Merge branch 'rcu/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu into core/rcu

17 files changed, 199 insertions, 153 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index f4e516e9c37c..f0fb9124e410 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -189,7 +189,7 @@ config COMPACTION
 config MIGRATION
 	bool "Page migration"
 	def_bool y
-	depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE
+	depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION
 	help
 	  Allows the migration of the physical location of pages of processes
 	  while the virtual addresses are not changed. This is useful in
diff --git a/mm/bounce.c b/mm/bounce.c
index 13b6dad1eed2..1481de68184b 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -116,8 +116,8 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 		 */
 		vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;
 
-		flush_dcache_page(tovec->bv_page);
 		bounce_copy_vec(tovec, vfrom);
+		flush_dcache_page(tovec->bv_page);
 	}
 }
 
diff --git a/mm/compaction.c b/mm/compaction.c
index 94cce51b0b35..4d709ee59013 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -214,15 +214,16 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc)
 /* Similar to reclaim, but different enough that they don't share logic */
 static bool too_many_isolated(struct zone *zone)
 {
-
-	unsigned long inactive, isolated;
+	unsigned long active, inactive, isolated;
 
 	inactive = zone_page_state(zone, NR_INACTIVE_FILE) +
 					zone_page_state(zone, NR_INACTIVE_ANON);
+	active = zone_page_state(zone, NR_ACTIVE_FILE) +
+					zone_page_state(zone, NR_ACTIVE_ANON);
 	isolated = zone_page_state(zone, NR_ISOLATED_FILE) +
 					zone_page_state(zone, NR_ISOLATED_ANON);
 
-	return isolated > inactive;
+	return isolated > (inactive + active) / 2;
 }
 
 /*
diff --git a/mm/ksm.c b/mm/ksm.c
index e2ae00458320..b1873cf03ed9 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1504,8 +1504,6 @@ struct page *ksm_does_need_to_copy(struct page *page,
 {
 	struct page *new_page;
 
-	unlock_page(page);	/* any racers will COW it, not modify it */
-
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 	if (new_page) {
 		copy_user_highpage(new_page, page, address, vma);
@@ -1521,7 +1519,6 @@ struct page *ksm_does_need_to_copy(struct page *page,
 			add_page_to_unevictable_list(new_page);
 	}
 
-	page_cache_release(page);
 	return new_page;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 2ed2267439df..71b161b73bb5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2623,7 +2623,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned int flags, pte_t orig_pte)
 {
 	spinlock_t *ptl;
-	struct page *page;
+	struct page *page, *swapcache = NULL;
 	swp_entry_t entry;
 	pte_t pte;
 	struct mem_cgroup *ptr = NULL;
@@ -2679,10 +2679,23 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	lock_page(page);
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 
-	page = ksm_might_need_to_copy(page, vma, address);
-	if (!page) {
-		ret = VM_FAULT_OOM;
-		goto out;
+	/*
+	 * Make sure try_to_free_swap didn't release the swapcache
+	 * from under us. The page pin isn't enough to prevent that.
+	 */
+	if (unlikely(!PageSwapCache(page)))
+		goto out_page;
+
+	if (ksm_might_need_to_copy(page, vma, address)) {
+		swapcache = page;
+		page = ksm_does_need_to_copy(page, vma, address);
+
+		if (unlikely(!page)) {
+			ret = VM_FAULT_OOM;
+			page = swapcache;
+			swapcache = NULL;
+			goto out_page;
+		}
 	}
 
 	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
@@ -2735,6 +2748,18 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
 		try_to_free_swap(page);
 	unlock_page(page);
+	if (swapcache) {
+		/*
+		 * Hold the lock to avoid the swap entry to be reused
+		 * until we take the PT lock for the pte_same() check
+		 * (to avoid false positives from pte_same). For
+		 * further safety release the lock after the swap_free
+		 * so that the swap count won't change under a
+		 * parallel locked swapcache.
+		 */
+		unlock_page(swapcache);
+		page_cache_release(swapcache);
+	}
 
 	if (flags & FAULT_FLAG_WRITE) {
 		ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte);
@@ -2756,15 +2781,17 @@ out_page:
 	unlock_page(page);
 out_release:
 	page_cache_release(page);
+	if (swapcache) {
+		unlock_page(swapcache);
+		page_cache_release(swapcache);
+	}
 	return ret;
 }
 
 /*
- * This is like a special single-page "expand_downwards()",
- * except we must first make sure that 'address-PAGE_SIZE'
+ * This is like a special single-page "expand_{down|up}wards()",
+ * except we must first make sure that 'address{-|+}PAGE_SIZE'
  * doesn't hit another vma.
- *
- * The "find_vma()" will do the right thing even if we wrap
  */
 static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
 {
@@ -2783,6 +2810,15 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 
 		expand_stack(vma, address - PAGE_SIZE);
 	}
+	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
+		struct vm_area_struct *next = vma->vm_next;
+
+		/* As VM_GROWSDOWN but s/below/above/ */
+		if (next && next->vm_start == address + PAGE_SIZE)
+			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
+
+		expand_upwards(vma, address + PAGE_SIZE);
+	}
 	return 0;
 }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a4cfcdc00455..dd186c1a5d53 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -584,19 +584,19 @@ static inline int pageblock_free(struct page *page)
 /* Return the start of the next active pageblock after a given page */
 static struct page *next_active_pageblock(struct page *page)
 {
-	int pageblocks_stride;
-
 	/* Ensure the starting page is pageblock-aligned */
 	BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));
 
-	/* Move forward by at least 1 * pageblock_nr_pages */
-	pageblocks_stride = 1;
-
 	/* If the entire pageblock is free, move to the end of free page */
-	if (pageblock_free(page))
-		pageblocks_stride += page_order(page) - pageblock_order;
+	if (pageblock_free(page)) {
+		int order;
+		/* be careful. we don't have locks, page_order can be changed.*/
+		order = page_order(page);
+		if ((order < MAX_ORDER) && (order >= pageblock_order))
+			return page + (1 << order);
+	}
 
-	return page + (pageblocks_stride * pageblock_nr_pages);
+	return page + pageblock_nr_pages;
 }
 
 /* Checks if this range of memory is likely to be hot-removable. */
diff --git a/mm/mlock.c b/mm/mlock.c
index cbae7c5b9568..b70919ce4f72 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -135,12 +135,6 @@ void munlock_vma_page(struct page *page)
 	}
 }
 
-/* Is the vma a continuation of the stack vma above it? */
-static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr)
-{
-	return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
-}
-
 static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr)
 {
 	return (vma->vm_flags & VM_GROWSDOWN) &&
diff --git a/mm/mmap.c b/mm/mmap.c
index 331e51af38c9..6128dc8e5ede 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1716,9 +1716,6 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
  * PA-RISC uses this for its stack; IA64 for its Register Backing Store.
  * vma is the last one with address > vma->vm_end.  Have to extend vma.
  */
-#ifndef CONFIG_IA64
-static
-#endif
 int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 {
 	int error;
diff --git a/mm/mmzone.c b/mm/mmzone.c
index f5b7d1760213..e35bfb82c855 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -87,3 +87,24 @@ int memmap_valid_within(unsigned long pfn,
 	return 1;
 }
 #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
+
+#ifdef CONFIG_SMP
+/* Called when a more accurate view of NR_FREE_PAGES is needed */
+unsigned long zone_nr_free_pages(struct zone *zone)
+{
+	unsigned long nr_free_pages = zone_page_state(zone, NR_FREE_PAGES);
+
+	/*
+	 * While kswapd is awake, it is considered the zone is under some
+	 * memory pressure. Under pressure, there is a risk that
+	 * per-cpu-counter-drift will allow the min watermark to be breached
+	 * potentially causing a live-lock. While kswapd is awake and
+	 * free pages are low, get a better estimate for free pages
+	 */
+	if (nr_free_pages < zone->percpu_drift_mark &&
+			!waitqueue_active(&zone->zone_pgdat->kswapd_wait))
+		return zone_page_state_snapshot(zone, NR_FREE_PAGES);
+
+	return nr_free_pages;
+}
+#endif /* CONFIG_SMP */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index c09ef5219cbe..e3bccac1f025 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -985,22 +985,16 @@ continue_unlock:
 				}
 			}
 
-			if (wbc->nr_to_write > 0) {
-				if (--wbc->nr_to_write == 0 &&
-				    wbc->sync_mode == WB_SYNC_NONE) {
-					/*
-					 * We stop writing back only if we are
-					 * not doing integrity sync. In case of
-					 * integrity sync we have to keep going
-					 * because someone may be concurrently
-					 * dirtying pages, and we might have
-					 * synced a lot of newly appeared dirty
-					 * pages, but have not synced all of the
-					 * old dirty pages.
-					 */
-					done = 1;
-					break;
-				}
+			/*
+			 * We stop writing back only if we are not doing
+			 * integrity sync. In case of integrity sync we have to
+			 * keep going until we have written all the pages
+			 * we tagged for writeback prior to entering this loop.
+			 */
+			if (--wbc->nr_to_write <= 0 &&
+			    wbc->sync_mode == WB_SYNC_NONE) {
+				done = 1;
+				break;
 			}
 		}
 		pagevec_release(&pvec);
@@ -1132,6 +1126,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		task_io_account_write(PAGE_CACHE_SIZE);
 	}
 }
+EXPORT_SYMBOL(account_page_dirtied);
 
 /*
  * For address_spaces which do not use buffers.  Just tag the page as dirty in
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a9649f4b261e..a8cfa9cc6e86 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -588,13 +588,13 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 {
 	int migratetype = 0;
 	int batch_free = 0;
+	int to_free = count;
 
 	spin_lock(&zone->lock);
 	zone->all_unreclaimable = 0;
 	zone->pages_scanned = 0;
 
-	__mod_zone_page_state(zone, NR_FREE_PAGES, count);
-	while (count) {
+	while (to_free) {
 		struct page *page;
 		struct list_head *list;
 
@@ -619,8 +619,9 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
 			__free_one_page(page, zone, 0, page_private(page));
 			trace_mm_page_pcpu_drain(page, 0, page_private(page));
-		} while (--count && --batch_free && !list_empty(list));
+		} while (--to_free && --batch_free && !list_empty(list));
 	}
+	__mod_zone_page_state(zone, NR_FREE_PAGES, count);
 	spin_unlock(&zone->lock);
 }
 
@@ -631,8 +632,8 @@ static void free_one_page(struct zone *zone, struct page *page, int order,
 	zone->all_unreclaimable = 0;
 	zone->pages_scanned = 0;
 
-	__mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
 	__free_one_page(page, zone, order, migratetype);
+	__mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
 	spin_unlock(&zone->lock);
 }
 
@@ -1461,7 +1462,7 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 {
 	/* free_pages my go negative - that's OK */
 	long min = mark;
-	long free_pages = zone_page_state(z, NR_FREE_PAGES) - (1 << order) + 1;
+	long free_pages = zone_nr_free_pages(z) - (1 << order) + 1;
 	int o;
 
 	if (alloc_flags & ALLOC_HIGH)
@@ -1846,6 +1847,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 	struct page *page = NULL;
 	struct reclaim_state reclaim_state;
 	struct task_struct *p = current;
+	bool drained = false;
 
 	cond_resched();
 
@@ -1864,14 +1866,25 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 
 	cond_resched();
 
-	if (order != 0)
-		drain_all_pages();
+	if (unlikely(!(*did_some_progress)))
+		return NULL;
 
-	if (likely(*did_some_progress))
-		page = get_page_from_freelist(gfp_mask, nodemask, order,
+retry:
+	page = get_page_from_freelist(gfp_mask, nodemask, order,
 					zonelist, high_zoneidx,
 					alloc_flags, preferred_zone,
 					migratetype);
+
+	/*
+	 * If an allocation failed after direct reclaim, it could be because
+	 * pages are pinned on the per-cpu lists. Drain them and try again
+	 */
+	if (!page && !drained) {
+		drain_all_pages();
+		drained = true;
+		goto retry;
+	}
+
 	return page;
 }
 
@@ -2423,7 +2436,7 @@ void show_free_areas(void)
 			" all_unreclaimable? %s"
 			"\n",
 			zone->name,
-			K(zone_page_state(zone, NR_FREE_PAGES)),
+			K(zone_nr_free_pages(zone)),
 			K(min_wmark_pages(zone)),
 			K(low_wmark_pages(zone)),
 			K(high_wmark_pages(zone)),
diff --git a/mm/percpu.c b/mm/percpu.c
index e61dc2cc5873..58c572b18b07 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -393,7 +393,9 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
 		goto out_unlock;
 
 	old_size = chunk->map_alloc * sizeof(chunk->map[0]);
-	memcpy(new, chunk->map, old_size);
+	old = chunk->map;
+
+	memcpy(new, old, old_size);
 
 	chunk->map_alloc = new_alloc;
 	chunk->map = new;
@@ -1162,7 +1164,7 @@ static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
 		}
 
 		/*
-		 * Don't accept if wastage is over 25%.  The
+		 * Don't accept if wastage is over 1/3.  The
 		 * greater-than comparison ensures upa==1 always
 		 * passes the following check.
 		 */
diff --git a/mm/percpu_up.c b/mm/percpu_up.c
index c4351c7f57d2..db884fae5721 100644
--- a/mm/percpu_up.c
+++ b/mm/percpu_up.c
@@ -14,13 +14,13 @@ void __percpu *__alloc_percpu(size_t size, size_t align)
 	 * percpu sections on SMP for which this path isn't used.
 	 */
 	WARN_ON_ONCE(align > SMP_CACHE_BYTES);
-	return kzalloc(size, GFP_KERNEL);
+	return (void __percpu __force *)kzalloc(size, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(__alloc_percpu);
 
 void free_percpu(void __percpu *p)
 {
-	kfree(p);
+	kfree(this_cpu_ptr(p));
 }
 EXPORT_SYMBOL_GPL(free_percpu);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 87b9e8ad4509..f6f0d2dda2ea 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -316,7 +316,7 @@ void __init anon_vma_init(void)
  */
 struct anon_vma *page_lock_anon_vma(struct page *page)
 {
-	struct anon_vma *anon_vma;
+	struct anon_vma *anon_vma, *root_anon_vma;
 	unsigned long anon_mapping;
 
 	rcu_read_lock();
@@ -327,8 +327,21 @@ struct anon_vma *page_lock_anon_vma(struct page *page)
 		goto out;
 
 	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
-	anon_vma_lock(anon_vma);
-	return anon_vma;
+	root_anon_vma = ACCESS_ONCE(anon_vma->root);
+	spin_lock(&root_anon_vma->lock);
+
+	/*
+	 * If this page is still mapped, then its anon_vma cannot have been
+	 * freed.  But if it has been unmapped, we have no security against
+	 * the anon_vma structure being freed and reused (for another anon_vma:
+	 * SLAB_DESTROY_BY_RCU guarantees that - so the spin_lock above cannot
+	 * corrupt): with anon_vma_prepare() or anon_vma_fork() redirecting
+	 * anon_vma->root before page_unlock_anon_vma() is called to unlock.
+	 */
+	if (page_mapped(page))
+		return anon_vma;
+
+	spin_unlock(&root_anon_vma->lock);
 out:
 	rcu_read_unlock();
 	return NULL;
diff --git a/mm/slab.c b/mm/slab.c
index 88435fcc8387..fcae9815d3b3 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2330,8 +2330,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	}
 #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
 	if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
-	    && cachep->obj_size > cache_line_size() && size < PAGE_SIZE) {
-		cachep->obj_offset += PAGE_SIZE - size;
+	    && cachep->obj_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) {
+		cachep->obj_offset += PAGE_SIZE - ALIGN(size, align);
 		size = PAGE_SIZE;
 	}
 #endif
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1f3f9c59a73a..7c703ff2f36f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -47,8 +47,6 @@ long nr_swap_pages;
 long total_swap_pages;
 static int least_priority;
 
-static bool swap_for_hibernation;
-
 static const char Bad_file[] = "Bad swap file entry ";
 static const char Unused_file[] = "Unused swap file entry ";
 static const char Bad_offset[] = "Bad swap offset entry ";
@@ -141,8 +139,7 @@ static int discard_swap(struct swap_info_struct *si)
 	nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9);
 	if (nr_blocks) {
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL,
-				BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+				nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT);
 		if (err)
 			return err;
 		cond_resched();
@@ -153,8 +150,7 @@ static int discard_swap(struct swap_info_struct *si)
 		nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
 
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL,
-				BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+				nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT);
 		if (err)
 			break;
 
@@ -193,8 +189,7 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 			start_block <<= PAGE_SHIFT - 9;
 			nr_blocks <<= PAGE_SHIFT - 9;
 			if (blkdev_issue_discard(si->bdev, start_block,
-				    nr_blocks, GFP_NOIO, BLKDEV_IFL_WAIT |
-							BLKDEV_IFL_BARRIER))
+				    nr_blocks, GFP_NOIO, BLKDEV_IFL_WAIT))
 				break;
 		}
 
@@ -320,10 +315,8 @@ checks:
 	if (offset > si->highest_bit)
 		scan_base = offset = si->lowest_bit;
 
-	/* reuse swap entry of cache-only swap if not hibernation. */
-	if (vm_swap_full()
-		&& usage == SWAP_HAS_CACHE
-		&& si->swap_map[offset] == SWAP_HAS_CACHE) {
+	/* reuse swap entry of cache-only swap if not busy. */
+	if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
 		int swap_was_freed;
 		spin_unlock(&swap_lock);
 		swap_was_freed = __try_to_reclaim_swap(si, offset);
@@ -453,8 +446,6 @@ swp_entry_t get_swap_page(void)
 	spin_lock(&swap_lock);
 	if (nr_swap_pages <= 0)
 		goto noswap;
-	if (swap_for_hibernation)
-		goto noswap;
 	nr_swap_pages--;
 
 	for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
@@ -487,6 +478,28 @@ noswap:
 	return (swp_entry_t) {0};
 }
 
+/* The only caller of this function is now susupend routine */
+swp_entry_t get_swap_page_of_type(int type)
+{
+	struct swap_info_struct *si;
+	pgoff_t offset;
+
+	spin_lock(&swap_lock);
+	si = swap_info[type];
+	if (si && (si->flags & SWP_WRITEOK)) {
+		nr_swap_pages--;
+		/* This is called for allocating swap entry, not cache */
+		offset = scan_swap_map(si, 1);
+		if (offset) {
+			spin_unlock(&swap_lock);
+			return swp_entry(type, offset);
+		}
+		nr_swap_pages++;
+	}
+	spin_unlock(&swap_lock);
+	return (swp_entry_t) {0};
+}
+
 static struct swap_info_struct *swap_info_get(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
@@ -670,6 +683,24 @@ int try_to_free_swap(struct page *page)
 	if (page_swapcount(page))
 		return 0;
 
+	/*
+	 * Once hibernation has begun to create its image of memory,
+	 * there's a danger that one of the calls to try_to_free_swap()
+	 * - most probably a call from __try_to_reclaim_swap() while
+	 * hibernation is allocating its own swap pages for the image,
+	 * but conceivably even a call from memory reclaim - will free
+	 * the swap from a page which has already been recorded in the
+	 * image as a clean swapcache page, and then reuse its swap for
+	 * another page of the image.  On waking from hibernation, the
+	 * original page might be freed under memory pressure, then
+	 * later read back in from swap, now with the wrong data.
+	 *
+	 * Hibernation clears bits from gfp_allowed_mask to prevent
+	 * memory reclaim from writing to disk, so check that here.
+	 */
+	if (!(gfp_allowed_mask & __GFP_IO))
+		return 0;
+
 	delete_from_swap_cache(page);
 	SetPageDirty(page);
 	return 1;
@@ -746,74 +777,6 @@ int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep)
 #endif
 
 #ifdef CONFIG_HIBERNATION
-
-static pgoff_t hibernation_offset[MAX_SWAPFILES];
-/*
- * Once hibernation starts to use swap, we freeze swap_map[]. Otherwise,
- * saved swap_map[] image to the disk will be an incomplete because it's
- * changing without synchronization with hibernation snap shot.
- * At resume, we just make swap_for_hibernation=false. We can forget
- * used maps easily.
- */
-void hibernation_freeze_swap(void)
-{
-	int i;
-
-	spin_lock(&swap_lock);
-
-	printk(KERN_INFO "PM: Freeze Swap\n");
-	swap_for_hibernation = true;
-	for (i = 0; i < MAX_SWAPFILES; i++)
-		hibernation_offset[i] = 1;
-	spin_unlock(&swap_lock);
-}
-
-void hibernation_thaw_swap(void)
-{
-	spin_lock(&swap_lock);
-	if (swap_for_hibernation) {
-		printk(KERN_INFO "PM: Thaw Swap\n");
-		swap_for_hibernation = false;
-	}
-	spin_unlock(&swap_lock);
-}
-
-/*
- * Because updateing swap_map[] can make not-saved-status-change,
- * we use our own easy allocator.
- * Please see kernel/power/swap.c, Used swaps are recorded into
- * RB-tree.
- */
-swp_entry_t get_swap_for_hibernation(int type)
-{
-	pgoff_t off;
-	swp_entry_t val = {0};
-	struct swap_info_struct *si;
-
-	spin_lock(&swap_lock);
-
-	si = swap_info[type];
-	if (!si || !(si->flags & SWP_WRITEOK))
-		goto done;
-
-	for (off = hibernation_offset[type]; off < si->max; ++off) {
-		if (!si->swap_map[off])
-			break;
-	}
-	if (off < si->max) {
-		val = swp_entry(type, off);
-		hibernation_offset[type] = off + 1;
-	}
-done:
-	spin_unlock(&swap_lock);
-	return val;
-}
-
-void swap_free_for_hibernation(swp_entry_t ent)
-{
-	/* Nothing to do */
-}
-
 /*
  * Find the swap type that corresponds to given device (if any).
  *
@@ -2084,7 +2047,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 			p->flags |= SWP_SOLIDSTATE;
 			p->cluster_next = 1 + (random32() % p->highest_bit);
 		}
-		if (discard_swap(p) == 0)
+		if (discard_swap(p) == 0 && (swap_flags & SWAP_FLAG_DISCARD))
 			p->flags |= SWP_DISCARDABLE;
 	}
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f389168f9a83..355a9e669aaa 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -138,11 +138,24 @@ static void refresh_zone_stat_thresholds(void)
 	int threshold;
 
 	for_each_populated_zone(zone) {
+		unsigned long max_drift, tolerate_drift;
+
 		threshold = calculate_threshold(zone);
 
 		for_each_online_cpu(cpu)
 			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
 							= threshold;
+
+		/*
+		 * Only set percpu_drift_mark if there is a danger that
+		 * NR_FREE_PAGES reports the low watermark is ok when in fact
+		 * the min watermark could be breached by an allocation
+		 */
+		tolerate_drift = low_wmark_pages(zone) - min_wmark_pages(zone);
+		max_drift = num_online_cpus() * threshold;
+		if (max_drift > tolerate_drift)
+			zone->percpu_drift_mark = high_wmark_pages(zone) +
+					max_drift;
 	}
 }
 
@@ -813,7 +826,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n        scanned  %lu"
 		   "\n        spanned  %lu"
 		   "\n        present  %lu",
-		   zone_page_state(zone, NR_FREE_PAGES),
+		   zone_nr_free_pages(zone),
 		   min_wmark_pages(zone),
 		   low_wmark_pages(zone),
 		   high_wmark_pages(zone),
@@ -998,6 +1011,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
+		refresh_zone_stat_thresholds();
 		start_cpu_timer(cpu);
 		node_set_state(cpu_to_node(cpu), N_CPU);
 		break;