Merge branch 'linux-3.4.35' into rel-17

Bug 1243631

Change-Id: I915826047b2e20f0ad0a7d75df295c6cbf6e5b0a

21 files changed, 403 insertions, 265 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 0131170c9d54..53cf62b186b6 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -766,13 +766,17 @@ void * __init alloc_bootmem_section(unsigned long size,
 				    unsigned long section_nr)
 {
 	bootmem_data_t *bdata;
-	unsigned long pfn, goal;
+	unsigned long pfn, goal, limit;
 
 	pfn = section_nr_to_pfn(section_nr);
 	goal = pfn << PAGE_SHIFT;
+	limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
 	bdata = &bootmem_node_data[early_pfn_to_nid(pfn)];
 
-	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, 0);
+	if (goal + size > limit)
+		limit = 0;
+
+	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, limit);
 }
 #endif
 
diff --git a/mm/compaction.c b/mm/compaction.c
index eede98104e9f..10f9bf96f7f0 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -840,7 +840,7 @@ static int compact_node(int nid)
 }
 
 /* Compact all nodes in the system */
-static int compact_nodes(void)
+static void compact_nodes(void)
 {
 	int nid;
 
@@ -849,8 +849,6 @@ static int compact_nodes(void)
 
 	for_each_online_node(nid)
 		compact_node(nid);
-
-	return COMPACT_COMPLETE;
 }
 
 /* The written value is actually unused, all memory is compacted */
@@ -861,7 +859,7 @@ int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void __user *buffer, size_t *length, loff_t *ppos)
 {
 	if (write)
-		return compact_nodes();
+		compact_nodes();
 
 	return 0;
 }
diff --git a/mm/dmapool.c b/mm/dmapool.c
index c5ab33bca0a8..da1b0f0b8709 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -50,7 +50,6 @@ struct dma_pool {		/* the pool */
 	size_t allocation;
 	size_t boundary;
 	char name[32];
-	wait_queue_head_t waitq;
 	struct list_head pools;
 };
 
@@ -62,8 +61,6 @@ struct dma_page {		/* cacheable header for 'allocation' bytes */
 	unsigned int offset;
 };
 
-#define	POOL_TIMEOUT_JIFFIES	((100 /* msec */ * HZ) / 1000)
-
 static DEFINE_MUTEX(pools_lock);
 
 static ssize_t
@@ -172,7 +169,6 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev,
 	retval->size = size;
 	retval->boundary = boundary;
 	retval->allocation = allocation;
-	init_waitqueue_head(&retval->waitq);
 
 	if (dev) {
 		int ret;
@@ -227,7 +223,6 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags)
 		memset(page->vaddr, POOL_POISON_FREED, pool->allocation);
 #endif
 		pool_initialise_page(pool, page);
-		list_add(&page->page_list, &pool->page_list);
 		page->in_use = 0;
 		page->offset = 0;
 	} else {
@@ -315,30 +310,21 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 	might_sleep_if(mem_flags & __GFP_WAIT);
 
 	spin_lock_irqsave(&pool->lock, flags);
- restart:
 	list_for_each_entry(page, &pool->page_list, page_list) {
 		if (page->offset < pool->allocation)
 			goto ready;
 	}
-	page = pool_alloc_page(pool, GFP_ATOMIC);
-	if (!page) {
-		if (mem_flags & __GFP_WAIT) {
-			DECLARE_WAITQUEUE(wait, current);
 
-			__set_current_state(TASK_UNINTERRUPTIBLE);
-			__add_wait_queue(&pool->waitq, &wait);
-			spin_unlock_irqrestore(&pool->lock, flags);
+	/* pool_alloc_page() might sleep, so temporarily drop &pool->lock */
+	spin_unlock_irqrestore(&pool->lock, flags);
 
-			schedule_timeout(POOL_TIMEOUT_JIFFIES);
+	page = pool_alloc_page(pool, mem_flags);
+	if (!page)
+		return NULL;
 
-			spin_lock_irqsave(&pool->lock, flags);
-			__remove_wait_queue(&pool->waitq, &wait);
-			goto restart;
-		}
-		retval = NULL;
-		goto done;
-	}
+	spin_lock_irqsave(&pool->lock, flags);
 
+	list_add(&page->page_list, &pool->page_list);
  ready:
 	page->in_use++;
 	offset = page->offset;
@@ -348,7 +334,6 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 #ifdef	DMAPOOL_DEBUG
 	memset(retval, POOL_POISON_ALLOCATED, pool->size);
 #endif
- done:
 	spin_unlock_irqrestore(&pool->lock, flags);
 	return retval;
 }
@@ -435,8 +420,6 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
 	page->in_use--;
 	*(int *)vaddr = page->offset;
 	page->offset = offset;
-	if (waitqueue_active(&pool->waitq))
-		wake_up_locked(&pool->waitq);
 	/*
 	 * Resist a temptation to do
 	 *    if (!is_page_busy(page)) pool_free_page(pool, page);
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 469491e0af79..dcb98722a22f 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -17,6 +17,7 @@
 #include <linux/fadvise.h>
 #include <linux/writeback.h>
 #include <linux/syscalls.h>
+#include <linux/swap.h>
 
 #include <asm/unistd.h>
 
@@ -124,9 +125,22 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
 		end_index = (endbyte >> PAGE_CACHE_SHIFT);
 
-		if (end_index >= start_index)
-			invalidate_mapping_pages(mapping, start_index,
+		if (end_index >= start_index) {
+			unsigned long count = invalidate_mapping_pages(mapping,
+						start_index, end_index);
+
+			/*
+			 * If fewer pages were invalidated than expected then
+			 * it is possible that some of the pages were on
+			 * a per-cpu pagevec for a remote CPU. Drain all
+			 * pagevecs and try again.
+			 */
+			if (count < (end_index - start_index + 1)) {
+				lru_add_drain_all();
+				invalidate_mapping_pages(mapping, start_index,
 						end_index);
+			}
+		}
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f0e5306eeb55..caf15b6fa753 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -950,6 +950,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(THP_FAULT_FALLBACK);
 		ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 						   pmd, orig_pmd, page, haddr);
+		if (ret & VM_FAULT_OOM)
+			split_huge_page(page);
 		put_page(page);
 		goto out;
 	}
@@ -957,6 +959,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
 		put_page(new_page);
+		split_huge_page(page);
 		put_page(page);
 		ret |= VM_FAULT_OOM;
 		goto out;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a799df59d310..c384e0901f9c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2431,7 +2431,8 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * from page cache lookup which is in HPAGE_SIZE units.
 	 */
 	address = address & huge_page_mask(h);
-	pgoff = vma_hugecache_offset(h, vma, address);
+	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) +
+			vma->vm_pgoff;
 	mapping = vma->vm_file->f_dentry->d_inode->i_mapping;
 
 	/*
diff --git a/mm/memblock.c b/mm/memblock.c
index 280d3d7835d6..11e5bd174f3c 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -908,6 +908,30 @@ int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t si
 	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
 }
 
+void __init_memblock memblock_trim_memory(phys_addr_t align)
+{
+	int i;
+	phys_addr_t start, end, orig_start, orig_end;
+	struct memblock_type *mem = &memblock.memory;
+
+	for (i = 0; i < mem->cnt; i++) {
+		orig_start = mem->regions[i].base;
+		orig_end = mem->regions[i].base + mem->regions[i].size;
+		start = round_up(orig_start, align);
+		end = round_down(orig_end, align);
+
+		if (start == orig_start && end == orig_end)
+			continue;
+
+		if (start < end) {
+			mem->regions[i].base = start;
+			mem->regions[i].size = end - start;
+		} else {
+			memblock_remove_region(mem, i);
+			i--;
+		}
+	}
+}
 
 void __init_memblock memblock_set_current_limit(phys_addr_t limit)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7685d4a0b3ce..81c275b3afed 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1489,17 +1489,26 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
 	u64 limit;
-	u64 memsw;
 
 	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-	limit += total_swap_pages << PAGE_SHIFT;
 
-	memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
 	/*
-	 * If memsw is finite and limits the amount of swap space available
-	 * to this memcg, return that limit.
+	 * Do not consider swap space if we cannot swap due to swappiness
 	 */
-	return min(limit, memsw);
+	if (mem_cgroup_swappiness(memcg)) {
+		u64 memsw;
+
+		limit += total_swap_pages << PAGE_SHIFT;
+		memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+
+		/*
+		 * If memsw is finite and limits the amount of swap space
+		 * available to this memcg, return that limit.
+		 */
+		limit = min(limit, memsw);
+	}
+
+	return limit;
 }
 
 static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 9299eea77f72..b68c8f66e4d3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1481,9 +1481,17 @@ int soft_offline_page(struct page *page, int flags)
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
+	struct page *hpage = compound_trans_head(page);
 
 	if (PageHuge(page))
 		return soft_offline_huge_page(page, flags);
+	if (PageTransHuge(hpage)) {
+		if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
+			pr_info("soft offline: %#lx: failed to split THP\n",
+				pfn);
+			return -EBUSY;
+		}
+	}
 
 	ret = get_any_page(page, pfn, flags);
 	if (ret < 0)
diff --git a/mm/memory.c b/mm/memory.c
index 6105f475fa86..2f42aab50e9b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -182,10 +182,14 @@ static int tlb_next_batch(struct mmu_gather *tlb)
 		return 1;
 	}
 
+	if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
+		return 0;
+
 	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
 	if (!batch)
 		return 0;
 
+	tlb->batch_count++;
 	batch->next = NULL;
 	batch->nr   = 0;
 	batch->max  = MAX_GATHER_BATCH;
@@ -212,6 +216,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
 	tlb->local.nr   = 0;
 	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
 	tlb->active     = &tlb->local;
+	tlb->batch_count = 0;
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;
@@ -3489,6 +3494,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(is_vm_hugetlb_page(vma)))
 		return hugetlb_fault(mm, vma, address, flags);
 
+retry:
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
@@ -3502,13 +3508,24 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 							  pmd, flags);
 	} else {
 		pmd_t orig_pmd = *pmd;
+		int ret;
+
 		barrier();
 		if (pmd_trans_huge(orig_pmd)) {
 			if (flags & FAULT_FLAG_WRITE &&
 			    !pmd_write(orig_pmd) &&
-			    !pmd_trans_splitting(orig_pmd))
-				return do_huge_pmd_wp_page(mm, vma, address,
-							   pmd, orig_pmd);
+			    !pmd_trans_splitting(orig_pmd)) {
+				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
+							  orig_pmd);
+				/*
+				 * If COW results in an oom, the huge pmd will
+				 * have been split, so retry the fault on the
+				 * pte for a smaller charge.
+				 */
+				if (unlikely(ret & VM_FAULT_OOM))
+					goto retry;
+				return ret;
+			}
 			return 0;
 		}
 	}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index fc898cb4fe8f..77ad30613a3d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -127,9 +127,6 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 	struct mem_section *ms;
 	struct page *page, *memmap;
 
-	if (!pfn_valid(start_pfn))
-		return;
-
 	section_nr = pfn_to_section_nr(start_pfn);
 	ms = __nr_to_section(section_nr);
 
@@ -188,9 +185,16 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 	end_pfn = pfn + pgdat->node_spanned_pages;
 
 	/* register_section info */
-	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION)
-		register_page_bootmem_info_section(pfn);
-
+	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		/*
+		 * Some platforms can assign the same pfn to multiple nodes - on
+		 * node0 as well as nodeN.  To avoid registering a pfn against
+		 * multiple nodes we check that this pfn does not already
+		 * reside in some other node.
+		 */
+		if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
+			register_page_bootmem_info_section(pfn);
+	}
 }
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP */
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index bf5b485ecd31..82f1b027ba1c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -607,6 +607,42 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 	return first;
 }
 
+/*
+ * Apply policy to a single VMA
+ * This must be called with the mmap_sem held for writing.
+ */
+static int vma_replace_policy(struct vm_area_struct *vma,
+						struct mempolicy *pol)
+{
+	int err;
+	struct mempolicy *old;
+	struct mempolicy *new;
+
+	pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
+		 vma->vm_start, vma->vm_end, vma->vm_pgoff,
+		 vma->vm_ops, vma->vm_file,
+		 vma->vm_ops ? vma->vm_ops->set_policy : NULL);
+
+	new = mpol_dup(pol);
+	if (IS_ERR(new))
+		return PTR_ERR(new);
+
+	if (vma->vm_ops && vma->vm_ops->set_policy) {
+		err = vma->vm_ops->set_policy(vma, new);
+		if (err)
+			goto err_out;
+	}
+
+	old = vma->vm_policy;
+	vma->vm_policy = new; /* protected by mmap_sem */
+	mpol_put(old);
+
+	return 0;
+ err_out:
+	mpol_put(new);
+	return err;
+}
+
 /* Step 2: apply policy to a range and do splits. */
 static int mbind_range(struct mm_struct *mm, unsigned long start,
 		       unsigned long end, struct mempolicy *new_pol)
@@ -655,23 +691,9 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 			if (err)
 				goto out;
 		}
-
-		/*
-		 * Apply policy to a single VMA. The reference counting of
-		 * policy for vma_policy linkages has already been handled by
-		 * vma_merge and split_vma as necessary. If this is a shared
-		 * policy then ->set_policy will increment the reference count
-		 * for an sp node.
-		 */
-		pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
-			vma->vm_start, vma->vm_end, vma->vm_pgoff,
-			vma->vm_ops, vma->vm_file,
-			vma->vm_ops ? vma->vm_ops->set_policy : NULL);
-		if (vma->vm_ops && vma->vm_ops->set_policy) {
-			err = vma->vm_ops->set_policy(vma, new_pol);
-			if (err)
-				goto out;
-		}
+		err = vma_replace_policy(vma, new_pol);
+		if (err)
+			goto out;
 	}
 
  out:
@@ -1510,8 +1532,18 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 									addr);
 			if (vpol)
 				pol = vpol;
-		} else if (vma->vm_policy)
+		} else if (vma->vm_policy) {
 			pol = vma->vm_policy;
+
+			/*
+			 * shmem_alloc_page() passes MPOL_F_SHARED policy with
+			 * a pseudo vma whose vma->vm_ops=NULL. Take a reference
+			 * count on these policies which will be dropped by
+			 * mpol_cond_put() later
+			 */
+			if (mpol_needs_cond_ref(pol))
+				mpol_get(pol);
+		}
 	}
 	if (!pol)
 		pol = &default_policy;
@@ -1977,28 +2009,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 	return new;
 }
 
-/*
- * If *frompol needs [has] an extra ref, copy *frompol to *tompol ,
- * eliminate the * MPOL_F_* flags that require conditional ref and
- * [NOTE!!!] drop the extra ref.  Not safe to reference *frompol directly
- * after return.  Use the returned value.
- *
- * Allows use of a mempolicy for, e.g., multiple allocations with a single
- * policy lookup, even if the policy needs/has extra ref on lookup.
- * shmem_readahead needs this.
- */
-struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
-						struct mempolicy *frompol)
-{
-	if (!mpol_needs_cond_ref(frompol))
-		return frompol;
-
-	*tompol = *frompol;
-	tompol->flags &= ~MPOL_F_SHARED;	/* copy doesn't need unref */
-	__mpol_put(frompol);
-	return tompol;
-}
-
 /* Slow path of a mempolicy comparison */
 bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 {
@@ -2035,7 +2045,7 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
  */
 
 /* lookup first element intersecting start-end */
-/* Caller holds sp->lock */
+/* Caller holds sp->mutex */
 static struct sp_node *
 sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
 {
@@ -2099,36 +2109,50 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
 
 	if (!sp->root.rb_node)
 		return NULL;
-	spin_lock(&sp->lock);
+	mutex_lock(&sp->mutex);
 	sn = sp_lookup(sp, idx, idx+1);
 	if (sn) {
 		mpol_get(sn->policy);
 		pol = sn->policy;
 	}
-	spin_unlock(&sp->lock);
+	mutex_unlock(&sp->mutex);
 	return pol;
 }
 
+static void sp_free(struct sp_node *n)
+{
+	mpol_put(n->policy);
+	kmem_cache_free(sn_cache, n);
+}
+
 static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 {
 	pr_debug("deleting %lx-l%lx\n", n->start, n->end);
 	rb_erase(&n->nd, &sp->root);
-	mpol_put(n->policy);
-	kmem_cache_free(sn_cache, n);
+	sp_free(n);
 }
 
 static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
 				struct mempolicy *pol)
 {
-	struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
+	struct sp_node *n;
+	struct mempolicy *newpol;
 
+	n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
 	if (!n)
 		return NULL;
+
+	newpol = mpol_dup(pol);
+	if (IS_ERR(newpol)) {
+		kmem_cache_free(sn_cache, n);
+		return NULL;
+	}
+	newpol->flags |= MPOL_F_SHARED;
+
 	n->start = start;
 	n->end = end;
-	mpol_get(pol);
-	pol->flags |= MPOL_F_SHARED;	/* for unref */
-	n->policy = pol;
+	n->policy = newpol;
+
 	return n;
 }
 
@@ -2136,10 +2160,10 @@ static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
 static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 				 unsigned long end, struct sp_node *new)
 {
-	struct sp_node *n, *new2 = NULL;
+	struct sp_node *n;
+	int ret = 0;
 
-restart:
-	spin_lock(&sp->lock);
+	mutex_lock(&sp->mutex);
 	n = sp_lookup(sp, start, end);
 	/* Take care of old policies in the same range. */
 	while (n && n->start < end) {
@@ -2152,16 +2176,14 @@ restart:
 		} else {
 			/* Old policy spanning whole new range. */
 			if (n->end > end) {
+				struct sp_node *new2;
+				new2 = sp_alloc(end, n->end, n->policy);
 				if (!new2) {
-					spin_unlock(&sp->lock);
-					new2 = sp_alloc(end, n->end, n->policy);
-					if (!new2)
-						return -ENOMEM;
-					goto restart;
+					ret = -ENOMEM;
+					goto out;
 				}
 				n->end = start;
 				sp_insert(sp, new2);
-				new2 = NULL;
 				break;
 			} else
 				n->end = start;
@@ -2172,12 +2194,9 @@ restart:
 	}
 	if (new)
 		sp_insert(sp, new);
-	spin_unlock(&sp->lock);
-	if (new2) {
-		mpol_put(new2->policy);
-		kmem_cache_free(sn_cache, new2);
-	}
-	return 0;
+out:
+	mutex_unlock(&sp->mutex);
+	return ret;
 }
 
 /**
@@ -2195,7 +2214,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 	int ret;
 
 	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
-	spin_lock_init(&sp->lock);
+	mutex_init(&sp->mutex);
 
 	if (mpol) {
 		struct vm_area_struct pvma;
@@ -2249,7 +2268,7 @@ int mpol_set_shared_policy(struct shared_policy *info,
 	}
 	err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
 	if (err && new)
-		kmem_cache_free(sn_cache, new);
+		sp_free(new);
 	return err;
 }
 
@@ -2261,16 +2280,14 @@ void mpol_free_shared_policy(struct shared_policy *p)
 
 	if (!p->root.rb_node)
 		return;
-	spin_lock(&p->lock);
+	mutex_lock(&p->mutex);
 	next = rb_first(&p->root);
 	while (next) {
 		n = rb_entry(next, struct sp_node, nd);
 		next = rb_next(&n->nd);
-		rb_erase(&n->nd, &p->root);
-		mpol_put(n->policy);
-		kmem_cache_free(sn_cache, n);
+		sp_delete(p, n);
 	}
-	spin_unlock(&p->lock);
+	mutex_unlock(&p->mutex);
 }
 
 /* assumes fs == KERNEL_DS */
@@ -2327,8 +2344,7 @@ void numa_default_policy(void)
  */
 
 /*
- * "local" is pseudo-policy:  MPOL_PREFERRED with MPOL_F_LOCAL flag
- * Used only for mpol_parse_str() and mpol_to_str()
+ * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag.
  */
 #define MPOL_LOCAL MPOL_MAX
 static const char * const policy_modes[] =
@@ -2343,28 +2359,21 @@ static const char * const policy_modes[] =
 
 #ifdef CONFIG_TMPFS
 /**
- * mpol_parse_str - parse string to mempolicy
+ * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option.
  * @str:  string containing mempolicy to parse
  * @mpol:  pointer to struct mempolicy pointer, returned on success.
- * @no_context:  flag whether to "contextualize" the mempolicy
+ * @unused:  redundant argument, to be removed later.
  *
  * Format of input:
  *	<mode>[=<flags>][:<nodelist>]
  *
- * if @no_context is true, save the input nodemask in w.user_nodemask in
- * the returned mempolicy.  This will be used to "clone" the mempolicy in
- * a specific context [cpuset] at a later time.  Used to parse tmpfs mpol
- * mount option.  Note that if 'static' or 'relative' mode flags were
- * specified, the input nodemask will already have been saved.  Saving
- * it again is redundant, but safe.
- *
  * On success, returns 0, else 1
  */
-int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
+int mpol_parse_str(char *str, struct mempolicy **mpol, int unused)
 {
 	struct mempolicy *new = NULL;
 	unsigned short mode;
-	unsigned short uninitialized_var(mode_flags);
+	unsigned short mode_flags;
 	nodemask_t nodes;
 	char *nodelist = strchr(str, ':');
 	char *flags = strchr(str, '=');
@@ -2452,24 +2461,23 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
 	if (IS_ERR(new))
 		goto out;
 
-	if (no_context) {
-		/* save for contextualization */
-		new->w.user_nodemask = nodes;
-	} else {
-		int ret;
-		NODEMASK_SCRATCH(scratch);
-		if (scratch) {
-			task_lock(current);
-			ret = mpol_set_nodemask(new, &nodes, scratch);
-			task_unlock(current);
-		} else
-			ret = -ENOMEM;
-		NODEMASK_SCRATCH_FREE(scratch);
-		if (ret) {
-			mpol_put(new);
-			goto out;
-		}
-	}
+	/*
+	 * Save nodes for mpol_to_str() to show the tmpfs mount options
+	 * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo.
+	 */
+	if (mode != MPOL_PREFERRED)
+		new->v.nodes = nodes;
+	else if (nodelist)
+		new->v.preferred_node = first_node(nodes);
+	else
+		new->flags |= MPOL_F_LOCAL;
+
+	/*
+	 * Save nodes for contextualization: this will be used to "clone"
+	 * the mempolicy in a specific context [cpuset] at a later time.
+	 */
+	new->w.user_nodemask = nodes;
+
 	err = 0;
 
 out:
@@ -2489,13 +2497,13 @@ out:
  * @buffer:  to contain formatted mempolicy string
  * @maxlen:  length of @buffer
  * @pol:  pointer to mempolicy to be formatted
- * @no_context:  "context free" mempolicy - use nodemask in w.user_nodemask
+ * @unused:  redundant argument, to be removed later.
  *
  * Convert a mempolicy into a string.
  * Returns the number of characters in buffer (if positive)
  * or an error (negative)
  */
-int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
+int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int unused)
 {
 	char *p = buffer;
 	int l;
@@ -2521,7 +2529,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
 	case MPOL_PREFERRED:
 		nodes_clear(nodes);
 		if (flags & MPOL_F_LOCAL)
-			mode = MPOL_LOCAL;	/* pseudo-policy */
+			mode = MPOL_LOCAL;
 		else
 			node_set(pol->v.preferred_node, nodes);
 		break;
@@ -2529,14 +2537,11 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
 	case MPOL_BIND:
 		/* Fall through */
 	case MPOL_INTERLEAVE:
-		if (no_context)
-			nodes = pol->w.user_nodemask;
-		else
-			nodes = pol->v.nodes;
+		nodes = pol->v.nodes;
 		break;
 
 	default:
-		BUG();
+		return -EINVAL;
 	}
 
 	l = strlen(policy_modes[mode]);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 862b60822d9f..8d1ca2de4080 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -14,10 +14,14 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/err.h>
+#include <linux/srcu.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 
+/* global SRCU for all MMs */
+static struct srcu_struct srcu;
+
 /*
  * This function can't run concurrently against mmu_notifier_register
  * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
@@ -25,58 +29,61 @@
  * in parallel despite there being no task using this mm any more,
  * through the vmas outside of the exit_mmap context, such as with
  * vmtruncate. This serializes against mmu_notifier_unregister with
- * the mmu_notifier_mm->lock in addition to RCU and it serializes
- * against the other mmu notifiers with RCU. struct mmu_notifier_mm
+ * the mmu_notifier_mm->lock in addition to SRCU and it serializes
+ * against the other mmu notifiers with SRCU. struct mmu_notifier_mm
  * can't go away from under us as exit_mmap holds an mm_count pin
  * itself.
  */
 void __mmu_notifier_release(struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
+	int id;
 
 	/*
-	 * RCU here will block mmu_notifier_unregister until
-	 * ->release returns.
+	 * srcu_read_lock() here will block synchronize_srcu() in
+	 * mmu_notifier_unregister() until all registered
+	 * ->release() callouts this function makes have
+	 * returned.
 	 */
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist)
-		/*
-		 * if ->release runs before mmu_notifier_unregister it
-		 * must be handled as it's the only way for the driver
-		 * to flush all existing sptes and stop the driver
-		 * from establishing any more sptes before all the
-		 * pages in the mm are freed.
-		 */
-		if (mn->ops->release)
-			mn->ops->release(mn, mm);
-	rcu_read_unlock();
-
+	id = srcu_read_lock(&srcu);
 	spin_lock(&mm->mmu_notifier_mm->lock);
 	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
 		mn = hlist_entry(mm->mmu_notifier_mm->list.first,
 				 struct mmu_notifier,
 				 hlist);
+
 		/*
-		 * We arrived before mmu_notifier_unregister so
-		 * mmu_notifier_unregister will do nothing other than
-		 * to wait ->release to finish and
-		 * mmu_notifier_unregister to return.
+		 * Unlink.  This will prevent mmu_notifier_unregister()
+		 * from also making the ->release() callout.
 		 */
 		hlist_del_init_rcu(&mn->hlist);
+		spin_unlock(&mm->mmu_notifier_mm->lock);
+
+		/*
+		 * Clear sptes. (see 'release' description in mmu_notifier.h)
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+
+		spin_lock(&mm->mmu_notifier_mm->lock);
 	}
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
 	/*
-	 * synchronize_rcu here prevents mmu_notifier_release to
-	 * return to exit_mmap (which would proceed freeing all pages
-	 * in the mm) until the ->release method returns, if it was
-	 * invoked by mmu_notifier_unregister.
-	 *
-	 * The mmu_notifier_mm can't go away from under us because one
-	 * mm_count is hold by exit_mmap.
+	 * All callouts to ->release() which we have done are complete.
+	 * Allow synchronize_srcu() in mmu_notifier_unregister() to complete
+	 */
+	srcu_read_unlock(&srcu, id);
+
+	/*
+	 * mmu_notifier_unregister() may have unlinked a notifier and may
+	 * still be calling out to it.	Additionally, other notifiers
+	 * may have been active via vmtruncate() et. al. Block here
+	 * to ensure that all notifier callouts for this mm have been
+	 * completed and the sptes are really cleaned up before returning
+	 * to exit_mmap().
 	 */
-	synchronize_rcu();
+	synchronize_srcu(&srcu);
 }
 
 /*
@@ -89,14 +96,14 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
-	int young = 0;
+	int young = 0, id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->clear_flush_young)
 			young |= mn->ops->clear_flush_young(mn, mm, address);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 
 	return young;
 }
@@ -106,9 +113,9 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
-	int young = 0;
+	int young = 0, id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->test_young) {
 			young = mn->ops->test_young(mn, mm, address);
@@ -116,7 +123,7 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
 				break;
 		}
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 
 	return young;
 }
@@ -126,8 +133,9 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->change_pte)
 			mn->ops->change_pte(mn, mm, address, pte);
@@ -138,7 +146,7 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 		else if (mn->ops->invalidate_page)
 			mn->ops->invalidate_page(mn, mm, address);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 void __mmu_notifier_invalidate_page(struct mm_struct *mm,
@@ -146,13 +154,14 @@ void __mmu_notifier_invalidate_page(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_page)
 			mn->ops->invalidate_page(mn, mm, address);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
@@ -160,13 +169,14 @@ void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_range_start)
 			mn->ops->invalidate_range_start(mn, mm, start, end);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
@@ -174,13 +184,14 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_range_end)
 			mn->ops->invalidate_range_end(mn, mm, start, end);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 static int do_mmu_notifier_register(struct mmu_notifier *mn,
@@ -192,6 +203,12 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn,
 
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
 
+	/*
+	* Verify that mmu_notifier_init() already run and the global srcu is
+	* initialized.
+	*/
+	BUG_ON(!srcu.per_cpu_ref);
+
 	ret = -ENOMEM;
 	mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
 	if (unlikely(!mmu_notifier_mm))
@@ -274,8 +291,8 @@ void __mmu_notifier_mm_destroy(struct mm_struct *mm)
 /*
  * This releases the mm_count pin automatically and frees the mm
  * structure if it was the last user of it. It serializes against
- * running mmu notifiers with RCU and against mmu_notifier_unregister
- * with the unregister lock + RCU. All sptes must be dropped before
+ * running mmu notifiers with SRCU and against mmu_notifier_unregister
+ * with the unregister lock + SRCU. All sptes must be dropped before
  * calling mmu_notifier_unregister. ->release or any other notifier
  * method may be invoked concurrently with mmu_notifier_unregister,
  * and only after mmu_notifier_unregister returned we're guaranteed
@@ -285,35 +302,43 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
+	spin_lock(&mm->mmu_notifier_mm->lock);
 	if (!hlist_unhashed(&mn->hlist)) {
-		/*
-		 * RCU here will force exit_mmap to wait ->release to finish
-		 * before freeing the pages.
-		 */
-		rcu_read_lock();
+		int id;
 
 		/*
-		 * exit_mmap will block in mmu_notifier_release to
-		 * guarantee ->release is called before freeing the
-		 * pages.
+		 * Ensure we synchronize up with __mmu_notifier_release().
 		 */
+		id = srcu_read_lock(&srcu);
+
+		hlist_del_rcu(&mn->hlist);
+		spin_unlock(&mm->mmu_notifier_mm->lock);
+
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
-		rcu_read_unlock();
 
-		spin_lock(&mm->mmu_notifier_mm->lock);
-		hlist_del_rcu(&mn->hlist);
+		/*
+		 * Allow __mmu_notifier_release() to complete.
+		 */
+		srcu_read_unlock(&srcu, id);
+	} else
 		spin_unlock(&mm->mmu_notifier_mm->lock);
-	}
 
 	/*
-	 * Wait any running method to finish, of course including
-	 * ->release if it was run by mmu_notifier_relase instead of us.
+	 * Wait for any running method to finish, including ->release() if it
+	 * was run by __mmu_notifier_release() instead of us.
 	 */
-	synchronize_rcu();
+	synchronize_srcu(&srcu);
 
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
 	mmdrop(mm);
 }
 EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
+
+static int __init mmu_notifier_init(void)
+{
+	return init_srcu_struct(&srcu);
+}
+
+module_init(mmu_notifier_init);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 26adea8ca2e7..bc8465f579a8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -187,6 +187,18 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 		     zone_reclaimable_pages(z) - z->dirty_balance_reserve;
 	}
 	/*
+	 * Unreclaimable memory (kernel memory or anonymous memory
+	 * without swap) can bring down the dirtyable pages below
+	 * the zone's dirty balance reserve and the above calculation
+	 * will underflow.  However we still want to add in nodes
+	 * which are below threshold (negative values) to get a more
+	 * accurate calculation but make sure that the total never
+	 * underflows.
+	 */
+	if ((long)x < 0)
+		x = 0;
+
+	/*
 	 * Make sure that the number of highmem pages is never larger
 	 * than the number of the total dirtyable memory. This can only
 	 * occur in very strange VM situations but we want to make sure
@@ -208,8 +220,8 @@ unsigned long global_dirtyable_memory(void)
 {
 	unsigned long x;
 
-	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages() -
-	    dirty_balance_reserve;
+	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
+	x -= min(x, dirty_balance_reserve);
 
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);
@@ -276,9 +288,12 @@ static unsigned long zone_dirtyable_memory(struct zone *zone)
 	 * highmem zone can hold its share of dirty pages, so we don't
 	 * care about vm_highmem_is_dirtyable here.
 	 */
-	return zone_page_state(zone, NR_FREE_PAGES) +
-	       zone_reclaimable_pages(zone) -
-	       zone->dirty_balance_reserve;
+	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;
 }
 
 /**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0f20f1c354ef..ef868e299932 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -581,7 +581,7 @@ static inline void __free_one_page(struct page *page,
 		combined_idx = buddy_idx & page_idx;
 		higher_page = page + (combined_idx - page_idx);
 		buddy_idx = __find_buddy_index(combined_idx, order + 1);
-		higher_buddy = page + (buddy_idx - combined_idx);
+		higher_buddy = higher_page + (buddy_idx - combined_idx);
 		if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
 			list_add_tail(&page->lru,
 				&zone->free_area[order].free_list[migratetype]);
@@ -4273,10 +4273,11 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
  * round what is now in bits to nearest long in bits, then return it in
  * bytes.
  */
-static unsigned long __init usemap_size(unsigned long zonesize)
+static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize)
 {
 	unsigned long usemapsize;
 
+	zonesize += zone_start_pfn & (pageblock_nr_pages-1);
 	usemapsize = roundup(zonesize, pageblock_nr_pages);
 	usemapsize = usemapsize >> pageblock_order;
 	usemapsize *= NR_PAGEBLOCK_BITS;
@@ -4286,17 +4287,19 @@ static unsigned long __init usemap_size(unsigned long zonesize)
 }
 
 static void __init setup_usemap(struct pglist_data *pgdat,
-				struct zone *zone, unsigned long zonesize)
+				struct zone *zone,
+				unsigned long zone_start_pfn,
+				unsigned long zonesize)
 {
-	unsigned long usemapsize = usemap_size(zonesize);
+	unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
 	zone->pageblock_flags = NULL;
 	if (usemapsize)
 		zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat,
 								   usemapsize);
 }
 #else
-static inline void setup_usemap(struct pglist_data *pgdat,
-				struct zone *zone, unsigned long zonesize) {}
+static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
+				unsigned long zone_start_pfn, unsigned long zonesize) {}
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -4424,7 +4427,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 			continue;
 
 		set_pageblock_order(pageblock_default_order());
-		setup_usemap(pgdat, zone, size);
+		setup_usemap(pgdat, zone, zone_start_pfn, size);
 		ret = init_currently_empty_zone(zone, zone_start_pfn,
 						size, MEMMAP_EARLY);
 		BUG_ON(ret);
@@ -5409,7 +5412,7 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
 	pfn &= (PAGES_PER_SECTION-1);
 	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 #else
-	pfn = pfn - zone->zone_start_pfn;
+	pfn = pfn - round_down(zone->zone_start_pfn, pageblock_nr_pages);
 	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 #endif /* CONFIG_SPARSEMEM */
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 5b5ad584ffb7..bfca52c96999 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -56,6 +56,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
 #include <linux/hugetlb.h>
+#include <linux/backing-dev.h>
 
 #include <asm/tlbflush.h>
 
@@ -977,11 +978,8 @@ int page_mkclean(struct page *page)
 
 	if (page_mapped(page)) {
 		struct address_space *mapping = page_mapping(page);
-		if (mapping) {
+		if (mapping)
 			ret = page_mkclean_file(mapping, page);
-			if (page_test_and_clear_dirty(page_to_pfn(page), 1))
-				ret = 1;
-		}
 	}
 
 	return ret;
@@ -1167,6 +1165,7 @@ void page_add_file_rmap(struct page *page)
  */
 void page_remove_rmap(struct page *page)
 {
+	struct address_space *mapping = page_mapping(page);
 	bool anon = PageAnon(page);
 	bool locked;
 	unsigned long flags;
@@ -1189,8 +1188,19 @@ void page_remove_rmap(struct page *page)
 	 * this if the page is anon, so about to be freed; but perhaps
 	 * not if it's in swapcache - there might be another pte slot
 	 * containing the swap entry, but page not yet written to swap.
+	 *
+	 * And we can skip it on file pages, so long as the filesystem
+	 * participates in dirty tracking; but need to catch shm and tmpfs
+	 * and ramfs pages which have been modified since creation by read
+	 * fault.
+	 *
+	 * Note that mapping must be decided above, before decrementing
+	 * mapcount (which luckily provides a barrier): once page is unmapped,
+	 * it could be truncated and page->mapping reset to NULL at any moment.
+	 * Note also that we are relying on page_mapping(page) to set mapping
+	 * to &swapper_space when PageSwapCache(page).
 	 */
-	if ((!anon || PageSwapCache(page)) &&
+	if (mapping && !mapping_cap_account_dirty(mapping) &&
 	    page_test_and_clear_dirty(page_to_pfn(page), 1))
 		set_page_dirty(page);
 	/*
diff --git a/mm/shmem.c b/mm/shmem.c
index 2910f0d58c46..448956691e6b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -595,7 +595,7 @@ static void shmem_evict_inode(struct inode *inode)
 		kfree(xattr->name);
 		kfree(xattr);
 	}
-	BUG_ON(inode->i_blocks);
+	WARN_ON(inode->i_blocks);
 	shmem_free_inode(inode->i_sb);
 	end_writeback(inode);
 }
@@ -798,24 +798,28 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
 static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
 			struct shmem_inode_info *info, pgoff_t index)
 {
-	struct mempolicy mpol, *spol;
 	struct vm_area_struct pvma;
-
-	spol = mpol_cond_copy(&mpol,
-			mpol_shared_policy_lookup(&info->policy, index));
+	struct page *page;
 
 	/* Create a pseudo vma that just contains the policy */
 	pvma.vm_start = 0;
 	pvma.vm_pgoff = index;
 	pvma.vm_ops = NULL;
-	pvma.vm_policy = spol;
-	return swapin_readahead(swap, gfp, &pvma, 0);
+	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
+
+	page = swapin_readahead(swap, gfp, &pvma, 0);
+
+	/* Drop reference taken by mpol_shared_policy_lookup() */
+	mpol_cond_put(pvma.vm_policy);
+
+	return page;
 }
 
 static struct page *shmem_alloc_page(gfp_t gfp,
 			struct shmem_inode_info *info, pgoff_t index)
 {
 	struct vm_area_struct pvma;
+	struct page *page;
 
 	/* Create a pseudo vma that just contains the policy */
 	pvma.vm_start = 0;
@@ -823,10 +827,12 @@ static struct page *shmem_alloc_page(gfp_t gfp,
 	pvma.vm_ops = NULL;
 	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
 
-	/*
-	 * alloc_page_vma() will drop the shared policy reference
-	 */
-	return alloc_page_vma(gfp, &pvma, 0);
+	page = alloc_page_vma(gfp, &pvma, 0);
+
+	/* Drop reference taken by mpol_shared_policy_lookup() */
+	mpol_cond_put(pvma.vm_policy);
+
+	return page;
 }
 #else /* !CONFIG_NUMA */
 #ifdef CONFIG_TMPFS
@@ -2018,12 +2024,14 @@ static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
 {
 	struct inode *inode;
 	struct dentry *dentry = NULL;
-	u64 inum = fid->raw[2];
-	inum = (inum << 32) | fid->raw[1];
+	u64 inum;
 
 	if (fh_len < 3)
 		return NULL;
 
+	inum = fid->raw[2];
+	inum = (inum << 32) | fid->raw[1];
+
 	inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
 			shmem_match, fid->raw);
 	if (inode) {
@@ -2169,6 +2177,7 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
 	unsigned long inodes;
 	int error = -EINVAL;
 
+	config.mpol = NULL;
 	if (shmem_parse_options(data, &config, true))
 		return error;
 
@@ -2193,8 +2202,13 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
 	sbinfo->max_inodes  = config.max_inodes;
 	sbinfo->free_inodes = config.max_inodes - inodes;
 
-	mpol_put(sbinfo->mpol);
-	sbinfo->mpol        = config.mpol;	/* transfers initial ref */
+	/*
+	 * Preserve previous mempolicy unless mpol remount option was specified.
+	 */
+	if (config.mpol) {
+		mpol_put(sbinfo->mpol);
+		sbinfo->mpol = config.mpol;	/* transfers initial ref */
+	}
 out:
 	spin_unlock(&sbinfo->stat_lock);
 	return error;
diff --git a/mm/slab.c b/mm/slab.c
index e901a36e2520..da2bb689a008 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1685,9 +1685,6 @@ void __init kmem_cache_init_late(void)
 
 	g_cpucache_up = LATE;
 
-	/* Annotate slab for lockdep -- annotate the malloc caches */
-	init_lock_keys();
-
 	/* 6) resize the head arrays to their final sizes */
 	mutex_lock(&cache_chain_mutex);
 	list_for_each_entry(cachep, &cache_chain, next)
@@ -1695,6 +1692,9 @@ void __init kmem_cache_init_late(void)
 			BUG();
 	mutex_unlock(&cache_chain_mutex);
 
+	/* Annotate slab for lockdep -- annotate the malloc caches */
+	init_lock_keys();
+
 	/* Done! */
 	g_cpucache_up = FULL;
 
diff --git a/mm/sparse.c b/mm/sparse.c
index a8bc7d364deb..290dba25a7ed 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -619,7 +619,7 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 {
 	return; /* XXX: Not implemented yet */
 }
-static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
 {
 }
 #else
@@ -660,10 +660,11 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 			   get_order(sizeof(struct page) * nr_pages));
 }
 
-static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
 {
 	unsigned long maps_section_nr, removing_section_nr, i;
 	unsigned long magic;
+	struct page *page = virt_to_page(memmap);
 
 	for (i = 0; i < nr_pages; i++, page++) {
 		magic = (unsigned long) page->lru.next;
@@ -712,13 +713,10 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 	 */
 
 	if (memmap) {
-		struct page *memmap_page;
-		memmap_page = virt_to_page(memmap);
-
 		nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
 			>> PAGE_SHIFT;
 
-		free_map_bootmem(memmap_page, nr_pages);
+		free_map_bootmem(memmap, nr_pages);
 	}
 }
 
diff --git a/mm/truncate.c b/mm/truncate.c
index 61a183b89df6..4224627695ba 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -394,11 +394,12 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
 		return 0;
 
+	clear_page_mlock(page);
+
 	spin_lock_irq(&mapping->tree_lock);
 	if (PageDirty(page))
 		goto failed;
 
-	clear_page_mlock(page);
 	BUG_ON(page_has_private(page));
 	__delete_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index be5bc0af2e76..e6ca5051c021 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1983,10 +1983,10 @@ static void get_scan_count(struct mem_cgroup_zone *mz, struct scan_control *sc,
 	 * proportional to the fraction of recently scanned pages on
 	 * each list that were recently referenced and in active use.
 	 */
-	ap = (anon_prio + 1) * (reclaim_stat->recent_scanned[0] + 1);
+	ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1);
 	ap /= reclaim_stat->recent_rotated[0] + 1;
 
-	fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
+	fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
 	fp /= reclaim_stat->recent_rotated[1] + 1;
 	spin_unlock_irq(&mz->zone->lru_lock);
 
@@ -1999,7 +1999,7 @@ out:
 		unsigned long scan;
 
 		scan = zone_nr_lru_pages(mz, lru);
-		if (priority || noswap) {
+		if (priority || noswap || !vmscan_swappiness(mz, sc)) {
 			scan >>= priority;
 			if (!scan && force_scan)
 				scan = SWAP_CLUSTER_MAX;
@@ -3128,6 +3128,8 @@ static int kswapd(void *p)
 						&balanced_classzone_idx);
 		}
 	}
+
+	current->reclaim_state = NULL;
 	return 0;
 }