Merge pull request #40 from toradex/4.9-2.3.x-imx

4.9 2.3.x imx

17 files changed, 377 insertions, 203 deletions

diff --git a/mm/frame_vector.c b/mm/frame_vector.c
index 375a103d7a56..d73eed0443f6 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -61,8 +61,10 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 	 * get_user_pages_longterm() and disallow it for filesystem-dax
 	 * mappings.
 	 */
-	if (vma_is_fsdax(vma))
-		return -EOPNOTSUPP;
+	if (vma_is_fsdax(vma)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
 
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) {
 		vec->got_ref = true;
diff --git a/mm/gup.c b/mm/gup.c
index be4ccddac26f..d71da7216c6e 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1122,8 +1122,6 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 	int locked = 0;
 	long ret = 0;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
-	VM_BUG_ON(len != PAGE_ALIGN(len));
 	end = start + len;
 
 	for (nstart = start; nstart < end; nstart = nend) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e4c6c3edaf6a..7ea8da990b9d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1445,7 +1445,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		  unsigned long new_addr, unsigned long old_end,
-		  pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
+		  pmd_t *old_pmd, pmd_t *new_pmd)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	pmd_t pmd;
@@ -1476,7 +1476,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		if (new_ptl != old_ptl)
 			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
 		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
-		if (pmd_present(pmd) && pmd_dirty(pmd))
+		if (pmd_present(pmd))
 			force_flush = true;
 		VM_BUG_ON(!pmd_none(*new_pmd));
 
@@ -1487,12 +1487,10 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
 		}
 		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
-		if (new_ptl != old_ptl)
-			spin_unlock(new_ptl);
 		if (force_flush)
 			flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
-		else
-			*need_flush = true;
+		if (new_ptl != old_ptl)
+			spin_unlock(new_ptl);
 		spin_unlock(old_ptl);
 		return true;
 	}
@@ -1841,7 +1839,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 	}
 }
 
-static void freeze_page(struct page *page)
+static void unmap_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
 		TTU_RMAP_LOCKED;
@@ -1864,7 +1862,7 @@ static void freeze_page(struct page *page)
 	VM_BUG_ON_PAGE(ret, page + i - 1);
 }
 
-static void unfreeze_page(struct page *page)
+static void remap_page(struct page *page)
 {
 	int i;
 
@@ -1878,26 +1876,13 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	struct page *page_tail = head + tail;
 
 	VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);
-	VM_BUG_ON_PAGE(page_ref_count(page_tail) != 0, page_tail);
 
 	/*
-	 * tail_page->_refcount 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_inc() or
-	 * 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_inc()/atomic_add().
+	 * Clone page flags before unfreezing refcount.
+	 *
+	 * After successful get_page_unless_zero() might follow flags change,
+	 * for exmaple lock_page() which set PG_waiters.
 	 */
-	if (PageAnon(head)) {
-		page_ref_inc(page_tail);
-	} else {
-		/* Additional pin to radix tree */
-		page_ref_add(page_tail, 2);
-	}
-
 	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	page_tail->flags |= (head->flags &
 			((1L << PG_referenced) |
@@ -1909,36 +1894,42 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (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.
-	 */
+	/* ->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 flags must be visible before we make the page non-compound. */
 	smp_wmb();
 
+	/*
+	 * Clear PageTail before unfreezing page refcount.
+	 *
+	 * After successful get_page_unless_zero() might follow put_page()
+	 * which needs correct compound_head().
+	 */
 	clear_compound_head(page_tail);
 
+	/* Finally unfreeze refcount. Additional reference from page cache. */
+	page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) ||
+					  PageSwapCache(head)));
+
 	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);
 }
 
 static void __split_huge_page(struct page *page, struct list_head *list,
-		unsigned long flags)
+		pgoff_t end, unsigned long flags)
 {
 	struct page *head = compound_head(page);
 	struct zone *zone = page_zone(head);
 	struct lruvec *lruvec;
-	pgoff_t end = -1;
 	int i;
 
 	lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);
@@ -1946,9 +1937,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	/* complete memcg works before add pages to LRU */
 	mem_cgroup_split_huge_fixup(head);
 
-	if (!PageAnon(page))
-		end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE);
-
 	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
 		__split_huge_page_tail(head, i, lruvec, list);
 		/* Some pages can be beyond i_size: drop them from page cache */
@@ -1973,7 +1961,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 
 	spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 
-	unfreeze_page(head);
+	remap_page(head);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		struct page *subpage = head + i;
@@ -2101,6 +2089,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	int count, mapcount, extra_pins, ret;
 	bool mlocked;
 	unsigned long flags;
+	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -2122,6 +2111,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			goto out;
 		}
 		extra_pins = 0;
+		end = -1;
 		mapping = NULL;
 		anon_vma_lock_write(anon_vma);
 	} else {
@@ -2137,10 +2127,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		extra_pins = HPAGE_PMD_NR;
 		anon_vma = NULL;
 		i_mmap_lock_read(mapping);
+
+		/*
+		 *__split_huge_page() may need to trim off pages beyond EOF:
+		 * but on 32-bit, i_size_read() takes an irq-unsafe seqlock,
+		 * which cannot be nested inside the page tree lock. So note
+		 * end now: i_size itself may be changed at any moment, but
+		 * head page lock is good enough to serialize the trimming.
+		 */
+		end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
 	}
 
