_free_zone_pages(gfp_zone(GFP_USER));
 }
 EXPORT_SYMBOL_GPL(nr_free_buffer_pages);
 
-/*
- * Amount of free RAM allocatable within all zones
+/**
+ * nr_free_pagecache_pages - count number of pages beyond high watermark
+ *
+ * nr_free_pagecache_pages() counts the number of pages which are beyond the
+ * high watermark within all zones.
  */
-unsigned int nr_free_pagecache_pages(void)
+unsigned long nr_free_pagecache_pages(void)
 {
 	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
 }
@@ -2854,7 +2892,7 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 	val->totalram = pgdat->node_present_pages;
 	val->freeram = node_page_state(nid, NR_FREE_PAGES);
 #ifdef CONFIG_HIGHMEM
-	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
+	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages;
 	val->freehigh = zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM],
 			NR_FREE_PAGES);
 #else
@@ -2897,7 +2935,9 @@ static void show_migration_types(unsigned char type)
 #ifdef CONFIG_CMA
 		[MIGRATE_CMA]		= 'C',
 #endif
+#ifdef CONFIG_MEMORY_ISOLATION
 		[MIGRATE_ISOLATE]	= 'I',
+#endif
 	};
 	char tmp[MIGRATE_TYPES + 1];
 	char *p = tmp;
@@ -3236,7 +3276,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 {
 	int n, val;
 	int min_val = INT_MAX;
-	int best_node = -1;
+	int best_node = NUMA_NO_NODE;
 	const struct cpumask *tmp = cpumask_of_node(0);
 
 	/* Use the local node if we haven't already */
@@ -3780,7 +3820,7 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 	 * the block.
 	 */
 	start_pfn = zone->zone_start_pfn;
-	end_pfn = start_pfn + zone->spanned_pages;
+	end_pfn = zone_end_pfn(zone);
 	start_pfn = roundup(start_pfn, pageblock_nr_pages);
 	reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
 							pageblock_order;
@@ -3876,8 +3916,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		set_page_links(page, zone, nid, pfn);
 		mminit_verify_page_links(page, zone, nid, pfn);
 		init_page_count(page);
-		reset_page_mapcount(page);
-		reset_page_last_nid(page);
+		page_mapcount_reset(page);
+		page_nid_reset_last(page);
 		SetPageReserved(page);
 		/*
 		 * Mark the block movable so that blocks are reserved for
@@ -3894,7 +3934,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		 * pfn out of zone.
 		 */
 		if ((z->zone_start_pfn <= pfn)
-		    && (pfn < z->zone_start_pfn + z->spanned_pages)
+		    && (pfn < zone_end_pfn(z))
 		    && !(pfn & (pageblock_nr_pages - 1)))
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 
@@ -3932,7 +3972,7 @@ static int __meminit zone_batchsize(struct zone *zone)
 	 *
 	 * OK, so we don't know how big the cache is.  So guess.
 	 */
-	batch = zone->present_pages / 1024;
+	batch = zone->managed_pages / 1024;
 	if (batch * PAGE_SIZE > 512 * 1024)
 		batch = (512 * 1024) / PAGE_SIZE;
 	batch /= 4;		/* We effectively *= 4 below */
@@ -4016,7 +4056,7 @@ static void __meminit setup_zone_pageset(struct zone *zone)
 
 		if (percpu_pagelist_fraction)
 			setup_pagelist_highmark(pcp,
-				(zone->present_pages /
+				(zone->managed_pages /
 					percpu_pagelist_fraction));
 	}
 }
@@ -4372,6 +4412,77 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
 }
 
+/**
+ * sanitize_zone_movable_limit - Sanitize the zone_movable_limit array.
+ *
+ * zone_movable_limit is initialized as 0. This function will try to get
+ * the first ZONE_MOVABLE pfn of each node from movablemem_map, and
+ * assigne them to zone_movable_limit.
+ * zone_movable_limit[nid] == 0 means no limit for the node.
+ *
+ * Note: Each range is represented as [start_pfn, end_pfn)
+ */
+static void __meminit sanitize_zone_movable_limit(void)
+{
+	int map_pos = 0, i, nid;
+	unsigned long start_pfn, end_pfn;
+
+	if (!movablemem_map.nr_map)
+		return;
+
+	/* Iterate all ranges from minimum to maximum */
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+		/*
+		 * If we have found lowest pfn of ZONE_MOVABLE of the node
+		 * specified by user, just go on to check next range.
+		 */
+		if (zone_movable_limit[nid])
+			continue;
+
+#ifdef CONFIG_ZONE_DMA
+		/* Skip DMA memory. */
+		if (start_pfn < arch_zone_highest_possible_pfn[ZONE_DMA])
+			start_pfn = arch_zone_highest_possible_pfn[ZONE_DMA];
+#endif
+
+#ifdef CONFIG_ZONE_DMA32
+		/* Skip DMA32 memory. */
+		if (start_pfn < arch_zone_highest_possible_pfn[ZONE_DMA32])
+			start_pfn = arch_zone_highest_possible_pfn[ZONE_DMA32];
+#endif
+
+#ifdef CONFIG_HIGHMEM
+		/* Skip lowmem if ZONE_MOVABLE is highmem. */
+		if (zone_movable_is_highmem() &&
+		    start_pfn < arch_zone_lowest_possible_pfn[ZONE_HIGHMEM])
+			start_pfn = arch_zone_lowest_possible_pfn[ZONE_HIGHMEM];
+#endif
+
+		if (start_pfn >= end_pfn)
+			continue;
+
+		while (map_pos < movablemem_map.nr_map) {
+			if (end_pfn <= movablemem_map.map[map_pos].start_pfn)
+				break;
+
+			if (start_pfn >= movablemem_map.map[map_pos].end_pfn) {
+				map_pos++;
+				continue;
+			}
+
+			/*
+			 * The start_pfn of ZONE_MOVABLE is either the minimum
+			 * pfn specified by movablemem_map, or 0, which means
+			 * the node has no ZONE_MOVABLE.
+			 */
+			zone_movable_limit[nid] = max(start_pfn,
+					movablemem_map.map[map_pos].start_pfn);
+
+			break;
+		}
+	}
+}
+
 #else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
 					unsigned long zone_type,
@@ -4389,7 +4500,6 @@ static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
 
 	return zholes_size[zone_type];
 }
-
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
@@ -4573,7 +4683,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		nr_all_pages += freesize;
 
 		zone->spanned_pages = size;
-		zone->present_pages = freesize;
+		zone->present_pages = realsize;
 		/*
 		 * Set an approximate value for lowmem here, it will be adjusted
 		 * when the bootmem allocator frees pages into the buddy system.
@@ -4625,7 +4735,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 		 * for the buddy allocator to function correctly.
 		 */
 		start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
-		end = pgdat->node_start_pfn + pgdat->node_spanned_pages;
+		end = pgdat_end_pfn(pgdat);
 		end = ALIGN(end, MAX_ORDER_NR_PAGES);
 		size =  (end - start) * sizeof(struct page);
 		map = alloc_remap(pgdat->node_id, size);
@@ -4831,12 +4941,19 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 		required_kernelcore = max(required_kernelcore, corepages);
 	}
 
-	/* If kernelcore was not specified, there is no ZONE_MOVABLE */
-	if (!required_kernelcore)
+	/*
+	 * If neither kernelcore/movablecore nor movablemem_map is specified,
+	 * there is no ZONE_MOVABLE. But if movablemem_map is specified, the
+	 * start pfn of ZONE_MOVABLE has been stored in zone_movable_limit[].
+	 */
+	if (!required_kernelcore) {
+		if (movablemem_map.nr_map)
+			memcpy(zone_movable_pfn, zone_movable_limit,
+				sizeof(zone_movable_pfn));
 		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:
@@ -4864,10 +4981,24 @@ restart:
 		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
 			unsigned long size_pages;
 
+			/*
+			 * Find more memory for kernelcore in
+			 * [zone_movable_pfn[nid], zone_movable_limit[nid]).
+			 */
 			start_pfn = max(start_pfn, zone_movable_pfn[nid]);
 			if (start_pfn >= end_pfn)
 				continue;
 
+			if (zone_movable_limit[nid]) {
+				end_pfn = min(end_pfn, zone_movable_limit[nid]);
+				/* No range left for kernelcore in this node */
+				if (start_pfn >= end_pfn) {
+					zone_movable_pfn[nid] =
+							zone_movable_limit[nid];
+					break;
+				}
+			}
+
 			/* Account for what is only usable for kernelcore */
 			if (start_pfn < usable_startpfn) {
 				unsigned long kernel_pages;
@@ -4927,12 +5058,12 @@ restart:
 	if (usable_nodes && required_kernelcore > usable_nodes)
 		goto restart;
 
+out:
 	/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
 	for (nid = 0; nid < MAX_NUMNODES; nid++)
 		zone_movable_pfn[nid] =
 			roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
 
-out:
 	/* restore the node_state */
 	node_states[N_MEMORY] = saved_node_state;
 }
@@ -4995,6 +5126,8 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 
 	/* Find the PFNs that ZONE_MOVABLE begins at in each node */
 	memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
+	find_usable_zone_for_movable();
+	sanitize_zone_movable_limit();
 	find_zone_movable_pfns_for_nodes();
 
 	/* Print out the zone ranges */
@@ -5078,6 +5211,181 @@ static int __init cmdline_parse_movablecore(char *p)
 early_param("kernelcore", cmdline_parse_kernelcore);
 early_param("movablecore", cmdline_parse_movablecore);
 
