Merge branch 'linus' into tracing/blktrace

Conflicts:
	block/blktrace.c

Semantic merge:
	kernel/trace/blktrace.c

Signed-off-by: Ingo Molnar <mingo@elte.hu>

29 files changed, 322 insertions, 147 deletions

diff --git a/fs/bio.c b/fs/bio.c
index 062299acbcc..72ab251cdb9 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -302,9 +302,10 @@ void bio_init(struct bio *bio)
 struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 {
 	struct bio *bio = NULL;
+	void *p;
 
 	if (bs) {
-		void *p = mempool_alloc(bs->bio_pool, gfp_mask);
+		p = mempool_alloc(bs->bio_pool, gfp_mask);
 
 		if (p)
 			bio = p + bs->front_pad;
@@ -329,7 +330,7 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 			}
 			if (unlikely(!bvl)) {
 				if (bs)
-					mempool_free(bio, bs->bio_pool);
+					mempool_free(p, bs->bio_pool);
 				else
 					kfree(bio);
 				bio = NULL;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 35443cc4b9a..42491d728e9 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -38,19 +38,12 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
 static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		   struct btrfs_path *path, int level, int slot);
 
-inline void btrfs_init_path(struct btrfs_path *p)
-{
-	memset(p, 0, sizeof(*p));
-}
-
 struct btrfs_path *btrfs_alloc_path(void)
 {
 	struct btrfs_path *path;
-	path = kmem_cache_alloc(btrfs_path_cachep, GFP_NOFS);
-	if (path) {
-		btrfs_init_path(path);
+	path = kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
+	if (path)
 		path->reada = 1;
-	}
 	return path;
 }
 
@@ -69,14 +62,38 @@ noinline void btrfs_set_path_blocking(struct btrfs_path *p)
 
 /*
  * reset all the locked nodes in the patch to spinning locks.
+ *
+ * held is used to keep lockdep happy, when lockdep is enabled
+ * we set held to a blocking lock before we go around and
+ * retake all the spinlocks in the path.  You can safely use NULL
+ * for held
  */
-noinline void btrfs_clear_path_blocking(struct btrfs_path *p)
+noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
+					struct extent_buffer *held)
 {
 	int i;
-	for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/* lockdep really cares that we take all of these spinlocks
+	 * in the right order.  If any of the locks in the path are not
+	 * currently blocking, it is going to complain.  So, make really
+	 * really sure by forcing the path to blocking before we clear
+	 * the path blocking.
+	 */
+	if (held)
+		btrfs_set_lock_blocking(held);
+	btrfs_set_path_blocking(p);
+#endif
+
+	for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) {
 		if (p->nodes[i] && p->locks[i])
 			btrfs_clear_lock_blocking(p->nodes[i]);
 	}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (held)
+		btrfs_clear_lock_blocking(held);
+#endif
 }
 
 /* this also releases the path */
@@ -286,7 +303,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 						  trans->transid, level, &ins);
 		BUG_ON(ret);
 		cow = btrfs_init_new_buffer(trans, root, prealloc_dest,
-					    buf->len);
+					    buf->len, level);
 	} else {
 		cow = btrfs_alloc_free_block(trans, root, buf->len,
 					     parent_start,
@@ -917,9 +934,9 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 		/* promote the child to a root */
 		child = read_node_slot(root, mid, 0);
+		BUG_ON(!child);
 		btrfs_tree_lock(child);
 		btrfs_set_lock_blocking(child);
-		BUG_ON(!child);
 		ret = btrfs_cow_block(trans, root, child, mid, 0, &child, 0);
 		BUG_ON(ret);
 
@@ -1566,7 +1583,7 @@ cow_done:
 		if (!p->skip_locking)
 			p->locks[level] = 1;
 
-		btrfs_clear_path_blocking(p);
+		btrfs_clear_path_blocking(p, NULL);
 
 		/*
 		 * we have a lock on b and as long as we aren't changing
@@ -1605,7 +1622,7 @@ cow_done:
 
 				btrfs_set_path_blocking(p);
 				sret = split_node(trans, root, p, level);
-				btrfs_clear_path_blocking(p);
+				btrfs_clear_path_blocking(p, NULL);
 
 				BUG_ON(sret > 0);
 				if (sret) {
@@ -1625,7 +1642,7 @@ cow_done:
 
 				btrfs_set_path_blocking(p);
 				sret = balance_level(trans, root, p, level);
-				btrfs_clear_path_blocking(p);
+				btrfs_clear_path_blocking(p, NULL);
 
 				if (sret) {
 					ret = sret;
@@ -1688,13 +1705,13 @@ cow_done:
 			if (!p->skip_locking) {
 				int lret;
 
-				btrfs_clear_path_blocking(p);
+				btrfs_clear_path_blocking(p, NULL);
 				lret = btrfs_try_spin_lock(b);
 
 				if (!lret) {
 					btrfs_set_path_blocking(p);
 					btrfs_tree_lock(b);
-					btrfs_clear_path_blocking(p);
+					btrfs_clear_path_blocking(p, b);
 				}
 			}
 		} else {
@@ -1706,7 +1723,7 @@ cow_done:
 				btrfs_set_path_blocking(p);
 				sret = split_leaf(trans, root, key,
 						      p, ins_len, ret == 0);
-				btrfs_clear_path_blocking(p);
+				btrfs_clear_path_blocking(p, NULL);
 
