50 files changed, 2430 insertions, 1715 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 026771a9b097..723bbe04a0b0 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -20,7 +20,7 @@ config FLATMEM_MANUAL
 
 	  Some users of more advanced features like NUMA and
 	  memory hotplug may have different options here.
-	  DISCONTIGMEM is an more mature, better tested system,
+	  DISCONTIGMEM is a more mature, better tested system,
 	  but is incompatible with memory hotplug and may suffer
 	  decreased performance over SPARSEMEM.  If unsure between
 	  "Sparse Memory" and "Discontiguous Memory", choose
@@ -153,11 +153,18 @@ config MOVABLE_NODE
 	help
 	  Allow a node to have only movable memory.  Pages used by the kernel,
 	  such as direct mapping pages cannot be migrated.  So the corresponding
-	  memory device cannot be hotplugged.  This option allows users to
-	  online all the memory of a node as movable memory so that the whole
-	  node can be hotplugged.  Users who don't use the memory hotplug
-	  feature are fine with this option on since they don't online memory
-	  as movable.
+	  memory device cannot be hotplugged.  This option allows the following
+	  two things:
+	  - When the system is booting, node full of hotpluggable memory can
+	  be arranged to have only movable memory so that the whole node can
+	  be hot-removed. (need movable_node boot option specified).
+	  - After the system is up, the option allows users to online all the
+	  memory of a node as movable memory so that the whole node can be
+	  hot-removed.
+
+	  Users who don't use the memory hotplug feature are fine with this
+	  option on since they don't specify movable_node boot option or they
+	  don't online memory as movable.
 
 	  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.
@@ -183,7 +190,7 @@ config MEMORY_HOTPLUG_SPARSE
 config MEMORY_HOTREMOVE
 	bool "Allow for memory hot remove"
 	select MEMORY_ISOLATION
-	select HAVE_BOOTMEM_INFO_NODE if X86_64
+	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
 	depends on MIGRATION
 
@@ -211,9 +218,11 @@ config SPLIT_PTLOCK_CPUS
 	int
 	default "999999" if ARM && !CPU_CACHE_VIPT
 	default "999999" if PARISC && !PA20
-	default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC
 	default "4"
 
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+	boolean
+
 #
 # support for memory balloon compaction
 config BALLOON_COMPACTION
@@ -534,7 +543,7 @@ config ZSWAP
 
 config MEM_SOFT_DIRTY
 	bool "Track memory changes"
-	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
+	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
 	select PROC_PAGE_MONITOR
 	help
 	  This option enables memory changes tracking by introducing a
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 6ab7744e692e..90bd3507b413 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -172,11 +172,12 @@ void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
 static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 {
 	struct page *page;
-	unsigned long start, end, pages, count = 0;
+	unsigned long *map, start, end, pages, count = 0;
 
 	if (!bdata->node_bootmem_map)
 		return 0;
 
+	map = bdata->node_bootmem_map;
 	start = bdata->node_min_pfn;
 	end = bdata->node_low_pfn;
 
@@ -184,10 +185,9 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 		bdata - bootmem_node_data, start, end);
 
 	while (start < end) {
-		unsigned long *map, idx, vec;
+		unsigned long idx, vec;
 		unsigned shift;
 
-		map = bdata->node_bootmem_map;
 		idx = start - bdata->node_min_pfn;
 		shift = idx & (BITS_PER_LONG - 1);
 		/*
@@ -784,7 +784,7 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
 	/* update goal according ...MAX_DMA32_PFN */
-	end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages;
+	end_pfn = pgdat_end_pfn(pgdat);
 
 	if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
 	    (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
diff --git a/mm/bounce.c b/mm/bounce.c
index c9f0a4339a7d..5a7d58fb883b 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -204,6 +204,8 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	struct bio_vec *to, *from;
 	unsigned i;
 
+	if (force)
+		goto bounce;
 	bio_for_each_segment(from, *bio_orig, i)
 		if (page_to_pfn(from->bv_page) > queue_bounce_pfn(q))
 			goto bounce;
diff --git a/mm/compaction.c b/mm/compaction.c
index c43789388cd8..f58bcd016f43 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -134,6 +134,10 @@ static void update_pageblock_skip(struct compact_control *cc,
 			bool migrate_scanner)
 {
 	struct zone *zone = cc->zone;
+
+	if (cc->ignore_skip_hint)
+		return;
+
 	if (!page)
 		return;
 
@@ -235,10 +239,9 @@ static bool suitable_migration_target(struct page *page)
 }
 
 /*
- * Isolate free pages onto a private freelist. Caller must hold zone->lock.
- * If @strict is true, will abort returning 0 on any invalid PFNs or non-free
- * pages inside of the pageblock (even though it may still end up isolating
- * some pages).
+ * Isolate free pages onto a private freelist. If @strict is true, will abort
+ * returning 0 on any invalid PFNs or non-free pages inside of the pageblock
+ * (even though it may still end up isolating some pages).
  */
 static unsigned long isolate_freepages_block(struct compact_control *cc,
 				unsigned long blockpfn,
@@ -677,6 +680,13 @@ static void isolate_freepages(struct zone *zone,
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
 
+		/*
+		 * This can iterate a massively long zone without finding any
+		 * suitable migration targets, so periodically check if we need
+		 * to schedule.
+		 */
+		cond_resched();
+
 		if (!pfn_valid(pfn))
 			continue;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 1e6aec4a2d2e..b7749a92021c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1090,7 +1090,6 @@ static void shrink_readahead_size_eio(struct file *filp,
  * @filp:	the file to read
  * @ppos:	current file position
  * @desc:	read_descriptor
- * @actor:	read method
  *
  * This is a generic file read routine, and uses the
  * mapping->a_ops->readpage() function for the actual low-level stuff.
@@ -1099,7 +1098,7 @@ static void shrink_readahead_size_eio(struct file *filp,
  * of the logic when it comes to error handling etc.
  */
 static void do_generic_file_read(struct file *filp, loff_t *ppos,
-		read_descriptor_t *desc, read_actor_t actor)
+		read_descriptor_t *desc)
 {
 	struct address_space *mapping = filp->f_mapping;
 	struct inode *inode = mapping->host;
@@ -1200,13 +1199,14 @@ page_ok:
 		 * Ok, we have the page, and it's up-to-date, so
 		 * now we can copy it to user space...
 		 *
-		 * The actor routine returns how many bytes were actually used..
+		 * The file_read_actor routine returns how many bytes were
+		 * actually used..
 		 * NOTE! This may not be the same as how much of a user buffer
 		 * we filled up (we may be padding etc), so we can only update
 		 * "pos" here (the actor routine has to update the user buffer
 		 * pointers and the remaining count).
 		 */
-		ret = actor(desc, page, offset, nr);
+		ret = file_read_actor(desc, page, offset, nr);
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
@@ -1479,7 +1479,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		if (desc.count == 0)
 			continue;
 		desc.error = 0;
-		do_generic_file_read(filp, ppos, &desc, file_read_actor);
+		do_generic_file_read(filp, ppos, &desc);
 		retval += desc.written;
 		if (desc.error) {
 			retval = retval ?: desc.error;
@@ -1616,7 +1616,6 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct inode *inode = mapping->host;
 	pgoff_t offset = vmf->pgoff;
 	struct page *page;
-	bool memcg_oom;
 	pgoff_t size;
 	int ret = 0;
 
@@ -1625,11 +1624,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	/*
-	 * Do we have something in the page cache already?  Either
-	 * way, try readahead, but disable the memcg OOM killer for it
-	 * as readahead is optional and no errors are propagated up
-	 * the fault stack.  The OOM killer is enabled while trying to
-	 * instantiate the faulting page individually below.
+	 * Do we have something in the page cache already?
 	 */
 	page = find_get_page(mapping, offset);
 	if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
@@ -1637,14 +1632,10 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		 * We found the page, so try async readahead before
 		 * waiting for the lock.
 		 */
-		memcg_oom = mem_cgroup_toggle_oom(false);
 		do_async_mmap_readahead(vma, ra, file, page, offset);
-		mem_cgroup_toggle_oom(memcg_oom);
 	} else if (!page) {
 		/* No page in the page cache at all */
-		memcg_oom = mem_cgroup_toggle_oom(false);
 		do_sync_mmap_readahead(vma, ra, file, offset);
-		mem_cgroup_toggle_oom(memcg_oom);
 		count_vm_event(PGMAJFAULT);
 		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 28fe26b64f8a..d8d9fe3f685c 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -26,7 +26,7 @@
  * of ZERO_PAGE(), such as /dev/zero
  */
 static DEFINE_MUTEX(xip_sparse_mutex);
-static seqcount_t xip_sparse_seq = SEQCNT_ZERO;
+static seqcount_t xip_sparse_seq = SEQCNT_ZERO(xip_sparse_seq);
 static struct page *__xip_sparse_page;
 
 /* called under xip_sparse_mutex */
diff --git a/mm/fremap.c b/mm/fremap.c
index 5bff08147768..bbc4d660221a 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -208,9 +208,10 @@ get_write_lock:
 		if (mapping_cap_account_dirty(mapping)) {
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
+			/* mmap_region may free vma; grab the info now */
+			vm_flags = vma->vm_flags;
 
-			addr = mmap_region(file, start, size,
-					vma->vm_flags, pgoff);
+			addr = mmap_region(file, start, size, vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -218,7 +219,7 @@ get_write_lock:
 				BUG_ON(addr != start);
 				err = 0;
 			}
-			goto out;
+			goto out_freed;
 		}
 		mutex_lock(&mapping->i_mmap_mutex);
 		flush_dcache_mmap_lock(mapping);
@@ -253,6 +254,7 @@ get_write_lock:
 out:
 	if (vma)
 		vm_flags = vma->vm_flags;
+out_freed:
 	if (likely(!has_write_lock))
 		up_read(&mm->mmap_sem);
 	else
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7489884682d8..9c0b17295ba0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -27,11 +27,12 @@
 #include "internal.h"
 
 /*
- * By default transparent hugepage support is enabled for all mappings
- * and khugepaged scans all mappings. Defrag is only invoked by
- * khugepaged hugepage allocations and by page faults inside
- * MADV_HUGEPAGE regions to avoid the risk of slowing down short lived
- * allocations.
+ * By default transparent hugepage support is disabled in order that avoid
+ * to risk increase the memory footprint of applications without a guaranteed
+ * benefit. When transparent hugepage support is enabled, is for all mappings,
+ * and khugepaged scans all mappings.
+ * Defrag is invoked by khugepaged hugepage allocations and by page faults
+ * for all hugepage allocations.
  */
 unsigned long transparent_hugepage_flags __read_mostly =
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
@@ -709,6 +710,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 					struct page *page)
 {
 	pgtable_t pgtable;
+	spinlock_t *ptl;
 
 	VM_BUG_ON(!PageCompound(page));
 	pgtable = pte_alloc_one(mm, haddr);
@@ -723,9 +725,9 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 	 */
 	__SetPageUptodate(page);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_none(*pmd))) {
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		mem_cgroup_uncharge_page(page);
 		put_page(page);
 		pte_free(mm, pgtable);
@@ -737,8 +739,8 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		set_pmd_at(mm, haddr, pmd, entry);
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
-		mm->nr_ptes++;
-		spin_unlock(&mm->page_table_lock);
+		atomic_long_inc(&mm->nr_ptes);
+		spin_unlock(ptl);
 	}
 
 	return 0;
@@ -758,14 +760,7 @@ static inline struct page *alloc_hugepage_vma(int defrag,
 			       HPAGE_PMD_ORDER, vma, haddr, nd);
 }
 
-#ifndef CONFIG_NUMA
-static inline struct page *alloc_hugepage(int defrag)
-{
-	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
-			   HPAGE_PMD_ORDER);
-}
-#endif
-
+/* Caller must hold page table lock. */
 static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
 		struct page *zero_page)
@@ -778,7 +773,7 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 	entry = pmd_mkhuge(entry);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
-	mm->nr_ptes++;
+	atomic_long_inc(&mm->nr_ptes);
 	return true;
 }
 
@@ -797,6 +792,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return VM_FAULT_OOM;
 	if (!(flags & FAULT_FLAG_WRITE) &&
 			transparent_hugepage_use_zero_page()) {
+		spinlock_t *ptl;
 		pgtable_t pgtable;
 		struct page *zero_page;
 		bool set;
@@ -809,10 +805,10 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			count_vm_event(THP_FAULT_FALLBACK);
 			return VM_FAULT_FALLBACK;
 		}
-		spin_lock(&mm->page_table_lock);
+		ptl = pmd_lock(mm, pmd);
 		set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
 				zero_page);
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		if (!set) {
 			pte_free(mm, pgtable);
 			put_huge_zero_page();
@@ -845,6 +841,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 		  struct vm_area_struct *vma)
 {
+	spinlock_t *dst_ptl, *src_ptl;
 	struct page *src_page;
 	pmd_t pmd;
 	pgtable_t pgtable;
@@ -855,8 +852,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (unlikely(!pgtable))
 		goto out;
 
-	spin_lock(&dst_mm->page_table_lock);
-	spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING);
+	dst_ptl = pmd_lock(dst_mm, dst_pmd);
+	src_ptl = pmd_lockptr(src_mm, src_pmd);
+	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 
 	ret = -EAGAIN;
 	pmd = *src_pmd;
@@ -865,7 +863,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		goto out_unlock;
 	}
 	/*
-	 * mm->page_table_lock is enough to be sure that huge zero pmd is not
+	 * When page table lock is held, the huge zero pmd should not be
 	 * under splitting since we don't split the page itself, only pmd to
 	 * a page table.
 	 */
@@ -884,10 +882,11 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		ret = 0;
 		goto out_unlock;
 	}
+
 	if (unlikely(pmd_trans_splitting(pmd))) {
 		/* split huge page running from under us */
-		spin_unlock(&src_mm->page_table_lock);
-		spin_unlock(&dst_mm->page_table_lock);
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
 		pte_free(dst_mm, pgtable);
 
 		wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */
@@ -903,12 +902,12 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	pmd = pmd_mkold(pmd_wrprotect(pmd));
 	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
-	dst_mm->nr_ptes++;
+	atomic_long_inc(&dst_mm->nr_ptes);
 
 	ret = 0;
 out_unlock:
-	spin_unlock(&src_mm->page_table_lock);
-	spin_unlock(&dst_mm->page_table_lock);
+	spin_unlock(src_ptl);
+	spin_unlock(dst_ptl);
 out:
 	return ret;
 }
@@ -919,10 +918,11 @@ void huge_pmd_set_accessed(struct mm_struct *mm,
 			   pmd_t *pmd, pmd_t orig_pmd,
 			   int dirty)
 {
+	spinlock_t *ptl;
 	pmd_t entry;
 	unsigned long haddr;
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_same(*pmd, orig_pmd)))
 		goto unlock;
 
@@ -932,13 +932,14 @@ void huge_pmd_set_accessed(struct mm_struct *mm,
 		update_mmu_cache_pmd(vma, address, pmd);
 
 unlock:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 }
 
 static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd, pmd_t orig_pmd, unsigned long haddr)
 {
+	spinlock_t *ptl;
 	pgtable_t pgtable;
 	pmd_t _pmd;
 	struct page *page;
@@ -965,7 +966,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_same(*pmd, orig_pmd)))
 		goto out_free_page;
 
@@ -992,7 +993,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
 	}
 	smp_wmb(); /* make pte visible before pmd */
 	pmd_populate(mm, pmd, pgtable);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	put_huge_zero_page();
 	inc_mm_counter(mm, MM_ANONPAGES);
 
@@ -1002,7 +1003,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
 out:
 	return ret;
 out_free_page:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	mem_cgroup_uncharge_page(page);
 	put_page(page);
@@ -1016,6 +1017,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct page *page,
 					unsigned long haddr)
 {
+	spinlock_t *ptl;
 	pgtable_t pgtable;
 	pmd_t _pmd;
 	int ret = 0, i;
@@ -1062,7 +1064,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_same(*pmd, orig_pmd)))
 		goto out_free_pages;
 	VM_BUG_ON(!PageHead(page));
@@ -1088,7 +1090,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 	smp_wmb(); /* make pte visible before pmd */
 	pmd_populate(mm, pmd, pgtable);
 	page_remove_rmap(page);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
@@ -1099,7 +1101,7 @@ out:
 	return ret;
 
 out_free_pages:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	mem_cgroup_uncharge_start();
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
@@ -1114,17 +1116,19 @@ out_free_pages:
 int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pmd_t *pmd, pmd_t orig_pmd)
 {
+	spinlock_t *ptl;
 	int ret = 0;
 	struct page *page = NULL, *new_page;
 	unsigned long haddr;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
+	ptl = pmd_lockptr(mm, pmd);
 	VM_BUG_ON(!vma->anon_vma);
 	haddr = address & HPAGE_PMD_MASK;
 	if (is_huge_zero_pmd(orig_pmd))
 		goto alloc;
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	if (unlikely(!pmd_same(*pmd, orig_pmd)))
 		goto out_unlock;
 
@@ -1140,7 +1144,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_unlock;
 	}
 	get_page(page);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow())
@@ -1187,11 +1191,11 @@ alloc:
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	if (page)
 		put_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		mem_cgroup_uncharge_page(new_page);
 		put_page(new_page);
 		goto out_mn;
@@ -1213,13 +1217,13 @@ alloc:
 		}
 		ret |= VM_FAULT_WRITE;
 	}
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 out_mn:
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 out:
 	return ret;
 out_unlock:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	return ret;
 }
 
@@ -1231,7 +1235,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 	struct page *page = NULL;
 
-	assert_spin_locked(&mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(mm, pmd));
 
 	if (flags & FOLL_WRITE && !pmd_write(*pmd))
 		goto out;
@@ -1240,6 +1244,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
 		return ERR_PTR(-EFAULT);
 
+	/* Full NUMA hinting faults to serialise migration in fault paths */
+	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+		goto out;
+
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!PageHead(page));
 	if (flags & FOLL_TOUCH) {
@@ -1278,73 +1286,133 @@ out:
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+	spinlock_t *ptl;
+	struct anon_vma *anon_vma = NULL;
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
-	int target_nid;
-	int current_nid = -1;
-	bool migrated;
+	int page_nid = -1, this_nid = numa_node_id();
+	int target_nid, last_cpupid = -1;
+	bool page_locked;
+	bool migrated = false;
+	int flags = 0;
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmdp);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
+	/*
+	 * If there are potential migrations, wait for completion and retry
+	 * without disrupting NUMA hinting information. Do not relock and
+	 * check_same as the page may no longer be mapped.
+	 */
+	if (unlikely(pmd_trans_migrating(*pmdp))) {
+		spin_unlock(ptl);
+		wait_migrate_huge_page(vma->anon_vma, pmdp);
+		goto out;
+	}
+
 	page = pmd_page(pmd);
-	get_page(page);
-	current_nid = page_to_nid(page);
+	BUG_ON(is_huge_zero_page(page));
+	page_nid = page_to_nid(page);
+	last_cpupid = page_cpupid_last(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == this_nid) {
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
+		flags |= TNF_FAULT_LOCAL;
+	}
 
+	/*
+	 * Avoid grouping on DSO/COW pages in specific and RO pages
+	 * in general, RO pages shouldn't hurt as much anyway since
+	 * they can be in shared cache state.
+	 */
+	if (!pmd_write(pmd))
+		flags |= TNF_NO_GROUP;
+
+	/*
+	 * Acquire the page lock to serialise THP migrations but avoid dropping
+	 * page_table_lock if at all possible
+	 */
+	page_locked = trylock_page(page);
 	target_nid = mpol_misplaced(page, vma, haddr);
 	if (target_nid == -1) {
-		put_page(page);
-		goto clear_pmdnuma;
+		/* If the page was locked, there are no parallel migrations */
+		if (page_locked)
+			goto clear_pmdnuma;
 	}
 
-	/* Acquire the page lock to serialise THP migrations */
-	spin_unlock(&mm->page_table_lock);
-	lock_page(page);
+	/* Migration could have started since the pmd_trans_migrating check */
+	if (!page_locked) {
+		spin_unlock(ptl);
+		wait_on_page_locked(page);
+		page_nid = -1;
+		goto out;
+	}
 
-	/* Confirm the PTE did not while locked */
-	spin_lock(&mm->page_table_lock);
+	/*
+	 * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
+	 * to serialises splits
+	 */
+	get_page(page);
+	spin_unlock(ptl);
+	anon_vma = page_lock_anon_vma_read(page);
+
+	/* Confirm the PMD did not change while page_table_lock was released */
+	spin_lock(ptl);
 	if (unlikely(!pmd_same(pmd, *pmdp))) {
 		unlock_page(page);
 		put_page(page);
+		page_nid = -1;
 		goto out_unlock;
 	}
-	spin_unlock(&mm->page_table_lock);
 
-	/* Migrate the THP to the requested node */
+	/* Bail if we fail to protect against THP splits for any reason */
+	if (unlikely(!anon_vma)) {
+		put_page(page);
+		page_nid = -1;
+		goto clear_pmdnuma;
+	}
+
+	/*
+	 * Migrate the THP to the requested node, returns with page unlocked
+	 * and pmd_numa cleared.
+	 */
+	spin_unlock(ptl);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
 				pmdp, pmd, addr, page, target_nid);
-	if (!migrated)
-		goto check_same;
-
-	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
-	return 0;
+	if (migrated) {
+		flags |= TNF_MIGRATED;
+		page_nid = target_nid;
+	}
 
-check_same:
-	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(pmd, *pmdp)))
-		goto out_unlock;
+	goto out;
 clear_pmdnuma:
+	BUG_ON(!PageLocked(page));
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
+	unlock_page(page);
 out_unlock:
-	spin_unlock(&mm->page_table_lock);
-	if (current_nid != -1)
-		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
+	spin_unlock(ptl);
+
+out:
+	if (anon_vma)
+		page_unlock_anon_vma_read(anon_vma);
+
+	if (page_nid != -1)
+		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags);
+
 	return 0;
 }
 
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
+	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		struct page *page;
 		pgtable_t pgtable;
 		pmd_t orig_pmd;
@@ -1358,8 +1426,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
 		if (is_huge_zero_pmd(orig_pmd)) {
-			tlb->mm->nr_ptes--;
-			spin_unlock(&tlb->mm->page_table_lock);
+			atomic_long_dec(&tlb->mm->nr_ptes);
+			spin_unlock(ptl);
 			put_huge_zero_page();
 		} else {
 			page = pmd_page(orig_pmd);
@@ -1367,8 +1435,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			VM_BUG_ON(page_mapcount(page) < 0);
 			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
 			VM_BUG_ON(!PageHead(page));
-			tlb->mm->nr_ptes--;
-			spin_unlock(&tlb->mm->page_table_lock);
+			atomic_long_dec(&tlb->mm->nr_ptes);
+			spin_unlock(ptl);
 			tlb_remove_page(tlb, page);
 		}
 		pte_free(tlb->mm, pgtable);
@@ -1381,14 +1449,15 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end,
 		unsigned char *vec)
 {
+	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		/*
 		 * All logical pages in the range are present
 		 * if backed by a huge page.
 		 */
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 		memset(vec, 1, (end - addr) >> PAGE_SHIFT);
 		ret = 1;
 	}
@@ -1401,6 +1470,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		  unsigned long new_addr, unsigned long old_end,
 		  pmd_t *old_pmd, pmd_t *new_pmd)
 {
+	spinlock_t *old_ptl, *new_ptl;
 	int ret = 0;
 	pmd_t pmd;
 
@@ -1421,41 +1491,81 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		goto out;
 	}
 
-	ret = __pmd_trans_huge_lock(old_pmd, vma);
+	/*
+	 * We don't have to worry about the ordering of src and dst
+	 * ptlocks because exclusive mmap_sem prevents deadlock.
+	 */
+	ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl);
 	if (ret == 1) {
+		new_ptl = pmd_lockptr(mm, new_pmd);
+		if (new_ptl != old_ptl)
+			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
 		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
 		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
-		spin_unlock(&mm->page_table_lock);
+		if (new_ptl != old_ptl) {
+			pgtable_t pgtable;
+
+			/*
+			 * Move preallocated PTE page table if new_pmd is on
+			 * different PMD page table.
+			 */
+			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
+			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
+
+			spin_unlock(new_ptl);
+		}
+		spin_unlock(old_ptl);
 	}
 out:
 	return ret;
 }
 
+/*
+ * Returns
+ *  - 0 if PMD could not be locked
+ *  - 1 if PMD was locked but protections unchange and TLB flush unnecessary
+ *  - HPAGE_PMD_NR is protections changed and TLB flush necessary
+ */
 int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, pgprot_t newprot, int prot_numa)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pmd_t entry;
-		entry = pmdp_get_and_clear(mm, addr, pmd);
+		ret = 1;
 		if (!prot_numa) {
+			entry = pmdp_get_and_clear(mm, addr, pmd);
+			if (pmd_numa(entry))
+				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
+			ret = HPAGE_PMD_NR;
 			BUG_ON(pmd_write(entry));
 		} else {
 			struct page *page = pmd_page(*pmd);
 
-			/* only check non-shared pages */
-			if (page_mapcount(page) == 1 &&
+			/*
+			 * Do not trap faults against the zero page. The
+			 * read-only data is likely to be read-cached on the
+			 * local CPU cache and it is less useful to know about
+			 * local vs remote hits on the zero page.
+			 */
+			if (!is_huge_zero_page(page) &&
 			    !pmd_numa(*pmd)) {
+				entry = *pmd;
 				entry = pmd_mknuma(entry);
+				ret = HPAGE_PMD_NR;
 			}
 		}
-		set_pmd_at(mm, addr, pmd, entry);
-		spin_unlock(&vma->vm_mm->page_table_lock);
-		ret = 1;
+
+		/* Set PMD if cleared earlier */
+		if (ret == HPAGE_PMD_NR)
+			set_pmd_at(mm, addr, pmd, entry);
+
+		spin_unlock(ptl);
 	}
 
 	return ret;
@@ -1468,12 +1578,13 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
  * Note that if it returns 1, this routine returns without unlocking page
  * table locks. So callers must unlock them.
  */
-int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
+int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+		spinlock_t **ptl)
 {
-	spin_lock(&vma->vm_mm->page_table_lock);
+	*ptl = pmd_lock(vma->vm_mm, pmd);
 	if (likely(pmd_trans_huge(*pmd))) {
 		if (unlikely(pmd_trans_splitting(*pmd))) {
-			spin_unlock(&vma->vm_mm->page_table_lock);
+			spin_unlock(*ptl);
 			wait_split_huge_page(vma->anon_vma, pmd);
 			return -1;
 		} else {
@@ -1482,27 +1593,37 @@ int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
 			return 1;
 		}
 	}
-	spin_unlock(&vma->vm_mm->page_table_lock);
+	spin_unlock(*ptl);
 	return 0;
 }
 
+/*
+ * This function returns whether a given @page is mapped onto the @address
+ * in the virtual space of @mm.
+ *
+ * When it's true, this function returns *pmd with holding the page table lock
+ * and passing it back to the caller via @ptl.
+ * If it's false, returns NULL without holding the page table lock.
+ */
 pmd_t *page_check_address_pmd(struct page *page,
 			      struct mm_struct *mm,
 			      unsigned long address,
-			      enum page_check_address_pmd_flag flag)
+			      enum page_check_address_pmd_flag flag,
+			      spinlock_t **ptl)
 {
-	pmd_t *pmd, *ret = NULL;
+	pmd_t *pmd;
 
 	if (address & ~HPAGE_PMD_MASK)
-		goto out;
+		return NULL;
 
 	pmd = mm_find_pmd(mm, address);
 	if (!pmd)
-		goto out;
+		return NULL;
+	*ptl = pmd_lock(mm, pmd);
 	if (pmd_none(*pmd))
-		goto out;
+		goto unlock;
 	if (pmd_page(*pmd) != page)
-		goto out;
+		goto unlock;
 	/*
 	 * split_vma() may create temporary aliased mappings. There is
 	 * no risk as long as all huge pmd are found and have their
@@ -1512,14 +1633,15 @@ pmd_t *page_check_address_pmd(struct page *page,
 	 */
 	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
 	    pmd_trans_splitting(*pmd))
-		goto out;
+		goto unlock;
 	if (pmd_trans_huge(*pmd)) {
 		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
 			  !pmd_trans_splitting(*pmd));
-		ret = pmd;
+		return pmd;
 	}
-out:
-	return ret;
+unlock:
+	spin_unlock(*ptl);
+	return NULL;
 }
 
 static int __split_huge_page_splitting(struct page *page,
@@ -1527,6 +1649,7 @@ static int __split_huge_page_splitting(struct page *page,
 				       unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	pmd_t *pmd;
 	int ret = 0;
 	/* For mmu_notifiers */
@@ -1534,9 +1657,8 @@ static int __split_huge_page_splitting(struct page *page,
 	const unsigned long mmun_end   = address + HPAGE_PMD_SIZE;
 
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-	spin_lock(&mm->page_table_lock);
 	pmd = page_check_address_pmd(page, mm, address,
-				     PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG);
+			PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, &ptl);
 	if (pmd) {
 		/*
 		 * We can't temporarily set the pmd to null in order
@@ -1547,8 +1669,8 @@ static int __split_huge_page_splitting(struct page *page,
 		 */
 		pmdp_splitting_flush(vma, address, pmd);
 		ret = 1;
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 	return ret;
@@ -1636,7 +1758,7 @@ static void __split_huge_page_refcount(struct page *page,
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
-		page_nid_xchg_last(page_tail, page_nid_last(page));
+		page_cpupid_xchg_last(page_tail, page_cpupid_last(page));
 
 		BUG_ON(!PageAnon(page_tail));
 		BUG_ON(!PageUptodate(page_tail));
@@ -1679,14 +1801,14 @@ static int __split_huge_page_map(struct page *page,
 				 unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	pmd_t *pmd, _pmd;
 	int ret = 0, i;
 	pgtable_t pgtable;
 	unsigned long haddr;
 
-	spin_lock(&mm->page_table_lock);
 	pmd = page_check_address_pmd(page, mm, address,
-				     PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
+			PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, &ptl);
 	if (pmd) {
 		pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 		pmd_populate(mm, &_pmd, pgtable);
@@ -1741,8 +1863,8 @@ static int __split_huge_page_map(struct page *page,
 		pmdp_invalidate(vma, address, pmd);
 		pmd_populate(mm, pmd, pgtable);
 		ret = 1;
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 
 	return ret;
 }
@@ -2139,7 +2261,34 @@ static void khugepaged_alloc_sleep(void)
 			msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
 }
 