+/**
+ * movablemem_map_overlap() - Check if a range overlaps movablemem_map.map[].
+ * @start_pfn:	start pfn of the range to be checked
+ * @end_pfn: 	end pfn of the range to be checked (exclusive)
+ *
+ * This function checks if a given memory range [start_pfn, end_pfn) overlaps
+ * the movablemem_map.map[] array.
+ *
+ * Return: index of the first overlapped element in movablemem_map.map[]
+ *         or -1 if they don't overlap each other.
+ */
+int __init movablemem_map_overlap(unsigned long start_pfn,
+				   unsigned long end_pfn)
+{
+	int overlap;
+
+	if (!movablemem_map.nr_map)
+		return -1;
+
+	for (overlap = 0; overlap < movablemem_map.nr_map; overlap++)
+		if (start_pfn < movablemem_map.map[overlap].end_pfn)
+			break;
+
+	if (overlap == movablemem_map.nr_map ||
+	    end_pfn <= movablemem_map.map[overlap].start_pfn)
+		return -1;
+
+	return overlap;
+}
+
+/**
+ * insert_movablemem_map - Insert a memory range in to movablemem_map.map.
+ * @start_pfn:	start pfn of the range
+ * @end_pfn:	end pfn of the range
+ *
+ * This function will also merge the overlapped ranges, and sort the array
+ * by start_pfn in monotonic increasing order.
+ */
+void __init insert_movablemem_map(unsigned long start_pfn,
+				  unsigned long end_pfn)
+{
+	int pos, overlap;
+
+	/*
+	 * pos will be at the 1st overlapped range, or the position
+	 * where the element should be inserted.
+	 */
+	for (pos = 0; pos < movablemem_map.nr_map; pos++)
+		if (start_pfn <= movablemem_map.map[pos].end_pfn)
+			break;
+
+	/* If there is no overlapped range, just insert the element. */
+	if (pos == movablemem_map.nr_map ||
+	    end_pfn < movablemem_map.map[pos].start_pfn) {
+		/*
+		 * If pos is not the end of array, we need to move all
+		 * the rest elements backward.
+		 */
+		if (pos < movablemem_map.nr_map)
+			memmove(&movablemem_map.map[pos+1],
+				&movablemem_map.map[pos],
+				sizeof(struct movablemem_entry) *
+				(movablemem_map.nr_map - pos));
+		movablemem_map.map[pos].start_pfn = start_pfn;
+		movablemem_map.map[pos].end_pfn = end_pfn;
+		movablemem_map.nr_map++;
+		return;
+	}
+
+	/* overlap will be at the last overlapped range */
+	for (overlap = pos + 1; overlap < movablemem_map.nr_map; overlap++)
+		if (end_pfn < movablemem_map.map[overlap].start_pfn)
+			break;
+
+	/*
+	 * If there are more ranges overlapped, we need to merge them,
+	 * and move the rest elements forward.
+	 */
+	overlap--;
+	movablemem_map.map[pos].start_pfn = min(start_pfn,
+					movablemem_map.map[pos].start_pfn);
+	movablemem_map.map[pos].end_pfn = max(end_pfn,
+					movablemem_map.map[overlap].end_pfn);
+
+	if (pos != overlap && overlap + 1 != movablemem_map.nr_map)
+		memmove(&movablemem_map.map[pos+1],
+			&movablemem_map.map[overlap+1],
+			sizeof(struct movablemem_entry) *
+			(movablemem_map.nr_map - overlap - 1));
+
+	movablemem_map.nr_map -= overlap - pos;
+}
+
+/**
+ * movablemem_map_add_region - Add a memory range into movablemem_map.
+ * @start:	physical start address of range
+ * @end:	physical end address of range
+ *
+ * This function transform the physical address into pfn, and then add the
+ * range into movablemem_map by calling insert_movablemem_map().
+ */
+static void __init movablemem_map_add_region(u64 start, u64 size)
+{
+	unsigned long start_pfn, end_pfn;
+
+	/* In case size == 0 or start + size overflows */
+	if (start + size <= start)
+		return;
+
+	if (movablemem_map.nr_map >= ARRAY_SIZE(movablemem_map.map)) {
+		pr_err("movablemem_map: too many entries;"
+			" ignoring [mem %#010llx-%#010llx]\n",
+			(unsigned long long) start,
+			(unsigned long long) (start + size - 1));
+		return;
+	}
+
+	start_pfn = PFN_DOWN(start);
+	end_pfn = PFN_UP(start + size);
+	insert_movablemem_map(start_pfn, end_pfn);
+}
+
+/*
+ * cmdline_parse_movablemem_map - Parse boot option movablemem_map.
+ * @p:	The boot option of the following format:
+ *	movablemem_map=nn[KMG]@ss[KMG]
+ *
+ * This option sets the memory range [ss, ss+nn) to be used as movable memory.
+ *
+ * Return: 0 on success or -EINVAL on failure.
+ */
+static int __init cmdline_parse_movablemem_map(char *p)
+{
+	char *oldp;
+	u64 start_at, mem_size;
+
+	if (!p)
+		goto err;
+
+	if (!strcmp(p, "acpi"))
+		movablemem_map.acpi = true;
+
+	/*
+	 * If user decide to use info from BIOS, all the other user specified
+	 * ranges will be ingored.
+	 */
+	if (movablemem_map.acpi) {
+		if (movablemem_map.nr_map) {
+			memset(movablemem_map.map, 0,
+				sizeof(struct movablemem_entry)
+				* movablemem_map.nr_map);
+			movablemem_map.nr_map = 0;
+		}
+		return 0;
+	}
+
+	oldp = p;
+	mem_size = memparse(p, &p);
+	if (p == oldp)
+		goto err;
+
+	if (*p == '@') {
+		oldp = ++p;
+		start_at = memparse(p, &p);
+		if (p == oldp || *p != '\0')
+			goto err;
+
+		movablemem_map_add_region(start_at, mem_size);
+		return 0;
+	}
+err:
+	return -EINVAL;
+}
+early_param("movablemem_map", cmdline_parse_movablemem_map);
+
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 /**
@@ -5160,8 +5468,8 @@ static void calculate_totalreserve_pages(void)
 			/* we treat the high watermark as reserved pages. */
 			max += high_wmark_pages(zone);
 
-			if (max > zone->present_pages)
-				max = zone->present_pages;
+			if (max > zone->managed_pages)
+				max = zone->managed_pages;
 			reserve_pages += max;
 			/*
 			 * Lowmem reserves are not available to
@@ -5193,7 +5501,7 @@ static void setup_per_zone_lowmem_reserve(void)
 	for_each_online_pgdat(pgdat) {
 		for (j = 0; j < MAX_NR_ZONES; j++) {
 			struct zone *zone = pgdat->node_zones + j;
-			unsigned long present_pages = zone->present_pages;
+			unsigned long managed_pages = zone->managed_pages;
 
 			zone->lowmem_reserve[j] = 0;
 
@@ -5207,9 +5515,9 @@ static void setup_per_zone_lowmem_reserve(void)
 					sysctl_lowmem_reserve_ratio[idx] = 1;
 
 				lower_zone = pgdat->node_zones + idx;
-				lower_zone->lowmem_reserve[j] = present_pages /
+				lower_zone->lowmem_reserve[j] = managed_pages /
 					sysctl_lowmem_reserve_ratio[idx];
-				present_pages += lower_zone->present_pages;
+				managed_pages += lower_zone->managed_pages;
 			}
 		}
 	}
@@ -5228,14 +5536,14 @@ static void __setup_per_zone_wmarks(void)
 	/* Calculate total number of !ZONE_HIGHMEM pages */
 	for_each_zone(zone) {
 		if (!is_highmem(zone))
-			lowmem_pages += zone->present_pages;
+			lowmem_pages += zone->managed_pages;
 	}
 
 	for_each_zone(zone) {
 		u64 tmp;
 
 		spin_lock_irqsave(&zone->lock, flags);
-		tmp = (u64)pages_min * zone->present_pages;
+		tmp = (u64)pages_min * zone->managed_pages;
 		do_div(tmp, lowmem_pages);
 		if (is_highmem(zone)) {
 			/*
@@ -5247,13 +5555,10 @@ static void __setup_per_zone_wmarks(void)
 			 * deltas controls asynch page reclaim, and so should
 			 * not be capped for highmem.
 			 */
-			int min_pages;
+			unsigned long min_pages;
 
-			min_pages = zone->present_pages / 1024;
-			if (min_pages < SWAP_CLUSTER_MAX)
-				min_pages = SWAP_CLUSTER_MAX;
-			if (min_pages > 128)
-				min_pages = 128;
+			min_pages = zone->managed_pages / 1024;
+			min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL);
 			zone->watermark[WMARK_MIN] = min_pages;
 		} else {
 			/*
@@ -5314,7 +5619,7 @@ static void __meminit calculate_zone_inactive_ratio(struct zone *zone)
 	unsigned int gb, ratio;
 
 	/* Zone size in gigabytes */
-	gb = zone->present_pages >> (30 - PAGE_SHIFT);
+	gb = zone->managed_pages >> (30 - PAGE_SHIFT);
 	if (gb)
 		ratio = int_sqrt(10 * gb);
 	else
@@ -5400,7 +5705,7 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
 		return rc;
 
 	for_each_zone(zone)
-		zone->min_unmapped_pages = (zone->present_pages *
+		zone->min_unmapped_pages = (zone->managed_pages *
 				sysctl_min_unmapped_ratio) / 100;
 	return 0;
 }
@@ -5416,7 +5721,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
 		return rc;
 
 	for_each_zone(zone)
-		zone->min_slab_pages = (zone->present_pages *
+		zone->min_slab_pages = (zone->managed_pages *
 				sysctl_min_slab_ratio) / 100;
 	return 0;
 }
@@ -5458,7 +5763,7 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
 	for_each_populated_zone(zone) {
 		for_each_possible_cpu(cpu) {
 			unsigned long  high;
-			high = zone->present_pages / percpu_pagelist_fraction;
+			high = zone->managed_pages / percpu_pagelist_fraction;
 			setup_pagelist_highmark(
 				per_cpu_ptr(zone->pageset, cpu), high);
 		}
@@ -5645,8 +5950,7 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
 	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
-	VM_BUG_ON(pfn < zone->zone_start_pfn);
-	VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages);
+	VM_BUG_ON(!zone_spans_pfn(zone, pfn));
 
 	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
 		if (flags & value)
@@ -5744,8 +6048,7 @@ bool is_pageblock_removable_nolock(struct page *page)
 
 	zone = page_zone(page);
 	pfn = page_to_pfn(page);
-	if (zone->zone_start_pfn > pfn ||
-			zone->zone_start_pfn + zone->spanned_pages <= pfn)
+	if (!zone_spans_pfn(zone, pfn))
 		return false;
 
 	return !has_unmovable_pages(zone, page, 0, true);
@@ -5801,14 +6104,14 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 							&cc->migratepages);
 		cc->nr_migratepages -= nr_reclaimed;
 