 	/*
-	 * Racy check if we can split the page, before freeze_page() will
+	 * Racy check if we can split the page, before unmap_page() will
 	 * split PMDs
 	 */
 	if (total_mapcount(head) != page_count(head) - extra_pins - 1) {
@@ -2149,7 +2148,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	mlocked = PageMlocked(page);
-	freeze_page(head);
+	unmap_page(head);
 	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* Make sure the page is not on per-CPU pagevec as it takes pin */
@@ -2186,7 +2185,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		if (mapping)
 			__dec_node_page_state(page, NR_SHMEM_THPS);
 		spin_unlock(&pgdata->split_queue_lock);
-		__split_huge_page(page, list, flags);
+		__split_huge_page(page, list, end, flags);
 		ret = 0;
 	} else {
 		if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
@@ -2201,7 +2200,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 fail:		if (mapping)
 			spin_unlock(&mapping->tree_lock);
 		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
-		unfreeze_page(head);
+		remap_page(head);
 		ret = -EBUSY;
 	}
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f9e735537c37..3e50fcfe6ad8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3220,7 +3220,7 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte)
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
 {
-	pte_t *src_pte, *dst_pte, entry;
+	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
 	int cow;
@@ -3248,15 +3248,30 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			break;
 		}
 
-		/* If the pagetables are shared don't copy or take references */
-		if (dst_pte == src_pte)
+		/*
+		 * If the pagetables are shared don't copy or take references.
+		 * dst_pte == src_pte is the common case of src/dest sharing.
+		 *
+		 * However, src could have 'unshared' and dst shares with
+		 * another vma.  If dst_pte !none, this implies sharing.
+		 * Check here before taking page table lock, and once again
+		 * after taking the lock below.
+		 */
+		dst_entry = huge_ptep_get(dst_pte);
+		if ((dst_pte == src_pte) || !huge_pte_none(dst_entry))
 			continue;
 
 		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);
 		entry = huge_ptep_get(src_pte);
-		if (huge_pte_none(entry)) { /* skip none entry */
+		dst_entry = huge_ptep_get(dst_pte);
+		if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
+			/*
+			 * Skip if src entry none.  Also, skip in the
+			 * unlikely case dst entry !none as this implies
+			 * sharing with another vma.
+			 */
 			;
 		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
 				    is_hugetlb_entry_hwpoisoned(entry))) {
@@ -3645,6 +3660,12 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 		return err;
 	ClearPagePrivate(page);
 
+	/*
+	 * set page dirty so that it will not be removed from cache/file
+	 * by non-hugetlbfs specific code paths.
+	 */
+	set_page_dirty(page);
+
 	spin_lock(&inode->i_lock);
 	inode->i_blocks += blocks_per_huge_page(h);
 	spin_unlock(&inode->i_lock);
@@ -4149,6 +4170,12 @@ int hugetlb_reserve_pages(struct inode *inode,
 	struct resv_map *resv_map;
 	long gbl_reserve;
 
+	/* This should never happen */
+	if (from > to) {
+		VM_WARN(1, "%s called with a negative range\n", __func__);
+		return -EINVAL;
+	}
+
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
 	 * attempt will be made for VM_NORESERVE to allocate a page
@@ -4238,7 +4265,9 @@ int hugetlb_reserve_pages(struct inode *inode,
 	return 0;
 out_err:
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
-		region_abort(resv_map, from, to);
+		/* Don't call region_abort if region_chg failed */
+		if (chg >= 0)
+			region_abort(resv_map, from, to);
 	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		kref_put(&resv_map->refs, resv_map_release);
 	return ret;
@@ -4312,13 +4341,41 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 	/*
 	 * check on proper vm_flags and page table alignment
 	 */
-	if (vma->vm_flags & VM_MAYSHARE &&
-	    vma->vm_start <= base && end <= vma->vm_end)
+	if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end))
 		return true;
 	return false;
 }
 
 /*
+ * Determine if start,end range within vma could be mapped by shared pmd.
+ * If yes, adjust start and end to cover range associated with possible
+ * shared pmd mappings.
+ */
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+	unsigned long check_addr = *start;
+
+	if (!(vma->vm_flags & VM_MAYSHARE))
+		return;
+
+	for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) {
+		unsigned long a_start = check_addr & PUD_MASK;
+		unsigned long a_end = a_start + PUD_SIZE;
+
+		/*
+		 * If sharing is possible, adjust start/end if necessary.
+		 */
+		if (range_in_vma(vma, a_start, a_end)) {
+			if (a_start < *start)
+				*start = a_start;
+			if (a_end > *end)
+				*end = a_end;
+		}
+	}
+}
+
+/*
  * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
  * and returns the corresponding pte. While this is not necessary for the
  * !shared pmd case because we can allocate the pmd later as well, it makes the
@@ -4414,6 +4471,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
+
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
 #define want_pmd_share()	(0)
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 1df37ee996d5..e0cfc3a54b6a 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1286,7 +1286,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  * collapse_shmem - collapse small tmpfs/shmem pages into huge one.
  *
  * Basic scheme is simple, details are more complex:
- *  - allocate and freeze a new huge page;
+ *  - allocate and lock a new huge page;
  *  - scan over radix tree replacing old pages the new one
  *    + swap in pages if necessary;
  *    + fill in gaps;
@@ -1294,11 +1294,11 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  *  - if replacing succeed:
  *    + copy data over;
  *    + free old pages;
- *    + unfreeze huge page;
+ *    + unlock huge page;
  *  - if replacing failed;
  *    + put all pages back and unfreeze them;
  *    + restore gaps in the radix-tree;
- *    + free huge page;
+ *    + unlock and free huge page;
  */
 static void collapse_shmem(struct mm_struct *mm,
 		struct address_space *mapping, pgoff_t start,
@@ -1332,18 +1332,15 @@ static void collapse_shmem(struct mm_struct *mm,
 		goto out;
 	}
 
+	__SetPageLocked(new_page);
+	__SetPageSwapBacked(new_page);
 	new_page->index = start;
 	new_page->mapping = mapping;
-	__SetPageSwapBacked(new_page);
-	__SetPageLocked(new_page);
-	BUG_ON(!page_ref_freeze(new_page, 1));
-
 
 	/*
-	 * At this point the new_page is 'frozen' (page_count() is zero), locked
-	 * and not up-to-date. It's safe to insert it into radix tree, because
-	 * nobody would be able to map it or use it in other way until we
-	 * unfreeze it.
+	 * At this point the new_page is locked and not up-to-date.
+	 * It's safe to insert it into the page cache, because nobody would
+	 * be able to map it or use it in another way until we unlock it.
 	 */
 
 	index = start;
@@ -1352,18 +1349,28 @@ static void collapse_shmem(struct mm_struct *mm,
 		int n = min(iter.index, end) - index;
 
 		/*
+		 * Stop if extent has been hole-punched, and is now completely
+		 * empty (the more obvious i_size_read() check would take an
+		 * irq-unsafe seqlock on 32-bit).
+		 */
+		if (n >= HPAGE_PMD_NR) {
+			result = SCAN_TRUNCATED;
+			goto tree_locked;
+		}
+
+		/*
 		 * Handle holes in the radix tree: charge it from shmem and
 		 * insert relevant subpage of new_page into the radix-tree.
 		 */
 		if (n && !shmem_charge(mapping->host, n)) {
 			result = SCAN_FAIL;
-			break;
+			goto tree_locked;
 		}
-		nr_none += n;
 		for (; index < min(iter.index, end); index++) {
 			radix_tree_insert(&mapping->page_tree, index,
 					new_page + (index % HPAGE_PMD_NR));
 		}
+		nr_none += n;
 
 		/* We are done. */
 		if (index >= end)
@@ -1379,12 +1386,12 @@ static void collapse_shmem(struct mm_struct *mm,
 				result = SCAN_FAIL;
 				goto tree_unlocked;
 			}
-			spin_lock_irq(&mapping->tree_lock);
 		} else if (trylock_page(page)) {
 			get_page(page);
+			spin_unlock_irq(&mapping->tree_lock);
 		} else {
 			result = SCAN_PAGE_LOCK;
-			break;
+			goto tree_locked;
 		}
 
 		/*
@@ -1393,17 +1400,24 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(!PageUptodate(page), page);
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
+
+		/*
+		 * If file was truncated then extended, or hole-punched, before
+		 * we locked the first page, then a THP might be there already.
+		 */
+		if (PageTransCompound(page)) {
+			result = SCAN_PAGE_COMPOUND;
+			goto out_unlock;
+		}
 
 		if (page_mapping(page) != mapping) {
 			result = SCAN_TRUNCATED;
 			goto out_unlock;
 		}
-		spin_unlock_irq(&mapping->tree_lock);
 
 		if (isolate_lru_page(page)) {
 			result = SCAN_DEL_PAGE_LRU;
-			goto out_isolate_failed;
+			goto out_unlock;
 		}
 
 		if (page_mapped(page))
@@ -1425,7 +1439,9 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		if (!page_ref_freeze(page, 3)) {
 			result = SCAN_PAGE_COUNT;
-			goto out_lru;
+			spin_unlock_irq(&mapping->tree_lock);
+			putback_lru_page(page);
+			goto out_unlock;
 		}
 
 		/*
@@ -1441,17 +1457,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		slot = radix_tree_iter_next(&iter);
 		index++;
 		continue;
-out_lru:
-		spin_unlock_irq(&mapping->tree_lock);
-		putback_lru_page(page);
-out_isolate_failed:
-		unlock_page(page);
-		put_page(page);
-		goto tree_unlocked;
 out_unlock:
 		unlock_page(page);
 		put_page(page);
-		break;
+		goto tree_unlocked;
 	}
 
 	/*
@@ -1459,14 +1468,18 @@ out_unlock:
 	 * This code only triggers if there's nothing in radix tree
 	 * beyond 'end'.
 	 */
-	if (result == SCAN_SUCCEED && index < end) {
+	if (index < end) {
 		int n = end - index;
 
+		/* Stop if extent has been truncated, and is now empty */
+		if (n >= HPAGE_PMD_NR) {
+			result = SCAN_TRUNCATED;
+			goto tree_locked;
+		}
 		if (!shmem_charge(mapping->host, n)) {
 			result = SCAN_FAIL;
 			goto tree_locked;
 		}
-
 		for (; index < end; index++) {
 			radix_tree_insert(&mapping->page_tree, index,
 					new_page + (index % HPAGE_PMD_NR));
@@ -1474,57 +1487,62 @@ out_unlock:
 		nr_none += n;
 	}
 
+	__inc_node_page_state(new_page, NR_SHMEM_THPS);
+	if (nr_none) {
+		struct zone *zone = page_zone(new_page);
+
+		__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
+		__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+	}
+
 tree_locked:
 	spin_unlock_irq(&mapping->tree_lock);
 tree_unlocked:
 
 	if (result == SCAN_SUCCEED) {
-		unsigned long flags;
-		struct zone *zone = page_zone(new_page);
-
 		/*
 		 * Replacing old pages with new one has succeed, now we need to
 		 * copy the content and free old pages.
 		 */
+		index = start;
 		list_for_each_entry_safe(page, tmp, &pagelist, lru) {
+			while (index < page->index) {
+				clear_highpage(new_page + (index % HPAGE_PMD_NR));
+				index++;
+			}
 			copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
 					page);
 			list_del(&page->lru);
-			unlock_page(page);
-			page_ref_unfreeze(page, 1);
 			page->mapping = NULL;
+			page_ref_unfreeze(page, 1);
 			ClearPageActive(page);
 			ClearPageUnevictable(page);
+			unlock_page(page);
 			put_page(page);
+			index++;
 		}
-
-		local_irq_save(flags);
-		__inc_node_page_state(new_page, NR_SHMEM_THPS);
-		if (nr_none) {
-			__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
-			__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+		while (index < end) {
+			clear_highpage(new_page + (index % HPAGE_PMD_NR));
+			index++;
 		}
-		local_irq_restore(flags);
 
-		/*
-		 * Remove pte page tables, so we can re-faulti
-		 * the page as huge.
-		 */
-		retract_page_tables(mapping, start);
-
-		/* Everything is ready, let's unfreeze the new_page */
-		set_page_dirty(new_page);
 		SetPageUptodate(new_page);
-		page_ref_unfreeze(new_page, HPAGE_PMD_NR);
+		page_ref_add(new_page, HPAGE_PMD_NR - 1);
+		set_page_dirty(new_page);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_anon(new_page);
-		unlock_page(new_page);
 
+		/*
+		 * Remove pte page tables, so we can re-fault the page as huge.
+		 */
+		retract_page_tables(mapping, start);
 		*hpage = NULL;
 	} else {
 		/* Something went wrong: rollback changes to the radix-tree */
-		shmem_uncharge(mapping->host, nr_none);
 		spin_lock_irq(&mapping->tree_lock);
+		mapping->nrpages -= nr_none;
+		shmem_uncharge(mapping->host, nr_none);
+
 		radix_tree_for_each_slot(slot, &mapping->page_tree, &iter,
 				start) {
 			if (iter.index >= end)
@@ -1549,20 +1567,19 @@ tree_unlocked:
 			page_ref_unfreeze(page, 2);
 			radix_tree_replace_slot(slot, page);
 			spin_unlock_irq(&mapping->tree_lock);
-			putback_lru_page(page);
 			unlock_page(page);
+			putback_lru_page(page);
 			spin_lock_irq(&mapping->tree_lock);
 			slot = radix_tree_iter_next(&iter);
 		}
 		VM_BUG_ON(nr_none);
 		spin_unlock_irq(&mapping->tree_lock);
 
-		/* Unfreeze new_page, caller would take care about freeing it */
-		page_ref_unfreeze(new_page, 1);
 		mem_cgroup_cancel_charge(new_page, memcg, true);
-		unlock_page(new_page);
 		new_page->mapping = NULL;
 	}
+
+	unlock_page(new_page);
 out:
 	VM_BUG_ON(!list_empty(&pagelist));
 	/* TODO: tracepoints */
diff --git a/mm/madvise.c b/mm/madvise.c
index a49afe08698b..4a01c4bd786c 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -81,7 +81,7 @@ static long madvise_behavior(struct vm_area_struct *vma,
 		new_flags |= VM_DONTDUMP;
 		break;
 	case MADV_DODUMP:
-		if (new_flags & VM_SPECIAL) {
+		if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) {
 			error = -EINVAL;
 			goto out;
 		}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c9f715b2917f..0f962cc3f1bf 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1508,7 +1508,7 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 			while ((i < MAX_ORDER_NR_PAGES) &&
 				!pfn_valid_within(pfn + i))
 				i++;
-			if (i == MAX_ORDER_NR_PAGES)
+			if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn)
 				continue;
 			page = pfn_to_page(pfn + i);
 			if (zone && page_zone(page) != zone)
@@ -1522,7 +1522,7 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 
 	if (zone) {
 		*valid_start = start;
-		*valid_end = end;
+		*valid_end = min(end, end_pfn);
 		return 1;
 	} else {
 		return 0;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 69c4a0c92ebb..e21d9b44247b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2027,8 +2027,36 @@ retry_cpuset:
 		nmask = policy_nodemask(gfp, pol);
 		if (!nmask || node_isset(hpage_node, *nmask)) {
 			mpol_cond_put(pol);
-			page = __alloc_pages_node(hpage_node,
-						gfp | __GFP_THISNODE, order);
+			/*
+			 * We cannot invoke reclaim if __GFP_THISNODE
+			 * is set. Invoking reclaim with
+			 * __GFP_THISNODE set, would cause THP
+			 * allocations to trigger heavy swapping
+			 * despite there may be tons of free memory
+			 * (including potentially plenty of THP
+			 * already available in the buddy) on all the
+			 * other NUMA nodes.
+			 *
+			 * At most we could invoke compaction when
+			 * __GFP_THISNODE is set (but we would need to
+			 * refrain from invoking reclaim even if
+			 * compaction returned COMPACT_SKIPPED because
+			 * there wasn't not enough memory to succeed
+			 * compaction). For now just avoid
+			 * __GFP_THISNODE instead of limiting the
+			 * allocation path to a strict and single
+			 * compaction invocation.
+			 *
+			 * Supposedly if direct reclaim was enabled by
+			 * the caller, the app prefers THP regardless
+			 * of the node it comes from so this would be
+			 * more desiderable behavior than only
+			 * providing THP originated from the local
+			 * node in such case.
+			 */
+			if (!(gfp & __GFP_DIRECT_RECLAIM))
+				gfp |= __GFP_THISNODE;
+			page = __alloc_pages_node(hpage_node, gfp, order);
 			goto out;
 		}
 	}
diff --git a/mm/mmap.c b/mm/mmap.c
index aa97074a4a99..283755645d17 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2876,21 +2876,15 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk(unsigned long addr, unsigned long request)
+static int do_brk(unsigned long addr, unsigned long len)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	unsigned long flags, len;
+	unsigned long flags;
 	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
-	len = PAGE_ALIGN(request);
-	if (len < request)
-		return -ENOMEM;
-	if (!len)
-		return 0;
-
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
@@ -2959,12 +2953,19 @@ out:
 	return 0;
 }
 
-int vm_brk(unsigned long addr, unsigned long len)
+int vm_brk(unsigned long addr, unsigned long request)
 {
 	struct mm_struct *mm = current->mm;
+	unsigned long len;
 	int ret;
 	bool populate;
 
+	len = PAGE_ALIGN(request);
+	if (len < request)
+		return -ENOMEM;
+	if (!len)
+		return 0;
+
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 15976716dd40..9e6035969d7b 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -104,7 +104,7 @@ static pte_t move_soft_dirty_pte(pte_t pte)
 static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		unsigned long old_addr, unsigned long old_end,
 		struct vm_area_struct *new_vma, pmd_t *new_pmd,
-		unsigned long new_addr, bool need_rmap_locks, bool *need_flush)
+		unsigned long new_addr, bool need_rmap_locks)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *old_pte, *new_pte, pte;
@@ -152,15 +152,17 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 
 		pte = ptep_get_and_clear(mm, old_addr, old_pte);
 		/*
-		 * If we are remapping a dirty PTE, make sure
+		 * If we are remapping a valid PTE, make sure
 		 * to flush TLB before we drop the PTL for the
-		 * old PTE or we may race with page_mkclean().
+		 * PTE.
 		 *
-		 * This check has to be done after we removed the
-		 * old PTE from page tables or another thread may
-		 * dirty it after the check and before the removal.
+		 * NOTE! Both old and new PTL matter: the old one
+		 * for racing with page_mkclean(), the new one to
+		 * make sure the physical page stays valid until
+		 * the TLB entry for the old mapping has been
+		 * flushed.
 		 */
-		if (pte_present(pte) && pte_dirty(pte))
+		if (pte_present(pte))
 			force_flush = true;
 		pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
 		pte = move_soft_dirty_pte(pte);
@@ -168,13 +170,11 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	}
 
 	arch_leave_lazy_mmu_mode();
+	if (force_flush)
+		flush_tlb_range(vma, old_end - len, old_end);
 	if (new_ptl != old_ptl)
 		spin_unlock(new_ptl);
 	pte_unmap(new_pte - 1);
-	if (force_flush)
-		flush_tlb_range(vma, old_end - len, old_end);
-	else
-		*need_flush = true;
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (need_rmap_locks)
 		drop_rmap_locks(vma);
@@ -189,7 +189,6 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 {
 	unsigned long extent, next, old_end;
 	pmd_t *old_pmd, *new_pmd;
-	bool need_flush = false;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
@@ -220,8 +219,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				if (need_rmap_locks)
 					take_rmap_locks(vma);
 				moved = move_huge_pmd(vma, old_addr, new_addr,
-						    old_end, old_pmd, new_pmd,
-						    &need_flush);
+						    old_end, old_pmd, new_pmd);
 				if (need_rmap_locks)
 					drop_rmap_locks(vma);
 				if (moved)
@@ -239,10 +237,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		if (extent > LATENCY_LIMIT)
 			extent = LATENCY_LIMIT;
 		move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma,
-			  new_pmd, new_addr, need_rmap_locks, &need_flush);
+			  new_pmd, new_addr, need_rmap_locks);
 	}
-	if (need_flush)
-		flush_tlb_range(vma, old_end-len, old_addr);
 
 	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 94488b0362f8..a7276d8c96f3 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1476,6 +1476,9 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	pte_t pteval;
 	spinlock_t *ptl;
 	int ret = SWAP_AGAIN;
+	unsigned long sh_address;
+	bool pmd_sharing_possible = false;
+	unsigned long spmd_start, spmd_end;
 	struct rmap_private *rp = arg;
 	enum ttu_flags flags = rp->flags;
 
@@ -1491,6 +1494,32 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			goto out;
 	}
 
+	/*
+	 * Only use the range_start/end mmu notifiers if huge pmd sharing
+	 * is possible.  In the normal case, mmu_notifier_invalidate_page
+	 * is sufficient as we only unmap a page.  However, if we unshare
+	 * a pmd, we will unmap a PUD_SIZE range.
+	 */
+	if (PageHuge(page)) {
+		spmd_start = address;
+		spmd_end = spmd_start + vma_mmu_pagesize(vma);
+
+		/*
+		 * Check if pmd sharing is possible.  If possible, we could
+		 * unmap a PUD_SIZE range.  spmd_start/spmd_end will be
+		 * modified if sharing is possible.
+		 */
+		adjust_range_if_pmd_sharing_possible(vma, &spmd_start,
+								&spmd_end);
+		if (spmd_end - spmd_start != vma_mmu_pagesize(vma)) {
+			sh_address = address;
+
+			pmd_sharing_possible = true;
+			mmu_notifier_invalidate_range_start(vma->vm_mm,
+							spmd_start, spmd_end);
+		}
+	}
+
 	pte = page_check_address(page, mm, address, &ptl,
 				 PageTransCompound(page));
 	if (!pte)
@@ -1524,6 +1553,30 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		}
   	}
 
+	/*
+	 * Call huge_pmd_unshare to potentially unshare a huge pmd.  Pass
+	 * sh_address as it will be modified if unsharing is successful.
+	 */
+	if (PageHuge(page) && huge_pmd_unshare(mm, &sh_address, pte)) {
+		/*
+		 * huge_pmd_unshare unmapped an entire PMD page.  There is
+		 * no way of knowing exactly which PMDs may be cached for
+		 * this mm, so flush them all.  spmd_start/spmd_end cover
+		 * this PUD_SIZE range.
+		 */
+		flush_cache_range(vma, spmd_start, spmd_end);
+		flush_tlb_range(vma, spmd_start, spmd_end);
+
+		/*
+		 * The ref count of the PMD page was dropped which is part
+		 * of the way map counting is done for shared PMDs.  When
+		 * there is no other sharing, huge_pmd_unshare returns false
+		 * and we will unmap the actual page and drop map count
+		 * to zero.
+		 */
+		goto out_unmap;
+	}
+
 	/* Nuke the page table entry. */
 	flush_cache_page(vma, address, page_to_pfn(page));
 	if (should_defer_flush(mm, flags)) {
@@ -1621,6 +1674,9 @@ out_unmap:
 	if (ret != SWAP_FAIL && ret != SWAP_MLOCK && !(flags & TTU_MUNLOCK))
 		mmu_notifier_invalidate_page(mm, address);
 out:
+	if (pmd_sharing_possible)
+		mmu_notifier_invalidate_range_end(vma->vm_mm,
+							spmd_start, spmd_end);
 	return ret;
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 4b5cca167baf..9b17bd4cbc5e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -181,6 +181,38 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages)
 		vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE));
 }
 
+static inline bool shmem_inode_acct_block(struct inode *inode, long pages)
+{
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+
+	if (shmem_acct_block(info->flags, pages))
+		return false;
+
+	if (sbinfo->max_blocks) {
+		if (percpu_counter_compare(&sbinfo->used_blocks,
+					   sbinfo->max_blocks - pages) > 0)
+			goto unacct;
+		percpu_counter_add(&sbinfo->used_blocks, pages);
+	}
+
+	return true;
+
+unacct:
+	shmem_unacct_blocks(info->flags, pages);
+	return false;
+}
+
+static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages)
+{
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+
+	if (sbinfo->max_blocks)
+		percpu_counter_sub(&sbinfo->used_blocks, pages);
+	shmem_unacct_blocks(info->flags, pages);
+}
+
 static const struct super_operations shmem_ops;
 static const struct address_space_operations shmem_aops;
 static const struct file_operations shmem_file_operations;
@@ -237,61 +269,46 @@ static void shmem_recalc_inode(struct inode *inode)
 
 	freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
 	if (freed > 0) {
-		struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
-		if (sbinfo->max_blocks)
-			percpu_counter_add(&sbinfo->used_blocks, -freed);
 		info->alloced -= freed;
 		inode->i_blocks -= freed * BLOCKS_PER_PAGE;
-		shmem_unacct_blocks(info->flags, freed);
+		shmem_inode_unacct_blocks(inode, freed);
 	}
 }
 
 bool shmem_charge(struct inode *inode, long pages)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	unsigned long flags;
 
-	if (shmem_acct_block(info->flags, pages))
+	if (!shmem_inode_acct_block(inode, pages))
 		return false;
+
+	/* nrpages adjustment first, then shmem_recalc_inode() when balanced */
+	inode->i_mapping->nrpages += pages;
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced += pages;
 	inode->i_blocks += pages * BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
 	spin_unlock_irqrestore(&info->lock, flags);
-	inode->i_mapping->nrpages += pages;
 
-	if (!sbinfo->max_blocks)
-		return true;
-	if (percpu_counter_compare(&sbinfo->used_blocks,
-				sbinfo->max_blocks - pages) > 0) {
-		inode->i_mapping->nrpages -= pages;
-		spin_lock_irqsave(&info->lock, flags);
-		info->alloced -= pages;
-		shmem_recalc_inode(inode);
-		spin_unlock_irqrestore(&info->lock, flags);
-		shmem_unacct_blocks(info->flags, pages);
-		return false;
-	}
-	percpu_counter_add(&sbinfo->used_blocks, pages);
 	return true;
 }
 
 void shmem_uncharge(struct inode *inode, long pages)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	unsigned long flags;
 
+	/* nrpages adjustment done by __delete_from_page_cache() or caller */
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced -= pages;
 	inode->i_blocks -= pages * BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
 	spin_unlock_irqrestore(&info->lock, flags);
 
-	if (sbinfo->max_blocks)
-		percpu_counter_sub(&sbinfo->used_blocks, pages);
-	shmem_unacct_blocks(info->flags, pages);
+	shmem_inode_unacct_blocks(inode, pages);
 }
 
 /*
@@ -1424,9 +1441,10 @@ static struct page *shmem_alloc_page(gfp_t gfp,
 }
 
 static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
-		struct shmem_inode_info *info, struct shmem_sb_info *sbinfo,
+		struct inode *inode,
 		pgoff_t index, bool huge)
 {
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct page *page;
 	int nr;
 	int err = -ENOSPC;
@@ -1435,14 +1453,8 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
 		huge = false;
 	nr = huge ? HPAGE_PMD_NR : 1;
 
-	if (shmem_acct_block(info->flags, nr))
+	if (!shmem_inode_acct_block(inode, nr))
 		goto failed;
-	if (sbinfo->max_blocks) {
-		if (percpu_counter_compare(&sbinfo->used_blocks,
-					sbinfo->max_blocks - nr) > 0)
-			goto unacct;
-		percpu_counter_add(&sbinfo->used_blocks, nr);
-	}
 
 	if (huge)
 		page = shmem_alloc_hugepage(gfp, info, index);
@@ -1455,10 +1467,7 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
 	}
 
 	err = -ENOMEM;
-	if (sbinfo->max_blocks)
-		percpu_counter_add(&sbinfo->used_blocks, -nr);
-unacct:
-	shmem_unacct_blocks(info->flags, nr);
+	shmem_inode_unacct_blocks(inode, nr);
 failed:
 	return ERR_PTR(err);
 }
@@ -1485,11 +1494,13 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 {
 	struct page *oldpage, *newpage;
 	struct address_space *swap_mapping;
+	swp_entry_t entry;
 	pgoff_t swap_index;
 	int error;
 
 	oldpage = *pagep;
-	swap_index = page_private(oldpage);
+	entry.val = page_private(oldpage);
+	swap_index = swp_offset(entry);
 	swap_mapping = page_mapping(oldpage);
 
 	/*
@@ -1508,7 +1519,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	__SetPageLocked(newpage);
 	__SetPageSwapBacked(newpage);
 	SetPageUptodate(newpage);
-	set_page_private(newpage, swap_index);
+	set_page_private(newpage, entry.val);
 	SetPageSwapCache(newpage);
 
 	/*
@@ -1718,10 +1729,9 @@ repeat:
 		}
 
 alloc_huge:
-		page = shmem_alloc_and_acct_page(gfp, info, sbinfo,
-				index, true);
+		page = shmem_alloc_and_acct_page(gfp, inode, index, true);
 		if (IS_ERR(page)) {
-alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, info, sbinfo,
+alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, inode,
 					index, false);
 		}
 		if (IS_ERR(page)) {
@@ -1843,10 +1853,7 @@ clear:
 	 * Error recovery.
 	 */
 unacct:
-	if (sbinfo->max_blocks)
-		percpu_counter_sub(&sbinfo->used_blocks,
-				1 << compound_order(page));
-	shmem_unacct_blocks(info->flags, 1 << compound_order(page));
+	shmem_inode_unacct_blocks(inode, 1 << compound_order(page));
 
 	if (PageTransHuge(page)) {
 		unlock_page(page);
@@ -2414,9 +2421,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 	inode_lock(inode);
 	/* We're holding i_mutex so we can access i_size directly */
 
-	if (offset < 0)
-		offset = -EINVAL;
-	else if (offset >= inode->i_size)
+	if (offset < 0 || offset >= inode->i_size)
 		offset = -ENXIO;
 	else {
 		start = offset >> PAGE_SHIFT;
diff --git a/mm/slab.c b/mm/slab.c
index c59844dbd034..263dcda6897b 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3690,6 +3690,8 @@ __do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
 	struct kmem_cache *cachep;
 	void *ret;
 
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE))
+		return NULL;
 	cachep = kmalloc_slab(size, flags);
 	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
 		return cachep;
@@ -3725,6 +3727,8 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	struct kmem_cache *cachep;
 	void *ret;
 
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE))
+		return NULL;
 	cachep = kmalloc_slab(size, flags);
 	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
 		return cachep;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 622f6b6ae844..13f1926f8fcd 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -883,18 +883,18 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
 {
 	int index;
 
-	if (unlikely(size > KMALLOC_MAX_SIZE)) {
-		WARN_ON_ONCE(!(flags & __GFP_NOWARN));
-		return NULL;
-	}
-
 	if (size <= 192) {
 		if (!size)
 			return ZERO_SIZE_PTR;
 
 		index = size_index[size_index_elem(size)];
-	} else
+	} else {
+		if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
+			WARN_ON(1);
+			return NULL;
+		}
 		index = fls(size - 1);
+	}
 
 #ifdef CONFIG_ZONE_DMA
 	if (unlikely((flags & GFP_DMA)))
diff --git a/mm/slub.c b/mm/slub.c
index e0ce5dec84ba..131dee87a67c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1793,7 +1793,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 {
 	struct page *page, *page2;
 	void *object = NULL;
-	int available = 0;
+	unsigned int available = 0;
 	int objects;
 
 	/*
@@ -4870,10 +4870,10 @@ static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf)
 static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf,
 				 size_t length)
 {
-	unsigned long objects;
+	unsigned int objects;
 	int err;
 
-	err = kstrtoul(buf, 10, &objects);
+	err = kstrtouint(buf, 10, &objects);
 	if (err)
 		return err;
 	if (objects && !kmem_cache_has_cpu_partial(s))
diff --git a/mm/truncate.c b/mm/truncate.c
index 9c809e7d73c3..befdc6f575d2 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -443,9 +443,13 @@ void truncate_inode_pages_final(struct address_space *mapping)
 		 */
 		spin_lock_irq(&mapping->tree_lock);
 		spin_unlock_irq(&mapping->tree_lock);
-
-		truncate_inode_pages(mapping, 0);
 	}
+
+	/*
+	 * Cleancache needs notification even if there are no pages or shadow
+	 * entries.
+	 */
+	truncate_inode_pages(mapping, 0);
 }
 EXPORT_SYMBOL(truncate_inode_pages_final);
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 5f658b6a684f..5e6a4d76659d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1078,6 +1078,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
+#else
+	"", /* nr_tlb_remote_flush */
+	"", /* nr_tlb_remote_flush_received */
 #endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",
@@ -1086,7 +1089,6 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_DEBUG_VM_VMACACHE
 	"vmacache_find_calls",
 	"vmacache_find_hits",
-	"vmacache_full_flushes",
 #endif
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };