Merge commit 'v2.6.35.14' into del-5.8/main

Conflicts:
	arch/arm/plat-mxc/include/mach/gpio.h
	arch/x86/kernel/cpu/mtrr/main.c
	drivers/mmc/core/core.c
	drivers/net/smsc911x.c
	fs/proc/task_mmu.c
	include/linux/pm_runtime.h
	mm/memory.c
	mm/mlock.c

Signed-off-by: Alex Gonzalez <alex.gonzalez@digi.com>

26 files changed, 482 insertions, 160 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 123bcef13e51..3f2b8d037c98 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -29,6 +29,7 @@ EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
 struct backing_dev_info noop_backing_dev_info = {
 	.name		= "noop",
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
@@ -254,6 +255,7 @@ static int __init default_bdi_init(void)
 	err = bdi_init(&default_backing_dev_info);
 	if (!err)
 		bdi_register(&default_backing_dev_info, NULL, "default");
+	err = bdi_init(&noop_backing_dev_info);
 
 	return err;
 }
@@ -644,6 +646,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		bdi_set_min_ratio(bdi, 0);
 		bdi_prune_sb(bdi);
 
 		if (!bdi_cap_flush_forker(bdi))
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/filemap.c b/mm/filemap.c
index 20e5642e9f9f..183d2d439b28 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -631,7 +631,9 @@ repeat:
 	pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
 	if (pagep) {
 		page = radix_tree_deref_slot(pagep);
-		if (unlikely(!page || page == RADIX_TREE_RETRY))
+		if (unlikely(!page))
+			goto out;
+		if (radix_tree_deref_retry(page))
 			goto repeat;
 
 		if (!page_cache_get_speculative(page))
@@ -647,6 +649,7 @@ repeat:
 			goto repeat;
 		}
 	}
+out:
 	rcu_read_unlock();
 
 	return page;
@@ -764,12 +767,11 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
-		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
-		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page)) {
+			if (ret)
+				start = pages[ret-1]->index;
 			goto restart;
+		}
 
 		if (!page_cache_get_speculative(page))
 			goto repeat;
@@ -817,11 +819,7 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
-		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
-		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page))
 			goto restart;
 
 		if (page->mapping == NULL || page->index != index)
@@ -874,11 +872,7 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
-		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
-		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page))
 			goto restart;
 
 		if (!page_cache_get_speculative(page))
@@ -1016,6 +1010,9 @@ find_page:
 				goto page_not_up_to_date;
 			if (!trylock_page(page))
 				goto page_not_up_to_date;
+			/* Did it get truncated before we got the lock? */
+			if (!page->mapping)
+				goto page_not_up_to_date_locked;
 			if (!mapping->a_ops->is_partially_uptodate(page,
 								desc, offset))
 				goto page_not_up_to_date_locked;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 54d42b009dbe..ffede4d34c69 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1030,10 +1030,10 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	 */
 	chg = vma_needs_reservation(h, vma, addr);
 	if (chg < 0)
-		return ERR_PTR(chg);
+		return ERR_PTR(-VM_FAULT_OOM);
 	if (chg)
 		if (hugetlb_get_quota(inode->i_mapping, chg))
-			return ERR_PTR(-ENOSPC);
+			return ERR_PTR(-VM_FAULT_SIGBUS);
 
 	spin_lock(&hugetlb_lock);
 	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
@@ -1109,6 +1109,14 @@ static void __init gather_bootmem_prealloc(void)
 		WARN_ON(page_count(page) != 1);
 		prep_compound_huge_page(page, h->order);
 		prep_new_huge_page(h, page, page_to_nid(page));
+		/*
+		 * If we had gigantic hugepages allocated at boot time, we need
+		 * to restore the 'stolen' pages to totalram_pages in order to
+		 * fix confusing memory reports from free(1) and another
+		 * side-effects, like CommitLimit going negative.
+		 */
+		if (h->order > (MAX_ORDER - 1))
+			totalram_pages += 1 << h->order;
 	}
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index 6a697bb97fc5..dedb0aff673f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -62,7 +62,7 @@ extern bool is_free_buddy_page(struct page *page);
  */
 static inline unsigned long page_order(struct page *page)
 {
-	VM_BUG_ON(!PageBuddy(page));
+	/* PageBuddy() must be checked by the caller */
 	return page_private(page);
 }
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 2c0d032ac898..49c94b53a6c6 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1368,9 +1368,12 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	++(*pos);
 
 	list_for_each_continue_rcu(n, &object_list) {
-		next_obj = list_entry(n, struct kmemleak_object, object_list);
-		if (get_object(next_obj))
+		struct kmemleak_object *obj =
+			list_entry(n, struct kmemleak_object, object_list);
+		if (get_object(obj)) {
+			next_obj = obj;
 			break;
+		}
 	}
 
 	put_object(prev_obj);
diff --git a/mm/ksm.c b/mm/ksm.c
index 6c3e99b4ae7c..2db786a576ac 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -731,7 +731,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 	if (!ptep)
 		goto out;
 
-	if (pte_write(*ptep)) {
+	if (pte_write(*ptep) || pte_dirty(*ptep)) {
 		pte_t entry;
 
 		swapped = PageSwapCache(page);
@@ -754,7 +754,9 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 			set_pte_at(mm, addr, ptep, entry);
 			goto out_unlock;
 		}
-		entry = pte_wrprotect(entry);
+		if (pte_dirty(entry))
+			set_page_dirty(page);
+		entry = pte_mkclean(pte_wrprotect(entry));
 		set_pte_at_notify(mm, addr, ptep, entry);
 	}
 	*orig_pte = *ptep;
@@ -1270,6 +1272,12 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page)
 		slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list);
 		ksm_scan.mm_slot = slot;
 		spin_unlock(&ksm_mmlist_lock);
+		/*
+		 * Although we tested list_empty() above, a racing __ksm_exit
+		 * of the last mm on the list may have removed it since then.
+		 */
+		if (slot == &ksm_mm_head)
+			return NULL;
 next_mm:
 		ksm_scan.address = 0;
 		ksm_scan.rmap_list = &slot->rmap_list;
@@ -1523,8 +1531,6 @@ 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);
@@ -1540,7 +1546,6 @@ 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 c43447382fec..d2f0c08adf82 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1353,7 +1353,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
 
-	/* 
+	/*
 	 * Require read or write permissions.
 	 * If FOLL_FORCE is set, we only require the "MAY" flags.
 	 */
@@ -1497,7 +1497,63 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	return i;
 }
 
-/**
+/*
+ * fixup_user_fault() - manually resolve a user page fault
+ * @tsk:	the task_struct to use for page fault accounting, or
+ *		NULL if faults are not to be recorded.
+ * @mm:		mm_struct of target mm
+ * @address:	user address
+ * @fault_flags:flags to pass down to handle_mm_fault()
+ *
+ * This is meant to be called in the specific scenario where for locking reasons
+ * we try to access user memory in atomic context (within a pagefault_disable()
+ * section), this returns -EFAULT, and we want to resolve the user fault before
+ * trying again.
+ *
+ * Typically this is meant to be used by the futex code.
+ *
+ * The main difference with get_user_pages() is that this function will
+ * unconditionally call handle_mm_fault() which will in turn perform all the
+ * necessary SW fixup of the dirty and young bits in the PTE, while
+ * handle_mm_fault() only guarantees to update these in the struct page.
+ *
+ * This is important for some architectures where those bits also gate the
+ * access permission to the page because they are maintained in software.  On
+ * such architectures, gup() will not be enough to make a subsequent access
+ * succeed.
+ *
+ * This should be called with the mm_sem held for read.
+ */
+int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+		     unsigned long address, unsigned int fault_flags)
+{
+	struct vm_area_struct *vma;
+	int ret;
+
+	vma = find_extend_vma(mm, address);
+	if (!vma || address < vma->vm_start)
+		return -EFAULT;
+
+	ret = handle_mm_fault(mm, vma, address, fault_flags);
+	if (ret & VM_FAULT_ERROR) {
+		if (ret & VM_FAULT_OOM)
+			return -ENOMEM;
+		if (ret & VM_FAULT_HWPOISON)
+			return -EFAULT;
+		if (ret & VM_FAULT_SIGBUS)
+			return -EFAULT;
+		BUG();
+	}
+	if (tsk) {
+		if (ret & VM_FAULT_MAJOR)
+			tsk->maj_flt++;
+		else
+			tsk->min_flt++;
+	}
+	return 0;
+}
+
+/*
  * get_user_pages() - pin user pages in memory
  * @tsk:	task_struct of target task
  * @mm:		mm_struct of target mm
@@ -2573,6 +2629,7 @@ void unmap_mapping_range(struct address_space *mapping,
 		details.last_index = ULONG_MAX;
 	details.i_mmap_lock = &mapping->i_mmap_lock;
 
+	mutex_lock(&mapping->unmap_mutex);
 	spin_lock(&mapping->i_mmap_lock);
 
 	/* Protect against endless unmapping loops */
@@ -2589,6 +2646,7 @@ void unmap_mapping_range(struct address_space *mapping,
 	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
 		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
 	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->unmap_mutex);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
@@ -2626,7 +2684,7 @@ 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;
@@ -2681,10 +2739,25 @@ 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 or reuse_swap_page or swapoff did not
+	 * release the swapcache from under us.  The page pin, and pte_same
+	 * test below, are not enough to exclude that.  Even if it is still
+	 * swapcache, we need to check that the page's swap has not changed.
+	 */
+	if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val))
+		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 +2808,18 @@ 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);
@@ -2756,25 +2841,43 @@ 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)
 {
 	address &= PAGE_MASK;
 	if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
-		address -= PAGE_SIZE;
-		if (find_vma(vma->vm_mm, address) != vma)
-			return -ENOMEM;
+		struct vm_area_struct *prev = vma->vm_prev;
 
-		expand_stack(vma, address);
+		/*
+		 * Is there a mapping abutting this one below?
+		 *
+		 * That's only ok if it's the same stack mapping
+		 * that has gotten split..
+		 */
+		if (prev && prev->vm_end == address)
+			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
+
+		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;
 }
@@ -2792,22 +2895,23 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	pte_t entry;
 
+	pte_unmap(page_table);
+
+	/* Check if we need to add a guard page to the stack */
 	if (check_stack_guard_page(vma, address) < 0)
 		return VM_FAULT_SIGBUS;
 
+	/* Use the zero-page for reads */
 	if (!(flags & FAULT_FLAG_WRITE)) {
 		entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
 						vma->vm_page_prot));
-		ptl = pte_lockptr(mm, pmd);
-		spin_lock(ptl);
+		page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
 		if (!pte_none(*page_table))
 			goto unlock;
 		goto setpte;
 	}
 
 	/* Allocate our own private page. */
-	pte_unmap(page_table);
-
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
 	page = alloc_zeroed_user_highpage_movable(vma, address);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a4cfcdc00455..6345dfe78d2c 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. */
@@ -659,7 +659,7 @@ static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
  * Scanning pfn is much easier than scanning lru list.
  * Scan pfn from start to end and Find LRU page.
  */
-int scan_lru_pages(unsigned long start, unsigned long end)
+unsigned long scan_lru_pages(unsigned long start, unsigned long end)
 {
 	unsigned long pfn;
 	struct page *page;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 5bc0a96beb51..407cda2d753f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1576,7 +1576,7 @@ unsigned slab_node(struct mempolicy *policy)
 		(void)first_zones_zonelist(zonelist, highest_zoneidx,
 							&policy->v.nodes,
 							&zone);
-		return zone->node;
+		return zone ? zone->node : numa_node_id();
 	}
 
 	default:
diff --git a/mm/migrate.c b/mm/migrate.c
index 4205b1d6049e..ca71d064bce7 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -266,7 +266,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	 */
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	__inc_zone_page_state(newpage, NR_FILE_PAGES);
-	if (PageSwapBacked(page)) {
+	if (!PageSwapCache(page) && PageSwapBacked(page)) {
 		__dec_zone_page_state(page, NR_SHMEM);
 		__inc_zone_page_state(newpage, NR_SHMEM);
 	}
diff --git a/mm/mlock.c b/mm/mlock.c
index 49e5e4cb8232..b70919ce4f72 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -135,6 +135,13 @@ void munlock_vma_page(struct page *page)
 	}
 }
 
+static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	return (vma->vm_flags & VM_GROWSDOWN) &&
+		(vma->vm_start == addr) &&
+		!vma_stack_continue(vma->vm_prev, addr);
+}
+
 /**
  * __mlock_vma_pages_range() -  mlock a range of pages in the vma.
  * @vma:   target vma
@@ -168,11 +175,9 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
 		gup_flags |= FOLL_WRITE;
 
 	/* We don't try to access the guard page of a stack vma */
-	if (vma->vm_flags & VM_GROWSDOWN) {
-		if (start == vma->vm_start) {
-			start += PAGE_SIZE;
-			nr_pages--;
-		}
+	if (stack_guard_page(vma, start)) {
+		addr += PAGE_SIZE;
+		nr_pages--;
 	}
 
 	while (nr_pages > 0) {
diff --git a/mm/mmap.c b/mm/mmap.c
index 456ec6f27889..073b39d32bc4 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -388,17 +388,23 @@ static inline void
 __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct rb_node *rb_parent)
 {
+	struct vm_area_struct *next;
+
+	vma->vm_prev = prev;
 	if (prev) {
-		vma->vm_next = prev->vm_next;
+		next = prev->vm_next;
 		prev->vm_next = vma;
 	} else {
 		mm->mmap = vma;
 		if (rb_parent)
-			vma->vm_next = rb_entry(rb_parent,
+			next = rb_entry(rb_parent,
 					struct vm_area_struct, vm_rb);
 		else
-			vma->vm_next = NULL;
+			next = NULL;
 	}
+	vma->vm_next = next;
+	if (next)
+		next->vm_prev = vma;
 }
 
 void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -485,7 +491,11 @@ static inline void
 __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev)
 {
-	prev->vm_next = vma->vm_next;
+	struct vm_area_struct *next = vma->vm_next;
+
+	prev->vm_next = next;
+	if (next)
+		next->vm_prev = prev;
 	rb_erase(&vma->vm_rb, &mm->mm_rb);
 	if (mm->mmap_cache == vma)
 		mm->mmap_cache = prev;
@@ -1694,9 +1704,6 @@ 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;
@@ -1900,6 +1907,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long addr;
 
 	insertion_point = (prev ? &prev->vm_next : &mm->mmap);
+	vma->vm_prev = NULL;
 	do {
 		rb_erase(&vma->vm_rb, &mm->mm_rb);
 		mm->map_count--;
@@ -1907,6 +1915,8 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 		vma = vma->vm_next;
 	} while (vma && vma->vm_start < end);
 	*insertion_point = vma;
+	if (vma)
+		vma->vm_prev = prev;
 	tail_vma->vm_next = NULL;
 	if (mm->unmap_area == arch_unmap_area)
 		addr = prev ? prev->vm_end : mm->mmap_base;
@@ -1984,6 +1994,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 			removed_exe_file_vma(mm);
 		fput(new->vm_file);
 	}
+	unlink_anon_vmas(new);
  out_free_mpol:
 	mpol_put(pol);
  out_free_vma:
@@ -2433,6 +2444,7 @@ int install_special_mapping(struct mm_struct *mm,
 			    unsigned long addr, unsigned long len,
 			    unsigned long vm_flags, struct page **pages)
 {
+	int ret;
 	struct vm_area_struct *vma;
 
 	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
@@ -2450,16 +2462,23 @@ int install_special_mapping(struct mm_struct *mm,
 	vma->vm_ops = &special_mapping_vmops;
 	vma->vm_private_data = pages;
 
-	if (unlikely(insert_vm_struct(mm, vma))) {
-		kmem_cache_free(vm_area_cachep, vma);
-		return -ENOMEM;
-	}
+	ret = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1);
+	if (ret)
+		goto out;
+
+	ret = insert_vm_struct(mm, vma);
+	if (ret)
+		goto out;
 
 	mm->total_vm += len >> PAGE_SHIFT;
 
 	perf_event_mmap(vma);
 
 	return 0;
+
+out:
+	kmem_cache_free(vm_area_cachep, vma);
+	return ret;
 }
 
 static DEFINE_MUTEX(mm_all_locks_mutex);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 2d1bf7cf8851..4c5133873097 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -211,6 +211,7 @@ success:
 	mmu_notifier_invalidate_range_end(mm, start, end);
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
+	perf_event_mmap(vma);
 	return 0;
 
 fail:
@@ -299,7 +300,6 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
 		if (error)
 			goto out;
-		perf_event_mmap(vma);
 		nstart = tmp;
 
 		if (nstart < prev->vm_end)
diff --git a/mm/mremap.c b/mm/mremap.c
index cde56ee51ef7..97de5aef9431 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -91,9 +91,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		 */
 		mapping = vma->vm_file->f_mapping;
 		spin_lock(&mapping->i_mmap_lock);
-		if (new_vma->vm_truncate_count &&
-		    new_vma->vm_truncate_count != vma->vm_truncate_count)
-			new_vma->vm_truncate_count = 0;
+		new_vma->vm_truncate_count = 0;
 	}
 
 	/*
@@ -276,9 +274,16 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 	if (old_len > vma->vm_end - addr)
 		goto Efault;
 
-	if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) {
-		if (new_len > old_len)
+	/* Need to be careful about a growing mapping */
+	if (new_len > old_len) {
+		unsigned long pgoff;
+
+		if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))
 			goto Efault;
+		pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
+		pgoff += vma->vm_pgoff;
+		if (pgoff + (new_len >> PAGE_SHIFT) < pgoff)
+			goto Einval;
 	}
 
 	if (vma->vm_flags & VM_LOCKED) {
diff --git a/mm/nommu.c b/mm/nommu.c
index b76f3ee0abe0..fbdb2e766758 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -609,7 +609,7 @@ static void protect_vma(struct vm_area_struct *vma, unsigned long flags)
  */
 static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	struct vm_area_struct *pvma, **pp;
+	struct vm_area_struct *pvma, **pp, *next;
 	struct address_space *mapping;
 	struct rb_node **p, *parent;
 
@@ -669,8 +669,11 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 			break;
 	}
 
-	vma->vm_next = *pp;
+	next = *pp;
 	*pp = vma;
+	vma->vm_next = next;
+	if (next)
+		next->vm_prev = vma;
 }
 
 /*
@@ -1670,6 +1673,7 @@ void exit_mmap(struct mm_struct *mm)
 		mm->mmap = vma->vm_next;
 		delete_vma_from_mm(vma);
 		delete_vma(mm, vma);
+		cond_resched();
 	}
 
 	kleave("");
@@ -1743,10 +1747,13 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	return NULL;
 }
 
-int remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-		unsigned long to, unsigned long size, pgprot_t prot)
+int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+		unsigned long pfn, unsigned long size, pgprot_t prot)
 {
-	vma->vm_start = vma->vm_pgoff << PAGE_SHIFT;
+	if (addr != (pfn << PAGE_SHIFT))
+		return -EINVAL;
+
+	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
 	return 0;
 }
 EXPORT_SYMBOL(remap_pfn_range);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 37498ef61548..582cba18ae02 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -949,22 +949,16 @@ 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);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9bd339eb04c6..98c699d9136f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -103,19 +103,24 @@ gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
  * only be modified with pm_mutex held, unless the suspend/hibernate code is
  * guaranteed not to run in parallel with that modification).
  */
-void set_gfp_allowed_mask(gfp_t mask)
+
+static gfp_t saved_gfp_mask;
+
+void pm_restore_gfp_mask(void)
 {
 	WARN_ON(!mutex_is_locked(&pm_mutex));
-	gfp_allowed_mask = mask;
+	if (saved_gfp_mask) {
+		gfp_allowed_mask = saved_gfp_mask;
+		saved_gfp_mask = 0;
+	}
 }
 
-gfp_t clear_gfp_allowed_mask(gfp_t mask)
+void pm_restrict_gfp_mask(void)
 {
-	gfp_t ret = gfp_allowed_mask;
-
 	WARN_ON(!mutex_is_locked(&pm_mutex));
-	gfp_allowed_mask &= ~mask;
-	return ret;
+	WARN_ON(saved_gfp_mask);
+	saved_gfp_mask = gfp_allowed_mask;
+	gfp_allowed_mask &= ~GFP_IOFS;
 }
 #endif /* CONFIG_PM_SLEEP */
 
@@ -530,7 +535,7 @@ static inline void __free_one_page(struct page *page,
 	 * so it's less likely to be used soon and more likely to be merged
 	 * as a higher order page
 	 */
-	if ((order < MAX_ORDER-1) && pfn_valid_within(page_to_pfn(buddy))) {
+	if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) {
 		struct page *higher_page, *higher_buddy;
 		combined_idx = __find_combined_index(page_idx, order);
 		higher_page = page + combined_idx - page_idx;
@@ -588,13 +593,13 @@ 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 +624,9 @@ 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 +637,8 @@ 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);
 }
 
@@ -1453,24 +1459,24 @@ static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 #endif /* CONFIG_FAIL_PAGE_ALLOC */
 
 /*
- * Return 1 if free pages are above 'mark'. This takes into account the order
+ * Return true if free pages are above 'mark'. This takes into account the order
  * of the allocation.
  */
-int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
-		      int classzone_idx, int alloc_flags)
+static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags, long free_pages)
 {
 	/* free_pages my go negative - that's OK */
 	long min = mark;
-	long free_pages = zone_page_state(z, NR_FREE_PAGES) - (1 << order) + 1;
 	int o;
 
+	free_pages -= (1 << order) + 1;
 	if (alloc_flags & ALLOC_HIGH)
 		min -= min / 2;
 	if (alloc_flags & ALLOC_HARDER)
 		min -= min / 4;
 
 	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
-		return 0;
+		return false;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
 		free_pages -= z->free_area[o].nr_free << o;
@@ -1479,9 +1485,28 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 		min >>= 1;
 
 		if (free_pages <= min)
-			return 0;
+			return false;
 	}
-	return 1;
+	return true;
+}
+
+bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags)
+{
+	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+					zone_page_state(z, NR_FREE_PAGES));
+}
+
+bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags)
+{
+	long free_pages = zone_page_state(z, NR_FREE_PAGES);
+
+	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
+		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
+
+	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+								free_pages);
 }
 
 #ifdef CONFIG_NUMA
@@ -1843,6 +1868,7 @@ __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();
 
@@ -1861,14 +1887,25 @@ __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;
 }
 
@@ -1990,6 +2027,7 @@ restart:
 	 */
 	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
+rebalance:
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -1997,7 +2035,6 @@ restart:
 	if (page)
 		goto got_pg;
 
-rebalance:
 	/* Allocate without watermarks if the context allows */
 	if (alloc_flags & ALLOC_NO_WATERMARKS) {
 		page = __alloc_pages_high_priority(gfp_mask, order,
diff --git a/mm/percpu.c b/mm/percpu.c
index 6470e7710231..0a09fff3d05d 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1413,9 +1413,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 			if (pcpu_first_unit_cpu == NR_CPUS)
 				pcpu_first_unit_cpu = cpu;
+			pcpu_last_unit_cpu = cpu;
 		}
 	}
-	pcpu_last_unit_cpu = cpu;
 	pcpu_nr_units = unit;
 
 	for_each_possible_cpu(cpu)
diff --git a/mm/shmem.c b/mm/shmem.c
index f65f84062db5..676eed337809 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2756,5 +2756,6 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 		fput(vma->vm_file);
 	vma->vm_file = file;
 	vma->vm_ops = &shmem_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
diff --git a/mm/slab.c b/mm/slab.c
index e49f8f46f46d..91e691bf9a0e 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2289,8 +2289,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	if (ralign < align) {
 		ralign = align;
 	}
-	/* disable debug if not aligning with REDZONE_ALIGN */
-	if (ralign & (__alignof__(unsigned long long) - 1))
+	/* disable debug if necessary */
+	if (ralign > __alignof__(unsigned long long))
 		flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
 	/*
 	 * 4) Store it.
@@ -2316,8 +2316,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	 */
 	if (flags & SLAB_RED_ZONE) {
 		/* add space for red zone words */
-		cachep->obj_offset += align;
-		size += align + sizeof(unsigned long long);
+		cachep->obj_offset += sizeof(unsigned long long);
+		size += 2 * sizeof(unsigned long long);
 	}
 	if (flags & SLAB_STORE_USER) {
 		/* user store requires one word storage behind the end of
@@ -2331,8 +2331,8 @@ 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 f08d165871b3..c731d1456495 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -139,8 +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();
@@ -151,8 +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;
 
@@ -191,8 +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;
 		}
 
@@ -688,6 +685,24 @@ 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;
@@ -2034,7 +2049,7 @@ 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/vmalloc.c b/mm/vmalloc.c
index ae007462b7f6..20a402ce7bd2 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -513,6 +513,15 @@ static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
 static void purge_fragmented_blocks_allcpus(void);
 
 /*
+ * called before a call to iounmap() if the caller wants vm_area_struct's
+ * immediately freed.
+ */
+void set_iounmap_nonlazy(void)
+{
+	atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
+}
+
+/*
  * Purges all lazily-freed vmap areas.
  *
  * If sync is 0 then don't purge if there is already a purge in progress.
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b94fe1b3da43..22e56769e006 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1726,13 +1726,12 @@ static void shrink_zone(int priority, struct zone *zone,
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static bool shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
 	struct zoneref *z;
 	struct zone *zone;
-	bool all_unreclaimable = true;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 					sc->nodemask) {
@@ -1759,8 +1758,38 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
 		}
 
 		shrink_zone(priority, zone, sc);
-		all_unreclaimable = false;
 	}
+}
+
+static bool zone_reclaimable(struct zone *zone)
+{
+	return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
+}
+
+/*
+ * As hibernation is going on, kswapd is freezed so that it can't mark
+ * the zone into all_unreclaimable. It can't handle OOM during hibernation.
+ * So let's check zone's unreclaimable in direct reclaim as well as kswapd.
+ */
+static bool all_unreclaimable(struct zonelist *zonelist,
+		struct scan_control *sc)
+{
+	struct zoneref *z;
+	struct zone *zone;
+	bool all_unreclaimable = true;
+
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+			gfp_zone(sc->gfp_mask), sc->nodemask) {
+		if (!populated_zone(zone))
+			continue;
+		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+			continue;
+		if (zone_reclaimable(zone)) {
+			all_unreclaimable = false;
+			break;
+		}
+	}
+
 	return all_unreclaimable;
 }
 
@@ -1784,7 +1813,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	int priority;
-	bool all_unreclaimable;
 	unsigned long total_scanned = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long lru_pages = 0;
@@ -1815,7 +1843,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
-		all_unreclaimable = shrink_zones(priority, zonelist, sc);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -1879,7 +1907,7 @@ out:
 		return sc->nr_reclaimed;
 
 	/* top priority shrink_zones still had more to do? don't OOM, then */
-	if (scanning_global_lru(sc) && !all_unreclaimable)
+	if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc))
 		return 1;
 
 	return 0;
@@ -1979,7 +2007,7 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
 		if (zone->all_unreclaimable)
 			continue;
 
-		if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
+		if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone),
 								0, 0))
 			return 1;
 	}
@@ -2076,7 +2104,7 @@ loop_again:
 				shrink_active_list(SWAP_CLUSTER_MAX, zone,
 							&sc, priority, 0);
 
-			if (!zone_watermark_ok(zone, order,
+			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
 				break;
@@ -2127,7 +2155,7 @@ loop_again:
 			 * We put equal pressure on every zone, unless one
 			 * zone has way too many pages free already.
 			 */
-			if (!zone_watermark_ok(zone, order,
+			if (!zone_watermark_ok_safe(zone, order,
 					8*high_wmark_pages(zone), end_zone, 0))
 				shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
@@ -2137,8 +2165,7 @@ loop_again:
 			total_scanned += sc.nr_scanned;
 			if (zone->all_unreclaimable)
 				continue;
-			if (nr_slab == 0 &&
-			    zone->pages_scanned >= (zone_reclaimable_pages(zone) * 6))
+			if (nr_slab == 0 && !zone_reclaimable(zone))
 				zone->all_unreclaimable = 1;
 			/*
 			 * If we've done a decent amount of scanning and
@@ -2149,7 +2176,7 @@ loop_again:
 			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
 
-			if (!zone_watermark_ok(zone, order,
+			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), end_zone, 0)) {
 				all_zones_ok = 0;
 				/*
@@ -2157,7 +2184,7 @@ loop_again:
 				 * means that we have a GFP_ATOMIC allocation
 				 * failure risk. Hurry up!
 				 */
-				if (!zone_watermark_ok(zone, order,
+				if (!zone_watermark_ok_safe(zone, order,
 					    min_wmark_pages(zone), end_zone, 0))
 					has_under_min_watermark_zone = 1;
 			}
@@ -2299,9 +2326,11 @@ static int kswapd(void *p)
 				 * premature sleep. If not, then go fully
 				 * to sleep until explicitly woken up
 				 */
-				if (!sleeping_prematurely(pgdat, order, remaining))
+				if (!sleeping_prematurely(pgdat, order, remaining)) {
+					restore_pgdat_percpu_threshold(pgdat);
 					schedule();
-				else {
+					reduce_pgdat_percpu_threshold(pgdat);
+				} else {
 					if (remaining)
 						count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
 					else
@@ -2337,15 +2366,16 @@ void wakeup_kswapd(struct zone *zone, int order)
 	if (!populated_zone(zone))
 		return;
 
-	pgdat = zone->zone_pgdat;
-	if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
+	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 		return;
+	pgdat = zone->zone_pgdat;
 	if (pgdat->kswapd_max_order < order)
 		pgdat->kswapd_max_order = order;
-	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
-		return;
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
+	if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0))
+		return;
+
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7759941d4e77..41dc8cd96a68 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -81,6 +81,30 @@ EXPORT_SYMBOL(vm_stat);
 
 #ifdef CONFIG_SMP
 
+static int calculate_pressure_threshold(struct zone *zone)
+{
+	int threshold;
+	int watermark_distance;
+
+	/*
+	 * As vmstats are not up to date, there is drift between the estimated
+	 * and real values. For high thresholds and a high number of CPUs, it
+	 * is possible for the min watermark to be breached while the estimated
+	 * value looks fine. The pressure threshold is a reduced value such
+	 * that even the maximum amount of drift will not accidentally breach
+	 * the min watermark
+	 */
+	watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone);
+	threshold = max(1, (int)(watermark_distance / num_online_cpus()));
+
+	/*
+	 * Maximum threshold is 125
+	 */
+	threshold = min(125, threshold);
+
+	return threshold;
+}
+
 static int calculate_threshold(struct zone *zone)
 {
 	int threshold;
@@ -138,14 +162,69 @@ 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;
 	}
 }
 
+void reduce_pgdat_percpu_threshold(pg_data_t *pgdat)
+{
+	struct zone *zone;
+	int cpu;
+	int threshold;
+	int i;
+
+	get_online_cpus();
+	for (i = 0; i < pgdat->nr_zones; i++) {
+		zone = &pgdat->node_zones[i];
+		if (!zone->percpu_drift_mark)
+			continue;
+
+		threshold = calculate_pressure_threshold(zone);
+		for_each_online_cpu(cpu)
+			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
+							= threshold;
+	}
+	put_online_cpus();
+}
+
+void restore_pgdat_percpu_threshold(pg_data_t *pgdat)
+{
+	struct zone *zone;
+	int cpu;
+	int threshold;
+	int i;
+
+	get_online_cpus();
+	for (i = 0; i < pgdat->nr_zones; i++) {
+		zone = &pgdat->node_zones[i];
+		if (!zone->percpu_drift_mark)
+			continue;
+
+		threshold = calculate_threshold(zone);
+		for_each_online_cpu(cpu)
+			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
+							= threshold;
+	}
+	put_online_cpus();
+}
+
 /*
  * For use when we know that interrupts are disabled.
  */