-		ret = migrate_pages(&cc->migratepages,
-				    alloc_migrate_target,
-				    0, false, MIGRATE_SYNC,
-				    MR_CMA);
+		ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
+				    0, MIGRATE_SYNC, MR_CMA);
 	}
-
-	putback_movable_pages(&cc->migratepages);
-	return ret > 0 ? 0 : ret;
+	if (ret < 0) {
+		putback_movable_pages(&cc->migratepages);
+		return ret;
+	}
+	return 0;
 }
 
 /**
diff --git a/mm/rmap.c b/mm/rmap.c
index 3d38edffda4..807c96bf0dc 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -105,7 +105,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma)
 	 */
 	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
 		anon_vma_lock_write(anon_vma);
-		anon_vma_unlock(anon_vma);
+		anon_vma_unlock_write(anon_vma);
 	}
 
 	kmem_cache_free(anon_vma_cachep, anon_vma);
@@ -191,7 +191,7 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 			avc = NULL;
 		}
 		spin_unlock(&mm->page_table_lock);
-		anon_vma_unlock(anon_vma);
+		anon_vma_unlock_write(anon_vma);
 
 		if (unlikely(allocated))
 			put_anon_vma(allocated);
@@ -308,7 +308,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	vma->anon_vma = anon_vma;
 	anon_vma_lock_write(anon_vma);
 	anon_vma_chain_link(vma, avc, anon_vma);
-	anon_vma_unlock(anon_vma);
+	anon_vma_unlock_write(anon_vma);
 
 	return 0;
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 5dd56f6efdb..1ad79243cb7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -335,19 +335,19 @@ static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
 					pgoff_t start, unsigned int nr_pages,
 					struct page **pages, pgoff_t *indices)
 {
-	unsigned int i;
-	unsigned int ret;
-	unsigned int nr_found;
+	void **slot;
+	unsigned int ret = 0;
+	struct radix_tree_iter iter;
+
+	if (!nr_pages)
+		return 0;
 
 	rcu_read_lock();
 restart:
-	nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
-				(void ***)pages, indices, start, nr_pages);
-	ret = 0;
-	for (i = 0; i < nr_found; i++) {
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
 		struct page *page;
 repeat:
-		page = radix_tree_deref_slot((void **)pages[i]);
+		page = radix_tree_deref_slot(slot);
 		if (unlikely(!page))
 			continue;
 		if (radix_tree_exception(page)) {
@@ -364,17 +364,16 @@ repeat:
 			goto repeat;
 
 		/* Has the page moved? */
-		if (unlikely(page != *((void **)pages[i]))) {
+		if (unlikely(page != *slot)) {
 			page_cache_release(page);
 			goto repeat;
 		}
 export:
-		indices[ret] = indices[i];
+		indices[ret] = iter.index;
 		pages[ret] = page;
-		ret++;
+		if (++ret == nr_pages)
+			break;
 	}
-	if (unlikely(!ret && nr_found))
-		goto restart;
 	rcu_read_unlock();
 	return ret;
 }
@@ -2386,6 +2385,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
 			       bool remount)
 {
 	char *this_char, *value, *rest;
+	struct mempolicy *mpol = NULL;
 	uid_t uid;
 	gid_t gid;
 
@@ -2414,7 +2414,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
 			printk(KERN_ERR
 			    "tmpfs: No value for mount option '%s'\n",
 			    this_char);
-			return 1;
+			goto error;
 		}
 
 		if (!strcmp(this_char,"size")) {
@@ -2463,19 +2463,24 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
 			if (!gid_valid(sbinfo->gid))
 				goto bad_val;
 		} else if (!strcmp(this_char,"mpol")) {
-			if (mpol_parse_str(value, &sbinfo->mpol))
+			mpol_put(mpol);
+			mpol = NULL;
+			if (mpol_parse_str(value, &mpol))
 				goto bad_val;
 		} else {
 			printk(KERN_ERR "tmpfs: Bad mount option %s\n",
 			       this_char);
-			return 1;
+			goto error;
 		}
 	}
+	sbinfo->mpol = mpol;
 	return 0;
 
 bad_val:
 	printk(KERN_ERR "tmpfs: Bad value '%s' for mount option '%s'\n",
 	       value, this_char);
+error:
+	mpol_put(mpol);
 	return 1;
 
 }
@@ -2487,6 +2492,7 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
 	unsigned long inodes;
 	int error = -EINVAL;
 
+	config.mpol = NULL;
 	if (shmem_parse_options(data, &config, true))
 		return error;
 
@@ -2511,8 +2517,13 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
 	sbinfo->max_inodes  = config.max_inodes;
 	sbinfo->free_inodes = config.max_inodes - inodes;
 
-	mpol_put(sbinfo->mpol);
-	sbinfo->mpol        = config.mpol;	/* transfers initial ref */
+	/*
+	 * Preserve previous mempolicy unless mpol remount option was specified.
+	 */
+	if (config.mpol) {
+		mpol_put(sbinfo->mpol);
+		sbinfo->mpol = config.mpol;	/* transfers initial ref */
+	}
 out:
 	spin_unlock(&sbinfo->stat_lock);
 	return error;
@@ -2545,6 +2556,7 @@ static void shmem_put_super(struct super_block *sb)
 	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
 
 	percpu_counter_destroy(&sbinfo->used_blocks);
+	mpol_put(sbinfo->mpol);
 	kfree(sbinfo);
 	sb->s_fs_info = NULL;
 }
diff --git a/mm/slob.c b/mm/slob.c
index a99fdf7a090..eeed4a05a2e 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -360,7 +360,7 @@ static void slob_free(void *block, int size)
 			clear_slob_page_free(sp);
 		spin_unlock_irqrestore(&slob_lock, flags);
 		__ClearPageSlab(sp);
-		reset_page_mapcount(sp);
+		page_mapcount_reset(sp);
 		slob_free_pages(b, 0);
 		return;
 	}
diff --git a/mm/slub.c b/mm/slub.c
index ba2ca53f6c3..ebcc44eb43b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1408,7 +1408,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 	__ClearPageSlab(page);
 
 	memcg_release_pages(s, order);
-	reset_page_mapcount(page);
+	page_mapcount_reset(page);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += pages;
 	__free_memcg_kmem_pages(page, order);
diff --git a/mm/sparse.c b/mm/sparse.c
index 6b5fb762e2c..7ca6dc84794 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -615,10 +615,11 @@ static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
 }
 static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 {
-	return; /* XXX: Not implemented yet */
+	vmemmap_free(memmap, nr_pages);
 }
 static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
 {
+	vmemmap_free(memmap, nr_pages);
 }
 #else
 static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
@@ -697,7 +698,7 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 	/*
 	 * Check to see if allocation came from hot-plug-add
 	 */
-	if (PageSlab(usemap_page)) {
+	if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
 		kfree(usemap);
 		if (memmap)
 			__kfree_section_memmap(memmap, PAGES_PER_SECTION);
@@ -782,7 +783,7 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 
 	for (i = 0; i < PAGES_PER_SECTION; i++) {
 		if (PageHWPoison(&memmap[i])) {
-			atomic_long_sub(1, &mce_bad_pages);
+			atomic_long_sub(1, &num_poisoned_pages);
 			ClearPageHWPoison(&memmap[i]);
 		}
 	}
@@ -796,8 +797,10 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
 {
 	struct page *memmap = NULL;
-	unsigned long *usemap = NULL;
+	unsigned long *usemap = NULL, flags;
+	struct pglist_data *pgdat = zone->zone_pgdat;
 
+	pgdat_resize_lock(pgdat, &flags);
 	if (ms->section_mem_map) {
 		usemap = ms->pageblock_flags;
 		memmap = sparse_decode_mem_map(ms->section_mem_map,
@@ -805,6 +808,7 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
 		ms->section_mem_map = 0;
 		ms->pageblock_flags = NULL;
 	}
+	pgdat_resize_unlock(pgdat, &flags);
 
 	clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION);
 	free_section_usemap(memmap, usemap);
diff --git a/mm/swap.c b/mm/swap.c
index 6310dc2008f..8a529a01e8f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -855,9 +855,14 @@ EXPORT_SYMBOL(pagevec_lookup_tag);
 void __init swap_setup(void)
 {
 	unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT);
-
 #ifdef CONFIG_SWAP
-	bdi_init(swapper_space.backing_dev_info);
+	int i;
+
+	bdi_init(swapper_spaces[0].backing_dev_info);
+	for (i = 0; i < MAX_SWAPFILES; i++) {
+		spin_lock_init(&swapper_spaces[i].tree_lock);
+		INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear);
+	}
 #endif
 
 	/* Use a smaller cluster for small-memory machines */
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 0cb36fb1f61..7efcf152592 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -36,12 +36,12 @@ static struct backing_dev_info swap_backing_dev_info = {
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
 };
 
-struct address_space swapper_space = {
-	.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
-	.tree_lock	= __SPIN_LOCK_UNLOCKED(swapper_space.tree_lock),
-	.a_ops		= &swap_aops,
-	.i_mmap_nonlinear = LIST_HEAD_INIT(swapper_space.i_mmap_nonlinear),
-	.backing_dev_info = &swap_backing_dev_info,
+struct address_space swapper_spaces[MAX_SWAPFILES] = {
+	[0 ... MAX_SWAPFILES - 1] = {
+		.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
+		.a_ops		= &swap_aops,
+		.backing_dev_info = &swap_backing_dev_info,
+	}
 };
 
 #define INC_CACHE_INFO(x)	do { swap_cache_info.x++; } while (0)
@@ -53,13 +53,24 @@ static struct {
 	unsigned long find_total;
 } swap_cache_info;
 
