Merge branch 'akpm' (patches from Andrew)

Merge second patch-bomb from Andrew Morton:

 - more MM stuff:

    - Kirill's page-flags rework

    - Kirill's now-allegedly-fixed THP rework

    - MADV_FREE implementation

    - DAX feature work (msync/fsync).  This isn't quite complete but DAX
      is new and it's good enough and the guys have a handle on what
      needs to be done - I expect this to be wrapped in the next week or
      two.

  - some vsprintf maintenance work

  - various other misc bits

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (145 commits)
  printk: change recursion_bug type to bool
  lib/vsprintf: factor out %pN[F] handler as netdev_bits()
  lib/vsprintf: refactor duplicate code to special_hex_number()
  printk-formats.txt: remove unimplemented %pT
  printk: help pr_debug and pr_devel to optimize out arguments
  lib/test_printf.c: test dentry printing
  lib/test_printf.c: add test for large bitmaps
  lib/test_printf.c: account for kvasprintf tests
  lib/test_printf.c: add a few number() tests
  lib/test_printf.c: test precision quirks
  lib/test_printf.c: check for out-of-bound writes
  lib/test_printf.c: don't BUG
  lib/kasprintf.c: add sanity check to kvasprintf
  lib/vsprintf.c: warn about too large precisions and field widths
  lib/vsprintf.c: help gcc make number() smaller
  lib/vsprintf.c: expand field_width to 24 bits
  lib/vsprintf.c: eliminate potential race in string()
  lib/vsprintf.c: move string() below widen_string()
  lib/vsprintf.c: pull out padding code from dentry_name()
  printk: do cond_resched() between lines while outputting to consoles
  ...

37 files changed, 2155 insertions, 1444 deletions

diff --git a/mm/debug.c b/mm/debug.c
index 5d2072e..f05b2d5 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -40,9 +40,6 @@ static const struct trace_print_flags pageflag_names[] = {
 #ifdef CONFIG_MEMORY_FAILURE
 	{1UL << PG_hwpoison,		"hwpoison"	},
 #endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	{1UL << PG_compound_lock,	"compound_lock"	},
-#endif
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
 	{1UL << PG_young,		"young"		},
 	{1UL << PG_idle,		"idle"		},
@@ -82,9 +79,12 @@ static void dump_flags(unsigned long flags,
 void dump_page_badflags(struct page *page, const char *reason,
 		unsigned long badflags)
 {
-	pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
+	pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
 		  page, atomic_read(&page->_count), page_mapcount(page),
 		  page->mapping, page->index);
+	if (PageCompound(page))
+		pr_cont(" compound_mapcount: %d", compound_mapcount(page));
+	pr_cont("\n");
 	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
 	dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names));
 	if (reason)
diff --git a/mm/filemap.c b/mm/filemap.c
index ff42d31..847ee43c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -204,7 +204,7 @@ void __delete_from_page_cache(struct page *page, void *shadow,
 		__dec_zone_page_state(page, NR_FILE_PAGES);
 	if (PageSwapBacked(page))
 		__dec_zone_page_state(page, NR_SHMEM);
-	BUG_ON(page_mapped(page));
+	VM_BUG_ON_PAGE(page_mapped(page), page);
 
 	/*
 	 * At this point page must be either written or cleaned by truncate.
@@ -618,7 +618,7 @@ static int __add_to_page_cache_locked(struct page *page,
 
 	if (!huge) {
 		error = mem_cgroup_try_charge(page, current->mm,
-					      gfp_mask, &memcg);
+					      gfp_mask, &memcg, false);
 		if (error)
 			return error;
 	}
@@ -626,7 +626,7 @@ static int __add_to_page_cache_locked(struct page *page,
 	error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
 	if (error) {
 		if (!huge)
-			mem_cgroup_cancel_charge(page, memcg);
+			mem_cgroup_cancel_charge(page, memcg, false);
 		return error;
 	}
 
@@ -645,7 +645,7 @@ static int __add_to_page_cache_locked(struct page *page,
 		__inc_zone_page_state(page, NR_FILE_PAGES);
 	spin_unlock_irq(&mapping->tree_lock);
 	if (!huge)
-		mem_cgroup_commit_charge(page, memcg, false);
+		mem_cgroup_commit_charge(page, memcg, false, false);
 	trace_mm_filemap_add_to_page_cache(page);
 	return 0;
 err_insert:
@@ -653,7 +653,7 @@ err_insert:
 	/* Leave page->index set: truncation relies upon it */
 	spin_unlock_irq(&mapping->tree_lock);
 	if (!huge)
-		mem_cgroup_cancel_charge(page, memcg);
+		mem_cgroup_cancel_charge(page, memcg, false);
 	page_cache_release(page);
 	return error;
 }
@@ -682,11 +682,11 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 	void *shadow = NULL;
 	int ret;
 
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	ret = __add_to_page_cache_locked(page, mapping, offset,
 					 gfp_mask, &shadow);
 	if (unlikely(ret))
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 	else {
 		/*
 		 * The page might have been evicted from cache only
@@ -809,6 +809,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
  */
 void unlock_page(struct page *page)
 {
+	page = compound_head(page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	clear_bit_unlock(PG_locked, &page->flags);
 	smp_mb__after_atomic();
@@ -873,18 +874,20 @@ EXPORT_SYMBOL_GPL(page_endio);
  */
 void __lock_page(struct page *page)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	struct page *page_head = compound_head(page);
+	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
 
-	__wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io,
+	__wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_page);
 
 int __lock_page_killable(struct page *page)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	struct page *page_head = compound_head(page);
+	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
 
-	return __wait_on_bit_lock(page_waitqueue(page), &wait,
+	return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
 					bit_wait_io, TASK_KILLABLE);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
diff --git a/mm/gup.c b/mm/gup.c
index deafa2c..b64a361 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -4,6 +4,7 @@
 #include <linux/spinlock.h>
 
 #include <linux/mm.h>
+#include <linux/memremap.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
@@ -62,6 +63,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmd, unsigned int flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct dev_pagemap *pgmap = NULL;
 	struct page *page;
 	spinlock_t *ptl;
 	pte_t *ptep, pte;
@@ -98,7 +100,17 @@ retry:
 	}
 
 	page = vm_normal_page(vma, address, pte);
-	if (unlikely(!page)) {
+	if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
+		/*
+		 * Only return device mapping pages in the FOLL_GET case since
+		 * they are only valid while holding the pgmap reference.
+		 */
+		pgmap = get_dev_pagemap(pte_pfn(pte), NULL);
+		if (pgmap)
+			page = pte_page(pte);
+		else
+			goto no_page;
+	} else if (unlikely(!page)) {
 		if (flags & FOLL_DUMP) {
 			/* Avoid special (like zero) pages in core dumps */
 			page = ERR_PTR(-EFAULT);
@@ -116,8 +128,28 @@ retry:
 		}
 	}
 
-	if (flags & FOLL_GET)
-		get_page_foll(page);
+	if (flags & FOLL_SPLIT && PageTransCompound(page)) {
+		int ret;
+		get_page(page);
+		pte_unmap_unlock(ptep, ptl);
+		lock_page(page);
+		ret = split_huge_page(page);
+		unlock_page(page);
+		put_page(page);
+		if (ret)
+			return ERR_PTR(ret);
+		goto retry;
+	}
+
+	if (flags & FOLL_GET) {
+		get_page(page);
+
+		/* drop the pgmap reference now that we hold the page */
+		if (pgmap) {
+			put_dev_pagemap(pgmap);
+			pgmap = NULL;
+		}
+	}
 	if (flags & FOLL_TOUCH) {
 		if ((flags & FOLL_WRITE) &&
 		    !pte_dirty(pte) && !PageDirty(page))
@@ -130,6 +162,10 @@ retry:
 		mark_page_accessed(page);
 	}
 	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
+		/* Do not mlock pte-mapped THP */
+		if (PageTransCompound(page))
+			goto out;
+
 		/*
 		 * The preliminary mapping check is mainly to avoid the
 		 * pointless overhead of lock_page on the ZERO_PAGE
@@ -220,27 +256,45 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	}
 	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
 		return no_page_table(vma, flags);
-	if (pmd_trans_huge(*pmd)) {
-		if (flags & FOLL_SPLIT) {
-			split_huge_page_pmd(vma, address, pmd);
-			return follow_page_pte(vma, address, pmd, flags);
-		}
+	if (pmd_devmap(*pmd)) {
 		ptl = pmd_lock(mm, pmd);
-		if (likely(pmd_trans_huge(*pmd))) {
-			if (unlikely(pmd_trans_splitting(*pmd))) {
-				spin_unlock(ptl);
-				wait_split_huge_page(vma->anon_vma, pmd);
-			} else {
-				page = follow_trans_huge_pmd(vma, address,
-							     pmd, flags);
-				spin_unlock(ptl);
-				*page_mask = HPAGE_PMD_NR - 1;
-				return page;
-			}
-		} else
+		page = follow_devmap_pmd(vma, address, pmd, flags);
+		spin_unlock(ptl);
+		if (page)
+			return page;
+	}
+	if (likely(!pmd_trans_huge(*pmd)))
+		return follow_page_pte(vma, address, pmd, flags);
+
+	ptl = pmd_lock(mm, pmd);
+	if (unlikely(!pmd_trans_huge(*pmd))) {
+		spin_unlock(ptl);
+		return follow_page_pte(vma, address, pmd, flags);
+	}
+	if (flags & FOLL_SPLIT) {
+		int ret;
+		page = pmd_page(*pmd);
+		if (is_huge_zero_page(page)) {
+			spin_unlock(ptl);
+			ret = 0;
+			split_huge_pmd(vma, pmd, address);
+		} else {
+			get_page(page);
 			spin_unlock(ptl);
+			lock_page(page);
+			ret = split_huge_page(page);
+			unlock_page(page);
+			put_page(page);
+		}
+
+		return ret ? ERR_PTR(ret) :
+			follow_page_pte(vma, address, pmd, flags);
 	}
-	return follow_page_pte(vma, address, pmd, flags);
+
+	page = follow_trans_huge_pmd(vma, address, pmd, flags);
+	spin_unlock(ptl);
+	*page_mask = HPAGE_PMD_NR - 1;
+	return page;
 }
 
 static int get_gate_page(struct mm_struct *mm, unsigned long address,
@@ -564,6 +618,8 @@ EXPORT_SYMBOL(__get_user_pages);
  * @mm:		mm_struct of target mm
  * @address:	user address
  * @fault_flags:flags to pass down to handle_mm_fault()
+ * @unlocked:	did we unlock the mmap_sem while retrying, maybe NULL if caller
+ *		does not allow retry
  *
  * This is meant to be called in the specific scenario where for locking reasons
  * we try to access user memory in atomic context (within a pagefault_disable()
@@ -575,22 +631,28 @@ EXPORT_SYMBOL(__get_user_pages);
  * The main difference with get_user_pages() is that this function will
  * unconditionally call handle_mm_fault() which will in turn perform all the
  * necessary SW fixup of the dirty and young bits in the PTE, while
- * handle_mm_fault() only guarantees to update these in the struct page.
+ * get_user_pages() only guarantees to update these in the struct page.
  *
  * This is important for some architectures where those bits also gate the
  * access permission to the page because they are maintained in software.  On
  * such architectures, gup() will not be enough to make a subsequent access
  * succeed.
  *
- * This has the same semantics wrt the @mm->mmap_sem as does filemap_fault().
+ * This function will not return with an unlocked mmap_sem. So it has not the
+ * same semantics wrt the @mm->mmap_sem as does filemap_fault().
  */
 int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
-		     unsigned long address, unsigned int fault_flags)
+		     unsigned long address, unsigned int fault_flags,
+		     bool *unlocked)
 {
 	struct vm_area_struct *vma;
 	vm_flags_t vm_flags;
-	int ret;
+	int ret, major = 0;
 
+	if (unlocked)
+		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+
+retry:
 	vma = find_extend_vma(mm, address);
 	if (!vma || address < vma->vm_start)
 		return -EFAULT;
@@ -600,6 +662,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 		return -EFAULT;
 
 	ret = handle_mm_fault(mm, vma, address, fault_flags);
+	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
 		if (ret & VM_FAULT_OOM)
 			return -ENOMEM;
@@ -609,8 +672,19 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 			return -EFAULT;
 		BUG();
 	}
+
+	if (ret & VM_FAULT_RETRY) {
+		down_read(&mm->mmap_sem);
+		if (!(fault_flags & FAULT_FLAG_TRIED)) {
+			*unlocked = true;
+			fault_flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			fault_flags |= FAULT_FLAG_TRIED;
+			goto retry;
+		}
+	}
+
 	if (tsk) {
-		if (ret & VM_FAULT_MAJOR)
+		if (major)
 			tsk->maj_flt++;
 		else
 			tsk->min_flt++;
@@ -896,7 +970,6 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK;
 	if (vma->vm_flags & VM_LOCKONFAULT)
 		gup_flags &= ~FOLL_POPULATE;
-
 	/*
 	 * We want to touch writable mappings with a write fault in order
 	 * to break COW, except for shared mappings because these don't COW
@@ -1036,9 +1109,6 @@ struct page *get_dump_page(unsigned long addr)
  *  *) HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table is used to free
  *      pages containing page tables.
  *
- *  *) THP splits will broadcast an IPI, this can be achieved by overriding
- *      pmdp_splitting_flush.
- *
  *  *) ptes can be read atomically by the architecture.
  *
  *  *) access_ok is sufficient to validate userspace address ranges.
@@ -1066,7 +1136,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 		 * for an example see gup_get_pte in arch/x86/mm/gup.c
 		 */
 		pte_t pte = READ_ONCE(*ptep);
-		struct page *page;
+		struct page *head, *page;
 
 		/*
 		 * Similar to the PMD case below, NUMA hinting must take slow
@@ -1078,15 +1148,17 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
+		head = compound_head(page);
 
-		if (!page_cache_get_speculative(page))
+		if (!page_cache_get_speculative(head))
 			goto pte_unmap;
 
 		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-			put_page(page);
+			put_page(head);
 			goto pte_unmap;
 		}
 
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
 		(*nr)++;
 
@@ -1119,7 +1191,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 	int refs;
 
 	if (write && !pmd_write(orig))
@@ -1128,7 +1200,6 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	refs = 0;
 	head = pmd_page(orig);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
@@ -1149,24 +1220,13 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 	}
 
-	/*
-	 * Any tail pages need their mapcount reference taken before we
-	 * return. (This allows the THP code to bump their ref count when
-	 * they are split into base pages).
-	 */
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }
 
 static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 	int refs;
 
 	if (write && !pud_write(orig))
@@ -1175,7 +1235,6 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	refs = 0;
 	head = pud_page(orig);
 	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
@@ -1196,12 +1255,6 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 	}
 
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }
 
@@ -1210,7 +1263,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 			struct page **pages, int *nr)
 {
 	int refs;
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 
 	if (write && !pgd_write(orig))
 		return 0;
@@ -1218,7 +1271,6 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 	refs = 0;
 	head = pgd_page(orig);
 	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
@@ -1239,12 +1291,6 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		return 0;
 	}
 
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }
 
@@ -1259,7 +1305,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		pmd_t pmd = READ_ONCE(*pmdp);
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
+		if (pmd_none(pmd))
 			return 0;
 
 		if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f952f05..b2db981 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -16,12 +16,16 @@
 #include <linux/swap.h>
 #include <linux/shrinker.h>
 #include <linux/mm_inline.h>
+#include <linux/swapops.h>
 #include <linux/dax.h>
 #include <linux/kthread.h>
 #include <linux/khugepaged.h>
 #include <linux/freezer.h>
+#include <linux/pfn_t.h>
 #include <linux/mman.h>
+#include <linux/memremap.h>
 #include <linux/pagemap.h>
+#include <linux/debugfs.h>
 #include <linux/migrate.h>
 #include <linux/hashtable.h>
 #include <linux/userfaultfd_k.h>
@@ -45,6 +49,7 @@ enum scan_result {
 	SCAN_PAGE_LRU,
 	SCAN_PAGE_LOCK,
 	SCAN_PAGE_ANON,
+	SCAN_PAGE_COMPOUND,
 	SCAN_ANY_PROCESS,
 	SCAN_VMA_NULL,
 	SCAN_VMA_CHECK,
@@ -133,6 +138,10 @@ static struct khugepaged_scan khugepaged_scan = {
 	.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
 };
 
+static DEFINE_SPINLOCK(split_queue_lock);
+static LIST_HEAD(split_queue);
+static unsigned long split_queue_len;
+static struct shrinker deferred_split_shrinker;
 
 static void set_recommended_min_free_kbytes(void)
 {
@@ -665,6 +674,9 @@ static int __init hugepage_init(void)
 	err = register_shrinker(&huge_zero_page_shrinker);
 	if (err)
 		goto err_hzp_shrinker;
+	err = register_shrinker(&deferred_split_shrinker);
+	if (err)
+		goto err_split_shrinker;
 
 	/*
 	 * By default disable transparent hugepages on smaller systems,
@@ -682,6 +694,8 @@ static int __init hugepage_init(void)
 
 	return 0;
 err_khugepaged:
+	unregister_shrinker(&deferred_split_shrinker);
+err_split_shrinker:
 	unregister_shrinker(&huge_zero_page_shrinker);
 err_hzp_shrinker:
 	khugepaged_slab_exit();
@@ -738,6 +752,27 @@ static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
 	return entry;
 }
 
+static inline struct list_head *page_deferred_list(struct page *page)
+{
+	/*
+	 * ->lru in the tail pages is occupied by compound_head.
+	 * Let's use ->mapping + ->index in the second tail page as list_head.
+	 */
+	return (struct list_head *)&page[2].mapping;
+}
+
+void prep_transhuge_page(struct page *page)
+{
+	/*
+	 * we use page->mapping and page->indexlru in second tail page
+	 * as list_head: assuming THP order >= 2
+	 */
+	BUILD_BUG_ON(HPAGE_PMD_ORDER < 2);
+
+	INIT_LIST_HEAD(page_deferred_list(page));
+	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
+}
+
 static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long address, pmd_t *pmd,
@@ -751,7 +786,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, mm, gfp, &memcg)) {
+	if (mem_cgroup_try_charge(page, mm, gfp, &memcg, true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -759,7 +794,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 
 	pgtable = pte_alloc_one(mm, haddr);
 	if (unlikely(!pgtable)) {
-		mem_cgroup_cancel_charge(page, memcg);
+		mem_cgroup_cancel_charge(page, memcg, true);
 		put_page(page);
 		return VM_FAULT_OOM;
 	}
@@ -775,7 +810,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_none(*pmd))) {
 		spin_unlock(ptl);
-		mem_cgroup_cancel_charge(page, memcg);
+		mem_cgroup_cancel_charge(page, memcg, true);
 		put_page(page);
 		pte_free(mm, pgtable);
 	} else {
@@ -786,7 +821,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 			int ret;
 
 			spin_unlock(ptl);
-			mem_cgroup_cancel_charge(page, memcg);
+			mem_cgroup_cancel_charge(page, memcg, true);
 			put_page(page);
 			pte_free(mm, pgtable);
 			ret = handle_userfault(vma, address, flags,
@@ -797,8 +832,8 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		page_add_new_anon_rmap(page, vma, haddr);
-		mem_cgroup_commit_charge(page, memcg, false);
+		page_add_new_anon_rmap(page, vma, haddr, true);
+		mem_cgroup_commit_charge(page, memcg, false, true);
 		lru_cache_add_active_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		set_pmd_at(mm, haddr, pmd, entry);
@@ -892,32 +927,33 @@ 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;
 	}
+	prep_transhuge_page(page);
 	return __do_huge_pmd_anonymous_page(mm, vma, address, pmd, page, gfp,
 					    flags);
 }
 
 static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, unsigned long pfn, pgprot_t prot, bool write)
+		pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t entry;
 	spinlock_t *ptl;
 
 	ptl = pmd_lock(mm, pmd);
-	if (pmd_none(*pmd)) {
-		entry = pmd_mkhuge(pfn_pmd(pfn, prot));
-		if (write) {
-			entry = pmd_mkyoung(pmd_mkdirty(entry));
-			entry = maybe_pmd_mkwrite(entry, vma);
-		}
-		set_pmd_at(mm, addr, pmd, entry);
-		update_mmu_cache_pmd(vma, addr, pmd);
-	}
+	entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
+	if (pfn_t_devmap(pfn))
+		entry = pmd_mkdevmap(entry);
+	if (write) {
+		entry = pmd_mkyoung(pmd_mkdirty(entry));
+		entry = maybe_pmd_mkwrite(entry, vma);
+	}
+	set_pmd_at(mm, addr, pmd, entry);
+	update_mmu_cache_pmd(vma, addr, pmd);
 	spin_unlock(ptl);
 }
 
 int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
-			pmd_t *pmd, unsigned long pfn, bool write)
+			pmd_t *pmd, pfn_t pfn, bool write)
 {
 	pgprot_t pgprot = vma->vm_page_prot;
 	/*
@@ -929,7 +965,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
 						(VM_PFNMAP|VM_MIXEDMAP));
 	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
-	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
+	BUG_ON(!pfn_t_devmap(pfn));
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return VM_FAULT_SIGBUS;
@@ -939,6 +975,63 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	return VM_FAULT_NOPAGE;
 }
 
+static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd)
+{
+	pmd_t _pmd;
+
+	/*
+	 * We should set the dirty bit only for FOLL_WRITE but for now
+	 * the dirty bit in the pmd is meaningless.  And if the dirty
+	 * bit will become meaningful and we'll only set it with
+	 * FOLL_WRITE, an atomic set_bit will be required on the pmd to
+	 * set the young bit, instead of the current set_pmd_at.
+	 */
+	_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
+	if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
+				pmd, _pmd,  1))
+		update_mmu_cache_pmd(vma, addr, pmd);
+}
+
+struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, int flags)
+{
+	unsigned long pfn = pmd_pfn(*pmd);
+	struct mm_struct *mm = vma->vm_mm;
+	struct dev_pagemap *pgmap;
+	struct page *page;
+
+	assert_spin_locked(pmd_lockptr(mm, pmd));
+
+	if (flags & FOLL_WRITE && !pmd_write(*pmd))
+		return NULL;
+
+	if (pmd_present(*pmd) && pmd_devmap(*pmd))
+		/* pass */;
+	else
+		return NULL;
+
+	if (flags & FOLL_TOUCH)
+		touch_pmd(vma, addr, pmd);
+
+	/*
+	 * device mapped pages can only be returned if the
+	 * caller will manage the page reference count.
+	 */
+	if (!(flags & FOLL_GET))
+		return ERR_PTR(-EEXIST);
+
+	pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
+	pgmap = get_dev_pagemap(pfn, NULL);
+	if (!pgmap)
+		return ERR_PTR(-EFAULT);
+	page = pfn_to_page(pfn);
+	get_page(page);
+	put_dev_pagemap(pgmap);
+
+	return page;
+}
+
 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)
@@ -960,7 +1053,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 	ret = -EAGAIN;
 	pmd = *src_pmd;
-	if (unlikely(!pmd_trans_huge(pmd))) {
+	if (unlikely(!pmd_trans_huge(pmd) && !pmd_devmap(pmd))) {
 		pte_free(dst_mm, pgtable);
 		goto out_unlock;
 	}
@@ -983,26 +1076,20 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		goto out_unlock;
 	}
 
