Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	Documentation/networking/ip-sysctl.txt
	drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

Both conflicts were simply overlapping context.

A build fix for qlcnic is in here too, simply removing the added
devinit annotations which no longer exist.

Signed-off-by: David S. Miller <davem@davemloft.net>

13 files changed, 163 insertions, 237 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 1324cd74faec..b93376c39b61 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -185,10 +185,23 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 
 	while (start < end) {
 		unsigned long *map, idx, vec;
+		unsigned shift;
 
 		map = bdata->node_bootmem_map;
 		idx = start - bdata->node_min_pfn;
+		shift = idx & (BITS_PER_LONG - 1);
+		/*
+		 * vec holds at most BITS_PER_LONG map bits,
+		 * bit 0 corresponds to start.
+		 */
 		vec = ~map[idx / BITS_PER_LONG];
+
+		if (shift) {
+			vec >>= shift;
+			if (end - start >= BITS_PER_LONG)
+				vec |= ~map[idx / BITS_PER_LONG + 1] <<
+					(BITS_PER_LONG - shift);
+		}
 		/*
 		 * If we have a properly aligned and fully unreserved
 		 * BITS_PER_LONG block of pages in front of us, free
@@ -201,19 +214,18 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 			count += BITS_PER_LONG;
 			start += BITS_PER_LONG;
 		} else {
-			unsigned long off = 0;
+			unsigned long cur = start;
 
-			vec >>= start & (BITS_PER_LONG - 1);
-			while (vec) {
+			start = ALIGN(start + 1, BITS_PER_LONG);
+			while (vec && cur != start) {
 				if (vec & 1) {
-					page = pfn_to_page(start + off);
+					page = pfn_to_page(cur);
 					__free_pages_bootmem(page, 0);
 					count++;
 				}
 				vec >>= 1;
-				off++;
+				++cur;
 			}
-			start = ALIGN(start + 1, BITS_PER_LONG);
 		}
 	}
 
diff --git a/mm/compaction.c b/mm/compaction.c
index 6b807e466497..c62bd063d766 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -816,6 +816,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 static int compact_finished(struct zone *zone,
 			    struct compact_control *cc)
 {
+	unsigned int order;
 	unsigned long watermark;
 
 	if (fatal_signal_pending(current))
@@ -850,22 +851,16 @@ static int compact_finished(struct zone *zone,
 		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
-	if (cc->page) {
-		/* Was a suitable page captured? */
-		if (*cc->page)
+	for (order = cc->order; order < MAX_ORDER; order++) {
+		struct free_area *area = &zone->free_area[order];
+
+		/* Job done if page is free of the right migratetype */
+		if (!list_empty(&area->free_list[cc->migratetype]))
+			return COMPACT_PARTIAL;
+
+		/* Job done if allocation would set block type */
+		if (cc->order >= pageblock_order && area->nr_free)
 			return COMPACT_PARTIAL;
-	} else {
-		unsigned int order;
-		for (order = cc->order; order < MAX_ORDER; order++) {
-			struct free_area *area = &zone->free_area[cc->order];
-			/* Job done if page is free of the right migratetype */
-			if (!list_empty(&area->free_list[cc->migratetype]))
-				return COMPACT_PARTIAL;
-
-			/* Job done if allocation would set block type */
-			if (cc->order >= pageblock_order && area->nr_free)
-				return COMPACT_PARTIAL;
-		}
 	}
 
 	return COMPACT_CONTINUE;
@@ -921,60 +916,6 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	return COMPACT_CONTINUE;
 }
 
-static void compact_capture_page(struct compact_control *cc)
-{
-	unsigned long flags;
-	int mtype, mtype_low, mtype_high;
-
-	if (!cc->page || *cc->page)
-		return;
-
-	/*
-	 * For MIGRATE_MOVABLE allocations we capture a suitable page ASAP
-	 * regardless of the migratetype of the freelist is is captured from.
-	 * This is fine because the order for a high-order MIGRATE_MOVABLE
-	 * allocation is typically at least a pageblock size and overall
-	 * fragmentation is not impaired. Other allocation types must
-	 * capture pages from their own migratelist because otherwise they
-	 * could pollute other pageblocks like MIGRATE_MOVABLE with
-	 * difficult to move pages and making fragmentation worse overall.
-	 */
-	if (cc->migratetype == MIGRATE_MOVABLE) {
-		mtype_low = 0;
-		mtype_high = MIGRATE_PCPTYPES;
-	} else {
-		mtype_low = cc->migratetype;
-		mtype_high = cc->migratetype + 1;
-	}
-
-	/* Speculatively examine the free lists without zone lock */
-	for (mtype = mtype_low; mtype < mtype_high; mtype++) {
-		int order;
-		for (order = cc->order; order < MAX_ORDER; order++) {
-			struct page *page;
-			struct free_area *area;
-			area = &(cc->zone->free_area[order]);
-			if (list_empty(&area->free_list[mtype]))
-				continue;
-
-			/* Take the lock and attempt capture of the page */
-			if (!compact_trylock_irqsave(&cc->zone->lock, &flags, cc))
-				return;
-			if (!list_empty(&area->free_list[mtype])) {
-				page = list_entry(area->free_list[mtype].next,
-							struct page, lru);
-				if (capture_free_page(page, cc->order, mtype)) {
-					spin_unlock_irqrestore(&cc->zone->lock,
-									flags);
-					*cc->page = page;
-					return;
-				}
-			}
-			spin_unlock_irqrestore(&cc->zone->lock, flags);
-		}
-	}
-}
-
 static int compact_zone(struct zone *zone, struct compact_control *cc)
 {
 	int ret;
@@ -1054,9 +995,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 				goto out;
 			}
 		}
-
-		/* Capture a page now if it is a suitable size */
-		compact_capture_page(cc);
 	}
 
 out:
@@ -1069,8 +1007,7 @@ out:
 
 static unsigned long compact_zone_order(struct zone *zone,
 				 int order, gfp_t gfp_mask,
-				 bool sync, bool *contended,
-				 struct page **page)
+				 bool sync, bool *contended)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1080,7 +1017,6 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
 		.sync = sync,
-		.page = page,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1110,7 +1046,7 @@ int sysctl_extfrag_threshold = 500;
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended, struct page **page)
+			bool sync, bool *contended)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1136,7 +1072,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		int status;
 
 		status = compact_zone_order(zone, order, gfp_mask, sync,
-						contended, page);
+						contended);
 		rc = max(status, rc);
 
 		/* If a normal allocation would succeed, stop compacting */
@@ -1192,7 +1128,6 @@ int compact_pgdat(pg_data_t *pgdat, int order)
 	struct compact_control cc = {
 		.order = order,
 		.sync = false,
-		.page = NULL,
 	};
 
 	return __compact_pgdat(pgdat, &cc);
@@ -1203,14 +1138,13 @@ static int compact_node(int nid)
 	struct compact_control cc = {
 		.order = -1,
 		.sync = true,
-		.page = NULL,
 	};
 
 	return __compact_pgdat(NODE_DATA(nid), &cc);
 }
 
 /* Compact all nodes in the system */
-static int compact_nodes(void)
+static void compact_nodes(void)
 {
 	int nid;
 
@@ -1219,8 +1153,6 @@ 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 */
@@ -1231,7 +1163,7 @@ 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/huge_memory.c b/mm/huge_memory.c
index 9e894edc7811..6001ee6347a9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1819,9 +1819,19 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(is_huge_zero_pfn(page_to_pfn(page)));
 	BUG_ON(!PageAnon(page));
-	anon_vma = page_lock_anon_vma_read(page);
+
+	/*
+	 * The caller does not necessarily hold an mmap_sem that would prevent
+	 * the anon_vma disappearing so we first we take a reference to it
+	 * and then lock the anon_vma for write. This is similar to
+	 * page_lock_anon_vma_read except the write lock is taken to serialise
+	 * against parallel split or collapse operations.
+	 */
+	anon_vma = page_get_anon_vma(page);
 	if (!anon_vma)
 		goto out;
+	anon_vma_lock_write(anon_vma);
+
 	ret = 0;
 	if (!PageCompound(page))
 		goto out_unlock;
@@ -1832,7 +1842,8 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(PageCompound(page));
 out_unlock:
-	page_unlock_anon_vma_read(anon_vma);
+	anon_vma_unlock(anon_vma);
+	put_anon_vma(anon_vma);
 out:
 	return ret;
 }
diff --git a/mm/internal.h b/mm/internal.h
index d597f94cc205..9ba21100ebf3 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -135,7 +135,6 @@ struct compact_control {
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
 	bool contended;			/* True if a lock was contended */
-	struct page **page;		/* Page captured of requested size */
 };
 
 unsigned long
diff --git a/mm/memblock.c b/mm/memblock.c
index 625905523c2a..88adc8afb610 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -314,7 +314,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
 		}
 
 		this->size += next->size;
-		memmove(next, next + 1, (type->cnt - (i + 1)) * sizeof(*next));
+		/* move forward from next + 1, index of which is i + 2 */
+		memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next));
 		type->cnt--;
 	}
 }
diff --git a/mm/memory.c b/mm/memory.c
index e0a9b0ce4f10..bb1369f7b9b4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -184,10 +184,14 @@ 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;
@@ -216,6 +220,7 @@ 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;
@@ -3706,6 +3711,14 @@ retry:
 		if (pmd_trans_huge(orig_pmd)) {
 			unsigned int dirty = flags & FAULT_FLAG_WRITE;
 
+			/*
+			 * If the pmd is splitting, return and retry the
+			 * the fault.  Alternative: wait until the split
+			 * is done, and goto retry.
+			 */
+			if (pmd_trans_splitting(orig_pmd))
+				return 0;
+
 			if (pmd_numa(orig_pmd))
 				return do_huge_pmd_numa_page(mm, vma, address,
 							     orig_pmd, pmd);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d1b315e98627..e2df1c1fb41f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2132,7 +2132,7 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
  */
 
 /* lookup first element intersecting start-end */
-/* Caller holds sp->mutex */
+/* Caller holds sp->lock */
 static struct sp_node *
 sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
 {
@@ -2196,13 +2196,13 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
 
 	if (!sp->root.rb_node)
 		return NULL;
-	mutex_lock(&sp->mutex);
+	spin_lock(&sp->lock);
 	sn = sp_lookup(sp, idx, idx+1);
 	if (sn) {
 		mpol_get(sn->policy);
 		pol = sn->policy;
 	}
-	mutex_unlock(&sp->mutex);
+	spin_unlock(&sp->lock);
 	return pol;
 }
 
@@ -2328,6 +2328,14 @@ static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 	sp_free(n);
 }
 
+static void sp_node_init(struct sp_node *node, unsigned long start,
+			unsigned long end, struct mempolicy *pol)
+{
+	node->start = start;
+	node->end = end;
+	node->policy = pol;
+}
+
 static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
 				struct mempolicy *pol)
 {
@@ -2344,10 +2352,7 @@ static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
 		return NULL;
 	}
 	newpol->flags |= MPOL_F_SHARED;
-
-	n->start = start;
-	n->end = end;
-	n->policy = newpol;
+	sp_node_init(n, start, end, newpol);
 
 	return n;
 }
@@ -2357,9 +2362,12 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 				 unsigned long end, struct sp_node *new)
 {
 	struct sp_node *n;
+	struct sp_node *n_new = NULL;
+	struct mempolicy *mpol_new = NULL;
 	int ret = 0;
 
-	mutex_lock(&sp->mutex);
+restart:
+	spin_lock(&sp->lock);
 	n = sp_lookup(sp, start, end);
 	/* Take care of old policies in the same range. */
 	while (n && n->start < end) {
@@ -2372,14 +2380,16 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 		} 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) {
-					ret = -ENOMEM;
-					goto out;
-				}
+				if (!n_new)
+					goto alloc_new;
+
+				*mpol_new = *n->policy;
+				atomic_set(&mpol_new->refcnt, 1);
+				sp_node_init(n_new, n->end, end, mpol_new);
+				sp_insert(sp, n_new);
 				n->end = start;
-				sp_insert(sp, new2);
+				n_new = NULL;
+				mpol_new = NULL;
 				break;
 			} else
 				n->end = start;
@@ -2390,9 +2400,27 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 	}
 	if (new)
 		sp_insert(sp, new);
-out:
-	mutex_unlock(&sp->mutex);
+	spin_unlock(&sp->lock);
+	ret = 0;
+
+err_out:
+	if (mpol_new)
+		mpol_put(mpol_new);
+	if (n_new)
+		kmem_cache_free(sn_cache, n_new);
+
 	return ret;
+
+alloc_new:
+	spin_unlock(&sp->lock);
+	ret = -ENOMEM;
+	n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL);
+	if (!n_new)
+		goto err_out;
+	mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
+	if (!mpol_new)
+		goto err_out;
+	goto restart;
 }
 
 /**
@@ -2410,7 +2438,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 	int ret;
 
 	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
-	mutex_init(&sp->mutex);
+	spin_lock_init(&sp->lock);
 
 	if (mpol) {
 		struct vm_area_struct pvma;
@@ -2476,14 +2504,14 @@ void mpol_free_shared_policy(struct shared_policy *p)
 
 	if (!p->root.rb_node)
 		return;
-	mutex_lock(&p->mutex);
+	spin_lock(&p->lock);
 	next = rb_first(&p->root);
 	while (next) {
 		n = rb_entry(next, struct sp_node, nd);
 		next = rb_next(&n->nd);
 		sp_delete(p, n);
 	}
-	mutex_unlock(&p->mutex);
+	spin_unlock(&p->lock);
 }
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -2595,8 +2623,7 @@ 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.
  */
 static const char * const policy_modes[] =
 {
@@ -2610,28 +2637,20 @@ 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
  *
  * 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)
 {
 	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, '=');
@@ -2719,24 +2738,23 @@ 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:
@@ -2756,13 +2774,12 @@ 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
  *
  * 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)
 {
 	char *p = buffer;
 	int l;
@@ -2788,7 +2805,7 @@ 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;
@@ -2796,10 +2813,7 @@ 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:
diff --git a/mm/migrate.c b/mm/migrate.c
index 3b676b0c5c3e..c38778610aa8 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1679,9 +1679,21 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	page_xchg_last_nid(new_page, page_last_nid(page));
 
 	isolated = numamigrate_isolate_page(pgdat, page);
-	if (!isolated) {
+
+	/*
+	 * Failing to isolate or a GUP pin prevents migration. The expected
+	 * page count is 2. 1 for anonymous pages without a mapping and 1
+	 * for the callers pin. If the page was isolated, the page will
+	 * need to be put back on the LRU.
+	 */
+	if (!isolated || page_count(page) != 2) {
 		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 		put_page(new_page);
+		if (isolated) {
+			putback_lru_page(page);
+			isolated = 0;
+			goto out;
+		}
 		goto out_keep_locked;
 	}
 
diff --git a/mm/mmap.c b/mm/mmap.c
index f54b235f29a9..35730ee9d515 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2886,7 +2886,7 @@ static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
 		 * The LSB of head.next can't change from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		down_write(&anon_vma->root->rwsem);
+		down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_sem);
 		/*
 		 * We can safely modify head.next after taking the
 		 * anon_vma->root->rwsem. If some other vma in this mm shares
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4ba5e37127fc..df2022ff0c8a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -221,11 +221,6 @@ EXPORT_SYMBOL(nr_online_nodes);
 
 int page_group_by_mobility_disabled __read_mostly;
 
-/*
- * NOTE:
- * Don't use set_pageblock_migratetype(page, MIGRATE_ISOLATE) directly.
- * Instead, use {un}set_pageblock_isolate.
- */
 void set_pageblock_migratetype(struct page *page, int migratetype)
 {
 
@@ -1389,14 +1384,8 @@ void split_page(struct page *page, unsigned int order)
 		set_page_refcounted(page + i);
 }
 
-/*
- * Similar to the split_page family of functions except that the page
- * required at the given order and being isolated now to prevent races
- * with parallel allocators
- */
-int capture_free_page(struct page *page, int alloc_order, int migratetype)
+static int __isolate_free_page(struct page *page, unsigned int order)
 {
-	unsigned int order;
 	unsigned long watermark;
 	struct zone *zone;
 	int mt;
@@ -1404,7 +1393,6 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 	BUG_ON(!PageBuddy(page));
 
 	zone = page_zone(page);
-	order = page_order(page);
 	mt = get_pageblock_migratetype(page);
 
 	if (mt != MIGRATE_ISOLATE) {
@@ -1413,7 +1401,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
 			return 0;
 
-		__mod_zone_freepage_state(zone, -(1UL << alloc_order), mt);
+		__mod_zone_freepage_state(zone, -(1UL << order), mt);
 	}
 
 	/* Remove page from free list */
@@ -1421,11 +1409,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 	zone->free_area[order].nr_free--;
 	rmv_page_order(page);
 
-	if (alloc_order != order)
-		expand(zone, page, alloc_order, order,
-			&zone->free_area[order], migratetype);
-
-	/* Set the pageblock if the captured page is at least a pageblock */
+	/* Set the pageblock if the isolated page is at least a pageblock */
 	if (order >= pageblock_order - 1) {
 		struct page *endpage = page + (1 << order) - 1;
 		for (; page < endpage; page += pageblock_nr_pages) {
@@ -1436,7 +1420,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 		}
 	}
 
-	return 1UL << alloc_order;
+	return 1UL << order;
 }
 
 /*
@@ -1454,10 +1438,9 @@ int split_free_page(struct page *page)
 	unsigned int order;
 	int nr_pages;
 
-	BUG_ON(!PageBuddy(page));
 	order = page_order(page);
 
-	nr_pages = capture_free_page(page, order, 0);
+	nr_pages = __isolate_free_page(page, order);
 	if (!nr_pages)
 		return 0;
 
@@ -1655,20 +1638,6 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	return true;
 }
 
-#ifdef CONFIG_MEMORY_ISOLATION
-static inline unsigned long nr_zone_isolate_freepages(struct zone *zone)
-{
-	if (unlikely(zone->nr_pageblock_isolate))
-		return zone->nr_pageblock_isolate * pageblock_nr_pages;
-	return 0;
-}
-#else
-static inline unsigned long nr_zone_isolate_freepages(struct zone *zone)
-{
-	return 0;
-}
-#endif
-
 bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 		      int classzone_idx, int alloc_flags)
 {
@@ -1684,14 +1653,6 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
 	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
 		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
 
-	/*
-	 * If the zone has MIGRATE_ISOLATE type free pages, we should consider
-	 * it.  nr_zone_isolate_freepages is never accurate so kswapd might not
-	 * sleep although it could do so.  But this is more desirable for memory
-	 * hotplug than sleeping which can cause a livelock in the direct
-	 * reclaim path.
-	 */
-	free_pages -= nr_zone_isolate_freepages(z);
 	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
 								free_pages);
 }
@@ -2163,8 +2124,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
-	struct page *page = NULL;
-
 	if (!order)
 		return NULL;
 
@@ -2176,16 +2135,12 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, sync_migration,
-						contended_compaction, &page);
+						contended_compaction);
 	current->flags &= ~PF_MEMALLOC;
 
-	/* If compaction captured a page, prep and use it */
-	if (page) {
-		prep_new_page(page, order, gfp_mask);
-		goto got_page;
-	}
-
 	if (*did_some_progress != COMPACT_SKIPPED) {
+		struct page *page;
+
 		/* Page migration frees to the PCP lists but we want merging */
 		drain_pages(get_cpu());
 		put_cpu();
@@ -2195,7 +2150,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 				alloc_flags & ~ALLOC_NO_WATERMARKS,
 				preferred_zone, migratetype);
 		if (page) {
-got_page:
 			preferred_zone->compact_blockskip_flush = false;
 			preferred_zone->compact_considered = 0;
 			preferred_zone->compact_defer_shift = 0;
@@ -5631,7 +5585,7 @@ 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/page_isolation.c b/mm/page_isolation.c
index 9d2264ea4606..383bdbb98b04 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -8,28 +8,6 @@
 #include <linux/memory.h>
 #include "internal.h"
 
-/* called while holding zone->lock */
-static void set_pageblock_isolate(struct page *page)
-{
-	if (get_pageblock_migratetype(page) == MIGRATE_ISOLATE)
-		return;
-
-	set_pageblock_migratetype(page, MIGRATE_ISOLATE);
-	page_zone(page)->nr_pageblock_isolate++;
-}
-
-/* called while holding zone->lock */
-static void restore_pageblock_isolate(struct page *page, int migratetype)
-{
-	struct zone *zone = page_zone(page);
-	if (WARN_ON(get_pageblock_migratetype(page) != MIGRATE_ISOLATE))
-		return;
-
-	BUG_ON(zone->nr_pageblock_isolate <= 0);
-	set_pageblock_migratetype(page, migratetype);
-	zone->nr_pageblock_isolate--;
-}
-
 int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
 {
 	struct zone *zone;
@@ -80,7 +58,7 @@ out:
 		unsigned long nr_pages;
 		int migratetype = get_pageblock_migratetype(page);
 
-		set_pageblock_isolate(page);
+		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
 		nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE);
 
 		__mod_zone_freepage_state(zone, -nr_pages, migratetype);
@@ -103,7 +81,7 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 		goto out;
 	nr_pages = move_freepages_block(zone, page, migratetype);
 	__mod_zone_freepage_state(zone, nr_pages, migratetype);
-	restore_pageblock_isolate(page, migratetype);
+	set_pageblock_migratetype(page, migratetype);
 out:
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index 5c90d84c2b02..5dd56f6efdbd 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -889,7 +889,7 @@ static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
 	if (!mpol || mpol->mode == MPOL_DEFAULT)
 		return;		/* show nothing */
 
-	mpol_to_str(buffer, sizeof(buffer), mpol, 1);
+	mpol_to_str(buffer, sizeof(buffer), mpol);
 
 	seq_printf(seq, ",mpol=%s", buffer);
 }
@@ -2463,7 +2463,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
 			if (!gid_valid(sbinfo->gid))
 				goto bad_val;
 		} else if (!strcmp(this_char,"mpol")) {
-			if (mpol_parse_str(value, &sbinfo->mpol, 1))
+			if (mpol_parse_str(value, &sbinfo->mpol))
 				goto bad_val;
 		} else {
 			printk(KERN_ERR "tmpfs: Bad mount option %s\n",
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 23291b9ae871..196709f5ee58 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2775,7 +2775,7 @@ loop_again:
 		if (total_scanned && (sc.priority < DEF_PRIORITY - 2)) {
 			if (has_under_min_watermark_zone)
 				count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
-			else
+			else if (unbalanced_zone)
 				wait_iff_congested(unbalanced_zone, BLK_RW_ASYNC, HZ/10);
 		}
 
@@ -3122,8 +3122,8 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
    not required for correctness.  So if the last cpu in a node goes
    away, we get changed to run anywhere: as the first one comes back,
    restore their cpu bindings. */
-static int __devinit cpu_callback(struct notifier_block *nfb,
-				  unsigned long action, void *hcpu)
+static int cpu_callback(struct notifier_block *nfb, unsigned long action,
+			void *hcpu)
 {
 	int nid;