+unsigned long total_swapcache_pages(void)
+{
+	int i;
+	unsigned long ret = 0;
+
+	for (i = 0; i < MAX_SWAPFILES; i++)
+		ret += swapper_spaces[i].nrpages;
+	return ret;
+}
+
 void show_swap_cache_info(void)
 {
-	printk("%lu pages in swap cache\n", total_swapcache_pages);
+	printk("%lu pages in swap cache\n", total_swapcache_pages());
 	printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n",
 		swap_cache_info.add_total, swap_cache_info.del_total,
 		swap_cache_info.find_success, swap_cache_info.find_total);
-	printk("Free swap  = %ldkB\n", nr_swap_pages << (PAGE_SHIFT - 10));
+	printk("Free swap  = %ldkB\n",
+		get_nr_swap_pages() << (PAGE_SHIFT - 10));
 	printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
 }
 
@@ -70,6 +81,7 @@ void show_swap_cache_info(void)
 static int __add_to_swap_cache(struct page *page, swp_entry_t entry)
 {
 	int error;
+	struct address_space *address_space;
 
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(PageSwapCache(page));
@@ -79,14 +91,16 @@ static int __add_to_swap_cache(struct page *page, swp_entry_t entry)
 	SetPageSwapCache(page);
 	set_page_private(page, entry.val);
 
-	spin_lock_irq(&swapper_space.tree_lock);
-	error = radix_tree_insert(&swapper_space.page_tree, entry.val, page);
+	address_space = swap_address_space(entry);
+	spin_lock_irq(&address_space->tree_lock);
+	error = radix_tree_insert(&address_space->page_tree,
+					entry.val, page);
 	if (likely(!error)) {
-		total_swapcache_pages++;
+		address_space->nrpages++;
 		__inc_zone_page_state(page, NR_FILE_PAGES);
 		INC_CACHE_INFO(add_total);
 	}
-	spin_unlock_irq(&swapper_space.tree_lock);
+	spin_unlock_irq(&address_space->tree_lock);
 
 	if (unlikely(error)) {
 		/*
@@ -122,14 +136,19 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
  */
 void __delete_from_swap_cache(struct page *page)
 {
+	swp_entry_t entry;
+	struct address_space *address_space;
+
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(!PageSwapCache(page));
 	VM_BUG_ON(PageWriteback(page));
 
-	radix_tree_delete(&swapper_space.page_tree, page_private(page));
+	entry.val = page_private(page);
+	address_space = swap_address_space(entry);
+	radix_tree_delete(&address_space->page_tree, page_private(page));
 	set_page_private(page, 0);
 	ClearPageSwapCache(page);
-	total_swapcache_pages--;
+	address_space->nrpages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	INC_CACHE_INFO(del_total);
 }
@@ -195,12 +214,14 @@ int add_to_swap(struct page *page)
 void delete_from_swap_cache(struct page *page)
 {
 	swp_entry_t entry;
+	struct address_space *address_space;
 
 	entry.val = page_private(page);
 
-	spin_lock_irq(&swapper_space.tree_lock);
+	address_space = swap_address_space(entry);
+	spin_lock_irq(&address_space->tree_lock);
 	__delete_from_swap_cache(page);
-	spin_unlock_irq(&swapper_space.tree_lock);
+	spin_unlock_irq(&address_space->tree_lock);
 
 	swapcache_free(entry, page);
 	page_cache_release(page);
@@ -263,7 +284,7 @@ struct page * lookup_swap_cache(swp_entry_t entry)
 {
 	struct page *page;
 
-	page = find_get_page(&swapper_space, entry.val);
+	page = find_get_page(swap_address_space(entry), entry.val);
 
 	if (page)
 		INC_CACHE_INFO(find_success);
@@ -290,7 +311,8 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * called after lookup_swap_cache() failed, re-calling
 		 * that would confuse statistics.
 		 */
-		found_page = find_get_page(&swapper_space, entry.val);
+		found_page = find_get_page(swap_address_space(entry),
+					entry.val);
 		if (found_page)
 			break;
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index e97a0e5aea9..c72c648f750 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -47,9 +47,11 @@ static sector_t map_swap_entry(swp_entry_t, struct block_device**);
 
 DEFINE_SPINLOCK(swap_lock);
 static unsigned int nr_swapfiles;
-long nr_swap_pages;
+atomic_long_t nr_swap_pages;
+/* protected with swap_lock. reading in vm_swap_full() doesn't need lock */
 long total_swap_pages;
 static int least_priority;
+static atomic_t highest_priority_index = ATOMIC_INIT(-1);
 
 static const char Bad_file[] = "Bad swap file entry ";
 static const char Unused_file[] = "Unused swap file entry ";
@@ -79,7 +81,7 @@ __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset)
 	struct page *page;
 	int ret = 0;
 
-	page = find_get_page(&swapper_space, entry.val);
+	page = find_get_page(swap_address_space(entry), entry.val);
 	if (!page)
 		return 0;
 	/*
@@ -223,7 +225,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 			si->lowest_alloc = si->max;
 			si->highest_alloc = 0;
 		}
-		spin_unlock(&swap_lock);
+		spin_unlock(&si->lock);
 
 		/*
 		 * If seek is expensive, start searching for new cluster from
@@ -242,7 +244,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 			if (si->swap_map[offset])
 				last_in_cluster = offset + SWAPFILE_CLUSTER;
 			else if (offset == last_in_cluster) {
-				spin_lock(&swap_lock);
+				spin_lock(&si->lock);
 				offset -= SWAPFILE_CLUSTER - 1;
 				si->cluster_next = offset;
 				si->cluster_nr = SWAPFILE_CLUSTER - 1;
@@ -263,7 +265,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 			if (si->swap_map[offset])
 				last_in_cluster = offset + SWAPFILE_CLUSTER;
 			else if (offset == last_in_cluster) {
-				spin_lock(&swap_lock);
+				spin_lock(&si->lock);
 				offset -= SWAPFILE_CLUSTER - 1;
 				si->cluster_next = offset;
 				si->cluster_nr = SWAPFILE_CLUSTER - 1;
@@ -277,7 +279,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 		}
 
 		offset = scan_base;
-		spin_lock(&swap_lock);
+		spin_lock(&si->lock);
 		si->cluster_nr = SWAPFILE_CLUSTER - 1;
 		si->lowest_alloc = 0;
 	}
@@ -293,9 +295,9 @@ checks:
 	/* reuse swap entry of cache-only swap if not busy. */
 	if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
 		int swap_was_freed;
-		spin_unlock(&swap_lock);
+		spin_unlock(&si->lock);
 		swap_was_freed = __try_to_reclaim_swap(si, offset);
-		spin_lock(&swap_lock);
+		spin_lock(&si->lock);
 		/* entry was freed successfully, try to use this again */
 		if (swap_was_freed)
 			goto checks;
@@ -335,13 +337,13 @@ checks:
 			    si->lowest_alloc <= last_in_cluster)
 				last_in_cluster = si->lowest_alloc - 1;
 			si->flags |= SWP_DISCARDING;
-			spin_unlock(&swap_lock);
+			spin_unlock(&si->lock);
 
 			if (offset < last_in_cluster)
 				discard_swap_cluster(si, offset,
 					last_in_cluster - offset + 1);
 
-			spin_lock(&swap_lock);
+			spin_lock(&si->lock);
 			si->lowest_alloc = 0;
 			si->flags &= ~SWP_DISCARDING;
 
@@ -355,10 +357,10 @@ checks:
 			 * could defer that delay until swap_writepage,
 			 * but it's easier to keep this self-contained.
 			 */
-			spin_unlock(&swap_lock);
+			spin_unlock(&si->lock);
 			wait_on_bit(&si->flags, ilog2(SWP_DISCARDING),
 				wait_for_discard, TASK_UNINTERRUPTIBLE);
-			spin_lock(&swap_lock);
+			spin_lock(&si->lock);
 		} else {
 			/*
 			 * Note pages allocated by racing tasks while
@@ -374,14 +376,14 @@ checks:
 	return offset;
 
 scan:
-	spin_unlock(&swap_lock);
+	spin_unlock(&si->lock);
 	while (++offset <= si->highest_bit) {
 		if (!si->swap_map[offset]) {
-			spin_lock(&swap_lock);
+			spin_lock(&si->lock);
 			goto checks;
 		}
 		if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
-			spin_lock(&swap_lock);
+			spin_lock(&si->lock);
 			goto checks;
 		}
 		if (unlikely(--latency_ration < 0)) {
@@ -392,11 +394,11 @@ scan:
 	offset = si->lowest_bit;
 	while (++offset < scan_base) {
 		if (!si->swap_map[offset]) {
-			spin_lock(&swap_lock);
+			spin_lock(&si->lock);
 			goto checks;
 		}
 		if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
-			spin_lock(&swap_lock);
+			spin_lock(&si->lock);
 			goto checks;
 		}
 		if (unlikely(--latency_ration < 0)) {
@@ -404,7 +406,7 @@ scan:
 			latency_ration = LATENCY_LIMIT;
 		}
 	}
-	spin_lock(&swap_lock);
+	spin_lock(&si->lock);
 
 no_page:
 	si->flags -= SWP_SCANNING;
@@ -417,13 +419,34 @@ swp_entry_t get_swap_page(void)
 	pgoff_t offset;
 	int type, next;
 	int wrapped = 0;
+	int hp_index;
 
 	spin_lock(&swap_lock);
-	if (nr_swap_pages <= 0)
+	if (atomic_long_read(&nr_swap_pages) <= 0)
 		goto noswap;
-	nr_swap_pages--;
+	atomic_long_dec(&nr_swap_pages);
 
 	for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
+		hp_index = atomic_xchg(&highest_priority_index, -1);
+		/*
+		 * highest_priority_index records current highest priority swap
+		 * type which just frees swap entries. If its priority is
+		 * higher than that of swap_list.next swap type, we use it.  It
+		 * isn't protected by swap_lock, so it can be an invalid value
+		 * if the corresponding swap type is swapoff. We double check
+		 * the flags here. It's even possible the swap type is swapoff
+		 * and swapon again and its priority is changed. In such rare
+		 * case, low prority swap type might be used, but eventually
+		 * high priority swap will be used after several rounds of
+		 * swap.
+		 */
+		if (hp_index != -1 && hp_index != type &&
+		    swap_info[type]->prio < swap_info[hp_index]->prio &&
+		    (swap_info[hp_index]->flags & SWP_WRITEOK)) {
+			type = hp_index;
+			swap_list.next = type;
+		}
+
 		si = swap_info[type];
 		next = si->next;
 		if (next < 0 ||
@@ -432,22 +455,29 @@ swp_entry_t get_swap_page(void)
 			wrapped++;
 		}
 