 				BUG_ON(sret > 0);
 				if (sret) {
@@ -3926,7 +3943,6 @@ find_next_key:
 				btrfs_release_path(root, path);
 				goto again;
 			} else {
-				btrfs_clear_path_blocking(path);
 				goto out;
 			}
 		}
@@ -3946,7 +3962,7 @@ find_next_key:
 		path->locks[level - 1] = 1;
 		path->nodes[level - 1] = cur;
 		unlock_up(path, level, 1);
-		btrfs_clear_path_blocking(path);
+		btrfs_clear_path_blocking(path, NULL);
 	}
 out:
 	if (ret == 0)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 531db112c8b..766b31ae318 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -43,11 +43,7 @@ struct btrfs_ordered_sum;
 
 #define BTRFS_ACL_NOT_CACHED    ((void *)-1)
 
-#ifdef CONFIG_LOCKDEP
-# define BTRFS_MAX_LEVEL 7
-#else
-# define BTRFS_MAX_LEVEL 8
-#endif
+#define BTRFS_MAX_LEVEL 8
 
 /* holds pointers to all of the tree roots */
 #define BTRFS_ROOT_TREE_OBJECTID 1ULL
@@ -1715,7 +1711,8 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 					     u64 empty_size);
 struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
 					    struct btrfs_root *root,
-					    u64 bytenr, u32 blocksize);
+					    u64 bytenr, u32 blocksize,
+					    int level);
 int btrfs_alloc_extent(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root,
 		       u64 num_bytes, u64 parent, u64 min_bytes,
@@ -1834,9 +1831,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 void btrfs_release_path(struct btrfs_root *root, struct btrfs_path *p);
 struct btrfs_path *btrfs_alloc_path(void);
 void btrfs_free_path(struct btrfs_path *p);
-void btrfs_init_path(struct btrfs_path *p);
 void btrfs_set_path_blocking(struct btrfs_path *p);
-void btrfs_clear_path_blocking(struct btrfs_path *p);
 void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
 
 int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 5aebddd7119..adda739a021 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -75,6 +75,40 @@ struct async_submit_bio {
 	struct btrfs_work work;
 };
 
+/* These are used to set the lockdep class on the extent buffer locks.
+ * The class is set by the readpage_end_io_hook after the buffer has
+ * passed csum validation but before the pages are unlocked.
+ *
+ * The lockdep class is also set by btrfs_init_new_buffer on freshly
+ * allocated blocks.
+ *
+ * The class is based on the level in the tree block, which allows lockdep
+ * to know that lower nodes nest inside the locks of higher nodes.
+ *
+ * We also add a check to make sure the highest level of the tree is
+ * the same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this
+ * code needs update as well.
+ */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# if BTRFS_MAX_LEVEL != 8
+#  error
+# endif
+static struct lock_class_key btrfs_eb_class[BTRFS_MAX_LEVEL + 1];
+static const char *btrfs_eb_name[BTRFS_MAX_LEVEL + 1] = {
+	/* leaf */
+	"btrfs-extent-00",
+	"btrfs-extent-01",
+	"btrfs-extent-02",
+	"btrfs-extent-03",
+	"btrfs-extent-04",
+	"btrfs-extent-05",
+	"btrfs-extent-06",
+	"btrfs-extent-07",
+	/* highest possible level */
+	"btrfs-extent-08",
+};
+#endif
+
 /*
  * extents on the btree inode are pretty simple, there's one extent
  * that covers the entire device
@@ -347,6 +381,15 @@ static int check_tree_block_fsid(struct btrfs_root *root,
 	return ret;
 }
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void btrfs_set_buffer_lockdep_class(struct extent_buffer *eb, int level)
+{
+	lockdep_set_class_and_name(&eb->lock,
+			   &btrfs_eb_class[level],
+			   btrfs_eb_name[level]);
+}
+#endif
+
 static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 			       struct extent_state *state)
 {
@@ -392,6 +435,8 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 	}
 	found_level = btrfs_header_level(eb);
 
+	btrfs_set_buffer_lockdep_class(eb, found_level);
+
 	ret = csum_tree_block(root, eb, 1);
 	if (ret)
 		ret = -EIO;
@@ -1777,7 +1822,6 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	ret = find_and_setup_root(tree_root, fs_info,
 				  BTRFS_DEV_TREE_OBJECTID, dev_root);
 	dev_root->track_dirty = 1;
-
 	if (ret)
 		goto fail_extent_root;
 
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 494a56eb298..95029db227b 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -101,4 +101,14 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
 int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root);
 int btree_lock_page_hook(struct page *page);
+
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void btrfs_set_buffer_lockdep_class(struct extent_buffer *eb, int level);
+#else
+static inline void btrfs_set_buffer_lockdep_class(struct extent_buffer *eb,
+						 int level)
+{
+}
+#endif
 #endif
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 7527523c2d2..0a5d796c9f7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1323,8 +1323,25 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 int btrfs_extent_post_op(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root)
 {
-	finish_current_insert(trans, root->fs_info->extent_root, 1);
-	del_pending_extents(trans, root->fs_info->extent_root, 1);
+	u64 start;
+	u64 end;
+	int ret;
+
+	while(1) {
+		finish_current_insert(trans, root->fs_info->extent_root, 1);
+		del_pending_extents(trans, root->fs_info->extent_root, 1);
+
+		/* is there more work to do? */
+		ret = find_first_extent_bit(&root->fs_info->pending_del,
+					    0, &start, &end, EXTENT_WRITEBACK);
+		if (!ret)
+			continue;
+		ret = find_first_extent_bit(&root->fs_info->extent_ins,
+					    0, &start, &end, EXTENT_WRITEBACK);
+		if (!ret)
+			continue;
+		break;
+	}
 	return 0;
 }
 
@@ -2211,13 +2228,12 @@ static int finish_current_insert(struct btrfs_trans_handle *trans,
 	u64 end;
 	u64 priv;
 	u64 search = 0;
-	u64 skipped = 0;
 	struct btrfs_fs_info *info = extent_root->fs_info;
 	struct btrfs_path *path;
 	struct pending_extent_op *extent_op, *tmp;
 	struct list_head insert_list, update_list;
 	int ret;
-	int num_inserts = 0, max_inserts;
+	int num_inserts = 0, max_inserts, restart = 0;
 
 	path = btrfs_alloc_path();
 	INIT_LIST_HEAD(&insert_list);
@@ -2233,19 +2249,19 @@ again:
 		ret = find_first_extent_bit(&info->extent_ins, search, &start,
 					    &end, EXTENT_WRITEBACK);
 		if (ret) {
-			if (skipped && all && !num_inserts &&
+			if (restart && !num_inserts &&
 			    list_empty(&update_list)) {
-				skipped = 0;
+				restart = 0;
 				search = 0;
 				continue;
 			}
-			mutex_unlock(&info->extent_ins_mutex);
 			break;
 		}
 
 		ret = try_lock_extent(&info->extent_ins, start, end, GFP_NOFS);
 		if (!ret) {
-			skipped = 1;
+			if (all)
+				restart = 1;
 			search = end + 1;
 			if (need_resched()) {
 				mutex_unlock(&info->extent_ins_mutex);
@@ -2264,7 +2280,7 @@ again:
 			list_add_tail(&extent_op->list, &insert_list);
 			search = end + 1;
 			if (num_inserts == max_inserts) {
-				mutex_unlock(&info->extent_ins_mutex);
+				restart = 1;
 				break;
 			}
 		} else if (extent_op->type == PENDING_BACKREF_UPDATE) {
@@ -2280,7 +2296,6 @@ again:
 	 * somebody marked this thing for deletion then just unlock it and be
 	 * done, the free_extents will handle it
 	 */
-	mutex_lock(&info->extent_ins_mutex);
 	list_for_each_entry_safe(extent_op, tmp, &update_list, list) {
 		clear_extent_bits(&info->extent_ins, extent_op->bytenr,
 				  extent_op->bytenr + extent_op->num_bytes - 1,
@@ -2302,6 +2317,10 @@ again:
 	if (!list_empty(&update_list)) {
 		ret = update_backrefs(trans, extent_root, path, &update_list);
 		BUG_ON(ret);
+
+		/* we may have COW'ed new blocks, so lets start over */
+		if (all)
+			restart = 1;
 	}
 
 	/*
@@ -2309,9 +2328,9 @@ again:
 	 * need to make sure everything is cleaned then reset everything and
 	 * go back to the beginning
 	 */
-	if (!num_inserts && all && skipped) {
+	if (!num_inserts && restart) {
 		search = 0;
-		skipped = 0;
+		restart = 0;
 		INIT_LIST_HEAD(&update_list);
 		INIT_LIST_HEAD(&insert_list);
 		goto again;
@@ -2368,27 +2387,19 @@ again:
 	BUG_ON(ret);
 
 	/*
-	 * if we broke out of the loop in order to insert stuff because we hit
-	 * the maximum number of inserts at a time we can handle, then loop
-	 * back and pick up where we left off
+	 * if restart is set for whatever reason we need to go back and start
+	 * searching through the pending list again.
+	 *
+	 * We just inserted some extents, which could have resulted in new
+	 * blocks being allocated, which would result in new blocks needing
+	 * updates, so if all is set we _must_ restart to get the updated
+	 * blocks.
 	 */
-	if (num_inserts == max_inserts) {
-		INIT_LIST_HEAD(&insert_list);
-		INIT_LIST_HEAD(&update_list);
-		num_inserts = 0;
-		goto again;
-	}
-
-	/*
-	 * again, if we need to make absolutely sure there are no more pending
-	 * extent operations left and we know that we skipped some, go back to
-	 * the beginning and do it all again
-	 */
-	if (all && skipped) {
+	if (restart || all) {
 		INIT_LIST_HEAD(&insert_list);
 		INIT_LIST_HEAD(&update_list);
 		search = 0;
-		skipped = 0;
+		restart = 0;
 		num_inserts = 0;
 		goto again;
 	}
@@ -2709,6 +2720,8 @@ again:
 		goto again;
 	}
 
+	if (!err)
+		finish_current_insert(trans, extent_root, 0);
 	return err;
 }
 
@@ -2859,7 +2872,8 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 
 	if (data & BTRFS_BLOCK_GROUP_METADATA) {
 		last_ptr = &root->fs_info->last_alloc;
-		empty_cluster = 64 * 1024;
+		if (!btrfs_test_opt(root, SSD))
+			empty_cluster = 64 * 1024;
 	}
 
 	if ((data & BTRFS_BLOCK_GROUP_DATA) && btrfs_test_opt(root, SSD))
@@ -3402,7 +3416,8 @@ int btrfs_alloc_extent(struct btrfs_trans_handle *trans,
 
 struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
 					    struct btrfs_root *root,
-					    u64 bytenr, u32 blocksize)
+					    u64 bytenr, u32 blocksize,
+					    int level)
 {
 	struct extent_buffer *buf;
 
@@ -3410,6 +3425,7 @@ struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
 	btrfs_set_header_generation(buf, trans->transid);
+	btrfs_set_buffer_lockdep_class(buf, level);
 	btrfs_tree_lock(buf);
 	clean_tree_block(trans, root, buf);
 
@@ -3453,7 +3469,8 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 		return ERR_PTR(ret);
 	}
 
-	buf = btrfs_init_new_buffer(trans, root, ins.objectid, blocksize);
+	buf = btrfs_init_new_buffer(trans, root, ins.objectid,
+				    blocksize, level);
 	return buf;
 }
 
@@ -5641,7 +5658,9 @@ static noinline int relocate_one_extent(struct btrfs_root *extent_root,
 			prev_block = block_start;
 		}
 
+		mutex_lock(&extent_root->fs_info->trans_mutex);
 		btrfs_record_root_in_trans(found_root);
+		mutex_unlock(&extent_root->fs_info->trans_mutex);
 		if (ref_path->owner_objectid >= BTRFS_FIRST_FREE_OBJECTID) {
 			/*
 			 * try to update data extent references while
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 37d43b516b7..ebe6b29e606 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -415,8 +415,6 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig,
 
 	node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node);
 	if (node) {
-		struct extent_state *found;
-		found = rb_entry(node, struct extent_state, rb_node);
 		free_extent_state(prealloc);
 		return -EEXIST;
 	}
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 2aa79873eb4..cc7334d833c 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -84,7 +84,6 @@ int btrfs_find_free_objectid(struct btrfs_trans_handle *trans,
 	search_key.type = 0;
 	search_key.offset = 0;
 
-	btrfs_init_path(path);
 	start_found = 0;
 	ret = btrfs_search_slot(trans, root, &search_key, path, 0, 0);
 	if (ret < 0)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8f0706210a4..3cee77ae03c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2531,8 +2531,6 @@ noinline int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	key.offset = (u64)-1;
 	key.type = (u8)-1;
 
-	btrfs_init_path(path);
-
 search_again:
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret < 0)
@@ -4263,7 +4261,7 @@ static int btrfs_releasepage(struct page *page, gfp_t gfp_flags)
 {
 	if (PageWriteback(page) || PageDirty(page))
 		return 0;
-	return __btrfs_releasepage(page, gfp_flags);
+	return __btrfs_releasepage(page, gfp_flags & GFP_NOFS);
 }
 
 static void btrfs_invalidatepage(struct page *page, unsigned long offset)
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 9ebe9385129..85506c4a3af 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -25,21 +25,10 @@
 #include "extent_io.h"
 #include "locking.h"
 
-/*
- * btrfs_header_level() isn't free, so don't call it when lockdep isn't
- * on
- */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static inline void spin_nested(struct extent_buffer *eb)
-{
-	spin_lock_nested(&eb->lock, BTRFS_MAX_LEVEL - btrfs_header_level(eb));
-}
-#else
 static inline void spin_nested(struct extent_buffer *eb)
 {
 	spin_lock(&eb->lock);
 }
-#endif
 
 /*
  * Setting a lock to blocking will drop the spinlock and set the
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f3fd7e2cbc3..19a4daf03cc 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -379,7 +379,6 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 	btrfs_start_delalloc_inodes(root);
 	btrfs_wait_ordered_extents(root, 0);
 
-	btrfs_clean_old_snapshots(root);
 	trans = btrfs_start_transaction(root, 1);
 	ret = btrfs_commit_transaction(trans, root);
 	sb->s_dirt = 0;
@@ -511,6 +510,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	struct btrfs_root *root = btrfs_sb(sb);
 	int ret;
 
+	ret = btrfs_parse_options(root, data);
+	if (ret)
+		return -EINVAL;
+
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
 
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 919172de5c9..4112d53d4f4 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -688,7 +688,9 @@ static noinline int drop_dirty_roots(struct btrfs_root *tree_root,
 		num_bytes -= btrfs_root_used(&dirty->root->root_item);
 		bytes_used = btrfs_root_used(&root->root_item);
 		if (num_bytes) {
+			mutex_lock(&root->fs_info->trans_mutex);
 			btrfs_record_root_in_trans(root);
+			mutex_unlock(&root->fs_info->trans_mutex);
 			btrfs_set_root_used(&root->root_item,
 					    bytes_used - num_bytes);
 		}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 20794290256..9c462fbd60f 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2832,7 +2832,9 @@ again:
 		BUG_ON(!wc.replay_dest);
 
 		wc.replay_dest->log_root = log;
+		mutex_lock(&fs_info->trans_mutex);
 		btrfs_record_root_in_trans(wc.replay_dest);
+		mutex_unlock(&fs_info->trans_mutex);
 		ret = walk_log_tree(trans, log, &wc);
 		BUG_ON(ret);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bcd14ebccae..1316139bf9e 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2894,10 +2894,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 		free_extent_map(em);
 	}
 
-	map = kzalloc(sizeof(*map), GFP_NOFS);
-	if (!map)
-		return -ENOMEM;
-
 	em = alloc_extent_map(GFP_NOFS);
 	if (!em)
 		return -ENOMEM;
@@ -3106,6 +3102,8 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	if (!sb)
 		return -ENOMEM;
 	btrfs_set_buffer_uptodate(sb);
+	btrfs_set_buffer_lockdep_class(sb, 0);
+
 	write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
 	array_size = btrfs_super_sys_array_size(super_copy);
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 665d446b25b..9f697419ed8 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -777,6 +777,7 @@ static int __set_page_dirty(struct page *page,
 			__inc_zone_page_state(page, NR_FILE_DIRTY);
 			__inc_bdi_stat(mapping->backing_dev_info,
 					BDI_RECLAIMABLE);
+			task_dirty_inc(current);
 			task_io_account_write(PAGE_CACHE_SIZE);
 		}
 		radix_tree_tag_set(&mapping->page_tree,
@@ -3108,7 +3109,7 @@ int sync_dirty_buffer(struct buffer_head *bh)
 	if (test_clear_buffer_dirty(bh)) {
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
-		ret = submit_bh(WRITE_SYNC, bh);
+		ret = submit_bh(WRITE, bh);
 		wait_on_buffer(bh);
 		if (buffer_eopnotsupp(bh)) {
 			clear_buffer_eopnotsupp(bh);
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 9c6d815dd19..39bd4d38e88 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1938,6 +1938,8 @@ ULONG_IOCTL(SET_BITMAP_FILE)
 /* Big K */
 COMPATIBLE_IOCTL(PIO_FONT)
 COMPATIBLE_IOCTL(GIO_FONT)
+COMPATIBLE_IOCTL(PIO_CMAP)
+COMPATIBLE_IOCTL(GIO_CMAP)
 ULONG_IOCTL(KDSIGACCEPT)
 COMPATIBLE_IOCTL(KDGETKEYCODE)
 COMPATIBLE_IOCTL(KDSETKEYCODE)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index aafc9eba1c2..b0c87dce66a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -868,7 +868,7 @@ static inline unsigned ext4_rec_len_from_disk(__le16 dlen)
 {
 	unsigned len = le16_to_cpu(dlen);
 
-	if (len == EXT4_MAX_REC_LEN)
+	if (len == EXT4_MAX_REC_LEN || len == 0)
 		return 1 << 16;
 	return len;
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 03ba20be132..cbd2ca99d11 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -47,8 +47,10 @@
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
 					      loff_t new_size)
 {
-	return jbd2_journal_begin_ordered_truncate(&EXT4_I(inode)->jinode,
-						   new_size);
+	return jbd2_journal_begin_ordered_truncate(
+					EXT4_SB(inode->i_sb)->s_journal,
+					&EXT4_I(inode)->jinode,
+					new_size);
 }
 
 static void ext4_invalidatepage(struct page *page, unsigned long offset);
@@ -2437,6 +2439,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	int no_nrwrite_index_update;
 	int pages_written = 0;
 	long pages_skipped;
+	int range_cyclic, cycled = 1, io_done = 0;
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
@@ -2488,9 +2491,15 @@ static int ext4_da_writepages(struct address_space *mapping,
 	if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 		range_whole = 1;
 
-	if (wbc->range_cyclic)
+	range_cyclic = wbc->range_cyclic;
+	if (wbc->range_cyclic) {
 		index = mapping->writeback_index;
-	else
+		if (index)
+			cycled = 0;
+		wbc->range_start = index << PAGE_CACHE_SHIFT;
+		wbc->range_end  = LLONG_MAX;
+		wbc->range_cyclic = 0;
+	} else
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 
 	mpd.wbc = wbc;
@@ -2504,6 +2513,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	wbc->no_nrwrite_index_update = 1;
 	pages_skipped = wbc->pages_skipped;
 
+retry:
 	while (!ret && wbc->nr_to_write > 0) {
 
 		/*
@@ -2546,6 +2556,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 			pages_written += mpd.pages_written;
 			wbc->pages_skipped = pages_skipped;
 			ret = 0;
+			io_done = 1;
 		} else if (wbc->nr_to_write)
 			/*
 			 * There is no more writeout needed
@@ -2554,6 +2565,13 @@ static int ext4_da_writepages(struct address_space *mapping,
 			 */
 			break;
 	}
+	if (!io_done && !cycled) {
+		cycled = 1;
+		index = 0;
+		wbc->range_start = index << PAGE_CACHE_SHIFT;
+		wbc->range_end  = mapping->writeback_index - 1;
+		goto retry;
+	}
 	if (pages_skipped != wbc->pages_skipped)
 		printk(KERN_EMERG "This should not happen leaving %s "
 				"with nr_to_write = %ld ret = %d\n",
@@ -2561,6 +2579,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 
 	/* Update index */
 	index += pages_written;
+	wbc->range_cyclic = range_cyclic;
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
 		/*
 		 * set the writeback_index so that range_cyclic
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index deba54f6cbe..4415beeb0b6 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3693,6 +3693,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 	pa->pa_free = pa->pa_len;
 	atomic_set(&pa->pa_count, 1);
 	spin_lock_init(&pa->pa_lock);
+	INIT_LIST_HEAD(&pa->pa_inode_list);
+	INIT_LIST_HEAD(&pa->pa_group_list);
 	pa->pa_deleted = 0;
 	pa->pa_linear = 0;
 
@@ -3755,6 +3757,7 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
 	atomic_set(&pa->pa_count, 1);
 	spin_lock_init(&pa->pa_lock);
 	INIT_LIST_HEAD(&pa->pa_inode_list);
+	INIT_LIST_HEAD(&pa->pa_group_list);
 	pa->pa_deleted = 0;
 	pa->pa_linear = 1;
 
@@ -4476,23 +4479,26 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 			pa->pa_free -= ac->ac_b_ex.fe_len;
 			pa->pa_len -= ac->ac_b_ex.fe_len;
 			spin_unlock(&pa->pa_lock);
-			/*
-			 * We want to add the pa to the right bucket.
-			 * Remove it from the list and while adding
-			 * make sure the list to which we are adding
-			 * doesn't grow big.
-			 */
-			if (likely(pa->pa_free)) {
-				spin_lock(pa->pa_obj_lock);
-				list_del_rcu(&pa->pa_inode_list);
-				spin_unlock(pa->pa_obj_lock);
-				ext4_mb_add_n_trim(ac);
-			}
 		}
-		ext4_mb_put_pa(ac, ac->ac_sb, pa);
 	}
 	if (ac->alloc_semp)
 		up_read(ac->alloc_semp);
+	if (pa) {
+		/*
+		 * We want to add the pa to the right bucket.
+		 * Remove it from the list and while adding
+		 * make sure the list to which we are adding
+		 * doesn't grow big.  We need to release
+		 * alloc_semp before calling ext4_mb_add_n_trim()
+		 */
+		if (pa->pa_linear && likely(pa->pa_free)) {
+			spin_lock(pa->pa_obj_lock);
+			list_del_rcu(&pa->pa_inode_list);
+			spin_unlock(pa->pa_obj_lock);
+			ext4_mb_add_n_trim(ac);
+		}
+		ext4_mb_put_pa(ac, ac->ac_sb, pa);
+	}
 	if (ac->ac_bitmap_page)
 		page_cache_release(ac->ac_bitmap_page);
 	if (ac->ac_buddy_page)
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 734abca25e3..fe64d9f7985 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -481,7 +481,7 @@ int ext4_ext_migrate(struct inode *inode)
 					+ 1);
 	if (IS_ERR(handle)) {
 		retval = PTR_ERR(handle);
-		goto err_out;
+		return retval;
 	}
 	tmp_inode = ext4_new_inode(handle,
 				inode->i_sb->s_root->d_inode,
@@ -489,8 +489,7 @@ int ext4_ext_migrate(struct inode *inode)
 	if (IS_ERR(tmp_inode)) {
 		retval = -ENOMEM;
 		ext4_journal_stop(handle);
-		tmp_inode = NULL;
-		goto err_out;
+		return retval;
 	}
 	i_size_write(tmp_inode, i_size_read(inode));
 	/*
@@ -618,8 +617,7 @@ err_out:
 
 	ext4_journal_stop(handle);
 
-	if (tmp_inode)
-		iput(tmp_inode);
+	iput(tmp_inode);
 
 	return retval;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e5f06a5f045..a5732c58f67 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3046,14 +3046,17 @@ static void ext4_write_super(struct super_block *sb)
 static int ext4_sync_fs(struct super_block *sb, int wait)
 {
 	int ret = 0;
+	tid_t target;
 
 	trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
 	sb->s_dirt = 0;
 	if (EXT4_SB(sb)->s_journal) {
-		if (wait)
-			ret = ext4_force_commit(sb);
-		else
- 			jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+		if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal,
+					      &target)) {
+			if (wait)
+				jbd2_log_wait_commit(EXT4_SB(sb)->s_journal,
+						     target);
+		}
 	} else {
 		ext4_commit_super(sb, EXT4_SB(sb)->s_es, wait);
 	}
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index eb343008ede..58144102bf2 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -450,7 +450,7 @@ int __jbd2_log_space_left(journal_t *journal)
 }
 
 /*
- * Called under j_state_lock.  Returns true if a transaction was started.
+ * Called under j_state_lock.  Returns true if a transaction commit was started.
  */
 int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 {
@@ -518,7 +518,8 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
 
 /*
  * Start a commit of the current running transaction (if any).  Returns true
- * if a transaction was started, and fills its tid in at *ptid
+ * if a transaction is going to be committed (or is currently already
+ * committing), and fills its tid in at *ptid
  */
 int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
 {
@@ -528,15 +529,19 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
 	if (journal->j_running_transaction) {
 		tid_t tid = journal->j_running_transaction->t_tid;
 
-		ret = __jbd2_log_start_commit(journal, tid);
-		if (ret && ptid)
+		__jbd2_log_start_commit(journal, tid);
+		/* There's a running transaction and we've just made sure
+		 * it's commit has been scheduled. */
+		if (ptid)
 			*ptid = tid;
-	} else if (journal->j_committing_transaction && ptid) {
+		ret = 1;
+	} else if (journal->j_committing_transaction) {
 		/*
 		 * If ext3_write_super() recently started a commit, then we
 		 * have to wait for completion of that transaction
 		 */
-		*ptid = journal->j_committing_transaction->t_tid;
+		if (ptid)
+			*ptid = journal->j_committing_transaction->t_tid;
 		ret = 1;
 	}
 	spin_unlock(&journal->j_state_lock);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 46b4e347ed7..28ce21d8598 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2129,26 +2129,46 @@ done:
 }
 
 /*
- * This function must be called when inode is journaled in ordered mode
- * before truncation happens. It starts writeout of truncated part in
- * case it is in the committing transaction so that we stand to ordered
- * mode consistency guarantees.
+ * File truncate and transaction commit interact with each other in a
+ * non-trivial way.  If a transaction writing data block A is
+ * committing, we cannot discard the data by truncate until we have
+ * written them.  Otherwise if we crashed after the transaction with
+ * write has committed but before the transaction with truncate has
+ * committed, we could see stale data in block A.  This function is a
+ * helper to solve this problem.  It starts writeout of the truncated
+ * part in case it is in the committing transaction.
+ *
+ * Filesystem code must call this function when inode is journaled in
+ * ordered mode before truncation happens and after the inode has been
+ * placed on orphan list with the new inode size. The second condition
+ * avoids the race that someone writes new data and we start
+ * committing the transaction after this function has been called but
+ * before a transaction for truncate is started (and furthermore it
+ * allows us to optimize the case where the addition to orphan list
+ * happens in the same transaction as write --- we don't have to write
+ * any data in such case).
  */
-int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode,
+int jbd2_journal_begin_ordered_truncate(journal_t *journal,
+					struct jbd2_inode *jinode,
 					loff_t new_size)
 {
-	journal_t *journal;
-	transaction_t *commit_trans;
+	transaction_t *inode_trans, *commit_trans;
 	int ret = 0;
 
-	if (!inode->i_transaction && !inode->i_next_transaction)
+	/* This is a quick check to avoid locking if not necessary */
+	if (!jinode->i_transaction)
 		goto out;
-	journal = inode->i_transaction->t_journal;
+	/* Locks are here just to force reading of recent values, it is
+	 * enough that the transaction was not committing before we started
+	 * a transaction adding the inode to orphan list */
 	spin_lock(&journal->j_state_lock);
 	commit_trans = journal->j_committing_transaction;
 	spin_unlock(&journal->j_state_lock);
-	if (inode->i_transaction == commit_trans) {
-		ret = filemap_fdatawrite_range(inode->i_vfs_inode->i_mapping,
+	spin_lock(&journal->j_list_lock);
+	inode_trans = jinode->i_transaction;
+	spin_unlock(&journal->j_list_lock);
+	if (inode_trans == commit_trans) {
+		ret = filemap_fdatawrite_range(jinode->i_vfs_inode->i_mapping,
 			new_size, LLONG_MAX);
 		if (ret)
 			jbd2_journal_abort(journal, ret);
diff --git a/fs/namespace.c b/fs/namespace.c
index 228d8c4bfd1..06f8e63f6cb 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -614,9 +614,11 @@ static inline void __mntput(struct vfsmount *mnt)
 	 */
 	for_each_possible_cpu(cpu) {
 		struct mnt_writer *cpu_writer = &per_cpu(mnt_writers, cpu);
-		if (cpu_writer->mnt != mnt)
-			continue;
 		spin_lock(&cpu_writer->lock);
+		if (cpu_writer->mnt != mnt) {
+			spin_unlock(&cpu_writer->lock);
+			continue;
+		}
 		atomic_add(cpu_writer->count, &mnt->__mnt_writers);
 		cpu_writer->count = 0;
 		/*
diff --git a/fs/notify/inotify/inotify.c b/fs/notify/inotify/inotify.c
index dae3f28f30d..331f2e88e28 100644
--- a/fs/notify/inotify/inotify.c
+++ b/fs/notify/inotify/inotify.c
@@ -156,7 +156,7 @@ static int inotify_handle_get_wd(struct inotify_handle *ih,
 	int ret;
 
 	do {
-		if (unlikely(!idr_pre_get(&ih->idr, GFP_KERNEL)))
+		if (unlikely(!idr_pre_get(&ih->idr, GFP_NOFS)))
 			return -ENOSPC;
 		ret = idr_get_new_above(&ih->idr, watch, ih->last_wd+1, &watch->wd);
 	} while (ret == -EAGAIN);
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 3c3532e1307..172850a9a12 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -513,8 +513,10 @@ static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
 static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
 					       loff_t new_size)
 {
-	return jbd2_journal_begin_ordered_truncate(&OCFS2_I(inode)->ip_jinode,
-						   new_size);
+	return jbd2_journal_begin_ordered_truncate(
+				OCFS2_SB(inode->i_sb)->journal->j_journal,
+				&OCFS2_I(inode)->ip_jinode,
+				new_size);
 }
 
 #endif /* OCFS2_JOURNAL_H */
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 5267098532b..a1a4cfe1921 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -48,8 +48,16 @@ int seq_open(struct file *file, const struct seq_operations *op)
 	 */
 	file->f_version = 0;
 
-	/* SEQ files support lseek, but not pread/pwrite */
-	file->f_mode &= ~(FMODE_PREAD | FMODE_PWRITE);
+	/*
+	 * seq_files support lseek() and pread().  They do not implement
+	 * write() at all, but we clear FMODE_PWRITE here for historical
+	 * reasons.
+	 *
+	 * If a client of seq_files a) implements file.write() and b) wishes to
+	 * support pwrite() then that client will need to implement its own
+	 * file.open() which calls seq_open() and then sets FMODE_PWRITE.
+	 */
+	file->f_mode &= ~FMODE_PWRITE;
 	return 0;
 }
 EXPORT_SYMBOL(seq_open);
@@ -131,6 +139,22 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 	int err = 0;
 
 	mutex_lock(&m->lock);
+
+	/* Don't assume *ppos is where we left it */
+	if (unlikely(*ppos != m->read_pos)) {
+		m->read_pos = *ppos;
+		while ((err = traverse(m, *ppos)) == -EAGAIN)
+			;
+		if (err) {
+			/* With prejudice... */
+			m->read_pos = 0;
+			m->version = 0;
+			m->index = 0;
+			m->count = 0;
+			goto Done;
+		}
+	}
+
 	/*
 	 * seq_file->op->..m_start/m_stop/m_next may do special actions
 	 * or optimisations based on the file->f_version, so we want to
@@ -230,8 +254,10 @@ Fill:
 Done:
 	if (!copied)
 		copied = err;
-	else
+	else {
 		*ppos += copied;
+		m->read_pos += copied;
+	}
 	file->f_version = m->version;
 	mutex_unlock(&m->lock);
 	return copied;
@@ -266,16 +292,18 @@ loff_t seq_lseek(struct file *file, loff_t offset, int origin)
 			if (offset < 0)
 				break;
 			retval = offset;
-			if (offset != file->f_pos) {
+			if (offset != m->read_pos) {
 				while ((retval=traverse(m, offset)) == -EAGAIN)
 					;
 				if (retval) {
 					/* with extreme prejudice... */
 					file->f_pos = 0;
+					m->read_pos = 0;
 					m->version = 0;
 					m->index = 0;
 					m->count = 0;
 				} else {
+					m->read_pos = offset;
 					retval = file->f_pos = offset;
 				}
 			}
diff --git a/fs/super.c b/fs/super.c
index 61dce001dd5..8349ed6b141 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -82,7 +82,22 @@ static struct super_block *alloc_super(struct file_system_type *type)
 		 * lock ordering than usbfs:
 		 */
 		lockdep_set_class(&s->s_lock, &type->s_lock_key);
-		down_write(&s->s_umount);
+		/*
+		 * sget() can have s_umount recursion.
+		 *
+		 * When it cannot find a suitable sb, it allocates a new
+		 * one (this one), and tries again to find a suitable old
+		 * one.
+		 *
+		 * In case that succeeds, it will acquire the s_umount
+		 * lock of the old one. Since these are clearly distrinct
+		 * locks, and this object isn't exposed yet, there's no
+		 * risk of deadlocks.
+		 *
+		 * Annotate this by putting this lock in a different
+		 * subclass.
+		 */
+		down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING);
 		s->s_count = S_BIAS;
 		atomic_set(&s->s_active, 1);
 		mutex_init(&s->s_vfs_rename_mutex);
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 6a123b8ff3f..b042bd7034b 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -186,10 +186,9 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 	BUILD_BUG_ON(TFD_CLOEXEC != O_CLOEXEC);
 	BUILD_BUG_ON(TFD_NONBLOCK != O_NONBLOCK);
 
-	if (flags & ~(TFD_CLOEXEC | TFD_NONBLOCK))
-		return -EINVAL;
-	if (clockid != CLOCK_MONOTONIC &&
-	    clockid != CLOCK_REALTIME)
+	if ((flags & ~TFD_CREATE_FLAGS) ||
+	    (clockid != CLOCK_MONOTONIC &&
+	     clockid != CLOCK_REALTIME))
 		return -EINVAL;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -201,7 +200,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 	hrtimer_init(&ctx->tmr, clockid, HRTIMER_MODE_ABS);
 
 	ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx,
-			       flags & (O_CLOEXEC | O_NONBLOCK));
+			       flags & TFD_SHARED_FCNTL_FLAGS);
 	if (ufd < 0)
 		kfree(ctx);
 
@@ -219,7 +218,8 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 	if (copy_from_user(&ktmr, utmr, sizeof(ktmr)))
 		return -EFAULT;
 
-	if (!timespec_valid(&ktmr.it_value) ||
+	if ((flags & ~TFD_SETTIME_FLAGS) ||
+	    !timespec_valid(&ktmr.it_value) ||
 	    !timespec_valid(&ktmr.it_interval))
 		return -EINVAL;