+static int khugepaged_node_load[MAX_NUMNODES];
+
 #ifdef CONFIG_NUMA
+static int khugepaged_find_target_node(void)
+{
+	static int last_khugepaged_target_node = NUMA_NO_NODE;
+	int nid, target_node = 0, max_value = 0;
+
+	/* find first node with max normal pages hit */
+	for (nid = 0; nid < MAX_NUMNODES; nid++)
+		if (khugepaged_node_load[nid] > max_value) {
+			max_value = khugepaged_node_load[nid];
+			target_node = nid;
+		}
+
+	/* do some balance if several nodes have the same hit record */
+	if (target_node <= last_khugepaged_target_node)
+		for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES;
+				nid++)
+			if (max_value == khugepaged_node_load[nid]) {
+				target_node = nid;
+				break;
+			}
+
+	last_khugepaged_target_node = target_node;
+	return target_node;
+}
+
 static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
 {
 	if (IS_ERR(*hpage)) {
@@ -2173,9 +2322,8 @@ static struct page
 	 * mmap_sem in read mode is good idea also to allow greater
 	 * scalability.
 	 */
-	*hpage  = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
-				      node, __GFP_OTHER_NODE);
-
+	*hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask(
+		khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER);
 	/*
 	 * After allocating the hugepage, release the mmap_sem read lock in
 	 * preparation for taking it in write mode.
@@ -2191,6 +2339,17 @@ static struct page
 	return *hpage;
 }
 #else
+static int khugepaged_find_target_node(void)
+{
+	return 0;
+}
+
+static inline struct page *alloc_hugepage(int defrag)
+{
+	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
+			   HPAGE_PMD_ORDER);
+}
+
 static struct page *khugepaged_alloc_hugepage(bool *wait)
 {
 	struct page *hpage;
@@ -2257,7 +2416,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	pte_t *pte;
 	pgtable_t pgtable;
 	struct page *new_page;
-	spinlock_t *ptl;
+	spinlock_t *pmd_ptl, *pte_ptl;
 	int isolated;
 	unsigned long hstart, hend;
 	unsigned long mmun_start;	/* For mmu_notifiers */
@@ -2300,12 +2459,12 @@ static void collapse_huge_page(struct mm_struct *mm,
 	anon_vma_lock_write(vma->anon_vma);
 
 	pte = pte_offset_map(pmd, address);
-	ptl = pte_lockptr(mm, pmd);
+	pte_ptl = pte_lockptr(mm, pmd);
 
 	mmun_start = address;
 	mmun_end   = address + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-	spin_lock(&mm->page_table_lock); /* probably unnecessary */
+	pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
 	/*
 	 * After this gup_fast can't run anymore. This also removes
 	 * any huge TLB entry from the CPU so we won't allow
@@ -2313,16 +2472,16 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * to avoid the risk of CPU bugs in that area.
 	 */
 	_pmd = pmdp_clear_flush(vma, address, pmd);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(pmd_ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
-	spin_lock(ptl);
+	spin_lock(pte_ptl);
 	isolated = __collapse_huge_page_isolate(vma, address, pte);
-	spin_unlock(ptl);
+	spin_unlock(pte_ptl);
 
 	if (unlikely(!isolated)) {
 		pte_unmap(pte);
-		spin_lock(&mm->page_table_lock);
+		spin_lock(pmd_ptl);
 		BUG_ON(!pmd_none(*pmd));
 		/*
 		 * We can only use set_pmd_at when establishing
@@ -2330,7 +2489,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 		 * points to regular pagetables. Use pmd_populate for that
 		 */
 		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(pmd_ptl);
 		anon_vma_unlock_write(vma->anon_vma);
 		goto out;
 	}
@@ -2341,7 +2500,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 */
 	anon_vma_unlock_write(vma->anon_vma);
 
-	__collapse_huge_page_copy(pte, new_page, vma, address, ptl);
+	__collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl);
 	pte_unmap(pte);
 	__SetPageUptodate(new_page);
 	pgtable = pmd_pgtable(_pmd);
@@ -2356,13 +2515,13 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 */
 	smp_wmb();
 
-	spin_lock(&mm->page_table_lock);
+	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
 	page_add_new_anon_rmap(new_page, vma, address);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(pmd_ptl);
 
 	*hpage = NULL;
 
@@ -2397,6 +2556,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	if (pmd_trans_huge(*pmd))
 		goto out;
 
+	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
 	     _pte++, _address += PAGE_SIZE) {
@@ -2413,12 +2573,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		if (unlikely(!page))
 			goto out_unmap;
 		/*
-		 * Chose the node of the first page. This could
-		 * be more sophisticated and look at more pages,
-		 * but isn't for now.
+		 * Record which node the original page is from and save this
+		 * information to khugepaged_node_load[].
+		 * Khupaged will allocate hugepage from the node has the max
+		 * hit record.
 		 */
-		if (node == NUMA_NO_NODE)
-			node = page_to_nid(page);
+		node = page_to_nid(page);
+		khugepaged_node_load[node]++;
 		VM_BUG_ON(PageCompound(page));
 		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
 			goto out_unmap;
@@ -2433,9 +2594,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		ret = 1;
 out_unmap:
 	pte_unmap_unlock(pte, ptl);
-	if (ret)
+	if (ret) {
+		node = khugepaged_find_target_node();
 		/* collapse_huge_page will return with the mmap_sem released */
 		collapse_huge_page(mm, address, hpage, vma, node);
+	}
 out:
 	return ret;
 }
@@ -2687,6 +2850,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd)
 {
+	spinlock_t *ptl;
 	struct page *page;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
@@ -2697,29 +2861,37 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 
 	mmun_start = haddr;
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
+again:
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_trans_huge(*pmd))) {
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 		return;
 	}
 	if (is_huge_zero_pmd(*pmd)) {
 		__split_huge_zero_page_pmd(vma, haddr, pmd);
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 		return;
 	}
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!page_count(page));
 	get_page(page);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 	split_huge_page(page);
 
 	put_page(page);
-	BUG_ON(pmd_trans_huge(*pmd));
+
+	/*
+	 * We don't always have down_write of mmap_sem here: a racing
+	 * do_huge_pmd_wp_page() might have copied-on-write to another
+	 * huge page before our split_huge_page() got the anon_vma lock.
+	 */
+	if (unlikely(pmd_trans_huge(*pmd)))
+		goto again;
 }
 
 void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b49579c7f2a5..dee6cf4e6d34 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -476,40 +476,6 @@ static int vma_has_reserves(struct vm_area_struct *vma, long chg)
 	return 0;
 }
 
-static void copy_gigantic_page(struct page *dst, struct page *src)
-{
-	int i;
-	struct hstate *h = page_hstate(src);
-	struct page *dst_base = dst;
-	struct page *src_base = src;
-
-	for (i = 0; i < pages_per_huge_page(h); ) {
-		cond_resched();
-		copy_highpage(dst, src);
-
-		i++;
-		dst = mem_map_next(dst, dst_base, i);
-		src = mem_map_next(src, src_base, i);
-	}
-}
-
-void copy_huge_page(struct page *dst, struct page *src)
-{
-	int i;
-	struct hstate *h = page_hstate(src);
-
-	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
-		copy_gigantic_page(dst, src);
-		return;
-	}
-
-	might_sleep();
-	for (i = 0; i < pages_per_huge_page(h); i++) {
-		cond_resched();
-		copy_highpage(dst + i, src + i);
-	}
-}
-
 static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
 	int nid = page_to_nid(page);
@@ -653,6 +619,7 @@ static void free_huge_page(struct page *page)
 	BUG_ON(page_count(page));
 	BUG_ON(page_mapcount(page));
 	restore_reserve = PagePrivate(page);
+	ClearPagePrivate(page);
 
 	spin_lock(&hugetlb_lock);
 	hugetlb_cgroup_uncharge_page(hstate_index(h),
@@ -695,8 +662,22 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
 	/* we rely on prep_new_huge_page to set the destructor */
 	set_compound_order(page, order);
 	__SetPageHead(page);
+	__ClearPageReserved(page);
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
 		__SetPageTail(p);
+		/*
+		 * For gigantic hugepages allocated through bootmem at
+		 * boot, it's safer to be consistent with the not-gigantic
+		 * hugepages and clear the PG_reserved bit from all tail pages
+		 * too.  Otherwse drivers using get_user_pages() to access tail
+		 * pages may get the reference counting wrong if they see
+		 * PG_reserved set on a tail page (despite the head page not
+		 * having PG_reserved set).  Enforcing this consistency between
+		 * head and tail pages allows drivers to optimize away a check
+		 * on the head page when they need know if put_page() is needed
+		 * after get_user_pages().
+		 */
+		__ClearPageReserved(p);
 		set_page_count(p, 0);
 		p->first_page = page;
 	}
@@ -721,6 +702,23 @@ int PageHuge(struct page *page)
 }
 EXPORT_SYMBOL_GPL(PageHuge);
 
+/*
+ * PageHeadHuge() only returns true for hugetlbfs head page, but not for
+ * normal or transparent huge pages.
+ */
+int PageHeadHuge(struct page *page_head)
+{
+	compound_page_dtor *dtor;
+
+	if (!PageHead(page_head))
+		return 0;
+
+	dtor = get_compound_page_dtor(page_head);
+
+	return dtor == free_huge_page;
+}
+EXPORT_SYMBOL_GPL(PageHeadHuge);
+
 pgoff_t __basepage_index(struct page *page)
 {
 	struct page *page_head = compound_head(page);
@@ -1329,9 +1327,9 @@ static void __init gather_bootmem_prealloc(void)
 #else
 		page = virt_to_page(m);
 #endif
-		__ClearPageReserved(page);
 		WARN_ON(page_count(page) != 1);
 		prep_compound_huge_page(page, h->order);
+		WARN_ON(PageReserved(page));
 		prep_new_huge_page(h, page, page_to_nid(page));
 		/*
 		 * If we had gigantic hugepages allocated at boot time, we need
@@ -2361,6 +2359,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
+		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr);
 		if (!src_pte)
 			continue;
@@ -2372,8 +2371,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		if (dst_pte == src_pte)
 			continue;
 
-		spin_lock(&dst->page_table_lock);
-		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
+		dst_ptl = huge_pte_lock(h, dst, dst_pte);
+		src_ptl = huge_pte_lockptr(h, src, src_pte);
+		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 		if (!huge_pte_none(huge_ptep_get(src_pte))) {
 			if (cow)
 				huge_ptep_set_wrprotect(src, addr, src_pte);
@@ -2383,8 +2383,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			page_dup_rmap(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
-		spin_unlock(&src->page_table_lock);
-		spin_unlock(&dst->page_table_lock);
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
 	}
 	return 0;
 
@@ -2427,6 +2427,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	unsigned long address;
 	pte_t *ptep;
 	pte_t pte;
+	spinlock_t *ptl;
 	struct page *page;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
@@ -2440,25 +2441,25 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	tlb_start_vma(tlb, vma);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 again:
-	spin_lock(&mm->page_table_lock);
 	for (address = start; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
 
+		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep))
-			continue;
+			goto unlock;
 
 		pte = huge_ptep_get(ptep);
 		if (huge_pte_none(pte))
-			continue;
+			goto unlock;
 
 		/*
 		 * HWPoisoned hugepage is already unmapped and dropped reference
 		 */
 		if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
 			huge_pte_clear(mm, address, ptep);
-			continue;
+			goto unlock;
 		}
 
 		page = pte_page(pte);
@@ -2469,7 +2470,7 @@ again:
 		 */
 		if (ref_page) {
 			if (page != ref_page)
-				continue;
+				goto unlock;
 
 			/*
 			 * Mark the VMA as having unmapped its page so that
@@ -2486,13 +2487,18 @@ again:
 
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
-		if (force_flush)
+		if (force_flush) {
+			spin_unlock(ptl);
 			break;
+		}
 		/* Bail out after unmapping reference page if supplied */
-		if (ref_page)
+		if (ref_page) {
+			spin_unlock(ptl);
 			break;
+		}
+unlock:
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	/*
 	 * mmu_gather ran out of room to batch pages, we break out of
 	 * the PTE lock to avoid doing the potential expensive TLB invalidate
@@ -2598,7 +2604,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
  */
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte,
-			struct page *pagecache_page)
+			struct page *pagecache_page, spinlock_t *ptl)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct page *old_page, *new_page;
@@ -2632,8 +2638,8 @@ retry_avoidcopy:
 
 	page_cache_get(old_page);
 
-	/* Drop page_table_lock as buddy allocator may be called */
-	spin_unlock(&mm->page_table_lock);
+	/* Drop page table lock as buddy allocator may be called */
+	spin_unlock(ptl);
 	new_page = alloc_huge_page(vma, address, outside_reserve);
 
 	if (IS_ERR(new_page)) {
@@ -2651,13 +2657,13 @@ retry_avoidcopy:
 			BUG_ON(huge_pte_none(pte));
 			if (unmap_ref_private(mm, vma, old_page, address)) {
 				BUG_ON(huge_pte_none(pte));
-				spin_lock(&mm->page_table_lock);
+				spin_lock(ptl);
 				ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 				if (likely(pte_same(huge_ptep_get(ptep), pte)))
 					goto retry_avoidcopy;
 				/*
-				 * race occurs while re-acquiring page_table_lock, and
-				 * our job is done.
+				 * race occurs while re-acquiring page table
+				 * lock, and our job is done.
 				 */
 				return 0;
 			}
@@ -2665,7 +2671,7 @@ retry_avoidcopy:
 		}
 
 		/* Caller expects lock to be held */
-		spin_lock(&mm->page_table_lock);
+		spin_lock(ptl);
 		if (err == -ENOMEM)
 			return VM_FAULT_OOM;
 		else
@@ -2680,7 +2686,7 @@ retry_avoidcopy:
 		page_cache_release(new_page);
 		page_cache_release(old_page);
 		/* Caller expects lock to be held */
-		spin_lock(&mm->page_table_lock);
+		spin_lock(ptl);
 		return VM_FAULT_OOM;
 	}
 
@@ -2692,10 +2698,10 @@ retry_avoidcopy:
 	mmun_end = mmun_start + huge_page_size(h);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	/*
-	 * Retake the page_table_lock to check for racing updates
+	 * Retake the page table lock to check for racing updates
 	 * before the page tables are altered
 	 */
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
 		ClearPagePrivate(new_page);
@@ -2709,13 +2715,13 @@ retry_avoidcopy:
 		/* Make the old page be freed below */
 		new_page = old_page;
 	}
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	page_cache_release(new_page);
 	page_cache_release(old_page);
 
 	/* Caller expects lock to be held */
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	return 0;
 }
 
@@ -2763,6 +2769,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	struct address_space *mapping;
 	pte_t new_pte;
+	spinlock_t *ptl;
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -2849,7 +2856,8 @@ retry:
 			goto backout_unlocked;
 		}
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(h, mm, ptep);
+	spin_lock(ptl);
 	size = i_size_read(mapping->host) >> huge_page_shift(h);
 	if (idx >= size)
 		goto backout;
@@ -2870,16 +2878,16 @@ retry:
 
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
-		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
+		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl);
 	}
 
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	unlock_page(page);
 out:
 	return ret;
 
 backout:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 backout_unlocked:
 	unlock_page(page);
 	put_page(page);
@@ -2891,6 +2899,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	pte_t *ptep;
 	pte_t entry;
+	spinlock_t *ptl;
 	int ret;
 	struct page *page = NULL;
 	struct page *pagecache_page = NULL;
@@ -2903,7 +2912,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait_huge(mm, ptep);
+			migration_entry_wait_huge(vma, mm, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
@@ -2959,17 +2968,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (page != pagecache_page)
 		lock_page(page);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(h, mm, ptep);
+	spin_lock(ptl);
 	/* Check for a racing update before calling hugetlb_cow */
 	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
-		goto out_page_table_lock;
+		goto out_ptl;
 
 
 	if (flags & FAULT_FLAG_WRITE) {
 		if (!huge_pte_write(entry)) {
 			ret = hugetlb_cow(mm, vma, address, ptep, entry,
-							pagecache_page);
-			goto out_page_table_lock;
+					pagecache_page, ptl);
+			goto out_ptl;
 		}
 		entry = huge_pte_mkdirty(entry);
 	}
@@ -2978,8 +2988,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 						flags & FAULT_FLAG_WRITE))
 		update_mmu_cache(vma, address, ptep);
 
-out_page_table_lock:
-	spin_unlock(&mm->page_table_lock);
+out_ptl:
+	spin_unlock(ptl);
 
 	if (pagecache_page) {
 		unlock_page(pagecache_page);
@@ -3005,9 +3015,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long remainder = *nr_pages;
 	struct hstate *h = hstate_vma(vma);
 
-	spin_lock(&mm->page_table_lock);
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
+		spinlock_t *ptl = NULL;
 		int absent;
 		struct page *page;
 
@@ -3015,8 +3025,12 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * Some archs (sparc64, sh*) have multiple pte_ts to
 		 * each hugepage.  We have to make sure we get the
 		 * first, for the page indexing below to work.
+		 *
+		 * Note that page table lock is not held when pte is null.
 		 */
 		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
+		if (pte)
+			ptl = huge_pte_lock(h, mm, pte);
 		absent = !pte || huge_pte_none(huge_ptep_get(pte));
 
 		/*
@@ -3028,6 +3042,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		if (absent && (flags & FOLL_DUMP) &&
 		    !hugetlbfs_pagecache_present(h, vma, vaddr)) {
+			if (pte)
+				spin_unlock(ptl);
 			remainder = 0;
 			break;
 		}
@@ -3047,10 +3063,10 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		      !huge_pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
-			spin_unlock(&mm->page_table_lock);
+			if (pte)
+				spin_unlock(ptl);
 			ret = hugetlb_fault(mm, vma, vaddr,
 				(flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0);
-			spin_lock(&mm->page_table_lock);
 			if (!(ret & VM_FAULT_ERROR))
 				continue;
 
@@ -3081,8 +3097,8 @@ same_page:
 			 */
 			goto same_page;
 		}
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	*nr_pages = remainder;
 	*position = vaddr;
 
@@ -3103,13 +3119,15 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_cache_range(vma, address, end);
 
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
-	spin_lock(&mm->page_table_lock);
 	for (; address < end; address += huge_page_size(h)) {
+		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
+		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			pages++;
+			spin_unlock(ptl);
 			continue;
 		}
 		if (!huge_pte_none(huge_ptep_get(ptep))) {
@@ -3119,8 +3137,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			set_huge_pte_at(mm, address, ptep, pte);
 			pages++;
 		}
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	/*
 	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
 	 * may have cleared our pud entry and done put_page on the page table:
@@ -3283,6 +3301,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	unsigned long saddr;
 	pte_t *spte = NULL;
 	pte_t *pte;
+	spinlock_t *ptl;
 
 	if (!vma_shareable(vma, addr))
 		return (pte_t *)pmd_alloc(mm, pud, addr);
@@ -3305,13 +3324,14 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	if (!spte)
 		goto out;
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte);
+	spin_lock(ptl);
 	if (pud_none(*pud))
 		pud_populate(mm, pud,
 				(pmd_t *)((unsigned long)spte & PAGE_MASK));
 	else
 		put_page(virt_to_page(spte));
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 out:
 	pte = (pte_t *)pmd_alloc(mm, pud, addr);
 	mutex_unlock(&mapping->i_mmap_mutex);
@@ -3325,7 +3345,7 @@ out:
  * indicated by page_count > 1, unmap is achieved by clearing pud and
  * decrementing the ref count. If count == 1, the pte page is not shared.
  *
- * called with vma->vm_mm->page_table_lock held.
+ * called with page table lock held.
  *
  * returns: 1 successfully unmapped a shared pte page
  *	    0 the underlying pte page is not shared, or it is the last user
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index afc2daa91c60..4c84678371eb 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -20,8 +20,6 @@ static int hwpoison_inject(void *data, u64 val)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!hwpoison_filter_enable)
-		goto inject;
 	if (!pfn_valid(pfn))
 		return -ENXIO;
 
@@ -33,6 +31,9 @@ static int hwpoison_inject(void *data, u64 val)
 	if (!get_page_unless_zero(hpage))
 		return 0;
 
+	if (!hwpoison_filter_enable)
+		goto inject;
+
 	if (!PageLRU(p) && !PageHuge(p))
 		shake_page(p, 0);
 	/*
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index e126b0ef9ad2..31f01c5011e5 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -753,7 +753,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 	}
 
 	spin_lock_irqsave(&object->lock, flags);
-	if (ptr + size > object->pointer + object->size) {
+	if (size == SIZE_MAX) {
+		size = object->pointer + object->size - ptr;
+	} else if (ptr + size > object->pointer + object->size) {
 		kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr);
 		dump_object_info(object);
 		kmem_cache_free(scan_area_cache, area);
diff --git a/mm/ksm.c b/mm/ksm.c
index 0bea2b262a47..175fff79dc95 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2309,8 +2309,8 @@ static ssize_t merge_across_nodes_store(struct kobject *kobj,
 			 * 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);
+			buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf),
+				      GFP_KERNEL);
 			/* Let us assume that RB_ROOT is NULL is zero */
 			if (!buf)
 				err = -ENOMEM;
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 72467914b856..72f9decb0104 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -81,8 +81,9 @@ restart:
 		 * decrement nr_to_walk first so that we don't livelock if we
 		 * get stuck on large numbesr of LRU_RETRY items
 		 */
-		if (--(*nr_to_walk) == 0)
+		if (!*nr_to_walk)
 			break;
+		--*nr_to_walk;
 
 		ret = isolate(item, &nlru->lock, cb_arg);
 		switch (ret) {
diff --git a/mm/madvise.c b/mm/madvise.c
index 6975bc812542..539eeb96b323 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -343,10 +343,11 @@ static long madvise_remove(struct vm_area_struct *vma,
  */
 static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
 {
+	struct page *p;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	for (; start < end; start += PAGE_SIZE) {
-		struct page *p;
+	for (; start < end; start += PAGE_SIZE <<
+				compound_order(compound_head(p))) {
 		int ret;
 
 		ret = get_user_pages_fast(start, 1, 0, &p);
diff --git a/mm/memblock.c b/mm/memblock.c
index 0ac412a0a7ee..53e477bb5558 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -20,6 +20,8 @@
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
 
+#include <asm-generic/sections.h>
+
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 
@@ -32,6 +34,7 @@ struct memblock memblock __initdata_memblock = {
 	.reserved.cnt		= 1,	/* empty dummy entry */
 	.reserved.max		= INIT_MEMBLOCK_REGIONS,
 
+	.bottom_up		= false,
 	.current_limit		= MEMBLOCK_ALLOC_ANYWHERE,
 };
 
@@ -82,6 +85,73 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
 	return (i < type->cnt) ? i : -1;
 }
 
+/*
+ * __memblock_find_range_bottom_up - find free area utility in bottom-up
+ * @start: start of candidate range
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @size: size of free area to find
+ * @align: alignment of free area to find
+ * @nid: nid of the free area to find, %MAX_NUMNODES for any node
+ *
+ * Utility called from memblock_find_in_range_node(), find free area bottom-up.
+ *
+ * RETURNS:
+ * Found address on success, 0 on failure.
+ */
+static phys_addr_t __init_memblock
+__memblock_find_range_bottom_up(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;
+
+	for_each_free_mem_range(i, nid, &this_start, &this_end, NULL) {
+		this_start = clamp(this_start, start, end);
+		this_end = clamp(this_end, start, end);
+
+		cand = round_up(this_start, align);
+		if (cand < this_end && this_end - cand >= size)
+			return cand;
+	}
+
+	return 0;
+}
+
+/**
+ * __memblock_find_range_top_down - find free area utility, in top-down
+ * @start: start of candidate range
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @size: size of free area to find
+ * @align: alignment of free area to find
+ * @nid: nid of the free area to find, %MAX_NUMNODES for any node
+ *
+ * Utility called from memblock_find_in_range_node(), find free area top-down.
+ *
+ * RETURNS:
+ * Found address on success, 0 on failure.
+ */
+static phys_addr_t __init_memblock
+__memblock_find_range_top_down(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;
+
+	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);
+
+		if (this_end < size)
+			continue;
+
+		cand = round_down(this_end - size, align);
+		if (cand >= this_start)
+			return cand;
+	}
+
+	return 0;
+}
+
 /**
  * memblock_find_in_range_node - find free area in given range and node
  * @start: start of candidate range
@@ -92,15 +162,23 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
  *
  * Find @size free area aligned to @align in the specified range and node.
  *
+ * When allocation direction is bottom-up, the @start should be greater
+ * than the end of the kernel image. Otherwise, it will be trimmed. The
+ * reason is that we want the bottom-up allocation just near the kernel
+ * image so it is highly likely that the allocated memory and the kernel
+ * will reside in the same node.
+ *
+ * If bottom-up allocation failed, will try to allocate memory top-down.
+ *
  * RETURNS:
- * Found address on success, %0 on failure.
+ * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 					phys_addr_t end, phys_addr_t size,
 					phys_addr_t align, int nid)
 {
-	phys_addr_t this_start, this_end, cand;
-	u64 i;
+	int ret;
+	phys_addr_t kernel_end;
 
 	/* pump up @end */
 	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
@@ -109,19 +187,39 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 	/* avoid allocating the first page */
 	start = max_t(phys_addr_t, start, PAGE_SIZE);
 	end = max(start, end);
+	kernel_end = __pa_symbol(_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);
+	/*
+	 * try bottom-up allocation only when bottom-up mode
+	 * is set and @end is above the kernel image.
+	 */
+	if (memblock_bottom_up() && end > kernel_end) {
+		phys_addr_t bottom_up_start;
 
-		if (this_end < size)
-			continue;
+		/* make sure we will allocate above the kernel */
+		bottom_up_start = max(start, kernel_end);
 
-		cand = round_down(this_end - size, align);
-		if (cand >= this_start)
-			return cand;
+		/* ok, try bottom-up allocation first */
+		ret = __memblock_find_range_bottom_up(bottom_up_start, end,
+						      size, align, nid);
+		if (ret)
+			return ret;
+
+		/*
+		 * we always limit bottom-up allocation above the kernel,
+		 * but top-down allocation doesn't have the limit, so
+		 * retrying top-down allocation may succeed when bottom-up
+		 * allocation failed.
+		 *
+		 * bottom-up allocation is expected to be fail very rarely,
+		 * so we use WARN_ONCE() here to see the stack trace if
+		 * fail happens.
+		 */
+		WARN_ONCE(1, "memblock: bottom-up allocation failed, "
+			     "memory hotunplug may be affected\n");
 	}
-	return 0;
+
+	return __memblock_find_range_top_down(start, end, size, align, nid);
 }
 
 /**
@@ -134,7 +232,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
  * Find @size free area aligned to @align in the specified range.
  *
  * RETURNS:
- * Found address on success, %0 on failure.
+ * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					phys_addr_t end, phys_addr_t size,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d5ff3ce13029..7f1a356153c0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -39,6 +39,7 @@
 #include <linux/limits.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
+#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
@@ -53,10 +54,12 @@
 #include <linux/page_cgroup.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
+#include <linux/lockdep.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
 #include <net/tcp_memcontrol.h>
+#include "slab.h"
 
 #include <asm/uaccess.h>
 
@@ -160,6 +163,10 @@ struct mem_cgroup_per_zone {
 
 	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
 
+	struct rb_node		tree_node;	/* RB tree node */
+	unsigned long long	usage_in_excess;/* Set to the value by which */
+						/* the soft limit is exceeded*/
+	bool			on_tree;
 	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
 						/* use container_of	   */
 };
@@ -168,6 +175,26 @@ struct mem_cgroup_per_node {
 	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
 };
 
+/*
+ * Cgroups above their limits are maintained in a RB-Tree, independent of
+ * their hierarchy representation
+ */
+
+struct mem_cgroup_tree_per_zone {
+	struct rb_root rb_root;
+	spinlock_t lock;
+};
+
+struct mem_cgroup_tree_per_node {
+	struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
+};
+
+struct mem_cgroup_tree {
+	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
+};
+
+static struct mem_cgroup_tree soft_limit_tree __read_mostly;
+
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
 	u64 threshold;
@@ -286,7 +313,7 @@ struct mem_cgroup {
 
 	atomic_t	dead_count;
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
-	struct tcp_memcontrol tcp_mem;
+	struct cg_proto tcp_mem;
 #endif
 #if defined(CONFIG_MEMCG_KMEM)
 	/* analogous to slab_common's slab_caches list. per-memcg */
@@ -303,22 +330,6 @@ struct mem_cgroup {
 	atomic_t	numainfo_events;
 	atomic_t	numainfo_updating;
 #endif
-	/*
-	 * Protects soft_contributed transitions.
-	 * See mem_cgroup_update_soft_limit
-	 */
-	spinlock_t soft_lock;
-
-	/*
-	 * If true then this group has increased parents' children_in_excess
-	 * when it got over the soft limit.
-	 * When a group falls bellow the soft limit, parents' children_in_excess
-	 * is decreased and soft_contributed changed to false.
-	 */
-	bool soft_contributed;
-
-	/* Number of children that are in soft limit excess */
-	atomic_t children_in_excess;
 
 	struct mem_cgroup_per_node *nodeinfo[0];
 	/* WARNING: nodeinfo must be the last member here */
@@ -327,7 +338,7 @@ struct mem_cgroup {
 static size_t memcg_size(void)
 {
 	return sizeof(struct mem_cgroup) +
-		nr_node_ids * sizeof(struct mem_cgroup_per_node);
+		nr_node_ids * sizeof(struct mem_cgroup_per_node *);
 }
 
 /* internal only representation about the status of kmem accounting. */
@@ -422,6 +433,7 @@ static bool move_file(void)
  * limit reclaim to prevent infinite loops, if they ever occur.
  */
 #define	MEM_CGROUP_MAX_RECLAIM_LOOPS		100
+#define	MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS	2
 
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
@@ -488,6 +500,29 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 	return (memcg == root_mem_cgroup);
 }
 
+/*
+ * We restrict the id in the range of [1, 65535], so it can fit into
+ * an unsigned short.
+ */
+#define MEM_CGROUP_ID_MAX	USHRT_MAX
+
+static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
+{
+	/*
+	 * The ID of the root cgroup is 0, but memcg treat 0 as an
+	 * invalid ID, so we return (cgroup_id + 1).
+	 */
+	return memcg->css.cgroup->id + 1;
+}
+
+static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
+{
+	struct cgroup_subsys_state *css;
+
+	css = css_from_id(id - 1, &mem_cgroup_subsys);
+	return mem_cgroup_from_css(css);
+}
+
 /* Writing them here to avoid exposing memcg's inner layout */
 #if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)
 
@@ -540,13 +575,13 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
 	if (!memcg || mem_cgroup_is_root(memcg))
 		return NULL;
 
-	return &memcg->tcp_mem.cg_proto;
+	return &memcg->tcp_mem;
 }
 EXPORT_SYMBOL(tcp_proto_cgroup);
 
 static void disarm_sock_keys(struct mem_cgroup *memcg)
 {
-	if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto))
+	if (!memcg_proto_activated(&memcg->tcp_mem))
 		return;
 	static_key_slow_dec(&memcg_socket_limit_enabled);
 }
@@ -559,16 +594,11 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * This will be the memcg's index in each cache's ->memcg_params->memcg_caches.
- * There are two main reasons for not using the css_id for this:
- *  1) this works better in sparse environments, where we have a lot of memcgs,
- *     but only a few kmem-limited. Or also, if we have, for instance, 200
- *     memcgs, and none but the 200th is kmem-limited, we'd have to have a
- *     200 entry array for that.
- *
- *  2) In order not to violate the cgroup API, we would like to do all memory
- *     allocation in ->create(). At that point, we haven't yet allocated the
- *     css_id. Having a separate index prevents us from messing with the cgroup
- *     core for this
+ * The main reason for not using cgroup id for this:
+ *  this works better in sparse environments, where we have a lot of memcgs,
+ *  but only a few kmem-limited. Or also, if we have, for instance, 200
+ *  memcgs, and none but the 200th is kmem-limited, we'd have to have a
+ *  200 entry array for that.
  *
  * The current size of the caches array is stored in
  * memcg_limited_groups_array_size.  It will double each time we have to
@@ -583,14 +613,14 @@ int memcg_limited_groups_array_size;
  * cgroups is a reasonable guess. In the future, it could be a parameter or
  * tunable, but that is strictly not necessary.
  *
- * MAX_SIZE should be as large as the number of css_ids. Ideally, we could get
+ * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get
  * this constant directly from cgroup, but it is understandable that this is
  * better kept as an internal representation in cgroup.c. In any case, the
- * css_id space is not getting any smaller, and we don't have to necessarily
+ * cgrp_id space is not getting any smaller, and we don't have to necessarily
  * increase ours as well if it increases.
  */
 #define MEMCG_CACHES_MIN_SIZE 4
-#define MEMCG_CACHES_MAX_SIZE 65535
+#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX
 
 /*
  * A lot of the calls to the cache allocation functions are expected to be
@@ -648,6 +678,164 @@ page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 	return mem_cgroup_zoneinfo(memcg, nid, zid);
 }
 
+static struct mem_cgroup_tree_per_zone *
+soft_limit_tree_node_zone(int nid, int zid)
+{
+	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+}
+
+static struct mem_cgroup_tree_per_zone *
+soft_limit_tree_from_page(struct page *page)
+{
+	int nid = page_to_nid(page);
+	int zid = page_zonenum(page);
+
+	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+}
+
+static void
+__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz,
+				unsigned long long new_usage_in_excess)
+{
+	struct rb_node **p = &mctz->rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct mem_cgroup_per_zone *mz_node;
+
+	if (mz->on_tree)
+		return;
+
+	mz->usage_in_excess = new_usage_in_excess;
+	if (!mz->usage_in_excess)
+		return;
+	while (*p) {
+		parent = *p;
+		mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
+					tree_node);
+		if (mz->usage_in_excess < mz_node->usage_in_excess)
+			p = &(*p)->rb_left;
+		/*
+		 * We can't avoid mem cgroups that are over their soft
+		 * limit by the same amount
+		 */
+		else if (mz->usage_in_excess >= mz_node->usage_in_excess)
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&mz->tree_node, parent, p);
+	rb_insert_color(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = true;
+}
+
+static void
+__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz)
+{
+	if (!mz->on_tree)
+		return;
+	rb_erase(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = false;
+}
+
+static void
+mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz)
+{
+	spin_lock(&mctz->lock);
+	__mem_cgroup_remove_exceeded(memcg, mz, mctz);
+	spin_unlock(&mctz->lock);
+}
+
+
+static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
+{
+	unsigned long long excess;
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_tree_per_zone *mctz;
+	int nid = page_to_nid(page);
+	int zid = page_zonenum(page);
+	mctz = soft_limit_tree_from_page(page);
+
+	/*
+	 * Necessary to update all ancestors when hierarchy is used.
+	 * because their event counter is not touched.
+	 */
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
+		mz = mem_cgroup_zoneinfo(memcg, nid, zid);
+		excess = res_counter_soft_limit_excess(&memcg->res);
+		/*
+		 * We have to update the tree if mz is on RB-tree or
+		 * mem is over its softlimit.
+		 */
+		if (excess || mz->on_tree) {
+			spin_lock(&mctz->lock);
+			/* if on-tree, remove it */
+			if (mz->on_tree)
+				__mem_cgroup_remove_exceeded(memcg, mz, mctz);
+			/*
+			 * Insert again. mz->usage_in_excess will be updated.
+			 * If excess is 0, no tree ops.
+			 */
+			__mem_cgroup_insert_exceeded(memcg, mz, mctz, excess);
+			spin_unlock(&mctz->lock);
+		}
+	}
+}
+
+static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
+{
+	int node, zone;
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_tree_per_zone *mctz;
+
+	for_each_node(node) {
+		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+			mz = mem_cgroup_zoneinfo(memcg, node, zone);
+			mctz = soft_limit_tree_node_zone(node, zone);
+			mem_cgroup_remove_exceeded(memcg, mz, mctz);
+		}
+	}
+}
+
+static struct mem_cgroup_per_zone *
+__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+{
+	struct rb_node *rightmost = NULL;
+	struct mem_cgroup_per_zone *mz;
+
+retry:
+	mz = NULL;
+	rightmost = rb_last(&mctz->rb_root);
+	if (!rightmost)
+		goto done;		/* Nothing to reclaim from */
+
+	mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node);
+	/*
+	 * Remove the node now but someone else can add it back,
+	 * we will to add it back at the end of reclaim to its correct
+	 * position in the tree.
+	 */
+	__mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
+	if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
+		!css_tryget(&mz->memcg->css))
+		goto retry;
+done:
+	return mz;
+}
+
+static struct mem_cgroup_per_zone *
+mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+{
+	struct mem_cgroup_per_zone *mz;
+
+	spin_lock(&mctz->lock);
+	mz = __mem_cgroup_largest_soft_limit_node(mctz);
+	spin_unlock(&mctz->lock);
+	return mz;
+}
+
 /*
  * Implementation Note: reading percpu statistics for memcg.
  *
@@ -698,6 +886,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 	unsigned long val = 0;
 	int cpu;
 
+	get_online_cpus();
 	for_each_online_cpu(cpu)
 		val += per_cpu(memcg->stat->events[idx], cpu);
 #ifdef CONFIG_HOTPLUG_CPU
@@ -705,6 +894,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 	val += memcg->nocpu_base.events[idx];
 	spin_unlock(&memcg->pcp_counter_lock);
 #endif
+	put_online_cpus();
 	return val;
 }
 
@@ -822,48 +1012,6 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
 }
 
 /*
- * Called from rate-limited memcg_check_events when enough
- * MEM_CGROUP_TARGET_SOFTLIMIT events are accumulated and it makes sure
- * that all the parents up the hierarchy will be notified that this group
- * is in excess or that it is not in excess anymore. mmecg->soft_contributed
- * makes the transition a single action whenever the state flips from one to
- * the other.
- */
-static void mem_cgroup_update_soft_limit(struct mem_cgroup *memcg)
-{
-	unsigned long long excess = res_counter_soft_limit_excess(&memcg->res);
-	struct mem_cgroup *parent = memcg;
-	int delta = 0;
-
-	spin_lock(&memcg->soft_lock);
-	if (excess) {
-		if (!memcg->soft_contributed) {
-			delta = 1;
-			memcg->soft_contributed = true;
-		}
-	} else {
-		if (memcg->soft_contributed) {
-			delta = -1;
-			memcg->soft_contributed = false;
-		}
-	}
-
-	/*
-	 * Necessary to update all ancestors when hierarchy is used
-	 * because their event counter is not touched.
-	 * We track children even outside the hierarchy for the root
-	 * cgroup because tree walk starting at root should visit
-	 * all cgroups and we want to prevent from pointless tree
-	 * walk if no children is below the limit.
-	 */
-	while (delta && (parent = parent_mem_cgroup(parent)))
-		atomic_add(delta, &parent->children_in_excess);
-	if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
-		atomic_add(delta, &root_mem_cgroup->children_in_excess);
-	spin_unlock(&memcg->soft_lock);
-}
-
-/*
  * Check events in order.
  *
  */
@@ -886,7 +1034,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 
 		mem_cgroup_threshold(memcg);
 		if (unlikely(do_softlimit))
-			mem_cgroup_update_soft_limit(memcg);
+			mem_cgroup_update_tree(memcg, page);
 #if MAX_NUMNODES > 1
 		if (unlikely(do_numainfo))
 			atomic_inc(&memcg->numainfo_events);
@@ -929,15 +1077,6 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return memcg;
 }
 
-static enum mem_cgroup_filter_t
-mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root,
-		mem_cgroup_iter_filter cond)
-{
-	if (!cond)
-		return VISIT;
-	return cond(memcg, root);
-}
-
 /*
  * Returns a next (in a pre-order walk) alive memcg (with elevated css
  * ref. count) or NULL if the whole root's subtree has been visited.
@@ -945,7 +1084,7 @@ mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root,
  * helper function to be used by mem_cgroup_iter
  */
 static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
-		struct mem_cgroup *last_visited, mem_cgroup_iter_filter cond)
+		struct mem_cgroup *last_visited)
 {
 	struct cgroup_subsys_state *prev_css, *next_css;
 
@@ -963,31 +1102,11 @@ skip_node:
 	if (next_css) {
 		struct mem_cgroup *mem = mem_cgroup_from_css(next_css);
 
-		switch (mem_cgroup_filter(mem, root, cond)) {
-		case SKIP:
+		if (css_tryget(&mem->css))
+			return mem;
+		else {
 			prev_css = next_css;
 			goto skip_node;
-		case SKIP_TREE:
-			if (mem == root)
-				return NULL;
-			/*
-			 * css_rightmost_descendant is not an optimal way to
-			 * skip through a subtree (especially for imbalanced
-			 * trees leaning to right) but that's what we have right
-			 * now. More effective solution would be traversing
-			 * right-up for first non-NULL without calling
-			 * css_next_descendant_pre afterwards.
-			 */
-			prev_css = css_rightmost_descendant(next_css);
-			goto skip_node;
-		case VISIT:
-			if (css_tryget(&mem->css))
-				return mem;
-			else {
-				prev_css = next_css;
-				goto skip_node;
-			}
-			break;
 		}
 	}
 
@@ -1051,7 +1170,6 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
  * @root: hierarchy root
  * @prev: previously returned memcg, NULL on first invocation
  * @reclaim: cookie for shared reclaim walks, NULL for full walks
- * @cond: filter for visited nodes, NULL for no filter
  *
  * Returns references to children of the hierarchy below @root, or
  * @root itself, or %NULL after a full round-trip.
@@ -1064,18 +1182,15 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
  * divide up the memcgs in the hierarchy among all concurrent
  * reclaimers operating on the same zone and priority.
  */
-struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
+struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup *prev,
-				   struct mem_cgroup_reclaim_cookie *reclaim,
-				   mem_cgroup_iter_filter cond)
+				   struct mem_cgroup_reclaim_cookie *reclaim)
 {
 	struct mem_cgroup *memcg = NULL;
 	struct mem_cgroup *last_visited = NULL;
 
-	if (mem_cgroup_disabled()) {
-		/* first call must return non-NULL, second return NULL */
-		return (struct mem_cgroup *)(unsigned long)!prev;
-	}
+	if (mem_cgroup_disabled())
+		return NULL;
 
 	if (!root)
 		root = root_mem_cgroup;
@@ -1086,9 +1201,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
 	if (!root->use_hierarchy && root != root_mem_cgroup) {
 		if (prev)
 			goto out_css_put;
-		if (mem_cgroup_filter(root, root, cond) == VISIT)
-			return root;
-		return NULL;
+		return root;
 	}
 
 	rcu_read_lock();
@@ -1111,7 +1224,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
 			last_visited = mem_cgroup_iter_load(iter, root, &seq);
 		}
 
-		memcg = __mem_cgroup_iter_next(root, last_visited, cond);
+		memcg = __mem_cgroup_iter_next(root, last_visited);
 
 		if (reclaim) {
 			mem_cgroup_iter_update(iter, last_visited, memcg, seq);
@@ -1122,11 +1235,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
 				reclaim->generation = iter->generation;
 		}
 
-		/*
-		 * We have finished the whole tree walk or no group has been
-		 * visited because filter told us to skip the root node.
-		 */
-		if (!memcg && (prev || (cond && !last_visited)))
+		if (prev && !memcg)
 			goto out_unlock;
 	}
 out_unlock:
@@ -1318,7 +1427,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 		return true;
 	if (!root_memcg->use_hierarchy || !memcg)
 		return false;
-	return css_is_ancestor(&memcg->css, &root_memcg->css);
+	return cgroup_is_descendant(memcg->css.cgroup, root_memcg->css.cgroup);
 }
 
 static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
@@ -1767,7 +1876,6 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
 	return total;
 }
 
-#if MAX_NUMNODES > 1
 /**
  * test_mem_cgroup_node_reclaimable
  * @memcg: the target memcg
@@ -1790,6 +1898,7 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg,
 	return false;
 
 }
+#if MAX_NUMNODES > 1
 
 /*
  * Always updating the nodemask is not very good - even if we have an empty
@@ -1857,52 +1966,112 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 	return node;
 }
 
+/*
+ * Check all nodes whether it contains reclaimable pages or not.
+ * For quick scan, we make use of scan_nodes. This will allow us to skip
+ * unused nodes. But scan_nodes is lazily updated and may not cotain
+ * enough new information. We need to do double check.
+ */
+static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
+{
+	int nid;
+
+	/*
+	 * quick check...making use of scan_node.
+	 * We can skip unused nodes.
+	 */
+	if (!nodes_empty(memcg->scan_nodes)) {
+		for (nid = first_node(memcg->scan_nodes);
+		     nid < MAX_NUMNODES;
+		     nid = next_node(nid, memcg->scan_nodes)) {
+
+			if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
+				return true;
+		}
+	}
+	/*
+	 * Check rest of nodes.
+	 */
+	for_each_node_state(nid, N_MEMORY) {
+		if (node_isset(nid, memcg->scan_nodes))
+			continue;
+		if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
+			return true;
+	}
+	return false;
+}
+
 #else
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 {
 	return 0;
 }
 
-#endif
-
-/*
- * A group is eligible for the soft limit reclaim under the given root
- * hierarchy if
- *	a) it is over its soft limit
- *	b) any parent up the hierarchy is over its soft limit
- *
- * If the given group doesn't have any children over the limit then it
- * doesn't make any sense to iterate its subtree.
- */
-enum mem_cgroup_filter_t
-mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-		struct mem_cgroup *root)
+static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
 {
-	struct mem_cgroup *parent;
-
-	if (!memcg)
-		memcg = root_mem_cgroup;
-	parent = memcg;
-
-	if (res_counter_soft_limit_excess(&memcg->res))
-		return VISIT;
+	return test_mem_cgroup_node_reclaimable(memcg, 0, noswap);
+}
+#endif
 
-	/*
-	 * If any parent up to the root in the hierarchy is over its soft limit
-	 * then we have to obey and reclaim from this group as well.
-	 */
-	while ((parent = parent_mem_cgroup(parent))) {
-		if (res_counter_soft_limit_excess(&parent->res))
-			return VISIT;
-		if (parent == root)
+static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
+				   struct zone *zone,
+				   gfp_t gfp_mask,
+				   unsigned long *total_scanned)
+{
+	struct mem_cgroup *victim = NULL;
+	int total = 0;
+	int loop = 0;
+	unsigned long excess;
+	unsigned long nr_scanned;
+	struct mem_cgroup_reclaim_cookie reclaim = {
+		.zone = zone,
+		.priority = 0,
+	};
+
+	excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;
+
+	while (1) {
+		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
+		if (!victim) {
+			loop++;
+			if (loop >= 2) {
+				/*
+				 * If we have not been able to reclaim
+				 * anything, it might because there are
+				 * no reclaimable pages under this hierarchy
+				 */
+				if (!total)
+					break;
+				/*
+				 * We want to do more targeted reclaim.
+				 * excess >> 2 is not to excessive so as to
+				 * reclaim too much, nor too less that we keep
+				 * coming back to reclaim from this cgroup
+				 */
+				if (total >= (excess >> 2) ||
+					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
+					break;
+			}
+			continue;
+		}
+		if (!mem_cgroup_reclaimable(victim, false))
+			continue;
+		total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
+						     zone, &nr_scanned);
+		*total_scanned += nr_scanned;
+		if (!res_counter_soft_limit_excess(&root_memcg->res))
 			break;
 	}
-
-	if (!atomic_read(&memcg->children_in_excess))
-		return SKIP_TREE;
-	return SKIP;
+	mem_cgroup_iter_break(root_memcg, victim);
+	return total;
 }
 
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map memcg_oom_lock_dep_map = {
+	.name = "memcg_oom_lock",
+};
+#endif
+
 static DEFINE_SPINLOCK(memcg_oom_lock);
 
 /*
@@ -1940,7 +2109,8 @@ static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
 			}
 			iter->oom_lock = false;
 		}
-	}
+	} else
+		mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_);
 
 	spin_unlock(&memcg_oom_lock);
 
@@ -1952,6 +2122,7 @@ static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
 	struct mem_cgroup *iter;
 
 	spin_lock(&memcg_oom_lock);
+	mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_);
 	for_each_mem_cgroup_tree(iter, memcg)
 		iter->oom_lock = false;
 	spin_unlock(&memcg_oom_lock);
@@ -2018,110 +2189,59 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 		memcg_wakeup_oom(memcg);
 }
 
-/*
- * try to call OOM killer
- */
 static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	bool locked;
-	int wakeups;
-
 	if (!current->memcg_oom.may_oom)
 		return;
-
-	current->memcg_oom.in_memcg_oom = 1;
-
 	/*
-	 * As with any blocking lock, a contender needs to start
-	 * listening for wakeups before attempting the trylock,
-	 * otherwise it can miss the wakeup from the unlock and sleep
-	 * indefinitely.  This is just open-coded because our locking
-	 * is so particular to memcg hierarchies.
+	 * We are in the middle of the charge context here, so we
+	 * don't want to block when potentially sitting on a callstack
+	 * that holds all kinds of filesystem and mm locks.
+	 *
+	 * Also, the caller may handle a failed allocation gracefully
+	 * (like optional page cache readahead) and so an OOM killer
+	 * invocation might not even be necessary.
+	 *
+	 * That's why we don't do anything here except remember the
+	 * OOM context and then deal with it at the end of the page
+	 * fault when the stack is unwound, the locks are released,
+	 * and when we know whether the fault was overall successful.
 	 */
-	wakeups = atomic_read(&memcg->oom_wakeups);
-	mem_cgroup_mark_under_oom(memcg);
-
-	locked = mem_cgroup_oom_trylock(memcg);
-
-	if (locked)
-		mem_cgroup_oom_notify(memcg);
-
-	if (locked && !memcg->oom_kill_disable) {
-		mem_cgroup_unmark_under_oom(memcg);
-		mem_cgroup_out_of_memory(memcg, mask, order);
-		mem_cgroup_oom_unlock(memcg);
-		/*
-		 * There is no guarantee that an OOM-lock contender
-		 * sees the wakeups triggered by the OOM kill
-		 * uncharges.  Wake any sleepers explicitely.
-		 */
-		memcg_oom_recover(memcg);
-	} else {
-		/*
-		 * A system call can just return -ENOMEM, but if this
-		 * is a page fault and somebody else is handling the
-		 * OOM already, we need to sleep on the OOM waitqueue
-		 * for this memcg until the situation is resolved.
-		 * Which can take some time because it might be
-		 * handled by a userspace task.
-		 *
-		 * However, this is the charge context, which means
-		 * that we may sit on a large call stack and hold
-		 * various filesystem locks, the mmap_sem etc. and we
-		 * don't want the OOM handler to deadlock on them
-		 * while we sit here and wait.  Store the current OOM
-		 * context in the task_struct, then return -ENOMEM.
-		 * At the end of the page fault handler, with the
-		 * stack unwound, pagefault_out_of_memory() will check
-		 * back with us by calling
-		 * mem_cgroup_oom_synchronize(), possibly putting the
-		 * task to sleep.
-		 */
-		current->memcg_oom.oom_locked = locked;
-		current->memcg_oom.wakeups = wakeups;
-		css_get(&memcg->css);
-		current->memcg_oom.wait_on_memcg = memcg;
-	}
+	css_get(&memcg->css);
+	current->memcg_oom.memcg = memcg;
+	current->memcg_oom.gfp_mask = mask;
+	current->memcg_oom.order = order;
 }
 
 /**
  * mem_cgroup_oom_synchronize - complete memcg OOM handling
+ * @handle: actually kill/wait or just clean up the OOM state
  *
- * This has to be called at the end of a page fault if the the memcg
- * OOM handler was enabled and the fault is returning %VM_FAULT_OOM.
+ * This has to be called at the end of a page fault if the memcg OOM
+ * handler was enabled.
  *
- * Memcg supports userspace OOM handling, so failed allocations must
+ * Memcg supports userspace OOM handling where failed allocations must
  * sleep on a waitqueue until the userspace task resolves the
  * situation.  Sleeping directly in the charge context with all kinds
  * of locks held is not a good idea, instead we remember an OOM state
  * in the task and mem_cgroup_oom_synchronize() has to be called at
- * the end of the page fault to put the task to sleep and clean up the
- * OOM state.
+ * the end of the page fault to complete the OOM handling.
  *
  * Returns %true if an ongoing memcg OOM situation was detected and
- * finalized, %false otherwise.
+ * completed, %false otherwise.
  */
-bool mem_cgroup_oom_synchronize(void)
+bool mem_cgroup_oom_synchronize(bool handle)
 {
+	struct mem_cgroup *memcg = current->memcg_oom.memcg;
 	struct oom_wait_info owait;
-	struct mem_cgroup *memcg;
+	bool locked;
 
 	/* OOM is global, do not handle */
-	if (!current->memcg_oom.in_memcg_oom)
-		return false;
-
-	/*
-	 * We invoked the OOM killer but there is a chance that a kill
-	 * did not free up any charges.  Everybody else might already
-	 * be sleeping, so restart the fault and keep the rampage
-	 * going until some charges are released.
-	 */
-	memcg = current->memcg_oom.wait_on_memcg;
 	if (!memcg)
-		goto out;
+		return false;
 
-	if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
-		goto out_memcg;
+	if (!handle)
+		goto cleanup;
 
 	owait.memcg = memcg;
 	owait.wait.flags = 0;
@@ -2130,13 +2250,25 @@ bool mem_cgroup_oom_synchronize(void)
 	INIT_LIST_HEAD(&owait.wait.task_list);
 
 	prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
-	/* Only sleep if we didn't miss any wakeups since OOM */
-	if (atomic_read(&memcg->oom_wakeups) == current->memcg_oom.wakeups)
+	mem_cgroup_mark_under_oom(memcg);
+
+	locked = mem_cgroup_oom_trylock(memcg);
+
+	if (locked)
+		mem_cgroup_oom_notify(memcg);
+
+	if (locked && !memcg->oom_kill_disable) {
+		mem_cgroup_unmark_under_oom(memcg);
+		finish_wait(&memcg_oom_waitq, &owait.wait);
+		mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask,
+					 current->memcg_oom.order);
+	} else {
 		schedule();
-	finish_wait(&memcg_oom_waitq, &owait.wait);
-out_memcg:
-	mem_cgroup_unmark_under_oom(memcg);
-	if (current->memcg_oom.oom_locked) {
+		mem_cgroup_unmark_under_oom(memcg);
+		finish_wait(&memcg_oom_waitq, &owait.wait);
+	}
+
+	if (locked) {
 		mem_cgroup_oom_unlock(memcg);
 		/*
 		 * There is no guarantee that an OOM-lock contender
@@ -2145,10 +2277,9 @@ out_memcg:
 		 */
 		memcg_oom_recover(memcg);
 	}
+cleanup:
+	current->memcg_oom.memcg = NULL;
 	css_put(&memcg->css);
-	current->memcg_oom.wait_on_memcg = NULL;
-out:
-	current->memcg_oom.in_memcg_oom = 0;
 	return true;
 }
 
@@ -2562,6 +2693,12 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 		     || fatal_signal_pending(current)))
 		goto bypass;
 
+	if (unlikely(task_in_memcg_oom(current)))
+		goto nomem;
+
+	if (gfp_mask & __GFP_NOFAIL)
+		oom = false;
+
 	/*
 	 * We always charge the cgroup the mm_struct belongs to.
 	 * The mm_struct's mem_cgroup changes on task migration if the
@@ -2659,8 +2796,10 @@ done:
 	*ptr = memcg;
 	return 0;
 nomem:
-	*ptr = NULL;
-	return -ENOMEM;
+	if (!(gfp_mask & __GFP_NOFAIL)) {
+		*ptr = NULL;
+		return -ENOMEM;
+	}
 bypass:
 	*ptr = root_mem_cgroup;
 	return -EINTR;
@@ -2709,15 +2848,10 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
  */
 static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 {
-	struct cgroup_subsys_state *css;
-
 	/* ID 0 is unused ID */
 	if (!id)
 		return NULL;
-	css = css_lookup(&mem_cgroup_subsys, id);
-	if (!css)
-		return NULL;
-	return mem_cgroup_from_css(css);
+	return mem_cgroup_from_id(id);
 }
 
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
@@ -2812,7 +2946,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	unlock_page_cgroup(pc);
 
 	/*
-	 * "charge_statistics" updated event counter.
+	 * "charge_statistics" updated event counter. Then, check it.
+	 * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
+	 * if they exceeds softlimit.
 	 */
 	memcg_check_events(memcg, page);
 }
@@ -2836,7 +2972,7 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
 
 	VM_BUG_ON(p->is_root_cache);
 	cachep = p->root_cache;
-	return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)];
+	return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg));
 }
 
 #ifdef CONFIG_SLABINFO
@@ -2865,21 +3001,14 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 	struct res_counter *fail_res;
 	struct mem_cgroup *_memcg;
 	int ret = 0;
-	bool may_oom;
 
 	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
 	if (ret)
 		return ret;
 
-	/*
-	 * Conditions under which we can wait for the oom_killer. Those are
-	 * the same conditions tested by the core page allocator
-	 */
-	may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY);
-
 	_memcg = memcg;
 	ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT,
-				      &_memcg, may_oom);
+				      &_memcg, oom_gfp_allowed(gfp));
 
 	if (ret == -EINTR)  {
 		/*
@@ -3019,7 +3148,7 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
 {
 	struct memcg_cache_params *cur_params = s->memcg_params;
 
-	VM_BUG_ON(s->memcg_params && !s->memcg_params->is_root_cache);
+	VM_BUG_ON(!is_root_cache(s));
 
 	if (num_groups > memcg_limited_groups_array_size) {
 		int i;
@@ -3280,7 +3409,7 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	idx = memcg_cache_id(memcg);
 
 	mutex_lock(&memcg_cache_mutex);
-	new_cachep = cachep->memcg_params->memcg_caches[idx];
+	new_cachep = cache_from_memcg_idx(cachep, idx);
 	if (new_cachep) {
 		css_put(&memcg->css);
 		goto out;
@@ -3326,8 +3455,8 @@ void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
 	 * we'll take the set_limit_mutex to protect ourselves against this.
 	 */
 	mutex_lock(&set_limit_mutex);
-	for (i = 0; i < memcg_limited_groups_array_size; i++) {
-		c = s->memcg_params->memcg_caches[i];
+	for_each_memcg_cache_index(i) {
+		c = cache_from_memcg_idx(s, i);
 		if (!c)
 			continue;
 
@@ -3460,8 +3589,8 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
 	 * code updating memcg_caches will issue a write barrier to match this.
 	 */
 	read_barrier_depends();
-	if (likely(cachep->memcg_params->memcg_caches[idx])) {
-		cachep = cachep->memcg_params->memcg_caches[idx];
+	if (likely(cache_from_memcg_idx(cachep, idx))) {
+		cachep = cache_from_memcg_idx(cachep, idx);
 		goto out;
 	}
 
@@ -3663,8 +3792,7 @@ void mem_cgroup_move_account_page_stat(struct mem_cgroup *from,
 {
 	/* Update stat data for mem_cgroup */
 	preempt_disable();
-	WARN_ON_ONCE(from->stat->count[idx] < nr_pages);
-	__this_cpu_add(from->stat->count[idx], -nr_pages);
+	__this_cpu_sub(from->stat->count[idx], nr_pages);
 	__this_cpu_add(to->stat->count[idx], nr_pages);
 	preempt_enable();
 }
@@ -4232,7 +4360,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 	 * css_get() was called in uncharge().
 	 */
 	if (do_swap_account && swapout && memcg)
-		swap_cgroup_record(ent, css_id(&memcg->css));
+		swap_cgroup_record(ent, mem_cgroup_id(memcg));
 }
 #endif
 
@@ -4284,8 +4412,8 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry,
 {
 	unsigned short old_id, new_id;
 
-	old_id = css_id(&from->css);
-	new_id = css_id(&to->css);
+	old_id = mem_cgroup_id(from);
+	new_id = mem_cgroup_id(to);
 
 	if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
 		mem_cgroup_swap_statistics(from, false);
@@ -4647,6 +4775,98 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 	return ret;
 }
 
+unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+					    gfp_t gfp_mask,
+					    unsigned long *total_scanned)
+{
+	unsigned long nr_reclaimed = 0;
+	struct mem_cgroup_per_zone *mz, *next_mz = NULL;
+	unsigned long reclaimed;
+	int loop = 0;
+	struct mem_cgroup_tree_per_zone *mctz;
+	unsigned long long excess;
+	unsigned long nr_scanned;
+
+	if (order > 0)
+		return 0;
+
+	mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
+	/*
+	 * This loop can run a while, specially if mem_cgroup's continuously
+	 * keep exceeding their soft limit and putting the system under
+	 * pressure
+	 */
+	do {
+		if (next_mz)
+			mz = next_mz;
+		else
+			mz = mem_cgroup_largest_soft_limit_node(mctz);
+		if (!mz)
+			break;
+
+		nr_scanned = 0;
+		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
+						    gfp_mask, &nr_scanned);
+		nr_reclaimed += reclaimed;
+		*total_scanned += nr_scanned;
+		spin_lock(&mctz->lock);
+
+		/*
+		 * If we failed to reclaim anything from this memory cgroup
+		 * it is time to move on to the next cgroup
+		 */
+		next_mz = NULL;
+		if (!reclaimed) {
+			do {
+				/*
+				 * Loop until we find yet another one.
+				 *
+				 * By the time we get the soft_limit lock
+				 * again, someone might have aded the
+				 * group back on the RB tree. Iterate to
+				 * make sure we get a different mem.
+				 * mem_cgroup_largest_soft_limit_node returns
+				 * NULL if no other cgroup is present on
+				 * the tree
+				 */
+				next_mz =
+				__mem_cgroup_largest_soft_limit_node(mctz);
+				if (next_mz == mz)
+					css_put(&next_mz->memcg->css);
+				else /* next_mz == NULL or other memcg */
+					break;
+			} while (1);
+		}
+		__mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
+		excess = res_counter_soft_limit_excess(&mz->memcg->res);
+		/*
+		 * One school of thought says that we should not add
+		 * back the node to the tree if reclaim returns 0.
+		 * But our reclaim could return 0, simply because due
+		 * to priority we are exposing a smaller subset of
+		 * memory to reclaim from. Consider this as a longer
+		 * term TODO.
+		 */
+		/* If excess == 0, no tree ops */
+		__mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess);
+		spin_unlock(&mctz->lock);
+		css_put(&mz->memcg->css);
+		loop++;
+		/*
+		 * Could not reclaim anything and there are no more
+		 * mem cgroups to try or we seem to be looping without
+		 * reclaiming anything.
+		 */
+		if (!nr_reclaimed &&
+			(next_mz == NULL ||
+			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
+			break;
+	} while (!nr_reclaimed);
+	if (next_mz)
+		css_put(&next_mz->memcg->css);
+	return nr_reclaimed;
+}
+
 /**
  * mem_cgroup_force_empty_list - clears LRU of a group
  * @memcg: group to clear
@@ -4748,31 +4968,18 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 	} while (usage > 0);
 }
 
-/*
- * 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_subsys_state *pos;
-
-	/* bounce at first found */
-	css_for_each_child(pos, &memcg->css)
-		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);
+	lockdep_assert_held(&memcg_create_mutex);
+	/*
+	 * The lock does not prevent addition or deletion to the list
+	 * of children, but it prevents a new child from being
+	 * initialized based on this parent in css_online(), so it's
+	 * enough to decide whether hierarchically inherited
+	 * attributes can still be changed or not.
+	 */
+	return memcg->use_hierarchy &&
+		!list_empty(&memcg->css.cgroup->children);
 }
 
 /*
@@ -4852,7 +5059,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
 	 */
 	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
 				(val == 1 || val == 0)) {
-		if (!__memcg_has_children(memcg))
+		if (list_empty(&memcg->css.cgroup->children))
 			memcg->use_hierarchy = val;
 		else
 			retval = -EBUSY;
@@ -5179,45 +5386,50 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
 static int memcg_numa_stat_show(struct cgroup_subsys_state *css,
 				struct cftype *cft, struct seq_file *m)
 {
+	struct numa_stat {
+		const char *name;
+		unsigned int lru_mask;
+	};
+
+	static const struct numa_stat stats[] = {
+		{ "total", LRU_ALL },
+		{ "file", LRU_ALL_FILE },
+		{ "anon", LRU_ALL_ANON },
+		{ "unevictable", BIT(LRU_UNEVICTABLE) },
+	};
+	const struct numa_stat *stat;
 	int nid;
-	unsigned long total_nr, file_nr, anon_nr, unevictable_nr;
-	unsigned long node_nr;
+	unsigned long nr;
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
-	total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL);
-	seq_printf(m, "total=%lu", total_nr);
-	for_each_node_state(nid, N_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL);
-		seq_printf(m, " N%d=%lu", nid, node_nr);
-	}
-	seq_putc(m, '\n');
-
-	file_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_FILE);
-	seq_printf(m, "file=%lu", file_nr);
-	for_each_node_state(nid, N_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
-				LRU_ALL_FILE);
-		seq_printf(m, " N%d=%lu", nid, node_nr);
+	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
+		nr = mem_cgroup_nr_lru_pages(memcg, stat->lru_mask);
+		seq_printf(m, "%s=%lu", stat->name, nr);
+		for_each_node_state(nid, N_MEMORY) {
+			nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
+							  stat->lru_mask);
+			seq_printf(m, " N%d=%lu", nid, nr);
+		}
+		seq_putc(m, '\n');
 	}
-	seq_putc(m, '\n');
 
-	anon_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_ANON);
-	seq_printf(m, "anon=%lu", anon_nr);
-	for_each_node_state(nid, N_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
-				LRU_ALL_ANON);
-		seq_printf(m, " N%d=%lu", nid, node_nr);
+	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
+		struct mem_cgroup *iter;
+
+		nr = 0;
+		for_each_mem_cgroup_tree(iter, memcg)
+			nr += mem_cgroup_nr_lru_pages(iter, stat->lru_mask);
+		seq_printf(m, "hierarchical_%s=%lu", stat->name, nr);
+		for_each_node_state(nid, N_MEMORY) {
+			nr = 0;
+			for_each_mem_cgroup_tree(iter, memcg)
+				nr += mem_cgroup_node_nr_lru_pages(
+					iter, nid, stat->lru_mask);
+			seq_printf(m, " N%d=%lu", nid, nr);
+		}
+		seq_putc(m, '\n');
 	}
-	seq_putc(m, '\n');
 
-	unevictable_nr = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE));
-	seq_printf(m, "unevictable=%lu", unevictable_nr);
-	for_each_node_state(nid, N_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
-				BIT(LRU_UNEVICTABLE));
-		seq_printf(m, " N%d=%lu", nid, node_nr);
-	}
-	seq_putc(m, '\n');
 	return 0;
 }
 #endif /* CONFIG_NUMA */
@@ -5911,6 +6123,8 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		mz = &pn->zoneinfo[zone];
 		lruvec_init(&mz->lruvec);
+		mz->usage_in_excess = 0;
+		mz->on_tree = false;
 		mz->memcg = memcg;
 	}
 	memcg->nodeinfo[node] = pn;
@@ -5966,7 +6180,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 	int node;
 	size_t size = memcg_size();
 
-	free_css_id(&mem_cgroup_subsys, &memcg->css);
+	mem_cgroup_remove_from_trees(memcg);
 
 	for_each_node(node)
 		free_mem_cgroup_per_zone_info(memcg, node);
@@ -6002,6 +6216,29 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
+static void __init mem_cgroup_soft_limit_tree_init(void)
+{
+	struct mem_cgroup_tree_per_node *rtpn;
+	struct mem_cgroup_tree_per_zone *rtpz;
+	int tmp, node, zone;
+
+	for_each_node(node) {
+		tmp = node;
+		if (!node_state(node, N_NORMAL_MEMORY))
+			tmp = -1;
+		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
+		BUG_ON(!rtpn);
+
+		soft_limit_tree.rb_tree_per_node[node] = rtpn;
+
+		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+			rtpz = &rtpn->rb_tree_per_zone[zone];
+			rtpz->rb_root = RB_ROOT;
+			spin_lock_init(&rtpz->lock);
+		}
+	}
+}
+
 static struct cgroup_subsys_state * __ref
 mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
@@ -6031,7 +6268,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	mutex_init(&memcg->thresholds_lock);
 	spin_lock_init(&memcg->move_lock);
 	vmpressure_init(&memcg->vmpressure);
-	spin_lock_init(&memcg->soft_lock);
 
 	return &memcg->css;
 
@@ -6047,6 +6283,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css));
 	int error = 0;
 
+	if (css->cgroup->id > MEM_CGROUP_ID_MAX)
+		return -ENOSPC;
+
 	if (!parent)
 		return 0;
 
@@ -6109,13 +6348,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
 	mem_cgroup_reparent_charges(memcg);
-	if (memcg->soft_contributed) {
-		while ((memcg = parent_mem_cgroup(memcg)))
-			atomic_dec(&memcg->children_in_excess);
-
-		if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
-			atomic_dec(&root_mem_cgroup->children_in_excess);
-	}
 	mem_cgroup_destroy_all_caches(memcg);
 	vmpressure_cleanup(&memcg->vmpressure);
 }
@@ -6123,6 +6355,42 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	/*
+	 * XXX: css_offline() would be where we should reparent all
+	 * memory to prepare the cgroup for destruction.  However,
+	 * memcg does not do css_tryget() and res_counter charging
+	 * under the same RCU lock region, which means that charging
+	 * could race with offlining.  Offlining only happens to
+	 * cgroups with no tasks in them but charges can show up
+	 * without any tasks from the swapin path when the target
+	 * memcg is looked up from the swapout record and not from the
+	 * current task as it usually is.  A race like this can leak
+	 * charges and put pages with stale cgroup pointers into
+	 * circulation:
+	 *
+	 * #0                        #1
+	 *                           lookup_swap_cgroup_id()
+	 *                           rcu_read_lock()
+	 *                           mem_cgroup_lookup()
+	 *                           css_tryget()
+	 *                           rcu_read_unlock()
+	 * disable css_tryget()
+	 * call_rcu()
+	 *   offline_css()
+	 *     reparent_charges()
+	 *                           res_counter_charge()
+	 *                           css_put()
+	 *                             css_free()
+	 *                           pc->mem_cgroup = dead memcg
+	 *                           add page to lru
+	 *
+	 * The bulk of the charges are still moved in offline_css() to
+	 * avoid pinning a lot of pages in case a long-term reference
+	 * like a swapout record is deferring the css_free() to long
+	 * after offlining.  But this makes sure we catch any charges
+	 * made after offlining:
+	 */
+	mem_cgroup_reparent_charges(memcg);
 
 	memcg_destroy_kmem(memcg);
 	__mem_cgroup_free(memcg);
@@ -6325,7 +6593,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 	}
 	/* There is a swap entry and a page doesn't exist or isn't charged */
 	if (ent.val && !ret &&
-			css_id(&mc.from->css) == lookup_swap_cgroup_id(ent)) {
+	    mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) {
 		ret = MC_TARGET_SWAP;
 		if (target)
 			target->ent = ent;
@@ -6376,10 +6644,10 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
 			mc.precharge += HPAGE_PMD_NR;
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 		return 0;
 	}
 
@@ -6568,9 +6836,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	 *    to be unlocked in __split_huge_page_splitting(), where the main
 	 *    part of thp split is not executed yet.
 	 */
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		if (mc.precharge < HPAGE_PMD_NR) {
-			spin_unlock(&vma->vm_mm->page_table_lock);
+			spin_unlock(ptl);
 			return 0;
 		}
 		target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
@@ -6587,7 +6855,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 			}
 			put_page(page);
 		}
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 		return 0;
 	}
 
@@ -6745,7 +7013,6 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.bind = mem_cgroup_bind,
 	.base_cftypes = mem_cgroup_files,
 	.early_init = 0,
-	.use_id = 1,
 };
 
 #ifdef CONFIG_MEMCG_SWAP
@@ -6790,6 +7057,7 @@ 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;
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 947ed5413279..fabe55046c1d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -938,6 +938,16 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 				BUG_ON(!PageHWPoison(p));
 				return SWAP_FAIL;
 			}
+			/*
+			 * We pinned the head page for hwpoison handling,
+			 * now we split the thp and we are interested in
+			 * the hwpoisoned raw page, so move the refcount
+			 * to it.
+			 */
+			if (hpage != p) {
+				put_page(hpage);
+				get_page(p);
+			}
 			/* THP is split, so ppage should be the real poisoned page. */
 			ppage = p;
 		}
@@ -1114,8 +1124,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			 * shake_page could have turned it free.
 			 */
 			if (is_free_buddy_page(p)) {
-				action_result(pfn, "free buddy, 2nd try",
-						DELAYED);
+				if (flags & MF_COUNT_INCREASED)
+					action_result(pfn, "free buddy", DELAYED);
+				else
+					action_result(pfn, "free buddy, 2nd try", DELAYED);
 				return 0;
 			}
 			action_result(pfn, "non LRU", IGNORED);
@@ -1267,7 +1279,7 @@ void memory_failure_queue(unsigned long pfn, int trapno, int flags)
 
 	mf_cpu = &get_cpu_var(memory_failure_cpu);
 	spin_lock_irqsave(&mf_cpu->lock, proc_flags);
-	if (kfifo_put(&mf_cpu->fifo, &entry))
+	if (kfifo_put(&mf_cpu->fifo, entry))
 		schedule_work_on(smp_processor_id(), &mf_cpu->work);
 	else
 		pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n",
@@ -1349,7 +1361,7 @@ int unpoison_memory(unsigned long pfn)
 	 * worked by memory_failure() and the page lock is not held yet.
 	 * In such case, we yield to memory_failure() and make unpoison fail.
 	 */
-	if (PageTransHuge(page)) {
+	if (!PageHuge(page) && PageTransHuge(page)) {
 		pr_info("MCE: Memory failure is now running on %#lx\n", pfn);
 			return 0;
 	}
@@ -1421,19 +1433,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 		return 1;
 
 	/*
-	 * The lock_memory_hotplug prevents a race with memory hotplug.
-	 * This is a big hammer, a better would be nicer.
-	 */
-	lock_memory_hotplug();
-
-	/*
-	 * Isolate the page, so that it doesn't get reallocated if it
-	 * was free. This flag should be kept set until the source page
-	 * is freed and PG_hwpoison on it is set.
-	 */
-	if (get_pageblock_migratetype(p) != MIGRATE_ISOLATE)
-		set_migratetype_isolate(p, true);
-	/*
 	 * When the target page is a free hugepage, just remove it
 	 * from free hugepage list.
 	 */
@@ -1453,7 +1452,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 		/* Not a free page */
 		ret = 1;
 	}
-	unlock_memory_hotplug();
 	return ret;
 }
 
@@ -1517,10 +1515,16 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		if (ret > 0)
 			ret = -EIO;
 	} else {
-		set_page_hwpoison_huge_page(hpage);
-		dequeue_hwpoisoned_huge_page(hpage);
-		atomic_long_add(1 << compound_order(hpage),
-				&num_poisoned_pages);
+		/* overcommit hugetlb page will be freed to buddy */
+		if (PageHuge(page)) {
+			set_page_hwpoison_huge_page(hpage);
+			dequeue_hwpoisoned_huge_page(hpage);
+			atomic_long_add(1 << compound_order(hpage),
+					&num_poisoned_pages);
+		} else {
+			SetPageHWPoison(page);
+			atomic_long_inc(&num_poisoned_pages);
+		}
 	}
 	return ret;
 }
@@ -1652,15 +1656,28 @@ int soft_offline_page(struct page *page, int flags)
 		}
 	}
 
+	/*
+	 * The lock_memory_hotplug prevents a race with memory hotplug.
+	 * This is a big hammer, a better would be nicer.
+	 */
+	lock_memory_hotplug();
+
+	/*
+	 * Isolate the page, so that it doesn't get reallocated if it
+	 * was free. This flag should be kept set until the source page
+	 * is freed and PG_hwpoison on it is set.
+	 */
+	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
+		set_migratetype_isolate(page, true);
+
 	ret = get_any_page(page, pfn, flags);
-	if (ret < 0)
-		goto unset;
-	if (ret) { /* for in-use pages */
+	unlock_memory_hotplug();
+	if (ret > 0) { /* 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 */
+	} else if (ret == 0) { /* for free pages */
 		if (PageHuge(page)) {
 			set_page_hwpoison_huge_page(hpage);
 			dequeue_hwpoisoned_huge_page(hpage);
@@ -1671,7 +1688,6 @@ int soft_offline_page(struct page *page, int flags)
 			atomic_long_inc(&num_poisoned_pages);
 		}
 	}
-unset:
 	unset_migratetype_isolate(page, MIGRATE_MOVABLE);
 	return ret;
 }
diff --git a/mm/memory.c b/mm/memory.c
index ca0003947115..6768ce9e57d2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -69,8 +69,8 @@
 
 #include "internal.h"
 
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
-#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nid.
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
 #endif
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -382,7 +382,7 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 	pgtable_t token = pmd_pgtable(*pmd);
 	pmd_clear(pmd);
 	pte_free_tlb(tlb, token, addr);
-	tlb->mm->nr_ptes--;
+	atomic_long_dec(&tlb->mm->nr_ptes);
 }
 
 static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -453,8 +453,6 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 
 /*
  * This function frees user-level page tables of a process.
- *
- * Must be called with pagetable lock held.
  */
 void free_pgd_range(struct mmu_gather *tlb,
 			unsigned long addr, unsigned long end,
@@ -552,6 +550,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		pmd_t *pmd, unsigned long address)
 {
+	spinlock_t *ptl;
 	pgtable_t new = pte_alloc_one(mm, address);
 	int wait_split_huge_page;
 	if (!new)
@@ -572,15 +571,15 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	wait_split_huge_page = 0;
 	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
-		mm->nr_ptes++;
+		atomic_long_inc(&mm->nr_ptes);
 		pmd_populate(mm, pmd, new);
 		new = NULL;
 	} else if (unlikely(pmd_trans_splitting(*pmd)))
 		wait_split_huge_page = 1;
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	if (new)
 		pte_free(mm, new);
 	if (wait_split_huge_page)
@@ -681,7 +680,7 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 	if (vma->vm_ops)
 		printk(KERN_ALERT "vma->vm_ops->fault: %pSR\n",
 		       vma->vm_ops->fault);
-	if (vma->vm_file && vma->vm_file->f_op)
+	if (vma->vm_file)
 		printk(KERN_ALERT "vma->vm_file->f_op->mmap: %pSR\n",
 		       vma->vm_file->f_op->mmap);
 	dump_stack();
@@ -837,6 +836,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 					 */
 					make_migration_entry_read(&entry);
 					pte = swp_entry_to_pte(entry);
+					if (pte_swp_soft_dirty(*src_pte))
+						pte = pte_swp_mksoft_dirty(pte);
 					set_pte_at(src_mm, addr, src_pte, pte);
 				}
 			}
@@ -1516,20 +1517,20 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 			split_huge_page_pmd(vma, address, pmd);
 			goto split_fallthrough;
 		}
-		spin_lock(&mm->page_table_lock);
+		ptl = pmd_lock(mm, pmd);
 		if (likely(pmd_trans_huge(*pmd))) {
 			if (unlikely(pmd_trans_splitting(*pmd))) {
-				spin_unlock(&mm->page_table_lock);
+				spin_unlock(ptl);
 				wait_split_huge_page(vma->anon_vma, pmd);
 			} else {
 				page = follow_trans_huge_pmd(vma, address,
 							     pmd, flags);
-				spin_unlock(&mm->page_table_lock);
+				spin_unlock(ptl);
 				*page_mask = HPAGE_PMD_NR - 1;
 				goto out;
 			}
 		} else
-			spin_unlock(&mm->page_table_lock);
+			spin_unlock(ptl);
 		/* fall through */
 	}
 split_fallthrough:
@@ -2719,6 +2720,14 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		get_page(dirty_page);
 
 reuse:
+		/*
+		 * Clear the pages cpupid information as the existing
+		 * information potentially belongs to a now completely
+		 * unrelated process.
+		 */
+		if (old_page)
+			page_cpupid_xchg_last(old_page, (1 << LAST_CPUPID_SHIFT) - 1);
+
 		flush_cache_page(vma, address, pte_pfn(orig_pte));
 		entry = pte_mkyoung(orig_pte);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
@@ -3519,13 +3528,16 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
-				unsigned long addr, int current_nid)
+				unsigned long addr, int page_nid,
+				int *flags)
 {
 	get_page(page);
 
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == numa_node_id()) {
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
+		*flags |= TNF_FAULT_LOCAL;
+	}
 
 	return mpol_misplaced(page, vma, addr);
 }
@@ -3535,9 +3547,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
-	int current_nid = -1;
+	int page_nid = -1;
+	int last_cpupid;
 	int target_nid;
 	bool migrated = false;
+	int flags = 0;
 
 	/*
 	* The "pte" at this point cannot be used safely without
@@ -3564,123 +3578,44 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		pte_unmap_unlock(ptep, ptl);
 		return 0;
 	}
+	BUG_ON(is_zero_pfn(page_to_pfn(page)));
+
+	/*
+	 * Avoid grouping on DSO/COW pages in specific and RO pages
+	 * in general, RO pages shouldn't hurt as much anyway since
+	 * they can be in shared cache state.
+	 */
+	if (!pte_write(pte))
+		flags |= TNF_NO_GROUP;
 
-	current_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+	/*
+	 * Flag if the page is shared between multiple address spaces. This
+	 * is later used when determining whether to group tasks together
+	 */
+	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
+		flags |= TNF_SHARED;
+
+	last_cpupid = page_cpupid_last(page);
+	page_nid = page_to_nid(page);
+	target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags);
 	pte_unmap_unlock(ptep, ptl);
 	if (target_nid == -1) {
-		/*
-		 * Account for the fault against the current node if it not
-		 * being replaced regardless of where the page is located.
-		 */
-		current_nid = numa_node_id();
 		put_page(page);
 		goto out;
 	}
 
 	/* Migrate to the requested node */
-	migrated = migrate_misplaced_page(page, target_nid);
-	if (migrated)
-		current_nid = target_nid;
-
-out:
-	if (current_nid != -1)
-		task_numa_fault(current_nid, 1, migrated);
-	return 0;
-}
-
-/* NUMA hinting page fault entry point for regular pmds */
-#ifdef CONFIG_NUMA_BALANCING
-static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
-		     unsigned long addr, pmd_t *pmdp)
-{
-	pmd_t pmd;
-	pte_t *pte, *orig_pte;
-	unsigned long _addr = addr & PMD_MASK;
-	unsigned long offset;
-	spinlock_t *ptl;
-	bool numa = false;
-	int local_nid = numa_node_id();
-
-	spin_lock(&mm->page_table_lock);
-	pmd = *pmdp;
-	if (pmd_numa(pmd)) {
-		set_pmd_at(mm, _addr, pmdp, pmd_mknonnuma(pmd));
-		numa = true;
+	migrated = migrate_misplaced_page(page, vma, target_nid);
+	if (migrated) {
+		page_nid = target_nid;
+		flags |= TNF_MIGRATED;
 	}
-	spin_unlock(&mm->page_table_lock);
-
-	if (!numa)
-		return 0;
 
-	/* we're in a page fault so some vma must be in the range */
-	BUG_ON(!vma);
-	BUG_ON(vma->vm_start >= _addr + PMD_SIZE);
-	offset = max(_addr, vma->vm_start) & ~PMD_MASK;
-	VM_BUG_ON(offset >= PMD_SIZE);
-	orig_pte = pte = pte_offset_map_lock(mm, pmdp, _addr, &ptl);
-	pte += offset >> PAGE_SHIFT;
-	for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
-		pte_t pteval = *pte;
-		struct page *page;
-		int curr_nid = local_nid;
-		int target_nid;
-		bool migrated;
-		if (!pte_present(pteval))
-			continue;
-		if (!pte_numa(pteval))
-			continue;
-		if (addr >= vma->vm_end) {
-			vma = find_vma(mm, addr);
-			/* there's a pte present so there must be a vma */
-			BUG_ON(!vma);
-			BUG_ON(addr < vma->vm_start);
-		}
-		if (pte_numa(pteval)) {
-			pteval = pte_mknonnuma(pteval);
-			set_pte_at(mm, addr, pte, pteval);
-		}
-		page = vm_normal_page(vma, addr, pteval);
-		if (unlikely(!page))
-			continue;
-		/* only check non-shared pages */
-		if (unlikely(page_mapcount(page) != 1))
-			continue;
-
-		/*
-		 * Note that the NUMA fault is later accounted to either
-		 * the node that is currently running or where the page is
-		 * migrated to.
-		 */
-		curr_nid = local_nid;
-		target_nid = numa_migrate_prep(page, vma, addr,
-					       page_to_nid(page));
-		if (target_nid == -1) {
-			put_page(page);
-			continue;
-		}
-
-		/* Migrate to the requested node */
-		pte_unmap_unlock(pte, ptl);
-		migrated = migrate_misplaced_page(page, target_nid);
-		if (migrated)
-			curr_nid = target_nid;
-		task_numa_fault(curr_nid, 1, migrated);
-
-		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
-	}
-	pte_unmap_unlock(orig_pte, ptl);
-
-	return 0;
-}
-#else
-static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
-		     unsigned long addr, pmd_t *pmdp)
-{
-	BUG();
+out:
+	if (page_nid != -1)
+		task_numa_fault(last_cpupid, page_nid, 1, flags);
 	return 0;
 }
-#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * These routines also need to handle stuff like marking pages dirty
@@ -3820,8 +3755,8 @@ retry:
 		}
 	}
 
-	if (pmd_numa(*pmd))
-		return do_pmd_numa_page(mm, vma, address, pmd);
+	/* THP should already have been handled */
+	BUG_ON(pmd_numa(*pmd));
 
 	/*
 	 * Use __pte_alloc instead of pte_alloc_map, because we can't
@@ -3863,15 +3798,21 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * space.  Kernel faults are handled more gracefully.
 	 */
 	if (flags & FAULT_FLAG_USER)
-		mem_cgroup_enable_oom();
+		mem_cgroup_oom_enable();
 
 	ret = __handle_mm_fault(mm, vma, address, flags);
 
-	if (flags & FAULT_FLAG_USER)
-		mem_cgroup_disable_oom();
-
-	if (WARN_ON(task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)))
-		mem_cgroup_oom_synchronize();
+	if (flags & FAULT_FLAG_USER) {
+		mem_cgroup_oom_disable();
+                /*
+                 * The task may have entered a memcg OOM situation but
+                 * if the allocation error was handled gracefully (no
+                 * VM_FAULT_OOM), there is no need to kill anything.
+                 * Just clean up the OOM state peacefully.
+                 */
+                if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
+                        mem_cgroup_oom_synchronize(false);
+	}
 
 	return ret;
 }
@@ -4329,3 +4270,21 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 	}
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
+
+#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS
+bool ptlock_alloc(struct page *page)
+{
+	spinlock_t *ptl;
+
+	ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
+	if (!ptl)
+		return false;
+	page->ptl = ptl;
+	return true;
+}
+
+void ptlock_free(struct page *page)
+{
+	kfree(page->ptl);
+}
+#endif
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ed85fe3870e2..489f235502db 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -31,6 +31,7 @@
 #include <linux/firmware-map.h>
 #include <linux/stop_machine.h>
 #include <linux/hugetlb.h>
+#include <linux/memblock.h>
 
 #include <asm/tlbflush.h>
 
@@ -365,8 +366,7 @@ out_fail:
 static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
 			    unsigned long end_pfn)
 {
-	unsigned long old_pgdat_end_pfn =
-		pgdat->node_start_pfn + pgdat->node_spanned_pages;
+	unsigned long old_pgdat_end_pfn = pgdat_end_pfn(pgdat);
 
 	if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
 		pgdat->node_start_pfn = start_pfn;
@@ -402,13 +402,12 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 static int __meminit __add_section(int nid, struct zone *zone,
 					unsigned long phys_start_pfn)
 {
-	int nr_pages = PAGES_PER_SECTION;
 	int ret;
 
 	if (pfn_valid(phys_start_pfn))
 		return -EEXIST;
 
-	ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);
+	ret = sparse_add_one_section(zone, phys_start_pfn);
 
 	if (ret < 0)
 		return ret;
@@ -579,9 +578,9 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 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 pgdat_start_pfn = pgdat->node_start_pfn;
+	unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
+	unsigned long pgdat_end_pfn = p;
 	unsigned long pfn;
 	struct mem_section *ms;
 	int nid = pgdat->node_id;
@@ -935,7 +934,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	arg.nr_pages = nr_pages;
 	node_states_check_changes_online(nr_pages, zone, &arg);
 
-	nid = page_to_nid(pfn_to_page(pfn));
+	nid = pfn_to_nid(pfn);
 
 	ret = memory_notify(MEM_GOING_ONLINE, &arg);
 	ret = notifier_to_errno(ret);
@@ -1044,17 +1043,23 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
 }
 
 
-/*
+/**
+ * try_online_node - online a node if offlined
+ *
  * called by cpu_up() to online a node without onlined memory.
  */
-int mem_online_node(int nid)
+int try_online_node(int nid)
 {
 	pg_data_t	*pgdat;
 	int	ret;
 
+	if (node_online(nid))
+		return 0;
+
 	lock_memory_hotplug();
 	pgdat = hotadd_new_pgdat(nid, 0);
 	if (!pgdat) {
+		pr_err("Cannot online node %d due to NULL pgdat\n", nid);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1062,6 +1067,12 @@ int mem_online_node(int nid)
 	ret = register_one_node(nid);
 	BUG_ON(ret);
 
+	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
+		mutex_lock(&zonelists_mutex);
+		build_all_zonelists(NULL, NULL);
+		mutex_unlock(&zonelists_mutex);
+	}
+
 out:
 	unlock_memory_hotplug();
 	return ret;
@@ -1412,6 +1423,36 @@ static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
 }
 #endif /* CONFIG_MOVABLE_NODE */
 
+static int __init cmdline_parse_movable_node(char *p)
+{
+#ifdef CONFIG_MOVABLE_NODE
+	/*
+	 * Memory used by the kernel cannot be hot-removed because Linux
+	 * cannot migrate the kernel pages. When memory hotplug is
+	 * enabled, we should prevent memblock from allocating memory
+	 * for the kernel.
+	 *
+	 * ACPI SRAT records all hotpluggable memory ranges. But before
+	 * SRAT is parsed, we don't know about it.
+	 *
+	 * The kernel image is loaded into memory at very early time. We
+	 * cannot prevent this anyway. So on NUMA system, we set any
+	 * node the kernel resides in as un-hotpluggable.
+	 *
+	 * Since on modern servers, one node could have double-digit
+	 * gigabytes memory, we can assume the memory around the kernel
+	 * image is also un-hotpluggable. So before SRAT is parsed, just
+	 * allocate memory near the kernel image to try the best to keep
+	 * the kernel away from hotpluggable memory.
+	 */
+	memblock_set_bottom_up(true);
+#else
+	pr_warn("movable_node option not supported\n");
+#endif
+	return 0;
+}
+early_param("movable_node", cmdline_parse_movable_node);
+
 /* check which state of node_states will be changed when offline memory */
 static void node_states_check_changes_offline(unsigned long nr_pages,
 		struct zone *zone, struct memory_notify *arg)
@@ -1702,7 +1743,7 @@ int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static int is_memblock_offlined_cb(struct memory_block *mem, void *arg)
+static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
 {
 	int ret = !is_memblock_offlined(mem);
 
@@ -1854,7 +1895,7 @@ void __ref remove_memory(int nid, u64 start, u64 size)
 	 * if this is not the case.
 	 */
 	ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL,
-				is_memblock_offlined_cb);
+				check_memblock_offlined_cb);
 	if (ret) {
 		unlock_memory_hotplug();
 		BUG();
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 04729647f359..0cd2c4d4e270 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -525,8 +525,9 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 #ifdef CONFIG_HUGETLB_PAGE
 	int nid;
 	struct page *page;
+	spinlock_t *ptl;
 
-	spin_lock(&vma->vm_mm->page_table_lock);
+	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
 	page = pte_page(huge_ptep_get((pte_t *)pmd));
 	nid = page_to_nid(page);
 	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
@@ -536,7 +537,7 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1))
 		isolate_huge_page(page, private);
 unlock:
-	spin_unlock(&vma->vm_mm->page_table_lock);
+	spin_unlock(ptl);
 #else
 	BUG();
 #endif
@@ -1125,7 +1126,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	tmp = *from;
 	while (!nodes_empty(tmp)) {
 		int s,d;
-		int source = -1;
+		int source = NUMA_NO_NODE;
 		int dest = 0;
 
 		for_each_node_mask(s, tmp) {
@@ -1160,7 +1161,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 			if (!node_isset(dest, tmp))
 				break;
 		}
-		if (source == -1)
+		if (source == NUMA_NO_NODE)
 			break;
 
 		node_clear(source, tmp);
@@ -1196,14 +1197,16 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int *
 			break;
 		vma = vma->vm_next;
 	}
+
+	if (PageHuge(page)) {
+		if (vma)
+			return alloc_huge_page_noerr(vma, address, 1);
+		else
+			return NULL;
+	}
 	/*
-	 * queue_pages_range() confirms that @page belongs to some vma,
-	 * so vma shouldn't be NULL.
+	 * if !vma, alloc_page_vma() will use task or system default policy
 	 */
-	BUG_ON(!vma);
-
-	if (PageHuge(page))
-		return alloc_huge_page_noerr(vma, address, 1);
 	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 }
 #else
@@ -1317,7 +1320,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 		if (nr_failed && (flags & MPOL_MF_STRICT))
 			err = -EIO;
 	} else
-		putback_lru_pages(&pagelist);
+		putback_movable_pages(&pagelist);
 
 	up_write(&mm->mmap_sem);
  mpol_out:
@@ -1679,6 +1682,30 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 	return pol;
 }
 
+bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma)
+{
+	struct mempolicy *pol = get_task_policy(task);
+	if (vma) {
+		if (vma->vm_ops && vma->vm_ops->get_policy) {
+			bool ret = false;
+
+			pol = vma->vm_ops->get_policy(vma, vma->vm_start);
+			if (pol && (pol->flags & MPOL_F_MOF))
+				ret = true;
+			mpol_cond_put(pol);
+
+			return ret;
+		} else if (vma->vm_policy) {
+			pol = vma->vm_policy;
+		}
+	}
+
+	if (!pol)
+		return default_policy.flags & MPOL_F_MOF;
+
+	return pol->flags & MPOL_F_MOF;
+}
+
 static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
 {
 	enum zone_type dynamic_policy_zone = policy_zone;
@@ -1811,7 +1838,7 @@ static unsigned offset_il_node(struct mempolicy *pol,
 	unsigned nnodes = nodes_weight(pol->v.nodes);
 	unsigned target;
 	int c;
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	if (!nnodes)
 		return numa_node_id();
@@ -1848,11 +1875,11 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
 
 /*
  * Return the bit number of a random bit set in the nodemask.
- * (returns -1 if nodemask is empty)
+ * (returns NUMA_NO_NODE if nodemask is empty)
  */
 int node_random(const nodemask_t *maskp)
 {
-	int w, bit = -1;
+	int w, bit = NUMA_NO_NODE;
 
 	w = nodes_weight(*maskp);
 	if (w)
@@ -2277,6 +2304,35 @@ static void sp_free(struct sp_node *n)
 	kmem_cache_free(sn_cache, n);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
+{
+	/* Never defer a private fault */
+	if (cpupid_match_pid(p, last_cpupid))
+		return false;
+
+	if (p->numa_migrate_deferred) {
+		p->numa_migrate_deferred--;
+		return true;
+	}
+	return false;
+}
+
+static inline void defer_numa_migrate(struct task_struct *p)
+{
+	p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred;
+}
+#else
+static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
+{
+	return false;
+}
+
+static inline void defer_numa_migrate(struct task_struct *p)
+{
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /**
  * mpol_misplaced - check whether current page node is valid in policy
  *
@@ -2300,6 +2356,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 	struct zone *zone;
 	int curnid = page_to_nid(page);
 	unsigned long pgoff;
+	int thiscpu = raw_smp_processor_id();
+	int thisnid = cpu_to_node(thiscpu);
 	int polnid = -1;
 	int ret = -1;
 
@@ -2348,9 +2406,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 
 	/* Migrate the page towards the node whose CPU is referencing it */
 	if (pol->flags & MPOL_F_MORON) {
-		int last_nid;
+		int last_cpupid;
+		int this_cpupid;
 
-		polnid = numa_node_id();
+		polnid = thisnid;
+		this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid);
 
 		/*
 		 * Multi-stage node selection is used in conjunction
@@ -2373,8 +2433,25 @@ 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_nid_xchg_last(page, polnid);
-		if (last_nid != polnid)
+		last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+		if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) {
+
+			/* See sysctl_numa_balancing_migrate_deferred comment */
+			if (!cpupid_match_pid(current, last_cpupid))
+				defer_numa_migrate(current);
+
+			goto out;
+		}
+
+		/*
+		 * The quadratic filter above reduces extraneous migration
+		 * of shared pages somewhat. This code reduces it even more,
+		 * reducing the overhead of page migrations of shared pages.
+		 * This makes workloads with shared pages rely more on
+		 * "move task near its memory", and less on "move memory
+		 * towards its task", which is exactly what we want.
+		 */
+		if (numa_migrate_deferred(current, last_cpupid))
 			goto out;
 	}
 
@@ -2840,62 +2917,45 @@ out:
  * @maxlen:  length of @buffer
  * @pol:  pointer to mempolicy to be formatted
  *
- * Convert a mempolicy into a string.
- * Returns the number of characters in buffer (if positive)
- * or an error (negative)
+ * Convert @pol into a string.  If @buffer is too short, truncate the string.
+ * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the
+ * longest flag, "relative", and to display at least a few node ids.
  */
-int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 {
 	char *p = buffer;
-	int l;
-	nodemask_t nodes;
-	unsigned short mode;
-	unsigned short flags = pol ? pol->flags : 0;
-
-	/*
-	 * Sanity check:  room for longest mode, flag and some nodes
-	 */
-	VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
+	nodemask_t nodes = NODE_MASK_NONE;
+	unsigned short mode = MPOL_DEFAULT;
+	unsigned short flags = 0;
 
-	if (!pol || pol == &default_policy)
-		mode = MPOL_DEFAULT;
-	else
+	if (pol && pol != &default_policy) {
 		mode = pol->mode;
+		flags = pol->flags;
+	}
 
 	switch (mode) {
 	case MPOL_DEFAULT:
-		nodes_clear(nodes);
 		break;
-
 	case MPOL_PREFERRED:
-		nodes_clear(nodes);
 		if (flags & MPOL_F_LOCAL)
 			mode = MPOL_LOCAL;
 		else
 			node_set(pol->v.preferred_node, nodes);
 		break;
-
 	case MPOL_BIND:
-		/* Fall through */
 	case MPOL_INTERLEAVE:
 		nodes = pol->v.nodes;
 		break;
-
 	default:
-		return -EINVAL;
+		WARN_ON_ONCE(1);
+		snprintf(p, maxlen, "unknown");
+		return;
 	}
 
-	l = strlen(policy_modes[mode]);
-	if (buffer + maxlen < p + l + 1)
-		return -ENOSPC;
-
-	strcpy(p, policy_modes[mode]);
-	p += l;
+	p += snprintf(p, maxlen, "%s", policy_modes[mode]);
 
 	if (flags & MPOL_MODE_FLAGS) {
-		if (buffer + maxlen < p + 2)
-			return -ENOSPC;
-		*p++ = '=';
+		p += snprintf(p, buffer + maxlen - p, "=");
 
 		/*
 		 * Currently, the only defined flags are mutually exclusive
@@ -2907,10 +2967,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	}
 
 	if (!nodes_empty(nodes)) {
-		if (buffer + maxlen < p + 2)
-			return -ENOSPC;
-		*p++ = ':';
+		p += snprintf(p, buffer + maxlen - p, ":");
 	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
 	}
-	return p - buffer;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 9c8d5f59d30b..9194375b2307 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -36,6 +36,7 @@
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
 #include <linux/balloon_compaction.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlbflush.h>
 
@@ -107,7 +108,7 @@ void putback_movable_pages(struct list_head *l)
 		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
-		if (unlikely(balloon_page_movable(page)))
+		if (unlikely(isolated_balloon_page(page)))
 			balloon_page_putback(page);
 		else
 			putback_lru_page(page);
@@ -130,7 +131,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 		ptep = huge_pte_offset(mm, addr);
 		if (!ptep)
 			goto out;
-		ptl = &mm->page_table_lock;
+		ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep);
 	} else {
 		pmd = mm_find_pmd(mm, addr);
 		if (!pmd)
@@ -161,6 +162,8 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 
 	get_page(new);
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
+	if (pte_swp_soft_dirty(*ptep))
+		pte = pte_mksoft_dirty(pte);
 	if (is_write_migration_entry(entry))
 		pte = pte_mkwrite(pte);
 #ifdef CONFIG_HUGETLB_PAGE
@@ -247,9 +250,10 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 	__migration_entry_wait(mm, ptep, ptl);
 }
 
-void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte)
 {
-	spinlock_t *ptl = &(mm)->page_table_lock;
+	spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte);
 	__migration_entry_wait(mm, pte, ptl);
 }
 
@@ -313,14 +317,15 @@ static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
  */
 int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page,
-		struct buffer_head *head, enum migrate_mode mode)
+		struct buffer_head *head, enum migrate_mode mode,
+		int extra_count)
 {
-	int expected_count = 0;
+	int expected_count = 1 + extra_count;
 	void **pslot;
 
 	if (!mapping) {
 		/* Anonymous page without mapping */
-		if (page_count(page) != 1)
+		if (page_count(page) != expected_count)
 			return -EAGAIN;
 		return MIGRATEPAGE_SUCCESS;
 	}
@@ -330,7 +335,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	pslot = radix_tree_lookup_slot(&mapping->page_tree,
  					page_index(page));
 
-	expected_count = 2 + page_has_private(page);
+	expected_count += 1 + page_has_private(page);
 	if (page_count(page) != expected_count ||
 		radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
 		spin_unlock_irq(&mapping->tree_lock);
@@ -439,10 +444,60 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 }
 
 /*
+ * Gigantic pages are so large that we do not guarantee that page++ pointer
+ * arithmetic will work across the entire page.  We need something more
+ * specialized.
+ */
+static void __copy_gigantic_page(struct page *dst, struct page *src,
+				int nr_pages)
+{
+	int i;
+	struct page *dst_base = dst;
+	struct page *src_base = src;
+
+	for (i = 0; i < nr_pages; ) {
+		cond_resched();
+		copy_highpage(dst, src);
+
+		i++;
+		dst = mem_map_next(dst, dst_base, i);
+		src = mem_map_next(src, src_base, i);
+	}
+}
+
+static void copy_huge_page(struct page *dst, struct page *src)
+{
+	int i;
+	int nr_pages;
+
+	if (PageHuge(src)) {
+		/* hugetlbfs page */
+		struct hstate *h = page_hstate(src);
+		nr_pages = pages_per_huge_page(h);
+
+		if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
+			__copy_gigantic_page(dst, src, nr_pages);
+			return;
+		}
+	} else {
+		/* thp page */
+		BUG_ON(!PageTransHuge(src));
+		nr_pages = hpage_nr_pages(src);
+	}
+
+	for (i = 0; i < nr_pages; i++) {
+		cond_resched();
+		copy_highpage(dst + i, src + i);
+	}
+}
+
+/*
  * Copy the page to its new location
  */
 void migrate_page_copy(struct page *newpage, struct page *page)
 {
+	int cpupid;
+
 	if (PageHuge(page) || PageTransHuge(page))
 		copy_huge_page(newpage, page);
 	else
@@ -479,6 +534,13 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 			__set_page_dirty_nobuffers(newpage);
  	}
 
+	/*
+	 * Copy NUMA information to the new page, to prevent over-eager
+	 * future migrations of this same page.
+	 */
+	cpupid = page_cpupid_xchg_last(page, -1);
+	page_cpupid_xchg_last(newpage, cpupid);
+
 	mlock_migrate_page(newpage, page);
 	ksm_migrate_page(newpage, page);
 	/*
@@ -523,7 +585,7 @@ int migrate_page(struct address_space *mapping,
 
 	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
 
-	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
+	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
 
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
@@ -550,7 +612,7 @@ int buffer_migrate_page(struct address_space *mapping,
 
 	head = page_buffers(page);
 
-	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
+	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode, 0);
 
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
@@ -1498,7 +1560,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					  __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 	if (newpage)
-		page_nid_xchg_last(newpage, page_nid_last(page));
+		page_cpupid_xchg_last(newpage, page_cpupid_last(page));
 
 	return newpage;
 }
@@ -1594,12 +1656,25 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 	return 1;
 }
 
+bool pmd_trans_migrating(pmd_t pmd)
+{
+	struct page *page = pmd_page(pmd);
+	return PageLocked(page);
+}
+
+void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+	struct page *page = pmd_page(*pmd);
+	wait_on_page_locked(page);
+}
+
 /*
  * Attempt to migrate a misplaced page to the specified destination
  * node. Caller is expected to have an elevated reference count on
  * the page that will be dropped by this function before returning.
  */
-int migrate_misplaced_page(struct page *page, int node)
+int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
+			   int node)
 {
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated;
@@ -1607,10 +1682,11 @@ int migrate_misplaced_page(struct page *page, int node)
 	LIST_HEAD(migratepages);
 
 	/*
-	 * Don't migrate pages that are mapped in multiple processes.
-	 * TODO: Handle false sharing detection instead of this hammer
+	 * Don't migrate file pages that are mapped in multiple processes
+	 * with execute permissions as they are probably shared libraries.
 	 */
-	if (page_mapcount(page) != 1)
+	if (page_mapcount(page) != 1 && page_is_file_cache(page) &&
+	    (vma->vm_flags & VM_EXEC))
 		goto out;
 
 	/*
@@ -1653,19 +1729,15 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 				unsigned long address,
 				struct page *page, int node)
 {
-	unsigned long haddr = address & HPAGE_PMD_MASK;
+	spinlock_t *ptl;
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated = 0;
 	struct page *new_page = NULL;
 	struct mem_cgroup *memcg = NULL;
 	int page_lru = page_is_file_cache(page);
-
-	/*
-	 * Don't migrate pages that are mapped in multiple processes.
-	 * TODO: Handle false sharing detection instead of this hammer
-	 */
-	if (page_mapcount(page) != 1)
-		goto out_dropref;
+	unsigned long mmun_start = address & HPAGE_PMD_MASK;
+	unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
+	pmd_t orig_entry;
 
 	/*
 	 * Rate-limit the amount of data that is being migrated to a node.
@@ -1680,7 +1752,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	if (!new_page)
 		goto out_fail;
 
-	page_nid_xchg_last(new_page, page_nid_last(page));
+	page_cpupid_xchg_last(new_page, page_cpupid_last(page));
 
 	isolated = numamigrate_isolate_page(pgdat, page);
 	if (!isolated) {
@@ -1688,6 +1760,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		goto out_fail;
 	}
 
+	if (mm_tlb_flush_pending(mm))
+		flush_tlb_range(vma, mmun_start, mmun_end);
+
 	/* Prepare a page as a migration target */
 	__set_page_locked(new_page);
 	SetPageSwapBacked(new_page);
@@ -1699,9 +1774,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	WARN_ON(PageLRU(new_page));
 
 	/* Recheck the target PMD */
-	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(*pmd, entry))) {
-		spin_unlock(&mm->page_table_lock);
+	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+	ptl = pmd_lock(mm, pmd);
+	if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) {
+fail_putback:
+		spin_unlock(ptl);
+		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 		/* Reverse changes made by migrate_page_copy() */
 		if (TestClearPageActive(new_page))
@@ -1713,12 +1791,13 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		unlock_page(new_page);
 		put_page(new_page);		/* Free it */
 
-		unlock_page(page);
+		/* Retake the callers reference and putback on LRU */
+		get_page(page);
 		putback_lru_page(page);
+		mod_zone_page_state(page_zone(page),
+			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
 
-		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-		isolated = 0;
-		goto out;
+		goto out_unlock;
 	}
 
 	/*
@@ -1730,23 +1809,43 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	 */
 	mem_cgroup_prepare_migration(page, new_page, &memcg);
 
+	orig_entry = *pmd;
 	entry = mk_pmd(new_page, vma->vm_page_prot);
-	entry = pmd_mknonnuma(entry);
-	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 	entry = pmd_mkhuge(entry);
+	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
-	page_add_new_anon_rmap(new_page, vma, haddr);
-
-	set_pmd_at(mm, haddr, pmd, entry);
+	/*
+	 * Clear the old entry under pagetable lock and establish the new PTE.
+	 * Any parallel GUP will either observe the old page blocking on the
+	 * page lock, block on the page table lock or observe the new page.
+	 * The SetPageUptodate on the new page and page_add_new_anon_rmap
+	 * guarantee the copy is visible before the pagetable update.
+	 */
+	flush_cache_range(vma, mmun_start, mmun_end);
+	page_add_new_anon_rmap(new_page, vma, mmun_start);
+	pmdp_clear_flush(vma, mmun_start, pmd);
+	set_pmd_at(mm, mmun_start, pmd, entry);
+	flush_tlb_range(vma, mmun_start, mmun_end);
 	update_mmu_cache_pmd(vma, address, &entry);
+
+	if (page_count(page) != 2) {
+		set_pmd_at(mm, mmun_start, pmd, orig_entry);
+		flush_tlb_range(vma, mmun_start, mmun_end);
+		update_mmu_cache_pmd(vma, address, &entry);
+		page_remove_rmap(new_page);
+		goto fail_putback;
+	}
+
 	page_remove_rmap(page);
+
 	/*
 	 * Finish the charge transaction under the page table lock to
 	 * prevent split_huge_page() from dividing up the charge
 	 * before it's fully transferred to the new page.
 	 */
 	mem_cgroup_end_migration(memcg, page, new_page, true);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
+	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 	unlock_page(new_page);
 	unlock_page(page);
@@ -1756,7 +1855,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
 	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
 
-out:
 	mod_zone_page_state(page_zone(page),
 			NR_ISOLATED_ANON + page_lru,
 			-HPAGE_PMD_NR);
@@ -1765,6 +1863,15 @@ out:
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
+	ptl = pmd_lock(mm, pmd);
+	if (pmd_same(*pmd, entry)) {
+		entry = pmd_mknonnuma(entry);
+		set_pmd_at(mm, mmun_start, pmd, entry);
+		update_mmu_cache_pmd(vma, address, &entry);
+	}
+	spin_unlock(ptl);
+
+out_unlock:
 	unlock_page(page);
 	put_page(page);
 	return 0;
diff --git a/mm/mlock.c b/mm/mlock.c
index d63802663242..192e6eebe4f2 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -133,7 +133,10 @@ static void __munlock_isolation_failed(struct page *page)
 
 /**
  * munlock_vma_page - munlock a vma page
- * @page - page to be unlocked
+ * @page - page to be unlocked, either a normal page or THP page head
+ *
+ * returns the size of the page as a page mask (0 for normal page,
+ *         HPAGE_PMD_NR - 1 for THP head page)
  *
  * called from munlock()/munmap() path with page supposedly on the LRU.
  * When we munlock a page, because the vma where we found the page is being
@@ -148,21 +151,30 @@ static void __munlock_isolation_failed(struct page *page)
  */
 unsigned int munlock_vma_page(struct page *page)
 {
-	unsigned int page_mask = 0;
+	unsigned int nr_pages;
 
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {
-		unsigned int nr_pages = hpage_nr_pages(page);
+		nr_pages = hpage_nr_pages(page);
 		mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
-		page_mask = nr_pages - 1;
 		if (!isolate_lru_page(page))
 			__munlock_isolated_page(page);
 		else
 			__munlock_isolation_failed(page);
+	} else {
+		nr_pages = hpage_nr_pages(page);
 	}
 
-	return page_mask;
+	/*
+	 * Regardless of the original PageMlocked flag, we determine nr_pages
+	 * after touching the flag. This leaves a possible race with a THP page
+	 * split, such that a whole THP page was munlocked, but nr_pages == 1.
+	 * Returning a smaller mask due to that is OK, the worst that can
+	 * happen is subsequent useless scanning of the former tail pages.
+	 * The NR_MLOCK accounting can however become broken.
+	 */
+	return nr_pages - 1;
 }
 
 /**
@@ -286,10 +298,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked = -nr;
+	int delta_munlocked;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
+	pagevec_init(&pvec_putback, 0);
+
 	/* Phase 1: page isolation */
 	spin_lock_irq(&zone->lru_lock);
 	for (i = 0; i < nr; i++) {
@@ -318,18 +332,21 @@ skip_munlock:
 			/*
 			 * We won't be munlocking this page in the next phase
 			 * but we still need to release the follow_page_mask()
-			 * pin.
+			 * pin. We cannot do it under lru_lock however. If it's
+			 * the last pin, __page_cache_release would deadlock.
 			 */
+			pagevec_add(&pvec_putback, pvec->pages[i]);
 			pvec->pages[i] = NULL;
-			put_page(page);
-			delta_munlocked++;
 		}
 	}
+	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
 	spin_unlock_irq(&zone->lru_lock);
 
+	/* Now we can release pins of pages that we are not munlocking */
+	pagevec_release(&pvec_putback);
+
 	/* Phase 2: page munlock */
-	pagevec_init(&pvec_putback, 0);
 	for (i = 0; i < nr; i++) {
 		struct page *page = pvec->pages[i];
 
@@ -379,10 +396,14 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
 
 	/*
 	 * Initialize pte walk starting at the already pinned page where we
-	 * are sure that there is a pte.
+	 * are sure that there is a pte, as it was pinned under the same
+	 * mmap_sem write op.
 	 */
 	pte = get_locked_pte(vma->vm_mm, start,	&ptl);
-	end = min(end, pmd_addr_end(start, end));
+	/* Make sure we do not cross the page table boundary */
+	end = pgd_addr_end(start, end);
+	end = pud_addr_end(start, end);
+	end = pmd_addr_end(start, end);
 
 	/* The page next to the pinned page is the first we will try to get */
 	start += PAGE_SIZE;
@@ -436,7 +457,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 
 	while (start < end) {
 		struct page *page = NULL;
-		unsigned int page_mask, page_increm;
+		unsigned int page_mask;
+		unsigned long page_increm;
 		struct pagevec pvec;
 		struct zone *zone;
 		int zoneid;
@@ -486,7 +508,9 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 				goto next;
 			}
 		}
-		page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+		/* It's a bug to munlock in the middle of a THP page */
+		VM_BUG_ON((start >> PAGE_SHIFT) & page_mask);
+		page_increm = 1 + page_mask;
 		start += page_increm * PAGE_SIZE;
 next:
 		cond_resched();
@@ -736,6 +760,7 @@ static int do_mlockall(int flags)
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
+		cond_resched();
 	}
 out:
 	return 0;
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 633c08863fd8..68562e92d50c 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -71,26 +71,26 @@ 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 - LAST_NID_SHIFT;
+	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_CPUPID_SHIFT;
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
-		"Section %d Node %d Zone %d Lastnid %d Flags %d\n",
+		"Section %d Node %d Zone %d Lastcpupid %d Flags %d\n",
 		SECTIONS_WIDTH,
 		NODES_WIDTH,
 		ZONES_WIDTH,
-		LAST_NID_WIDTH,
+		LAST_CPUPID_WIDTH,
 		NR_PAGEFLAGS);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
-		"Section %d Node %d Zone %d Lastnid %d\n",
+		"Section %d Node %d Zone %d Lastcpupid %d\n",
 		SECTIONS_SHIFT,
 		NODES_SHIFT,
 		ZONES_SHIFT,
-		LAST_NID_SHIFT);
+		LAST_CPUPID_SHIFT);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
-		"Section %lu Node %lu Zone %lu Lastnid %lu\n",
+		"Section %lu Node %lu Zone %lu Lastcpupid %lu\n",
 		(unsigned long)SECTIONS_PGSHIFT,
 		(unsigned long)NODES_PGSHIFT,
 		(unsigned long)ZONES_PGSHIFT,
-		(unsigned long)LAST_NID_PGSHIFT);
+		(unsigned long)LAST_CPUPID_PGSHIFT);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
 		"Node/Zone ID: %lu -> %lu\n",
 		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
@@ -102,9 +102,9 @@ void __init mminit_verify_pageflags_layout(void)
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
 		"Node not in page flags");
 #endif
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
-		"Last nid not in page flags");
+		"Last cpupid not in page flags");
 #endif
 
 	if (SECTIONS_WIDTH) {
diff --git a/mm/mmap.c b/mm/mmap.c
index 9d548512ff8a..834b2d785f1e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -179,14 +179,12 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		goto error;
 	}
 
-	allowed = (totalram_pages - hugetlb_total_pages())
-	       	* sysctl_overcommit_ratio / 100;
+	allowed = vm_commit_limit();
 	/*
 	 * Reserve some for root
 	 */
 	if (!cap_sys_admin)
 		allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
-	allowed += total_swap_pages;
 
 	/*
 	 * Don't let a single process grow so big a user can't recover
@@ -1299,7 +1297,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 				vm_flags &= ~VM_MAYEXEC;
 			}
 
-			if (!file->f_op || !file->f_op->mmap)
+			if (!file->f_op->mmap)
 				return -ENODEV;
 			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
 				return -EINVAL;
@@ -1856,7 +1854,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct vm_area_struct *vma;
 	struct vm_unmapped_area_info info;
 
-	if (len > TASK_SIZE)
+	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
@@ -1865,14 +1863,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 		    (!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
 
 	info.flags = 0;
 	info.length = len;
-	info.low_limit = TASK_UNMAPPED_BASE;
+	info.low_limit = mm->mmap_base;
 	info.high_limit = TASK_SIZE;
 	info.align_mask = 0;
 	return vm_unmapped_area(&info);
@@ -1895,7 +1893,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	struct vm_unmapped_area_info info;
 
 	/* requested length too big for entire address space */
-	if (len > TASK_SIZE)
+	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
@@ -1905,14 +1903,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 				(!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
-	info.low_limit = PAGE_SIZE;
+	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
 	info.high_limit = mm->mmap_base;
 	info.align_mask = 0;
 	addr = vm_unmapped_area(&info);
@@ -1951,7 +1949,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		return -ENOMEM;
 
 	get_area = current->mm->get_unmapped_area;
-	if (file && file->f_op && file->f_op->get_unmapped_area)
+	if (file && file->f_op->get_unmapped_area)
 		get_area = file->f_op->get_unmapped_area;
 	addr = get_area(file, addr, len, pgoff, flags);
 	if (IS_ERR_VALUE(addr))
@@ -2726,7 +2724,8 @@ void exit_mmap(struct mm_struct *mm)
 	}
 	vm_unacct_memory(nr_accounted);
 
-	WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
+	WARN_ON(atomic_long_read(&mm->nr_ptes) >
+			(FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
 }
 
 /* Insert vm structure into process list sorted by address
diff --git a/mm/mmzone.c b/mm/mmzone.c
index 2ac0afbd68f3..bf34fb8556db 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -97,20 +97,20 @@ void lruvec_init(struct lruvec *lruvec)
 		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)
+#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
+int page_cpupid_xchg_last(struct page *page, int cpupid)
 {
 	unsigned long old_flags, flags;
-	int last_nid;
+	int last_cpupid;
 
 	do {
 		old_flags = flags = page->flags;
-		last_nid = page_nid_last(page);
+		last_cpupid = page_cpupid_last(page);
 
-		flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
-		flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
+		flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
+		flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
 	} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));
 
-	return last_nid;
+	return last_cpupid;
 }
 #endif
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 94722a4d6b43..bb53a6591aea 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,14 +37,12 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa, bool *ret_all_same_node)
+		int dirty_accountable, int prot_numa)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
 	unsigned long pages = 0;
-	bool all_same_node = true;
-	int last_nid = -1;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	arch_enter_lazy_mmu_mode();
@@ -54,25 +52,21 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			pte_t ptent;
 			bool updated = false;
 
-			ptent = ptep_modify_prot_start(mm, addr, pte);
 			if (!prot_numa) {
+				ptent = ptep_modify_prot_start(mm, addr, pte);
+				if (pte_numa(ptent))
+					ptent = pte_mknonnuma(ptent);
 				ptent = pte_modify(ptent, newprot);
 				updated = true;
 			} else {
 				struct page *page;
 
+				ptent = *pte;
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page) {
-					int this_nid = page_to_nid(page);
-					if (last_nid == -1)
-						last_nid = this_nid;
-					if (last_nid != this_nid)
-						all_same_node = false;
-
-					/* only check non-shared pages */
-					if (!pte_numa(oldpte) &&
-					    page_mapcount(page) == 1) {
+					if (!pte_numa(oldpte)) {
 						ptent = pte_mknuma(ptent);
+						set_pte_at(mm, addr, pte, ptent);
 						updated = true;
 					}
 				}
@@ -89,45 +83,35 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 			if (updated)
 				pages++;
-			ptep_modify_prot_commit(mm, addr, pte, ptent);
+
+			/* Only !prot_numa always clears the pte */
+			if (!prot_numa)
+				ptep_modify_prot_commit(mm, addr, pte, ptent);
 		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
 			if (is_write_migration_entry(entry)) {
+				pte_t newpte;
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write
 				 */
 				make_migration_entry_read(&entry);
-				set_pte_at(mm, addr, pte,
-					swp_entry_to_pte(entry));
+				newpte = swp_entry_to_pte(entry);
+				if (pte_swp_soft_dirty(oldpte))
+					newpte = pte_swp_mksoft_dirty(newpte);
+				set_pte_at(mm, addr, pte, newpte);
+
+				pages++;
 			}
-			pages++;
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
-	*ret_all_same_node = all_same_node;
 	return pages;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-				       pmd_t *pmd)
-{
-	spin_lock(&mm->page_table_lock);
-	set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd));
-	spin_unlock(&mm->page_table_lock);
-}
-#else
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-				       pmd_t *pmd)
-{
-	BUG();
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pud_t *pud, unsigned long addr, unsigned long end,
 		pgprot_t newprot, int dirty_accountable, int prot_numa)
@@ -135,36 +119,39 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 	pmd_t *pmd;
 	unsigned long next;
 	unsigned long pages = 0;
-	bool all_same_node;
+	unsigned long nr_huge_updates = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
+		unsigned long this_pages;
+
 		next = pmd_addr_end(addr, end);
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				split_huge_page_pmd(vma, addr, pmd);
-			else if (change_huge_pmd(vma, pmd, addr, newprot,
-						 prot_numa)) {
-				pages += HPAGE_PMD_NR;
-				continue;
+			else {
+				int nr_ptes = change_huge_pmd(vma, pmd, addr,
+						newprot, prot_numa);
+
+				if (nr_ptes) {
+					if (nr_ptes == HPAGE_PMD_NR) {
+						pages += HPAGE_PMD_NR;
+						nr_huge_updates++;
+					}
+					continue;
+				}
 			}
 			/* fall through */
 		}
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		pages += change_pte_range(vma, pmd, addr, next, newprot,
-				 dirty_accountable, prot_numa, &all_same_node);
-
-		/*
-		 * If we are changing protections for NUMA hinting faults then
-		 * set pmd_numa if the examined pages were all on the same
-		 * node. This allows a regular PMD to be handled as one fault
-		 * and effectively batches the taking of the PTL
-		 */
-		if (prot_numa && all_same_node)
-			change_pmd_protnuma(vma->vm_mm, addr, pmd);
+		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
+				 dirty_accountable, prot_numa);
+		pages += this_pages;
 	} while (pmd++, addr = next, addr != end);
 
+	if (nr_huge_updates)
+		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
 	return pages;
 }
 
@@ -201,6 +188,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
 	flush_cache_range(vma, addr, end);
+	set_tlb_flush_pending(mm);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
@@ -212,6 +200,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	/* Only flush the TLB if we actually modified any entries: */
 	if (pages)
 		flush_tlb_range(vma, start, end);
+	clear_tlb_flush_pending(mm);
 
 	return pages;
 }
diff --git a/mm/mremap.c b/mm/mremap.c
index 91b13d6a16d4..0843feb66f3d 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -25,7 +25,6 @@
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
-#include <asm/pgalloc.h>
 
 #include "internal.h"
 
@@ -63,10 +62,8 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 		return NULL;
 
 	pmd = pmd_alloc(mm, pud, addr);
-	if (!pmd) {
-		pud_free(mm, pud);
+	if (!pmd)
 		return NULL;
-	}
 
 	VM_BUG_ON(pmd_trans_huge(*pmd));
 
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 61107cf55bb3..2c254d374655 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -82,27 +82,18 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size)
 
 static void __init __free_pages_memory(unsigned long start, unsigned long end)
 {
-	unsigned long i, start_aligned, end_aligned;
-	int order = ilog2(BITS_PER_LONG);
+	int order;
 
-	start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
-	end_aligned = end & ~(BITS_PER_LONG - 1);
+	while (start < end) {
+		order = min(MAX_ORDER - 1UL, __ffs(start));
 
-	if (end_aligned <= start_aligned) {
-		for (i = start; i < end; i++)
-			__free_pages_bootmem(pfn_to_page(i), 0);
+		while (start + (1UL << order) > end)
+			order--;
 
-		return;
-	}
-
-	for (i = start; i < start_aligned; i++)
-		__free_pages_bootmem(pfn_to_page(i), 0);
+		__free_pages_bootmem(pfn_to_page(start), order);
 
-	for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG)
-		__free_pages_bootmem(pfn_to_page(i), order);
-
-	for (i = end_aligned; i < end; i++)
-		__free_pages_bootmem(pfn_to_page(i), 0);
+		start += (1UL << order);
+	}
 }
 
 static unsigned long __init __free_memory_core(phys_addr_t start,
diff --git a/mm/nommu.c b/mm/nommu.c
index ecd1f158548e..fec093adad9c 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -937,7 +937,7 @@ static int validate_mmap_request(struct file *file,
 		struct address_space *mapping;
 
 		/* files must support mmap */
-		if (!file->f_op || !file->f_op->mmap)
+		if (!file->f_op->mmap)
 			return -ENODEV;
 
 		/* work out if what we've got could possibly be shared
@@ -1948,13 +1948,12 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		goto error;
 	}
 
-	allowed = totalram_pages * sysctl_overcommit_ratio / 100;
+	allowed = vm_commit_limit();
 	/*
 	 * Reserve some 3% for root
 	 */
 	if (!cap_sys_admin)
 		allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
-	allowed += total_swap_pages;
 
 	/*
 	 * Don't let a single process grow so big a user can't recover
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 314e9d274381..1e4a600a6163 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -161,7 +161,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * The baseline for the badness score is the proportion of RAM that each
 	 * task's rss, pagetable and swap space use.
 	 */
-	points = get_mm_rss(p->mm) + p->mm->nr_ptes +
+	points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) +
 		 get_mm_counter(p->mm, MM_SWAPENTS);
 	task_unlock(p);
 
@@ -364,10 +364,10 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5hd %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu         %5hd %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
-			task->mm->nr_ptes,
+			atomic_long_read(&task->mm->nr_ptes),
 			get_mm_counter(task->mm, MM_SWAPENTS),
 			task->signal->oom_score_adj, task->comm);
 		task_unlock(task);
@@ -680,7 +680,7 @@ void pagefault_out_of_memory(void)
 {
 	struct zonelist *zonelist;
 
-	if (mem_cgroup_oom_synchronize())
+	if (mem_cgroup_oom_synchronize(true))
 		return;
 
 	zonelist = node_zonelist(first_online_node, GFP_KERNEL);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f5236f804aa6..63807583d8e8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1210,11 +1210,11 @@ static unsigned long dirty_poll_interval(unsigned long dirty,
 	return 1;
 }
 
-static long bdi_max_pause(struct backing_dev_info *bdi,
-			  unsigned long bdi_dirty)
+static unsigned long bdi_max_pause(struct backing_dev_info *bdi,
+				   unsigned long bdi_dirty)
 {
-	long bw = bdi->avg_write_bandwidth;
-	long t;
+	unsigned long bw = bdi->avg_write_bandwidth;
+	unsigned long t;
 
 	/*
 	 * Limit pause time for small memory systems. If sleeping for too long
@@ -1226,7 +1226,7 @@ static long bdi_max_pause(struct backing_dev_info *bdi,
 	t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
 	t++;
 
-	return min_t(long, t, MAX_PAUSE);
+	return min_t(unsigned long, t, MAX_PAUSE);
 }
 
 static long bdi_min_pause(struct backing_dev_info *bdi,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0ee638f76ebe..5248fe070aa4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -234,8 +234,8 @@ int page_group_by_mobility_disabled __read_mostly;
 
 void set_pageblock_migratetype(struct page *page, int migratetype)
 {
-
-	if (unlikely(page_group_by_mobility_disabled))
+	if (unlikely(page_group_by_mobility_disabled &&
+		     migratetype < MIGRATE_PCPTYPES))
 		migratetype = MIGRATE_UNMOVABLE;
 
 	set_pageblock_flags_group(page, (unsigned long)migratetype,
@@ -626,7 +626,7 @@ static inline int free_pages_check(struct page *page)
 		bad_page(page);
 		return 1;
 	}
-	page_nid_reset_last(page);
+	page_cpupid_reset_last(page);
 	if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
 		page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	return 0;
@@ -1027,6 +1027,10 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
 {
 	int current_order = page_order(page);
 
+	/*
+	 * When borrowing from MIGRATE_CMA, we need to release the excess
+	 * buddy pages to CMA itself.
+	 */
 	if (is_migrate_cma(fallback_type))
 		return fallback_type;
 
@@ -1091,21 +1095,11 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			list_del(&page->lru);
 			rmv_page_order(page);
 
-			/*
-			 * Borrow the excess buddy pages as well, irrespective
-			 * of whether we stole freepages, or took ownership of
-			 * the pageblock or not.
-			 *
-			 * Exception: When borrowing from MIGRATE_CMA, release
-			 * the excess buddy pages to CMA itself.
-			 */
 			expand(zone, page, order, current_order, area,
-			       is_migrate_cma(migratetype)
-			     ? migratetype : start_migratetype);
+			       new_type);
 
-			trace_mm_page_alloc_extfrag(page, order,
-				current_order, start_migratetype, migratetype,
-				new_type == start_migratetype);
+			trace_mm_page_alloc_extfrag(page, order, current_order,
+				start_migratetype, migratetype, new_type);
 
 			return page;
 		}
@@ -1711,7 +1705,7 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
  * comments in mmzone.h.  Reduces cache footprint of zonelist scans
  * that have to skip over a lot of full or unallowed zones.
  *
- * If the zonelist cache is present in the passed in zonelist, then
+ * If the zonelist cache is present in the passed zonelist, then
  * returns a pointer to the allowed node mask (either the current
  * tasks mems_allowed, or node_states[N_MEMORY].)
  *
@@ -1822,7 +1816,7 @@ static void zlc_clear_zones_full(struct zonelist *zonelist)
 
 static bool zone_local(struct zone *local_zone, struct zone *zone)
 {
-	return node_distance(local_zone->node, zone->node) == LOCAL_DISTANCE;
+	return local_zone->node == zone->node;
 }
 
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
@@ -1919,18 +1913,17 @@ zonelist_scan:
 		 * page was allocated in should have no effect on the
 		 * time the page has in memory before being reclaimed.
 		 *
-		 * When zone_reclaim_mode is enabled, try to stay in
-		 * local zones in the fastpath.  If that fails, the
-		 * slowpath is entered, which will do another pass
-		 * starting with the local zones, but ultimately fall
-		 * back to remote zones that do not partake in the
-		 * fairness round-robin cycle of this zonelist.
+		 * Try to stay in local zones in the fastpath.  If
+		 * that fails, the slowpath is entered, which will do
+		 * another pass starting with the local zones, but
+		 * ultimately fall back to remote zones that do not
+		 * partake in the fairness round-robin cycle of this
+		 * zonelist.
 		 */
 		if (alloc_flags & ALLOC_WMARK_LOW) {
 			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
 				continue;
-			if (zone_reclaim_mode &&
-			    !zone_local(preferred_zone, zone))
+			if (!zone_local(preferred_zone, zone))
 				continue;
 		}
 		/*
@@ -2396,7 +2389,7 @@ static void prepare_slowpath(gfp_t gfp_mask, unsigned int order,
 		 * thrash fairness information for zones that are not
 		 * actually part of this zonelist's round-robin cycle.
 		 */
-		if (zone_reclaim_mode && !zone_local(preferred_zone, zone))
+		if (!zone_local(preferred_zone, zone))
 			continue;
 		mod_zone_page_state(zone, NR_ALLOC_BATCH,
 				    high_wmark_pages(zone) -
@@ -2593,7 +2586,7 @@ rebalance:
 	 * running out of options and have to consider going OOM
 	 */
 	if (!did_some_progress) {
-		if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+		if (oom_gfp_allowed(gfp_mask)) {
 			if (oom_killer_disabled)
 				goto nopage;
 			/* Coredumps can quickly deplete all memory reserves */
@@ -3881,8 +3874,6 @@ static inline unsigned long wait_table_bits(unsigned long size)
 	return ffz(~size);
 }
 
-#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
-
 /*
  * Check if a pageblock contains reserved pages
  */
@@ -4015,7 +4006,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		mminit_verify_page_links(page, zone, nid, pfn);
 		init_page_count(page);
 		page_mapcount_reset(page);
-		page_nid_reset_last(page);
+		page_cpupid_reset_last(page);
 		SetPageReserved(page);
 		/*
 		 * Mark the block movable so that blocks are reserved for
@@ -4266,7 +4257,7 @@ static __meminit void zone_pcp_init(struct zone *zone)
 	 */
 	zone->pageset = &boot_pageset;
 
-	if (zone->present_pages)
+	if (populated_zone(zone))
 		printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%u\n",
 			zone->name, zone->present_pages,
 					 zone_batchsize(zone));
@@ -5160,7 +5151,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid)
 
 	for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
 		struct zone *zone = &pgdat->node_zones[zone_type];
-		if (zone->present_pages) {
+		if (populated_zone(zone)) {
 			node_set_state(nid, N_HIGH_MEMORY);
 			if (N_NORMAL_MEMORY != N_HIGH_MEMORY &&
 			    zone_type <= ZONE_NORMAL)
@@ -6366,10 +6357,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		list_del(&page->lru);
 		rmv_page_order(page);
 		zone->free_area[order].nr_free--;
-#ifdef CONFIG_HIGHMEM
-		if (PageHighMem(page))
-			totalhigh_pages -= 1 << order;
-#endif
 		for (i = 0; i < (1 << order); i++)
 			SetPageReserved((page+i));
 		pfn += (1 << order);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 5da2cbcfdbb5..2beeabf502c5 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -242,7 +242,7 @@ int walk_page_range(unsigned long addr, unsigned long end,
 		if (err)
 			break;
 		pgd++;
-	} while (addr = next, addr != end);
+	} while (addr = next, addr < end);
 
 	return err;
 }
diff --git a/mm/percpu.c b/mm/percpu.c
index 8c8e08f3a692..0d10defe951e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1706,8 +1706,9 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 
 out_free_areas:
 	for (group = 0; group < ai->nr_groups; group++)
-		free_fn(areas[group],
-			ai->groups[group].nr_units * ai->unit_size);
+		if (areas[group])
+			free_fn(areas[group],
+				ai->groups[group].nr_units * ai->unit_size);
 out_free:
 	pcpu_free_alloc_info(ai);
 	if (areas)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 3929a40bd6c0..a8b919925934 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -110,9 +110,10 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
 		       pte_t *ptep)
 {
+	struct mm_struct *mm = (vma)->vm_mm;
 	pte_t pte;
-	pte = ptep_get_and_clear((vma)->vm_mm, address, ptep);
-	if (pte_accessible(pte))
+	pte = ptep_get_and_clear(mm, address, ptep);
+	if (pte_accessible(mm, pte))
 		flush_tlb_page(vma, address);
 	return pte;
 }
@@ -151,14 +152,14 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pgtable)
 {
-	assert_spin_locked(&mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
 	/* FIFO */
-	if (!mm->pmd_huge_pte)
+	if (!pmd_huge_pte(mm, pmdp))
 		INIT_LIST_HEAD(&pgtable->lru);
 	else
-		list_add(&pgtable->lru, &mm->pmd_huge_pte->lru);
-	mm->pmd_huge_pte = pgtable;
+		list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru);
+	pmd_huge_pte(mm, pmdp) = pgtable;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
@@ -170,14 +171,14 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
 	pgtable_t pgtable;
 
-	assert_spin_locked(&mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
 	/* FIFO */
-	pgtable = mm->pmd_huge_pte;
+	pgtable = pmd_huge_pte(mm, pmdp);
 	if (list_empty(&pgtable->lru))
-		mm->pmd_huge_pte = NULL;
+		pmd_huge_pte(mm, pmdp) = NULL;
 	else {
-		mm->pmd_huge_pte = list_entry(pgtable->lru.next,
+		pmd_huge_pte(mm, pmdp) = list_entry(pgtable->lru.next,
 					      struct page, lru);
 		list_del(&pgtable->lru);
 	}
@@ -191,6 +192,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
+	pmd_t entry = *pmdp;
+	if (pmd_numa(entry))
+		entry = pmd_mknonnuma(entry);
 	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 }
diff --git a/mm/readahead.c b/mm/readahead.c
index e4ed04149785..7cdbb44aa90b 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -401,6 +401,7 @@ ondemand_readahead(struct address_space *mapping,
 		   unsigned long req_size)
 {
 	unsigned long max = max_sane_readahead(ra->ra_pages);
+	pgoff_t prev_offset;
 
 	/*
 	 * start of file
@@ -452,8 +453,11 @@ ondemand_readahead(struct address_space *mapping,
 
 	/*
 	 * sequential cache miss
+	 * trivial case: (offset - prev_offset) == 1
+	 * unaligned reads: (offset - prev_offset) == 0
 	 */
-	if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL)
+	prev_offset = (unsigned long long)ra->prev_pos >> PAGE_CACHE_SHIFT;
+	if (offset - prev_offset <= 1UL)
 		goto initial_readahead;
 
 	/*
@@ -569,7 +573,7 @@ static ssize_t
 do_readahead(struct address_space *mapping, struct file *filp,
 	     pgoff_t index, unsigned long nr)
 {
-	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
+	if (!mapping || !mapping->a_ops)
 		return -EINVAL;
 
 	force_page_cache_readahead(mapping, filp, index, nr);
diff --git a/mm/rmap.c b/mm/rmap.c
index fd3ee7a54a13..068522d8502a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -600,8 +600,12 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 	spinlock_t *ptl;
 
 	if (unlikely(PageHuge(page))) {
+		/* when pud is not present, pte will be NULL */
 		pte = huge_pte_offset(mm, address);
-		ptl = &mm->page_table_lock;
+		if (!pte)
+			return NULL;
+
+		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
 		goto check;
 	}
 
@@ -665,25 +669,23 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			unsigned long *vm_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	int referenced = 0;
 
 	if (unlikely(PageTransHuge(page))) {
 		pmd_t *pmd;
 
-		spin_lock(&mm->page_table_lock);
 		/*
 		 * rmap might return false positives; we must filter
 		 * these out using page_check_address_pmd().
 		 */
 		pmd = page_check_address_pmd(page, mm, address,
-					     PAGE_CHECK_ADDRESS_PMD_FLAG);
-		if (!pmd) {
-			spin_unlock(&mm->page_table_lock);
+					     PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl);
+		if (!pmd)
 			goto out;
-		}
 
 		if (vma->vm_flags & VM_LOCKED) {
-			spin_unlock(&mm->page_table_lock);
+			spin_unlock(ptl);
 			*mapcount = 0;	/* break early from loop */
 			*vm_flags |= VM_LOCKED;
 			goto out;
@@ -692,10 +694,9 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		/* go ahead even if the pmd is pmd_trans_splitting() */
 		if (pmdp_clear_flush_young_notify(vma, address, pmd))
 			referenced++;
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 	} else {
 		pte_t *pte;
-		spinlock_t *ptl;
 
 		/*
 		 * rmap might return false positives; we must filter
diff --git a/mm/shmem.c b/mm/shmem.c
index 8297623fcaed..902a14842b74 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2918,13 +2918,8 @@ static struct dentry_operations anon_ops = {
 	.d_dname = simple_dname
 };
 
-/**
- * shmem_file_setup - get an unlinked file living in tmpfs
- * @name: name for dentry (to be seen in /proc/<pid>/maps
- * @size: size to be set for the file
- * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
- */
-struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
+static struct file *__shmem_file_setup(const char *name, loff_t size,
+				       unsigned long flags, unsigned int i_flags)
 {
 	struct file *res;
 	struct inode *inode;
@@ -2957,6 +2952,7 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags
 	if (!inode)
 		goto put_dentry;
 
+	inode->i_flags |= i_flags;
 	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
 	clear_nlink(inode);	/* It is unlinked */
@@ -2977,6 +2973,32 @@ put_memory:
 	shmem_unacct_size(flags, size);
 	return res;
 }
+
+/**
+ * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be
+ * 	kernel internal.  There will be NO LSM permission checks against the
+ * 	underlying inode.  So users of this interface must do LSM checks at a
+ * 	higher layer.  The one user is the big_key implementation.  LSM checks
+ * 	are provided at the key level rather than the inode level.
+ * @name: name for dentry (to be seen in /proc/<pid>/maps
+ * @size: size to be set for the file
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
+ */
+struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags)
+{
+	return __shmem_file_setup(name, size, flags, S_PRIVATE);
+}
+
+/**
+ * shmem_file_setup - get an unlinked file living in tmpfs
+ * @name: name for dentry (to be seen in /proc/<pid>/maps
+ * @size: size to be set for the file
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
+ */
+struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
+{
+	return __shmem_file_setup(name, size, flags, 0);
+}
 EXPORT_SYMBOL_GPL(shmem_file_setup);
 
 /**
diff --git a/mm/slab.c b/mm/slab.c
index 2580db062df9..eb043bf05f4c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -164,72 +164,6 @@
 static bool pfmemalloc_active __read_mostly;
 
 /*
- * kmem_bufctl_t:
- *
- * Bufctl's are used for linking objs within a slab
- * linked offsets.
- *
- * This implementation relies on "struct page" for locating the cache &
- * slab an object belongs to.
- * This allows the bufctl structure to be small (one int), but limits
- * the number of objects a slab (not a cache) can contain when off-slab
- * bufctls are used. The limit is the size of the largest general cache
- * that does not use off-slab slabs.
- * For 32bit archs with 4 kB pages, is this 56.
- * This is not serious, as it is only for large objects, when it is unwise
- * to have too many per slab.
- * Note: This limit can be raised by introducing a general cache whose size
- * is less than 512 (PAGE_SIZE<<3), but greater than 256.
- */
-
-typedef unsigned int kmem_bufctl_t;
-#define BUFCTL_END	(((kmem_bufctl_t)(~0U))-0)
-#define BUFCTL_FREE	(((kmem_bufctl_t)(~0U))-1)
-#define	BUFCTL_ACTIVE	(((kmem_bufctl_t)(~0U))-2)
-#define	SLAB_LIMIT	(((kmem_bufctl_t)(~0U))-3)
-
-/*
- * struct slab_rcu
- *
- * slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to
- * arrange for kmem_freepages to be called via RCU.  This is useful if
- * we need to approach a kernel structure obliquely, from its address
- * obtained without the usual locking.  We can lock the structure to
- * stabilize it and check it's still at the given address, only if we
- * can be sure that the memory has not been meanwhile reused for some
- * other kind of object (which our subsystem's lock might corrupt).
- *
- * rcu_read_lock before reading the address, then rcu_read_unlock after
- * taking the spinlock within the structure expected at that address.
- */
-struct slab_rcu {
-	struct rcu_head head;
-	struct kmem_cache *cachep;
-	void *addr;
-};
-
-/*
- * struct slab
- *
- * Manages the objs in a slab. Placed either at the beginning of mem allocated
- * for a slab, or allocated from an general cache.
- * Slabs are chained into three list: fully used, partial, fully free slabs.
- */
-struct slab {
-	union {
-		struct {
-			struct list_head list;
-			unsigned long colouroff;
-			void *s_mem;		/* including colour offset */
-			unsigned int inuse;	/* num of objs active in slab */
-			kmem_bufctl_t free;
-			unsigned short nodeid;
-		};
-		struct slab_rcu __slab_cover_slab_rcu;
-	};
-};
-
-/*
  * struct array_cache
  *
  * Purpose:
@@ -456,18 +390,10 @@ static inline struct kmem_cache *virt_to_cache(const void *obj)
 	return page->slab_cache;
 }
 
-static inline struct slab *virt_to_slab(const void *obj)
-{
-	struct page *page = virt_to_head_page(obj);
-
-	VM_BUG_ON(!PageSlab(page));
-	return page->slab_page;
-}
-
-static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab,
+static inline void *index_to_obj(struct kmem_cache *cache, struct page *page,
 				 unsigned int idx)
 {
-	return slab->s_mem + cache->size * idx;
+	return page->s_mem + cache->size * idx;
 }
 
 /*
@@ -477,9 +403,9 @@ static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab,
  *   reciprocal_divide(offset, cache->reciprocal_buffer_size)
  */
 static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
+					const struct page *page, void *obj)
 {
-	u32 offset = (obj - slab->s_mem);
+	u32 offset = (obj - page->s_mem);
 	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
 }
 
@@ -641,7 +567,7 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 
 static size_t slab_mgmt_size(size_t nr_objs, size_t align)
 {
-	return ALIGN(sizeof(struct slab)+nr_objs*sizeof(kmem_bufctl_t), align);
+	return ALIGN(nr_objs * sizeof(unsigned int), align);
 }
 
 /*
@@ -660,8 +586,7 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 	 * on it. For the latter case, the memory allocated for a
 	 * slab is used for:
 	 *
-	 * - The struct slab
-	 * - One kmem_bufctl_t for each object
+	 * - One unsigned int for each object
 	 * - Padding to respect alignment of @align
 	 * - @buffer_size bytes for each object
 	 *
@@ -674,8 +599,6 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 		mgmt_size = 0;
 		nr_objs = slab_size / buffer_size;
 
-		if (nr_objs > SLAB_LIMIT)
-			nr_objs = SLAB_LIMIT;
 	} else {
 		/*
 		 * Ignore padding for the initial guess. The padding
@@ -685,8 +608,7 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 		 * into the memory allocation when taking the padding
 		 * into account.
 		 */
-		nr_objs = (slab_size - sizeof(struct slab)) /
-			  (buffer_size + sizeof(kmem_bufctl_t));
+		nr_objs = (slab_size) / (buffer_size + sizeof(unsigned int));
 
 		/*
 		 * This calculated number will be either the right
@@ -696,9 +618,6 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 		       > slab_size)
 			nr_objs--;
 
-		if (nr_objs > SLAB_LIMIT)
-			nr_objs = SLAB_LIMIT;
-
 		mgmt_size = slab_mgmt_size(nr_objs, align);
 	}
 	*num = nr_objs;
@@ -829,10 +748,8 @@ static struct array_cache *alloc_arraycache(int node, int entries,
 	return nc;
 }
 
-static inline bool is_slab_pfmemalloc(struct slab *slabp)
+static inline bool is_slab_pfmemalloc(struct page *page)
 {
-	struct page *page = virt_to_page(slabp->s_mem);
-
 	return PageSlabPfmemalloc(page);
 }
 
@@ -841,23 +758,23 @@ static void recheck_pfmemalloc_active(struct kmem_cache *cachep,
 						struct array_cache *ac)
 {
 	struct kmem_cache_node *n = cachep->node[numa_mem_id()];
-	struct slab *slabp;
+	struct page *page;
 	unsigned long flags;
 
 	if (!pfmemalloc_active)
 		return;
 
 	spin_lock_irqsave(&n->list_lock, flags);
-	list_for_each_entry(slabp, &n->slabs_full, list)
-		if (is_slab_pfmemalloc(slabp))
+	list_for_each_entry(page, &n->slabs_full, lru)
+		if (is_slab_pfmemalloc(page))
 			goto out;
 
-	list_for_each_entry(slabp, &n->slabs_partial, list)
-		if (is_slab_pfmemalloc(slabp))
+	list_for_each_entry(page, &n->slabs_partial, lru)
+		if (is_slab_pfmemalloc(page))
 			goto out;
 
-	list_for_each_entry(slabp, &n->slabs_free, list)
-		if (is_slab_pfmemalloc(slabp))
+	list_for_each_entry(page, &n->slabs_free, lru)
+		if (is_slab_pfmemalloc(page))
 			goto out;
 
 	pfmemalloc_active = false;
@@ -897,8 +814,8 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
 		 */
 		n = cachep->node[numa_mem_id()];
 		if (!list_empty(&n->slabs_free) && force_refill) {
-			struct slab *slabp = virt_to_slab(objp);
-			ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem));
+			struct page *page = virt_to_head_page(objp);
+			ClearPageSlabPfmemalloc(page);
 			clear_obj_pfmemalloc(&objp);
 			recheck_pfmemalloc_active(cachep, ac);
 			return objp;
@@ -1099,8 +1016,7 @@ static void drain_alien_cache(struct kmem_cache *cachep,
 
 static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
 {
-	struct slab *slabp = virt_to_slab(objp);
-	int nodeid = slabp->nodeid;
+	int nodeid = page_to_nid(virt_to_page(objp));
 	struct kmem_cache_node *n;
 	struct array_cache *alien = NULL;
 	int node;
@@ -1111,7 +1027,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
 	 * Make sure we are not freeing a object from another node to the array
 	 * cache on this cpu.
 	 */
-	if (likely(slabp->nodeid == node))
+	if (likely(nodeid == node))
 		return 0;
 
 	n = cachep->node[node];
@@ -1512,6 +1428,8 @@ void __init kmem_cache_init(void)
 {
 	int i;
 
+	BUILD_BUG_ON(sizeof(((struct page *)NULL)->lru) <
+					sizeof(struct rcu_head));
 	kmem_cache = &kmem_cache_boot;
 	setup_node_pointer(kmem_cache);
 
@@ -1687,7 +1605,7 @@ static noinline void
 slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
 {
 	struct kmem_cache_node *n;
-	struct slab *slabp;
+	struct page *page;
 	unsigned long flags;
 	int node;
 
@@ -1706,15 +1624,15 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
 			continue;
 
 		spin_lock_irqsave(&n->list_lock, flags);
-		list_for_each_entry(slabp, &n->slabs_full, list) {
+		list_for_each_entry(page, &n->slabs_full, lru) {
 			active_objs += cachep->num;
 			active_slabs++;
 		}
-		list_for_each_entry(slabp, &n->slabs_partial, list) {
-			active_objs += slabp->inuse;
+		list_for_each_entry(page, &n->slabs_partial, lru) {
+			active_objs += page->active;
 			active_slabs++;
 		}
-		list_for_each_entry(slabp, &n->slabs_free, list)
+		list_for_each_entry(page, &n->slabs_free, lru)
 			num_slabs++;
 
 		free_objects += n->free_objects;
@@ -1736,19 +1654,11 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
  * did not request dmaable memory, we might get it, but that
  * would be relatively rare and ignorable.
  */
-static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
+								int nodeid)
 {
 	struct page *page;
 	int nr_pages;
-	int i;
-
-#ifndef CONFIG_MMU
-	/*
-	 * Nommu uses slab's for process anonymous memory allocations, and thus
-	 * requires __GFP_COMP to properly refcount higher order allocations
-	 */
-	flags |= __GFP_COMP;
-#endif
 
 	flags |= cachep->allocflags;
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
@@ -1772,12 +1682,9 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	else
 		add_zone_page_state(page_zone(page),
 			NR_SLAB_UNRECLAIMABLE, nr_pages);
-	for (i = 0; i < nr_pages; i++) {
-		__SetPageSlab(page + i);
-
-		if (page->pfmemalloc)
-			SetPageSlabPfmemalloc(page + i);
-	}
+	__SetPageSlab(page);
+	if (page->pfmemalloc)
+		SetPageSlabPfmemalloc(page);
 	memcg_bind_pages(cachep, cachep->gfporder);
 
 	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
@@ -1789,17 +1696,15 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 			kmemcheck_mark_unallocated_pages(page, nr_pages);
 	}
 
-	return page_address(page);
+	return page;
 }
 
 /*
  * Interface to system's page release.
  */
-static void kmem_freepages(struct kmem_cache *cachep, void *addr)
+static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
 {
-	unsigned long i = (1 << cachep->gfporder);
-	struct page *page = virt_to_page(addr);
-	const unsigned long nr_freed = i;
+	const unsigned long nr_freed = (1 << cachep->gfporder);
 
 	kmemcheck_free_shadow(page, cachep->gfporder);
 
@@ -1809,27 +1714,28 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 	else
 		sub_zone_page_state(page_zone(page),
 				NR_SLAB_UNRECLAIMABLE, nr_freed);
-	while (i--) {
-		BUG_ON(!PageSlab(page));
-		__ClearPageSlabPfmemalloc(page);
-		__ClearPageSlab(page);
-		page++;
-	}
+
+	BUG_ON(!PageSlab(page));
+	__ClearPageSlabPfmemalloc(page);
+	__ClearPageSlab(page);
+	page_mapcount_reset(page);
+	page->mapping = NULL;
 
 	memcg_release_pages(cachep, cachep->gfporder);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += nr_freed;
-	free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder);
+	__free_memcg_kmem_pages(page, cachep->gfporder);
 }
 
 static void kmem_rcu_free(struct rcu_head *head)
 {
-	struct slab_rcu *slab_rcu = (struct slab_rcu *)head;
-	struct kmem_cache *cachep = slab_rcu->cachep;
+	struct kmem_cache *cachep;
+	struct page *page;
 
-	kmem_freepages(cachep, slab_rcu->addr);
-	if (OFF_SLAB(cachep))
-		kmem_cache_free(cachep->slabp_cache, slab_rcu);
+	page = container_of(head, struct page, rcu_head);
+	cachep = page->slab_cache;
+
+	kmem_freepages(cachep, page);
 }
 
 #if DEBUG
@@ -1978,19 +1884,19 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 		/* Print some data about the neighboring objects, if they
 		 * exist:
 		 */
-		struct slab *slabp = virt_to_slab(objp);
+		struct page *page = virt_to_head_page(objp);
 		unsigned int objnr;
 
-		objnr = obj_to_index(cachep, slabp, objp);
+		objnr = obj_to_index(cachep, page, objp);
 		if (objnr) {
-			objp = index_to_obj(cachep, slabp, objnr - 1);
+			objp = index_to_obj(cachep, page, objnr - 1);
 			realobj = (char *)objp + obj_offset(cachep);
 			printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
 			       realobj, size);
 			print_objinfo(cachep, objp, 2);
 		}
 		if (objnr + 1 < cachep->num) {
-			objp = index_to_obj(cachep, slabp, objnr + 1);
+			objp = index_to_obj(cachep, page, objnr + 1);
 			realobj = (char *)objp + obj_offset(cachep);
 			printk(KERN_ERR "Next obj: start=%p, len=%d\n",
 			       realobj, size);
@@ -2001,11 +1907,12 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 #endif
 
 #if DEBUG
-static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy_debugcheck(struct kmem_cache *cachep,
+						struct page *page)
 {
 	int i;
 	for (i = 0; i < cachep->num; i++) {
-		void *objp = index_to_obj(cachep, slabp, i);
+		void *objp = index_to_obj(cachep, page, i);
 
 		if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -2030,7 +1937,8 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab
 	}
 }
 #else
-static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy_debugcheck(struct kmem_cache *cachep,
+						struct page *page)
 {
 }
 #endif
@@ -2044,23 +1952,34 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab
  * Before calling the slab must have been unlinked from the cache.  The
  * cache-lock is not held/needed.
  */
-static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy(struct kmem_cache *cachep, struct page *page)
 {
-	void *addr = slabp->s_mem - slabp->colouroff;
+	void *freelist;
 
-	slab_destroy_debugcheck(cachep, slabp);
+	freelist = page->freelist;
+	slab_destroy_debugcheck(cachep, page);
 	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
-		struct slab_rcu *slab_rcu;
+		struct rcu_head *head;
+
+		/*
+		 * RCU free overloads the RCU head over the LRU.
+		 * slab_page has been overloeaded over the LRU,
+		 * however it is not used from now on so that
+		 * we can use it safely.
+		 */
+		head = (void *)&page->rcu_head;
+		call_rcu(head, kmem_rcu_free);
 
-		slab_rcu = (struct slab_rcu *)slabp;
-		slab_rcu->cachep = cachep;
-		slab_rcu->addr = addr;
-		call_rcu(&slab_rcu->head, kmem_rcu_free);
 	} else {
-		kmem_freepages(cachep, addr);
-		if (OFF_SLAB(cachep))
-			kmem_cache_free(cachep->slabp_cache, slabp);
+		kmem_freepages(cachep, page);
 	}
+
+	/*
+	 * From now on, we don't use freelist
+	 * although actual page can be freed in rcu context
+	 */
+	if (OFF_SLAB(cachep))
+		kmem_cache_free(cachep->freelist_cache, freelist);
 }
 
 /**
@@ -2097,8 +2016,8 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 			 * use off-slab slabs. Needed to avoid a possible
 			 * looping condition in cache_grow().
 			 */
-			offslab_limit = size - sizeof(struct slab);
-			offslab_limit /= sizeof(kmem_bufctl_t);
+			offslab_limit = size;
+			offslab_limit /= sizeof(unsigned int);
 
  			if (num > offslab_limit)
 				break;
@@ -2220,7 +2139,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 int
 __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 {
-	size_t left_over, slab_size, ralign;
+	size_t left_over, freelist_size, ralign;
 	gfp_t gfp;
 	int err;
 	size_t size = cachep->size;
@@ -2339,22 +2258,21 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	if (!cachep->num)
 		return -E2BIG;
 
-	slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t)
-			  + sizeof(struct slab), cachep->align);
+	freelist_size =
+		ALIGN(cachep->num * sizeof(unsigned int), cachep->align);
 
 	/*
 	 * If the slab has been placed off-slab, and we have enough space then
 	 * move it on-slab. This is at the expense of any extra colouring.
 	 */
-	if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) {
+	if (flags & CFLGS_OFF_SLAB && left_over >= freelist_size) {
 		flags &= ~CFLGS_OFF_SLAB;
-		left_over -= slab_size;
+		left_over -= freelist_size;
 	}
 
 	if (flags & CFLGS_OFF_SLAB) {
 		/* really off slab. No need for manual alignment */
-		slab_size =
-		    cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab);
+		freelist_size = cachep->num * sizeof(unsigned int);
 
 #ifdef CONFIG_PAGE_POISONING
 		/* If we're going to use the generic kernel_map_pages()
@@ -2371,16 +2289,16 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	if (cachep->colour_off < cachep->align)
 		cachep->colour_off = cachep->align;
 	cachep->colour = left_over / cachep->colour_off;
-	cachep->slab_size = slab_size;
+	cachep->freelist_size = freelist_size;
 	cachep->flags = flags;
-	cachep->allocflags = 0;
+	cachep->allocflags = __GFP_COMP;
 	if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
 		cachep->allocflags |= GFP_DMA;
 	cachep->size = size;
 	cachep->reciprocal_buffer_size = reciprocal_value(size);
 
 	if (flags & CFLGS_OFF_SLAB) {
-		cachep->slabp_cache = kmalloc_slab(slab_size, 0u);
+		cachep->freelist_cache = kmalloc_slab(freelist_size, 0u);
 		/*
 		 * This is a possibility for one of the malloc_sizes caches.
 		 * But since we go off slab only for object size greater than
@@ -2388,7 +2306,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 		 * this should not happen at all.
 		 * But leave a BUG_ON for some lucky dude.
 		 */
-		BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache));
+		BUG_ON(ZERO_OR_NULL_PTR(cachep->freelist_cache));
 	}
 
 	err = setup_cpu_cache(cachep, gfp);
@@ -2494,7 +2412,7 @@ static int drain_freelist(struct kmem_cache *cache,
 {
 	struct list_head *p;
 	int nr_freed;
-	struct slab *slabp;
+	struct page *page;
 
 	nr_freed = 0;
 	while (nr_freed < tofree && !list_empty(&n->slabs_free)) {
@@ -2506,18 +2424,18 @@ static int drain_freelist(struct kmem_cache *cache,
 			goto out;
 		}
 
-		slabp = list_entry(p, struct slab, list);
+		page = list_entry(p, struct page, lru);
 #if DEBUG
-		BUG_ON(slabp->inuse);
+		BUG_ON(page->active);
 #endif
-		list_del(&slabp->list);
+		list_del(&page->lru);
 		/*
 		 * Safe to drop the lock. The slab is no longer linked
 		 * to the cache.
 		 */
 		n->free_objects -= cache->num;
 		spin_unlock_irq(&n->list_lock);
-		slab_destroy(cache, slabp);
+		slab_destroy(cache, page);
 		nr_freed++;
 	}
 out:
@@ -2600,52 +2518,42 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
  * descriptors in kmem_cache_create, we search through the malloc_sizes array.
  * If we are creating a malloc_sizes cache here it would not be visible to
  * kmem_find_general_cachep till the initialization is complete.
- * Hence we cannot have slabp_cache same as the original cache.
+ * Hence we cannot have freelist_cache same as the original cache.
  */
-static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
-				   int colour_off, gfp_t local_flags,
-				   int nodeid)
+static void *alloc_slabmgmt(struct kmem_cache *cachep,
+				   struct page *page, int colour_off,
+				   gfp_t local_flags, int nodeid)
 {
-	struct slab *slabp;
+	void *freelist;
+	void *addr = page_address(page);
 
 	if (OFF_SLAB(cachep)) {
 		/* Slab management obj is off-slab. */
-		slabp = kmem_cache_alloc_node(cachep->slabp_cache,
+		freelist = kmem_cache_alloc_node(cachep->freelist_cache,
 					      local_flags, nodeid);
-		/*
-		 * If the first object in the slab is leaked (it's allocated
-		 * but no one has a reference to it), we want to make sure
-		 * kmemleak does not treat the ->s_mem pointer as a reference
-		 * to the object. Otherwise we will not report the leak.
-		 */
-		kmemleak_scan_area(&slabp->list, sizeof(struct list_head),
-				   local_flags);
-		if (!slabp)
+		if (!freelist)
 			return NULL;
 	} else {
-		slabp = objp + colour_off;
-		colour_off += cachep->slab_size;
+		freelist = addr + colour_off;
+		colour_off += cachep->freelist_size;
 	}
-	slabp->inuse = 0;
-	slabp->colouroff = colour_off;
-	slabp->s_mem = objp + colour_off;
-	slabp->nodeid = nodeid;
-	slabp->free = 0;
-	return slabp;
+	page->active = 0;
+	page->s_mem = addr + colour_off;
+	return freelist;
 }
 
-static inline kmem_bufctl_t *slab_bufctl(struct slab *slabp)
+static inline unsigned int *slab_freelist(struct page *page)
 {
-	return (kmem_bufctl_t *) (slabp + 1);
+	return (unsigned int *)(page->freelist);
 }
 
 static void cache_init_objs(struct kmem_cache *cachep,
-			    struct slab *slabp)
+			    struct page *page)
 {
 	int i;
 
 	for (i = 0; i < cachep->num; i++) {
-		void *objp = index_to_obj(cachep, slabp, i);
+		void *objp = index_to_obj(cachep, page, i);
 #if DEBUG
 		/* need to poison the objs? */
 		if (cachep->flags & SLAB_POISON)
@@ -2681,9 +2589,8 @@ static void cache_init_objs(struct kmem_cache *cachep,
 		if (cachep->ctor)
 			cachep->ctor(objp);
 #endif
-		slab_bufctl(slabp)[i] = i + 1;
+		slab_freelist(page)[i] = i;
 	}
-	slab_bufctl(slabp)[i - 1] = BUFCTL_END;
 }
 
 static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
@@ -2696,41 +2603,41 @@ static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
 	}
 }
 
-static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp,
+static void *slab_get_obj(struct kmem_cache *cachep, struct page *page,
 				int nodeid)
 {
-	void *objp = index_to_obj(cachep, slabp, slabp->free);
-	kmem_bufctl_t next;
+	void *objp;
 
-	slabp->inuse++;
-	next = slab_bufctl(slabp)[slabp->free];
+	objp = index_to_obj(cachep, page, slab_freelist(page)[page->active]);
+	page->active++;
 #if DEBUG
-	slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE;
-	WARN_ON(slabp->nodeid != nodeid);
+	WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
 #endif
-	slabp->free = next;
 
 	return objp;
 }
 
-static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp,
+static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
 				void *objp, int nodeid)
 {
-	unsigned int objnr = obj_to_index(cachep, slabp, objp);
-
+	unsigned int objnr = obj_to_index(cachep, page, objp);
 #if DEBUG
+	unsigned int i;
+
 	/* Verify that the slab belongs to the intended node */
-	WARN_ON(slabp->nodeid != nodeid);
+	WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
 
-	if (slab_bufctl(slabp)[objnr] + 1 <= SLAB_LIMIT + 1) {
-		printk(KERN_ERR "slab: double free detected in cache "
-				"'%s', objp %p\n", cachep->name, objp);
-		BUG();
+	/* Verify double free bug */
+	for (i = page->active; i < cachep->num; i++) {
+		if (slab_freelist(page)[i] == objnr) {
+			printk(KERN_ERR "slab: double free detected in cache "
+					"'%s', objp %p\n", cachep->name, objp);
+			BUG();
+		}
 	}
 #endif
-	slab_bufctl(slabp)[objnr] = slabp->free;
-	slabp->free = objnr;
-	slabp->inuse--;
+	page->active--;
+	slab_freelist(page)[page->active] = objnr;
 }
 
 /*
@@ -2738,23 +2645,11 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp,
  * for the slab allocator to be able to lookup the cache and slab of a
  * virtual address for kfree, ksize, and slab debugging.
  */
-static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
-			   void *addr)
+static void slab_map_pages(struct kmem_cache *cache, struct page *page,
+			   void *freelist)
 {
-	int nr_pages;
-	struct page *page;
-
-	page = virt_to_page(addr);
-
-	nr_pages = 1;
-	if (likely(!PageCompound(page)))
-		nr_pages <<= cache->gfporder;
-
-	do {
-		page->slab_cache = cache;
-		page->slab_page = slab;
-		page++;
-	} while (--nr_pages);
+	page->slab_cache = cache;
+	page->freelist = freelist;
 }
 
 /*
@@ -2762,9 +2657,9 @@ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
  * kmem_cache_alloc() when there are no active objs left in a cache.
  */
 static int cache_grow(struct kmem_cache *cachep,
-		gfp_t flags, int nodeid, void *objp)
+		gfp_t flags, int nodeid, struct page *page)
 {
-	struct slab *slabp;
+	void *freelist;
 	size_t offset;
 	gfp_t local_flags;
 	struct kmem_cache_node *n;
@@ -2805,20 +2700,20 @@ static int cache_grow(struct kmem_cache *cachep,
 	 * Get mem for the objs.  Attempt to allocate a physical page from
 	 * 'nodeid'.
 	 */
-	if (!objp)
-		objp = kmem_getpages(cachep, local_flags, nodeid);
-	if (!objp)
+	if (!page)
+		page = kmem_getpages(cachep, local_flags, nodeid);
+	if (!page)
 		goto failed;
 
 	/* Get slab management. */
-	slabp = alloc_slabmgmt(cachep, objp, offset,
+	freelist = alloc_slabmgmt(cachep, page, offset,
 			local_flags & ~GFP_CONSTRAINT_MASK, nodeid);
-	if (!slabp)
+	if (!freelist)
 		goto opps1;
 
-	slab_map_pages(cachep, slabp, objp);
+	slab_map_pages(cachep, page, freelist);
 
-	cache_init_objs(cachep, slabp);
+	cache_init_objs(cachep, page);
 
 	if (local_flags & __GFP_WAIT)
 		local_irq_disable();
@@ -2826,13 +2721,13 @@ static int cache_grow(struct kmem_cache *cachep,
 	spin_lock(&n->list_lock);
 
 	/* Make slab active. */
-	list_add_tail(&slabp->list, &(n->slabs_free));
+	list_add_tail(&page->lru, &(n->slabs_free));
 	STATS_INC_GROWN(cachep);
 	n->free_objects += cachep->num;
 	spin_unlock(&n->list_lock);
 	return 1;
 opps1:
-	kmem_freepages(cachep, objp);
+	kmem_freepages(cachep, page);
 failed:
 	if (local_flags & __GFP_WAIT)
 		local_irq_disable();
@@ -2880,9 +2775,8 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
 static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 				   unsigned long caller)
 {
-	struct page *page;
 	unsigned int objnr;
-	struct slab *slabp;
+	struct page *page;
 
 	BUG_ON(virt_to_cache(objp) != cachep);
 
@@ -2890,8 +2784,6 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	kfree_debugcheck(objp);
 	page = virt_to_head_page(objp);
 
-	slabp = page->slab_page;
-
 	if (cachep->flags & SLAB_RED_ZONE) {
 		verify_redzone_free(cachep, objp);
 		*dbg_redzone1(cachep, objp) = RED_INACTIVE;
@@ -2900,14 +2792,11 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	if (cachep->flags & SLAB_STORE_USER)
 		*dbg_userword(cachep, objp) = (void *)caller;
 
-	objnr = obj_to_index(cachep, slabp, objp);
+	objnr = obj_to_index(cachep, page, objp);
 
 	BUG_ON(objnr >= cachep->num);
-	BUG_ON(objp != index_to_obj(cachep, slabp, objnr));
+	BUG_ON(objp != index_to_obj(cachep, page, objnr));
 
-#ifdef CONFIG_DEBUG_SLAB_LEAK
-	slab_bufctl(slabp)[objnr] = BUFCTL_FREE;
-#endif
 	if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
 		if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
@@ -2924,33 +2813,9 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	return objp;
 }
 
-static void check_slabp(struct kmem_cache *cachep, struct slab *slabp)
-{
-	kmem_bufctl_t i;
-	int entries = 0;
-
-	/* Check slab's freelist to see if this obj is there. */
-	for (i = slabp->free; i != BUFCTL_END; i = slab_bufctl(slabp)[i]) {
-		entries++;
-		if (entries > cachep->num || i >= cachep->num)
-			goto bad;
-	}
-	if (entries != cachep->num - slabp->inuse) {
-bad:
-		printk(KERN_ERR "slab: Internal list corruption detected in "
-			"cache '%s'(%d), slabp %p(%d). Tainted(%s). Hexdump:\n",
-			cachep->name, cachep->num, slabp, slabp->inuse,
-			print_tainted());
-		print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, slabp,
-			sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t),
-			1);
-		BUG();
-	}
-}
 #else
 #define kfree_debugcheck(x) do { } while(0)
 #define cache_free_debugcheck(x,objp,z) (objp)
-#define check_slabp(x,y) do { } while(0)
 #endif
 
 static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
@@ -2989,7 +2854,7 @@ retry:
 
 	while (batchcount > 0) {
 		struct list_head *entry;
-		struct slab *slabp;
+		struct page *page;
 		/* Get slab alloc is to come from. */
 		entry = n->slabs_partial.next;
 		if (entry == &n->slabs_partial) {
@@ -2999,8 +2864,7 @@ retry:
 				goto must_grow;
 		}
 
-		slabp = list_entry(entry, struct slab, list);
-		check_slabp(cachep, slabp);
+		page = list_entry(entry, struct page, lru);
 		check_spinlock_acquired(cachep);
 
 		/*
@@ -3008,24 +2872,23 @@ retry:
 		 * there must be at least one object available for
 		 * allocation.
 		 */
-		BUG_ON(slabp->inuse >= cachep->num);
+		BUG_ON(page->active >= cachep->num);
 
-		while (slabp->inuse < cachep->num && batchcount--) {
+		while (page->active < cachep->num && batchcount--) {
 			STATS_INC_ALLOCED(cachep);
 			STATS_INC_ACTIVE(cachep);
 			STATS_SET_HIGH(cachep);
 
-			ac_put_obj(cachep, ac, slab_get_obj(cachep, slabp,
+			ac_put_obj(cachep, ac, slab_get_obj(cachep, page,
 									node));
 		}
-		check_slabp(cachep, slabp);
 
 		/* move slabp to correct slabp list: */
-		list_del(&slabp->list);
-		if (slabp->free == BUFCTL_END)
-			list_add(&slabp->list, &n->slabs_full);
+		list_del(&page->lru);
+		if (page->active == cachep->num)
+			list_add(&page->list, &n->slabs_full);
 		else
-			list_add(&slabp->list, &n->slabs_partial);
+			list_add(&page->list, &n->slabs_partial);
 	}
 
 must_grow:
@@ -3097,16 +2960,6 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 		*dbg_redzone1(cachep, objp) = RED_ACTIVE;
 		*dbg_redzone2(cachep, objp) = RED_ACTIVE;
 	}
-#ifdef CONFIG_DEBUG_SLAB_LEAK
-	{
-		struct slab *slabp;
-		unsigned objnr;
-
-		slabp = virt_to_head_page(objp)->slab_page;
-		objnr = (unsigned)(objp - slabp->s_mem) / cachep->size;
-		slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE;
-	}
-#endif
 	objp += obj_offset(cachep);
 	if (cachep->ctor && cachep->flags & SLAB_POISON)
 		cachep->ctor(objp);
@@ -3248,18 +3101,20 @@ retry:
 		 * We may trigger various forms of reclaim on the allowed
 		 * set and go into memory reserves if necessary.
 		 */
+		struct page *page;
+
 		if (local_flags & __GFP_WAIT)
 			local_irq_enable();
 		kmem_flagcheck(cache, flags);
-		obj = kmem_getpages(cache, local_flags, numa_mem_id());
+		page = kmem_getpages(cache, local_flags, numa_mem_id());
 		if (local_flags & __GFP_WAIT)
 			local_irq_disable();
-		if (obj) {
+		if (page) {
 			/*
 			 * Insert into the appropriate per node queues
 			 */
-			nid = page_to_nid(virt_to_page(obj));
-			if (cache_grow(cache, flags, nid, obj)) {
+			nid = page_to_nid(page);
+			if (cache_grow(cache, flags, nid, page)) {
 				obj = ____cache_alloc_node(cache,
 					flags | GFP_THISNODE, nid);
 				if (!obj)
@@ -3288,7 +3143,7 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
 				int nodeid)
 {
 	struct list_head *entry;
-	struct slab *slabp;
+	struct page *page;
 	struct kmem_cache_node *n;
 	void *obj;
 	int x;
@@ -3308,26 +3163,24 @@ retry:
 			goto must_grow;
 	}
 
-	slabp = list_entry(entry, struct slab, list);
+	page = list_entry(entry, struct page, lru);
 	check_spinlock_acquired_node(cachep, nodeid);
-	check_slabp(cachep, slabp);
 
 	STATS_INC_NODEALLOCS(cachep);
 	STATS_INC_ACTIVE(cachep);
 	STATS_SET_HIGH(cachep);
 
-	BUG_ON(slabp->inuse == cachep->num);
+	BUG_ON(page->active == cachep->num);
 
-	obj = slab_get_obj(cachep, slabp, nodeid);
-	check_slabp(cachep, slabp);
+	obj = slab_get_obj(cachep, page, nodeid);
 	n->free_objects--;
 	/* move slabp to correct slabp list: */
-	list_del(&slabp->list);
+	list_del(&page->lru);
 
-	if (slabp->free == BUFCTL_END)
-		list_add(&slabp->list, &n->slabs_full);
+	if (page->active == cachep->num)
+		list_add(&page->lru, &n->slabs_full);
 	else
-		list_add(&slabp->list, &n->slabs_partial);
+		list_add(&page->lru, &n->slabs_partial);
 
 	spin_unlock(&n->list_lock);
 	goto done;
@@ -3477,23 +3330,21 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
 
 	for (i = 0; i < nr_objects; i++) {
 		void *objp;
-		struct slab *slabp;
+		struct page *page;
 
 		clear_obj_pfmemalloc(&objpp[i]);
 		objp = objpp[i];
 
-		slabp = virt_to_slab(objp);
+		page = virt_to_head_page(objp);
 		n = cachep->node[node];
-		list_del(&slabp->list);
+		list_del(&page->lru);
 		check_spinlock_acquired_node(cachep, node);
-		check_slabp(cachep, slabp);
-		slab_put_obj(cachep, slabp, objp, node);
+		slab_put_obj(cachep, page, objp, node);
 		STATS_DEC_ACTIVE(cachep);
 		n->free_objects++;
-		check_slabp(cachep, slabp);
 
 		/* fixup slab chains */
-		if (slabp->inuse == 0) {
+		if (page->active == 0) {
 			if (n->free_objects > n->free_limit) {
 				n->free_objects -= cachep->num;
 				/* No need to drop any previously held
@@ -3502,16 +3353,16 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
 				 * a different cache, refer to comments before
 				 * alloc_slabmgmt.
 				 */
-				slab_destroy(cachep, slabp);
+				slab_destroy(cachep, page);
 			} else {
-				list_add(&slabp->list, &n->slabs_free);
+				list_add(&page->lru, &n->slabs_free);
 			}
 		} else {
 			/* Unconditionally move a slab to the end of the
 			 * partial list on free - maximum time for the
 			 * other objects to be freed, too.
 			 */
-			list_add_tail(&slabp->list, &n->slabs_partial);
+			list_add_tail(&page->lru, &n->slabs_partial);
 		}
 	}
 }
@@ -3551,10 +3402,10 @@ free_done:
 
 		p = n->slabs_free.next;
 		while (p != &(n->slabs_free)) {
-			struct slab *slabp;
+			struct page *page;
 
-			slabp = list_entry(p, struct slab, list);
-			BUG_ON(slabp->inuse);
+			page = list_entry(p, struct page, lru);
+			BUG_ON(page->active);
 
 			i++;
 			p = p->next;
@@ -3982,7 +3833,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 
 	VM_BUG_ON(!mutex_is_locked(&slab_mutex));
 	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg(cachep, i);
+		c = cache_from_memcg_idx(cachep, i);
 		if (c)
 			/* return value determined by the parent cache only */
 			__do_tune_cpucache(c, limit, batchcount, shared, gfp);
@@ -4158,7 +4009,7 @@ out:
 #ifdef CONFIG_SLABINFO
 void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 {
-	struct slab *slabp;
+	struct page *page;
 	unsigned long active_objs;
 	unsigned long num_objs;
 	unsigned long active_slabs = 0;
@@ -4178,23 +4029,23 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 		check_irq_on();
 		spin_lock_irq(&n->list_lock);
 
-		list_for_each_entry(slabp, &n->slabs_full, list) {
-			if (slabp->inuse != cachep->num && !error)
+		list_for_each_entry(page, &n->slabs_full, lru) {
+			if (page->active != cachep->num && !error)
 				error = "slabs_full accounting error";
 			active_objs += cachep->num;
 			active_slabs++;
 		}
-		list_for_each_entry(slabp, &n->slabs_partial, list) {
-			if (slabp->inuse == cachep->num && !error)
-				error = "slabs_partial inuse accounting error";
-			if (!slabp->inuse && !error)
-				error = "slabs_partial/inuse accounting error";
-			active_objs += slabp->inuse;
+		list_for_each_entry(page, &n->slabs_partial, lru) {
+			if (page->active == cachep->num && !error)
+				error = "slabs_partial accounting error";
+			if (!page->active && !error)
+				error = "slabs_partial accounting error";
+			active_objs += page->active;
 			active_slabs++;
 		}
-		list_for_each_entry(slabp, &n->slabs_free, list) {
-			if (slabp->inuse && !error)
-				error = "slabs_free/inuse accounting error";
+		list_for_each_entry(page, &n->slabs_free, lru) {
+			if (page->active && !error)
+				error = "slabs_free accounting error";
 			num_slabs++;
 		}
 		free_objects += n->free_objects;
@@ -4346,15 +4197,27 @@ static inline int add_caller(unsigned long *n, unsigned long v)
 	return 1;
 }
 
-static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s)
+static void handle_slab(unsigned long *n, struct kmem_cache *c,
+						struct page *page)
 {
 	void *p;
-	int i;
+	int i, j;
+
 	if (n[0] == n[1])
 		return;
-	for (i = 0, p = s->s_mem; i < c->num; i++, p += c->size) {
-		if (slab_bufctl(s)[i] != BUFCTL_ACTIVE)
+	for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) {
+		bool active = true;
+
+		for (j = page->active; j < c->num; j++) {
+			/* Skip freed item */
+			if (slab_freelist(page)[j] == i) {
+				active = false;
+				break;
+			}
+		}
+		if (!active)
 			continue;
+
 		if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
 			return;
 	}
@@ -4379,7 +4242,7 @@ static void show_symbol(struct seq_file *m, unsigned long address)
 static int leaks_show(struct seq_file *m, void *p)
 {
 	struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
-	struct slab *slabp;
+	struct page *page;
 	struct kmem_cache_node *n;
 	const char *name;
 	unsigned long *x = m->private;
@@ -4403,10 +4266,10 @@ static int leaks_show(struct seq_file *m, void *p)
 		check_irq_on();
 		spin_lock_irq(&n->list_lock);
 
-		list_for_each_entry(slabp, &n->slabs_full, list)
-			handle_slab(x, cachep, slabp);
-		list_for_each_entry(slabp, &n->slabs_partial, list)
-			handle_slab(x, cachep, slabp);
+		list_for_each_entry(page, &n->slabs_full, lru)
+			handle_slab(x, cachep, page);
+		list_for_each_entry(page, &n->slabs_partial, lru)
+			handle_slab(x, cachep, page);
 		spin_unlock_irq(&n->list_lock);
 	}
 	name = cachep->name;
diff --git a/mm/slab.h b/mm/slab.h
index a535033f7e9a..0859c4241ba1 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -160,7 +160,8 @@ static inline const char *cache_name(struct kmem_cache *s)
 	return s->name;
 }
 
-static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
+static inline struct kmem_cache *
+cache_from_memcg_idx(struct kmem_cache *s, int idx)
 {
 	if (!s->memcg_params)
 		return NULL;
@@ -204,7 +205,8 @@ static inline const char *cache_name(struct kmem_cache *s)
 	return s->name;
 }
 
-static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
+static inline struct kmem_cache *
+cache_from_memcg_idx(struct kmem_cache *s, int idx)
 {
 	return NULL;
 }
diff --git a/mm/slab_common.c b/mm/slab_common.c
index a3443278ce3a..0b7bb399b0e4 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -56,6 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 			continue;
 		}
 
+#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON)
 		/*
 		 * For simplicity, we won't check this in the list of memcg
 		 * caches. We have control over memcg naming, and if there
@@ -69,6 +70,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 			s = NULL;
 			return -EINVAL;
 		}
+#endif
 	}
 
 	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
@@ -569,7 +571,7 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
 		return;
 
 	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg(s, i);
+		c = cache_from_memcg_idx(s, i);
 		if (!c)
 			continue;
 
diff --git a/mm/slub.c b/mm/slub.c
index c3eb3d3ca835..545a170ebf9f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -155,7 +155,7 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
 /*
  * Maximum number of desirable partial slabs.
  * The existence of more partial slabs makes kmem_cache_shrink
- * sort the partial list by the number of objects in the.
+ * sort the partial list by the number of objects in use.
  */
 #define MAX_PARTIAL 10
 
@@ -933,6 +933,16 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
  * Hooks for other subsystems that check memory allocations. In a typical
  * production configuration these hooks all should produce no code at all.
  */
+static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
+{
+	kmemleak_alloc(ptr, size, 1, flags);
+}
+
+static inline void kfree_hook(const void *x)
+{
+	kmemleak_free(x);
+}
+
 static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
 {
 	flags &= gfp_allowed_mask;
@@ -955,7 +965,7 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
 	kmemleak_free_recursive(x, s->flags);
 
 	/*
-	 * Trouble is that we may no longer disable interupts in the fast path
+	 * Trouble is that we may no longer disable interrupts in the fast path
 	 * So in order to make the debug calls that expect irqs to be
 	 * disabled we need to disable interrupts temporarily.
 	 */
@@ -1217,8 +1227,8 @@ static unsigned long kmem_cache_flags(unsigned long object_size,
 	/*
 	 * Enable debugging if selected on the kernel commandline.
 	 */
-	if (slub_debug && (!slub_debug_slabs ||
-		!strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs))))
+	if (slub_debug && (!slub_debug_slabs || (name &&
+		!strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))))
 		flags |= slub_debug;
 
 	return flags;
@@ -1260,13 +1270,30 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node,
 static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
+static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
+{
+	kmemleak_alloc(ptr, size, 1, flags);
+}
+
+static inline void kfree_hook(const void *x)
+{
+	kmemleak_free(x);
+}
+
 static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
 							{ return 0; }
 
 static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
-		void *object) {}
+		void *object)
+{
+	kmemleak_alloc_recursive(object, s->object_size, 1, s->flags,
+		flags & gfp_allowed_mask);
+}
 
-static inline void slab_free_hook(struct kmem_cache *s, void *x) {}
+static inline void slab_free_hook(struct kmem_cache *s, void *x)
+{
+	kmemleak_free_recursive(x, s->flags);
+}
 
 #endif /* CONFIG_SLUB_DEBUG */
 
@@ -2829,8 +2856,8 @@ static struct kmem_cache *kmem_cache_node;
  * slab on the node for this slabcache. There are no concurrent accesses
  * possible.
  *
- * Note that this function only works on the kmalloc_node_cache
- * when allocating for the kmalloc_node_cache. This is used for bootstrapping
+ * Note that this function only works on the kmem_cache_node
+ * when allocating for the kmem_cache_node. This is used for bootstrapping
  * memory on a fresh node that has no slab structures yet.
  */
 static void early_kmem_cache_node_alloc(int node)
@@ -3272,7 +3299,7 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 	if (page)
 		ptr = page_address(page);
 
-	kmemleak_alloc(ptr, size, 1, flags);
+	kmalloc_large_node_hook(ptr, size, flags);
 	return ptr;
 }
 
@@ -3336,7 +3363,7 @@ void kfree(const void *x)
 	page = virt_to_head_page(x);
 	if (unlikely(!PageSlab(page))) {
 		BUG_ON(!PageCompound(page));
-		kmemleak_free(x);
+		kfree_hook(x);
 		__free_memcg_kmem_pages(page, compound_order(page));
 		return;
 	}
@@ -4983,7 +5010,7 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		 * through the descendants with best-effort propagation.
 		 */
 		for_each_memcg_cache_index(i) {
-			struct kmem_cache *c = cache_from_memcg(s, i);
+			struct kmem_cache *c = cache_from_memcg_idx(s, i);
 			if (c)
 				attribute->store(c, buf, len);
 		}
diff --git a/mm/sparse.c b/mm/sparse.c
index 4ac1d7ef548f..8cc7be0e9590 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -590,33 +590,32 @@ void __init sparse_init(void)
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
-						 unsigned long nr_pages)
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
 {
 	/* This will make the necessary allocations eventually. */
 	return sparse_mem_map_populate(pnum, nid);
 }
-static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
+static void __kfree_section_memmap(struct page *memmap)
 {
 	unsigned long start = (unsigned long)memmap;
-	unsigned long end = (unsigned long)(memmap + nr_pages);
+	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
 
 	vmemmap_free(start, end);
 }
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap)
 {
 	unsigned long start = (unsigned long)memmap;
-	unsigned long end = (unsigned long)(memmap + nr_pages);
+	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
 
 	vmemmap_free(start, end);
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 #else
-static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
+static struct page *__kmalloc_section_memmap(void)
 {
 	struct page *page, *ret;
-	unsigned long memmap_size = sizeof(struct page) * nr_pages;
+	unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
 
 	page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
 	if (page)
@@ -634,28 +633,30 @@ got_map_ptr:
 	return ret;
 }
 
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
-						  unsigned long nr_pages)
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
 {
-	return __kmalloc_section_memmap(nr_pages);
+	return __kmalloc_section_memmap();
 }
 
-static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
+static void __kfree_section_memmap(struct page *memmap)
 {
 	if (is_vmalloc_addr(memmap))
 		vfree(memmap);
 	else
 		free_pages((unsigned long)memmap,
-			   get_order(sizeof(struct page) * nr_pages));
+			   get_order(sizeof(struct page) * PAGES_PER_SECTION));
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap)
 {
 	unsigned long maps_section_nr, removing_section_nr, i;
-	unsigned long magic;
+	unsigned long magic, nr_pages;
 	struct page *page = virt_to_page(memmap);
 
+	nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
+		>> PAGE_SHIFT;
+
 	for (i = 0; i < nr_pages; i++, page++) {
 		magic = (unsigned long) page->lru.next;
 
@@ -684,8 +685,7 @@ static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
  * set.  If this is <=0, then that means that the passed-in
  * map was not consumed and must be freed.
  */
-int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
-			   int nr_pages)
+int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
 	struct pglist_data *pgdat = zone->zone_pgdat;
@@ -702,12 +702,12 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 	ret = sparse_index_init(section_nr, pgdat->node_id);
 	if (ret < 0 && ret != -EEXIST)
 		return ret;
-	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages);
+	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id);
 	if (!memmap)
 		return -ENOMEM;
 	usemap = __kmalloc_section_usemap();
 	if (!usemap) {
-		__kfree_section_memmap(memmap, nr_pages);
+		__kfree_section_memmap(memmap);
 		return -ENOMEM;
 	}
 
@@ -719,7 +719,7 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 		goto out;
 	}
 
-	memset(memmap, 0, sizeof(struct page) * nr_pages);
+	memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION);
 
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
 
@@ -729,7 +729,7 @@ out:
 	pgdat_resize_unlock(pgdat, &flags);
 	if (ret <= 0) {
 		kfree(usemap);
-		__kfree_section_memmap(memmap, nr_pages);
+		__kfree_section_memmap(memmap);
 	}
 	return ret;
 }
@@ -759,7 +759,6 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 {
 	struct page *usemap_page;
-	unsigned long nr_pages;
 
 	if (!usemap)
 		return;
@@ -771,7 +770,7 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 	if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
 		kfree(usemap);
 		if (memmap)
-			__kfree_section_memmap(memmap, PAGES_PER_SECTION);
+			__kfree_section_memmap(memmap);
 		return;
 	}
 
@@ -780,12 +779,8 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 	 * on the section which has pgdat at boot time. Just keep it as is now.
 	 */
 
-	if (memmap) {
-		nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
-			>> PAGE_SHIFT;
-
-		free_map_bootmem(memmap, nr_pages);
-	}
+	if (memmap)
+		free_map_bootmem(memmap);
 }
 
 void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
diff --git a/mm/swap.c b/mm/swap.c
index 759c3caf44bd..84b26aaabd03 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -82,19 +82,6 @@ static void __put_compound_page(struct page *page)
 
 static void put_compound_page(struct page *page)
 {
-	/*
-	 * hugetlbfs pages cannot be split from under us.  If this is a
-	 * hugetlbfs page, check refcount on head page and release the page if
-	 * the refcount becomes zero.
-	 */
-	if (PageHuge(page)) {
-		page = compound_head(page);
-		if (put_page_testzero(page))
-			__put_compound_page(page);
-
-		return;
-	}
-
 	if (unlikely(PageTail(page))) {
 		/* __split_huge_page_refcount can run under us */
 		struct page *page_head = compound_trans_head(page);
@@ -111,14 +98,31 @@ static void put_compound_page(struct page *page)
 			 * still hot on arches that do not support
 			 * this_cpu_cmpxchg_double().
 			 */
-			if (PageSlab(page_head)) {
-				if (PageTail(page)) {
+			if (PageSlab(page_head) || PageHeadHuge(page_head)) {
+				if (likely(PageTail(page))) {
+					/*
+					 * __split_huge_page_refcount
+					 * cannot race here.
+					 */
+					VM_BUG_ON(!PageHead(page_head));
+					atomic_dec(&page->_mapcount);
 					if (put_page_testzero(page_head))
 						VM_BUG_ON(1);
-
-					atomic_dec(&page->_mapcount);
-					goto skip_lock_tail;
+					if (put_page_testzero(page_head))
+						__put_compound_page(page_head);
+					return;
 				} else
+					/*
+					 * __split_huge_page_refcount
+					 * run before us, "page" was a
+					 * THP tail. The split
+					 * page_head has been freed
+					 * and reallocated as slab or
+					 * hugetlbfs page of smaller
+					 * order (only possible if
+					 * reallocated as slab on
+					 * x86).
+					 */
 					goto skip_lock;
 			}
 			/*
@@ -132,8 +136,27 @@ static void put_compound_page(struct page *page)
 				/* __split_huge_page_refcount run before us */
 				compound_unlock_irqrestore(page_head, flags);
 skip_lock:
-				if (put_page_testzero(page_head))
-					__put_single_page(page_head);
+				if (put_page_testzero(page_head)) {
+					/*
+					 * The head page may have been
+					 * freed and reallocated as a
+					 * compound page of smaller
+					 * order and then freed again.
+					 * All we know is that it
+					 * cannot have become: a THP
+					 * page, a compound page of
+					 * higher order, a tail page.
+					 * That is because we still
+					 * hold the refcount of the
+					 * split THP tail and
+					 * page_head was the THP head
+					 * before the split.
+					 */
+					if (PageHead(page_head))
+						__put_compound_page(page_head);
+					else
+						__put_single_page(page_head);
+				}
 out_put_single:
 				if (put_page_testzero(page))
 					__put_single_page(page);
@@ -155,7 +178,6 @@ out_put_single:
 			VM_BUG_ON(atomic_read(&page->_count) != 0);
 			compound_unlock_irqrestore(page_head, flags);
 
-skip_lock_tail:
 			if (put_page_testzero(page_head)) {
 				if (PageHead(page_head))
 					__put_compound_page(page_head);
@@ -198,51 +220,52 @@ bool __get_page_tail(struct page *page)
 	 * proper PT lock that already serializes against
 	 * split_huge_page().
 	 */
+	unsigned long flags;
 	bool got = false;
-	struct page *page_head;
-
-	/*
-	 * If this is a hugetlbfs page it cannot be split under us.  Simply
-	 * increment refcount for the head page.
-	 */
-	if (PageHuge(page)) {
-		page_head = compound_head(page);
-		atomic_inc(&page_head->_count);
-		got = true;
-	} else {
-		unsigned long flags;
+	struct page *page_head = compound_trans_head(page);
 
-		page_head = compound_trans_head(page);
-		if (likely(page != page_head &&
-					get_page_unless_zero(page_head))) {
-
-			/* Ref to put_compound_page() comment. */
-			if (PageSlab(page_head)) {
-				if (likely(PageTail(page))) {
-					__get_page_tail_foll(page, false);
-					return true;
-				} else {
-					put_page(page_head);
-					return false;
-				}
-			}
-
-			/*
-			 * page_head wasn't a dangling pointer but it
-			 * may not be a head page anymore by the time
-			 * we obtain the lock. That is ok as long as it
-			 * can't be freed from under us.
-			 */
-			flags = compound_lock_irqsave(page_head);
-			/* here __split_huge_page_refcount won't run anymore */
+	if (likely(page != page_head && get_page_unless_zero(page_head))) {
+		/* Ref to put_compound_page() comment. */
+		if (PageSlab(page_head) || PageHeadHuge(page_head)) {
 			if (likely(PageTail(page))) {
+				/*
+				 * This is a hugetlbfs page or a slab
+				 * page. __split_huge_page_refcount
+				 * cannot race here.
+				 */
+				VM_BUG_ON(!PageHead(page_head));
 				__get_page_tail_foll(page, false);
-				got = true;
-			}
-			compound_unlock_irqrestore(page_head, flags);
-			if (unlikely(!got))
+				return true;
+			} else {
+				/*
+				 * __split_huge_page_refcount run
+				 * before us, "page" was a THP
+				 * tail. The split page_head has been
+				 * freed and reallocated as slab or
+				 * hugetlbfs page of smaller order
+				 * (only possible if reallocated as
+				 * slab on x86).
+				 */
 				put_page(page_head);
+				return false;
+			}
+		}
+
+		/*
+		 * page_head wasn't a dangling pointer but it
+		 * may not be a head page anymore by the time
+		 * we obtain the lock. That is ok as long as it
+		 * can't be freed from under us.
+		 */
+		flags = compound_lock_irqsave(page_head);
+		/* here __split_huge_page_refcount won't run anymore */
+		if (likely(PageTail(page))) {
+			__get_page_tail_foll(page, false);
+			got = true;
 		}
+		compound_unlock_irqrestore(page_head, flags);
+		if (unlikely(!got))
+			put_page(page_head);
 	}
 	return got;
 }
@@ -934,7 +957,8 @@ void __init swap_setup(void)
 #ifdef CONFIG_SWAP
 	int i;
 
-	bdi_init(swapper_spaces[0].backing_dev_info);
+	if (bdi_init(swapper_spaces[0].backing_dev_info))
+		panic("Failed to init swap bdi");
 	for (i = 0; i < MAX_SWAPFILES; i++) {
 		spin_lock_init(&swapper_spaces[i].tree_lock);
 		INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 3963fc24fcc1..612a7c9795f6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -707,7 +707,7 @@ noswap:
 	return (swp_entry_t) {0};
 }
 
-/* The only caller of this function is now susupend routine */
+/* The only caller of this function is now suspend routine */
 swp_entry_t get_swap_page_of_type(int type)
 {
 	struct swap_info_struct *si;
@@ -845,7 +845,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 }
 
 /*
- * Caller has made sure that the swapdevice corresponding to entry
+ * Caller has made sure that the swap device corresponding to entry
  * is still around or has not been recycled.
  */
 void swap_free(swp_entry_t entry)
@@ -947,7 +947,7 @@ int try_to_free_swap(struct page *page)
 	 * original page might be freed under memory pressure, then
 	 * later read back in from swap, now with the wrong data.
 	 *
-	 * Hibration suspends storage while it is writing the image
+	 * Hibernation suspends storage while it is writing the image
 	 * to disk so check that here.
 	 */
 	if (pm_suspended_storage())
@@ -1179,7 +1179,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	 * some architectures (e.g. x86_32 with PAE) we might catch a glimpse
 	 * of unmatched parts which look like swp_pte, so unuse_pte must
 	 * recheck under pte lock.  Scanning without pte lock lets it be
-	 * preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE.
+	 * preemptable whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE.
 	 */
 	pte = pte_offset_map(pmd, addr);
 	do {
@@ -1824,6 +1824,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct filename *pathname;
 	int i, type, prev;
 	int err;
+	unsigned int old_block_size;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1914,6 +1915,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	}
 
 	swap_file = p->swap_file;
+	old_block_size = p->old_block_size;
 	p->swap_file = NULL;
 	p->max = 0;
 	swap_map = p->swap_map;
@@ -1922,23 +1924,23 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	p->cluster_info = NULL;
 	p->flags = 0;
 	frontswap_map = frontswap_map_get(p);
-	frontswap_map_set(p, NULL);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 	frontswap_invalidate_area(type);
+	frontswap_map_set(p, NULL);
 	mutex_unlock(&swapon_mutex);
 	free_percpu(p->percpu_cluster);
 	p->percpu_cluster = NULL;
 	vfree(swap_map);
 	vfree(cluster_info);
 	vfree(frontswap_map);
-	/* Destroy swap account informatin */
+	/* Destroy swap account information */
 	swap_cgroup_swapoff(type);
 
 	inode = mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
 		struct block_device *bdev = I_BDEV(inode);
-		set_blocksize(bdev, p->old_block_size);
+		set_blocksize(bdev, old_block_size);
 		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
 	} else {
 		mutex_lock(&inode->i_mutex);
@@ -2784,8 +2786,8 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 
 	/*
 	 * We are fortunate that although vmalloc_to_page uses pte_offset_map,
-	 * no architecture is using highmem pages for kernel pagetables: so it
-	 * will not corrupt the GFP_ATOMIC caller's atomic pagetable kmaps.
+	 * no architecture is using highmem pages for kernel page tables: so it
+	 * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps.
 	 */
 	head = vmalloc_to_page(si->swap_map + offset);
 	offset &= ~PAGE_MASK;
diff --git a/mm/util.c b/mm/util.c
index eaf63fc2c92f..f7bc2096071c 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -7,6 +7,9 @@
 #include <linux/security.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mman.h>
+#include <linux/hugetlb.h>
+
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -398,6 +401,16 @@ struct address_space *page_mapping(struct page *page)
 	return mapping;
 }
 
+/*
+ * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
+ */
+unsigned long vm_commit_limit(void)
+{
+	return ((totalram_pages - hugetlb_total_pages())
+		* sysctl_overcommit_ratio / 100) + total_swap_pages;
+}
+
+
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 107454312d5e..0fdf96803c5b 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -359,6 +359,12 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	if (unlikely(!va))
 		return ERR_PTR(-ENOMEM);
 
+	/*
+	 * Only scan the relevant parts containing pointers to other objects
+	 * to avoid false negatives.
+	 */
+	kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK);
+
 retry:
 	spin_lock(&vmap_area_lock);
 	/*
@@ -1546,7 +1552,7 @@ static void *__vmalloc_node(unsigned long size, unsigned long align,
 			    gfp_t gfp_mask, pgprot_t prot,
 			    int node, const void *caller);
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
-				 pgprot_t prot, int node, const void *caller)
+				 pgprot_t prot, int node)
 {
 	const int order = 0;
 	struct page **pages;
@@ -1560,13 +1566,12 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	/* Please note that the recursion is strictly bounded. */
 	if (array_size > PAGE_SIZE) {
 		pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM,
-				PAGE_KERNEL, node, caller);
+				PAGE_KERNEL, node, area->caller);
 		area->flags |= VM_VPAGES;
 	} else {
 		pages = kmalloc_node(array_size, nested_gfp, node);
 	}
 	area->pages = pages;
-	area->caller = caller;
 	if (!area->pages) {
 		remove_vm_area(area->addr);
 		kfree(area);
@@ -1577,7 +1582,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		struct page *page;
 		gfp_t tmp_mask = gfp_mask | __GFP_NOWARN;
 
-		if (node < 0)
+		if (node == NUMA_NO_NODE)
 			page = alloc_page(tmp_mask);
 		else
 			page = alloc_pages_node(node, tmp_mask, order);
@@ -1634,9 +1639,9 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	if (!area)
 		goto fail;
 
-	addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+	addr = __vmalloc_area_node(area, gfp_mask, prot, node);
 	if (!addr)
-		goto fail;
+		return NULL;
 
 	/*
 	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED
@@ -1646,11 +1651,11 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	clear_vm_uninitialized_flag(area);
 
 	/*
-	 * A ref_count = 3 is needed because the vm_struct and vmap_area
-	 * structures allocated in the __get_vm_area_node() function contain
-	 * references to the virtual address of the vmalloc'ed block.
+	 * A ref_count = 2 is needed because vm_struct allocated in
+	 * __get_vm_area_node() contains a reference to the virtual address of
+	 * the vmalloc'ed block.
 	 */
-	kmemleak_alloc(addr, real_size, 3, gfp_mask);
+	kmemleak_alloc(addr, real_size, 2, gfp_mask);
 
 	return addr;
 
@@ -2563,6 +2568,11 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v)
 		if (!counters)
 			return;
 
+		/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
+		smp_rmb();
+		if (v->flags & VM_UNINITIALIZED)
+			return;
+
 		memset(counters, 0, nr_node_ids * sizeof(unsigned int));
 
 		for (nr = 0; nr < v->nr_pages; nr++)
@@ -2579,23 +2589,15 @@ static int s_show(struct seq_file *m, void *p)
 	struct vmap_area *va = p;
 	struct vm_struct *v;
 
-	if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING))
+	/*
+	 * s_show can encounter race with remove_vm_area, !VM_VM_AREA on
+	 * behalf of vmap area is being tear down or vm_map_ram allocation.
+	 */
+	if (!(va->flags & VM_VM_AREA))
 		return 0;
 
-	if (!(va->flags & VM_VM_AREA)) {
-		seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
-			(void *)va->va_start, (void *)va->va_end,
-					va->va_end - va->va_start);
-		return 0;
-	}
-
 	v = va->vm;
 
-	/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
-	smp_rmb();
-	if (v->flags & VM_UNINITIALIZED)
-		return 0;
-
 	seq_printf(m, "0x%pK-0x%pK %7ld",
 		v->addr, v->addr + v->size, v->size);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8ed1b775bdc9..eea668d9cff6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -48,6 +48,7 @@
 #include <asm/div64.h>
 
 #include <linux/swapops.h>
+#include <linux/balloon_compaction.h>
 
 #include "internal.h"
 
@@ -139,23 +140,11 @@ static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
 }
-
-static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
-{
-	struct mem_cgroup *root = sc->target_mem_cgroup;
-	return !mem_cgroup_disabled() &&
-		mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE;
-}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
 	return true;
 }
-
-static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
-{
-	return false;
-}
 #endif
 
 unsigned long zone_reclaimable_pages(struct zone *zone)
@@ -222,6 +211,7 @@ void unregister_shrinker(struct shrinker *shrinker)
 	down_write(&shrinker_rwsem);
 	list_del(&shrinker->list);
 	up_write(&shrinker_rwsem);
+	kfree(shrinker->nr_deferred);
 }
 EXPORT_SYMBOL(unregister_shrinker);
 
@@ -1125,7 +1115,8 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 	LIST_HEAD(clean_pages);
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
-		if (page_is_file_cache(page) && !PageDirty(page)) {
+		if (page_is_file_cache(page) && !PageDirty(page) &&
+		    !isolated_balloon_page(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
@@ -2176,11 +2167,9 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	}
 }
 
-static int
-__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
 {
 	unsigned long nr_reclaimed, nr_scanned;
-	int groups_scanned = 0;
 
 	do {
 		struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2188,17 +2177,15 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 			.zone = zone,
 			.priority = sc->priority,
 		};
-		struct mem_cgroup *memcg = NULL;
-		mem_cgroup_iter_filter filter = (soft_reclaim) ?
-			mem_cgroup_soft_reclaim_eligible : NULL;
+		struct mem_cgroup *memcg;
 
 		nr_reclaimed = sc->nr_reclaimed;
 		nr_scanned = sc->nr_scanned;
 
-		while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) {
+		memcg = mem_cgroup_iter(root, NULL, &reclaim);
+		do {
 			struct lruvec *lruvec;
 
-			groups_scanned++;
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 
 			shrink_lruvec(lruvec, sc);
@@ -2218,7 +2205,8 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 				mem_cgroup_iter_break(root, memcg);
 				break;
 			}
-		}
+			memcg = mem_cgroup_iter(root, memcg, &reclaim);
+		} while (memcg);
 
 		vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
 			   sc->nr_scanned - nr_scanned,
@@ -2226,37 +2214,6 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 
 	} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
-
-	return groups_scanned;
-}
-
-
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
-{
-	bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc);
-	unsigned long nr_scanned = sc->nr_scanned;
-	int scanned_groups;
-
-	scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim);
-	/*
-	 * memcg iterator might race with other reclaimer or start from
-	 * a incomplete tree walk so the tree walk in __shrink_zone
-	 * might have missed groups that are above the soft limit. Try
-	 * another loop to catch up with others. Do it just once to
-	 * prevent from reclaim latencies when other reclaimers always
-	 * preempt this one.
-	 */
-	if (do_soft_reclaim && !scanned_groups)
-		__shrink_zone(zone, sc, do_soft_reclaim);
-
-	/*
-	 * No group is over the soft limit or those that are do not have
-	 * pages in the zone we are reclaiming so we have to reclaim everybody
-	 */
-	if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) {
-		__shrink_zone(zone, sc, false);
-		return;
-	}
 }
 
 /* Returns true if compaction should go ahead for a high-order request */
@@ -2320,6 +2277,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
+	unsigned long nr_soft_reclaimed;
+	unsigned long nr_soft_scanned;
 	bool aborted_reclaim = false;
 
 	/*
@@ -2359,6 +2318,18 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 					continue;
 				}
 			}
+			/*
+			 * This steals pages from memory cgroups over softlimit
+			 * and returns the number of reclaimed pages and
+			 * scanned pages. This works for global memory pressure
+			 * and balancing, not for a memcg's limit.
+			 */
+			nr_soft_scanned = 0;
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+						sc->order, sc->gfp_mask,
+						&nr_soft_scanned);
+			sc->nr_reclaimed += nr_soft_reclaimed;
+			sc->nr_scanned += nr_soft_scanned;
 			/* need some check for avoid more shrink_zone() */
 		}
 
@@ -2952,6 +2923,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 {
 	int i;
 	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
+	unsigned long nr_soft_reclaimed;
+	unsigned long nr_soft_scanned;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.priority = DEF_PRIORITY,
@@ -3066,6 +3039,15 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 
 			sc.nr_scanned = 0;
 
+			nr_soft_scanned = 0;
+			/*
+			 * Call soft limit reclaim before calling shrink_zone.
+			 */
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+							order, sc.gfp_mask,
+							&nr_soft_scanned);
+			sc.nr_reclaimed += nr_soft_reclaimed;
+
 			/*
 			 * There should be no need to raise the scanning
 			 * priority if enough pages are already being scanned
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 9bb314577911..72496140ac08 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -812,6 +812,7 @@ const char * const vmstat_text[] = {
 
 #ifdef CONFIG_NUMA_BALANCING
 	"numa_pte_updates",
+	"numa_huge_pte_updates",
 	"numa_hint_faults",
 	"numa_hint_faults_local",
 	"numa_pages_migrated",
@@ -1229,6 +1230,20 @@ static void start_cpu_timer(int cpu)
 	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
 }
 
+static void vmstat_cpu_dead(int node)
+{
+	int cpu;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		if (cpu_to_node(cpu) == node)
+			goto end;
+
+	node_clear_state(node, N_CPU);
+end:
+	put_online_cpus();
+}
+
 /*
  * Use the cpu notifier to insure that the thresholds are recalculated
  * when necessary.
@@ -1258,6 +1273,7 @@ static int vmstat_cpuup_callback(struct notifier_block *nfb,
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		refresh_zone_stat_thresholds();
+		vmstat_cpu_dead(cpu_to_node(cpu));
 		break;
 	default:
 		break;
@@ -1276,8 +1292,12 @@ static int __init setup_vmstat(void)
 
 	register_cpu_notifier(&vmstat_notifier);
 
-	for_each_online_cpu(cpu)
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
 		start_cpu_timer(cpu);
+		node_set_state(cpu_to_node(cpu), N_CPU);
+	}
+	put_online_cpus();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
diff --git a/mm/zswap.c b/mm/zswap.c
index 841e35f1db22..5a63f78a5601 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -217,6 +217,7 @@ static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
 	if (!entry)
 		return NULL;
 	entry->refcount = 1;
+	RB_CLEAR_NODE(&entry->rbnode);
 	return entry;
 }
 
@@ -225,19 +226,6 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
 	kmem_cache_free(zswap_entry_cache, entry);
 }
 
-/* caller must hold the tree lock */
-static void zswap_entry_get(struct zswap_entry *entry)
-{
-	entry->refcount++;
-}
-
-/* caller must hold the tree lock */
-static int zswap_entry_put(struct zswap_entry *entry)
-{
-	entry->refcount--;
-	return entry->refcount;
-}
-
 /*********************************
 * rbtree functions
 **********************************/
@@ -285,6 +273,61 @@ static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry,
 	return 0;
 }
 
+static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
+{
+	if (!RB_EMPTY_NODE(&entry->rbnode)) {
+		rb_erase(&entry->rbnode, root);
+		RB_CLEAR_NODE(&entry->rbnode);
+	}
+}
+
+/*
+ * Carries out the common pattern of freeing and entry's zsmalloc allocation,
+ * freeing the entry itself, and decrementing the number of stored pages.
+ */
+static void zswap_free_entry(struct zswap_tree *tree,
+			struct zswap_entry *entry)
+{
+	zbud_free(tree->pool, entry->handle);
+	zswap_entry_cache_free(entry);
+	atomic_dec(&zswap_stored_pages);
+	zswap_pool_pages = zbud_get_pool_size(tree->pool);
+}
+
+/* caller must hold the tree lock */
+static void zswap_entry_get(struct zswap_entry *entry)
+{
+	entry->refcount++;
+}
+
+/* caller must hold the tree lock
+* remove from the tree and free it, if nobody reference the entry
+*/
+static void zswap_entry_put(struct zswap_tree *tree,
+			struct zswap_entry *entry)
+{
+	int refcount = --entry->refcount;
+
+	BUG_ON(refcount < 0);
+	if (refcount == 0) {
+		zswap_rb_erase(&tree->rbroot, entry);
+		zswap_free_entry(tree, entry);
+	}
+}
+
+/* caller must hold the tree lock */
+static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
+				pgoff_t offset)
+{
+	struct zswap_entry *entry = NULL;
+
+	entry = zswap_rb_search(root, offset);
+	if (entry)
+		zswap_entry_get(entry);
+
+	return entry;
+}
+
 /*********************************
 * per-cpu code
 **********************************/
@@ -368,18 +411,6 @@ static bool zswap_is_full(void)
 		zswap_pool_pages);
 }
 
-/*
- * Carries out the common pattern of freeing and entry's zsmalloc allocation,
- * freeing the entry itself, and decrementing the number of stored pages.
- */
-static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry)
-{
-	zbud_free(tree->pool, entry->handle);
-	zswap_entry_cache_free(entry);
-	atomic_dec(&zswap_stored_pages);
-	zswap_pool_pages = zbud_get_pool_size(tree->pool);
-}
-
 /*********************************
 * writeback code
 **********************************/
@@ -387,7 +418,7 @@ static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry)
 enum zswap_get_swap_ret {
 	ZSWAP_SWAPCACHE_NEW,
 	ZSWAP_SWAPCACHE_EXIST,
-	ZSWAP_SWAPCACHE_NOMEM
+	ZSWAP_SWAPCACHE_FAIL,
 };
 
 /*
@@ -401,9 +432,10 @@ enum zswap_get_swap_ret {
  * added to the swap cache, and returned in retpage.
  *
  * If success, the swap cache page is returned in retpage
- * Returns 0 if page was already in the swap cache, page is not locked
- * Returns 1 if the new page needs to be populated, page is locked
- * Returns <0 on error
+ * Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache
+ * Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated,
+ *     the new page is added to swapcache and locked
+ * Returns ZSWAP_SWAPCACHE_FAIL on error
  */
 static int zswap_get_swap_cache_page(swp_entry_t entry,
 				struct page **retpage)
@@ -475,7 +507,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
 	if (new_page)
 		page_cache_release(new_page);
 	if (!found_page)
-		return ZSWAP_SWAPCACHE_NOMEM;
+		return ZSWAP_SWAPCACHE_FAIL;
 	*retpage = found_page;
 	return ZSWAP_SWAPCACHE_EXIST;
 }
@@ -502,7 +534,7 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 	struct page *page;
 	u8 *src, *dst;
 	unsigned int dlen;
-	int ret, refcount;
+	int ret;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
@@ -517,23 +549,22 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 
 	/* find and ref zswap entry */
 	spin_lock(&tree->lock);
-	entry = zswap_rb_search(&tree->rbroot, offset);
+	entry = zswap_entry_find_get(&tree->rbroot, offset);
 	if (!entry) {
 		/* entry was invalidated */
 		spin_unlock(&tree->lock);
 		return 0;
 	}
-	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 	BUG_ON(offset != entry->offset);
 
 	/* try to allocate swap cache page */
 	switch (zswap_get_swap_cache_page(swpentry, &page)) {
-	case ZSWAP_SWAPCACHE_NOMEM: /* no memory */
+	case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
 		ret = -ENOMEM;
 		goto fail;
 
-	case ZSWAP_SWAPCACHE_EXIST: /* page is unlocked */
+	case ZSWAP_SWAPCACHE_EXIST:
 		/* page is already in the swap cache, ignore for now */
 		page_cache_release(page);
 		ret = -EEXIST;
@@ -556,43 +587,44 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 		SetPageUptodate(page);
 	}
 
+	/* move it to the tail of the inactive list after end_writeback */
+	SetPageReclaim(page);
+
 	/* start writeback */
 	__swap_writepage(page, &wbc, end_swap_bio_write);
 	page_cache_release(page);
 	zswap_written_back_pages++;
 
 	spin_lock(&tree->lock);
-
 	/* drop local reference */
-	zswap_entry_put(entry);
-	/* drop the initial reference from entry creation */
-	refcount = zswap_entry_put(entry);
+	zswap_entry_put(tree, entry);
 
 	/*
-	 * There are three possible values for refcount here:
-	 * (1) refcount is 1, load is in progress, unlink from rbtree,
-	 *     load will free
-	 * (2) refcount is 0, (normal case) entry is valid,
-	 *     remove from rbtree and free entry
-	 * (3) refcount is -1, invalidate happened during writeback,
-	 *     free entry
-	 */
-	if (refcount >= 0) {
-		/* no invalidate yet, remove from rbtree */
-		rb_erase(&entry->rbnode, &tree->rbroot);
-	}
+	* There are two possible situations for entry here:
+	* (1) refcount is 1(normal case),  entry is valid and on the tree
+	* (2) refcount is 0, entry is freed and not on the tree
+	*     because invalidate happened during writeback
+	*  search the tree and free the entry if find entry
+	*/
+	if (entry == zswap_rb_search(&tree->rbroot, offset))
+		zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
-	if (refcount <= 0) {
-		/* free the entry */
-		zswap_free_entry(tree, entry);
-		return 0;
-	}
-	return -EAGAIN;
 
+	goto end;
+
+	/*
+	* if we get here due to ZSWAP_SWAPCACHE_EXIST
+	* a load may happening concurrently
+	* it is safe and okay to not free the entry
+	* if we free the entry in the following put
+	* it it either okay to return !0
+	*/
 fail:
 	spin_lock(&tree->lock);
-	zswap_entry_put(entry);
+	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
+
+end:
 	return ret;
 }
 
@@ -676,11 +708,8 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 		if (ret == -EEXIST) {
 			zswap_duplicate_entry++;
 			/* remove from rbtree */
-			rb_erase(&dupentry->rbnode, &tree->rbroot);
-			if (!zswap_entry_put(dupentry)) {
-				/* free */
-				zswap_free_entry(tree, dupentry);
-			}
+			zswap_rb_erase(&tree->rbroot, dupentry);
+			zswap_entry_put(tree, dupentry);
 		}
 	} while (ret == -EEXIST);
 	spin_unlock(&tree->lock);
@@ -709,17 +738,16 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 	struct zswap_entry *entry;
 	u8 *src, *dst;
 	unsigned int dlen;
-	int refcount, ret;
+	int ret;
 
 	/* find */
 	spin_lock(&tree->lock);
-	entry = zswap_rb_search(&tree->rbroot, offset);
+	entry = zswap_entry_find_get(&tree->rbroot, offset);
 	if (!entry) {
 		/* entry was written back */
 		spin_unlock(&tree->lock);
 		return -1;
 	}
-	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 
 	/* decompress */
@@ -734,22 +762,9 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 	BUG_ON(ret);
 
 	spin_lock(&tree->lock);
-	refcount = zswap_entry_put(entry);
-	if (likely(refcount)) {
-		spin_unlock(&tree->lock);
-		return 0;
-	}
+	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
 
-	/*
-	 * We don't have to unlink from the rbtree because
-	 * zswap_writeback_entry() or zswap_frontswap_invalidate page()
-	 * has already done this for us if we are the last reference.
-	 */
-	/* free */
-
-	zswap_free_entry(tree, entry);
-
 	return 0;
 }
 
@@ -758,7 +773,6 @@ static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset)
 {
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry;
-	int refcount;
 
 	/* find */
 	spin_lock(&tree->lock);
@@ -770,20 +784,12 @@ static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset)
 	}
 
 	/* remove from rbtree */
-	rb_erase(&entry->rbnode, &tree->rbroot);
+	zswap_rb_erase(&tree->rbroot, entry);
 
 	/* drop the initial reference from entry creation */
-	refcount = zswap_entry_put(entry);
+	zswap_entry_put(tree, entry);
 
 	spin_unlock(&tree->lock);
-
-	if (refcount) {
-		/* writeback in progress, writeback will free */
-		return;
-	}
-
-	/* free */
-	zswap_free_entry(tree, entry);
 }
 
 /* frees all zswap entries for the given swap type */
@@ -797,13 +803,14 @@ static void zswap_frontswap_invalidate_area(unsigned type)
 
 	/* walk the tree and free everything */
 	spin_lock(&tree->lock);
-	rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode) {
-		zbud_free(tree->pool, entry->handle);
-		zswap_entry_cache_free(entry);
-		atomic_dec(&zswap_stored_pages);
-	}
+	rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode)
+		zswap_free_entry(tree, entry);
 	tree->rbroot = RB_ROOT;
 	spin_unlock(&tree->lock);
+
+	zbud_destroy_pool(tree->pool);
+	kfree(tree);
+	zswap_trees[type] = NULL;
 }
 
 static struct zbud_ops zswap_zbud_ops = {