-		if (!si->highest_bit)
+		spin_lock(&si->lock);
+		if (!si->highest_bit) {
+			spin_unlock(&si->lock);
 			continue;
-		if (!(si->flags & SWP_WRITEOK))
+		}
+		if (!(si->flags & SWP_WRITEOK)) {
+			spin_unlock(&si->lock);
 			continue;
+		}
 
 		swap_list.next = next;
+
+		spin_unlock(&swap_lock);
 		/* This is called for allocating swap entry for cache */
 		offset = scan_swap_map(si, SWAP_HAS_CACHE);
-		if (offset) {
-			spin_unlock(&swap_lock);
+		spin_unlock(&si->lock);
+		if (offset)
 			return swp_entry(type, offset);
-		}
+		spin_lock(&swap_lock);
 		next = swap_list.next;
 	}
 
-	nr_swap_pages++;
+	atomic_long_inc(&nr_swap_pages);
 noswap:
 	spin_unlock(&swap_lock);
 	return (swp_entry_t) {0};
@@ -459,19 +489,19 @@ swp_entry_t get_swap_page_of_type(int type)
 	struct swap_info_struct *si;
 	pgoff_t offset;
 
-	spin_lock(&swap_lock);
 	si = swap_info[type];
+	spin_lock(&si->lock);
 	if (si && (si->flags & SWP_WRITEOK)) {
-		nr_swap_pages--;
+		atomic_long_dec(&nr_swap_pages);
 		/* This is called for allocating swap entry, not cache */
 		offset = scan_swap_map(si, 1);
 		if (offset) {
-			spin_unlock(&swap_lock);
+			spin_unlock(&si->lock);
 			return swp_entry(type, offset);
 		}
-		nr_swap_pages++;
+		atomic_long_inc(&nr_swap_pages);
 	}
-	spin_unlock(&swap_lock);
+	spin_unlock(&si->lock);
 	return (swp_entry_t) {0};
 }
 
@@ -493,7 +523,7 @@ static struct swap_info_struct *swap_info_get(swp_entry_t entry)
 		goto bad_offset;
 	if (!p->swap_map[offset])
 		goto bad_free;
-	spin_lock(&swap_lock);
+	spin_lock(&p->lock);
 	return p;
 
 bad_free:
@@ -511,6 +541,27 @@ out:
 	return NULL;
 }
 
+/*
+ * This swap type frees swap entry, check if it is the highest priority swap
+ * type which just frees swap entry. get_swap_page() uses
+ * highest_priority_index to search highest priority swap type. The
+ * swap_info_struct.lock can't protect us if there are multiple swap types
+ * active, so we use atomic_cmpxchg.
+ */
+static void set_highest_priority_index(int type)
+{
+	int old_hp_index, new_hp_index;
+
+	do {
+		old_hp_index = atomic_read(&highest_priority_index);
+		if (old_hp_index != -1 &&
+			swap_info[old_hp_index]->prio >= swap_info[type]->prio)
+			break;
+		new_hp_index = type;
+	} while (atomic_cmpxchg(&highest_priority_index,
+		old_hp_index, new_hp_index) != old_hp_index);
+}
+
 static unsigned char swap_entry_free(struct swap_info_struct *p,
 				     swp_entry_t entry, unsigned char usage)
 {
@@ -553,10 +604,8 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 			p->lowest_bit = offset;
 		if (offset > p->highest_bit)
 			p->highest_bit = offset;
-		if (swap_list.next >= 0 &&
-		    p->prio > swap_info[swap_list.next]->prio)
-			swap_list.next = p->type;
-		nr_swap_pages++;
+		set_highest_priority_index(p->type);
+		atomic_long_inc(&nr_swap_pages);
 		p->inuse_pages--;
 		frontswap_invalidate_page(p->type, offset);
 		if (p->flags & SWP_BLKDEV) {
@@ -581,7 +630,7 @@ void swap_free(swp_entry_t entry)
 	p = swap_info_get(entry);
 	if (p) {
 		swap_entry_free(p, entry, 1);
-		spin_unlock(&swap_lock);
+		spin_unlock(&p->lock);
 	}
 }
 
@@ -598,7 +647,7 @@ void swapcache_free(swp_entry_t entry, struct page *page)
 		count = swap_entry_free(p, entry, SWAP_HAS_CACHE);
 		if (page)
 			mem_cgroup_uncharge_swapcache(page, entry, count != 0);
-		spin_unlock(&swap_lock);
+		spin_unlock(&p->lock);
 	}
 }
 
@@ -617,7 +666,7 @@ int page_swapcount(struct page *page)
 	p = swap_info_get(entry);
 	if (p) {
 		count = swap_count(p->swap_map[swp_offset(entry)]);
-		spin_unlock(&swap_lock);
+		spin_unlock(&p->lock);
 	}
 	return count;
 }
@@ -699,13 +748,14 @@ int free_swap_and_cache(swp_entry_t entry)
 	p = swap_info_get(entry);
 	if (p) {
 		if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) {
-			page = find_get_page(&swapper_space, entry.val);
+			page = find_get_page(swap_address_space(entry),
+						entry.val);
 			if (page && !trylock_page(page)) {
 				page_cache_release(page);
 				page = NULL;
 			}
 		}
-		spin_unlock(&swap_lock);
+		spin_unlock(&p->lock);
 	}
 	if (page) {
 		/*
@@ -803,11 +853,13 @@ unsigned int count_swap_pages(int type, int free)
 	if ((unsigned int)type < nr_swapfiles) {
 		struct swap_info_struct *sis = swap_info[type];
 
+		spin_lock(&sis->lock);
 		if (sis->flags & SWP_WRITEOK) {
 			n = sis->pages;
 			if (free)
 				n -= sis->inuse_pages;
 		}
+		spin_unlock(&sis->lock);
 	}
 	spin_unlock(&swap_lock);
 	return n;
@@ -822,11 +874,17 @@ unsigned int count_swap_pages(int type, int free)
 static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, swp_entry_t entry, struct page *page)
 {
+	struct page *swapcache;
 	struct mem_cgroup *memcg;
 	spinlock_t *ptl;
 	pte_t *pte;
 	int ret = 1;
 
+	swapcache = page;
+	page = ksm_might_need_to_copy(page, vma, addr);
+	if (unlikely(!page))
+		return -ENOMEM;
+
 	if (mem_cgroup_try_charge_swapin(vma->vm_mm, page,
 					 GFP_KERNEL, &memcg)) {
 		ret = -ENOMEM;
@@ -845,7 +903,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	get_page(page);
 	set_pte_at(vma->vm_mm, addr, pte,
 		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
-	page_add_anon_rmap(page, vma, addr);
+	if (page == swapcache)
+		page_add_anon_rmap(page, vma, addr);
+	else /* ksm created a completely new copy */
+		page_add_new_anon_rmap(page, vma, addr);
 	mem_cgroup_commit_charge_swapin(page, memcg);
 	swap_free(entry);
 	/*
@@ -856,6 +917,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 out:
 	pte_unmap_unlock(pte, ptl);
 out_nolock:
+	if (page != swapcache) {
+		unlock_page(page);
+		put_page(page);
+	}
 	return ret;
 }
 
@@ -1456,7 +1521,7 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 	p->swap_map = swap_map;
 	frontswap_map_set(p, frontswap_map);
 	p->flags |= SWP_WRITEOK;
-	nr_swap_pages += p->pages;
+	atomic_long_add(p->pages, &nr_swap_pages);
 	total_swap_pages += p->pages;
 
 	/* insert swap space into swap_list: */
@@ -1478,15 +1543,19 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
 				unsigned long *frontswap_map)
 {
 	spin_lock(&swap_lock);
+	spin_lock(&p->lock);
 	_enable_swap_info(p, prio, swap_map, frontswap_map);
 	frontswap_init(p->type);
+	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 }
 
 static void reinsert_swap_info(struct swap_info_struct *p)
 {
 	spin_lock(&swap_lock);
+	spin_lock(&p->lock);
 	_enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p));
+	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 }
 
@@ -1546,14 +1615,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		/* just pick something that's safe... */
 		swap_list.next = swap_list.head;
 	}
+	spin_lock(&p->lock);
 	if (p->prio < 0) {
 		for (i = p->next; i >= 0; i = swap_info[i]->next)
 			swap_info[i]->prio = p->prio--;
 		least_priority++;
 	}
-	nr_swap_pages -= p->pages;
+	atomic_long_sub(p->pages, &nr_swap_pages);
 	total_swap_pages -= p->pages;
 	p->flags &= ~SWP_WRITEOK;
+	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 
 	set_current_oom_origin();
@@ -1572,14 +1643,17 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 
 	mutex_lock(&swapon_mutex);
 	spin_lock(&swap_lock);
+	spin_lock(&p->lock);
 	drain_mmlist();
 
 	/* wait for anyone still in scan_swap_map */
 	p->highest_bit = 0;		/* cuts scans short */
 	while (p->flags >= SWP_SCANNING) {
+		spin_unlock(&p->lock);
 		spin_unlock(&swap_lock);
 		schedule_timeout_uninterruptible(1);
 		spin_lock(&swap_lock);
+		spin_lock(&p->lock);
 	}
 
 	swap_file = p->swap_file;
@@ -1589,6 +1663,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	p->swap_map = NULL;
 	p->flags = 0;
 	frontswap_invalidate_area(type);
+	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 	mutex_unlock(&swapon_mutex);
 	vfree(swap_map);
@@ -1794,6 +1869,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 	p->flags = SWP_USED;
 	p->next = -1;
 	spin_unlock(&swap_lock);
+	spin_lock_init(&p->lock);
 
 	return p;
 }
@@ -2116,7 +2192,7 @@ void si_swapinfo(struct sysinfo *val)
 		if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK))
 			nr_to_be_unused += si->inuse_pages;
 	}
-	val->freeswap = nr_swap_pages + nr_to_be_unused;
+	val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused;
 	val->totalswap = total_swap_pages + nr_to_be_unused;
 	spin_unlock(&swap_lock);
 }
@@ -2149,7 +2225,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 	p = swap_info[type];
 	offset = swp_offset(entry);
 
-	spin_lock(&swap_lock);
+	spin_lock(&p->lock);
 	if (unlikely(offset >= p->max))
 		goto unlock_out;
 
@@ -2184,7 +2260,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 	p->swap_map[offset] = count | has_cache;
 
 unlock_out:
-	spin_unlock(&swap_lock);
+	spin_unlock(&p->lock);
 out:
 	return err;
 
@@ -2309,7 +2385,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	}
 
 	if (!page) {
-		spin_unlock(&swap_lock);
+		spin_unlock(&si->lock);
 		return -ENOMEM;
 	}
 
@@ -2357,7 +2433,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	list_add_tail(&page->lru, &head->lru);
 	page = NULL;			/* now it's attached, don't free it */
 out:
-	spin_unlock(&swap_lock);
+	spin_unlock(&si->lock);
 outer:
 	if (page)
 		__free_page(page);
diff --git a/mm/util.c b/mm/util.c
index c55e26b17d9..ab1424dbe2e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -5,6 +5,8 @@
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/security.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -355,12 +357,16 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 {
 	unsigned long ret;
 	struct mm_struct *mm = current->mm;
+	unsigned long populate;
 
 	ret = security_mmap_file(file, prot, flag);
 	if (!ret) {
 		down_write(&mm->mmap_sem);
-		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff);
+		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
+				    &populate);
 		up_write(&mm->mmap_sem);
+		if (populate)
+			mm_populate(ret, populate);
 	}
 	return ret;
 }
@@ -378,6 +384,24 @@ unsigned long vm_mmap(struct file *file, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_mmap);
 
+struct address_space *page_mapping(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+
+	VM_BUG_ON(PageSlab(page));
+#ifdef CONFIG_SWAP
+	if (unlikely(PageSwapCache(page))) {
+		swp_entry_t entry;
+
+		entry.val = page_private(page);
+		mapping = swap_address_space(entry);
+	} else
+#endif
+	if ((unsigned long)mapping & PAGE_MAPPING_ANON)
+		mapping = NULL;
+	return mapping;
+}
+
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 5123a169ab7..0f751f2068c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1376,8 +1376,8 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
 				unsigned long start, unsigned long end)
 {
-	return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
-						__builtin_return_address(0));
+	return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE,
+				  GFP_KERNEL, __builtin_return_address(0));
 }
 EXPORT_SYMBOL_GPL(__get_vm_area);
 
@@ -1385,8 +1385,8 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
 				       unsigned long start, unsigned long end,
 				       const void *caller)
 {
-	return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
-				  caller);
+	return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE,
+				  GFP_KERNEL, caller);
 }
 
 /**
@@ -1401,14 +1401,15 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
 struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
 {
 	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
-				-1, GFP_KERNEL, __builtin_return_address(0));
+				  NUMA_NO_NODE, GFP_KERNEL,
+				  __builtin_return_address(0));
 }
 
 struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
 				const void *caller)
 {
 	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
-						-1, GFP_KERNEL, caller);
+				  NUMA_NO_NODE, GFP_KERNEL, caller);
 }
 
 /**
@@ -1650,7 +1651,7 @@ fail:
  *	@end:		vm area range end
  *	@gfp_mask:	flags for the page level allocator
  *	@prot:		protection mask for the allocated pages
- *	@node:		node to use for allocation or -1
+ *	@node:		node to use for allocation or NUMA_NO_NODE
  *	@caller:	caller's return address
  *
  *	Allocate enough pages to cover @size from the page level
@@ -1706,7 +1707,7 @@ fail:
  *	@align:		desired alignment
  *	@gfp_mask:	flags for the page level allocator
  *	@prot:		protection mask for the allocated pages
- *	@node:		node to use for allocation or -1
+ *	@node:		node to use for allocation or NUMA_NO_NODE
  *	@caller:	caller's return address
  *
  *	Allocate enough pages to cover @size from the page level
@@ -1723,7 +1724,7 @@ static void *__vmalloc_node(unsigned long size, unsigned long align,
 
 void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 {
-	return __vmalloc_node(size, 1, gfp_mask, prot, -1,
+	return __vmalloc_node(size, 1, gfp_mask, prot, NUMA_NO_NODE,
 				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__vmalloc);
@@ -1746,7 +1747,8 @@ static inline void *__vmalloc_node_flags(unsigned long size,
  */
 void *vmalloc(unsigned long size)
 {
-	return __vmalloc_node_flags(size, -1, GFP_KERNEL | __GFP_HIGHMEM);
+	return __vmalloc_node_flags(size, NUMA_NO_NODE,
+				    GFP_KERNEL | __GFP_HIGHMEM);
 }
 EXPORT_SYMBOL(vmalloc);
 
@@ -1762,7 +1764,7 @@ EXPORT_SYMBOL(vmalloc);
  */
 void *vzalloc(unsigned long size)
 {
-	return __vmalloc_node_flags(size, -1,
+	return __vmalloc_node_flags(size, NUMA_NO_NODE,
 				GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
 }
 EXPORT_SYMBOL(vzalloc);
@@ -1781,7 +1783,8 @@ void *vmalloc_user(unsigned long size)
 
 	ret = __vmalloc_node(size, SHMLBA,
 			     GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
-			     PAGE_KERNEL, -1, __builtin_return_address(0));
+			     PAGE_KERNEL, NUMA_NO_NODE,
+			     __builtin_return_address(0));
 	if (ret) {
 		area = find_vm_area(ret);
 		area->flags |= VM_USERMAP;
@@ -1846,7 +1849,7 @@ EXPORT_SYMBOL(vzalloc_node);
 void *vmalloc_exec(unsigned long size)
 {
 	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
-			      -1, __builtin_return_address(0));
+			      NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
@@ -1867,7 +1870,7 @@ void *vmalloc_exec(unsigned long size)
 void *vmalloc_32(unsigned long size)
 {
 	return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL,
-			      -1, __builtin_return_address(0));
+			      NUMA_NO_NODE, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(vmalloc_32);
 
@@ -1884,7 +1887,7 @@ void *vmalloc_32_user(unsigned long size)
 	void *ret;
 
 	ret = __vmalloc_node(size, 1, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
-			     -1, __builtin_return_address(0));
+			     NUMA_NO_NODE, __builtin_return_address(0));
 	if (ret) {
 		area = find_vm_area(ret);
 		area->flags |= VM_USERMAP;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 196709f5ee5..88c5fed8b9a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -128,7 +128,7 @@ struct scan_control {
  * From 0 .. 100.  Higher means more swappy.
  */
 int vm_swappiness = 60;
-long vm_total_pages;	/* The total number of pages which the VM controls */
+unsigned long vm_total_pages;	/* The total number of pages which the VM controls */
 
 static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
@@ -1579,16 +1579,6 @@ static inline int inactive_anon_is_low(struct lruvec *lruvec)
 }
 #endif
 
-static int inactive_file_is_low_global(struct zone *zone)
-{
-	unsigned long active, inactive;
-
-	active = zone_page_state(zone, NR_ACTIVE_FILE);
-	inactive = zone_page_state(zone, NR_INACTIVE_FILE);
-
-	return (active > inactive);
-}
-
 /**
  * inactive_file_is_low - check if file pages need to be deactivated
  * @lruvec: LRU vector to check
@@ -1605,10 +1595,13 @@ static int inactive_file_is_low_global(struct zone *zone)
  */
 static int inactive_file_is_low(struct lruvec *lruvec)
 {
-	if (!mem_cgroup_disabled())
-		return mem_cgroup_inactive_file_is_low(lruvec);
+	unsigned long inactive;
+	unsigned long active;
+
+	inactive = get_lru_size(lruvec, LRU_INACTIVE_FILE);
+	active = get_lru_size(lruvec, LRU_ACTIVE_FILE);
 
-	return inactive_file_is_low_global(lruvec_zone(lruvec));
+	return active > inactive;
 }
 
 static int inactive_list_is_low(struct lruvec *lruvec, enum lru_list lru)
@@ -1638,6 +1631,13 @@ static int vmscan_swappiness(struct scan_control *sc)
 	return mem_cgroup_swappiness(sc->target_mem_cgroup);
 }
 
+enum scan_balance {
+	SCAN_EQUAL,
+	SCAN_FRACT,
+	SCAN_ANON,
+	SCAN_FILE,
+};
+
 /*
  * Determine how aggressively the anon and file LRU lists should be
  * scanned.  The relative value of each set of LRU lists is determined
@@ -1650,15 +1650,16 @@ static int vmscan_swappiness(struct scan_control *sc)
 static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 			   unsigned long *nr)
 {
-	unsigned long anon, file, free;
+	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
+	u64 fraction[2];
+	u64 denominator = 0;	/* gcc */
+	struct zone *zone = lruvec_zone(lruvec);
 	unsigned long anon_prio, file_prio;
+	enum scan_balance scan_balance;
+	unsigned long anon, file, free;
+	bool force_scan = false;
 	unsigned long ap, fp;
-	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
-	u64 fraction[2], denominator;
 	enum lru_list lru;
-	int noswap = 0;
-	bool force_scan = false;
-	struct zone *zone = lruvec_zone(lruvec);
 
 	/*
 	 * If the zone or memcg is small, nr[l] can be 0.  This
@@ -1676,11 +1677,30 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 		force_scan = true;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
-	if (!sc->may_swap || (nr_swap_pages <= 0)) {
-		noswap = 1;
-		fraction[0] = 0;
-		fraction[1] = 1;
-		denominator = 1;
+	if (!sc->may_swap || (get_nr_swap_pages() <= 0)) {
+		scan_balance = SCAN_FILE;
+		goto out;
+	}
+
+	/*
+	 * Global reclaim will swap to prevent OOM even with no
+	 * swappiness, but memcg users want to use this knob to
+	 * disable swapping for individual groups completely when
+	 * using the memory controller's swap limit feature would be
+	 * too expensive.
+	 */
+	if (!global_reclaim(sc) && !vmscan_swappiness(sc)) {
+		scan_balance = SCAN_FILE;
+		goto out;
+	}
+
+	/*
+	 * Do not apply any pressure balancing cleverness when the
+	 * system is close to OOM, scan both anon and file equally
+	 * (unless the swappiness setting disagrees with swapping).
+	 */
+	if (!sc->priority && vmscan_swappiness(sc)) {
+		scan_balance = SCAN_EQUAL;
 		goto out;
 	}
 
@@ -1689,30 +1709,32 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	file  = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
 		get_lru_size(lruvec, LRU_INACTIVE_FILE);
 
+	/*
+	 * If it's foreseeable that reclaiming the file cache won't be
+	 * enough to get the zone back into a desirable shape, we have
+	 * to swap.  Better start now and leave the - probably heavily
+	 * thrashing - remaining file pages alone.
+	 */
 	if (global_reclaim(sc)) {
-		free  = zone_page_state(zone, NR_FREE_PAGES);
+		free = zone_page_state(zone, NR_FREE_PAGES);
 		if (unlikely(file + free <= high_wmark_pages(zone))) {
-			/*
-			 * If we have very few page cache pages, force-scan
-			 * anon pages.
-			 */
-			fraction[0] = 1;
-			fraction[1] = 0;
-			denominator = 1;
-			goto out;
-		} else if (!inactive_file_is_low_global(zone)) {
-			/*
-			 * There is enough inactive page cache, do not
-			 * reclaim anything from the working set right now.
-			 */
-			fraction[0] = 0;
-			fraction[1] = 1;
-			denominator = 1;
+			scan_balance = SCAN_ANON;
 			goto out;
 		}
 	}
 
 	/*
+	 * There is enough inactive page cache, do not reclaim
+	 * anything from the anonymous working set right now.
+	 */
+	if (!inactive_file_is_low(lruvec)) {
+		scan_balance = SCAN_FILE;
+		goto out;
+	}
+
+	scan_balance = SCAN_FRACT;
+
+	/*
 	 * With swappiness at 100, anonymous and file have the same priority.
 	 * This scanning priority is essentially the inverse of IO cost.
 	 */
@@ -1759,19 +1781,92 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 out:
 	for_each_evictable_lru(lru) {
 		int file = is_file_lru(lru);
+		unsigned long size;
 		unsigned long scan;
 
-		scan = get_lru_size(lruvec, lru);
-		if (sc->priority || noswap || !vmscan_swappiness(sc)) {
-			scan >>= sc->priority;
-			if (!scan && force_scan)
-				scan = SWAP_CLUSTER_MAX;
+		size = get_lru_size(lruvec, lru);
+		scan = size >> sc->priority;
+
+		if (!scan && force_scan)
+			scan = min(size, SWAP_CLUSTER_MAX);
+
+		switch (scan_balance) {
+		case SCAN_EQUAL:
+			/* Scan lists relative to size */
+			break;
+		case SCAN_FRACT:
+			/*
+			 * Scan types proportional to swappiness and
+			 * their relative recent reclaim efficiency.
+			 */
 			scan = div64_u64(scan * fraction[file], denominator);
+			break;
+		case SCAN_FILE:
+		case SCAN_ANON:
+			/* Scan one type exclusively */
+			if ((scan_balance == SCAN_FILE) != file)
+				scan = 0;
+			break;
+		default:
+			/* Look ma, no brain */
+			BUG();
 		}
 		nr[lru] = scan;
 	}
 }
 
+/*
+ * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
+ */
+static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+{
+	unsigned long nr[NR_LRU_LISTS];
+	unsigned long nr_to_scan;
+	enum lru_list lru;
+	unsigned long nr_reclaimed = 0;
+	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
+	struct blk_plug plug;
+
+	get_scan_count(lruvec, sc, nr);
+
+	blk_start_plug(&plug);
+	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
+					nr[LRU_INACTIVE_FILE]) {
+		for_each_evictable_lru(lru) {
+			if (nr[lru]) {
+				nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX);
+				nr[lru] -= nr_to_scan;
+
+				nr_reclaimed += shrink_list(lru, nr_to_scan,
+							    lruvec, sc);
+			}
+		}
+		/*
+		 * On large memory systems, scan >> priority can become
+		 * really large. This is fine for the starting priority;
+		 * we want to put equal scanning pressure on each zone.
+		 * However, if the VM has a harder time of freeing pages,
+		 * with multiple processes reclaiming pages, the total
+		 * freeing target can get unreasonably large.
+		 */
+		if (nr_reclaimed >= nr_to_reclaim &&
+		    sc->priority < DEF_PRIORITY)
+			break;
+	}
+	blk_finish_plug(&plug);
+	sc->nr_reclaimed += nr_reclaimed;
+
+	/*
+	 * Even if we did not try to evict anon pages at all, we want to
+	 * rebalance the anon lru active/inactive ratio.
+	 */
+	if (inactive_anon_is_low(lruvec))
+		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
+				   sc, LRU_ACTIVE_ANON);
+
+	throttle_vm_writeout(sc->gfp_mask);
+}
+
 /* Use reclaim/compaction for costly allocs or under memory pressure */
 static bool in_reclaim_compaction(struct scan_control *sc)
 {
@@ -1790,7 +1885,7 @@ static bool in_reclaim_compaction(struct scan_control *sc)
  * calls try_to_compact_zone() that it will have enough free pages to succeed.
  * It will give up earlier than that if there is difficulty reclaiming pages.
  */
-static inline bool should_continue_reclaim(struct lruvec *lruvec,
+static inline bool should_continue_reclaim(struct zone *zone,
 					unsigned long nr_reclaimed,
 					unsigned long nr_scanned,
 					struct scan_control *sc)
@@ -1830,15 +1925,15 @@ static inline bool should_continue_reclaim(struct lruvec *lruvec,
 	 * inactive lists are large enough, continue reclaiming
 	 */
 	pages_for_compaction = (2UL << sc->order);
-	inactive_lru_pages = get_lru_size(lruvec, LRU_INACTIVE_FILE);
-	if (nr_swap_pages > 0)
-		inactive_lru_pages += get_lru_size(lruvec, LRU_INACTIVE_ANON);
+	inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE);
+	if (get_nr_swap_pages() > 0)
+		inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON);
 	if (sc->nr_reclaimed < pages_for_compaction &&
 			inactive_lru_pages > pages_for_compaction)
 		return true;
 
 	/* If compaction would go ahead or the allocation would succeed, stop */
-	switch (compaction_suitable(lruvec_zone(lruvec), sc->order)) {
+	switch (compaction_suitable(zone, sc->order)) {
 	case COMPACT_PARTIAL:
 	case COMPACT_CONTINUE:
 		return false;
@@ -1847,98 +1942,48 @@ static inline bool should_continue_reclaim(struct lruvec *lruvec,
 	}
 }
 
-/*
- * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
- */
-static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
 {
-	unsigned long nr[NR_LRU_LISTS];
-	unsigned long nr_to_scan;
-	enum lru_list lru;
 	unsigned long nr_reclaimed, nr_scanned;
-	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
-	struct blk_plug plug;
-
-restart:
-	nr_reclaimed = 0;
-	nr_scanned = sc->nr_scanned;
-	get_scan_count(lruvec, sc, nr);
-
-	blk_start_plug(&plug);
-	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
-					nr[LRU_INACTIVE_FILE]) {
-		for_each_evictable_lru(lru) {
-			if (nr[lru]) {
-				nr_to_scan = min_t(unsigned long,
-						   nr[lru], SWAP_CLUSTER_MAX);
-				nr[lru] -= nr_to_scan;
-
-				nr_reclaimed += shrink_list(lru, nr_to_scan,
-							    lruvec, sc);
-			}
-		}
-		/*
-		 * On large memory systems, scan >> priority can become
-		 * really large. This is fine for the starting priority;
-		 * we want to put equal scanning pressure on each zone.
-		 * However, if the VM has a harder time of freeing pages,
-		 * with multiple processes reclaiming pages, the total
-		 * freeing target can get unreasonably large.
-		 */
-		if (nr_reclaimed >= nr_to_reclaim &&
-		    sc->priority < DEF_PRIORITY)
-			break;
-	}
-	blk_finish_plug(&plug);
-	sc->nr_reclaimed += nr_reclaimed;
 
-	/*
-	 * Even if we did not try to evict anon pages at all, we want to
-	 * rebalance the anon lru active/inactive ratio.
-	 */
-	if (inactive_anon_is_low(lruvec))
-		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
-				   sc, LRU_ACTIVE_ANON);
-
-	/* reclaim/compaction might need reclaim to continue */
-	if (should_continue_reclaim(lruvec, nr_reclaimed,
-				    sc->nr_scanned - nr_scanned, sc))
-		goto restart;
+	do {
+		struct mem_cgroup *root = sc->target_mem_cgroup;
+		struct mem_cgroup_reclaim_cookie reclaim = {
+			.zone = zone,
+			.priority = sc->priority,
+		};
+		struct mem_cgroup *memcg;
 
-	throttle_vm_writeout(sc->gfp_mask);
-}
+		nr_reclaimed = sc->nr_reclaimed;
+		nr_scanned = sc->nr_scanned;
 
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
-{
-	struct mem_cgroup *root = sc->target_mem_cgroup;
-	struct mem_cgroup_reclaim_cookie reclaim = {
-		.zone = zone,
-		.priority = sc->priority,
-	};
-	struct mem_cgroup *memcg;
+		memcg = mem_cgroup_iter(root, NULL, &reclaim);
+		do {
+			struct lruvec *lruvec;
 
-	memcg = mem_cgroup_iter(root, NULL, &reclaim);
-	do {
-		struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 
-		shrink_lruvec(lruvec, sc);
+			shrink_lruvec(lruvec, sc);
 
-		/*
-		 * Limit reclaim has historically picked one memcg and
-		 * scanned it with decreasing priority levels until
-		 * nr_to_reclaim had been reclaimed.  This priority
-		 * cycle is thus over after a single memcg.
-		 *
-		 * Direct reclaim and kswapd, on the other hand, have
-		 * to scan all memory cgroups to fulfill the overall
-		 * scan target for the zone.
-		 */
-		if (!global_reclaim(sc)) {
-			mem_cgroup_iter_break(root, memcg);
-			break;
-		}
-		memcg = mem_cgroup_iter(root, memcg, &reclaim);
-	} while (memcg);
+			/*
+			 * Direct reclaim and kswapd have to scan all memory
+			 * cgroups to fulfill the overall scan target for the
+			 * zone.
+			 *
+			 * Limit reclaim, on the other hand, only cares about
+			 * nr_to_reclaim pages to be reclaimed and it will
+			 * retry with decreasing priority if one round over the
+			 * whole hierarchy is not sufficient.
+			 */
+			if (!global_reclaim(sc) &&
+					sc->nr_reclaimed >= sc->nr_to_reclaim) {
+				mem_cgroup_iter_break(root, memcg);
+				break;
+			}
+			memcg = mem_cgroup_iter(root, memcg, &reclaim);
+		} while (memcg);
+	} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
+					 sc->nr_scanned - nr_scanned, sc));
 }
 
 /* Returns true if compaction should go ahead for a high-order request */
@@ -1958,7 +2003,7 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
 	 * a reasonable chance of completing and allocating the page
 	 */
 	balance_gap = min(low_wmark_pages(zone),
-		(zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
+		(zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
 			KSWAPD_ZONE_BALANCE_GAP_RATIO);
 	watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order);
 	watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0);
@@ -2150,6 +2195,13 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			goto out;
 
 		/*
+		 * If we're getting trouble reclaiming, start doing
+		 * writepage even in laptop mode.
+		 */
+		if (sc->priority < DEF_PRIORITY - 2)
+			sc->may_writepage = 1;
+
+		/*
 		 * Try to write back as many pages as we just scanned.  This
 		 * tends to cause slow streaming writers to write data to the
 		 * disk smoothly, at the dirtying rate, which is nice.   But
@@ -2300,7 +2352,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 {
 	unsigned long nr_reclaimed;
 	struct scan_control sc = {
-		.gfp_mask = gfp_mask,
+		.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
 		.may_writepage = !laptop_mode,
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.may_unmap = 1,
@@ -2473,7 +2525,7 @@ static bool zone_balanced(struct zone *zone, int order,
  */
 static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
 {
-	unsigned long present_pages = 0;
+	unsigned long managed_pages = 0;
 	unsigned long balanced_pages = 0;
 	int i;
 
@@ -2484,7 +2536,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
 		if (!populated_zone(zone))
 			continue;
 
-		present_pages += zone->present_pages;
+		managed_pages += zone->managed_pages;
 
 		/*
 		 * A special case here:
@@ -2494,18 +2546,18 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
 		 * they must be considered balanced here as well!
 		 */
 		if (zone->all_unreclaimable) {
-			balanced_pages += zone->present_pages;
+			balanced_pages += zone->managed_pages;
 			continue;
 		}
 
 		if (zone_balanced(zone, order, 0, i))
-			balanced_pages += zone->present_pages;
+			balanced_pages += zone->managed_pages;
 		else if (!order)
 			return false;
 	}
 
 	if (order)
-		return balanced_pages >= (present_pages >> 2);
+		return balanced_pages >= (managed_pages >> 2);
 	else
 		return true;
 }
@@ -2564,7 +2616,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 							int *classzone_idx)
 {
-	struct zone *unbalanced_zone;
+	bool pgdat_is_balanced = false;
 	int i;
 	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 	unsigned long total_scanned;
@@ -2595,9 +2647,6 @@ loop_again:
 
 	do {
 		unsigned long lru_pages = 0;
-		int has_under_min_watermark_zone = 0;
-
-		unbalanced_zone = NULL;
 
 		/*
 		 * Scan in the highmem->dma direction for the highest
@@ -2638,8 +2687,11 @@ loop_again:
 				zone_clear_flag(zone, ZONE_CONGESTED);
 			}
 		}
-		if (i < 0)
+
+		if (i < 0) {
+			pgdat_is_balanced = true;
 			goto out;
+		}
 
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
@@ -2689,7 +2741,7 @@ loop_again:
 			 * of the zone, whichever is smaller.
 			 */
 			balance_gap = min(low_wmark_pages(zone),
-				(zone->present_pages +
+				(zone->managed_pages +
 					KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
 				KSWAPD_ZONE_BALANCE_GAP_RATIO);
 			/*
@@ -2720,12 +2772,10 @@ loop_again:
 			}
 
 			/*
-			 * If we've done a decent amount of scanning and
-			 * the reclaim ratio is low, start doing writepage
-			 * even in laptop mode
+			 * If we're getting trouble reclaiming, start doing
+			 * writepage even in laptop mode.
 			 */
-			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
-			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
+			if (sc.priority < DEF_PRIORITY - 2)
 				sc.may_writepage = 1;
 
 			if (zone->all_unreclaimable) {
@@ -2734,17 +2784,7 @@ loop_again:
 				continue;
 			}
 
-			if (!zone_balanced(zone, testorder, 0, end_zone)) {
-				unbalanced_zone = zone;
-				/*
-				 * We are still under min water mark.  This
-				 * means that we have a GFP_ATOMIC allocation
-				 * failure risk. Hurry up!
-				 */
-				if (!zone_watermark_ok_safe(zone, order,
-					    min_wmark_pages(zone), end_zone, 0))
-					has_under_min_watermark_zone = 1;
-			} else {
+			if (zone_balanced(zone, testorder, 0, end_zone))
 				/*
 				 * If a zone reaches its high watermark,
 				 * consider it to be no longer congested. It's
@@ -2753,8 +2793,6 @@ loop_again:
 				 * speculatively avoid congestion waits
 				 */
 				zone_clear_flag(zone, ZONE_CONGESTED);
-			}
-
 		}
 
 		/*
@@ -2766,17 +2804,9 @@ loop_again:
 				pfmemalloc_watermark_ok(pgdat))
 			wake_up(&pgdat->pfmemalloc_wait);
 
-		if (pgdat_balanced(pgdat, order, *classzone_idx))
+		if (pgdat_balanced(pgdat, order, *classzone_idx)) {
+			pgdat_is_balanced = true;
 			break;		/* kswapd: all done */
-		/*
-		 * OK, kswapd is getting into trouble.  Take a nap, then take
-		 * another pass across the zones.
-		 */
-		if (total_scanned && (sc.priority < DEF_PRIORITY - 2)) {
-			if (has_under_min_watermark_zone)
-				count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
-			else if (unbalanced_zone)
-				wait_iff_congested(unbalanced_zone, BLK_RW_ASYNC, HZ/10);
 		}
 
 		/*
@@ -2788,9 +2818,9 @@ loop_again:
 		if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
 			break;
 	} while (--sc.priority >= 0);
-out:
 
-	if (!pgdat_balanced(pgdat, order, *classzone_idx)) {
+out:
+	if (!pgdat_is_balanced) {
 		cond_resched();
 
 		try_to_freeze();
@@ -3053,7 +3083,7 @@ unsigned long global_reclaimable_pages(void)
 	nr = global_page_state(NR_ACTIVE_FILE) +
 	     global_page_state(NR_INACTIVE_FILE);
 
-	if (nr_swap_pages > 0)
+	if (get_nr_swap_pages() > 0)
 		nr += global_page_state(NR_ACTIVE_ANON) +
 		      global_page_state(NR_INACTIVE_ANON);
 
@@ -3067,7 +3097,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
 	     zone_page_state(zone, NR_INACTIVE_FILE);
 
-	if (nr_swap_pages > 0)
+	if (get_nr_swap_pages() > 0)
 		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
 		      zone_page_state(zone, NR_INACTIVE_ANON);
 
@@ -3280,9 +3310,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
 		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
 		.may_swap = 1,
-		.nr_to_reclaim = max_t(unsigned long, nr_pages,
-				       SWAP_CLUSTER_MAX),
-		.gfp_mask = gfp_mask,
+		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
+		.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
 		.order = order,
 		.priority = ZONE_RECLAIM_PRIORITY,
 	};
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 9800306c819..e1d8ed172c4 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -142,7 +142,7 @@ int calculate_normal_threshold(struct zone *zone)
 	 * 125		1024		10	16-32 GB	9
 	 */
 
-	mem = zone->present_pages >> (27 - PAGE_SHIFT);
+	mem = zone->managed_pages >> (27 - PAGE_SHIFT);
 
 	threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem));
 
@@ -628,7 +628,9 @@ static char * const migratetype_names[MIGRATE_TYPES] = {
 #ifdef CONFIG_CMA
 	"CMA",
 #endif
+#ifdef CONFIG_MEMORY_ISOLATION
 	"Isolate",
+#endif
 };
 
 static void *frag_start(struct seq_file *m, loff_t *pos)
@@ -768,7 +770,6 @@ const char * const vmstat_text[] = {
 	"kswapd_inodesteal",
 	"kswapd_low_wmark_hit_quickly",
 	"kswapd_high_wmark_hit_quickly",
-	"kswapd_skip_congestion_wait",
 	"pageoutrun",
 	"allocstall",
 
@@ -890,7 +891,7 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m,
 	int mtype;
 	unsigned long pfn;
 	unsigned long start_pfn = zone->zone_start_pfn;
-	unsigned long end_pfn = start_pfn + zone->spanned_pages;
+	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long count[MIGRATE_TYPES] = { 0, };
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
author	Linus Torvalds <torvalds@linux-foundation.org>	2013-02-23 17:50:35 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2013-02-23 17:50:35 -0800
commit	5ce1a70e2f00f0bce0cab57f798ca354b9496169 (patch)
tree	6e80200536b7a3576fd71ff2c7135ffe87dc858e /mm
parent	9d3cae26acb471d5954cfdc25d1438b32060babe (diff)
parent	ef53d16cded7f89b3843b7a96970dab897843ea5 (diff)