Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux

Merging 3.18-rc4 in order to pick up the memzero_explicit helper.

16 files changed, 305 insertions, 166 deletions

diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index b3cbe19f71b..fcad8322ef3 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -68,11 +68,13 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
 		 * to be released by the balloon driver.
 		 */
 		if (trylock_page(page)) {
+#ifdef CONFIG_BALLOON_COMPACTION
 			if (!PagePrivate(page)) {
 				/* raced with isolation */
 				unlock_page(page);
 				continue;
 			}
+#endif
 			spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 			balloon_page_delete(page);
 			__count_vm_event(BALLOON_DEFLATE);
diff --git a/mm/cma.c b/mm/cma.c
index 963bc4add9a..fde706e1284 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -124,6 +124,7 @@ static int __init cma_activate_area(struct cma *cma)
 
 err:
 	kfree(cma->bitmap);
+	cma->count = 0;
 	return -EINVAL;
 }
 
@@ -217,9 +218,8 @@ int __init cma_declare_contiguous(phys_addr_t base,
 	phys_addr_t highmem_start = __pa(high_memory);
 	int ret = 0;
 
-	pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n",
-		__func__, (unsigned long)size, (unsigned long)base,
-		(unsigned long)limit, (unsigned long)alignment);
+	pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n",
+		__func__, &size, &base, &limit, &alignment);
 
 	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
 		pr_err("Not enough slots for CMA reserved regions!\n");
@@ -244,52 +244,72 @@ int __init cma_declare_contiguous(phys_addr_t base,
 	size = ALIGN(size, alignment);
 	limit &= ~(alignment - 1);
 
+	if (!base)
+		fixed = false;
+
 	/* size should be aligned with order_per_bit */
 	if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit))
 		return -EINVAL;
 
 	/*
-	 * adjust limit to avoid crossing low/high memory boundary for
-	 * automatically allocated regions
+	 * If allocating at a fixed base the request region must not cross the
+	 * low/high memory boundary.
 	 */
-	if (((limit == 0 || limit > memblock_end) &&
-	     (memblock_end - size < highmem_start &&
-	      memblock_end > highmem_start)) ||
-	    (!fixed && limit > highmem_start && limit - size < highmem_start)) {
-		limit = highmem_start;
-	}
-
-	if (fixed && base < highmem_start && base+size > highmem_start) {
+	if (fixed && base < highmem_start && base + size > highmem_start) {
 		ret = -EINVAL;
-		pr_err("Region at %08lx defined on low/high memory boundary (%08lx)\n",
-			(unsigned long)base, (unsigned long)highmem_start);
+		pr_err("Region at %pa defined on low/high memory boundary (%pa)\n",
+			&base, &highmem_start);
 		goto err;
 	}
 
+	/*
+	 * If the limit is unspecified or above the memblock end, its effective
+	 * value will be the memblock end. Set it explicitly to simplify further
+	 * checks.
+	 */
+	if (limit == 0 || limit > memblock_end)
+		limit = memblock_end;
+
 	/* Reserve memory */
-	if (base && fixed) {
+	if (fixed) {
 		if (memblock_is_region_reserved(base, size) ||
 		    memblock_reserve(base, size) < 0) {
 			ret = -EBUSY;
 			goto err;
 		}
 	} else {
-		phys_addr_t addr = memblock_alloc_range(size, alignment, base,
-							limit);
+		phys_addr_t addr = 0;
+
+		/*
+		 * All pages in the reserved area must come from the same zone.
+		 * If the requested region crosses the low/high memory boundary,
+		 * try allocating from high memory first and fall back to low
+		 * memory in case of failure.
+		 */
+		if (base < highmem_start && limit > highmem_start) {
+			addr = memblock_alloc_range(size, alignment,
+						    highmem_start, limit);
+			limit = highmem_start;
+		}
+
 		if (!addr) {
-			ret = -ENOMEM;
-			goto err;
-		} else {
-			base = addr;
+			addr = memblock_alloc_range(size, alignment, base,
+						    limit);
+			if (!addr) {
+				ret = -ENOMEM;
+				goto err;
+			}
 		}
+
+		base = addr;
 	}
 
 	ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma);
 	if (ret)
 		goto err;
 
-	pr_info("Reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
-		(unsigned long)base);
+	pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M,
+		&base);
 	return 0;
 
 err:
diff --git a/mm/compaction.c b/mm/compaction.c
index edba18aed17..ec74cf0123e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -784,6 +784,9 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 			cc->nr_migratepages = 0;
 			break;
 		}
+
+		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+			break;
 	}
 	acct_isolated(cc->zone, cc);
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 74c78aa8bc2..de984159cf0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -200,7 +200,7 @@ retry:
 	preempt_disable();
 	if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
 		preempt_enable();
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		goto retry;
 	}
 
@@ -232,7 +232,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
 	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
 		struct page *zero_page = xchg(&huge_zero_page, NULL);
 		BUG_ON(zero_page == NULL);
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		return HPAGE_PMD_NR;
 	}
 
@@ -803,7 +803,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return VM_FAULT_FALLBACK;
 	if (unlikely(anon_vma_prepare(vma)))
 		return VM_FAULT_OOM;
-	if (unlikely(khugepaged_enter(vma)))
+	if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
 		return VM_FAULT_OOM;
 	if (!(flags & FAULT_FLAG_WRITE) &&
 			transparent_hugepage_use_zero_page()) {
@@ -1970,7 +1970,7 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		 * register it here without waiting a page fault that
 		 * may not happen any time soon.
 		 */
-		if (unlikely(khugepaged_enter_vma_merge(vma)))
+		if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags)))
 			return -ENOMEM;
 		break;
 	case MADV_NOHUGEPAGE:
@@ -2071,7 +2071,8 @@ int __khugepaged_enter(struct mm_struct *mm)
 	return 0;
 }
 
-int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+			       unsigned long vm_flags)
 {
 	unsigned long hstart, hend;
 	if (!vma->anon_vma)
@@ -2083,11 +2084,11 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
 	if (vma->vm_ops)
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
-	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
+	VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
-		return khugepaged_enter(vma);
+		return khugepaged_enter(vma, vm_flags);
 	return 0;
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 23976fd885f..d6ac0e33e15 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1536,12 +1536,8 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg)
  *         start move here.
  */
 
-/* for quick checking without looking up memcg */
-atomic_t memcg_moving __read_mostly;
-
 static void mem_cgroup_start_move(struct mem_cgroup *memcg)
 {
-	atomic_inc(&memcg_moving);
 	atomic_inc(&memcg->moving_account);
 	synchronize_rcu();
 }
@@ -1552,10 +1548,8 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg)
 	 * Now, mem_cgroup_clear_mc() may call this function with NULL.
 	 * We check NULL in callee rather than caller.
 	 */
-	if (memcg) {
-		atomic_dec(&memcg_moving);
+	if (memcg)
 		atomic_dec(&memcg->moving_account);
-	}
 }
 
 /*
@@ -2204,41 +2198,52 @@ cleanup:
 	return true;
 }
 
-/*
- * Used to update mapped file or writeback or other statistics.
+/**
+ * mem_cgroup_begin_page_stat - begin a page state statistics transaction
+ * @page: page that is going to change accounted state
+ * @locked: &memcg->move_lock slowpath was taken
+ * @flags: IRQ-state flags for &memcg->move_lock
  *
- * Notes: Race condition
+ * This function must mark the beginning of an accounted page state
+ * change to prevent double accounting when the page is concurrently
+ * being moved to another memcg:
  *
- * Charging occurs during page instantiation, while the page is
- * unmapped and locked in page migration, or while the page table is
- * locked in THP migration.  No race is possible.
+ *   memcg = mem_cgroup_begin_page_stat(page, &locked, &flags);
+ *   if (TestClearPageState(page))
+ *     mem_cgroup_update_page_stat(memcg, state, -1);
+ *   mem_cgroup_end_page_stat(memcg, locked, flags);
  *
- * Uncharge happens to pages with zero references, no race possible.
+ * The RCU lock is held throughout the transaction.  The fast path can
+ * get away without acquiring the memcg->move_lock (@locked is false)
+ * because page moving starts with an RCU grace period.
  *
- * Charge moving between groups is protected by checking mm->moving
- * account and taking the move_lock in the slowpath.
+ * The RCU lock also protects the memcg from being freed when the page
+ * state that is going to change is the only thing preventing the page
+ * from being uncharged.  E.g. end-writeback clearing PageWriteback(),
+ * which allows migration to go ahead and uncharge the page before the
+ * account transaction might be complete.
  */
-
-void __mem_cgroup_begin_update_page_stat(struct page *page,
-				bool *locked, unsigned long *flags)
+struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
+					      bool *locked,
+					      unsigned long *flags)
 {
 	struct mem_cgroup *memcg;
 	struct page_cgroup *pc;
 
+	rcu_read_lock();
+
+	if (mem_cgroup_disabled())
+		return NULL;
+
 	pc = lookup_page_cgroup(page);
 again:
 	memcg = pc->mem_cgroup;
 	if (unlikely(!memcg || !PageCgroupUsed(pc)))
-		return;
-	/*
-	 * If this memory cgroup is not under account moving, we don't
-	 * need to take move_lock_mem_cgroup(). Because we already hold
-	 * rcu_read_lock(), any calls to move_account will be delayed until
-	 * rcu_read_unlock().
-	 */
-	VM_BUG_ON(!rcu_read_lock_held());
+		return NULL;
+
+	*locked = false;
 	if (atomic_read(&memcg->moving_account) <= 0)
-		return;
+		return memcg;
 
 	move_lock_mem_cgroup(memcg, flags);
 	if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) {
@@ -2246,36 +2251,40 @@ again:
 		goto again;
 	}
 	*locked = true;
+
+	return memcg;
 }
 
-void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags)
+/**
+ * mem_cgroup_end_page_stat - finish a page state statistics transaction
+ * @memcg: the memcg that was accounted against
+ * @locked: value received from mem_cgroup_begin_page_stat()
+ * @flags: value received from mem_cgroup_begin_page_stat()
+ */
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked,
+			      unsigned long flags)
 {
-	struct page_cgroup *pc = lookup_page_cgroup(page);
+	if (memcg && locked)
+		move_unlock_mem_cgroup(memcg, &flags);
 
-	/*
-	 * It's guaranteed that pc->mem_cgroup never changes while
-	 * lock is held because a routine modifies pc->mem_cgroup
-	 * should take move_lock_mem_cgroup().
-	 */
-	move_unlock_mem_cgroup(pc->mem_cgroup, flags);
+	rcu_read_unlock();
 }
 
-void mem_cgroup_update_page_stat(struct page *page,
+/**
+ * mem_cgroup_update_page_stat - update page state statistics
+ * @memcg: memcg to account against
+ * @idx: page state item to account
+ * @val: number of pages (positive or negative)
+ *
+ * See mem_cgroup_begin_page_stat() for locking requirements.
+ */
+void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
 				 enum mem_cgroup_stat_index idx, int val)
 {
-	struct mem_cgroup *memcg;
-	struct page_cgroup *pc = lookup_page_cgroup(page);
-	unsigned long uninitialized_var(flags);
-
-	if (mem_cgroup_disabled())
-		return;
-
 	VM_BUG_ON(!rcu_read_lock_held());
-	memcg = pc->mem_cgroup;
-	if (unlikely(!memcg || !PageCgroupUsed(pc)))
-		return;
 
-	this_cpu_add(memcg->stat->count[idx], val);
+	if (memcg)
+		this_cpu_add(memcg->stat->count[idx], val);
 }
 
 /*
diff --git a/mm/memory.c b/mm/memory.c
index 1cc6bfbd872..3e503831e04 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1147,6 +1147,7 @@ again:
 				print_bad_pte(vma, addr, ptent, page);
 			if (unlikely(!__tlb_remove_page(tlb, page))) {
 				force_flush = 1;
+				addr += PAGE_SIZE;
 				break;
 			}
 			continue;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 29d8693d0c6..252e1dbbed8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1912,7 +1912,6 @@ void try_offline_node(int nid)
 	unsigned long start_pfn = pgdat->node_start_pfn;
 	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
 	unsigned long pfn;
-	struct page *pgdat_page = virt_to_page(pgdat);
 	int i;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
@@ -1941,10 +1940,6 @@ void try_offline_node(int nid)
 	node_set_offline(nid);
 	unregister_one_node(nid);
 
-	if (!PageSlab(pgdat_page) && !PageCompound(pgdat_page))
-		/* node data is allocated from boot memory */
-		return;
-
 	/* free waittable in each zone */
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		struct zone *zone = pgdat->node_zones + i;
diff --git a/mm/mmap.c b/mm/mmap.c
index 7f855206e7f..87e82b38453 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1080,7 +1080,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 				end, prev->vm_pgoff, NULL);
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(prev);
+		khugepaged_enter_vma_merge(prev, vm_flags);
 		return prev;
 	}
 
@@ -1099,7 +1099,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 				next->vm_pgoff - pglen, NULL);
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(area);
+		khugepaged_enter_vma_merge(area, vm_flags);
 		return area;
 	}
 
@@ -2208,7 +2208,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 		}
 	}
 	vma_unlock_anon_vma(vma);
-	khugepaged_enter_vma_merge(vma);
+	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	validate_mm(vma->vm_mm);
 	return error;
 }
@@ -2277,7 +2277,7 @@ int expand_downwards(struct vm_area_struct *vma,
 		}
 	}
 	vma_unlock_anon_vma(vma);
-	khugepaged_enter_vma_merge(vma);
+	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	validate_mm(vma->vm_mm);
 	return error;
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index bbf405a3a18..5340f6b9131 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -404,6 +404,23 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 		dump_tasks(memcg, nodemask);
 }
 
+/*
+ * Number of OOM killer invocations (including memcg OOM killer).
+ * Primarily used by PM freezer to check for potential races with
+ * OOM killed frozen task.
+ */
+static atomic_t oom_kills = ATOMIC_INIT(0);
+
+int oom_kills_count(void)
+{
+	return atomic_read(&oom_kills);
+}
+
+void note_oom_kill(void)
+{
+	atomic_inc(&oom_kills);
+}
+
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /*
  * Must be called while holding a reference to p, which will be released upon
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ff24c9d8311..19ceae87522 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2116,23 +2116,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 EXPORT_SYMBOL(account_page_dirtied);
 
 /*
- * Helper function for set_page_writeback family.
- *
- * The caller must hold mem_cgroup_begin/end_update_page_stat() lock
- * while calling this function.
- * See test_set_page_writeback for example.
- *
- * NOTE: Unlike account_page_dirtied this does not rely on being atomic
- * wrt interrupts.
- */
-void account_page_writeback(struct page *page)
-{
-	mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
-	inc_zone_page_state(page, NR_WRITEBACK);
-}
-EXPORT_SYMBOL(account_page_writeback);
-
-/*
  * For address_spaces which do not use buffers.  Just tag the page as dirty in
  * its radix tree.
  *
@@ -2344,11 +2327,12 @@ EXPORT_SYMBOL(clear_page_dirty_for_io);
 int test_clear_page_writeback(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
-	int ret;
-	bool locked;
 	unsigned long memcg_flags;
+	struct mem_cgroup *memcg;
+	bool locked;
+	int ret;
 
-	mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags);
+	memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
 	if (mapping) {
 		struct backing_dev_info *bdi = mapping->backing_dev_info;
 		unsigned long flags;
@@ -2369,22 +2353,23 @@ int test_clear_page_writeback(struct page *page)
 		ret = TestClearPageWriteback(page);
 	}
 	if (ret) {
-		mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
+		mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
 		dec_zone_page_state(page, NR_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITTEN);
 	}
-	mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags);
+	mem_cgroup_end_page_stat(memcg, locked, memcg_flags);
 	return ret;
 }
 
 int __test_set_page_writeback(struct page *page, bool keep_write)
 {
 	struct address_space *mapping = page_mapping(page);
-	int ret;
-	bool locked;
 	unsigned long memcg_flags;
+	struct mem_cgroup *memcg;
+	bool locked;
+	int ret;
 
-	mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags);
+	memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
 	if (mapping) {
 		struct backing_dev_info *bdi = mapping->backing_dev_info;
 		unsigned long flags;
@@ -2410,9 +2395,11 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 	} else {
 		ret = TestSetPageWriteback(page);
 	}
-	if (!ret)
-		account_page_writeback(page);
-	mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags);
+	if (!ret) {
+		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
+		inc_zone_page_state(page, NR_WRITEBACK);
+	}
+	mem_cgroup_end_page_stat(memcg, locked, memcg_flags);
 	return ret;
 
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 736d8e1b638..9cd36b82244 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2252,6 +2252,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	}
 
 	/*
+	 * PM-freezer should be notified that there might be an OOM killer on
+	 * its way to kill and wake somebody up. This is too early and we might
+	 * end up not killing anything but false positives are acceptable.
+	 * See freeze_processes.
+	 */
+	note_oom_kill();
+
+	/*
 	 * Go through the zonelist yet one more time, keep very high watermark
 	 * here, this is only to catch a parallel oom killing, we must fail if
 	 * we're still under heavy pressure.
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 3708264d283..5331c2bd85a 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -171,6 +171,7 @@ static void free_page_cgroup(void *addr)
 			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
+		kmemleak_free(addr);
 		free_pages_exact(addr, table_size);
 	}
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 116a5053415..19886fb2f13 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1042,15 +1042,46 @@ void page_add_new_anon_rmap(struct page *page,
  */
 void page_add_file_rmap(struct page *page)
 {
-	bool locked;
+	struct mem_cgroup *memcg;
 	unsigned long flags;
+	bool locked;
 
-	mem_cgroup_begin_update_page_stat(page, &locked, &flags);
+	memcg = mem_cgroup_begin_page_stat(page, &locked, &flags);
 	if (atomic_inc_and_test(&page->_mapcount)) {
 		__inc_zone_page_state(page, NR_FILE_MAPPED);
-		mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
+		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED);
 	}
-	mem_cgroup_end_update_page_stat(page, &locked, &flags);
+	mem_cgroup_end_page_stat(memcg, locked, flags);
+}
+
+static void page_remove_file_rmap(struct page *page)
+{
+	struct mem_cgroup *memcg;
+	unsigned long flags;
+	bool locked;
+
+	memcg = mem_cgroup_begin_page_stat(page, &locked, &flags);
+
+	/* page still mapped by someone else? */
+	if (!atomic_add_negative(-1, &page->_mapcount))
+		goto out;
+
+	/* Hugepages are not counted in NR_FILE_MAPPED for now. */
+	if (unlikely(PageHuge(page)))
+		goto out;
+
+	/*
+	 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
+	 * these counters are not modified in interrupt context, and
+	 * pte lock(a spinlock) is held, which implies preemption disabled.
+	 */
+	__dec_zone_page_state(page, NR_FILE_MAPPED);
+	mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED);
+
+	if (unlikely(PageMlocked(page)))
+		clear_page_mlock(page);
+out:
+	mem_cgroup_end_page_stat(memcg, locked, flags);
 }
 
 /**
@@ -1061,46 +1092,33 @@ void page_add_file_rmap(struct page *page)
  */
 void page_remove_rmap(struct page *page)
 {
-	bool anon = PageAnon(page);
-	bool locked;
-	unsigned long flags;
-
-	/*
-	 * The anon case has no mem_cgroup page_stat to update; but may
-	 * uncharge_page() below, where the lock ordering can deadlock if
-	 * we hold the lock against page_stat move: so avoid it on anon.
-	 */
-	if (!anon)
-		mem_cgroup_begin_update_page_stat(page, &locked, &flags);
+	if (!PageAnon(page)) {
+		page_remove_file_rmap(page);
+		return;
+	}
 
 	/* page still mapped by someone else? */
 	if (!atomic_add_negative(-1, &page->_mapcount))
-		goto out;
+		return;
+
+	/* Hugepages are not counted in NR_ANON_PAGES for now. */
+	if (unlikely(PageHuge(page)))
+		return;
 
 	/*
-	 * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED
-	 * and not charged by memcg for now.
-	 *
 	 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
 	 * these counters are not modified in interrupt context, and
-	 * these counters are not modified in interrupt context, and
 	 * pte lock(a spinlock) is held, which implies preemption disabled.
 	 */
-	if (unlikely(PageHuge(page)))
-		goto out;
-	if (anon) {
-		if (PageTransHuge(page))
-			__dec_zone_page_state(page,
-					      NR_ANON_TRANSPARENT_HUGEPAGES);
-		__mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
-				-hpage_nr_pages(page));
-	} else {
-		__dec_zone_page_state(page, NR_FILE_MAPPED);
-		mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
-		mem_cgroup_end_update_page_stat(page, &locked, &flags);
-	}
+	if (PageTransHuge(page))
+		__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
+
+	__mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
+			      -hpage_nr_pages(page));
+
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
+
 	/*
 	 * It would be tidy to reset the PageAnon mapping here,
 	 * but that might overwrite a racing page_add_anon_rmap
@@ -1110,10 +1128,6 @@ void page_remove_rmap(struct page *page)
 	 * Leaving it set also helps swapoff to reinstate ptes
 	 * faster for those pages still in swapcache.
 	 */
-	return;
-out:
-	if (!anon)
-		mem_cgroup_end_update_page_stat(page, &locked, &flags);
 }
 
 /*
diff --git a/mm/shmem.c b/mm/shmem.c
index cd6fc7590e5..185836ba53e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2345,6 +2345,32 @@ static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, stru
 	return 0;
 }
 
+static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry)
+{
+	struct dentry *whiteout;
+	int error;
+
+	whiteout = d_alloc(old_dentry->d_parent, &old_dentry->d_name);
+	if (!whiteout)
+		return -ENOMEM;
+
+	error = shmem_mknod(old_dir, whiteout,
+			    S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
+	dput(whiteout);
+	if (error)
+		return error;
+
+	/*
+	 * Cheat and hash the whiteout while the old dentry is still in
+	 * place, instead of playing games with FS_RENAME_DOES_D_MOVE.
+	 *
+	 * d_lookup() will consistently find one of them at this point,
+	 * not sure which one, but that isn't even important.
+	 */
+	d_rehash(whiteout);
+	return 0;
+}
+
 /*
  * The VFS layer already does all the dentry stuff for rename,
  * we just have to decrement the usage count for the target if
@@ -2356,7 +2382,7 @@ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struc
 	struct inode *inode = old_dentry->d_inode;
 	int they_are_dirs = S_ISDIR(inode->i_mode);
 
-	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
 	if (flags & RENAME_EXCHANGE)
@@ -2365,6 +2391,14 @@ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struc
 	if (!simple_empty(new_dentry))
 		return -ENOTEMPTY;
 
+	if (flags & RENAME_WHITEOUT) {
+		int error;
+
+		error = shmem_whiteout(old_dir, old_dentry);
+		if (error)
+			return error;
+	}
+
 	if (new_dentry->d_inode) {
 		(void) shmem_unlink(new_dir, new_dentry);
 		if (they_are_dirs) {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3a6e0cfdf03..406944207b6 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -93,16 +93,6 @@ static int kmem_cache_sanity_check(const char *name, size_t size)
 			       s->object_size);
 			continue;
 		}
-
-#if !defined(CONFIG_SLUB)
-		if (!strcmp(s->name, name)) {
-			pr_err("%s (%s): Cache name already exists.\n",
-			       __func__, name);
-			dump_stack();
-			s = NULL;
-			return -EINVAL;
-		}
-#endif
 	}
 
 	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
diff --git a/mm/truncate.c b/mm/truncate.c
index 96d167372d8..f1e4d605236 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -20,6 +20,7 @@
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 static void clear_exceptional_entry(struct address_space *mapping,
@@ -714,17 +715,73 @@ EXPORT_SYMBOL(truncate_pagecache);
  * necessary) to @newsize. It will be typically be called from the filesystem's
  * setattr function when ATTR_SIZE is passed in.
  *
- * Must be called with inode_mutex held and before all filesystem specific
- * block truncation has been performed.
+ * Must be called with a lock serializing truncates and writes (generally
+ * i_mutex but e.g. xfs uses a different lock) and before all filesystem
+ * specific block truncation has been performed.
  */
 void truncate_setsize(struct inode *inode, loff_t newsize)
 {
+	loff_t oldsize = inode->i_size;
+
 	i_size_write(inode, newsize);
+	if (newsize > oldsize)
+		pagecache_isize_extended(inode, oldsize, newsize);
 	truncate_pagecache(inode, newsize);
 }
 EXPORT_SYMBOL(truncate_setsize);
 
 /**
+ * pagecache_isize_extended - update pagecache after extension of i_size
+ * @inode:	inode for which i_size was extended
+ * @from:	original inode size
+ * @to:		new inode size
+ *
+ * Handle extension of inode size either caused by extending truncate or by
+ * write starting after current i_size. We mark the page straddling current
+ * i_size RO so that page_mkwrite() is called on the nearest write access to
+ * the page.  This way filesystem can be sure that page_mkwrite() is called on
+ * the page before user writes to the page via mmap after the i_size has been
+ * changed.
+ *
+ * The function must be called after i_size is updated so that page fault
+ * coming after we unlock the page will already see the new i_size.
+ * The function must be called while we still hold i_mutex - this not only
+ * makes sure i_size is stable but also that userspace cannot observe new
+ * i_size value before we are prepared to store mmap writes at new inode size.
+ */
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
+{
+	int bsize = 1 << inode->i_blkbits;
+	loff_t rounded_from;
+	struct page *page;
+	pgoff_t index;
+
+	WARN_ON(to > inode->i_size);
+
+	if (from >= to || bsize == PAGE_CACHE_SIZE)
+		return;
+	/* Page straddling @from will not have any hole block created? */
+	rounded_from = round_up(from, bsize);
+	if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
+		return;
+
+	index = from >> PAGE_CACHE_SHIFT;
+	page = find_lock_page(inode->i_mapping, index);
+	/* Page not cached? Nothing to do */
+	if (!page)
+		return;
+	/*
+	 * See clear_page_dirty_for_io() for details why set_page_dirty()
+	 * is needed.
+	 */
+	if (page_mkclean(page))
+		set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+}
+EXPORT_SYMBOL(pagecache_isize_extended);
+
+/**
  * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
  * @inode: inode
  * @lstart: offset of beginning of hole