-	if (unlikely(pmd_trans_splitting(pmd))) {
-		/* split huge page running from under us */
-		spin_unlock(src_ptl);
-		spin_unlock(dst_ptl);
-		pte_free(dst_mm, pgtable);
-
-		wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */
-		goto out;
+	if (pmd_trans_huge(pmd)) {
+		/* thp accounting separate from pmd_devmap accounting */
+		src_page = pmd_page(pmd);
+		VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
+		get_page(src_page);
+		page_dup_rmap(src_page, true);
+		add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+		atomic_long_inc(&dst_mm->nr_ptes);
+		pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
 	}
-	src_page = pmd_page(pmd);
-	VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
-	get_page(src_page);
-	page_dup_rmap(src_page);
-	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 
 	pmdp_set_wrprotect(src_mm, addr, src_pmd);
 	pmd = pmd_mkold(pmd_wrprotect(pmd));
-	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
-	atomic_long_inc(&dst_mm->nr_ptes);
 
 	ret = 0;
 out_unlock:
@@ -1035,37 +1122,6 @@ unlock:
 	spin_unlock(ptl);
 }
 
-/*
- * Save CONFIG_DEBUG_PAGEALLOC from faulting falsely on tail pages
- * during copy_user_huge_page()'s copy_page_rep(): in the case when
- * the source page gets split and a tail freed before copy completes.
- * Called under pmd_lock of checked pmd, so safe from splitting itself.
- */
-static void get_user_huge_page(struct page *page)
-{
-	if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
-		struct page *endpage = page + HPAGE_PMD_NR;
-
-		atomic_add(HPAGE_PMD_NR, &page->_count);
-		while (++page < endpage)
-			get_huge_page_tail(page);
-	} else {
-		get_page(page);
-	}
-}
-
-static void put_user_huge_page(struct page *page)
-{
-	if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
-		struct page *endpage = page + HPAGE_PMD_NR;
-
-		while (page < endpage)
-			put_page(page++);
-	} else {
-		put_page(page);
-	}
-}
-
 static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long address,
@@ -1095,13 +1151,14 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					       vma, address, page_to_nid(page));
 		if (unlikely(!pages[i] ||
 			     mem_cgroup_try_charge(pages[i], mm, GFP_KERNEL,
-						   &memcg))) {
+						   &memcg, false))) {
 			if (pages[i])
 				put_page(pages[i]);
 			while (--i >= 0) {
 				memcg = (void *)page_private(pages[i]);
 				set_page_private(pages[i], 0);
-				mem_cgroup_cancel_charge(pages[i], memcg);
+				mem_cgroup_cancel_charge(pages[i], memcg,
+						false);
 				put_page(pages[i]);
 			}
 			kfree(pages);
@@ -1139,8 +1196,8 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		memcg = (void *)page_private(pages[i]);
 		set_page_private(pages[i], 0);
-		page_add_new_anon_rmap(pages[i], vma, haddr);
-		mem_cgroup_commit_charge(pages[i], memcg, false);
+		page_add_new_anon_rmap(pages[i], vma, haddr, false);
+		mem_cgroup_commit_charge(pages[i], memcg, false, false);
 		lru_cache_add_active_or_unevictable(pages[i], vma);
 		pte = pte_offset_map(&_pmd, haddr);
 		VM_BUG_ON(!pte_none(*pte));
@@ -1151,7 +1208,7 @@ 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);
+	page_remove_rmap(page, true);
 	spin_unlock(ptl);
 
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
@@ -1168,7 +1225,7 @@ out_free_pages:
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		memcg = (void *)page_private(pages[i]);
 		set_page_private(pages[i], 0);
-		mem_cgroup_cancel_charge(pages[i], memcg);
+		mem_cgroup_cancel_charge(pages[i], memcg, false);
 		put_page(pages[i]);
 	}
 	kfree(pages);
@@ -1198,7 +1255,17 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	page = pmd_page(orig_pmd);
 	VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page);
-	if (page_mapcount(page) == 1) {
+	/*
+	 * We can only reuse the page if nobody else maps the huge page or it's
+	 * part. We can do it by checking page_mapcount() on each sub-page, but
+	 * it's expensive.
+	 * The cheaper way is to check page_count() to be equal 1: every
+	 * mapcount takes page reference reference, so this way we can
+	 * guarantee, that the PMD is the only mapping.
+	 * This can give false negative if somebody pinned the page, but that's
+	 * fine.
+	 */
+	if (page_mapcount(page) == 1 && page_count(page) == 1) {
 		pmd_t entry;
 		entry = pmd_mkyoung(orig_pmd);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
@@ -1207,7 +1274,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		ret |= VM_FAULT_WRITE;
 		goto out_unlock;
 	}
-	get_user_huge_page(page);
+	get_page(page);
 	spin_unlock(ptl);
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
@@ -1217,30 +1284,33 @@ alloc:
 	} else
 		new_page = NULL;
 
-	if (unlikely(!new_page)) {
+	if (likely(new_page)) {
+		prep_transhuge_page(new_page);
+	} else {
 		if (!page) {
-			split_huge_page_pmd(vma, address, pmd);
+			split_huge_pmd(vma, pmd, address);
 			ret |= VM_FAULT_FALLBACK;
 		} else {
 			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 					pmd, orig_pmd, page, haddr);
 			if (ret & VM_FAULT_OOM) {
-				split_huge_page(page);
+				split_huge_pmd(vma, pmd, address);
 				ret |= VM_FAULT_FALLBACK;
 			}
-			put_user_huge_page(page);
+			put_page(page);
 		}
 		count_vm_event(THP_FAULT_FALLBACK);
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg))) {
+	if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg,
+					   true))) {
 		put_page(new_page);
 		if (page) {
-			split_huge_page(page);
-			put_user_huge_page(page);
+			split_huge_pmd(vma, pmd, address);
+			put_page(page);
 		} else
-			split_huge_page_pmd(vma, address, pmd);
+			split_huge_pmd(vma, pmd, address);
 		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
 		goto out;
@@ -1260,10 +1330,10 @@ alloc:
 
 	spin_lock(ptl);
 	if (page)
-		put_user_huge_page(page);
+		put_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
 		spin_unlock(ptl);
-		mem_cgroup_cancel_charge(new_page, memcg);
+		mem_cgroup_cancel_charge(new_page, memcg, true);
 		put_page(new_page);
 		goto out_mn;
 	} else {
@@ -1271,8 +1341,8 @@ alloc:
 		entry = mk_huge_pmd(new_page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		pmdp_huge_clear_flush_notify(vma, haddr, pmd);
-		page_add_new_anon_rmap(new_page, vma, haddr);
-		mem_cgroup_commit_charge(new_page, memcg, false);
+		page_add_new_anon_rmap(new_page, vma, haddr, true);
+		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_active_or_unevictable(new_page, vma);
 		set_pmd_at(mm, haddr, pmd, entry);
 		update_mmu_cache_pmd(vma, address, pmd);
@@ -1281,7 +1351,7 @@ alloc:
 			put_huge_zero_page();
 		} else {
 			VM_BUG_ON_PAGE(!PageHead(page), page);
-			page_remove_rmap(page);
+			page_remove_rmap(page, true);
 			put_page(page);
 		}
 		ret |= VM_FAULT_WRITE;
@@ -1319,23 +1389,23 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 
 	page = pmd_page(*pmd);
 	VM_BUG_ON_PAGE(!PageHead(page), page);
-	if (flags & FOLL_TOUCH) {
-		pmd_t _pmd;
+	if (flags & FOLL_TOUCH)
+		touch_pmd(vma, addr, pmd);
+	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
 		/*
-		 * We should set the dirty bit only for FOLL_WRITE but
-		 * for now the dirty bit in the pmd is meaningless.
-		 * And if the dirty bit will become meaningful and
-		 * we'll only set it with FOLL_WRITE, an atomic
-		 * set_bit will be required on the pmd to set the
-		 * young bit, instead of the current set_pmd_at.
+		 * We don't mlock() pte-mapped THPs. This way we can avoid
+		 * leaking mlocked pages into non-VM_LOCKED VMAs.
+		 *
+		 * In most cases the pmd is the only mapping of the page as we
+		 * break COW for the mlock() -- see gup_flags |= FOLL_WRITE for
+		 * writable private mappings in populate_vma_page_range().
+		 *
+		 * The only scenario when we have the page shared here is if we
+		 * mlocking read-only mapping shared over fork(). We skip
+		 * mlocking such pages.
 		 */
-		_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
-		if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
-					  pmd, _pmd,  1))
-			update_mmu_cache_pmd(vma, addr, pmd);
-	}
-	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
-		if (page->mapping && trylock_page(page)) {
+		if (compound_mapcount(page) == 1 && !PageDoubleMap(page) &&
+				page->mapping && trylock_page(page)) {
 			lru_add_drain();
 			if (page->mapping)
 				mlock_vma_page(page);
@@ -1345,7 +1415,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 	if (flags & FOLL_GET)
-		get_page_foll(page);
+		get_page(page);
 
 out:
 	return page;
@@ -1480,13 +1550,84 @@ out:
 	return 0;
 }
 
+int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		pmd_t *pmd, unsigned long addr, unsigned long next)
+
+{
+	spinlock_t *ptl;
+	pmd_t orig_pmd;
+	struct page *page;
+	struct mm_struct *mm = tlb->mm;
+	int ret = 0;
+
+	if (!pmd_trans_huge_lock(pmd, vma, &ptl))
+		goto out;
+
+	orig_pmd = *pmd;
+	if (is_huge_zero_pmd(orig_pmd)) {
+		ret = 1;
+		goto out;
+	}
+
+	page = pmd_page(orig_pmd);
+	/*
+	 * If other processes are mapping this page, we couldn't discard
+	 * the page unless they all do MADV_FREE so let's skip the page.
+	 */
+	if (page_mapcount(page) != 1)
+		goto out;
+
+	if (!trylock_page(page))
+		goto out;
+
+	/*
+	 * If user want to discard part-pages of THP, split it so MADV_FREE
+	 * will deactivate only them.
+	 */
+	if (next - addr != HPAGE_PMD_SIZE) {
+		get_page(page);
+		spin_unlock(ptl);
+		if (split_huge_page(page)) {
+			put_page(page);
+			unlock_page(page);
+			goto out_unlocked;
+		}
+		put_page(page);
+		unlock_page(page);
+		ret = 1;
+		goto out_unlocked;
+	}
+
+	if (PageDirty(page))
+		ClearPageDirty(page);
+	unlock_page(page);
+
+	if (PageActive(page))
+		deactivate_page(page);
+
+	if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
+		orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
+			tlb->fullmm);
+		orig_pmd = pmd_mkold(orig_pmd);
+		orig_pmd = pmd_mkclean(orig_pmd);
+
+		set_pmd_at(mm, addr, pmd, orig_pmd);
+		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+	}
+	ret = 1;
+out:
+	spin_unlock(ptl);
+out_unlocked:
+	return ret;
+}
+
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
 	pmd_t orig_pmd;
 	spinlock_t *ptl;
 
-	if (__pmd_trans_huge_lock(pmd, vma, &ptl) != 1)
+	if (!__pmd_trans_huge_lock(pmd, vma, &ptl))
 		return 0;
 	/*
 	 * For architectures like ppc64 we look at deposited pgtable
@@ -1508,7 +1649,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		put_huge_zero_page();
 	} else {
 		struct page *page = pmd_page(orig_pmd);
-		page_remove_rmap(page);
+		page_remove_rmap(page, true);
 		VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
 		add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
 		VM_BUG_ON_PAGE(!PageHead(page), page);
@@ -1520,13 +1661,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	return 1;
 }
 
-int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
+bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		  unsigned long old_addr,
 		  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;
 
 	struct mm_struct *mm = vma->vm_mm;
@@ -1535,7 +1675,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 	    (new_addr & ~HPAGE_PMD_MASK) ||
 	    old_end - old_addr < HPAGE_PMD_SIZE ||
 	    (new_vma->vm_flags & VM_NOHUGEPAGE))
-		goto out;
+		return false;
 
 	/*
 	 * The destination pmd shouldn't be established, free_pgtables()
@@ -1543,15 +1683,14 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 	 */
 	if (WARN_ON(!pmd_none(*new_pmd))) {
 		VM_BUG_ON(pmd_trans_huge(*new_pmd));
-		goto out;
+		return false;
 	}
 
 	/*
 	 * 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) {
+	if (__pmd_trans_huge_lock(old_pmd, vma, &old_ptl)) {
 		new_ptl = pmd_lockptr(mm, new_pmd);
 		if (new_ptl != old_ptl)
 			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
@@ -1567,9 +1706,9 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		if (new_ptl != old_ptl)
 			spin_unlock(new_ptl);
 		spin_unlock(old_ptl);
+		return true;
 	}
-out:
-	return ret;
+	return false;
 }
 
 /*
@@ -1585,7 +1724,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		pmd_t entry;
 		bool preserve_write = prot_numa && pmd_write(*pmd);
 		ret = 1;
@@ -1616,405 +1755,19 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 }
 
 /*
- * Returns 1 if a given pmd maps a stable (not under splitting) thp.
- * Returns -1 if it maps a thp under splitting. Returns 0 otherwise.
+ * Returns true if a given pmd maps a thp, false otherwise.
  *
- * Note that if it returns 1, this routine returns without unlocking page
- * table locks. So callers must unlock them.
+ * Note that if it returns true, this routine returns without unlocking page
+ * table lock. So callers must unlock it.
  */
-int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 		spinlock_t **ptl)
 {
 	*ptl = pmd_lock(vma->vm_mm, pmd);
-	if (likely(pmd_trans_huge(*pmd))) {
-		if (unlikely(pmd_trans_splitting(*pmd))) {
-			spin_unlock(*ptl);
-			wait_split_huge_page(vma->anon_vma, pmd);
-			return -1;
-		} else {
-			/* Thp mapped by 'pmd' is stable, so we can
-			 * handle it as it is. */
-			return 1;
-		}
-	}
-	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,
-			      spinlock_t **ptl)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-
-	if (address & ~HPAGE_PMD_MASK)
-		return NULL;
-
-	pgd = pgd_offset(mm, address);
-	if (!pgd_present(*pgd))
-		return NULL;
-	pud = pud_offset(pgd, address);
-	if (!pud_present(*pud))
-		return NULL;
-	pmd = pmd_offset(pud, address);
-
-	*ptl = pmd_lock(mm, pmd);
-	if (!pmd_present(*pmd))
-		goto unlock;
-	if (pmd_page(*pmd) != page)
-		goto unlock;
-	/*
-	 * split_vma() may create temporary aliased mappings. There is
-	 * no risk as long as all huge pmd are found and have their
-	 * splitting bit set before __split_huge_page_refcount
-	 * runs. Finding the same huge pmd more than once during the
-	 * same rmap walk is not a problem.
-	 */
-	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
-	    pmd_trans_splitting(*pmd))
-		goto unlock;
-	if (pmd_trans_huge(*pmd)) {
-		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
-			  !pmd_trans_splitting(*pmd));
-		return pmd;
-	}
-unlock:
+	if (likely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
+		return true;
 	spin_unlock(*ptl);
-	return NULL;
-}
-
-static int __split_huge_page_splitting(struct page *page,
-				       struct vm_area_struct *vma,
-				       unsigned long address)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	spinlock_t *ptl;
-	pmd_t *pmd;
-	int ret = 0;
-	/* For mmu_notifiers */
-	const unsigned long mmun_start = address;
-	const unsigned long mmun_end   = address + HPAGE_PMD_SIZE;
-
-	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-	pmd = page_check_address_pmd(page, mm, address,
-			PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, &ptl);
-	if (pmd) {
-		/*
-		 * We can't temporarily set the pmd to null in order
-		 * to split it, the pmd must remain marked huge at all
-		 * times or the VM won't take the pmd_trans_huge paths
-		 * and it won't wait on the anon_vma->root->rwsem to
-		 * serialize against split_huge_page*.
-		 */
-		pmdp_splitting_flush(vma, address, pmd);
-
-		ret = 1;
-		spin_unlock(ptl);
-	}
-	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-
-	return ret;
-}
-
-static void __split_huge_page_refcount(struct page *page,
-				       struct list_head *list)
-{
-	int i;
-	struct zone *zone = page_zone(page);
-	struct lruvec *lruvec;
-	int tail_count = 0;
-
-	/* prevent PageLRU to go away from under us, and freeze lru stats */
-	spin_lock_irq(&zone->lru_lock);
-	lruvec = mem_cgroup_page_lruvec(page, zone);
-
-	compound_lock(page);
-	/* complete memcg works before add pages to LRU */
-	mem_cgroup_split_huge_fixup(page);
-
-	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
-		struct page *page_tail = page + i;
-
-		/* tail_page->_mapcount cannot change */
-		BUG_ON(page_mapcount(page_tail) < 0);
-		tail_count += page_mapcount(page_tail);
-		/* check for overflow */
-		BUG_ON(tail_count < 0);
-		BUG_ON(atomic_read(&page_tail->_count) != 0);
-		/*
-		 * tail_page->_count is zero and not changing from
-		 * under us. But get_page_unless_zero() may be running
-		 * from under us on the tail_page. If we used
-		 * atomic_set() below instead of atomic_add(), we
-		 * would then run atomic_set() concurrently with
-		 * get_page_unless_zero(), and atomic_set() is
-		 * implemented in C not using locked ops. spin_unlock
-		 * on x86 sometime uses locked ops because of PPro
-		 * errata 66, 92, so unless somebody can guarantee
-		 * atomic_set() here would be safe on all archs (and
-		 * not only on x86), it's safer to use atomic_add().
-		 */
-		atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1,
-			   &page_tail->_count);
-
-		/* after clearing PageTail the gup refcount can be released */
-		smp_mb__after_atomic();
-
-		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
-		page_tail->flags |= (page->flags &
-				     ((1L << PG_referenced) |
-				      (1L << PG_swapbacked) |
-				      (1L << PG_mlocked) |
-				      (1L << PG_uptodate) |
-				      (1L << PG_active) |
-				      (1L << PG_unevictable)));
-		page_tail->flags |= (1L << PG_dirty);
-
-		clear_compound_head(page_tail);
-
-		if (page_is_young(page))
-			set_page_young(page_tail);
-		if (page_is_idle(page))
-			set_page_idle(page_tail);
-
-		/*
-		 * __split_huge_page_splitting() already set the
-		 * splitting bit in all pmd that could map this
-		 * hugepage, that will ensure no CPU can alter the
-		 * mapcount on the head page. The mapcount is only
-		 * accounted in the head page and it has to be
-		 * transferred to all tail pages in the below code. So
-		 * for this code to be safe, the split the mapcount
-		 * can't change. But that doesn't mean userland can't
-		 * keep changing and reading the page contents while
-		 * we transfer the mapcount, so the pmd splitting
-		 * status is achieved setting a reserved bit in the
-		 * pmd, not by clearing the present bit.
-		*/
-		page_tail->_mapcount = page->_mapcount;
-
-		BUG_ON(page_tail->mapping);
-		page_tail->mapping = page->mapping;
-
-		page_tail->index = page->index + i;
-		page_cpupid_xchg_last(page_tail, page_cpupid_last(page));
-
-		BUG_ON(!PageAnon(page_tail));
-		BUG_ON(!PageUptodate(page_tail));
-		BUG_ON(!PageDirty(page_tail));
-		BUG_ON(!PageSwapBacked(page_tail));
-
-		lru_add_page_tail(page, page_tail, lruvec, list);
-	}
-	atomic_sub(tail_count, &page->_count);
-	BUG_ON(atomic_read(&page->_count) <= 0);
-
-	__mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1);
-
-	ClearPageCompound(page);
-	compound_unlock(page);
-	spin_unlock_irq(&zone->lru_lock);
-
-	for (i = 1; i < HPAGE_PMD_NR; i++) {
-		struct page *page_tail = page + i;
-		BUG_ON(page_count(page_tail) <= 0);
-		/*
-		 * Tail pages may be freed if there wasn't any mapping
-		 * like if add_to_swap() is running on a lru page that
-		 * had its mapping zapped. And freeing these pages
-		 * requires taking the lru_lock so we do the put_page
-		 * of the tail pages after the split is complete.
-		 */
-		put_page(page_tail);
-	}
-
-	/*
-	 * Only the head page (now become a regular page) is required
-	 * to be pinned by the caller.
-	 */
-	BUG_ON(page_count(page) <= 0);
-}
-
-static int __split_huge_page_map(struct page *page,
-				 struct vm_area_struct *vma,
-				 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;
-
-	pmd = page_check_address_pmd(page, mm, address,
-			PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, &ptl);
-	if (pmd) {
-		pgtable = pgtable_trans_huge_withdraw(mm, pmd);
-		pmd_populate(mm, &_pmd, pgtable);
-		if (pmd_write(*pmd))
-			BUG_ON(page_mapcount(page) != 1);
-
-		haddr = address;
-		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
-			pte_t *pte, entry;
-			BUG_ON(PageCompound(page+i));
-			/*
-			 * Note that NUMA hinting access restrictions are not
-			 * transferred to avoid any possibility of altering
-			 * permissions across VMAs.
-			 */
-			entry = mk_pte(page + i, vma->vm_page_prot);
-			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-			if (!pmd_write(*pmd))
-				entry = pte_wrprotect(entry);
-			if (!pmd_young(*pmd))
-				entry = pte_mkold(entry);
-			pte = pte_offset_map(&_pmd, haddr);
-			BUG_ON(!pte_none(*pte));
-			set_pte_at(mm, haddr, pte, entry);
-			pte_unmap(pte);
-		}
-
-		smp_wmb(); /* make pte visible before pmd */
-		/*
-		 * Up to this point the pmd is present and huge and
-		 * userland has the whole access to the hugepage
-		 * during the split (which happens in place). If we
-		 * overwrite the pmd with the not-huge version
-		 * pointing to the pte here (which of course we could
-		 * if all CPUs were bug free), userland could trigger
-		 * a small page size TLB miss on the small sized TLB
-		 * while the hugepage TLB entry is still established
-		 * in the huge TLB. Some CPU doesn't like that. See
-		 * http://support.amd.com/us/Processor_TechDocs/41322.pdf,
-		 * Erratum 383 on page 93. Intel should be safe but is
-		 * also warns that it's only safe if the permission
-		 * and cache attributes of the two entries loaded in
-		 * the two TLB is identical (which should be the case
-		 * here). But it is generally safer to never allow
-		 * small and huge TLB entries for the same virtual
-		 * address to be loaded simultaneously. So instead of
-		 * doing "pmd_populate(); flush_pmd_tlb_range();" we first
-		 * mark the current pmd notpresent (atomically because
-		 * here the pmd_trans_huge and pmd_trans_splitting
-		 * must remain set at all times on the pmd until the
-		 * split is complete for this pmd), then we flush the
-		 * SMP TLB and finally we write the non-huge version
-		 * of the pmd entry with pmd_populate.
-		 */
-		pmdp_invalidate(vma, address, pmd);
-		pmd_populate(mm, pmd, pgtable);
-		ret = 1;
-		spin_unlock(ptl);
-	}
-
-	return ret;
-}
-
-/* must be called with anon_vma->root->rwsem held */
-static void __split_huge_page(struct page *page,
-			      struct anon_vma *anon_vma,
-			      struct list_head *list)
-{
-	int mapcount, mapcount2;
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-	struct anon_vma_chain *avc;
-
-	BUG_ON(!PageHead(page));
-	BUG_ON(PageTail(page));
-
-	mapcount = 0;
-	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
-		struct vm_area_struct *vma = avc->vma;
-		unsigned long addr = vma_address(page, vma);
-		BUG_ON(is_vma_temporary_stack(vma));
-		mapcount += __split_huge_page_splitting(page, vma, addr);
-	}
-	/*
-	 * It is critical that new vmas are added to the tail of the
-	 * anon_vma list. This guarantes that if copy_huge_pmd() runs
-	 * and establishes a child pmd before
-	 * __split_huge_page_splitting() freezes the parent pmd (so if
-	 * we fail to prevent copy_huge_pmd() from running until the
-	 * whole __split_huge_page() is complete), we will still see
-	 * the newly established pmd of the child later during the
-	 * walk, to be able to set it as pmd_trans_splitting too.
-	 */
-	if (mapcount != page_mapcount(page)) {
-		pr_err("mapcount %d page_mapcount %d\n",
-			mapcount, page_mapcount(page));
-		BUG();
-	}
-
-	__split_huge_page_refcount(page, list);
-
-	mapcount2 = 0;
-	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
-		struct vm_area_struct *vma = avc->vma;
-		unsigned long addr = vma_address(page, vma);
-		BUG_ON(is_vma_temporary_stack(vma));
-		mapcount2 += __split_huge_page_map(page, vma, addr);
-	}
-	if (mapcount != mapcount2) {
-		pr_err("mapcount %d mapcount2 %d page_mapcount %d\n",
-			mapcount, mapcount2, page_mapcount(page));
-		BUG();
-	}
-}
-
-/*
- * Split a hugepage into normal pages. This doesn't change the position of head
- * page. If @list is null, tail pages will be added to LRU list, otherwise, to
- * @list. Both head page and tail pages will inherit mapping, flags, and so on
- * from the hugepage.
- * Return 0 if the hugepage is split successfully otherwise return 1.
- */
-int split_huge_page_to_list(struct page *page, struct list_head *list)
-{
-	struct anon_vma *anon_vma;
-	int ret = 1;
-
-	BUG_ON(is_huge_zero_page(page));
-	BUG_ON(!PageAnon(page));
-
-	/*
-	 * The caller does not necessarily hold an mmap_sem that would prevent
-	 * the anon_vma disappearing so we first we take a reference to it
-	 * and then lock the anon_vma for write. This is similar to
-	 * page_lock_anon_vma_read except the write lock is taken to serialise
-	 * against parallel split or collapse operations.
-	 */
-	anon_vma = page_get_anon_vma(page);
-	if (!anon_vma)
-		goto out;
-	anon_vma_lock_write(anon_vma);
-
-	ret = 0;
-	if (!PageCompound(page))
-		goto out_unlock;
-
-	BUG_ON(!PageSwapBacked(page));
-	__split_huge_page(page, anon_vma, list);
-	count_vm_event(THP_SPLIT);
-
-	BUG_ON(PageCompound(page));
-out_unlock:
-	anon_vma_unlock_write(anon_vma);
-	put_anon_vma(anon_vma);
-out:
-	return ret;
+	return false;
 }
 
 #define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
@@ -2371,7 +2124,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 			 * superfluous.
 			 */
 			pte_clear(vma->vm_mm, address, _pte);
-			page_remove_rmap(src_page);
+			page_remove_rmap(src_page, false);
 			spin_unlock(ptl);
 			free_page_and_swap_cache(src_page);
 		}
@@ -2481,6 +2234,7 @@ khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm,
 		return NULL;
 	}
 
+	prep_transhuge_page(*hpage);
 	count_vm_event(THP_COLLAPSE_ALLOC);
 	return *hpage;
 }
@@ -2492,8 +2246,12 @@ static int khugepaged_find_target_node(void)
 
 static inline struct page *alloc_hugepage(int defrag)
 {
-	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
-			   HPAGE_PMD_ORDER);
+	struct page *page;
+
+	page = alloc_pages(alloc_hugepage_gfpmask(defrag, 0), HPAGE_PMD_ORDER);
+	if (page)
+		prep_transhuge_page(page);
+	return page;
 }
 
 static struct page *khugepaged_alloc_hugepage(bool *wait)
@@ -2543,7 +2301,6 @@ static bool hugepage_vma_check(struct vm_area_struct *vma)
 	if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
 	    (vma->vm_flags & VM_NOHUGEPAGE))
 		return false;
-
 	if (!vma->anon_vma || vma->vm_ops)
 		return false;
 	if (is_vma_temporary_stack(vma))
@@ -2583,7 +2340,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 		goto out_nolock;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) {
+	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out_nolock;
 	}
@@ -2682,8 +2439,8 @@ static void collapse_huge_page(struct mm_struct *mm,
 
 	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
-	page_add_new_anon_rmap(new_page, vma, address);
-	mem_cgroup_commit_charge(new_page, memcg, false);
+	page_add_new_anon_rmap(new_page, vma, address, true);
+	mem_cgroup_commit_charge(new_page, memcg, false, true);
 	lru_cache_add_active_or_unevictable(new_page, vma);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
@@ -2703,7 +2460,7 @@ out_nolock:
 	trace_mm_collapse_huge_page(mm, isolated, result);
 	return;
 out:
-	mem_cgroup_cancel_charge(new_page, memcg);
+	mem_cgroup_cancel_charge(new_page, memcg, true);
 	goto out_up_write;
 }
 
@@ -2755,6 +2512,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 			result = SCAN_PAGE_NULL;
 			goto out_unmap;
 		}
+
+		/* TODO: teach khugepaged to collapse THP mapped with pte */
+		if (PageCompound(page)) {
+			result = SCAN_PAGE_COMPOUND;
+			goto out_unmap;
+		}
+
 		/*
 		 * Record which node the original page is from and save this
 		 * information to khugepaged_node_load[].
@@ -2767,7 +2531,6 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 			goto out_unmap;
 		}
 		khugepaged_node_load[node]++;
-		VM_BUG_ON_PAGE(PageCompound(page), page);
 		if (!PageLRU(page)) {
 			result = SCAN_SCAN_ABORT;
 			goto out_unmap;
@@ -3040,8 +2803,8 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 	pmd_t _pmd;
 	int i;
 
-	pmdp_huge_clear_flush_notify(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
+	pmdp_huge_clear_flush_notify(vma, haddr, pmd);
 
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
@@ -3060,66 +2823,153 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 	put_huge_zero_page();
 }
 
-void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd)
+static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
+		unsigned long haddr, bool freeze)
 {
-	spinlock_t *ptl;
-	struct page *page = NULL;
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long haddr = address & HPAGE_PMD_MASK;
-	unsigned long mmun_start;	/* For mmu_notifiers */
-	unsigned long mmun_end;		/* For mmu_notifiers */
+	struct page *page;
+	pgtable_t pgtable;
+	pmd_t _pmd;
+	bool young, write, dirty;
+	int i;
 
-	BUG_ON(vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE);
+	VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
+	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
+	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
+	VM_BUG_ON(!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd));
+
+	count_vm_event(THP_SPLIT_PMD);
 
-	mmun_start = haddr;
-	mmun_end   = haddr + HPAGE_PMD_SIZE;
-again:
-	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-	ptl = pmd_lock(mm, pmd);
-	if (unlikely(!pmd_trans_huge(*pmd)))
-		goto unlock;
 	if (vma_is_dax(vma)) {
 		pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
 		if (is_huge_zero_pmd(_pmd))
 			put_huge_zero_page();
+		return;
 	} else if (is_huge_zero_pmd(*pmd)) {
-		__split_huge_zero_page_pmd(vma, haddr, pmd);
-	} else {
-		page = pmd_page(*pmd);
-		VM_BUG_ON_PAGE(!page_count(page), page);
-		get_page(page);
+		return __split_huge_zero_page_pmd(vma, haddr, pmd);
 	}
- unlock:
-	spin_unlock(ptl);
-	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
-	if (!page)
-		return;
+	page = pmd_page(*pmd);
+	VM_BUG_ON_PAGE(!page_count(page), page);
+	atomic_add(HPAGE_PMD_NR - 1, &page->_count);
+	write = pmd_write(*pmd);
+	young = pmd_young(*pmd);
+	dirty = pmd_dirty(*pmd);
 
-	split_huge_page(page);
-	put_page(page);
+	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+	pmd_populate(mm, &_pmd, pgtable);
 
+	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+		pte_t entry, *pte;
+		/*
+		 * Note that NUMA hinting access restrictions are not
+		 * transferred to avoid any possibility of altering
+		 * permissions across VMAs.
+		 */
+		if (freeze) {
+			swp_entry_t swp_entry;
+			swp_entry = make_migration_entry(page + i, write);
+			entry = swp_entry_to_pte(swp_entry);
+		} else {
+			entry = mk_pte(page + i, vma->vm_page_prot);
+			entry = maybe_mkwrite(entry, vma);
+			if (!write)
+				entry = pte_wrprotect(entry);
+			if (!young)
+				entry = pte_mkold(entry);
+		}
+		if (dirty)
+			SetPageDirty(page + i);
+		pte = pte_offset_map(&_pmd, haddr);
+		BUG_ON(!pte_none(*pte));
+		set_pte_at(mm, haddr, pte, entry);
+		atomic_inc(&page[i]._mapcount);
+		pte_unmap(pte);
+	}
+
+	/*
+	 * Set PG_double_map before dropping compound_mapcount to avoid
+	 * false-negative page_mapped().
+	 */
+	if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
+		for (i = 0; i < HPAGE_PMD_NR; i++)
+			atomic_inc(&page[i]._mapcount);
+	}
+
+	if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+		/* Last compound_mapcount is gone. */
+		__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
+		if (TestClearPageDoubleMap(page)) {
+			/* No need in mapcount reference anymore */
+			for (i = 0; i < HPAGE_PMD_NR; i++)
+				atomic_dec(&page[i]._mapcount);
+		}
+	}
+
+	smp_wmb(); /* make pte visible before 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.
+	 * Up to this point the pmd is present and huge and userland has the
+	 * whole access to the hugepage during the split (which happens in
+	 * place). If we overwrite the pmd with the not-huge version pointing
+	 * to the pte here (which of course we could if all CPUs were bug
+	 * free), userland could trigger a small page size TLB miss on the
+	 * small sized TLB while the hugepage TLB entry is still established in
+	 * the huge TLB. Some CPU doesn't like that.
+	 * See http://support.amd.com/us/Processor_TechDocs/41322.pdf, Erratum
+	 * 383 on page 93. Intel should be safe but is also warns that it's
+	 * only safe if the permission and cache attributes of the two entries
+	 * loaded in the two TLB is identical (which should be the case here).
+	 * But it is generally safer to never allow small and huge TLB entries
+	 * for the same virtual address to be loaded simultaneously. So instead
+	 * of doing "pmd_populate(); flush_pmd_tlb_range();" we first mark the
+	 * current pmd notpresent (atomically because here the pmd_trans_huge
+	 * and pmd_trans_splitting must remain set at all times on the pmd
+	 * until the split is complete for this pmd), then we flush the SMP TLB
+	 * and finally we write the non-huge version of the pmd entry with
+	 * pmd_populate.
 	 */
-	if (unlikely(pmd_trans_huge(*pmd)))
-		goto again;
+	pmdp_invalidate(vma, haddr, pmd);
+	pmd_populate(mm, pmd, pgtable);
+
+	if (freeze) {
+		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+			page_remove_rmap(page + i, false);
+			put_page(page + i);
+		}
+	}
 }
 
-void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd)
+void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+		unsigned long address)
 {
-	struct vm_area_struct *vma;
+	spinlock_t *ptl;
+	struct mm_struct *mm = vma->vm_mm;
+	struct page *page = NULL;
+	unsigned long haddr = address & HPAGE_PMD_MASK;
 
-	vma = find_vma(mm, address);
-	BUG_ON(vma == NULL);
-	split_huge_page_pmd(vma, address, pmd);
+	mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
+	ptl = pmd_lock(mm, pmd);
+	if (pmd_trans_huge(*pmd)) {
+		page = pmd_page(*pmd);
+		if (PageMlocked(page))
+			get_page(page);
+		else
+			page = NULL;
+	} else if (!pmd_devmap(*pmd))
+		goto out;
+	__split_huge_pmd_locked(vma, pmd, haddr, false);
+out:
+	spin_unlock(ptl);
+	mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE);
+	if (page) {
+		lock_page(page);
+		munlock_vma_page(page);
+		unlock_page(page);
+		put_page(page);
+	}
 }
 
-static void split_huge_page_address(struct mm_struct *mm,
+static void split_huge_pmd_address(struct vm_area_struct *vma,
 				    unsigned long address)
 {
 	pgd_t *pgd;
@@ -3128,7 +2978,7 @@ static void split_huge_page_address(struct mm_struct *mm,
 
 	VM_BUG_ON(!(address & ~HPAGE_PMD_MASK));
 
-	pgd = pgd_offset(mm, address);
+	pgd = pgd_offset(vma->vm_mm, address);
 	if (!pgd_present(*pgd))
 		return;
 
@@ -3137,13 +2987,13 @@ static void split_huge_page_address(struct mm_struct *mm,
 		return;
 
 	pmd = pmd_offset(pud, address);
-	if (!pmd_present(*pmd))
+	if (!pmd_present(*pmd) || (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)))
 		return;
 	/*
 	 * Caller holds the mmap_sem write mode, so a huge pmd cannot
 	 * materialize from under us.
 	 */
-	split_huge_page_pmd_mm(mm, address, pmd);
+	split_huge_pmd(vma, pmd, address);
 }
 
 void vma_adjust_trans_huge(struct vm_area_struct *vma,
@@ -3159,7 +3009,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 	if (start & ~HPAGE_PMD_MASK &&
 	    (start & HPAGE_PMD_MASK) >= vma->vm_start &&
 	    (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
-		split_huge_page_address(vma->vm_mm, start);
+		split_huge_pmd_address(vma, start);
 
 	/*
 	 * If the new end address isn't hpage aligned and it could
@@ -3169,7 +3019,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 	if (end & ~HPAGE_PMD_MASK &&
 	    (end & HPAGE_PMD_MASK) >= vma->vm_start &&
 	    (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
-		split_huge_page_address(vma->vm_mm, end);
+		split_huge_pmd_address(vma, end);
 
 	/*
 	 * If we're also updating the vma->vm_next->vm_start, if the new
@@ -3183,6 +3033,540 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 		if (nstart & ~HPAGE_PMD_MASK &&
 		    (nstart & HPAGE_PMD_MASK) >= next->vm_start &&
 		    (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end)
-			split_huge_page_address(next->vm_mm, nstart);
+			split_huge_pmd_address(next, nstart);
+	}
+}
+
+static void freeze_page_vma(struct vm_area_struct *vma, struct page *page,
+		unsigned long address)
+{
+	unsigned long haddr = address & HPAGE_PMD_MASK;
+	spinlock_t *ptl;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	int i, nr = HPAGE_PMD_NR;
+
+	/* Skip pages which doesn't belong to the VMA */
+	if (address < vma->vm_start) {
+		int off = (vma->vm_start - address) >> PAGE_SHIFT;
+		page += off;
+		nr -= off;
+		address = vma->vm_start;
+	}
+
+	pgd = pgd_offset(vma->vm_mm, address);
+	if (!pgd_present(*pgd))
+		return;
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		return;
+	pmd = pmd_offset(pud, address);
+	ptl = pmd_lock(vma->vm_mm, pmd);
+	if (!pmd_present(*pmd)) {
+		spin_unlock(ptl);
+		return;
+	}
+	if (pmd_trans_huge(*pmd)) {
+		if (page == pmd_page(*pmd))
+			__split_huge_pmd_locked(vma, pmd, haddr, true);
+		spin_unlock(ptl);
+		return;
+	}
+	spin_unlock(ptl);
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, address, &ptl);
+	for (i = 0; i < nr; i++, address += PAGE_SIZE, page++, pte++) {
+		pte_t entry, swp_pte;
+		swp_entry_t swp_entry;
+
+		/*
+		 * We've just crossed page table boundary: need to map next one.
+		 * It can happen if THP was mremaped to non PMD-aligned address.
+		 */
+		if (unlikely(address == haddr + HPAGE_PMD_SIZE)) {
+			pte_unmap_unlock(pte - 1, ptl);
+			pmd = mm_find_pmd(vma->vm_mm, address);
+			if (!pmd)
+				return;
+			pte = pte_offset_map_lock(vma->vm_mm, pmd,
+					address, &ptl);
+		}
+
+		if (!pte_present(*pte))
+			continue;
+		if (page_to_pfn(page) != pte_pfn(*pte))
+			continue;
+		flush_cache_page(vma, address, page_to_pfn(page));
+		entry = ptep_clear_flush(vma, address, pte);
+		if (pte_dirty(entry))
+			SetPageDirty(page);
+		swp_entry = make_migration_entry(page, pte_write(entry));
+		swp_pte = swp_entry_to_pte(swp_entry);
+		if (pte_soft_dirty(entry))
+			swp_pte = pte_swp_mksoft_dirty(swp_pte);
+		set_pte_at(vma->vm_mm, address, pte, swp_pte);
+		page_remove_rmap(page, false);
+		put_page(page);
+	}
+	pte_unmap_unlock(pte - 1, ptl);
+}
+
+static void freeze_page(struct anon_vma *anon_vma, struct page *page)
+{
+	struct anon_vma_chain *avc;
+	pgoff_t pgoff = page_to_pgoff(page);
+
+	VM_BUG_ON_PAGE(!PageHead(page), page);
+
+	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff,
+			pgoff + HPAGE_PMD_NR - 1) {
+		unsigned long address = __vma_address(page, avc->vma);
+
+		mmu_notifier_invalidate_range_start(avc->vma->vm_mm,
+				address, address + HPAGE_PMD_SIZE);
+		freeze_page_vma(avc->vma, page, address);
+		mmu_notifier_invalidate_range_end(avc->vma->vm_mm,
+				address, address + HPAGE_PMD_SIZE);
+	}
+}
+
+static void unfreeze_page_vma(struct vm_area_struct *vma, struct page *page,
+		unsigned long address)
+{
+	spinlock_t *ptl;
+	pmd_t *pmd;
+	pte_t *pte, entry;
+	swp_entry_t swp_entry;
+	unsigned long haddr = address & HPAGE_PMD_MASK;
+	int i, nr = HPAGE_PMD_NR;
+
+	/* Skip pages which doesn't belong to the VMA */
+	if (address < vma->vm_start) {
+		int off = (vma->vm_start - address) >> PAGE_SHIFT;
+		page += off;
+		nr -= off;
+		address = vma->vm_start;
+	}
+
+	pmd = mm_find_pmd(vma->vm_mm, address);
+	if (!pmd)
+		return;
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, address, &ptl);
+	for (i = 0; i < nr; i++, address += PAGE_SIZE, page++, pte++) {
+		/*
+		 * We've just crossed page table boundary: need to map next one.
+		 * It can happen if THP was mremaped to non-PMD aligned address.
+		 */
+		if (unlikely(address == haddr + HPAGE_PMD_SIZE)) {
+			pte_unmap_unlock(pte - 1, ptl);
+			pmd = mm_find_pmd(vma->vm_mm, address);
+			if (!pmd)
+				return;
+			pte = pte_offset_map_lock(vma->vm_mm, pmd,
+					address, &ptl);
+		}
+
+		if (!is_swap_pte(*pte))
+			continue;
+
+		swp_entry = pte_to_swp_entry(*pte);
+		if (!is_migration_entry(swp_entry))
+			continue;
+		if (migration_entry_to_page(swp_entry) != page)
+			continue;
+
+		get_page(page);
+		page_add_anon_rmap(page, vma, address, false);
+
+		entry = pte_mkold(mk_pte(page, vma->vm_page_prot));
+		if (PageDirty(page))
+			entry = pte_mkdirty(entry);
+		if (is_write_migration_entry(swp_entry))
+			entry = maybe_mkwrite(entry, vma);
+
+		flush_dcache_page(page);
+		set_pte_at(vma->vm_mm, address, pte, entry);
+
+		/* No need to invalidate - it was non-present before */
+		update_mmu_cache(vma, address, pte);
+	}
+	pte_unmap_unlock(pte - 1, ptl);
+}
+
+static void unfreeze_page(struct anon_vma *anon_vma, struct page *page)
+{
+	struct anon_vma_chain *avc;
+	pgoff_t pgoff = page_to_pgoff(page);
+
+	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
+			pgoff, pgoff + HPAGE_PMD_NR - 1) {
+		unsigned long address = __vma_address(page, avc->vma);
+
+		mmu_notifier_invalidate_range_start(avc->vma->vm_mm,
+				address, address + HPAGE_PMD_SIZE);
+		unfreeze_page_vma(avc->vma, page, address);
+		mmu_notifier_invalidate_range_end(avc->vma->vm_mm,
+				address, address + HPAGE_PMD_SIZE);
+	}
+}
+
+static int __split_huge_page_tail(struct page *head, int tail,
+		struct lruvec *lruvec, struct list_head *list)
+{
+	int mapcount;
+	struct page *page_tail = head + tail;
+
+	mapcount = atomic_read(&page_tail->_mapcount) + 1;
+	VM_BUG_ON_PAGE(atomic_read(&page_tail->_count) != 0, page_tail);
+
+	/*
+	 * tail_page->_count is zero and not changing from under us. But
+	 * get_page_unless_zero() may be running from under us on the
+	 * tail_page. If we used atomic_set() below instead of atomic_add(), we
+	 * would then run atomic_set() concurrently with
+	 * get_page_unless_zero(), and atomic_set() is implemented in C not
+	 * using locked ops. spin_unlock on x86 sometime uses locked ops
+	 * because of PPro errata 66, 92, so unless somebody can guarantee
+	 * atomic_set() here would be safe on all archs (and not only on x86),
+	 * it's safer to use atomic_add().
+	 */
+	atomic_add(mapcount + 1, &page_tail->_count);
+
+
+	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
+	page_tail->flags |= (head->flags &
+			((1L << PG_referenced) |
+			 (1L << PG_swapbacked) |
+			 (1L << PG_mlocked) |
+			 (1L << PG_uptodate) |
+			 (1L << PG_active) |
+			 (1L << PG_locked) |
+			 (1L << PG_unevictable) |
+			 (1L << PG_dirty)));
+
+	/*
+	 * After clearing PageTail the gup refcount can be released.
+	 * Page flags also must be visible before we make the page non-compound.
+	 */
+	smp_wmb();
+
+	clear_compound_head(page_tail);
+
+	if (page_is_young(head))
+		set_page_young(page_tail);
+	if (page_is_idle(head))
+		set_page_idle(page_tail);
+
+	/* ->mapping in first tail page is compound_mapcount */
+	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
+			page_tail);
+	page_tail->mapping = head->mapping;
+
+	page_tail->index = head->index + tail;
+	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
+	lru_add_page_tail(head, page_tail, lruvec, list);
+
+	return mapcount;
+}
+
+static void __split_huge_page(struct page *page, struct list_head *list)
+{
+	struct page *head = compound_head(page);
+	struct zone *zone = page_zone(head);
+	struct lruvec *lruvec;
+	int i, tail_mapcount;
+
+	/* prevent PageLRU to go away from under us, and freeze lru stats */
+	spin_lock_irq(&zone->lru_lock);
+	lruvec = mem_cgroup_page_lruvec(head, zone);
+
+	/* complete memcg works before add pages to LRU */
+	mem_cgroup_split_huge_fixup(head);
+
+	tail_mapcount = 0;
+	for (i = HPAGE_PMD_NR - 1; i >= 1; i--)
+		tail_mapcount += __split_huge_page_tail(head, i, lruvec, list);
+	atomic_sub(tail_mapcount, &head->_count);
+
+	ClearPageCompound(head);
+	spin_unlock_irq(&zone->lru_lock);
+
+	unfreeze_page(page_anon_vma(head), head);
+
+	for (i = 0; i < HPAGE_PMD_NR; i++) {
+		struct page *subpage = head + i;
+		if (subpage == page)
+			continue;
+		unlock_page(subpage);
+
+		/*
+		 * Subpages may be freed if there wasn't any mapping
+		 * like if add_to_swap() is running on a lru page that
+		 * had its mapping zapped. And freeing these pages
+		 * requires taking the lru_lock so we do the put_page
+		 * of the tail pages after the split is complete.
+		 */
+		put_page(subpage);
 	}
 }
+
+int total_mapcount(struct page *page)
+{
+	int i, ret;
+
+	VM_BUG_ON_PAGE(PageTail(page), page);
+
+	if (likely(!PageCompound(page)))
+		return atomic_read(&page->_mapcount) + 1;
+
+	ret = compound_mapcount(page);
+	if (PageHuge(page))
+		return ret;
+	for (i = 0; i < HPAGE_PMD_NR; i++)
+		ret += atomic_read(&page[i]._mapcount) + 1;
+	if (PageDoubleMap(page))
+		ret -= HPAGE_PMD_NR;
+	return ret;
+}
+
+/*
+ * This function splits huge page into normal pages. @page can point to any
+ * subpage of huge page to split. Split doesn't change the position of @page.
+ *
+ * Only caller must hold pin on the @page, otherwise split fails with -EBUSY.
+ * The huge page must be locked.
+ *
+ * If @list is null, tail pages will be added to LRU list, otherwise, to @list.
+ *
+ * Both head page and tail pages will inherit mapping, flags, and so on from
+ * the hugepage.
+ *
+ * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if
+ * they are not mapped.
+ *
+ * Returns 0 if the hugepage is split successfully.
+ * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under
+ * us.
+ */
+int split_huge_page_to_list(struct page *page, struct list_head *list)
+{
+	struct page *head = compound_head(page);
+	struct anon_vma *anon_vma;
+	int count, mapcount, ret;
+	bool mlocked;
+
+	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
+	VM_BUG_ON_PAGE(!PageAnon(page), page);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
+	VM_BUG_ON_PAGE(!PageCompound(page), page);
+
+	/*
+	 * The caller does not necessarily hold an mmap_sem that would prevent
+	 * the anon_vma disappearing so we first we take a reference to it
+	 * and then lock the anon_vma for write. This is similar to
+	 * page_lock_anon_vma_read except the write lock is taken to serialise
+	 * against parallel split or collapse operations.
+	 */
+	anon_vma = page_get_anon_vma(head);
+	if (!anon_vma) {
+		ret = -EBUSY;
+		goto out;
+	}
+	anon_vma_lock_write(anon_vma);
+
+	/*
+	 * Racy check if we can split the page, before freeze_page() will
+	 * split PMDs
+	 */
+	if (total_mapcount(head) != page_count(head) - 1) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	mlocked = PageMlocked(page);
+	freeze_page(anon_vma, head);
+	VM_BUG_ON_PAGE(compound_mapcount(head), head);
+
+	/* Make sure the page is not on per-CPU pagevec as it takes pin */
+	if (mlocked)
+		lru_add_drain();
+
+	/* Prevent deferred_split_scan() touching ->_count */
+	spin_lock(&split_queue_lock);
+	count = page_count(head);
+	mapcount = total_mapcount(head);
+	if (!mapcount && count == 1) {
+		if (!list_empty(page_deferred_list(head))) {
+			split_queue_len--;
+			list_del(page_deferred_list(head));
+		}
+		spin_unlock(&split_queue_lock);
+		__split_huge_page(page, list);
+		ret = 0;
+	} else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
+		spin_unlock(&split_queue_lock);
+		pr_alert("total_mapcount: %u, page_count(): %u\n",
+				mapcount, count);
+		if (PageTail(page))
+			dump_page(head, NULL);
+		dump_page(page, "total_mapcount(head) > 0");
+		BUG();
+	} else {
+		spin_unlock(&split_queue_lock);
+		unfreeze_page(anon_vma, head);
+		ret = -EBUSY;
+	}
+
+out_unlock:
+	anon_vma_unlock_write(anon_vma);
+	put_anon_vma(anon_vma);
+out:
+	count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);
+	return ret;
+}
+
+void free_transhuge_page(struct page *page)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&split_queue_lock, flags);
+	if (!list_empty(page_deferred_list(page))) {
+		split_queue_len--;
+		list_del(page_deferred_list(page));
+	}
+	spin_unlock_irqrestore(&split_queue_lock, flags);
+	free_compound_page(page);
+}
+
+void deferred_split_huge_page(struct page *page)
+{
+	unsigned long flags;
+
+	VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+
+	spin_lock_irqsave(&split_queue_lock, flags);
+	if (list_empty(page_deferred_list(page))) {
+		list_add_tail(page_deferred_list(page), &split_queue);
+		split_queue_len++;
+	}
+	spin_unlock_irqrestore(&split_queue_lock, flags);
+}
+
+static unsigned long deferred_split_count(struct shrinker *shrink,
+		struct shrink_control *sc)
+{
+	/*
+	 * Split a page from split_queue will free up at least one page,
+	 * at most HPAGE_PMD_NR - 1. We don't track exact number.
+	 * Let's use HPAGE_PMD_NR / 2 as ballpark.
+	 */
+	return ACCESS_ONCE(split_queue_len) * HPAGE_PMD_NR / 2;
+}
+
+static unsigned long deferred_split_scan(struct shrinker *shrink,
+		struct shrink_control *sc)
+{
+	unsigned long flags;
+	LIST_HEAD(list), *pos, *next;
+	struct page *page;
+	int split = 0;
+
+	spin_lock_irqsave(&split_queue_lock, flags);
+	list_splice_init(&split_queue, &list);
+
+	/* Take pin on all head pages to avoid freeing them under us */
+	list_for_each_safe(pos, next, &list) {
+		page = list_entry((void *)pos, struct page, mapping);
+		page = compound_head(page);
+		/* race with put_compound_page() */
+		if (!get_page_unless_zero(page)) {
+			list_del_init(page_deferred_list(page));
+			split_queue_len--;
+		}
+	}
+	spin_unlock_irqrestore(&split_queue_lock, flags);
+
+	list_for_each_safe(pos, next, &list) {
+		page = list_entry((void *)pos, struct page, mapping);
+		lock_page(page);
+		/* split_huge_page() removes page from list on success */
+		if (!split_huge_page(page))
+			split++;
+		unlock_page(page);
+		put_page(page);
+	}
+
+	spin_lock_irqsave(&split_queue_lock, flags);
+	list_splice_tail(&list, &split_queue);
+	spin_unlock_irqrestore(&split_queue_lock, flags);
+
+	return split * HPAGE_PMD_NR / 2;
+}
+
+static struct shrinker deferred_split_shrinker = {
+	.count_objects = deferred_split_count,
+	.scan_objects = deferred_split_scan,
+	.seeks = DEFAULT_SEEKS,
+};
+
+#ifdef CONFIG_DEBUG_FS
+static int split_huge_pages_set(void *data, u64 val)
+{
+	struct zone *zone;
+	struct page *page;
+	unsigned long pfn, max_zone_pfn;
+	unsigned long total = 0, split = 0;
+
+	if (val != 1)
+		return -EINVAL;
+
+	for_each_populated_zone(zone) {
+		max_zone_pfn = zone_end_pfn(zone);
+		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
+			if (!pfn_valid(pfn))
+				continue;
+
+			page = pfn_to_page(pfn);
+			if (!get_page_unless_zero(page))
+				continue;
+
+			if (zone != page_zone(page))
+				goto next;
+
+			if (!PageHead(page) || !PageAnon(page) ||
+					PageHuge(page))
+				goto next;
+
+			total++;
+			lock_page(page);
+			if (!split_huge_page(page))
+				split++;
+			unlock_page(page);
+next:
+			put_page(page);
+		}
+	}
+
+	pr_info("%lu of %lu THP split", split, total);
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set,
+		"%llu\n");
+
+static int __init split_huge_pages_debugfs(void)
+{
+	void *ret;
+
+	ret = debugfs_create_file("split_huge_pages", 0644, NULL, NULL,
+			&split_huge_pages_fops);
+	if (!ret)
+		pr_warn("Failed to create split_huge_pages in debugfs");
+	return 0;
+}
+late_initcall(split_huge_pages_debugfs);
+#endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index be934df..12908dc 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1267,8 +1267,8 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order)
 
 	/* we rely on prep_new_huge_page to set the destructor */
 	set_compound_order(page, order);
-	__SetPageHead(page);
 	__ClearPageReserved(page);
+	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
 		/*
 		 * For gigantic hugepages allocated through bootmem at
@@ -3102,7 +3102,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
 			get_page(ptepage);
-			page_dup_rmap(ptepage);
+			page_dup_rmap(ptepage, true);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 			hugetlb_count_add(pages_per_huge_page(h), dst);
 		}
@@ -3186,7 +3186,7 @@ again:
 			set_page_dirty(page);
 
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
-		page_remove_rmap(page);
+		page_remove_rmap(page, true);
 		force_flush = !__tlb_remove_page(tlb, page);
 		if (force_flush) {
 			address += sz;
@@ -3415,7 +3415,7 @@ retry_avoidcopy:
 		mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
 		set_huge_pte_at(mm, address, ptep,
 				make_huge_pte(vma, new_page, 1));
-		page_remove_rmap(old_page);
+		page_remove_rmap(old_page, true);
 		hugepage_add_new_anon_rmap(new_page, vma, address);
 		/* Make the old page be freed below */
 		new_page = old_page;
@@ -3585,7 +3585,7 @@ retry:
 		ClearPagePrivate(page);
 		hugepage_add_new_anon_rmap(page, vma, address);
 	} else
-		page_dup_rmap(page);
+		page_dup_rmap(page, true);
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, address, ptep, new_pte);
@@ -3865,7 +3865,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 same_page:
 		if (pages) {
 			pages[i] = mem_map_offset(page, pfn_offset);
-			get_page_foll(pages[i]);
+			get_page(pages[i]);
 		}
 
 		if (vmas)
diff --git a/mm/internal.h b/mm/internal.h
index 38e24b8..ed8b5ff 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -13,6 +13,7 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/pagemap.h>
 
 /*
  * The set of flags that only affect watermark checking and reclaim
@@ -66,50 +67,6 @@ static inline void set_page_refcounted(struct page *page)
 	set_page_count(page, 1);
 }
 
-static inline void __get_page_tail_foll(struct page *page,
-					bool get_page_head)
-{
-	/*
-	 * If we're getting a tail page, the elevated page->_count is
-	 * required only in the head page and we will elevate the head
-	 * page->_count and tail page->_mapcount.
-	 *
-	 * We elevate page_tail->_mapcount for tail pages to force
-	 * page_tail->_count to be zero at all times to avoid getting
-	 * false positives from get_page_unless_zero() with
-	 * speculative page access (like in
-	 * page_cache_get_speculative()) on tail pages.
-	 */
-	VM_BUG_ON_PAGE(atomic_read(&compound_head(page)->_count) <= 0, page);
-	if (get_page_head)
-		atomic_inc(&compound_head(page)->_count);
-	get_huge_page_tail(page);
-}
-
-/*
- * This is meant to be called as the FOLL_GET operation of
- * follow_page() and it must be called while holding the proper PT
- * lock while the pte (or pmd_trans_huge) is still mapping the page.
- */
-static inline void get_page_foll(struct page *page)
-{
-	if (unlikely(PageTail(page)))
-		/*
-		 * This is safe only because
-		 * __split_huge_page_refcount() can't run under
-		 * get_page_foll() because we hold the proper PT lock.
-		 */
-		__get_page_tail_foll(page, true);
-	else {
-		/*
-		 * Getting a normal page or the head of a compound page
-		 * requires to already have an elevated page->_count.
-		 */
-		VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page);
-		atomic_inc(&page->_count);
-	}
-}
-
 extern unsigned long highest_memmap_pfn;
 
 /*
@@ -309,10 +266,27 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
 
 extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern unsigned long vma_address(struct page *page,
-				 struct vm_area_struct *vma);
-#endif
+/*
+ * At what user virtual address is page expected in @vma?
+ */
+static inline unsigned long
+__vma_address(struct page *page, struct vm_area_struct *vma)
+{
+	pgoff_t pgoff = page_to_pgoff(page);
+	return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+}
+
+static inline unsigned long
+vma_address(struct page *page, struct vm_area_struct *vma)
+{
+	unsigned long address = __vma_address(page, vma);
+
+	/* page should be within @vma mapping range */
+	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
+
+	return address;
+}
+
 #else /* !CONFIG_MMU */
 static inline void clear_page_mlock(struct page *page) { }
 static inline void mlock_vma_page(struct page *page) { }
diff --git a/mm/ksm.c b/mm/ksm.c
index 2d162c5..ca6d2a0 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -441,20 +441,6 @@ static void break_cow(struct rmap_item *rmap_item)
 	up_read(&mm->mmap_sem);
 }
 
-static struct page *page_trans_compound_anon(struct page *page)
-{
-	if (PageTransCompound(page)) {
-		struct page *head = compound_head(page);
-		/*
-		 * head may actually be splitted and freed from under
-		 * us but it's ok here.
-		 */
-		if (PageAnon(head))
-			return head;
-	}
-	return NULL;
-}
-
 static struct page *get_mergeable_page(struct rmap_item *rmap_item)
 {
 	struct mm_struct *mm = rmap_item->mm;
@@ -470,7 +456,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item)
 	page = follow_page(vma, addr, FOLL_GET);
 	if (IS_ERR_OR_NULL(page))
 		goto out;
-	if (PageAnon(page) || page_trans_compound_anon(page)) {
+	if (PageAnon(page)) {
 		flush_anon_page(vma, page, addr);
 		flush_dcache_page(page);
 	} else {
@@ -956,13 +942,13 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	}
 
 	get_page(kpage);
-	page_add_anon_rmap(kpage, vma, addr);
+	page_add_anon_rmap(kpage, vma, addr, false);
 
 	flush_cache_page(vma, addr, pte_pfn(*ptep));
 	ptep_clear_flush_notify(vma, addr, ptep);
 	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
 
-	page_remove_rmap(page);
+	page_remove_rmap(page, false);
 	if (!page_mapped(page))
 		try_to_free_swap(page);
 	put_page(page);
@@ -975,33 +961,6 @@ out:
 	return err;
 }
 
-static int page_trans_compound_anon_split(struct page *page)
-{
-	int ret = 0;
-	struct page *transhuge_head = page_trans_compound_anon(page);
-	if (transhuge_head) {
-		/* Get the reference on the head to split it. */
-		if (get_page_unless_zero(transhuge_head)) {
-			/*
-			 * Recheck we got the reference while the head
-			 * was still anonymous.
-			 */
-			if (PageAnon(transhuge_head))
-				ret = split_huge_page(transhuge_head);
-			else
-				/*
-				 * Retry later if split_huge_page run
-				 * from under us.
-				 */
-				ret = 1;
-			put_page(transhuge_head);
-		} else
-			/* Retry later if split_huge_page run from under us. */
-			ret = 1;
-	}
-	return ret;
-}
-
 /*
  * try_to_merge_one_page - take two pages and merge them into one
  * @vma: the vma that holds the pte pointing to page
@@ -1020,9 +979,6 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 	if (page == kpage)			/* ksm page forked */
 		return 0;
 
-	if (PageTransCompound(page) && page_trans_compound_anon_split(page))
-		goto out;
-	BUG_ON(PageTransCompound(page));
 	if (!PageAnon(page))
 		goto out;
 
@@ -1035,6 +991,13 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 	 */
 	if (!trylock_page(page))
 		goto out;
+
+	if (PageTransCompound(page)) {
+		err = split_huge_page(page);
+		if (err)
+			goto out_unlock;
+	}
+
 	/*
 	 * If this anonymous page is mapped only here, its pte may need
 	 * to be write-protected.  If it's mapped elsewhere, all of its
@@ -1050,6 +1013,12 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 			 */
 			set_page_stable_node(page, NULL);
 			mark_page_accessed(page);
+			/*
+			 * Page reclaim just frees a clean page with no dirty
+			 * ptes: make sure that the ksm page would be swapped.
+			 */
+			if (!PageDirty(page))
+				SetPageDirty(page);
 			err = 0;
 		} else if (pages_identical(page, kpage))
 			err = replace_page(vma, page, kpage, orig_pte);
@@ -1065,6 +1034,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 		}
 	}
 
+out_unlock:
 	unlock_page(page);
 out:
 	return err;
@@ -1635,8 +1605,7 @@ next_mm:
 				cond_resched();
 				continue;
 			}
-			if (PageAnon(*page) ||
-			    page_trans_compound_anon(*page)) {
+			if (PageAnon(*page)) {
 				flush_anon_page(vma, *page, ksm_scan.address);
 				flush_dcache_page(*page);
 				rmap_item = get_next_rmap_item(slot,
@@ -1899,7 +1868,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
 
 		SetPageDirty(new_page);
 		__SetPageUptodate(new_page);
-		__set_page_locked(new_page);
+		__SetPageLocked(new_page);
 	}
 
 	return new_page;
diff --git a/mm/madvise.c b/mm/madvise.c
index c889fcb..f56825b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -20,6 +20,9 @@
 #include <linux/backing-dev.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/tlb.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -32,6 +35,7 @@ static int madvise_need_mmap_write(int behavior)
 	case MADV_REMOVE:
 	case MADV_WILLNEED:
 	case MADV_DONTNEED:
+	case MADV_FREE:
 		return 0;
 	default:
 		/* be safe, default to 1. list exceptions explicitly */
@@ -256,6 +260,194 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	return 0;
 }
 
+static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+
+{
+	struct mmu_gather *tlb = walk->private;
+	struct mm_struct *mm = tlb->mm;
+	struct vm_area_struct *vma = walk->vma;
+	spinlock_t *ptl;
+	pte_t *orig_pte, *pte, ptent;
+	struct page *page;
+	int nr_swap = 0;
+	unsigned long next;
+
+	next = pmd_addr_end(addr, end);
+	if (pmd_trans_huge(*pmd))
+		if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next))
+			goto next;
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
+
+	orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	arch_enter_lazy_mmu_mode();
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
+		ptent = *pte;
+
+		if (pte_none(ptent))
+			continue;
+		/*
+		 * If the pte has swp_entry, just clear page table to
+		 * prevent swap-in which is more expensive rather than
+		 * (page allocation + zeroing).
+		 */
+		if (!pte_present(ptent)) {
+			swp_entry_t entry;
+
+			entry = pte_to_swp_entry(ptent);
+			if (non_swap_entry(entry))
+				continue;
+			nr_swap--;
+			free_swap_and_cache(entry);
+			pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+			continue;
+		}
+
+		page = vm_normal_page(vma, addr, ptent);
+		if (!page)
+			continue;
+
+		/*
+		 * If pmd isn't transhuge but the page is THP and
+		 * is owned by only this process, split it and
+		 * deactivate all pages.
+		 */
+		if (PageTransCompound(page)) {
+			if (page_mapcount(page) != 1)
+				goto out;
+			get_page(page);
+			if (!trylock_page(page)) {
+				put_page(page);
+				goto out;
+			}
+			pte_unmap_unlock(orig_pte, ptl);
+			if (split_huge_page(page)) {
+				unlock_page(page);
+				put_page(page);
+				pte_offset_map_lock(mm, pmd, addr, &ptl);
+				goto out;
+			}
+			put_page(page);
+			unlock_page(page);
+			pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+			pte--;
+			addr -= PAGE_SIZE;
+			continue;
+		}
+
+		VM_BUG_ON_PAGE(PageTransCompound(page), page);
+
+		if (PageSwapCache(page) || PageDirty(page)) {
+			if (!trylock_page(page))
+				continue;
+			/*
+			 * If page is shared with others, we couldn't clear
+			 * PG_dirty of the page.
+			 */
+			if (page_mapcount(page) != 1) {
+				unlock_page(page);
+				continue;
+			}
+
+			if (PageSwapCache(page) && !try_to_free_swap(page)) {
+				unlock_page(page);
+				continue;
+			}
+
+			ClearPageDirty(page);
+			unlock_page(page);
+		}
+
+		if (pte_young(ptent) || pte_dirty(ptent)) {
+			/*
+			 * Some of architecture(ex, PPC) don't update TLB
+			 * with set_pte_at and tlb_remove_tlb_entry so for
+			 * the portability, remap the pte with old|clean
+			 * after pte clearing.
+			 */
+			ptent = ptep_get_and_clear_full(mm, addr, pte,
+							tlb->fullmm);
+
+			ptent = pte_mkold(ptent);
+			ptent = pte_mkclean(ptent);
+			set_pte_at(mm, addr, pte, ptent);
+			if (PageActive(page))
+				deactivate_page(page);
+			tlb_remove_tlb_entry(tlb, pte, addr);
+		}
+	}
+out:
+	if (nr_swap) {
+		if (current->mm == mm)
+			sync_mm_rss(mm);
+
+		add_mm_counter(mm, MM_SWAPENTS, nr_swap);
+	}
+	arch_leave_lazy_mmu_mode();
+	pte_unmap_unlock(orig_pte, ptl);
+	cond_resched();
+next:
+	return 0;
+}
+
+static void madvise_free_page_range(struct mmu_gather *tlb,
+			     struct vm_area_struct *vma,
+			     unsigned long addr, unsigned long end)
+{
+	struct mm_walk free_walk = {
+		.pmd_entry = madvise_free_pte_range,
+		.mm = vma->vm_mm,
+		.private = tlb,
+	};
+
+	tlb_start_vma(tlb, vma);
+	walk_page_range(addr, end, &free_walk);
+	tlb_end_vma(tlb, vma);
+}
+
+static int madvise_free_single_vma(struct vm_area_struct *vma,
+			unsigned long start_addr, unsigned long end_addr)
+{
+	unsigned long start, end;
+	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_gather tlb;
+
+	if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
+		return -EINVAL;
+
+	/* MADV_FREE works for only anon vma at the moment */
+	if (!vma_is_anonymous(vma))
+		return -EINVAL;
+
+	start = max(vma->vm_start, start_addr);
+	if (start >= vma->vm_end)
+		return -EINVAL;
+	end = min(vma->vm_end, end_addr);
+	if (end <= vma->vm_start)
+		return -EINVAL;
+
+	lru_add_drain();
+	tlb_gather_mmu(&tlb, mm, start, end);
+	update_hiwater_rss(mm);
+
+	mmu_notifier_invalidate_range_start(mm, start, end);
+	madvise_free_page_range(&tlb, vma, start, end);
+	mmu_notifier_invalidate_range_end(mm, start, end);
+	tlb_finish_mmu(&tlb, start, end);
+
+	return 0;
+}
+
+static long madvise_free(struct vm_area_struct *vma,
+			     struct vm_area_struct **prev,
+			     unsigned long start, unsigned long end)
+{
+	*prev = vma;
+	return madvise_free_single_vma(vma, start, end);
+}
+
 /*
  * Application no longer needs these pages.  If the pages are dirty,
  * it's OK to just throw them away.  The app will be more careful about
@@ -379,6 +571,14 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		return madvise_remove(vma, prev, start, end);
 	case MADV_WILLNEED:
 		return madvise_willneed(vma, prev, start, end);
+	case MADV_FREE:
+		/*
+		 * XXX: In this implementation, MADV_FREE works like
+		 * MADV_DONTNEED on swapless system or full swap.
+		 */
+		if (get_nr_swap_pages() > 0)
+			return madvise_free(vma, prev, start, end);
+		/* passthrough */
 	case MADV_DONTNEED:
 		return madvise_dontneed(vma, prev, start, end);
 	default:
@@ -398,6 +598,7 @@ madvise_behavior_valid(int behavior)
 	case MADV_REMOVE:
 	case MADV_WILLNEED:
 	case MADV_DONTNEED:
+	case MADV_FREE:
 #ifdef CONFIG_KSM
 	case MADV_MERGEABLE:
 	case MADV_UNMERGEABLE:
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 54eae4f..0eda673 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -382,14 +382,11 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
 {
 	struct mem_cgroup *memcg;
 
-	rcu_read_lock();
-
 	memcg = page->mem_cgroup;
 
 	if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		memcg = root_mem_cgroup;
 
-	rcu_read_unlock();
 	return &memcg->css;
 }
 
@@ -647,7 +644,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 					 struct page *page,
-					 int nr_pages)
+					 bool compound, int nr_pages)
 {
 	/*
 	 * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
@@ -660,9 +657,11 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
 				nr_pages);
 
-	if (PageTransHuge(page))
+	if (compound) {
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
 				nr_pages);
+	}
 
 	/* pagein of a big page is an event. So, ignore page size */
 	if (nr_pages > 0)
@@ -2431,9 +2430,7 @@ void __memcg_kmem_uncharge(struct page *page, int order)
 
 /*
  * Because tail pages are not marked as "used", set it. We're under
- * zone->lru_lock, 'splitting on pmd' and compound_lock.
- * charge/uncharge will be never happen and move_account() is done under
- * compound_lock(), so we don't have to take care of races.
+ * zone->lru_lock and migration entries setup in all page mappings.
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
@@ -3494,16 +3491,17 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 swap_buffers:
 	/* Swap primary and spare array */
 	thresholds->spare = thresholds->primary;
-	/* If all events are unregistered, free the spare array */
-	if (!new) {
-		kfree(thresholds->spare);
-		thresholds->spare = NULL;
-	}
 
 	rcu_assign_pointer(thresholds->primary, new);
 
 	/* To be sure that nobody uses thresholds */
 	synchronize_rcu();
+
+	/* If all events are unregistered, free the spare array */
+	if (!new) {
+		kfree(thresholds->spare);
+		thresholds->spare = NULL;
+	}
 unlock:
 	mutex_unlock(&memcg->thresholds_lock);
 }
@@ -4505,38 +4503,30 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
  * @from: mem_cgroup which the page is moved from.
  * @to:	mem_cgroup which the page is moved to. @from != @to.
  *
- * The caller must confirm following.
- * - page is not on LRU (isolate_page() is useful.)
- * - compound_lock is held when nr_pages > 1
+ * The caller must make sure the page is not on LRU (isolate_page() is useful.)
  *
  * This function doesn't do "charge" to new cgroup and doesn't do "uncharge"
  * from old cgroup.
  */
 static int mem_cgroup_move_account(struct page *page,
-				   unsigned int nr_pages,
+				   bool compound,
 				   struct mem_cgroup *from,
 				   struct mem_cgroup *to)
 {
 	unsigned long flags;
+	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
 	int ret;
 	bool anon;
 
 	VM_BUG_ON(from == to);
 	VM_BUG_ON_PAGE(PageLRU(page), page);
-	/*
-	 * The page is isolated from LRU. So, collapse function
-	 * will not handle this page. But page splitting can happen.
-	 * Do this check under compound_page_lock(). The caller should
-	 * hold it.
-	 */
-	ret = -EBUSY;
-	if (nr_pages > 1 && !PageTransHuge(page))
-		goto out;
+	VM_BUG_ON(compound && !PageTransHuge(page));
 
 	/*
 	 * Prevent mem_cgroup_replace_page() from looking at
 	 * page->mem_cgroup of its source page while we change it.
 	 */
+	ret = -EBUSY;
 	if (!trylock_page(page))
 		goto out;
 
@@ -4591,9 +4581,9 @@ static int mem_cgroup_move_account(struct page *page,
 	ret = 0;
 
 	local_irq_disable();
-	mem_cgroup_charge_statistics(to, page, nr_pages);
+	mem_cgroup_charge_statistics(to, page, compound, nr_pages);
 	memcg_check_events(to, page);
-	mem_cgroup_charge_statistics(from, page, -nr_pages);
+	mem_cgroup_charge_statistics(from, page, compound, -nr_pages);
 	memcg_check_events(from, page);
 	local_irq_enable();
 out_unlock:
@@ -4683,7 +4673,7 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
 			mc.precharge += HPAGE_PMD_NR;
 		spin_unlock(ptl);
@@ -4871,17 +4861,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	union mc_target target;
 	struct page *page;
 
-	/*
-	 * We don't take compound_lock() here but no race with splitting thp
-	 * happens because:
-	 *  - if pmd_trans_huge_lock() returns 1, the relevant thp is not
-	 *    under splitting, which means there's no concurrent thp split,
-	 *  - if another thread runs into split_huge_page() just after we
-	 *    entered this if-block, the thread must wait for page table lock
-	 *    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, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		if (mc.precharge < HPAGE_PMD_NR) {
 			spin_unlock(ptl);
 			return 0;
@@ -4890,7 +4870,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 		if (target_type == MC_TARGET_PAGE) {
 			page = target.page;
 			if (!isolate_lru_page(page)) {
-				if (!mem_cgroup_move_account(page, HPAGE_PMD_NR,
+				if (!mem_cgroup_move_account(page, true,
 							     mc.from, mc.to)) {
 					mc.precharge -= HPAGE_PMD_NR;
 					mc.moved_charge += HPAGE_PMD_NR;
@@ -4917,9 +4897,18 @@ retry:
 		switch (get_mctgt_type(vma, addr, ptent, &target)) {
 		case MC_TARGET_PAGE:
 			page = target.page;
+			/*
+			 * We can have a part of the split pmd here. Moving it
+			 * can be done but it would be too convoluted so simply
+			 * ignore such a partial THP and keep it in original
+			 * memcg. There should be somebody mapping the head.
+			 */
+			if (PageTransCompound(page))
+				goto put;
 			if (isolate_lru_page(page))
 				goto put;
-			if (!mem_cgroup_move_account(page, 1, mc.from, mc.to)) {
+			if (!mem_cgroup_move_account(page, false,
+						mc.from, mc.to)) {
 				mc.precharge--;
 				/* we uncharge from mc.from later. */
 				mc.moved_charge++;
@@ -5258,10 +5247,11 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg)
  * with mem_cgroup_cancel_charge() in case page instantiation fails.
  */
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
-			  gfp_t gfp_mask, struct mem_cgroup **memcgp)
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
+			  bool compound)
 {
 	struct mem_cgroup *memcg = NULL;
-	unsigned int nr_pages = 1;
+	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
 	int ret = 0;
 
 	if (mem_cgroup_disabled())
@@ -5291,11 +5281,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		}
 	}
 
-	if (PageTransHuge(page)) {
-		nr_pages <<= compound_order(page);
-		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-	}
-
 	if (!memcg)
 		memcg = get_mem_cgroup_from_mm(mm);
 
@@ -5324,9 +5309,9 @@ out:
  * Use mem_cgroup_cancel_charge() to cancel the transaction instead.
  */
 void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
-			      bool lrucare)
+			      bool lrucare, bool compound)
 {
-	unsigned int nr_pages = 1;
+	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
 
 	VM_BUG_ON_PAGE(!page->mapping, page);
 	VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page);
@@ -5343,13 +5328,8 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
 
 	commit_charge(page, memcg, lrucare);
 
-	if (PageTransHuge(page)) {
-		nr_pages <<= compound_order(page);
-		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-	}
-
 	local_irq_disable();
-	mem_cgroup_charge_statistics(memcg, page, nr_pages);
+	mem_cgroup_charge_statistics(memcg, page, compound, nr_pages);
 	memcg_check_events(memcg, page);
 	local_irq_enable();
 
@@ -5371,9 +5351,10 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
  *
  * Cancel a charge transaction started by mem_cgroup_try_charge().
  */
-void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg)
+void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
+		bool compound)
 {
-	unsigned int nr_pages = 1;
+	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
 
 	if (mem_cgroup_disabled())
 		return;
@@ -5385,11 +5366,6 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg)
 	if (!memcg)
 		return;
 
-	if (PageTransHuge(page)) {
-		nr_pages <<= compound_order(page);
-		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-	}
-
 	cancel_charge(memcg, nr_pages);
 }
 
@@ -5750,7 +5726,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	 * only synchronisation we have for udpating the per-CPU variables.
 	 */
 	VM_BUG_ON(!irqs_disabled());
-	mem_cgroup_charge_statistics(memcg, page, -1);
+	mem_cgroup_charge_statistics(memcg, page, false, -1);
 	memcg_check_events(memcg, page);
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 8424b64..ac595e7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -882,15 +882,7 @@ int get_hwpoison_page(struct page *page)
 {
 	struct page *head = compound_head(page);
 
-	if (PageHuge(head))
-		return get_page_unless_zero(head);
-
-	/*
-	 * Thp tail page has special refcounting rule (refcount of tail pages
-	 * is stored in ->_mapcount,) so we can't call get_page_unless_zero()
-	 * directly for tail pages.
-	 */
-	if (PageTransHuge(head)) {
+	if (!PageHuge(head) && PageTransHuge(head)) {
 		/*
 		 * Non anonymous thp exists only in allocation/free time. We
 		 * can't handle such a case correctly, so let's give it up.
@@ -902,41 +894,12 @@ int get_hwpoison_page(struct page *page)
 				page_to_pfn(page));
 			return 0;
 		}
-
-		if (get_page_unless_zero(head)) {
-			if (PageTail(page))
-				get_page(page);
-			return 1;
-		} else {
-			return 0;
-		}
 	}
 
-	return get_page_unless_zero(page);
+	return get_page_unless_zero(head);
 }
 EXPORT_SYMBOL_GPL(get_hwpoison_page);
 
-/**
- * put_hwpoison_page() - Put refcount for memory error handling:
- * @page:	raw error page (hit by memory error)
- */
-void put_hwpoison_page(struct page *page)
-{
-	struct page *head = compound_head(page);
-
-	if (PageHuge(head)) {
-		put_page(head);
-		return;
-	}
-
-	if (PageTransHuge(head))
-		if (page != head)
-			put_page(head);
-
-	put_page(page);
-}
-EXPORT_SYMBOL_GPL(put_hwpoison_page);
-
 /*
  * Do all that is necessary to remove user space mappings. Unmap
  * the pages and send SIGBUS to the processes if the data was dirty.
@@ -1149,7 +1112,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	}
 
 	if (!PageHuge(p) && PageTransHuge(hpage)) {
+		lock_page(hpage);
 		if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) {
+			unlock_page(hpage);
 			if (!PageAnon(hpage))
 				pr_err("MCE: %#lx: non anonymous thp\n", pfn);
 			else
@@ -1159,6 +1124,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			put_hwpoison_page(p);
 			return -EBUSY;
 		}
+		unlock_page(hpage);
+		get_hwpoison_page(p);
+		put_hwpoison_page(hpage);
 		VM_BUG_ON_PAGE(!page_count(p), p);
 		hpage = compound_head(p);
 	}
@@ -1166,7 +1134,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	/*
 	 * We ignore non-LRU pages for good reasons.
 	 * - PG_locked is only well defined for LRU pages and a few others
-	 * - to avoid races with __set_page_locked()
+	 * - to avoid races with __SetPageLocked()
 	 * - to avoid races with __SetPageSlab*() (and more non-atomic ops)
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.
@@ -1572,7 +1540,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		 * Did it turn free?
 		 */
 		ret = __get_any_page(page, pfn, 0);
-		if (!PageLRU(page)) {
+		if (ret == 1 && !PageLRU(page)) {
 			/* Drop page reference which is from __get_any_page() */
 			put_hwpoison_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
@@ -1716,6 +1684,49 @@ static int __soft_offline_page(struct page *page, int flags)
 	return ret;
 }
 
+static int soft_offline_in_use_page(struct page *page, int flags)
+{
+	int ret;
+	struct page *hpage = compound_head(page);
+
+	if (!PageHuge(page) && PageTransHuge(hpage)) {
+		lock_page(hpage);
+		if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) {
+			unlock_page(hpage);
+			if (!PageAnon(hpage))
+				pr_info("soft offline: %#lx: non anonymous thp\n", page_to_pfn(page));
+			else
+				pr_info("soft offline: %#lx: thp split failed\n", page_to_pfn(page));
+			put_hwpoison_page(hpage);
+			return -EBUSY;
+		}
+		unlock_page(hpage);
+		get_hwpoison_page(page);
+		put_hwpoison_page(hpage);
+	}
+
+	if (PageHuge(page))
+		ret = soft_offline_huge_page(page, flags);
+	else
+		ret = __soft_offline_page(page, flags);
+
+	return ret;
+}
+
+static void soft_offline_free_page(struct page *page)
+{
+	if (PageHuge(page)) {
+		struct page *hpage = compound_head(page);
+
+		set_page_hwpoison_huge_page(hpage);
+		if (!dequeue_hwpoisoned_huge_page(hpage))
+			num_poisoned_pages_add(1 << compound_order(hpage));
+	} else {
+		if (!TestSetPageHWPoison(page))
+			num_poisoned_pages_inc();
+	}
+}
+
 /**
  * soft_offline_page - Soft offline a page.
  * @page: page to offline
@@ -1742,7 +1753,6 @@ int soft_offline_page(struct page *page, int flags)
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
-	struct page *hpage = compound_head(page);
 
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
@@ -1750,34 +1760,15 @@ int soft_offline_page(struct page *page, int flags)
 			put_hwpoison_page(page);
 		return -EBUSY;
 	}
-	if (!PageHuge(page) && PageTransHuge(hpage)) {
-		if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
-			pr_info("soft offline: %#lx: failed to split THP\n",
-				pfn);
-			if (flags & MF_COUNT_INCREASED)
-				put_hwpoison_page(page);
-			return -EBUSY;
-		}
-	}
 
 	get_online_mems();
-
 	ret = get_any_page(page, pfn, flags);
 	put_online_mems();
-	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 if (ret == 0) { /* for free pages */
-		if (PageHuge(page)) {
-			set_page_hwpoison_huge_page(hpage);
-			if (!dequeue_hwpoisoned_huge_page(hpage))
-				num_poisoned_pages_add(1 << compound_order(hpage));
-		} else {
-			if (!TestSetPageHWPoison(page))
-				num_poisoned_pages_inc();
-		}
-	}
+
+	if (ret > 0)
+		ret = soft_offline_in_use_page(page, flags);
+	else if (ret == 0)
+		soft_offline_free_page(page);
+
 	return ret;
 }
diff --git a/mm/memory.c b/mm/memory.c
index d4e4d37..ff17850 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -50,6 +50,7 @@
 #include <linux/export.h>
 #include <linux/delayacct.h>
 #include <linux/init.h>
+#include <linux/pfn_t.h>
 #include <linux/writeback.h>
 #include <linux/memcontrol.h>
 #include <linux/mmu_notifier.h>
@@ -566,7 +567,6 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	spinlock_t *ptl;
 	pgtable_t new = pte_alloc_one(mm, address);
-	int wait_split_huge_page;
 	if (!new)
 		return -ENOMEM;
 
@@ -586,18 +586,14 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 
 	ptl = pmd_lock(mm, pmd);
-	wait_split_huge_page = 0;
 	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
 		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(ptl);
 	if (new)
 		pte_free(mm, new);
-	if (wait_split_huge_page)
-		wait_split_huge_page(vma->anon_vma, pmd);
 	return 0;
 }
 
@@ -613,8 +609,7 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
 	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
 		pmd_populate_kernel(&init_mm, pmd, new);
 		new = NULL;
-	} else
-		VM_BUG_ON(pmd_trans_splitting(*pmd));
+	}
 	spin_unlock(&init_mm.page_table_lock);
 	if (new)
 		pte_free_kernel(&init_mm, new);
@@ -870,7 +865,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	page = vm_normal_page(vma, addr, pte);
 	if (page) {
 		get_page(page);
-		page_dup_rmap(page);
+		page_dup_rmap(page, false);
 		rss[mm_counter(page)]++;
 	}
 
@@ -955,7 +950,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 	src_pmd = pmd_offset(src_pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		if (pmd_trans_huge(*src_pmd)) {
+		if (pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) {
 			int err;
 			VM_BUG_ON(next-addr != HPAGE_PMD_SIZE);
 			err = copy_huge_pmd(dst_mm, src_mm,
@@ -1118,7 +1113,7 @@ again:
 					mark_page_accessed(page);
 			}
 			rss[mm_counter(page)]--;
-			page_remove_rmap(page);
+			page_remove_rmap(page, false);
 			if (unlikely(page_mapcount(page) < 0))
 				print_bad_pte(vma, addr, ptent, page);
 			if (unlikely(!__tlb_remove_page(tlb, page))) {
@@ -1182,7 +1177,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		if (pmd_trans_huge(*pmd)) {
+		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE) {
 #ifdef CONFIG_DEBUG_VM
 				if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
@@ -1193,7 +1188,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 					BUG();
 				}
 #endif
-				split_huge_page_pmd(vma, addr, pmd);
+				split_huge_pmd(vma, pmd, addr);
 			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
 				goto next;
 			/* fall through */
@@ -1506,7 +1501,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 EXPORT_SYMBOL(vm_insert_page);
 
 static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
-			unsigned long pfn, pgprot_t prot)
+			pfn_t pfn, pgprot_t prot)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	int retval;
@@ -1522,7 +1517,10 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 		goto out_unlock;
 
 	/* Ok, finally just insert the thing.. */
-	entry = pte_mkspecial(pfn_pte(pfn, prot));
+	if (pfn_t_devmap(pfn))
+		entry = pte_mkdevmap(pfn_t_pte(pfn, prot));
+	else
+		entry = pte_mkspecial(pfn_t_pte(pfn, prot));
 	set_pte_at(mm, addr, pte, entry);
 	update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
 
@@ -1569,17 +1567,17 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
-	if (track_pfn_insert(vma, &pgprot, pfn))
+	if (track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)))
 		return -EINVAL;
 
-	ret = insert_pfn(vma, addr, pfn, pgprot);
+	ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot);
 
 	return ret;
 }
 EXPORT_SYMBOL(vm_insert_pfn);
 
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-			unsigned long pfn)
+			pfn_t pfn)
 {
 	BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));
 
@@ -1593,10 +1591,10 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 	 * than insert_pfn).  If a zero_pfn were inserted into a VM_MIXEDMAP
 	 * without pte special, it would there be refcounted as a normal page.
 	 */
-	if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) {
+	if (!HAVE_PTE_SPECIAL && pfn_t_valid(pfn)) {
 		struct page *page;
 
-		page = pfn_to_page(pfn);
+		page = pfn_t_to_page(pfn);
 		return insert_page(vma, addr, page, vma->vm_page_prot);
 	}
 	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
@@ -2087,7 +2085,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
 		cow_user_page(new_page, old_page, address, vma);
 	}
 
-	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg))
+	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false))
 		goto oom_free_new;
 
 	__SetPageUptodate(new_page);
@@ -2118,8 +2116,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * thread doing COW.
 		 */
 		ptep_clear_flush_notify(vma, address, page_table);
-		page_add_new_anon_rmap(new_page, vma, address);
-		mem_cgroup_commit_charge(new_page, memcg, false);
+		page_add_new_anon_rmap(new_page, vma, address, false);
+		mem_cgroup_commit_charge(new_page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(new_page, vma);
 		/*
 		 * We call the notify macro here because, when using secondary
@@ -2151,14 +2149,14 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
 			 * mapcount is visible. So transitively, TLBs to
 			 * old page will be flushed before it can be reused.
 			 */
-			page_remove_rmap(old_page);
+			page_remove_rmap(old_page, false);
 		}
 
 		/* Free the old page.. */
 		new_page = old_page;
 		page_copied = 1;
 	} else {
-		mem_cgroup_cancel_charge(new_page, memcg);
+		mem_cgroup_cancel_charge(new_page, memcg, false);
 	}
 
 	if (new_page)
@@ -2173,7 +2171,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		if (page_copied && (vma->vm_flags & VM_LOCKED)) {
 			lock_page(old_page);	/* LRU manipulation */
-			munlock_vma_page(old_page);
+			if (PageMlocked(old_page))
+				munlock_vma_page(old_page);
 			unlock_page(old_page);
 		}
 		page_cache_release(old_page);
@@ -2533,7 +2532,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_page;
 	}
 
-	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) {
+	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false)) {
 		ret = VM_FAULT_OOM;
 		goto out_page;
 	}
@@ -2567,7 +2566,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 		flags &= ~FAULT_FLAG_WRITE;
 		ret |= VM_FAULT_WRITE;
-		exclusive = 1;
+		exclusive = RMAP_EXCLUSIVE;
 	}
 	flush_icache_page(vma, page);
 	if (pte_swp_soft_dirty(orig_pte))
@@ -2575,10 +2574,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	set_pte_at(mm, address, page_table, pte);
 	if (page == swapcache) {
 		do_page_add_anon_rmap(page, vma, address, exclusive);
-		mem_cgroup_commit_charge(page, memcg, true);
+		mem_cgroup_commit_charge(page, memcg, true, false);
 	} else { /* ksm created a completely new copy */
-		page_add_new_anon_rmap(page, vma, address);
-		mem_cgroup_commit_charge(page, memcg, false);
+		page_add_new_anon_rmap(page, vma, address, false);
+		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
 	}
 
@@ -2613,7 +2612,7 @@ unlock:
 out:
 	return ret;
 out_nomap:
-	mem_cgroup_cancel_charge(page, memcg);
+	mem_cgroup_cancel_charge(page, memcg, false);
 	pte_unmap_unlock(page_table, ptl);
 out_page:
 	unlock_page(page);
@@ -2707,7 +2706,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!page)
 		goto oom;
 
-	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg))
+	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false))
 		goto oom_free_page;
 
 	/*
@@ -2728,15 +2727,15 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Deliver the page fault to userland, check inside PT lock */
 	if (userfaultfd_missing(vma)) {
 		pte_unmap_unlock(page_table, ptl);
-		mem_cgroup_cancel_charge(page, memcg);
+		mem_cgroup_cancel_charge(page, memcg, false);
 		page_cache_release(page);
 		return handle_userfault(vma, address, flags,
 					VM_UFFD_MISSING);
 	}
 
 	inc_mm_counter_fast(mm, MM_ANONPAGES);
-	page_add_new_anon_rmap(page, vma, address);
-	mem_cgroup_commit_charge(page, memcg, false);
+	page_add_new_anon_rmap(page, vma, address, false);
+	mem_cgroup_commit_charge(page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(page, vma);
 setpte:
 	set_pte_at(mm, address, page_table, entry);
@@ -2747,7 +2746,7 @@ unlock:
 	pte_unmap_unlock(page_table, ptl);
 	return 0;
 release:
-	mem_cgroup_cancel_charge(page, memcg);
+	mem_cgroup_cancel_charge(page, memcg, false);
 	page_cache_release(page);
 	goto unlock;
 oom_free_page:
@@ -2824,7 +2823,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	if (anon) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-		page_add_new_anon_rmap(page, vma, address);
+		page_add_new_anon_rmap(page, vma, address, false);
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page);
@@ -3000,7 +2999,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!new_page)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) {
+	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) {
 		page_cache_release(new_page);
 		return VM_FAULT_OOM;
 	}
@@ -3029,7 +3028,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto uncharge_out;
 	}
 	do_set_pte(vma, address, new_page, pte, true, true);
-	mem_cgroup_commit_charge(new_page, memcg, false);
+	mem_cgroup_commit_charge(new_page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(new_page, vma);
 	pte_unmap_unlock(pte, ptl);
 	if (fault_page) {
@@ -3044,7 +3043,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	return ret;
 uncharge_out:
-	mem_cgroup_cancel_charge(new_page, memcg);
+	mem_cgroup_cancel_charge(new_page, memcg, false);
 	page_cache_release(new_page);
 	return ret;
 }
@@ -3096,7 +3095,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
 	 * release semantics to prevent the compiler from undoing this copying.
 	 */
-	mapping = fault_page->mapping;
+	mapping = page_rmapping(fault_page);
 	unlock_page(fault_page);
 	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
 		/*
@@ -3198,6 +3197,12 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return 0;
 	}
 
+	/* TODO: handle PTE-mapped THP */
+	if (PageCompound(page)) {
+		pte_unmap_unlock(ptep, ptl);
+		return 0;
+	}
+
 	/*
 	 * Avoid grouping on RO pages in general. RO pages shouldn't hurt as
 	 * much anyway since they can be in shared cache state. This misses
@@ -3370,17 +3375,9 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		int ret;
 
 		barrier();
-		if (pmd_trans_huge(orig_pmd)) {
+		if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
 			unsigned int dirty = flags & FAULT_FLAG_WRITE;
 
-			/*
-			 * If the pmd is splitting, return and retry the
-			 * the fault.  Alternative: wait until the split
-			 * is done, and goto retry.
-			 */
-			if (pmd_trans_splitting(orig_pmd))
-				return 0;
-
 			if (pmd_protnone(orig_pmd))
 				return do_huge_pmd_numa_page(mm, vma, address,
 							     orig_pmd, pmd);
@@ -3407,7 +3404,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	    unlikely(__pte_alloc(mm, vma, pmd, address)))
 		return VM_FAULT_OOM;
 	/* if an huge pmd materialized from under us just retry later */
-	if (unlikely(pmd_trans_huge(*pmd)))
+	if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
 		return 0;
 	/*
 	 * A regular pmd is established and it can't morph into a huge pmd
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 92f9595..4af58a3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -17,6 +17,7 @@
 #include <linux/sysctl.h>
 #include <linux/cpu.h>
 #include <linux/memory.h>
+#include <linux/memremap.h>
 #include <linux/memory_hotplug.h>
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
@@ -506,10 +507,25 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
 	unsigned long i;
 	int err = 0;
 	int start_sec, end_sec;
+	struct vmem_altmap *altmap;
+
 	/* during initialize mem_map, align hot-added range to section */
 	start_sec = pfn_to_section_nr(phys_start_pfn);
 	end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
 
+	altmap = to_vmem_altmap((unsigned long) pfn_to_page(phys_start_pfn));
+	if (altmap) {
+		/*
+		 * Validate altmap is within bounds of the total request
+		 */
+		if (altmap->base_pfn != phys_start_pfn
+				|| vmem_altmap_offset(altmap) > nr_pages) {
+			pr_warn_once("memory add fail, invalid altmap\n");
+			return -EINVAL;
+		}
+		altmap->alloc = 0;
+	}
+
 	for (i = start_sec; i <= end_sec; i++) {
 		err = __add_section(nid, zone, section_nr_to_pfn(i));
 
@@ -731,7 +747,8 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn)
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 }
 
-static int __remove_section(struct zone *zone, struct mem_section *ms)
+static int __remove_section(struct zone *zone, struct mem_section *ms,
+		unsigned long map_offset)
 {
 	unsigned long start_pfn;
 	int scn_nr;
@@ -748,7 +765,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms)
 	start_pfn = section_nr_to_pfn(scn_nr);
 	__remove_zone(zone, start_pfn);
 
-	sparse_remove_one_section(zone, ms);
+	sparse_remove_one_section(zone, ms, map_offset);
 	return 0;
 }
 
@@ -767,9 +784,32 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 		 unsigned long nr_pages)
 {
 	unsigned long i;
-	int sections_to_remove;
-	resource_size_t start, size;
-	int ret = 0;
+	unsigned long map_offset = 0;
+	int sections_to_remove, ret = 0;
+
+	/* In the ZONE_DEVICE case device driver owns the memory region */
+	if (is_dev_zone(zone)) {
+		struct page *page = pfn_to_page(phys_start_pfn);
+		struct vmem_altmap *altmap;
+
+		altmap = to_vmem_altmap((unsigned long) page);
+		if (altmap)
+			map_offset = vmem_altmap_offset(altmap);
+	} else {
+		resource_size_t start, size;
+
+		start = phys_start_pfn << PAGE_SHIFT;
+		size = nr_pages * PAGE_SIZE;
+
+		ret = release_mem_region_adjustable(&iomem_resource, start,
+					size);
+		if (ret) {
+			resource_size_t endres = start + size - 1;
+
+			pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
+					&start, &endres, ret);
+		}
+	}
 
 	/*
 	 * We can only remove entire sections
@@ -777,23 +817,12 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 	BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
 	BUG_ON(nr_pages % PAGES_PER_SECTION);
 
-	start = phys_start_pfn << PAGE_SHIFT;
-	size = nr_pages * PAGE_SIZE;
-
-	/* in the ZONE_DEVICE case device driver owns the memory region */
-	if (!is_dev_zone(zone))
-		ret = release_mem_region_adjustable(&iomem_resource, start, size);
-	if (ret) {
-		resource_size_t endres = start + size - 1;
-
-		pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
-				&start, &endres, ret);
-	}
-
 	sections_to_remove = nr_pages / PAGES_PER_SECTION;
 	for (i = 0; i < sections_to_remove; i++) {
 		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
-		ret = __remove_section(zone, __pfn_to_section(pfn));
+
+		ret = __remove_section(zone, __pfn_to_section(pfn), map_offset);
+		map_offset = 0;
 		if (ret)
 			break;
 	}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d8caff0..27d1354 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -489,14 +489,33 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 	struct queue_pages *qp = walk->private;
 	unsigned long flags = qp->flags;
-	int nid;
+	int nid, ret;
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	split_huge_page_pmd(vma, addr, pmd);
-	if (pmd_trans_unstable(pmd))
-		return 0;
+	if (pmd_trans_huge(*pmd)) {
+		ptl = pmd_lock(walk->mm, pmd);
+		if (pmd_trans_huge(*pmd)) {
+			page = pmd_page(*pmd);
+			if (is_huge_zero_page(page)) {
+				spin_unlock(ptl);
+				split_huge_pmd(vma, pmd, addr);
+			} else {
+				get_page(page);
+				spin_unlock(ptl);
+				lock_page(page);
+				ret = split_huge_page(page);
+				unlock_page(page);
+				put_page(page);
+				if (ret)
+					return 0;
+			}
+		} else {
+			spin_unlock(ptl);
+		}
+	}
 
+retry:
 	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		if (!pte_present(*pte))
@@ -513,6 +532,21 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 		nid = page_to_nid(page);
 		if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
 			continue;
+		if (PageTail(page) && PageAnon(page)) {
+			get_page(page);
+			pte_unmap_unlock(pte, ptl);
+			lock_page(page);
+			ret = split_huge_page(page);
+			unlock_page(page);
+			put_page(page);
+			/* Failed to split -- skip. */
+			if (ret) {
+				pte = pte_offset_map_lock(walk->mm, pmd,
+						addr, &ptl);
+				continue;
+			}
+			goto retry;
+		}
 
 		if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
 			migrate_page_add(page, qp->pagelist, flags);
@@ -610,7 +644,8 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 
 	if (flags & MPOL_MF_LAZY) {
 		/* Similar to task_numa_work, skip inaccessible VMAs */
-		if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
+		if (vma_migratable(vma) &&
+			vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
 			change_prot_numa(vma, start, endvma);
 		return 1;
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index 7890d0b..b1034f9 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -165,9 +165,9 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 		if (PageAnon(new))
 			hugepage_add_anon_rmap(new, vma, addr);
 		else
-			page_dup_rmap(new);
+			page_dup_rmap(new, true);
 	} else if (PageAnon(new))
-		page_add_anon_rmap(new, vma, addr);
+		page_add_anon_rmap(new, vma, addr, false);
 	else
 		page_add_file_rmap(new);
 
@@ -943,9 +943,13 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page,
 		goto out;
 	}
 
-	if (unlikely(PageTransHuge(page)))
-		if (unlikely(split_huge_page(page)))
+	if (unlikely(PageTransHuge(page))) {
+		lock_page(page);
+		rc = split_huge_page(page);
+		unlock_page(page);
+		if (rc)
 			goto out;
+	}
 
 	rc = __unmap_and_move(page, newpage, force, mode);
 	if (rc == MIGRATEPAGE_SUCCESS)
@@ -1756,6 +1760,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		HPAGE_PMD_ORDER);
 	if (!new_page)
 		goto out_fail;
+	prep_transhuge_page(new_page);
 
 	isolated = numamigrate_isolate_page(pgdat, page);
 	if (!isolated) {
@@ -1767,7 +1772,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		flush_tlb_range(vma, mmun_start, mmun_end);
 
 	/* Prepare a page as a migration target */
-	__set_page_locked(new_page);
+	__SetPageLocked(new_page);
 	SetPageSwapBacked(new_page);
 
 	/* anon mapping, we can simply copy page->mapping to the new page: */
@@ -1815,7 +1820,7 @@ fail_putback:
 	 * guarantee the copy is visible before the pagetable update.
 	 */
 	flush_cache_range(vma, mmun_start, mmun_end);
-	page_add_anon_rmap(new_page, vma, mmun_start);
+	page_add_anon_rmap(new_page, vma, mmun_start, true);
 	pmdp_huge_clear_flush_notify(vma, mmun_start, pmd);
 	set_pmd_at(mm, mmun_start, pmd, entry);
 	flush_tlb_range(vma, mmun_start, mmun_end);
@@ -1826,14 +1831,14 @@ fail_putback:
 		flush_tlb_range(vma, mmun_start, mmun_end);
 		mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
 		update_mmu_cache_pmd(vma, address, &entry);
-		page_remove_rmap(new_page);
+		page_remove_rmap(new_page, true);
 		goto fail_putback;
 	}
 
 	mlock_migrate_page(new_page, page);
 	set_page_memcg(new_page, page_memcg(page));
 	set_page_memcg(page, NULL);
-	page_remove_rmap(page);
+	page_remove_rmap(page, true);
 
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
diff --git a/mm/mincore.c b/mm/mincore.c
index 14bb9fb..2a565ed 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -117,7 +117,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	unsigned char *vec = walk->private;
 	int nr = (end - addr) >> PAGE_SHIFT;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl)) {
 		memset(vec, 1, nr);
 		spin_unlock(ptl);
 		goto out;
diff --git a/mm/mlock.c b/mm/mlock.c
index 9cb87cb..e1e2b12 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -24,13 +24,13 @@
 
 #include "internal.h"
 
-int can_do_mlock(void)
+bool can_do_mlock(void)
 {
 	if (rlimit(RLIMIT_MEMLOCK) != 0)
-		return 1;
+		return true;
 	if (capable(CAP_IPC_LOCK))
-		return 1;
-	return 0;
+		return true;
+	return false;
 }
 EXPORT_SYMBOL(can_do_mlock);
 
@@ -82,6 +82,9 @@ void mlock_vma_page(struct page *page)
 	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
+	VM_BUG_ON_PAGE(PageTail(page), page);
+	VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page);
+
 	if (!TestSetPageMlocked(page)) {
 		mod_zone_page_state(page_zone(page), NR_MLOCK,
 				    hpage_nr_pages(page));
@@ -178,6 +181,8 @@ unsigned int munlock_vma_page(struct page *page)
 	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
+	VM_BUG_ON_PAGE(PageTail(page), page);
+
 	/*
 	 * Serialize with any parallel __split_huge_page_refcount() which
 	 * might otherwise copy PageMlocked to part of the tail pages before
@@ -388,6 +393,13 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
 		if (!page || page_zone_id(page) != zoneid)
 			break;
 
+		/*
+		 * Do not use pagevec for PTE-mapped THP,
+		 * munlock_vma_pages_range() will handle them.
+		 */
+		if (PageTransCompound(page))
+			break;
+
 		get_page(page);
 		/*
 		 * Increase the address that will be returned *before* the
@@ -444,7 +456,10 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 				&page_mask);
 
 		if (page && !IS_ERR(page)) {
-			if (PageTransHuge(page)) {
+			if (PageTransTail(page)) {
+				VM_BUG_ON_PAGE(PageMlocked(page), page);
+				put_page(page); /* follow_page_mask() */
+			} else if (PageTransHuge(page)) {
 				lock_page(page);
 				/*
 				 * Any THP page found by follow_page_mask() may
@@ -477,8 +492,6 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 				goto next;
 			}
 		}
-		/* 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:
diff --git a/mm/mmap.c b/mm/mmap.c
index b3f00b6..84b1262 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3184,10 +3184,16 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
  * mapping->flags avoid to take the same lock twice, if more than one
  * vma in this mm is backed by the same anon_vma or address_space.
  *
- * We can take all the locks in random order because the VM code
- * taking i_mmap_rwsem or anon_vma->rwsem outside the mmap_sem never
- * takes more than one of them in a row. Secondly we're protected
- * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
+ * We take locks in following order, accordingly to comment at beginning
+ * of mm/rmap.c:
+ *   - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for
+ *     hugetlb mapping);
+ *   - all i_mmap_rwsem locks;
+ *   - all anon_vma->rwseml
+ *
+ * We can take all locks within these types randomly because the VM code
+ * doesn't nest them and we protected from parallel mm_take_all_locks() by
+ * mm_all_locks_mutex.
  *
  * mm_take_all_locks() and mm_drop_all_locks are expensive operations
  * that may have to take thousand of locks.
@@ -3206,7 +3212,16 @@ int mm_take_all_locks(struct mm_struct *mm)
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		if (signal_pending(current))
 			goto out_unlock;
-		if (vma->vm_file && vma->vm_file->f_mapping)
+		if (vma->vm_file && vma->vm_file->f_mapping &&
+				is_vm_hugetlb_page(vma))
+			vm_lock_mapping(mm, vma->vm_file->f_mapping);
+	}
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (signal_pending(current))
+			goto out_unlock;
+		if (vma->vm_file && vma->vm_file->f_mapping &&
+				!is_vm_hugetlb_page(vma))
 			vm_lock_mapping(mm, vma->vm_file->f_mapping);
 	}
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index c764402..8eb7bb4 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -149,7 +149,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		unsigned long this_pages;
 
 		next = pmd_addr_end(addr, end);
-		if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd))
+		if (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)
+				&& pmd_none_or_clear_bad(pmd))
 			continue;
 
 		/* invoke the mmu notifier if the pmd is populated */
@@ -158,9 +159,9 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			mmu_notifier_invalidate_range_start(mm, mni_start, end);
 		}
 
-		if (pmd_trans_huge(*pmd)) {
+		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
-				split_huge_page_pmd(vma, addr, pmd);
+				split_huge_pmd(vma, pmd, addr);
 			else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
 						newprot, prot_numa);
diff --git a/mm/mremap.c b/mm/mremap.c
index e55b157..d77946a 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -192,25 +192,24 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		if (!new_pmd)
 			break;
 		if (pmd_trans_huge(*old_pmd)) {
-			int err = 0;
 			if (extent == HPAGE_PMD_SIZE) {
+				bool moved;
 				VM_BUG_ON_VMA(vma->vm_file || !vma->anon_vma,
 					      vma);
 				/* See comment in move_ptes() */
 				if (need_rmap_locks)
 					anon_vma_lock_write(vma->anon_vma);
-				err = move_huge_pmd(vma, new_vma, old_addr,
+				moved = move_huge_pmd(vma, new_vma, old_addr,
 						    new_addr, old_end,
 						    old_pmd, new_pmd);
 				if (need_rmap_locks)
 					anon_vma_unlock_write(vma->anon_vma);
+				if (moved) {
+					need_flush = true;
+					continue;
+				}
 			}
-			if (err > 0) {
-				need_flush = true;
-				continue;
-			} else if (!err) {
-				split_huge_page_pmd(vma, old_addr, old_pmd);
-			}
+			split_huge_pmd(vma, old_pmd, old_addr);
 			VM_BUG_ON(pmd_trans_huge(*old_pmd));
 		}
 		if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ce63d60..63358d9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -43,6 +43,7 @@
 #include <linux/vmalloc.h>
 #include <linux/vmstat.h>
 #include <linux/mempolicy.h>
+#include <linux/memremap.h>
 #include <linux/stop_machine.h>
 #include <linux/sort.h>
 #include <linux/pfn.h>
@@ -222,13 +223,15 @@ static char * const zone_names[MAX_NR_ZONES] = {
 #endif
 };
 
-static void free_compound_page(struct page *page);
 compound_page_dtor * const compound_page_dtors[] = {
 	NULL,
 	free_compound_page,
 #ifdef CONFIG_HUGETLB_PAGE
 	free_huge_page,
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	free_transhuge_page,
+#endif
 };
 
 int min_free_kbytes = 1024;
@@ -450,7 +453,7 @@ out:
  * This usage means that zero-order pages may not be compound.
  */
 
-static void free_compound_page(struct page *page)
+void free_compound_page(struct page *page)
 {
 	__free_pages_ok(page, compound_order(page));
 }
@@ -466,8 +469,10 @@ void prep_compound_page(struct page *page, unsigned int order)
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 		set_page_count(p, 0);
+		p->mapping = TAIL_MAPPING;
 		set_compound_head(p, page);
 	}
+	atomic_set(compound_mapcount_ptr(page), -1);
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -732,7 +737,7 @@ static inline int free_pages_check(struct page *page)
 	const char *bad_reason = NULL;
 	unsigned long bad_flags = 0;
 
-	if (unlikely(page_mapcount(page)))
+	if (unlikely(atomic_read(&page->_mapcount) != -1))
 		bad_reason = "nonzero mapcount";
 	if (unlikely(page->mapping != NULL))
 		bad_reason = "non-NULL mapping";
@@ -856,6 +861,27 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
 		ret = 0;
 		goto out;
 	}
+	switch (page - head_page) {
+	case 1:
+		/* the first tail page: ->mapping is compound_mapcount() */
+		if (unlikely(compound_mapcount(page))) {
+			bad_page(page, "nonzero compound_mapcount", 0);
+			goto out;
+		}
+		break;
+	case 2:
+		/*
+		 * the second tail page: ->mapping is
+		 * page_deferred_list().next -- ignore value.
+		 */
+		break;
+	default:
+		if (page->mapping != TAIL_MAPPING) {
+			bad_page(page, "corrupted mapping in tail page", 0);
+			goto out;
+		}
+		break;
+	}
 	if (unlikely(!PageTail(page))) {
 		bad_page(page, "PageTail not set", 0);
 		goto out;
@@ -866,6 +892,7 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
 	}
 	ret = 0;
 out:
+	page->mapping = NULL;
 	clear_compound_head(page);
 	return ret;
 }
@@ -1329,7 +1356,7 @@ static inline int check_new_page(struct page *page)
 	const char *bad_reason = NULL;
 	unsigned long bad_flags = 0;
 
-	if (unlikely(page_mapcount(page)))
+	if (unlikely(atomic_read(&page->_mapcount) != -1))
 		bad_reason = "nonzero mapcount";
 	if (unlikely(page->mapping != NULL))
 		bad_reason = "non-NULL mapping";
@@ -4459,16 +4486,22 @@ static inline unsigned long wait_table_bits(unsigned long size)
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		unsigned long start_pfn, enum memmap_context context)
 {
-	pg_data_t *pgdat = NODE_DATA(nid);
+	struct vmem_altmap *altmap = to_vmem_altmap(__pfn_to_phys(start_pfn));
 	unsigned long end_pfn = start_pfn + size;
+	pg_data_t *pgdat = NODE_DATA(nid);
 	unsigned long pfn;
-	struct zone *z;
 	unsigned long nr_initialised = 0;
 
 	if (highest_memmap_pfn < end_pfn - 1)
 		highest_memmap_pfn = end_pfn - 1;
 
-	z = &pgdat->node_zones[zone];
+	/*
+	 * Honor reservation requested by the driver for this ZONE_DEVICE
+	 * memory
+	 */
+	if (altmap && start_pfn == altmap->base_pfn)
+		start_pfn += altmap->reserve;
+
 	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
 		/*
 		 * There can be holes in boot-time mem_map[]s
diff --git a/mm/page_idle.c b/mm/page_idle.c
index d5dd790..4ea9c4e 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -55,25 +55,26 @@ static int page_idle_clear_pte_refs_one(struct page *page,
 					unsigned long addr, void *arg)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	spinlock_t *ptl;
 	pmd_t *pmd;
 	pte_t *pte;
+	spinlock_t *ptl;
 	bool referenced = false;
 
-	if (unlikely(PageTransHuge(page))) {
-		pmd = page_check_address_pmd(page, mm, addr,
-					     PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl);
-		if (pmd) {
-			referenced = pmdp_clear_young_notify(vma, addr, pmd);
-			spin_unlock(ptl);
-		}
+	if (!page_check_address_transhuge(page, mm, addr, &pmd, &pte, &ptl))
+		return SWAP_AGAIN;
+
+	if (pte) {
+		referenced = ptep_clear_young_notify(vma, addr, pte);
+		pte_unmap(pte);
+	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+		referenced = pmdp_clear_young_notify(vma, addr, pmd);
 	} else {
-		pte = page_check_address(page, mm, addr, &ptl, 0);
-		if (pte) {
-			referenced = ptep_clear_young_notify(vma, addr, pte);
-			pte_unmap_unlock(pte, ptl);
-		}
+		/* unexpected pmd-mapped page? */
+		WARN_ON_ONCE(1);
 	}
+
+	spin_unlock(ptl);
+
 	if (referenced) {
 		clear_page_idle(page);
 		/*
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 5e139fe..92c4c36 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -196,8 +196,10 @@ int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 {
 	unsigned long pfn;
 	struct page *page;
-	BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
-	BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
+
+	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
+	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
+
 	for (pfn = start_pfn;
 	     pfn < end_pfn;
 	     pfn += pageblock_nr_pages) {
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 29f2f8b..2072444 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -58,7 +58,7 @@ again:
 		if (!walk->pte_entry)
 			continue;
 
-		split_huge_page_pmd_mm(walk->mm, addr, pmd);
+		split_huge_pmd(walk->vma, pmd, addr);
 		if (pmd_trans_unstable(pmd))
 			goto again;
 		err = walk_pte_range(pmd, addr, next, walk);
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 4c681ba..9d47676 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -132,25 +132,13 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
 {
 	pmd_t pmd;
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	VM_BUG_ON(!pmd_trans_huge(*pmdp));
+	VM_BUG_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
 }
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
-			  pmd_t *pmdp)
-{
-	pmd_t pmd = pmd_mksplitting(*pmdp);
-	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
-	/* tlb flush only to serialize against gup-fast */
-	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
-}
-#endif
-
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pgtable)
diff --git a/mm/rmap.c b/mm/rmap.c
index 622756c..79f3bf0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -23,21 +23,22 @@
  * inode->i_mutex	(while writing or truncating, not reading or faulting)
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
- *       mapping->i_mmap_rwsem
- *         anon_vma->rwsem
- *           mm->page_table_lock or pte_lock
- *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
- *             swap_lock (in swap_duplicate, swap_info_get)
- *               mmlist_lock (in mmput, drain_mmlist and others)
- *               mapping->private_lock (in __set_page_dirty_buffers)
- *                 mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
- *                   mapping->tree_lock (widely used)
- *               inode->i_lock (in set_page_dirty's __mark_inode_dirty)
- *               bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
- *                 sb_lock (within inode_lock in fs/fs-writeback.c)
- *                 mapping->tree_lock (widely used, in set_page_dirty,
- *                           in arch-dependent flush_dcache_mmap_lock,
- *                           within bdi.wb->list_lock in __sync_single_inode)
+ *       hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
+ *         mapping->i_mmap_rwsem
+ *           anon_vma->rwsem
+ *             mm->page_table_lock or pte_lock
+ *               zone->lru_lock (in mark_page_accessed, isolate_lru_page)
+ *               swap_lock (in swap_duplicate, swap_info_get)
+ *                 mmlist_lock (in mmput, drain_mmlist and others)
+ *                 mapping->private_lock (in __set_page_dirty_buffers)
+ *                   mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
+ *                     mapping->tree_lock (widely used)
+ *                 inode->i_lock (in set_page_dirty's __mark_inode_dirty)
+ *                 bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
+ *                   sb_lock (within inode_lock in fs/fs-writeback.c)
+ *                   mapping->tree_lock (widely used, in set_page_dirty,
+ *                             in arch-dependent flush_dcache_mmap_lock,
+ *                             within bdi.wb->list_lock in __sync_single_inode)
  *
  * anon_vma->rwsem,mapping->i_mutex      (memory_failure, collect_procs_anon)
  *   ->tasklist_lock
@@ -567,27 +568,6 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
 	anon_vma_unlock_read(anon_vma);
 }
 
-/*
- * At what user virtual address is page expected in @vma?
- */
-static inline unsigned long
-__vma_address(struct page *page, struct vm_area_struct *vma)
-{
-	pgoff_t pgoff = page_to_pgoff(page);
-	return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
-}
-
-inline unsigned long
-vma_address(struct page *page, struct vm_area_struct *vma)
-{
-	unsigned long address = __vma_address(page, vma);
-
-	/* page should be within @vma mapping range */
-	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
-
-	return address;
-}
-
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 static void percpu_flush_tlb_batch_pages(void *data)
 {
@@ -819,6 +799,96 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
 	return 1;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * Check that @page is mapped at @address into @mm. In contrast to
+ * page_check_address(), this function can handle transparent huge pages.
+ *
+ * On success returns true with pte mapped and locked. For PMD-mapped
+ * transparent huge pages *@ptep is set to NULL.
+ */
+bool page_check_address_transhuge(struct page *page, struct mm_struct *mm,
+				  unsigned long address, pmd_t **pmdp,
+				  pte_t **ptep, spinlock_t **ptlp)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	if (unlikely(PageHuge(page))) {
+		/* when pud is not present, pte will be NULL */
+		pte = huge_pte_offset(mm, address);
+		if (!pte)
+			return false;
+
+		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
+		pmd = NULL;
+		goto check_pte;
+	}
+
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
+		return false;
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		return false;
+	pmd = pmd_offset(pud, address);
+
+	if (pmd_trans_huge(*pmd)) {
+		ptl = pmd_lock(mm, pmd);
+		if (!pmd_present(*pmd))
+			goto unlock_pmd;
+		if (unlikely(!pmd_trans_huge(*pmd))) {
+			spin_unlock(ptl);
+			goto map_pte;
+		}
+
+		if (pmd_page(*pmd) != page)
+			goto unlock_pmd;
+
+		pte = NULL;
+		goto found;
+unlock_pmd:
+		spin_unlock(ptl);
+		return false;
+	} else {
+		pmd_t pmde = *pmd;
+
+		barrier();
+		if (!pmd_present(pmde) || pmd_trans_huge(pmde))
+			return false;
+	}
+map_pte:
+	pte = pte_offset_map(pmd, address);
+	if (!pte_present(*pte)) {
+		pte_unmap(pte);
+		return false;
+	}
+
+	ptl = pte_lockptr(mm, pmd);
+check_pte:
+	spin_lock(ptl);
+
+	if (!pte_present(*pte)) {
+		pte_unmap_unlock(pte, ptl);
+		return false;
+	}
+
+	/* THP can be referenced by any subpage */
+	if (pte_pfn(*pte) - page_to_pfn(page) >= hpage_nr_pages(page)) {
+		pte_unmap_unlock(pte, ptl);
+		return false;
+	}
+found:
+	*ptep = pte;
+	*pmdp = pmd;
+	*ptlp = ptl;
+	return true;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 struct page_referenced_arg {
 	int mapcount;
 	int referenced;
@@ -832,49 +902,24 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			unsigned long address, void *arg)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct page_referenced_arg *pra = arg;
+	pmd_t *pmd;
+	pte_t *pte;
 	spinlock_t *ptl;
 	int referenced = 0;
-	struct page_referenced_arg *pra = arg;
-
-	if (unlikely(PageTransHuge(page))) {
-		pmd_t *pmd;
 
-		/*
-		 * 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, &ptl);
-		if (!pmd)
-			return SWAP_AGAIN;
-
-		if (vma->vm_flags & VM_LOCKED) {
-			spin_unlock(ptl);
-			pra->vm_flags |= VM_LOCKED;
-			return SWAP_FAIL; /* To break the loop */
-		}
+	if (!page_check_address_transhuge(page, mm, address, &pmd, &pte, &ptl))
+		return SWAP_AGAIN;
 
-		/* go ahead even if the pmd is pmd_trans_splitting() */
-		if (pmdp_clear_flush_young_notify(vma, address, pmd))
-			referenced++;
+	if (vma->vm_flags & VM_LOCKED) {
+		if (pte)
+			pte_unmap(pte);
 		spin_unlock(ptl);
-	} else {
-		pte_t *pte;
-
-		/*
-		 * rmap might return false positives; we must filter
-		 * these out using page_check_address().
-		 */
-		pte = page_check_address(page, mm, address, &ptl, 0);
-		if (!pte)
-			return SWAP_AGAIN;
-
-		if (vma->vm_flags & VM_LOCKED) {
-			pte_unmap_unlock(pte, ptl);
-			pra->vm_flags |= VM_LOCKED;
-			return SWAP_FAIL; /* To break the loop */
-		}
+		pra->vm_flags |= VM_LOCKED;
+		return SWAP_FAIL; /* To break the loop */
+	}
 
+	if (pte) {
 		if (ptep_clear_flush_young_notify(vma, address, pte)) {
 			/*
 			 * Don't treat a reference through a sequentially read
@@ -886,8 +931,15 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			if (likely(!(vma->vm_flags & VM_SEQ_READ)))
 				referenced++;
 		}
-		pte_unmap_unlock(pte, ptl);
+		pte_unmap(pte);
+	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+		if (pmdp_clear_flush_young_notify(vma, address, pmd))
+			referenced++;
+	} else {
+		/* unexpected pmd-mapped page? */
+		WARN_ON_ONCE(1);
 	}
+	spin_unlock(ptl);
 
 	if (referenced)
 		clear_page_idle(page);
@@ -935,7 +987,7 @@ int page_referenced(struct page *page,
 	int ret;
 	int we_locked = 0;
 	struct page_referenced_arg pra = {
-		.mapcount = page_mapcount(page),
+		.mapcount = total_mapcount(page),
 		.memcg = memcg,
 	};
 	struct rmap_walk_control rwc = {
@@ -1124,7 +1176,7 @@ static void __page_check_anon_rmap(struct page *page,
 	 * over the call to page_add_new_anon_rmap.
 	 */
 	BUG_ON(page_anon_vma(page)->root != vma->anon_vma->root);
-	BUG_ON(page->index != linear_page_index(vma, address));
+	BUG_ON(page_to_pgoff(page) != linear_page_index(vma, address));
 #endif
 }
 
@@ -1133,6 +1185,7 @@ static void __page_check_anon_rmap(struct page *page,
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
+ * @compound:	charge the page as compound or small page
  *
  * The caller needs to hold the pte lock, and the page must be locked in
  * the anon_vma case: to serialize mapping,index checking after setting,
@@ -1140,9 +1193,9 @@ static void __page_check_anon_rmap(struct page *page,
  * (but PageKsm is never downgraded to PageAnon).
  */
 void page_add_anon_rmap(struct page *page,
-	struct vm_area_struct *vma, unsigned long address)
+	struct vm_area_struct *vma, unsigned long address, bool compound)
 {
-	do_page_add_anon_rmap(page, vma, address, 0);
+	do_page_add_anon_rmap(page, vma, address, compound ? RMAP_COMPOUND : 0);
 }
 
 /*
@@ -1151,29 +1204,44 @@ void page_add_anon_rmap(struct page *page,
  * Everybody else should continue to use page_add_anon_rmap above.
  */
 void do_page_add_anon_rmap(struct page *page,
-	struct vm_area_struct *vma, unsigned long address, int exclusive)
+	struct vm_area_struct *vma, unsigned long address, int flags)
 {
-	int first = atomic_inc_and_test(&page->_mapcount);
+	bool compound = flags & RMAP_COMPOUND;
+	bool first;
+
+	if (compound) {
+		atomic_t *mapcount;
+		VM_BUG_ON_PAGE(!PageLocked(page), page);
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+		mapcount = compound_mapcount_ptr(page);
+		first = atomic_inc_and_test(mapcount);
+	} else {
+		first = atomic_inc_and_test(&page->_mapcount);
+	}
+
 	if (first) {
+		int nr = compound ? hpage_nr_pages(page) : 1;
 		/*
 		 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
 		 * these counters are not modified in interrupt context, and
 		 * pte lock(a spinlock) is held, which implies preemption
 		 * disabled.
 		 */
-		if (PageTransHuge(page))
+		if (compound) {
 			__inc_zone_page_state(page,
 					      NR_ANON_TRANSPARENT_HUGEPAGES);
-		__mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
-				hpage_nr_pages(page));
+		}
+		__mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr);
 	}
 	if (unlikely(PageKsm(page)))
 		return;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
+
 	/* address might be in next vma when migration races vma_adjust */
 	if (first)
-		__page_set_anon_rmap(page, vma, address, exclusive);
+		__page_set_anon_rmap(page, vma, address,
+				flags & RMAP_EXCLUSIVE);
 	else
 		__page_check_anon_rmap(page, vma, address);
 }
@@ -1183,21 +1251,31 @@ void do_page_add_anon_rmap(struct page *page,
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
+ * @compound:	charge the page as compound or small page
  *
  * Same as page_add_anon_rmap but must only be called on *new* pages.
  * This means the inc-and-test can be bypassed.
  * Page does not have to be locked.
  */
 void page_add_new_anon_rmap(struct page *page,
-	struct vm_area_struct *vma, unsigned long address)
+	struct vm_area_struct *vma, unsigned long address, bool compound)
 {
+	int nr = compound ? hpage_nr_pages(page) : 1;
+
 	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
 	SetPageSwapBacked(page);
-	atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
-	if (PageTransHuge(page))
+	if (compound) {
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+		/* increment count (starts at -1) */
+		atomic_set(compound_mapcount_ptr(page), 0);
 		__inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
-	__mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
-			hpage_nr_pages(page));
+	} else {
+		/* Anon THP always mapped first with PMD */
+		VM_BUG_ON_PAGE(PageTransCompound(page), page);
+		/* increment count (starts at -1) */
+		atomic_set(&page->_mapcount, 0);
+	}
+	__mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr);
 	__page_set_anon_rmap(page, vma, address, 1);
 }
 
@@ -1225,12 +1303,15 @@ static void page_remove_file_rmap(struct page *page)
 
 	memcg = mem_cgroup_begin_page_stat(page);
 
-	/* page still mapped by someone else? */
-	if (!atomic_add_negative(-1, &page->_mapcount))
+	/* Hugepages are not counted in NR_FILE_MAPPED for now. */
+	if (unlikely(PageHuge(page))) {
+		/* hugetlb pages are always mapped with pmds */
+		atomic_dec(compound_mapcount_ptr(page));
 		goto out;
+	}
 
-	/* Hugepages are not counted in NR_FILE_MAPPED for now. */
-	if (unlikely(PageHuge(page)))
+	/* page still mapped by someone else? */
+	if (!atomic_add_negative(-1, &page->_mapcount))
 		goto out;
 
 	/*
@@ -1247,41 +1328,79 @@ out:
 	mem_cgroup_end_page_stat(memcg);
 }
 
+static void page_remove_anon_compound_rmap(struct page *page)
+{
+	int i, nr;
+
+	if (!atomic_add_negative(-1, compound_mapcount_ptr(page)))
+		return;
+
+	/* Hugepages are not counted in NR_ANON_PAGES for now. */
+	if (unlikely(PageHuge(page)))
+		return;
+
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return;
+
+	__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
+
+	if (TestClearPageDoubleMap(page)) {
+		/*
+		 * Subpages can be mapped with PTEs too. Check how many of
+		 * themi are still mapped.
+		 */
+		for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) {
+			if (atomic_add_negative(-1, &page[i]._mapcount))
+				nr++;
+		}
+	} else {
+		nr = HPAGE_PMD_NR;
+	}
+
+	if (unlikely(PageMlocked(page)))
+		clear_page_mlock(page);
+
+	if (nr) {
+		__mod_zone_page_state(page_zone(page), NR_ANON_PAGES, -nr);
+		deferred_split_huge_page(page);
+	}
+}
+
 /**
  * page_remove_rmap - take down pte mapping from a page
- * @page: page to remove mapping from
+ * @page:	page to remove mapping from
+ * @compound:	uncharge the page as compound or small page
  *
  * The caller needs to hold the pte lock.
  */
-void page_remove_rmap(struct page *page)
+void page_remove_rmap(struct page *page, bool compound)
 {
 	if (!PageAnon(page)) {
+		VM_BUG_ON_PAGE(compound && !PageHuge(page), page);
 		page_remove_file_rmap(page);
 		return;
 	}
 
+	if (compound)
+		return page_remove_anon_compound_rmap(page);
+
 	/* page still mapped by someone else? */
 	if (!atomic_add_negative(-1, &page->_mapcount))
 		return;
 
-	/* Hugepages are not counted in NR_ANON_PAGES for now. */
-	if (unlikely(PageHuge(page)))
-		return;
-
 	/*
 	 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
 	 * these counters are not modified in interrupt context, and
 	 * pte lock(a spinlock) is held, which implies preemption disabled.
 	 */
-	if (PageTransHuge(page))
-		__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
-
-	__mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
-			      -hpage_nr_pages(page));
+	__dec_zone_page_state(page, NR_ANON_PAGES);
 
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
 
+	if (PageTransCompound(page))
+		deferred_split_huge_page(compound_head(page));
+
 	/*
 	 * It would be tidy to reset the PageAnon mapping here,
 	 * but that might overwrite a racing page_add_anon_rmap
@@ -1293,6 +1412,11 @@ void page_remove_rmap(struct page *page)
 	 */
 }
 
+struct rmap_private {
+	enum ttu_flags flags;
+	int lazyfreed;
+};
+
 /*
  * @arg: enum ttu_flags will be passed to this argument
  */
@@ -1304,7 +1428,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	pte_t pteval;
 	spinlock_t *ptl;
 	int ret = SWAP_AGAIN;
-	enum ttu_flags flags = (enum ttu_flags)arg;
+	struct rmap_private *rp = arg;
+	enum ttu_flags flags = rp->flags;
 
 	/* munlock has nothing to gain from examining un-locked vmas */
 	if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
@@ -1396,6 +1521,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		 * See handle_pte_fault() ...
 		 */
 		VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+
+		if (!PageDirty(page) && (flags & TTU_LZFREE)) {
+			/* It's a freeable page by MADV_FREE */
+			dec_mm_counter(mm, MM_ANONPAGES);
+			rp->lazyfreed++;
+			goto discard;
+		}
+
 		if (swap_duplicate(entry) < 0) {
 			set_pte_at(mm, address, pte, pteval);
 			ret = SWAP_FAIL;
@@ -1416,7 +1549,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	} else
 		dec_mm_counter(mm, mm_counter_file(page));
 
-	page_remove_rmap(page);
+discard:
+	page_remove_rmap(page, PageHuge(page));
 	page_cache_release(page);
 
 out_unmap:
@@ -1468,9 +1602,14 @@ static int page_not_mapped(struct page *page)
 int try_to_unmap(struct page *page, enum ttu_flags flags)
 {
 	int ret;
+	struct rmap_private rp = {
+		.flags = flags,
+		.lazyfreed = 0,
+	};
+
 	struct rmap_walk_control rwc = {
 		.rmap_one = try_to_unmap_one,
-		.arg = (void *)flags,
+		.arg = &rp,
 		.done = page_not_mapped,
 		.anon_lock = page_lock_anon_vma_read,
 	};
@@ -1490,8 +1629,11 @@ int try_to_unmap(struct page *page, enum ttu_flags flags)
 
 	ret = rmap_walk(page, &rwc);
 
-	if (ret != SWAP_MLOCK && !page_mapped(page))
+	if (ret != SWAP_MLOCK && !page_mapped(page)) {
 		ret = SWAP_SUCCESS;
+		if (rp.lazyfreed && !PageDirty(page))
+			ret = SWAP_LZFREE;
+	}
 	return ret;
 }
 
@@ -1513,9 +1655,14 @@ int try_to_unmap(struct page *page, enum ttu_flags flags)
 int try_to_munlock(struct page *page)
 {
 	int ret;
+	struct rmap_private rp = {
+		.flags = TTU_MUNLOCK,
+		.lazyfreed = 0,
+	};
+
 	struct rmap_walk_control rwc = {
 		.rmap_one = try_to_unmap_one,
-		.arg = (void *)TTU_MUNLOCK,
+		.arg = &rp,
 		.done = page_not_mapped,
 		.anon_lock = page_lock_anon_vma_read,
 
@@ -1698,7 +1845,7 @@ void hugepage_add_anon_rmap(struct page *page,
 	BUG_ON(!PageLocked(page));
 	BUG_ON(!anon_vma);
 	/* address might be in next vma when migration races vma_adjust */
-	first = atomic_inc_and_test(&page->_mapcount);
+	first = atomic_inc_and_test(compound_mapcount_ptr(page));
 	if (first)
 		__hugepage_set_anon_rmap(page, vma, address, 0);
 }
@@ -1707,7 +1854,7 @@ void hugepage_add_new_anon_rmap(struct page *page,
 			struct vm_area_struct *vma, unsigned long address)
 {
 	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
-	atomic_set(&page->_mapcount, 0);
+	atomic_set(compound_mapcount_ptr(page), 0);
 	__hugepage_set_anon_rmap(page, vma, address, 1);
 }
 #endif /* CONFIG_HUGETLB_PAGE */
diff --git a/mm/shmem.c b/mm/shmem.c
index 970ff5b..b98e101 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -810,7 +810,8 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
 	 * Charged back to the user (not to caller) when swap account is used.
 	 */
-	error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg);
+	error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg,
+			false);
 	if (error)
 		goto out;
 	/* No radix_tree_preload: swap entry keeps a place for page in tree */
@@ -833,9 +834,9 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	if (error) {
 		if (error != -ENOMEM)
 			error = 0;
-		mem_cgroup_cancel_charge(page, memcg);
+		mem_cgroup_cancel_charge(page, memcg, false);
 	} else
-		mem_cgroup_commit_charge(page, memcg, true);
+		mem_cgroup_commit_charge(page, memcg, true, false);
 out:
 	unlock_page(page);
 	page_cache_release(page);
@@ -1085,7 +1086,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	copy_highpage(newpage, oldpage);
 	flush_dcache_page(newpage);
 
-	__set_page_locked(newpage);
+	__SetPageLocked(newpage);
 	SetPageUptodate(newpage);
 	SetPageSwapBacked(newpage);
 	set_page_private(newpage, swap_index);
@@ -1218,7 +1219,8 @@ repeat:
 				goto failed;
 		}
 
-		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
+		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg,
+				false);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
 						swp_to_radix_entry(swap));
@@ -1235,14 +1237,14 @@ repeat:
 			 * "repeat": reading a hole and writing should succeed.
 			 */
 			if (error) {
-				mem_cgroup_cancel_charge(page, memcg);
+				mem_cgroup_cancel_charge(page, memcg, false);
 				delete_from_swap_cache(page);
 			}
 		}
 		if (error)
 			goto failed;
 
-		mem_cgroup_commit_charge(page, memcg, true);
+		mem_cgroup_commit_charge(page, memcg, true, false);
 
 		spin_lock(&info->lock);
 		info->swapped--;
@@ -1277,11 +1279,12 @@ repeat:
 		}
 
 		__SetPageSwapBacked(page);
-		__set_page_locked(page);
+		__SetPageLocked(page);
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 
-		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
+		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg,
+				false);
 		if (error)
 			goto decused;
 		error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);
@@ -1291,10 +1294,10 @@ repeat:
 			radix_tree_preload_end();
 		}
 		if (error) {
-			mem_cgroup_cancel_charge(page, memcg);
+			mem_cgroup_cancel_charge(page, memcg, false);
 			goto decused;
 		}
-		mem_cgroup_commit_charge(page, memcg, false);
+		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_anon(page);
 
 		spin_lock(&info->lock);
diff --git a/mm/slub.c b/mm/slub.c
index 2d0e610..b21fd24 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -338,11 +338,13 @@ static inline int oo_objects(struct kmem_cache_order_objects x)
  */
 static __always_inline void slab_lock(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	bit_spin_lock(PG_locked, &page->flags);
 }
 
 static __always_inline void slab_unlock(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	__bit_spin_unlock(PG_locked, &page->flags);
 }
 
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 4cba9c2..b60802b 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/bootmem.h>
+#include <linux/memremap.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -70,7 +71,7 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 }
 
 /* need to make sure size is all the same during early stage */
-void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node)
+static void * __meminit alloc_block_buf(unsigned long size, int node)
 {
 	void *ptr;
 
@@ -87,6 +88,77 @@ void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node)
 	return ptr;
 }
 
+static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap)
+{
+	return altmap->base_pfn + altmap->reserve + altmap->alloc
+		+ altmap->align;
+}
+
+static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap)
+{
+	unsigned long allocated = altmap->alloc + altmap->align;
+
+	if (altmap->free > allocated)
+		return altmap->free - allocated;
+	return 0;
+}
+
+/**
+ * vmem_altmap_alloc - allocate pages from the vmem_altmap reservation
+ * @altmap - reserved page pool for the allocation
+ * @nr_pfns - size (in pages) of the allocation
+ *
+ * Allocations are aligned to the size of the request
+ */
+static unsigned long __meminit vmem_altmap_alloc(struct vmem_altmap *altmap,
+		unsigned long nr_pfns)
+{
+	unsigned long pfn = vmem_altmap_next_pfn(altmap);
+	unsigned long nr_align;
+
+	nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG);
+	nr_align = ALIGN(pfn, nr_align) - pfn;
+
+	if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap))
+		return ULONG_MAX;
+	altmap->alloc += nr_pfns;
+	altmap->align += nr_align;
+	return pfn + nr_align;
+}
+
+static void * __meminit altmap_alloc_block_buf(unsigned long size,
+		struct vmem_altmap *altmap)
+{
+	unsigned long pfn, nr_pfns;
+	void *ptr;
+
+	if (size & ~PAGE_MASK) {
+		pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n",
+				__func__, size);
+		return NULL;
+	}
+
+	nr_pfns = size >> PAGE_SHIFT;
+	pfn = vmem_altmap_alloc(altmap, nr_pfns);
+	if (pfn < ULONG_MAX)
+		ptr = __va(__pfn_to_phys(pfn));
+	else
+		ptr = NULL;
+	pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n",
+			__func__, pfn, altmap->alloc, altmap->align, nr_pfns);
+
+	return ptr;
+}
+
+/* need to make sure size is all the same during early stage */
+void * __meminit __vmemmap_alloc_block_buf(unsigned long size, int node,
+		struct vmem_altmap *altmap)
+{
+	if (altmap)
+		return altmap_alloc_block_buf(size, altmap);
+	return alloc_block_buf(size, node);
+}
+
 void __meminit vmemmap_verify(pte_t *pte, int node,
 				unsigned long start, unsigned long end)
 {
@@ -103,7 +175,7 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
 	pte_t *pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte)) {
 		pte_t entry;
-		void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
+		void *p = alloc_block_buf(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
diff --git a/mm/sparse.c b/mm/sparse.c
index d1b48b6..3717cee 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -748,7 +748,7 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 	if (!memmap)
 		return;
 
-	for (i = 0; i < PAGES_PER_SECTION; i++) {
+	for (i = 0; i < nr_pages; i++) {
 		if (PageHWPoison(&memmap[i])) {
 			atomic_long_sub(1, &num_poisoned_pages);
 			ClearPageHWPoison(&memmap[i]);
@@ -788,7 +788,8 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 		free_map_bootmem(memmap);
 }
 
-void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
+void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
+		unsigned long map_offset)
 {
 	struct page *memmap = NULL;
 	unsigned long *usemap = NULL, flags;
@@ -804,7 +805,8 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
 	}
 	pgdat_resize_unlock(pgdat, &flags);
 
-	clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION);
+	clear_hwpoisoned_pages(memmap + map_offset,
+			PAGES_PER_SECTION - map_offset);
 	free_section_usemap(memmap, usemap);
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
diff --git a/mm/swap.c b/mm/swap.c
index 39395fb..09fe5e9 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -24,6 +24,7 @@
 #include <linux/export.h>
 #include <linux/mm_inline.h>
 #include <linux/percpu_counter.h>
+#include <linux/memremap.h>
 #include <linux/percpu.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
@@ -45,6 +46,7 @@ int page_cluster;
 static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
 static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
 static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
+static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
 
 /*
  * This path almost never happens for VM activity - pages are normally
@@ -89,260 +91,14 @@ static void __put_compound_page(struct page *page)
 	(*dtor)(page);
 }
 
-/**
- * Two special cases here: we could avoid taking compound_lock_irqsave
- * and could skip the tail refcounting(in _mapcount).
- *
- * 1. Hugetlbfs page:
- *
- *    PageHeadHuge will remain true until the compound page
- *    is released and enters the buddy allocator, and it could
- *    not be split by __split_huge_page_refcount().
- *
- *    So if we see PageHeadHuge set, and we have the tail page pin,
- *    then we could safely put head page.
- *
- * 2. Slab THP page:
- *
- *    PG_slab is cleared before the slab frees the head page, and
- *    tail pin cannot be the last reference left on the head page,
- *    because the slab code is free to reuse the compound page
- *    after a kfree/kmem_cache_free without having to check if
- *    there's any tail pin left.  In turn all tail pinsmust be always
- *    released while the head is still pinned by the slab code
- *    and so we know PG_slab will be still set too.
- *
- *    So if we see PageSlab set, and we have the tail page pin,
- *    then we could safely put head page.
- */
-static __always_inline
-void put_unrefcounted_compound_page(struct page *page_head, struct page *page)
-{
-	/*
-	 * If @page is a THP tail, we must read the tail page
-	 * flags after the head page flags. The
-	 * __split_huge_page_refcount side enforces write memory barriers
-	 * between clearing PageTail and before the head page
-	 * can be freed and reallocated.
-	 */
-	smp_rmb();
-	if (likely(PageTail(page))) {
-		/*
-		 * __split_huge_page_refcount cannot race
-		 * here, see the comment above this function.
-		 */
-		VM_BUG_ON_PAGE(!PageHead(page_head), page_head);
-		if (put_page_testzero(page_head)) {
-			/*
-			 * If this is the tail of a slab THP page,
-			 * the tail pin must not be the last reference
-			 * held on the page, because the PG_slab cannot
-			 * be cleared before all tail pins (which skips
-			 * the _mapcount tail refcounting) have been
-			 * released.
-			 *
-			 * If this is the tail of a hugetlbfs page,
-			 * the tail pin may be the last reference on
-			 * the page instead, because PageHeadHuge will
-			 * not go away until the compound page enters
-			 * the buddy allocator.
-			 */
-			VM_BUG_ON_PAGE(PageSlab(page_head), page_head);
-			__put_compound_page(page_head);
-		}
-	} 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).
-		 */
-		if (put_page_testzero(page))
-			__put_single_page(page);
-}
-
-static __always_inline
-void put_refcounted_compound_page(struct page *page_head, struct page *page)
-{
-	if (likely(page != page_head && get_page_unless_zero(page_head))) {
-		unsigned long flags;
-
-		/*
-		 * @page_head wasn't a dangling pointer but it may not
-		 * be a head page anymore by the time we obtain the
-		 * lock. That is ok as long as it can't be freed from
-		 * under us.
-		 */
-		flags = compound_lock_irqsave(page_head);
-		if (unlikely(!PageTail(page))) {
-			/* __split_huge_page_refcount run before us */
-			compound_unlock_irqrestore(page_head, flags);
-			if (put_page_testzero(page_head)) {
-				/*
-				 * The @page_head may have been freed
-				 * and reallocated as a compound page
-				 * of smaller order and then freed
-				 * again.  All we know is that it
-				 * cannot have become: a THP page, a
-				 * compound page of higher order, a
-				 * tail page.  That is because we
-				 * still hold the refcount of the
-				 * split THP tail and page_head was
-				 * the THP head before the split.
-				 */
-				if (PageHead(page_head))
-					__put_compound_page(page_head);
-				else
-					__put_single_page(page_head);
-			}
-out_put_single:
-			if (put_page_testzero(page))
-				__put_single_page(page);
-			return;
-		}
-		VM_BUG_ON_PAGE(page_head != compound_head(page), page);
-		/*
-		 * We can release the refcount taken by
-		 * get_page_unless_zero() now that
-		 * __split_huge_page_refcount() is blocked on the
-		 * compound_lock.
-		 */
-		if (put_page_testzero(page_head))
-			VM_BUG_ON_PAGE(1, page_head);
-		/* __split_huge_page_refcount will wait now */
-		VM_BUG_ON_PAGE(page_mapcount(page) <= 0, page);
-		atomic_dec(&page->_mapcount);
-		VM_BUG_ON_PAGE(atomic_read(&page_head->_count) <= 0, page_head);
-		VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page);
-		compound_unlock_irqrestore(page_head, flags);
-
-		if (put_page_testzero(page_head)) {
-			if (PageHead(page_head))
-				__put_compound_page(page_head);
-			else
-				__put_single_page(page_head);
-		}
-	} else {
-		/* @page_head is a dangling pointer */
-		VM_BUG_ON_PAGE(PageTail(page), page);
-		goto out_put_single;
-	}
-}
-
-static void put_compound_page(struct page *page)
-{
-	struct page *page_head;
-
-	/*
-	 * We see the PageCompound set and PageTail not set, so @page maybe:
-	 *  1. hugetlbfs head page, or
-	 *  2. THP head page.
-	 */
-	if (likely(!PageTail(page))) {
-		if (put_page_testzero(page)) {
-			/*
-			 * By the time all refcounts have been released
-			 * split_huge_page cannot run anymore from under us.
-			 */
-			if (PageHead(page))
-				__put_compound_page(page);
-			else
-				__put_single_page(page);
-		}
-		return;
-	}
-
-	/*
-	 * We see the PageCompound set and PageTail set, so @page maybe:
-	 *  1. a tail hugetlbfs page, or
-	 *  2. a tail THP page, or
-	 *  3. a split THP page.
-	 *
-	 *  Case 3 is possible, as we may race with
-	 *  __split_huge_page_refcount tearing down a THP page.
-	 */
-	page_head = compound_head(page);
-	if (!__compound_tail_refcounted(page_head))
-		put_unrefcounted_compound_page(page_head, page);
-	else
-		put_refcounted_compound_page(page_head, page);
-}
-
-void put_page(struct page *page)
+void __put_page(struct page *page)
 {
 	if (unlikely(PageCompound(page)))
-		put_compound_page(page);
-	else if (put_page_testzero(page))
+		__put_compound_page(page);
+	else
 		__put_single_page(page);
 }
-EXPORT_SYMBOL(put_page);
-
-/*
- * This function is exported but must not be called by anything other
- * than get_page(). It implements the slow path of get_page().
- */
-bool __get_page_tail(struct page *page)
-{
-	/*
-	 * This takes care of get_page() if run on a tail page
-	 * returned by one of the get_user_pages/follow_page variants.
-	 * get_user_pages/follow_page itself doesn't need the compound
-	 * lock because it runs __get_page_tail_foll() under the
-	 * proper PT lock that already serializes against
-	 * split_huge_page().
-	 */
-	unsigned long flags;
-	bool got;
-	struct page *page_head = compound_head(page);
-
-	/* Ref to put_compound_page() comment. */
-	if (!__compound_tail_refcounted(page_head)) {
-		smp_rmb();
-		if (likely(PageTail(page))) {
-			/*
-			 * This is a hugetlbfs page or a slab
-			 * page. __split_huge_page_refcount
-			 * cannot race here.
-			 */
-			VM_BUG_ON_PAGE(!PageHead(page_head), page_head);
-			__get_page_tail_foll(page, true);
-			return true;
-		} else {
-			/*
-			 * __split_huge_page_refcount run
-			 * before us, "page" was a THP
-			 * tail. The split page_head has been
-			 * freed and reallocated as slab or
-			 * hugetlbfs page of smaller order
-			 * (only possible if reallocated as
-			 * slab on x86).
-			 */
-			return false;
-		}
-	}
-
-	got = false;
-	if (likely(page != page_head && get_page_unless_zero(page_head))) {
-		/*
-		 * page_head wasn't a dangling pointer but it
-		 * may not be a head page anymore by the time
-		 * 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;
-}
-EXPORT_SYMBOL(__get_page_tail);
+EXPORT_SYMBOL(__put_page);
 
 /**
  * put_pages_list() - release a list of pages
@@ -604,6 +360,7 @@ static void __lru_cache_activate_page(struct page *page)
  */
 void mark_page_accessed(struct page *page)
 {
+	page = compound_head(page);
 	if (!PageActive(page) && !PageUnevictable(page) &&
 			PageReferenced(page)) {
 
@@ -799,6 +556,24 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec,
 	update_page_reclaim_stat(lruvec, file, 0);
 }
 
+
+static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
+			    void *arg)
+{
+	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+		int file = page_is_file_cache(page);
+		int lru = page_lru_base_type(page);
+
+		del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE);
+		ClearPageActive(page);
+		ClearPageReferenced(page);
+		add_page_to_lru_list(page, lruvec, lru);
+
+		__count_vm_event(PGDEACTIVATE);
+		update_page_reclaim_stat(lruvec, file, 0);
+	}
+}
+
 /*
  * Drain pages out of the cpu's pagevecs.
  * Either "cpu" is the current CPU, and preemption has already been
@@ -825,6 +600,10 @@ void lru_add_drain_cpu(int cpu)
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
 
+	pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+	if (pagevec_count(pvec))
+		pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+
 	activate_page_drain(cpu);
 }
 
@@ -854,6 +633,26 @@ void deactivate_file_page(struct page *page)
 	}
 }
 
+/**
+ * deactivate_page - deactivate a page
+ * @page: page to deactivate
+ *
+ * deactivate_page() moves @page to the inactive list if @page was on the active
+ * list and was not an unevictable page.  This is done to accelerate the reclaim
+ * of @page.
+ */
+void deactivate_page(struct page *page)
+{
+	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+		struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
+
+		page_cache_get(page);
+		if (!pagevec_add(pvec, page))
+			pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+		put_cpu_var(lru_deactivate_pvecs);
+	}
+}
+
 void lru_add_drain(void)
 {
 	lru_add_drain_cpu(get_cpu());
@@ -883,6 +682,7 @@ void lru_add_drain_all(void)
 		if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
 		    pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
 		    pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
+		    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
 		    need_activate_page_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			schedule_work_on(cpu, work);
@@ -918,15 +718,6 @@ void release_pages(struct page **pages, int nr, bool cold)
 	for (i = 0; i < nr; i++) {
 		struct page *page = pages[i];
 
-		if (unlikely(PageCompound(page))) {
-			if (zone) {
-				spin_unlock_irqrestore(&zone->lru_lock, flags);
-				zone = NULL;
-			}
-			put_compound_page(page);
-			continue;
-		}
-
 		/*
 		 * Make sure the IRQ-safe lock-holding time does not get
 		 * excessive with a continuous string of pages from the
@@ -937,9 +728,19 @@ void release_pages(struct page **pages, int nr, bool cold)
 			zone = NULL;
 		}
 
+		page = compound_head(page);
 		if (!put_page_testzero(page))
 			continue;
 
+		if (PageCompound(page)) {
+			if (zone) {
+				spin_unlock_irqrestore(&zone->lru_lock, flags);
+				zone = NULL;
+			}
+			__put_compound_page(page);
+			continue;
+		}
+
 		if (PageLRU(page)) {
 			struct zone *pagezone = page_zone(page);
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index d504adb..676ff29 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -185,13 +185,12 @@ int add_to_swap(struct page *page, struct list_head *list)
 	 * deadlock in the swap out path.
 	 */
 	/*
-	 * Add it to the swap cache and mark it dirty
+	 * Add it to the swap cache.
 	 */
 	err = add_to_swap_cache(page, entry,
 			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
 
-	if (!err) {	/* Success */
-		SetPageDirty(page);
+	if (!err) {
 		return 1;
 	} else {	/* -ENOMEM radix-tree allocation failure */
 		/*
@@ -353,7 +352,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		}
 
 		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
-		__set_page_locked(new_page);
+		__SetPageLocked(new_page);
 		SetPageSwapBacked(new_page);
 		err = __add_to_swap_cache(new_page, entry);
 		if (likely(!err)) {
@@ -367,7 +366,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		}
 		radix_tree_preload_end();
 		ClearPageSwapBacked(new_page);
-		__clear_page_locked(new_page);
+		__ClearPageLocked(new_page);
 		/*
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
diff --git a/mm/swapfile.c b/mm/swapfile.c
index e6b8591..2bb30aa 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -926,6 +926,9 @@ int reuse_swap_page(struct page *page)
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	if (unlikely(PageKsm(page)))
 		return 0;
+	/* The page is part of THP and cannot be reused */
+	if (PageTransCompound(page))
+		return 0;
 	count = page_mapcount(page);
 	if (count <= 1 && PageSwapCache(page)) {
 		count += page_swapcount(page);
@@ -1108,19 +1111,9 @@ unsigned int count_swap_pages(int type, int free)
 }
 #endif /* CONFIG_HIBERNATION */
 
-static inline int maybe_same_pte(pte_t pte, pte_t swp_pte)
+static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte)
 {
-#ifdef CONFIG_MEM_SOFT_DIRTY
-	/*
-	 * When pte keeps soft dirty bit the pte generated
-	 * from swap entry does not has it, still it's same
-	 * pte from logical point of view.
-	 */
-	pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte);
-	return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty);
-#else
-	return pte_same(pte, swp_pte);
-#endif
+	return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte);
 }
 
 /*
@@ -1142,14 +1135,15 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	if (unlikely(!page))
 		return -ENOMEM;
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) {
+	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL,
+				&memcg, false)) {
 		ret = -ENOMEM;
 		goto out_nolock;
 	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
-		mem_cgroup_cancel_charge(page, memcg);
+	if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
+		mem_cgroup_cancel_charge(page, memcg, false);
 		ret = 0;
 		goto out;
 	}
@@ -1160,11 +1154,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	set_pte_at(vma->vm_mm, addr, pte,
 		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	if (page == swapcache) {
-		page_add_anon_rmap(page, vma, addr);
-		mem_cgroup_commit_charge(page, memcg, true);
+		page_add_anon_rmap(page, vma, addr, false);
+		mem_cgroup_commit_charge(page, memcg, true, false);
 	} else { /* ksm created a completely new copy */
-		page_add_new_anon_rmap(page, vma, addr);
-		mem_cgroup_commit_charge(page, memcg, false);
+		page_add_new_anon_rmap(page, vma, addr, false);
+		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
 	}
 	swap_free(entry);
@@ -1206,7 +1200,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		 * swapoff spends a _lot_ of time in this loop!
 		 * Test inline before going to call unuse_pte.
 		 */
-		if (unlikely(maybe_same_pte(*pte, swp_pte))) {
+		if (unlikely(pte_same_as_swp(*pte, swp_pte))) {
 			pte_unmap(pte);
 			ret = unuse_pte(vma, pmd, addr, entry, page);
 			if (ret)
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 77fee93..806b0c7 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -63,7 +63,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 	__SetPageUptodate(page);
 
 	ret = -ENOMEM;
-	if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg))
+	if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false))
 		goto out_release;
 
 	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
@@ -76,8 +76,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 		goto out_release_uncharge_unlock;
 
 	inc_mm_counter(dst_mm, MM_ANONPAGES);
-	page_add_new_anon_rmap(page, dst_vma, dst_addr);
-	mem_cgroup_commit_charge(page, memcg, false);
+	page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
+	mem_cgroup_commit_charge(page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(page, dst_vma);
 
 	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
@@ -91,7 +91,7 @@ out:
 	return ret;
 out_release_uncharge_unlock:
 	pte_unmap_unlock(dst_pte, ptl);
-	mem_cgroup_cancel_charge(page, memcg);
+	mem_cgroup_cancel_charge(page, memcg, false);
 out_release:
 	page_cache_release(page);
 	goto out;
diff --git a/mm/util.c b/mm/util.c
index 2d28f79..6d1f920 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -386,7 +386,9 @@ struct anon_vma *page_anon_vma(struct page *page)
 
 struct address_space *page_mapping(struct page *page)
 {
-	unsigned long mapping;
+	struct address_space *mapping;
+
+	page = compound_head(page);
 
 	/* This happens if someone calls flush_dcache_page on slab page */
 	if (unlikely(PageSlab(page)))
@@ -399,11 +401,25 @@ struct address_space *page_mapping(struct page *page)
 		return swap_address_space(entry);
 	}
 
-	mapping = (unsigned long)page->mapping;
-	if (mapping & PAGE_MAPPING_FLAGS)
+	mapping = page->mapping;
+	if ((unsigned long)mapping & PAGE_MAPPING_FLAGS)
 		return NULL;
-	return page->mapping;
+	return mapping;
+}
+
+/* Slow path of page_mapcount() for compound pages */
+int __page_mapcount(struct page *page)
+{
+	int ret;
+
+	ret = atomic_read(&page->_mapcount) + 1;
+	page = compound_head(page);
+	ret += atomic_read(compound_mapcount_ptr(page)) + 1;
+	if (PageDoubleMap(page))
+		ret--;
+	return ret;
 }
+EXPORT_SYMBOL_GPL(__page_mapcount);
 
 int overcommit_ratio_handler(struct ctl_table *table, int write,
 			     void __user *buffer, size_t *lenp,
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 58ceeb1..fb42a5b 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -455,7 +455,7 @@ found:
 	free_vmap_cache = &va->rb_node;
 	spin_unlock(&vmap_area_lock);
 
-	BUG_ON(va->va_start & (align-1));
+	BUG_ON(!IS_ALIGNED(va->va_start, align));
 	BUG_ON(va->va_start < vstart);
 	BUG_ON(va->va_end > vend);
 
@@ -1086,7 +1086,7 @@ void vm_unmap_ram(const void *mem, unsigned int count)
 	BUG_ON(!addr);
 	BUG_ON(addr < VMALLOC_START);
 	BUG_ON(addr > VMALLOC_END);
-	BUG_ON(addr & (PAGE_SIZE-1));
+	BUG_ON(!IS_ALIGNED(addr, PAGE_SIZE));
 
 	debug_check_no_locks_freed(mem, size);
 	vmap_debug_free_range(addr, addr+size);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 108bd11..5ac8695 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -906,6 +906,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		int may_enter_fs;
 		enum page_references references = PAGEREF_RECLAIM_CLEAN;
 		bool dirty, writeback;
+		bool lazyfree = false;
+		int ret = SWAP_SUCCESS;
 
 		cond_resched();
 
@@ -1049,6 +1051,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto keep_locked;
 			if (!add_to_swap(page, page_list))
 				goto activate_locked;
+			lazyfree = true;
 			may_enter_fs = 1;
 
 			/* Adding to swap updated mapping */
@@ -1060,14 +1063,17 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * processes. Try to unmap it here.
 		 */
 		if (page_mapped(page) && mapping) {
-			switch (try_to_unmap(page,
-					ttu_flags|TTU_BATCH_FLUSH)) {
+			switch (ret = try_to_unmap(page, lazyfree ?
+				(ttu_flags | TTU_BATCH_FLUSH | TTU_LZFREE) :
+				(ttu_flags | TTU_BATCH_FLUSH))) {
 			case SWAP_FAIL:
 				goto activate_locked;
 			case SWAP_AGAIN:
 				goto keep_locked;
 			case SWAP_MLOCK:
 				goto cull_mlocked;
+			case SWAP_LZFREE:
+				goto lazyfree;
 			case SWAP_SUCCESS:
 				; /* try to free the page below */
 			}
@@ -1174,6 +1180,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			}
 		}
 
+lazyfree:
 		if (!mapping || !__remove_mapping(mapping, page, true))
 			goto keep_locked;
 
@@ -1184,8 +1191,11 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * we obviously don't have to worry about waking up a process
 		 * waiting on the page lock, because there are no references.
 		 */
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 free_it:
+		if (ret == SWAP_LZFREE)
+			count_vm_event(PGLAZYFREED);
+
 		nr_reclaimed++;
 
 		/*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 83a003b..64bd0aa 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -783,6 +783,7 @@ const char * const vmstat_text[] = {
 
 	"pgfault",
 	"pgmajfault",
+	"pglazyfreed",
 
 	TEXTS_FOR_ZONES("pgrefill")
 	TEXTS_FOR_ZONES("pgsteal_kswapd")
@@ -844,7 +845,9 @@ const char * const vmstat_text[] = {
 	"thp_fault_fallback",
 	"thp_collapse_alloc",
 	"thp_collapse_alloc_failed",
-	"thp_split",
+	"thp_split_page",
+	"thp_split_page_failed",
+	"thp_split_pmd",
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif