Merge branch 'linux-3.10.33' into dev-kernel-3.10

Bug 1456092

Change-Id: I3021247ec68a3c2dddd9e98cde13d70a45191d53
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>

16 files changed, 255 insertions, 162 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 05ccb4cc0bdb..9a3e351da29b 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -134,6 +134,10 @@ static void update_pageblock_skip(struct compact_control *cc,
 			bool migrate_scanner)
 {
 	struct zone *zone = cc->zone;
+
+	if (cc->ignore_skip_hint)
+		return;
+
 	if (!page)
 		return;
 
diff --git a/mm/fremap.c b/mm/fremap.c
index 87da3590c61e..1fb6bfe39d8c 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -203,9 +203,10 @@ get_write_lock:
 		if (mapping_cap_account_dirty(mapping)) {
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
+			/* mmap_region may free vma; grab the info now */
+			vm_flags = vma->vm_flags;
 
-			addr = mmap_region(file, start, size,
-					vma->vm_flags, pgoff);
+			addr = mmap_region(file, start, size, vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -213,7 +214,7 @@ get_write_lock:
 				BUG_ON(addr != start);
 				err = 0;
 			}
-			goto out;
+			goto out_freed;
 		}
 		mutex_lock(&mapping->i_mmap_mutex);
 		flush_dcache_mmap_lock(mapping);
@@ -248,6 +249,7 @@ get_write_lock:
 out:
 	if (vma)
 		vm_flags = vma->vm_flags;
+out_freed:
 	if (likely(!has_write_lock))
 		up_read(&mm->mmap_sem);
 	else
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c403a74e4bee..eb00e81601a5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1166,7 +1166,7 @@ alloc:
 
 	if (unlikely(!new_page)) {
 		count_vm_event(THP_FAULT_FALLBACK);
-		if (is_huge_zero_pmd(orig_pmd)) {
+		if (!page) {
 			ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
 					address, pmd, orig_pmd, haddr);
 		} else {
@@ -1190,7 +1190,7 @@ alloc:
 		goto out;
 	}
 
-	if (is_huge_zero_pmd(orig_pmd))
+	if (!page)
 		clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
 	else
 		copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
@@ -1215,7 +1215,7 @@ alloc:
 		page_add_new_anon_rmap(new_page, vma, haddr);
 		set_pmd_at(mm, haddr, pmd, entry);
 		update_mmu_cache_pmd(vma, address, pmd);
-		if (is_huge_zero_pmd(orig_pmd)) {
+		if (!page) {
 			add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
 			put_huge_zero_page();
 		} else {
@@ -1344,6 +1344,20 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_unlock;
 	}
 
+	/* Bail if we fail to protect against THP splits for any reason */
+	if (unlikely(!anon_vma)) {
+		put_page(page);
+		page_nid = -1;
+		goto clear_pmdnuma;
+	}
+
+	/*
+	 * The page_table_lock above provides a memory barrier
+	 * with change_protection_range.
+	 */
+	if (mm_tlb_flush_pending(mm))
+		flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+
 	/*
 	 * Migrate the THP to the requested node, returns with page unlocked
 	 * and pmd_numa cleared.
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7c5eb85ec645..aa3b9a63394b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -21,6 +21,7 @@
 #include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/page-isolation.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -517,9 +518,15 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
 
-	if (list_empty(&h->hugepage_freelists[nid]))
+	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
+		if (!is_migrate_isolate_page(page))
+			break;
+	/*
+	 * if 'non-isolated free hugepage' not found on the list,
+	 * the allocation fails.
+	 */
+	if (&h->hugepage_freelists[nid] == &page->lru)
 		return NULL;
-	page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
 	list_move(&page->lru, &h->hugepage_activelist);
 	set_page_refcounted(page);
 	h->free_huge_pages--;
@@ -690,6 +697,23 @@ int PageHuge(struct page *page)
 }
 EXPORT_SYMBOL_GPL(PageHuge);
 
+/*
+ * PageHeadHuge() only returns true for hugetlbfs head page, but not for
+ * normal or transparent huge pages.
+ */
+int PageHeadHuge(struct page *page_head)
+{
+	compound_page_dtor *dtor;
+
+	if (!PageHead(page_head))
+		return 0;
+
+	dtor = get_compound_page_dtor(page_head);
+
+	return dtor == free_huge_page;
+}
+EXPORT_SYMBOL_GPL(PageHeadHuge);
+
 pgoff_t __basepage_index(struct page *page)
 {
 	struct page *page_head = compound_head(page);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d8902c85b956..96f5e2d8390a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -380,7 +380,7 @@ struct mem_cgroup {
 static size_t memcg_size(void)
 {
 	return sizeof(struct mem_cgroup) +
-		nr_node_ids * sizeof(struct mem_cgroup_per_node);
+		nr_node_ids * sizeof(struct mem_cgroup_per_node *);
 }
 
 /* internal only representation about the status of kmem accounting. */
@@ -1221,7 +1221,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 			if (dead_count == iter->last_dead_count) {
 				smp_rmb();
 				last_visited = iter->last_visited;
-				if (last_visited &&
+				if (last_visited && last_visited != root &&
 				    !css_tryget(&last_visited->css))
 					last_visited = NULL;
 			}
@@ -1230,7 +1230,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		memcg = __mem_cgroup_iter_next(root, last_visited);
 
 		if (reclaim) {
-			if (last_visited)
+			if (last_visited && last_visited != root)
 				css_put(&last_visited->css);
 
 			iter->last_visited = memcg;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ceb0c7f1932f..e386beefc994 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -854,14 +854,14 @@ static int page_action(struct page_state *ps, struct page *p,
  * the pages and send SIGBUS to the processes if the data was dirty.
  */
 static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
-				  int trapno, int flags)
+				  int trapno, int flags, struct page **hpagep)
 {
 	enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
 	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	int ret;
 	int kill = 1, forcekill;
-	struct page *hpage = compound_head(p);
+	struct page *hpage = *hpagep;
 	struct page *ppage;
 
 	if (PageReserved(p) || PageSlab(p))
@@ -936,6 +936,21 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 				BUG_ON(!PageHWPoison(p));
 				return SWAP_FAIL;
 			}
+			/*
+			 * We pinned the head page for hwpoison handling,
+			 * now we split the thp and we are interested in
+			 * the hwpoisoned raw page, so move the refcount
+			 * to it. Similarly, page lock is shifted.
+			 */
+			if (hpage != p) {
+				if (!(flags & MF_COUNT_INCREASED)) {
+					put_page(hpage);
+					get_page(p);
+				}
+				lock_page(p);
+				unlock_page(hpage);
+				*hpagep = p;
+			}
 			/* THP is split, so ppage should be the real poisoned page. */
 			ppage = p;
 		}
@@ -952,17 +967,11 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	if (kill)
 		collect_procs(ppage, &tokill);
 
-	if (hpage != ppage)
-		lock_page(ppage);
-
 	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
 		printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
 				pfn, page_mapcount(ppage));
 
-	if (hpage != ppage)
-		unlock_page(ppage);
-
 	/*
 	 * Now that the dirty bit has been propagated to the
 	 * struct page and all unmaps done we can decide if
@@ -1179,8 +1188,12 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	/*
 	 * Now take care of user space mappings.
 	 * Abort on fail: __delete_from_page_cache() assumes unmapped page.
+	 *
+	 * When the raw error page is thp tail page, hpage points to the raw
+	 * page after thp split.
 	 */
-	if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) {
+	if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)
+	    != SWAP_SUCCESS) {
 		printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
 		res = -EBUSY;
 		goto out;
@@ -1410,7 +1423,8 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 
 	/*
 	 * Isolate the page, so that it doesn't get reallocated if it
-	 * was free.
+	 * was free. This flag should be kept set until the source page
+	 * is freed and PG_hwpoison on it is set.
 	 */
 	set_migratetype_isolate(p, true);
 	/*
@@ -1433,7 +1447,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 		/* Not a free page */
 		ret = 1;
 	}
-	unset_migratetype_isolate(p, MIGRATE_MOVABLE);
 	unlock_memory_hotplug();
 	return ret;
 }
@@ -1489,12 +1502,17 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 			pfn, ret, page->flags);
 	} else {
-		set_page_hwpoison_huge_page(hpage);
-		dequeue_hwpoisoned_huge_page(hpage);
-		atomic_long_add(1 << compound_trans_order(hpage),
-				&num_poisoned_pages);
+		/* overcommit hugetlb page will be freed to buddy */
+		if (PageHuge(page)) {
+			set_page_hwpoison_huge_page(hpage);
+			dequeue_hwpoisoned_huge_page(hpage);
+			atomic_long_add(1 << compound_order(hpage),
+					&num_poisoned_pages);
+		} else {
+			SetPageHWPoison(page);
+			atomic_long_inc(&num_poisoned_pages);
+		}
 	}
-	/* keep elevated page count for bad page */
 	return ret;
 }
 
@@ -1559,7 +1577,7 @@ int soft_offline_page(struct page *page, int flags)
 			atomic_long_inc(&num_poisoned_pages);
 		}
 	}
-	/* keep elevated page count for bad page */
+	unset_migratetype_isolate(page, MIGRATE_MOVABLE);
 	return ret;
 }
 
@@ -1625,7 +1643,22 @@ static int __soft_offline_page(struct page *page, int flags)
 			if (ret > 0)
 				ret = -EIO;
 		} else {
+			/*
+			 * After page migration succeeds, the source page can
+			 * be trapped in pagevec and actual freeing is delayed.
+			 * Freeing code works differently based on PG_hwpoison,
+			 * so there's a race. We need to make sure that the
+			 * source page should be freed back to buddy before
+			 * setting PG_hwpoison.
+			 */
+			if (!is_free_buddy_page(page))
+				lru_add_drain_all();
+			if (!is_free_buddy_page(page))
+				drain_all_pages();
 			SetPageHWPoison(page);
+			if (!is_free_buddy_page(page))
+				pr_info("soft offline: %#lx: page leaked\n",
+					pfn);
 			atomic_long_inc(&num_poisoned_pages);
 		}
 	} else {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 28fb17845f70..763be19461b4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2801,7 +2801,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	 */
 	VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
 
-	if (!pol || pol == &default_policy)
+	if (!pol || pol == &default_policy || (pol->flags & MPOL_F_MORON))
 		mode = MPOL_DEFAULT;
 	else
 		mode = pol->mode;
diff --git a/mm/migrate.c b/mm/migrate.c
index bf436c15f055..a88c12f2235d 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1715,7 +1715,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		putback_lru_page(page);
 		mod_zone_page_state(page_zone(page),
 			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
-		goto out_fail;
+
+		goto out_unlock;
 	}
 
 	/*
@@ -1765,6 +1766,7 @@ out_dropref:
 	set_pmd_at(mm, haddr, pmd, entry);
 	update_mmu_cache_pmd(vma, address, &entry);
 
+out_unlock:
 	unlock_page(page);
 	put_page(page);
 	return 0;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 78dba5ccd5b8..6b2403a2f814 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -207,6 +207,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
 	flush_cache_range(vma, addr, end);
+	set_tlb_flush_pending(mm);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
@@ -218,6 +219,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	/* Only flush the TLB if we actually modified any entries: */
 	if (pages)
 		flush_tlb_range(vma, start, end);
+	clear_tlb_flush_pending(mm);
 
 	return pages;
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 0c9f836fe97d..f22859784ded 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -170,7 +170,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * implementation used by LSMs.
 	 */
 	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
-		adj -= 30;
+		points -= (points * 3) / 100;
 
 	/* Normalize to oom_score_adj units */
 	adj *= totalpages / 1000;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index aca4364275b5..73cbc5dc150b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -188,6 +188,26 @@ static unsigned long writeout_period_time = 0;
  * global dirtyable memory first.
  */
 
+/**
+ * zone_dirtyable_memory - number of dirtyable pages in a zone
+ * @zone: the zone
+ *
+ * Returns the zone's number of pages potentially available for dirty
+ * page cache.  This is the base value for the per-zone dirty limits.
+ */
+static unsigned long zone_dirtyable_memory(struct zone *zone)
+{
+	unsigned long nr_pages;
+
+	nr_pages = zone_page_state(zone, NR_FREE_PAGES);
+	nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
+
+	nr_pages += zone_page_state(zone, NR_INACTIVE_FILE);
+	nr_pages += zone_page_state(zone, NR_ACTIVE_FILE);
+
+	return nr_pages;
+}
+
 static unsigned long highmem_dirtyable_memory(unsigned long total)
 {
 #ifdef CONFIG_HIGHMEM
@@ -195,11 +215,9 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 	unsigned long x = 0;
 
 	for_each_node_state(node, N_HIGH_MEMORY) {
-		struct zone *z =
-			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
+		struct zone *z = &NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
 
-		x += zone_page_state(z, NR_FREE_PAGES) +
-		     zone_reclaimable_pages(z) - z->dirty_balance_reserve;
+		x += zone_dirtyable_memory(z);
 	}
 	/*
 	 * Unreclaimable memory (kernel memory or anonymous memory
@@ -235,9 +253,12 @@ static unsigned long global_dirtyable_memory(void)
 {
 	unsigned long x;
 
-	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
+	x = global_page_state(NR_FREE_PAGES);
 	x -= min(x, dirty_balance_reserve);
 
+	x += global_page_state(NR_INACTIVE_FILE);
+	x += global_page_state(NR_ACTIVE_FILE);
+
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);
 
@@ -289,32 +310,6 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
 }
 
 /**
- * zone_dirtyable_memory - number of dirtyable pages in a zone
- * @zone: the zone
- *
- * Returns the zone's number of pages potentially available for dirty
- * page cache.  This is the base value for the per-zone dirty limits.
- */
-static unsigned long zone_dirtyable_memory(struct zone *zone)
-{
-	/*
-	 * The effective global number of dirtyable pages may exclude
-	 * highmem as a big-picture measure to keep the ratio between
-	 * dirty memory and lowmem reasonable.
-	 *
-	 * But this function is purely about the individual zone and a
-	 * highmem zone can hold its share of dirty pages, so we don't
-	 * care about vm_highmem_is_dirtyable here.
-	 */
-	unsigned long nr_pages = zone_page_state(zone, NR_FREE_PAGES) +
-		zone_reclaimable_pages(zone);
-
-	/* don't allow this to underflow */
-	nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
-	return nr_pages;
-}
-
-/**
  * zone_dirty_limit - maximum number of dirty pages allowed in a zone
  * @zone: the zone
  *
@@ -2031,11 +2026,12 @@ int __set_page_dirty_nobuffers(struct page *page)
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 		struct address_space *mapping2;
+		unsigned long flags;
 
 		if (!mapping)
 			return 1;
 
-		spin_lock_irq(&mapping->tree_lock);
+		spin_lock_irqsave(&mapping->tree_lock, flags);
 		mapping2 = page_mapping(page);
 		if (mapping2) { /* Race with truncate? */
 			BUG_ON(mapping2 != mapping);
@@ -2044,7 +2040,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 			radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 		}
-		spin_unlock_irq(&mapping->tree_lock);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */
 			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 0c8323fe6c8f..4b62a16fc3c1 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -86,9 +86,10 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
 		       pte_t *ptep)
 {
+	struct mm_struct *mm = (vma)->vm_mm;
 	pte_t pte;
-	pte = ptep_get_and_clear((vma)->vm_mm, address, ptep);
-	if (pte_accessible(pte))
+	pte = ptep_get_and_clear(mm, address, ptep);
+	if (pte_accessible(mm, pte))
 		flush_tlb_page(vma, address);
 	return pte;
 }
@@ -166,6 +167,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
+	pmd_t entry = *pmdp;
+	if (pmd_numa(entry))
+		entry = pmd_mknonnuma(entry);
 	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 6280da86b5d6..3f6077461aea 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -600,7 +600,11 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 	spinlock_t *ptl;
 
 	if (unlikely(PageHuge(page))) {
+		/* when pud is not present, pte will be NULL */
 		pte = huge_pte_offset(mm, address);
+		if (!pte)
+			return NULL;
+
 		ptl = &mm->page_table_lock;
 		goto check;
 	}
diff --git a/mm/slub.c b/mm/slub.c
index c34bd44e8be9..deaed7b47213 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4285,7 +4285,13 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 
 			page = ACCESS_ONCE(c->partial);
 			if (page) {
-				x = page->pobjects;
+				node = page_to_nid(page);
+				if (flags & SO_TOTAL)
+					WARN_ON_ONCE(1);
+				else if (flags & SO_OBJECTS)
+					WARN_ON_ONCE(1);
+				else
+					x = page->pages;
 				total += x;
 				nodes[node] += x;
 			}
diff --git a/mm/swap.c b/mm/swap.c
index 9f2225f2b5b0..ea58dbde788e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -79,19 +79,6 @@ static void __put_compound_page(struct page *page)
 
 static void put_compound_page(struct page *page)
 {
-	/*
-	 * hugetlbfs pages cannot be split from under us.  If this is a
-	 * hugetlbfs page, check refcount on head page and release the page if
-	 * the refcount becomes zero.
-	 */
-	if (PageHuge(page)) {
-		page = compound_head(page);
-		if (put_page_testzero(page))
-			__put_compound_page(page);
-
-		return;
-	}
-
 	if (unlikely(PageTail(page))) {
 		/* __split_huge_page_refcount can run under us */
 		struct page *page_head = compound_trans_head(page);
@@ -108,14 +95,31 @@ static void put_compound_page(struct page *page)
 			 * still hot on arches that do not support
 			 * this_cpu_cmpxchg_double().
 			 */
-			if (PageSlab(page_head)) {
-				if (PageTail(page)) {
+			if (PageSlab(page_head) || PageHeadHuge(page_head)) {
+				if (likely(PageTail(page))) {
+					/*
+					 * __split_huge_page_refcount
+					 * cannot race here.
+					 */
+					VM_BUG_ON(!PageHead(page_head));
+					atomic_dec(&page->_mapcount);
 					if (put_page_testzero(page_head))
 						VM_BUG_ON(1);
-
-					atomic_dec(&page->_mapcount);
-					goto skip_lock_tail;
+					if (put_page_testzero(page_head))
+						__put_compound_page(page_head);
+					return;
 				} else
+					/*
+					 * __split_huge_page_refcount
+					 * run before us, "page" was a
+					 * THP tail. The split
+					 * page_head has been freed
+					 * and reallocated as slab or
+					 * hugetlbfs page of smaller
+					 * order (only possible if
+					 * reallocated as slab on
+					 * x86).
+					 */
 					goto skip_lock;
 			}
 			/*
@@ -129,8 +133,27 @@ static void put_compound_page(struct page *page)
 				/* __split_huge_page_refcount run before us */
 				compound_unlock_irqrestore(page_head, flags);
 skip_lock:
-				if (put_page_testzero(page_head))
-					__put_single_page(page_head);
+				if (put_page_testzero(page_head)) {
+					/*
+					 * The head page may have been
+					 * freed and reallocated as a
+					 * compound page of smaller
+					 * order and then freed again.
+					 * All we know is that it
+					 * cannot have become: a THP
+					 * page, a compound page of
+					 * higher order, a tail page.
+					 * That is because we still
+					 * hold the refcount of the
+					 * split THP tail and
+					 * page_head was the THP head
+					 * before the split.
+					 */
+					if (PageHead(page_head))
+						__put_compound_page(page_head);
+					else
+						__put_single_page(page_head);
+				}
 out_put_single:
 				if (put_page_testzero(page))
 					__put_single_page(page);
@@ -152,7 +175,6 @@ out_put_single:
 			VM_BUG_ON(atomic_read(&page->_count) != 0);
 			compound_unlock_irqrestore(page_head, flags);
 
-skip_lock_tail:
 			if (put_page_testzero(page_head)) {
 				if (PageHead(page_head))
 					__put_compound_page(page_head);
@@ -195,51 +217,52 @@ bool __get_page_tail(struct page *page)
 	 * proper PT lock that already serializes against
 	 * split_huge_page().
 	 */
+	unsigned long flags;
 	bool got = false;
-	struct page *page_head;
-
-	/*
-	 * If this is a hugetlbfs page it cannot be split under us.  Simply
-	 * increment refcount for the head page.
-	 */
-	if (PageHuge(page)) {
-		page_head = compound_head(page);
-		atomic_inc(&page_head->_count);
-		got = true;
-	} else {
-		unsigned long flags;
+	struct page *page_head = compound_trans_head(page);
 
-		page_head = compound_trans_head(page);
-		if (likely(page != page_head &&
-					get_page_unless_zero(page_head))) {
-
-			/* Ref to put_compound_page() comment. */
-			if (PageSlab(page_head)) {
-				if (likely(PageTail(page))) {
-					__get_page_tail_foll(page, false);
-					return true;
-				} else {
-					put_page(page_head);
-					return false;
-				}
-			}
-
-			/*
-			 * page_head wasn't a dangling pointer but it
-			 * may not be a head page anymore by the time
-			 * we obtain the lock. That is ok as long as it
-			 * can't be freed from under us.
-			 */
-			flags = compound_lock_irqsave(page_head);
-			/* here __split_huge_page_refcount won't run anymore */
+	if (likely(page != page_head && get_page_unless_zero(page_head))) {
+		/* Ref to put_compound_page() comment. */
+		if (PageSlab(page_head) || PageHeadHuge(page_head)) {
 			if (likely(PageTail(page))) {
+				/*
+				 * This is a hugetlbfs page or a slab
+				 * page. __split_huge_page_refcount
+				 * cannot race here.
+				 */
+				VM_BUG_ON(!PageHead(page_head));
 				__get_page_tail_foll(page, false);
-				got = true;
-			}
-			compound_unlock_irqrestore(page_head, flags);
-			if (unlikely(!got))
+				return true;
+			} else {
+				/*
+				 * __split_huge_page_refcount run
+				 * before us, "page" was a THP
+				 * tail. The split page_head has been
+				 * freed and reallocated as slab or
+				 * hugetlbfs page of smaller order
+				 * (only possible if reallocated as
+				 * slab on x86).
+				 */
 				put_page(page_head);
+				return false;
+			}
+		}
+
+		/*
+		 * page_head wasn't a dangling pointer but it
+		 * may not be a head page anymore by the time
+		 * we obtain the lock. That is ok as long as it
+		 * can't be freed from under us.
+		 */
+		flags = compound_lock_irqsave(page_head);
+		/* here __split_huge_page_refcount won't run anymore */
+		if (likely(PageTail(page))) {
+			__get_page_tail_foll(page, false);
+			got = true;
 		}
+		compound_unlock_irqrestore(page_head, flags);
+		if (unlikely(!got))
+			put_page(page_head);
 	}
 	return got;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c052bffff636..a42363f73af4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2161,6 +2161,20 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	return aborted_reclaim;
 }
 
+static unsigned long zone_reclaimable_pages(struct zone *zone)
+{
+	int nr;
+
+	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
+	     zone_page_state(zone, NR_INACTIVE_FILE);
+
+	if (get_nr_swap_pages() > 0)
+		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
+		      zone_page_state(zone, NR_INACTIVE_ANON);
+
+	return nr;
+}
+
 static bool zone_reclaimable(struct zone *zone)
 {
 	return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
@@ -3119,41 +3133,6 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
-/*
- * The reclaimable count would be mostly accurate.
- * The less reclaimable pages may be
- * - mlocked pages, which will be moved to unevictable list when encountered
- * - mapped pages, which may require several travels to be reclaimed
- * - dirty pages, which is not "instantly" reclaimable
- */
-unsigned long global_reclaimable_pages(void)
-{
-	int nr;
-
-	nr = global_page_state(NR_ACTIVE_FILE) +
-	     global_page_state(NR_INACTIVE_FILE);
-
-	if (get_nr_swap_pages() > 0)
-		nr += global_page_state(NR_ACTIVE_ANON) +
-		      global_page_state(NR_INACTIVE_ANON);
-
-	return nr;
-}
-
-unsigned long zone_reclaimable_pages(struct zone *zone)
-{
-	int nr;
-
-	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
-	     zone_page_state(zone, NR_INACTIVE_FILE);
-
-	if (get_nr_swap_pages() > 0)
-		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
-		      zone_page_state(zone, NR_INACTIVE_ANON);
-
-	return nr;
-}
-
 #ifdef CONFIG_HIBERNATION
 /*
  * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of