Merge 4.5-rc4 into tty-next

We want the fixes in here, and this resolves a merge error in tty_io.c

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

19 files changed, 220 insertions, 165 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 97a4e06..03cbfa0 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -624,7 +624,7 @@ config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	bool
 
 config DEFERRED_STRUCT_PAGE_INIT
-	bool "Defer initialisation of struct pages to kswapd"
+	bool "Defer initialisation of struct pages to kthreads"
 	default n
 	depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	depends on MEMORY_HOTPLUG
@@ -633,9 +633,10 @@ config DEFERRED_STRUCT_PAGE_INIT
 	  single thread. On very large machines this can take a considerable
 	  amount of time. If this option is set, large machines will bring up
 	  a subset of memmap at boot and then initialise the rest in parallel
-	  when kswapd starts. This has a potential performance impact on
-	  processes running early in the lifetime of the systemm until kswapd
-	  finishes the initialisation.
+	  by starting one-off "pgdatinitX" kernel thread for each node X. This
+	  has a potential performance impact on processes running early in the
+	  lifetime of the system until these kthreads finish the
+	  initialisation.
 
 config IDLE_PAGE_TRACKING
 	bool "Enable idle page tracking"
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index cc5d29d..c554d17 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -328,7 +328,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	return 0;
 
 out_destroy_stat:
-	while (--i)
+	while (i--)
 		percpu_counter_destroy(&wb->stat[i]);
 	fprop_local_destroy_percpu(&wb->completions);
 out_put_cong:
@@ -989,7 +989,7 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
 		 * here rather than calling cond_resched().
 		 */
 		if (current->flags & PF_WQ_WORKER)
-			schedule_timeout(1);
+			schedule_timeout_uninterruptible(1);
 		else
 			cond_resched();
 
diff --git a/mm/filemap.c b/mm/filemap.c
index bc94386..23edcce 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1890,6 +1890,7 @@ EXPORT_SYMBOL(generic_file_read_iter);
  * page_cache_read - adds requested page to the page cache if not already there
  * @file:	file to read
  * @offset:	page index
+ * @gfp_mask:	memory allocation flags
  *
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.
diff --git a/mm/gup.c b/mm/gup.c
index b64a361..7bf19ff 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -430,10 +430,8 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 			 * Anon pages in shared mappings are surprising: now
 			 * just reject it.
 			 */
-			if (!is_cow_mapping(vm_flags)) {
-				WARN_ON_ONCE(vm_flags & VM_MAYWRITE);
+			if (!is_cow_mapping(vm_flags))
 				return -EFAULT;
-			}
 		}
 	} else if (!(vm_flags & VM_READ)) {
 		if (!(gup_flags & FOLL_FORCE))
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index fd3a07b..08fc0ba 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -138,9 +138,6 @@ 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)
@@ -861,7 +858,8 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		return false;
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
 	entry = pmd_mkhuge(entry);
-	pgtable_trans_huge_deposit(mm, pmd, pgtable);
+	if (pgtable)
+		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
 	atomic_long_inc(&mm->nr_ptes);
 	return true;
@@ -1039,13 +1037,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	spinlock_t *dst_ptl, *src_ptl;
 	struct page *src_page;
 	pmd_t pmd;
-	pgtable_t pgtable;
+	pgtable_t pgtable = NULL;
 	int ret;
 
-	ret = -ENOMEM;
-	pgtable = pte_alloc_one(dst_mm, addr);
-	if (unlikely(!pgtable))
-		goto out;
+	if (!vma_is_dax(vma)) {
+		ret = -ENOMEM;
+		pgtable = pte_alloc_one(dst_mm, addr);
+		if (unlikely(!pgtable))
+			goto out;
+	}
 
 	dst_ptl = pmd_lock(dst_mm, dst_pmd);
 	src_ptl = pmd_lockptr(src_mm, src_pmd);
@@ -1076,7 +1076,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		goto out_unlock;
 	}
 
-	if (pmd_trans_huge(pmd)) {
+	if (!vma_is_dax(vma)) {
 		/* thp accounting separate from pmd_devmap accounting */
 		src_page = pmd_page(pmd);
 		VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
@@ -3358,6 +3358,7 @@ int total_mapcount(struct page *page)
 int split_huge_page_to_list(struct page *page, struct list_head *list)
 {
 	struct page *head = compound_head(page);
+	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
 	struct anon_vma *anon_vma;
 	int count, mapcount, ret;
 	bool mlocked;
@@ -3401,19 +3402,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		lru_add_drain();
 
 	/* Prevent deferred_split_scan() touching ->_count */
-	spin_lock_irqsave(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	count = page_count(head);
 	mapcount = total_mapcount(head);
 	if (!mapcount && count == 1) {
 		if (!list_empty(page_deferred_list(head))) {
-			split_queue_len--;
+			pgdata->split_queue_len--;
 			list_del(page_deferred_list(head));
 		}
-		spin_unlock_irqrestore(&split_queue_lock, flags);
+		spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 		__split_huge_page(page, list);
 		ret = 0;
 	} else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
-		spin_unlock_irqrestore(&split_queue_lock, flags);
+		spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 		pr_alert("total_mapcount: %u, page_count(): %u\n",
 				mapcount, count);
 		if (PageTail(page))
@@ -3421,7 +3422,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		dump_page(page, "total_mapcount(head) > 0");
 		BUG();
 	} else {
-		spin_unlock_irqrestore(&split_queue_lock, flags);
+		spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 		unfreeze_page(anon_vma, head);
 		ret = -EBUSY;
 	}
@@ -3436,64 +3437,65 @@ out:
 
 void free_transhuge_page(struct page *page)
 {
+	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
 	unsigned long flags;
 
-	spin_lock_irqsave(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	if (!list_empty(page_deferred_list(page))) {
-		split_queue_len--;
+		pgdata->split_queue_len--;
 		list_del(page_deferred_list(page));
 	}
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 	free_compound_page(page);
 }
 
 void deferred_split_huge_page(struct page *page)
 {
+	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
 	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 
-	spin_lock_irqsave(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	if (list_empty(page_deferred_list(page))) {
-		list_add_tail(page_deferred_list(page), &split_queue);
-		split_queue_len++;
+		list_add_tail(page_deferred_list(page), &pgdata->split_queue);
+		pgdata->split_queue_len++;
 	}
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_unlock_irqrestore(&pgdata->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;
+	struct pglist_data *pgdata = NODE_DATA(sc->nid);
+	return ACCESS_ONCE(pgdata->split_queue_len);
 }
 
 static unsigned long deferred_split_scan(struct shrinker *shrink,
 		struct shrink_control *sc)
 {
+	struct pglist_data *pgdata = NODE_DATA(sc->nid);
 	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);
-
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	/* Take pin on all head pages to avoid freeing them under us */
-	list_for_each_safe(pos, next, &list) {
+	list_for_each_safe(pos, next, &pgdata->split_queue) {
 		page = list_entry((void *)pos, struct page, mapping);
 		page = compound_head(page);
-		/* race with put_compound_page() */
-		if (!get_page_unless_zero(page)) {
+		if (get_page_unless_zero(page)) {
+			list_move(page_deferred_list(page), &list);
+		} else {
+			/* We lost race with put_compound_page() */
 			list_del_init(page_deferred_list(page));
-			split_queue_len--;
+			pgdata->split_queue_len--;
 		}
+		if (!--sc->nr_to_scan)
+			break;
 	}
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 
 	list_for_each_safe(pos, next, &list) {
 		page = list_entry((void *)pos, struct page, mapping);
@@ -3505,17 +3507,24 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 		put_page(page);
 	}
 
-	spin_lock_irqsave(&split_queue_lock, flags);
-	list_splice_tail(&list, &split_queue);
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+	list_splice_tail(&list, &pgdata->split_queue);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 
-	return split * HPAGE_PMD_NR / 2;
+	/*
+	 * Stop shrinker if we didn't split any page, but the queue is empty.
+	 * This can happen if pages were freed under us.
+	 */
+	if (!split && list_empty(&pgdata->split_queue))
+		return SHRINK_STOP;
+	return split;
 }
 
 static struct shrinker deferred_split_shrinker = {
 	.count_objects = deferred_split_count,
 	.scan_objects = deferred_split_scan,
 	.seeks = DEFAULT_SEEKS,
+	.flags = SHRINKER_NUMA_AWARE,
 };
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 12908dc..06ae13e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1001,7 +1001,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 		((node = hstate_next_node_to_free(hs, mask)) || 1);	\
 		nr_nodes--)
 
-#if defined(CONFIG_CMA) && defined(CONFIG_X86_64)
+#if defined(CONFIG_X86_64) && ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA))
 static void destroy_compound_gigantic_page(struct page *page,
 					unsigned int order)
 {
@@ -1214,8 +1214,8 @@ void free_huge_page(struct page *page)
 
 	set_page_private(page, 0);
 	page->mapping = NULL;
-	BUG_ON(page_count(page));
-	BUG_ON(page_mapcount(page));
+	VM_BUG_ON_PAGE(page_count(page), page);
+	VM_BUG_ON_PAGE(page_mapcount(page), page);
 	restore_reserve = PagePrivate(page);
 	ClearPagePrivate(page);
 
@@ -1286,6 +1286,7 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order)
 		set_page_count(p, 0);
 		set_compound_head(p, page);
 	}
+	atomic_set(compound_mapcount_ptr(page), -1);
 }
 
 /*
diff --git a/mm/internal.h b/mm/internal.h
index ed8b5ff..a38a21e 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -216,6 +216,37 @@ static inline bool is_cow_mapping(vm_flags_t flags)
 	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 }
 
+/*
+ * These three helpers classifies VMAs for virtual memory accounting.
+ */
+
+/*
+ * Executable code area - executable, not writable, not stack
+ */
+static inline bool is_exec_mapping(vm_flags_t flags)
+{
+	return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC;
+}
+
+/*
+ * Stack area - atomatically grows in one direction
+ *
+ * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous:
+ * do_mmap() forbids all other combinations.
+ */
+static inline bool is_stack_mapping(vm_flags_t flags)
+{
+	return (flags & VM_STACK) == VM_STACK;
+}
+
+/*
+ * Data area - private, writable, not stack
+ */
+static inline bool is_data_mapping(vm_flags_t flags)
+{
+	return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
+}
+
 /* mm/util.c */
 void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct rb_node *rb_parent);
diff --git a/mm/memblock.c b/mm/memblock.c
index d2ed81e..dd79899 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1448,7 +1448,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size)
  * Remaining API functions
  */
 
-phys_addr_t __init memblock_phys_mem_size(void)
+phys_addr_t __init_memblock memblock_phys_mem_size(void)
 {
 	return memblock.memory.total_size;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 30991f8..635451a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1591,10 +1591,15 @@ 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_t_valid(pfn)) {
+	if (!HAVE_PTE_SPECIAL && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) {
 		struct page *page;
 
-		page = pfn_t_to_page(pfn);
+		/*
+		 * At this point we are committed to insert_page()
+		 * regardless of whether the caller specified flags that
+		 * result in pfn_t_has_page() == false.
+		 */
+		page = pfn_to_page(pfn_t_to_pfn(pfn));
 		return insert_page(vma, addr, page, vma->vm_page_prot);
 	}
 	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
@@ -2232,11 +2237,6 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	page_cache_get(old_page);
 
-	/*
-	 * Only catch write-faults on shared writable pages,
-	 * read-only shared pages can get COWed by
-	 * get_user_pages(.write=1, .force=1).
-	 */
 	if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
 		int tmp;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 27d1354..4c4187c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -548,8 +548,7 @@ retry:
 			goto retry;
 		}
 
-		if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
-			migrate_page_add(page, qp->pagelist, flags);
+		migrate_page_add(page, qp->pagelist, flags);
 	}
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
@@ -625,7 +624,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 	unsigned long endvma = vma->vm_end;
 	unsigned long flags = qp->flags;
 
-	if (vma->vm_flags & VM_PFNMAP)
+	if (!vma_migratable(vma))
 		return 1;
 
 	if (endvma > end)
@@ -644,16 +643,13 @@ 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_migratable(vma) &&
-			vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
+		if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
 			change_prot_numa(vma, start, endvma);
 		return 1;
 	}
 
-	if ((flags & MPOL_MF_STRICT) ||
-	    ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
-	     vma_migratable(vma)))
-		/* queue pages from current vma */
+	/* queue pages from current vma */
+	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
 		return 0;
 	return 1;
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 84b1262..2f2415a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -42,6 +42,7 @@
 #include <linux/memory.h>
 #include <linux/printk.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/moduleparam.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -69,6 +70,8 @@ const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX;
 int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
 #endif
 
+static bool ignore_rlimit_data = true;
+core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
 
 static void unmap_region(struct mm_struct *mm,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
@@ -387,8 +390,9 @@ static long vma_compute_subtree_gap(struct vm_area_struct *vma)
 }
 
 #ifdef CONFIG_DEBUG_VM_RB
-static int browse_rb(struct rb_root *root)
+static int browse_rb(struct mm_struct *mm)
 {
+	struct rb_root *root = &mm->mm_rb;
 	int i = 0, j, bug = 0;
 	struct rb_node *nd, *pn = NULL;
 	unsigned long prev = 0, pend = 0;
@@ -411,12 +415,14 @@ static int browse_rb(struct rb_root *root)
 				  vma->vm_start, vma->vm_end);
 			bug = 1;
 		}
+		spin_lock(&mm->page_table_lock);
 		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
 			pr_emerg("free gap %lx, correct %lx\n",
 			       vma->rb_subtree_gap,
 			       vma_compute_subtree_gap(vma));
 			bug = 1;
 		}
+		spin_unlock(&mm->page_table_lock);
 		i++;
 		pn = nd;
 		prev = vma->vm_start;
@@ -453,12 +459,16 @@ static void validate_mm(struct mm_struct *mm)
 	struct vm_area_struct *vma = mm->mmap;
 
 	while (vma) {
+		struct anon_vma *anon_vma = vma->anon_vma;
 		struct anon_vma_chain *avc;
 
-		vma_lock_anon_vma(vma);
-		list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
-			anon_vma_interval_tree_verify(avc);
-		vma_unlock_anon_vma(vma);
+		if (anon_vma) {
+			anon_vma_lock_read(anon_vma);
+			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
+				anon_vma_interval_tree_verify(avc);
+			anon_vma_unlock_read(anon_vma);
+		}
+
 		highest_address = vma->vm_end;
 		vma = vma->vm_next;
 		i++;
@@ -472,7 +482,7 @@ static void validate_mm(struct mm_struct *mm)
 			  mm->highest_vm_end, highest_address);
 		bug = 1;
 	}
-	i = browse_rb(&mm->mm_rb);
+	i = browse_rb(mm);
 	if (i != mm->map_count) {
 		if (i != -1)
 			pr_emerg("map_count %d rb %d\n", mm->map_count, i);
@@ -2139,32 +2149,27 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	int error;
+	int error = 0;
 
 	if (!(vma->vm_flags & VM_GROWSUP))
 		return -EFAULT;
 
-	/*
-	 * We must make sure the anon_vma is allocated
-	 * so that the anon_vma locking is not a noop.
-	 */
+	/* Guard against wrapping around to address 0. */
+	if (address < PAGE_ALIGN(address+4))
+		address = PAGE_ALIGN(address+4);
+	else
+		return -ENOMEM;
+
+	/* We must make sure the anon_vma is allocated. */
 	if (unlikely(anon_vma_prepare(vma)))
 		return -ENOMEM;
-	vma_lock_anon_vma(vma);
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller
 	 * is required to hold the mmap_sem in read mode.  We need the
 	 * anon_vma lock to serialize against concurrent expand_stacks.
-	 * Also guard against wrapping around to address 0.
 	 */
-	if (address < PAGE_ALIGN(address+4))
-		address = PAGE_ALIGN(address+4);
-	else {
-		vma_unlock_anon_vma(vma);
-		return -ENOMEM;
-	}
-	error = 0;
+	anon_vma_lock_write(vma->anon_vma);
 
 	/* Somebody else might have raced and expanded it already */
 	if (address > vma->vm_end) {
@@ -2182,7 +2187,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 				 * updates, but we only hold a shared mmap_sem
 				 * lock here, so we need to protect against
 				 * concurrent vma expansions.
-				 * vma_lock_anon_vma() doesn't help here, as
+				 * anon_vma_lock_write() doesn't help here, as
 				 * we don't guarantee that all growable vmas
 				 * in a mm share the same root anon vma.
 				 * So, we reuse mm->page_table_lock to guard
@@ -2205,7 +2210,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 			}
 		}
 	}
-	vma_unlock_anon_vma(vma);
+	anon_vma_unlock_write(vma->anon_vma);
 	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	validate_mm(mm);
 	return error;
@@ -2221,25 +2226,21 @@ int expand_downwards(struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 	int error;
 
-	/*
-	 * We must make sure the anon_vma is allocated
-	 * so that the anon_vma locking is not a noop.
-	 */
-	if (unlikely(anon_vma_prepare(vma)))
-		return -ENOMEM;
-
 	address &= PAGE_MASK;
 	error = security_mmap_addr(address);
 	if (error)
 		return error;
 
-	vma_lock_anon_vma(vma);
+	/* We must make sure the anon_vma is allocated. */
+	if (unlikely(anon_vma_prepare(vma)))
+		return -ENOMEM;
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller
 	 * is required to hold the mmap_sem in read mode.  We need the
 	 * anon_vma lock to serialize against concurrent expand_stacks.
 	 */
+	anon_vma_lock_write(vma->anon_vma);
 
 	/* Somebody else might have raced and expanded it already */
 	if (address < vma->vm_start) {
@@ -2257,7 +2258,7 @@ int expand_downwards(struct vm_area_struct *vma,
 				 * updates, but we only hold a shared mmap_sem
 				 * lock here, so we need to protect against
 				 * concurrent vma expansions.
-				 * vma_lock_anon_vma() doesn't help here, as
+				 * anon_vma_lock_write() doesn't help here, as
 				 * we don't guarantee that all growable vmas
 				 * in a mm share the same root anon vma.
 				 * So, we reuse mm->page_table_lock to guard
@@ -2278,7 +2279,7 @@ int expand_downwards(struct vm_area_struct *vma,
 			}
 		}
 	}
-	vma_unlock_anon_vma(vma);
+	anon_vma_unlock_write(vma->anon_vma);
 	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	validate_mm(mm);
 	return error;
@@ -2982,9 +2983,17 @@ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages)
 	if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT)
 		return false;
 
-	if ((flags & (VM_WRITE | VM_SHARED | (VM_STACK_FLAGS &
-				(VM_GROWSUP | VM_GROWSDOWN)))) == VM_WRITE)
-		return mm->data_vm + npages <= rlimit(RLIMIT_DATA);
+	if (is_data_mapping(flags) &&
+	    mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) {
+		if (ignore_rlimit_data)
+			pr_warn_once("%s (%d): VmData %lu exceed data ulimit "
+				     "%lu. Will be forbidden soon.\n",
+				     current->comm, current->pid,
+				     (mm->data_vm + npages) << PAGE_SHIFT,
+				     rlimit(RLIMIT_DATA));
+		else
+			return false;
+	}
 
 	return true;
 }
@@ -2993,11 +3002,11 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
 {
 	mm->total_vm += npages;
 
-	if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC)
+	if (is_exec_mapping(flags))
 		mm->exec_vm += npages;
-	else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN)))
+	else if (is_stack_mapping(flags))
 		mm->stack_vm += npages;
-	else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
+	else if (is_data_mapping(flags))
 		mm->data_vm += npages;
 }
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 8eb7bb4..f7cb3d4 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -160,9 +160,11 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		}
 
 		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
-			if (next - addr != HPAGE_PMD_SIZE)
+			if (next - addr != HPAGE_PMD_SIZE) {
 				split_huge_pmd(vma, pmd, addr);
-			else {
+				if (pmd_none(*pmd))
+					continue;
+			} else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
 						newprot, prot_numa);
 
diff --git a/mm/mremap.c b/mm/mremap.c
index d77946a..8eeba02 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -210,6 +210,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				}
 			}
 			split_huge_pmd(vma, old_pmd, old_addr);
+			if (pmd_none(*old_pmd))
+				continue;
 			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 63358d9..838ca8bb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5210,6 +5210,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	pgdat->numabalancing_migrate_nr_pages = 0;
 	pgdat->numabalancing_migrate_next_window = jiffies;
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	spin_lock_init(&pgdat->split_queue_lock);
+	INIT_LIST_HEAD(&pgdat->split_queue);
+	pgdat->split_queue_len = 0;
+#endif
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);
 	pgdat_page_ext_init(pgdat);
@@ -6615,7 +6620,7 @@ bool is_pageblock_removable_nolock(struct page *page)
 	return !has_unmovable_pages(zone, page, 0, true);
 }
 
-#ifdef CONFIG_CMA
+#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
 
 static unsigned long pfn_max_align_down(unsigned long pfn)
 {
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 9d47676..06a005b 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -90,9 +90,9 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
  * ARCHes with special requirements for evicting THP backing TLB entries can
  * implement this. Otherwise also, it can help optimize normal TLB flush in
  * THP regime. stock flush_tlb_range() typically has optimization to nuke the
- * entire TLB TLB if flush span is greater than a threshhold, which will
+ * entire TLB if flush span is greater than a threshold, which will
  * likely be true for a single huge page. Thus a single thp flush will
- * invalidate the entire TLB which is not desitable.
+ * invalidate the entire TLB which is not desirable.
  * e.g. see arch/arc: flush_pmd_tlb_range
  */
 #define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
@@ -195,7 +195,9 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(pmd_trans_huge(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
-	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	/* collapse entails shooting down ptes not pmd */
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
 }
 #endif
diff --git a/mm/util.c b/mm/util.c
index c108a65..4fb14ca 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -230,36 +230,11 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /* Check if the vma is being used as a stack by this task */
-static int vm_is_stack_for_task(struct task_struct *t,
-				struct vm_area_struct *vma)
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
 {
 	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
 }
 
-/*
- * Check if the vma is being used as a stack.
- * If is_group is non-zero, check in the entire thread group or else
- * just check in the current task. Returns the task_struct of the task
- * that the vma is stack for. Must be called under rcu_read_lock().
- */
-struct task_struct *task_of_stack(struct task_struct *task,
-				struct vm_area_struct *vma, bool in_group)
-{
-	if (vm_is_stack_for_task(task, vma))
-		return task;
-
-	if (in_group) {
-		struct task_struct *t;
-
-		for_each_thread(task, t) {
-			if (vm_is_stack_for_task(t, vma))
-				return t;
-		}
-	}
-
-	return NULL;
-}
-
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 9a6c070..149fdf6 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -248,9 +248,8 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
 
 	if (tree) {
 		spin_lock(&vmpr->sr_lock);
-		vmpr->tree_scanned += scanned;
+		scanned = vmpr->tree_scanned += scanned;
 		vmpr->tree_reclaimed += reclaimed;
-		scanned = vmpr->scanned;
 		spin_unlock(&vmpr->sr_lock);
 
 		if (scanned < vmpressure_win)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eb3dd37..71b1c29 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1443,7 +1443,7 @@ int isolate_lru_page(struct page *page)
 	int ret = -EBUSY;
 
 	VM_BUG_ON_PAGE(!page_count(page), page);
-	VM_BUG_ON_PAGE(PageTail(page), page);
+	WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
 
 	if (PageLRU(page)) {
 		struct zone *zone = page_zone(page);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 40b2c74..084c672 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1396,10 +1396,15 @@ static void vmstat_update(struct work_struct *w)
 		 * Counters were updated so we expect more updates
 		 * to occur in the future. Keep on running the
 		 * update worker thread.
+		 * If we were marked on cpu_stat_off clear the flag
+		 * so that vmstat_shepherd doesn't schedule us again.
 		 */
-		queue_delayed_work_on(smp_processor_id(), vmstat_wq,
-			this_cpu_ptr(&vmstat_work),
-			round_jiffies_relative(sysctl_stat_interval));
+		if (!cpumask_test_and_clear_cpu(smp_processor_id(),
+						cpu_stat_off)) {
+			queue_delayed_work_on(smp_processor_id(), vmstat_wq,
+				this_cpu_ptr(&vmstat_work),
+				round_jiffies_relative(sysctl_stat_interval));
+		}
 	} else {
 		/*
 		 * We did not update any counters so the app may be in
@@ -1417,18 +1422,6 @@ static void vmstat_update(struct work_struct *w)
  * until the diffs stay at zero. The function is used by NOHZ and can only be
  * invoked when tick processing is not active.
  */
-void quiet_vmstat(void)
-{
-	if (system_state != SYSTEM_RUNNING)
-		return;
-
-	do {
-		if (!cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off))
-			cancel_delayed_work(this_cpu_ptr(&vmstat_work));
-
-	} while (refresh_cpu_vm_stats(false));
-}
-
 /*
  * Check if the diffs for a certain cpu indicate that
  * an update is needed.
@@ -1452,6 +1445,30 @@ static bool need_update(int cpu)
 	return false;
 }
 
+void quiet_vmstat(void)
+{
+	if (system_state != SYSTEM_RUNNING)
+		return;
+
+	/*
+	 * If we are already in hands of the shepherd then there
+	 * is nothing for us to do here.
+	 */
+	if (cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off))
+		return;
+
+	if (!need_update(smp_processor_id()))
+		return;
+
+	/*
+	 * Just refresh counters and do not care about the pending delayed
+	 * vmstat_update. It doesn't fire that often to matter and canceling
+	 * it would be too expensive from this path.
+	 * vmstat_shepherd will take care about that for us.
+	 */
+	refresh_cpu_vm_stats(false);
+}
+
 
 /*
  * Shepherd worker thread that checks the
@@ -1469,18 +1486,25 @@ static void vmstat_shepherd(struct work_struct *w)
 
 	get_online_cpus();
 	/* Check processors whose vmstat worker threads have been disabled */
-	for_each_cpu(cpu, cpu_stat_off)
-		if (need_update(cpu) &&
-			cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
-
-			queue_delayed_work_on(cpu, vmstat_wq,
-				&per_cpu(vmstat_work, cpu), 0);
+	for_each_cpu(cpu, cpu_stat_off) {
+		struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
 
+		if (need_update(cpu)) {
+			if (cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
+				queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
+		} else {
+			/*
+			 * Cancel the work if quiet_vmstat has put this
+			 * cpu on cpu_stat_off because the work item might
+			 * be still scheduled
+			 */
+			cancel_delayed_work(dw);
+		}
+	}
 	put_online_cpus();
 
 	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));
-
 }
 
 static void __init start_shepherd_timer(void)
@@ -1488,7 +1512,7 @@ static void __init start_shepherd_timer(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		INIT_DELAYED_WORK(per_cpu_ptr(&vmstat_work, cpu),
+		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
 			vmstat_update);
 
 	if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL))