Merge branch 'akpm' (patch-bomb from Andrew Morton)

Merge patches from Andrew Morton:
 - memstick fixes

 - the rest of MM

 - various misc bits that were awaiting merges from linux-next into
   mainline: seq_file, printk, rtc, completions, w1, softirqs, llist,
   kfifo, hfsplus

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (72 commits)
  cmdline-parser: fix build
  hfsplus: Fix undefined __divdi3 in hfsplus_init_header_node()
  kfifo API type safety
  kfifo: kfifo_copy_{to,from}_user: fix copied bytes calculation
  sound/core/memalloc.c: use gen_pool_dma_alloc() to allocate iram buffer
  llists-move-llist_reverse_order-from-raid5-to-llistc-fix
  llists: move llist_reverse_order from raid5 to llist.c
  kernel: fix generic_exec_single indentation
  kernel-provide-a-__smp_call_function_single-stub-for-config_smp-fix
  kernel: provide a __smp_call_function_single stub for !CONFIG_SMP
  kernel: remove CONFIG_USE_GENERIC_SMP_HELPERS
  revert "softirq: Add support for triggering softirq work on softirqs"
  drivers/w1/masters/w1-gpio.c: use dev_get_platdata()
  sched: remove INIT_COMPLETION
  tree-wide: use reinit_completion instead of INIT_COMPLETION
  sched: replace INIT_COMPLETION with reinit_completion
  drivers/rtc/rtc-hid-sensor-time.c: enable HID input processing early
  drivers/rtc/rtc-hid-sensor-time.c: use dev_get_platdata()
  vsprintf: ignore %n again
  seq_file: remove "%n" usage from seq_file users
  ...

13 files changed, 263 insertions, 175 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 3f4ffda152b..de31af25620 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -218,9 +218,11 @@ config SPLIT_PTLOCK_CPUS
 	int
 	default "999999" if ARM && !CPU_CACHE_VIPT
 	default "999999" if PARISC && !PA20
-	default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC
 	default "4"
 
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+	boolean
+
 #
 # support for memory balloon compaction
 config BALLOON_COMPACTION
diff --git a/mm/filemap.c b/mm/filemap.c
index ae4846ff484..b7749a92021 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1090,7 +1090,6 @@ static void shrink_readahead_size_eio(struct file *filp,
  * @filp:	the file to read
  * @ppos:	current file position
  * @desc:	read_descriptor
- * @actor:	read method
  *
  * This is a generic file read routine, and uses the
  * mapping->a_ops->readpage() function for the actual low-level stuff.
@@ -1099,7 +1098,7 @@ static void shrink_readahead_size_eio(struct file *filp,
  * of the logic when it comes to error handling etc.
  */
 static void do_generic_file_read(struct file *filp, loff_t *ppos,
-		read_descriptor_t *desc, read_actor_t actor)
+		read_descriptor_t *desc)
 {
 	struct address_space *mapping = filp->f_mapping;
 	struct inode *inode = mapping->host;
@@ -1200,13 +1199,14 @@ page_ok:
 		 * Ok, we have the page, and it's up-to-date, so
 		 * now we can copy it to user space...
 		 *
-		 * The actor routine returns how many bytes were actually used..
+		 * The file_read_actor routine returns how many bytes were
+		 * actually used..
 		 * NOTE! This may not be the same as how much of a user buffer
 		 * we filled up (we may be padding etc), so we can only update
 		 * "pos" here (the actor routine has to update the user buffer
 		 * pointers and the remaining count).
 		 */
-		ret = actor(desc, page, offset, nr);
+		ret = file_read_actor(desc, page, offset, nr);
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
@@ -1479,7 +1479,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		if (desc.count == 0)
 			continue;
 		desc.error = 0;
-		do_generic_file_read(filp, ppos, &desc, file_read_actor);
+		do_generic_file_read(filp, ppos, &desc);
 		retval += desc.written;
 		if (desc.error) {
 			retval = retval ?: desc.error;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0556c6a4495..bccd5a628ea 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -710,6 +710,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 					struct page *page)
 {
 	pgtable_t pgtable;
+	spinlock_t *ptl;
 
 	VM_BUG_ON(!PageCompound(page));
 	pgtable = pte_alloc_one(mm, haddr);
@@ -724,9 +725,9 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 	 */
 	__SetPageUptodate(page);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_none(*pmd))) {
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		mem_cgroup_uncharge_page(page);
 		put_page(page);
 		pte_free(mm, pgtable);
@@ -738,8 +739,8 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		set_pmd_at(mm, haddr, pmd, entry);
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
-		mm->nr_ptes++;
-		spin_unlock(&mm->page_table_lock);
+		atomic_long_inc(&mm->nr_ptes);
+		spin_unlock(ptl);
 	}
 
 	return 0;
@@ -759,6 +760,7 @@ static inline struct page *alloc_hugepage_vma(int defrag,
 			       HPAGE_PMD_ORDER, vma, haddr, nd);
 }
 
+/* Caller must hold page table lock. */
 static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
 		struct page *zero_page)
@@ -771,7 +773,7 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 	entry = pmd_mkhuge(entry);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
-	mm->nr_ptes++;
+	atomic_long_inc(&mm->nr_ptes);
 	return true;
 }
 
@@ -790,6 +792,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return VM_FAULT_OOM;
 	if (!(flags & FAULT_FLAG_WRITE) &&
 			transparent_hugepage_use_zero_page()) {
+		spinlock_t *ptl;
 		pgtable_t pgtable;
 		struct page *zero_page;
 		bool set;
@@ -802,10 +805,10 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			count_vm_event(THP_FAULT_FALLBACK);
 			return VM_FAULT_FALLBACK;
 		}
-		spin_lock(&mm->page_table_lock);
+		ptl = pmd_lock(mm, pmd);
 		set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
 				zero_page);
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		if (!set) {
 			pte_free(mm, pgtable);
 			put_huge_zero_page();
@@ -838,6 +841,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 		  struct vm_area_struct *vma)
 {
+	spinlock_t *dst_ptl, *src_ptl;
 	struct page *src_page;
 	pmd_t pmd;
 	pgtable_t pgtable;
@@ -848,8 +852,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (unlikely(!pgtable))
 		goto out;
 
-	spin_lock(&dst_mm->page_table_lock);
-	spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING);
+	dst_ptl = pmd_lock(dst_mm, dst_pmd);
+	src_ptl = pmd_lockptr(src_mm, src_pmd);
+	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 
 	ret = -EAGAIN;
 	pmd = *src_pmd;
@@ -858,7 +863,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		goto out_unlock;
 	}
 	/*
-	 * mm->page_table_lock is enough to be sure that huge zero pmd is not
+	 * When page table lock is held, the huge zero pmd should not be
 	 * under splitting since we don't split the page itself, only pmd to
 	 * a page table.
 	 */
@@ -879,8 +884,8 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	}
 	if (unlikely(pmd_trans_splitting(pmd))) {
 		/* split huge page running from under us */
-		spin_unlock(&src_mm->page_table_lock);
-		spin_unlock(&dst_mm->page_table_lock);
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
 		pte_free(dst_mm, pgtable);
 
 		wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */
@@ -896,12 +901,12 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	pmd = pmd_mkold(pmd_wrprotect(pmd));
 	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
-	dst_mm->nr_ptes++;
+	atomic_long_inc(&dst_mm->nr_ptes);
 
 	ret = 0;
 out_unlock:
-	spin_unlock(&src_mm->page_table_lock);
-	spin_unlock(&dst_mm->page_table_lock);
+	spin_unlock(src_ptl);
+	spin_unlock(dst_ptl);
 out:
 	return ret;
 }
@@ -912,10 +917,11 @@ void huge_pmd_set_accessed(struct mm_struct *mm,
 			   pmd_t *pmd, pmd_t orig_pmd,
 			   int dirty)
 {
+	spinlock_t *ptl;
 	pmd_t entry;
 	unsigned long haddr;
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_same(*pmd, orig_pmd)))
 		goto unlock;
 
@@ -925,13 +931,14 @@ void huge_pmd_set_accessed(struct mm_struct *mm,
 		update_mmu_cache_pmd(vma, address, pmd);
 
 unlock:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 }
 
 static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd, pmd_t orig_pmd, unsigned long haddr)
 {
+	spinlock_t *ptl;
 	pgtable_t pgtable;
 	pmd_t _pmd;
 	struct page *page;
@@ -958,7 +965,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_same(*pmd, orig_pmd)))
 		goto out_free_page;
 
@@ -985,7 +992,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
 	}
 	smp_wmb(); /* make pte visible before pmd */
 	pmd_populate(mm, pmd, pgtable);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	put_huge_zero_page();
 	inc_mm_counter(mm, MM_ANONPAGES);
 
@@ -995,7 +1002,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
 out:
 	return ret;
 out_free_page:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	mem_cgroup_uncharge_page(page);
 	put_page(page);
@@ -1009,6 +1016,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct page *page,
 					unsigned long haddr)
 {
+	spinlock_t *ptl;
 	pgtable_t pgtable;
 	pmd_t _pmd;
 	int ret = 0, i;
@@ -1055,7 +1063,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_same(*pmd, orig_pmd)))
 		goto out_free_pages;
 	VM_BUG_ON(!PageHead(page));
@@ -1081,7 +1089,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 	smp_wmb(); /* make pte visible before pmd */
 	pmd_populate(mm, pmd, pgtable);
 	page_remove_rmap(page);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
@@ -1092,7 +1100,7 @@ out:
 	return ret;
 
 out_free_pages:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	mem_cgroup_uncharge_start();
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
@@ -1107,17 +1115,19 @@ out_free_pages:
 int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pmd_t *pmd, pmd_t orig_pmd)
 {
+	spinlock_t *ptl;
 	int ret = 0;
 	struct page *page = NULL, *new_page;
 	unsigned long haddr;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
+	ptl = pmd_lockptr(mm, pmd);
 	VM_BUG_ON(!vma->anon_vma);
 	haddr = address & HPAGE_PMD_MASK;
 	if (is_huge_zero_pmd(orig_pmd))
 		goto alloc;
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	if (unlikely(!pmd_same(*pmd, orig_pmd)))
 		goto out_unlock;
 
@@ -1133,7 +1143,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_unlock;
 	}
 	get_page(page);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow())
@@ -1180,11 +1190,11 @@ alloc:
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	if (page)
 		put_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		mem_cgroup_uncharge_page(new_page);
 		put_page(new_page);
 		goto out_mn;
@@ -1206,13 +1216,13 @@ alloc:
 		}
 		ret |= VM_FAULT_WRITE;
 	}
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 out_mn:
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 out:
 	return ret;
 out_unlock:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	return ret;
 }
 
@@ -1224,7 +1234,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 	struct page *page = NULL;
 
-	assert_spin_locked(&mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(mm, pmd));
 
 	if (flags & FOLL_WRITE && !pmd_write(*pmd))
 		goto out;
@@ -1271,6 +1281,7 @@ out:
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+	spinlock_t *ptl;
 	struct anon_vma *anon_vma = NULL;
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
@@ -1280,7 +1291,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	bool migrated = false;
 	int flags = 0;
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmdp);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
@@ -1318,7 +1329,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * relock and check_same as the page may no longer be mapped.
 		 * As the fault is being retried, do not account for it.
 		 */
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		wait_on_page_locked(page);
 		page_nid = -1;
 		goto out;
@@ -1326,13 +1337,13 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Page is misplaced, serialise migrations and parallel THP splits */
 	get_page(page);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	if (!page_locked)
 		lock_page(page);
 	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PMD did not change while page_table_lock was released */
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	if (unlikely(!pmd_same(pmd, *pmdp))) {
 		unlock_page(page);
 		put_page(page);
@@ -1344,7 +1355,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * Migrate the THP to the requested node, returns with page unlocked
 	 * and pmd_numa cleared.
 	 */
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
 				pmdp, pmd, addr, page, target_nid);
 	if (migrated) {
@@ -1361,7 +1372,7 @@ clear_pmdnuma:
 	update_mmu_cache_pmd(vma, addr, pmdp);
 	unlock_page(page);
 out_unlock:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 
 out:
 	if (anon_vma)
@@ -1376,9 +1387,10 @@ out:
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
+	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		struct page *page;
 		pgtable_t pgtable;
 		pmd_t orig_pmd;
@@ -1392,8 +1404,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
 		if (is_huge_zero_pmd(orig_pmd)) {
-			tlb->mm->nr_ptes--;
-			spin_unlock(&tlb->mm->page_table_lock);
+			atomic_long_dec(&tlb->mm->nr_ptes);
+			spin_unlock(ptl);
 			put_huge_zero_page();
 		} else {
 			page = pmd_page(orig_pmd);
@@ -1401,8 +1413,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			VM_BUG_ON(page_mapcount(page) < 0);
 			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
 			VM_BUG_ON(!PageHead(page));
-			tlb->mm->nr_ptes--;
-			spin_unlock(&tlb->mm->page_table_lock);
+			atomic_long_dec(&tlb->mm->nr_ptes);
+			spin_unlock(ptl);
 			tlb_remove_page(tlb, page);
 		}
 		pte_free(tlb->mm, pgtable);
@@ -1415,14 +1427,15 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end,
 		unsigned char *vec)
 {
+	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		/*
 		 * All logical pages in the range are present
 		 * if backed by a huge page.
 		 */
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 		memset(vec, 1, (end - addr) >> PAGE_SHIFT);
 		ret = 1;
 	}
@@ -1435,6 +1448,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		  unsigned long new_addr, unsigned long old_end,
 		  pmd_t *old_pmd, pmd_t *new_pmd)
 {
+	spinlock_t *old_ptl, *new_ptl;
 	int ret = 0;
 	pmd_t pmd;
 
@@ -1455,12 +1469,21 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		goto out;
 	}
 
-	ret = __pmd_trans_huge_lock(old_pmd, vma);
+	/*
+	 * We don't have to worry about the ordering of src and dst
+	 * ptlocks because exclusive mmap_sem prevents deadlock.
+	 */
+	ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl);
 	if (ret == 1) {
+		new_ptl = pmd_lockptr(mm, new_pmd);
+		if (new_ptl != old_ptl)
+			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
 		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
 		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
-		spin_unlock(&mm->page_table_lock);
+		if (new_ptl != old_ptl)
+			spin_unlock(new_ptl);
+		spin_unlock(old_ptl);
 	}
 out:
 	return ret;
@@ -1476,9 +1499,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, pgprot_t newprot, int prot_numa)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pmd_t entry;
 		ret = 1;
 		if (!prot_numa) {
@@ -1507,7 +1531,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		if (ret == HPAGE_PMD_NR)
 			set_pmd_at(mm, addr, pmd, entry);
 
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 	}
 
 	return ret;
@@ -1520,12 +1544,13 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
  * Note that if it returns 1, this routine returns without unlocking page
  * table locks. So callers must unlock them.
  */
-int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
+int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+		spinlock_t **ptl)
 {
-	spin_lock(&vma->vm_mm->page_table_lock);
+	*ptl = pmd_lock(vma->vm_mm, pmd);
 	if (likely(pmd_trans_huge(*pmd))) {
 		if (unlikely(pmd_trans_splitting(*pmd))) {
-			spin_unlock(&vma->vm_mm->page_table_lock);
+			spin_unlock(*ptl);
 			wait_split_huge_page(vma->anon_vma, pmd);
 			return -1;
 		} else {
@@ -1534,27 +1559,37 @@ int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
 			return 1;
 		}
 	}
-	spin_unlock(&vma->vm_mm->page_table_lock);
+	spin_unlock(*ptl);
 	return 0;
 }
 
+/*
+ * This function returns whether a given @page is mapped onto the @address
+ * in the virtual space of @mm.
+ *
+ * When it's true, this function returns *pmd with holding the page table lock
+ * and passing it back to the caller via @ptl.
+ * If it's false, returns NULL without holding the page table lock.
+ */
 pmd_t *page_check_address_pmd(struct page *page,
 			      struct mm_struct *mm,
 			      unsigned long address,
-			      enum page_check_address_pmd_flag flag)
+			      enum page_check_address_pmd_flag flag,
+			      spinlock_t **ptl)
 {
-	pmd_t *pmd, *ret = NULL;
+	pmd_t *pmd;
 
 	if (address & ~HPAGE_PMD_MASK)
-		goto out;
+		return NULL;
 
 	pmd = mm_find_pmd(mm, address);
 	if (!pmd)
-		goto out;
+		return NULL;
+	*ptl = pmd_lock(mm, pmd);
 	if (pmd_none(*pmd))
-		goto out;
+		goto unlock;
 	if (pmd_page(*pmd) != page)
-		goto out;
+		goto unlock;
 	/*
 	 * split_vma() may create temporary aliased mappings. There is
 	 * no risk as long as all huge pmd are found and have their
@@ -1564,14 +1599,15 @@ pmd_t *page_check_address_pmd(struct page *page,
 	 */
 	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
 	    pmd_trans_splitting(*pmd))
-		goto out;
+		goto unlock;
 	if (pmd_trans_huge(*pmd)) {
 		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
 			  !pmd_trans_splitting(*pmd));
-		ret = pmd;
+		return pmd;
 	}
-out:
-	return ret;
+unlock:
+	spin_unlock(*ptl);
+	return NULL;
 }
 
 static int __split_huge_page_splitting(struct page *page,
@@ -1579,6 +1615,7 @@ static int __split_huge_page_splitting(struct page *page,
 				       unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	pmd_t *pmd;
 	int ret = 0;
 	/* For mmu_notifiers */
@@ -1586,9 +1623,8 @@ static int __split_huge_page_splitting(struct page *page,
 	const unsigned long mmun_end   = address + HPAGE_PMD_SIZE;
 
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-	spin_lock(&mm->page_table_lock);
 	pmd = page_check_address_pmd(page, mm, address,
-				     PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG);
+			PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, &ptl);
 	if (pmd) {
 		/*
 		 * We can't temporarily set the pmd to null in order
@@ -1599,8 +1635,8 @@ static int __split_huge_page_splitting(struct page *page,
 		 */
 		pmdp_splitting_flush(vma, address, pmd);
 		ret = 1;
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 	return ret;
@@ -1731,14 +1767,14 @@ static int __split_huge_page_map(struct page *page,
 				 unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	pmd_t *pmd, _pmd;
 	int ret = 0, i;
 	pgtable_t pgtable;
 	unsigned long haddr;
 
-	spin_lock(&mm->page_table_lock);
 	pmd = page_check_address_pmd(page, mm, address,
-				     PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
+			PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, &ptl);
 	if (pmd) {
 		pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 		pmd_populate(mm, &_pmd, pgtable);
@@ -1793,8 +1829,8 @@ static int __split_huge_page_map(struct page *page,
 		pmdp_invalidate(vma, address, pmd);
 		pmd_populate(mm, pmd, pgtable);
 		ret = 1;
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 
 	return ret;
 }
@@ -2346,7 +2382,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	pte_t *pte;
 	pgtable_t pgtable;
 	struct page *new_page;
-	spinlock_t *ptl;
+	spinlock_t *pmd_ptl, *pte_ptl;
 	int isolated;
 	unsigned long hstart, hend;
 	unsigned long mmun_start;	/* For mmu_notifiers */
@@ -2389,12 +2425,12 @@ static void collapse_huge_page(struct mm_struct *mm,
 	anon_vma_lock_write(vma->anon_vma);
 
 	pte = pte_offset_map(pmd, address);
-	ptl = pte_lockptr(mm, pmd);
+	pte_ptl = pte_lockptr(mm, pmd);
 
 	mmun_start = address;
 	mmun_end   = address + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-	spin_lock(&mm->page_table_lock); /* probably unnecessary */
+	pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
 	/*
 	 * After this gup_fast can't run anymore. This also removes
 	 * any huge TLB entry from the CPU so we won't allow
@@ -2402,16 +2438,16 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * to avoid the risk of CPU bugs in that area.
 	 */
 	_pmd = pmdp_clear_flush(vma, address, pmd);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(pmd_ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
-	spin_lock(ptl);
+	spin_lock(pte_ptl);
 	isolated = __collapse_huge_page_isolate(vma, address, pte);
-	spin_unlock(ptl);
+	spin_unlock(pte_ptl);
 
 	if (unlikely(!isolated)) {
 		pte_unmap(pte);
-		spin_lock(&mm->page_table_lock);
+		spin_lock(pmd_ptl);
 		BUG_ON(!pmd_none(*pmd));
 		/*
 		 * We can only use set_pmd_at when establishing
@@ -2419,7 +2455,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 		 * points to regular pagetables. Use pmd_populate for that
 		 */
 		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(pmd_ptl);
 		anon_vma_unlock_write(vma->anon_vma);
 		goto out;
 	}
@@ -2430,7 +2466,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 */
 	anon_vma_unlock_write(vma->anon_vma);
 
-	__collapse_huge_page_copy(pte, new_page, vma, address, ptl);
+	__collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl);
 	pte_unmap(pte);
 	__SetPageUptodate(new_page);
 	pgtable = pmd_pgtable(_pmd);
@@ -2445,13 +2481,13 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 */
 	smp_wmb();
 
-	spin_lock(&mm->page_table_lock);
+	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
 	page_add_new_anon_rmap(new_page, vma, address);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(pmd_ptl);
 
 	*hpage = NULL;
 
@@ -2780,6 +2816,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd)
 {
+	spinlock_t *ptl;
 	struct page *page;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
@@ -2792,22 +2829,22 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
 again:
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_trans_huge(*pmd))) {
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 		return;
 	}
 	if (is_huge_zero_pmd(*pmd)) {
 		__split_huge_zero_page_pmd(vma, haddr, pmd);
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 		return;
 	}
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!page_count(page));
 	get_page(page);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 	split_huge_page(page);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0b7656e804d..7d57af21f49 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2376,6 +2376,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
+		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr);
 		if (!src_pte)
 			continue;
@@ -2387,8 +2388,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		if (dst_pte == src_pte)
 			continue;
 
-		spin_lock(&dst->page_table_lock);
-		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
+		dst_ptl = huge_pte_lock(h, dst, dst_pte);
+		src_ptl = huge_pte_lockptr(h, src, src_pte);
+		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 		if (!huge_pte_none(huge_ptep_get(src_pte))) {
 			if (cow)
 				huge_ptep_set_wrprotect(src, addr, src_pte);
@@ -2398,8 +2400,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			page_dup_rmap(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
-		spin_unlock(&src->page_table_lock);
-		spin_unlock(&dst->page_table_lock);
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
 	}
 	return 0;
 
@@ -2442,6 +2444,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	unsigned long address;
 	pte_t *ptep;
 	pte_t pte;
+	spinlock_t *ptl;
 	struct page *page;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
@@ -2455,25 +2458,25 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	tlb_start_vma(tlb, vma);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 again:
-	spin_lock(&mm->page_table_lock);
 	for (address = start; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
 
+		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep))
-			continue;
+			goto unlock;
 
 		pte = huge_ptep_get(ptep);
 		if (huge_pte_none(pte))
-			continue;
+			goto unlock;
 
 		/*
 		 * HWPoisoned hugepage is already unmapped and dropped reference
 		 */
 		if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
 			huge_pte_clear(mm, address, ptep);
-			continue;
+			goto unlock;
 		}
 
 		page = pte_page(pte);
@@ -2484,7 +2487,7 @@ again:
 		 */
 		if (ref_page) {
 			if (page != ref_page)
-				continue;
+				goto unlock;
 
 			/*
 			 * Mark the VMA as having unmapped its page so that
@@ -2501,13 +2504,18 @@ again:
 
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
-		if (force_flush)
+		if (force_flush) {
+			spin_unlock(ptl);
 			break;
+		}
 		/* Bail out after unmapping reference page if supplied */
-		if (ref_page)
+		if (ref_page) {
+			spin_unlock(ptl);
 			break;
+		}
+unlock:
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	/*
 	 * mmu_gather ran out of room to batch pages, we break out of
 	 * the PTE lock to avoid doing the potential expensive TLB invalidate
@@ -2613,7 +2621,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
  */
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte,
-			struct page *pagecache_page)
+			struct page *pagecache_page, spinlock_t *ptl)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct page *old_page, *new_page;
@@ -2647,8 +2655,8 @@ retry_avoidcopy:
 
 	page_cache_get(old_page);
 
-	/* Drop page_table_lock as buddy allocator may be called */
-	spin_unlock(&mm->page_table_lock);
+	/* Drop page table lock as buddy allocator may be called */
+	spin_unlock(ptl);
 	new_page = alloc_huge_page(vma, address, outside_reserve);
 
 	if (IS_ERR(new_page)) {
@@ -2666,13 +2674,13 @@ retry_avoidcopy:
 			BUG_ON(huge_pte_none(pte));
 			if (unmap_ref_private(mm, vma, old_page, address)) {
 				BUG_ON(huge_pte_none(pte));
-				spin_lock(&mm->page_table_lock);
+				spin_lock(ptl);
 				ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 				if (likely(pte_same(huge_ptep_get(ptep), pte)))
 					goto retry_avoidcopy;
 				/*
-				 * race occurs while re-acquiring page_table_lock, and
-				 * our job is done.
+				 * race occurs while re-acquiring page table
+				 * lock, and our job is done.
 				 */
 				return 0;
 			}
@@ -2680,7 +2688,7 @@ retry_avoidcopy:
 		}
 
 		/* Caller expects lock to be held */
-		spin_lock(&mm->page_table_lock);
+		spin_lock(ptl);
 		if (err == -ENOMEM)
 			return VM_FAULT_OOM;
 		else
@@ -2695,7 +2703,7 @@ retry_avoidcopy:
 		page_cache_release(new_page);
 		page_cache_release(old_page);
 		/* Caller expects lock to be held */
-		spin_lock(&mm->page_table_lock);
+		spin_lock(ptl);
 		return VM_FAULT_OOM;
 	}
 
@@ -2707,10 +2715,10 @@ retry_avoidcopy:
 	mmun_end = mmun_start + huge_page_size(h);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	/*
-	 * Retake the page_table_lock to check for racing updates
+	 * Retake the page table lock to check for racing updates
 	 * before the page tables are altered
 	 */
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
 		ClearPagePrivate(new_page);
@@ -2724,13 +2732,13 @@ retry_avoidcopy:
 		/* Make the old page be freed below */
 		new_page = old_page;
 	}
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	page_cache_release(new_page);
 	page_cache_release(old_page);
 
 	/* Caller expects lock to be held */
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	return 0;
 }
 
@@ -2778,6 +2786,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	struct address_space *mapping;
 	pte_t new_pte;
+	spinlock_t *ptl;
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -2864,7 +2873,8 @@ retry:
 			goto backout_unlocked;
 		}
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(h, mm, ptep);
+	spin_lock(ptl);
 	size = i_size_read(mapping->host) >> huge_page_shift(h);
 	if (idx >= size)
 		goto backout;
@@ -2885,16 +2895,16 @@ retry:
 
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
-		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
+		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl);
 	}
 
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	unlock_page(page);
 out:
 	return ret;
 
 backout:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 backout_unlocked:
 	unlock_page(page);
 	put_page(page);
@@ -2906,6 +2916,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	pte_t *ptep;
 	pte_t entry;
+	spinlock_t *ptl;
 	int ret;
 	struct page *page = NULL;
 	struct page *pagecache_page = NULL;
@@ -2918,7 +2929,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait_huge(mm, ptep);
+			migration_entry_wait_huge(vma, mm, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
@@ -2974,17 +2985,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (page != pagecache_page)
 		lock_page(page);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(h, mm, ptep);
+	spin_lock(ptl);
 	/* Check for a racing update before calling hugetlb_cow */
 	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
-		goto out_page_table_lock;
+		goto out_ptl;
 
 
 	if (flags & FAULT_FLAG_WRITE) {
 		if (!huge_pte_write(entry)) {
 			ret = hugetlb_cow(mm, vma, address, ptep, entry,
-							pagecache_page);
-			goto out_page_table_lock;
+					pagecache_page, ptl);
+			goto out_ptl;
 		}
 		entry = huge_pte_mkdirty(entry);
 	}
@@ -2993,8 +3005,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 						flags & FAULT_FLAG_WRITE))
 		update_mmu_cache(vma, address, ptep);
 
-out_page_table_lock:
-	spin_unlock(&mm->page_table_lock);
+out_ptl:
+	spin_unlock(ptl);
 
 	if (pagecache_page) {
 		unlock_page(pagecache_page);
@@ -3020,9 +3032,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long remainder = *nr_pages;
 	struct hstate *h = hstate_vma(vma);
 
-	spin_lock(&mm->page_table_lock);
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
+		spinlock_t *ptl = NULL;
 		int absent;
 		struct page *page;
 
@@ -3030,8 +3042,12 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * Some archs (sparc64, sh*) have multiple pte_ts to
 		 * each hugepage.  We have to make sure we get the
 		 * first, for the page indexing below to work.
+		 *
+		 * Note that page table lock is not held when pte is null.
 		 */
 		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
+		if (pte)
+			ptl = huge_pte_lock(h, mm, pte);
 		absent = !pte || huge_pte_none(huge_ptep_get(pte));
 
 		/*
@@ -3043,6 +3059,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		if (absent && (flags & FOLL_DUMP) &&
 		    !hugetlbfs_pagecache_present(h, vma, vaddr)) {
+			if (pte)
+				spin_unlock(ptl);
 			remainder = 0;
 			break;
 		}
@@ -3062,10 +3080,10 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		      !huge_pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
-			spin_unlock(&mm->page_table_lock);
+			if (pte)
+				spin_unlock(ptl);
 			ret = hugetlb_fault(mm, vma, vaddr,
 				(flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0);
-			spin_lock(&mm->page_table_lock);
 			if (!(ret & VM_FAULT_ERROR))
 				continue;
 
@@ -3096,8 +3114,8 @@ same_page:
 			 */
 			goto same_page;
 		}
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	*nr_pages = remainder;
 	*position = vaddr;
 
@@ -3118,13 +3136,15 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_cache_range(vma, address, end);
 
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
-	spin_lock(&mm->page_table_lock);
 	for (; address < end; address += huge_page_size(h)) {
+		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
+		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			pages++;
+			spin_unlock(ptl);
 			continue;
 		}
 		if (!huge_pte_none(huge_ptep_get(ptep))) {
@@ -3134,8 +3154,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			set_huge_pte_at(mm, address, ptep, pte);
 			pages++;
 		}
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	/*
 	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
 	 * may have cleared our pud entry and done put_page on the page table:
@@ -3298,6 +3318,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	unsigned long saddr;
 	pte_t *spte = NULL;
 	pte_t *pte;
+	spinlock_t *ptl;
 
 	if (!vma_shareable(vma, addr))
 		return (pte_t *)pmd_alloc(mm, pud, addr);
@@ -3320,13 +3341,14 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	if (!spte)
 		goto out;
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte);
+	spin_lock(ptl);
 	if (pud_none(*pud))
 		pud_populate(mm, pud,
 				(pmd_t *)((unsigned long)spte & PAGE_MASK));
 	else
 		put_page(virt_to_page(spte));
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 out:
 	pte = (pte_t *)pmd_alloc(mm, pud, addr);
 	mutex_unlock(&mapping->i_mmap_mutex);
@@ -3340,7 +3362,7 @@ out:
  * indicated by page_count > 1, unmap is achieved by clearing pud and
  * decrementing the ref count. If count == 1, the pte page is not shared.
  *
- * called with vma->vm_mm->page_table_lock held.
+ * called with page table lock held.
  *
  * returns: 1 successfully unmapped a shared pte page
  *	    0 the underlying pte page is not shared, or it is the last user
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e3cd40b2d5d..f1a0ae6e11b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6605,10 +6605,10 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
 			mc.precharge += HPAGE_PMD_NR;
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 		return 0;
 	}
 
@@ -6797,9 +6797,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	 *    to be unlocked in __split_huge_page_splitting(), where the main
 	 *    part of thp split is not executed yet.
 	 */
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		if (mc.precharge < HPAGE_PMD_NR) {
-			spin_unlock(&vma->vm_mm->page_table_lock);
+			spin_unlock(ptl);
 			return 0;
 		}
 		target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
@@ -6816,7 +6816,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 			}
 			put_page(page);
 		}
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 		return 0;
 	}
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f9d78ec7831..b7c171602ba 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1269,7 +1269,7 @@ void memory_failure_queue(unsigned long pfn, int trapno, int flags)
 
 	mf_cpu = &get_cpu_var(memory_failure_cpu);
 	spin_lock_irqsave(&mf_cpu->lock, proc_flags);
-	if (kfifo_put(&mf_cpu->fifo, &entry))
+	if (kfifo_put(&mf_cpu->fifo, entry))
 		schedule_work_on(smp_processor_id(), &mf_cpu->work);
 	else
 		pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n",
diff --git a/mm/memory.c b/mm/memory.c
index bf8665849a5..0409e8f43fa 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -382,7 +382,7 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 	pgtable_t token = pmd_pgtable(*pmd);
 	pmd_clear(pmd);
 	pte_free_tlb(tlb, token, addr);
-	tlb->mm->nr_ptes--;
+	atomic_long_dec(&tlb->mm->nr_ptes);
 }
 
 static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -550,6 +550,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		pmd_t *pmd, unsigned long address)
 {
+	spinlock_t *ptl;
 	pgtable_t new = pte_alloc_one(mm, address);
 	int wait_split_huge_page;
 	if (!new)
@@ -570,15 +571,15 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	wait_split_huge_page = 0;
 	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
-		mm->nr_ptes++;
+		atomic_long_inc(&mm->nr_ptes);
 		pmd_populate(mm, pmd, new);
 		new = NULL;
 	} else if (unlikely(pmd_trans_splitting(*pmd)))
 		wait_split_huge_page = 1;
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	if (new)
 		pte_free(mm, new);
 	if (wait_split_huge_page)
@@ -1516,20 +1517,20 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 			split_huge_page_pmd(vma, address, pmd);
 			goto split_fallthrough;
 		}
-		spin_lock(&mm->page_table_lock);
+		ptl = pmd_lock(mm, pmd);
 		if (likely(pmd_trans_huge(*pmd))) {
 			if (unlikely(pmd_trans_splitting(*pmd))) {
-				spin_unlock(&mm->page_table_lock);
+				spin_unlock(ptl);
 				wait_split_huge_page(vma->anon_vma, pmd);
 			} else {
 				page = follow_trans_huge_pmd(vma, address,
 							     pmd, flags);
-				spin_unlock(&mm->page_table_lock);
+				spin_unlock(ptl);
 				*page_mask = HPAGE_PMD_NR - 1;
 				goto out;
 			}
 		} else
-			spin_unlock(&mm->page_table_lock);
+			spin_unlock(ptl);
 		/* fall through */
 	}
 split_fallthrough:
@@ -4269,3 +4270,28 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 	}
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
+
+#if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS
+static struct kmem_cache *page_ptl_cachep;
+void __init ptlock_cache_init(void)
+{
+	page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
+			SLAB_PANIC, NULL);
+}
+
+bool ptlock_alloc(struct page *page)
+{
+	spinlock_t *ptl;
+
+	ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
+	if (!ptl)
+		return false;
+	page->ptl = ptl;
+	return true;
+}
+
+void ptlock_free(struct page *page)
+{
+	kfree(page->ptl);
+}
+#endif
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4cc19f6ab6c..c4403cdf343 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -525,8 +525,9 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 #ifdef CONFIG_HUGETLB_PAGE
 	int nid;
 	struct page *page;
+	spinlock_t *ptl;
 
-	spin_lock(&vma->vm_mm->page_table_lock);
+	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
 	page = pte_page(huge_ptep_get((pte_t *)pmd));
 	nid = page_to_nid(page);
 	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
@@ -536,7 +537,7 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1))
 		isolate_huge_page(page, private);
 unlock:
-	spin_unlock(&vma->vm_mm->page_table_lock);
+	spin_unlock(ptl);
 #else
 	BUG();
 #endif
diff --git a/mm/migrate.c b/mm/migrate.c
index dfc8300ecbb..316e720a202 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -130,7 +130,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 		ptep = huge_pte_offset(mm, addr);
 		if (!ptep)
 			goto out;
-		ptl = &mm->page_table_lock;
+		ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep);
 	} else {
 		pmd = mm_find_pmd(mm, addr);
 		if (!pmd)
@@ -249,9 +249,10 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 	__migration_entry_wait(mm, ptep, ptl);
 }
 
-void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte)
 {
-	spinlock_t *ptl = &(mm)->page_table_lock;
+	spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte);
 	__migration_entry_wait(mm, pte, ptl);
 }
 
@@ -1666,6 +1667,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 				unsigned long address,
 				struct page *page, int node)
 {
+	spinlock_t *ptl;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated = 0;
@@ -1705,9 +1707,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	WARN_ON(PageLRU(new_page));
 
 	/* Recheck the target PMD */
-	spin_lock(&mm->page_table_lock);
+	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_same(*pmd, entry))) {
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 
 		/* Reverse changes made by migrate_page_copy() */
 		if (TestClearPageActive(new_page))
@@ -1752,7 +1754,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	 * before it's fully transferred to the new page.
 	 */
 	mem_cgroup_end_migration(memcg, page, new_page, true);
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 
 	unlock_page(new_page);
 	unlock_page(page);
diff --git a/mm/mmap.c b/mm/mmap.c
index 5a6baddde15..834b2d785f1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2724,7 +2724,8 @@ void exit_mmap(struct mm_struct *mm)
 	}
 	vm_unacct_memory(nr_accounted);
 
-	WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
+	WARN_ON(atomic_long_read(&mm->nr_ptes) >
+			(FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
 }
 
 /* Insert vm structure into process list sorted by address
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 6738c47f1f7..1e4a600a616 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -161,7 +161,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * The baseline for the badness score is the proportion of RAM that each
 	 * task's rss, pagetable and swap space use.
 	 */
-	points = get_mm_rss(p->mm) + p->mm->nr_ptes +
+	points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) +
 		 get_mm_counter(p->mm, MM_SWAPENTS);
 	task_unlock(p);
 
@@ -364,10 +364,10 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5hd %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu         %5hd %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
-			task->mm->nr_ptes,
+			atomic_long_read(&task->mm->nr_ptes),
 			get_mm_counter(task->mm, MM_SWAPENTS),
 			task->signal->oom_score_adj, task->comm);
 		task_unlock(task);
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 3929a40bd6c..cbb38545d9d 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -151,14 +151,14 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pgtable)
 {
-	assert_spin_locked(&mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
 	/* FIFO */
-	if (!mm->pmd_huge_pte)
+	if (!pmd_huge_pte(mm, pmdp))
 		INIT_LIST_HEAD(&pgtable->lru);
 	else
-		list_add(&pgtable->lru, &mm->pmd_huge_pte->lru);
-	mm->pmd_huge_pte = pgtable;
+		list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru);
+	pmd_huge_pte(mm, pmdp) = pgtable;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
@@ -170,14 +170,14 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
 	pgtable_t pgtable;
 
-	assert_spin_locked(&mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
 	/* FIFO */
-	pgtable = mm->pmd_huge_pte;
+	pgtable = pmd_huge_pte(mm, pmdp);
 	if (list_empty(&pgtable->lru))
-		mm->pmd_huge_pte = NULL;
+		pmd_huge_pte(mm, pmdp) = NULL;
 	else {
-		mm->pmd_huge_pte = list_entry(pgtable->lru.next,
+		pmd_huge_pte(mm, pmdp) = list_entry(pgtable->lru.next,
 					      struct page, lru);
 		list_del(&pgtable->lru);
 	}
diff --git a/mm/rmap.c b/mm/rmap.c
index fd3ee7a54a1..55c8b8dc9ff 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -601,7 +601,7 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 
 	if (unlikely(PageHuge(page))) {
 		pte = huge_pte_offset(mm, address);
-		ptl = &mm->page_table_lock;
+		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
 		goto check;
 	}
 
@@ -665,25 +665,23 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			unsigned long *vm_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	int referenced = 0;
 
 	if (unlikely(PageTransHuge(page))) {
 		pmd_t *pmd;
 
-		spin_lock(&mm->page_table_lock);
 		/*
 		 * rmap might return false positives; we must filter
 		 * these out using page_check_address_pmd().
 		 */
 		pmd = page_check_address_pmd(page, mm, address,
-					     PAGE_CHECK_ADDRESS_PMD_FLAG);
-		if (!pmd) {
-			spin_unlock(&mm->page_table_lock);
+					     PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl);
+		if (!pmd)
 			goto out;
-		}
 
 		if (vma->vm_flags & VM_LOCKED) {
-			spin_unlock(&mm->page_table_lock);
+			spin_unlock(ptl);
 			*mapcount = 0;	/* break early from loop */
 			*vm_flags |= VM_LOCKED;
 			goto out;
@@ -692,10 +690,9 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		/* go ahead even if the pmd is pmd_trans_splitting() */
 		if (pmdp_clear_flush_young_notify(vma, address, pmd))
 			referenced++;
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 	} else {
 		pte_t *pte;
-		spinlock_t *ptl;
 
 		/*
 		 * rmap might return false positives; we must filter