1 files changed, 403 insertions, 256 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b8b60b660c8f..62176ad89846 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -31,6 +31,7 @@
 #include <linux/migrate.h>
 #include <linux/ratelimit.h>
 #include <linux/uuid.h>
+#include <linux/semaphore.h>
 #include <asm/unaligned.h>
 #include "compat.h"
 #include "ctree.h"
@@ -156,6 +157,7 @@ static struct btrfs_lockdep_keyset {
 	{ .id = BTRFS_TREE_LOG_OBJECTID,	.name_stem = "log"	},
 	{ .id = BTRFS_TREE_RELOC_OBJECTID,	.name_stem = "treloc"	},
 	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	.name_stem = "dreloc"	},
+	{ .id = BTRFS_UUID_TREE_OBJECTID,	.name_stem = "uuid"	},
 	{ .id = 0,				.name_stem = "tree"	},
 };
 
@@ -302,9 +304,8 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
 			printk_ratelimited(KERN_INFO "btrfs: %s checksum verify "
 				       "failed on %llu wanted %X found %X "
 				       "level %d\n",
-				       root->fs_info->sb->s_id,
-				       (unsigned long long)buf->start, val, found,
-				       btrfs_header_level(buf));
+				       root->fs_info->sb->s_id, buf->start,
+				       val, found, btrfs_header_level(buf));
 			if (result != (char *)&inline_result)
 				kfree(result);
 			return 1;
@@ -345,9 +346,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 	}
 	printk_ratelimited("parent transid verify failed on %llu wanted %llu "
 		       "found %llu\n",
-		       (unsigned long long)eb->start,
-		       (unsigned long long)parent_transid,
-		       (unsigned long long)btrfs_header_generation(eb));
+		       eb->start, parent_transid, btrfs_header_generation(eb));
 	ret = 1;
 	clear_extent_buffer_uptodate(eb);
 out:
@@ -497,8 +496,7 @@ static int check_tree_block_fsid(struct btrfs_root *root,
 	u8 fsid[BTRFS_UUID_SIZE];
 	int ret = 1;
 
-	read_extent_buffer(eb, fsid, (unsigned long)btrfs_header_fsid(eb),
-			   BTRFS_FSID_SIZE);
+	read_extent_buffer(eb, fsid, btrfs_header_fsid(eb), BTRFS_FSID_SIZE);
 	while (fs_devices) {
 		if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) {
 			ret = 0;
@@ -512,8 +510,7 @@ static int check_tree_block_fsid(struct btrfs_root *root,
 #define CORRUPT(reason, eb, root, slot)				\
 	printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu,"	\
 	       "root=%llu, slot=%d\n", reason,			\
-	       (unsigned long long)btrfs_header_bytenr(eb),	\
-	       (unsigned long long)root->objectid, slot)
+	       btrfs_header_bytenr(eb),	root->objectid, slot)
 
 static noinline int check_leaf(struct btrfs_root *root,
 			       struct extent_buffer *leaf)
@@ -576,8 +573,9 @@ static noinline int check_leaf(struct btrfs_root *root,
 	return 0;
 }
 
-static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
-			       struct extent_state *state, int mirror)
+static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
+				      u64 phy_offset, struct page *page,
+				      u64 start, u64 end, int mirror)
 {
 	struct extent_io_tree *tree;
 	u64 found_start;
@@ -612,14 +610,13 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 	if (found_start != eb->start) {
 		printk_ratelimited(KERN_INFO "btrfs bad tree block start "
 			       "%llu %llu\n",
-			       (unsigned long long)found_start,
-			       (unsigned long long)eb->start);
+			       found_start, eb->start);
 		ret = -EIO;
 		goto err;
 	}
 	if (check_tree_block_fsid(root, eb)) {
 		printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n",
-			       (unsigned long long)eb->start);
+			       eb->start);
 		ret = -EIO;
 		goto err;
 	}
@@ -1013,7 +1010,8 @@ static int btree_releasepage(struct page *page, gfp_t gfp_flags)
 	return try_release_extent_buffer(page);
 }
 
-static void btree_invalidatepage(struct page *page, unsigned long offset)
+static void btree_invalidatepage(struct page *page, unsigned int offset,
+				 unsigned int length)
 {
 	struct extent_io_tree *tree;
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
@@ -1147,6 +1145,10 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 		return NULL;
 
 	ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
+	if (ret) {
+		free_extent_buffer(buf);
+		return NULL;
+	}
 	return buf;
 
 }
@@ -1191,6 +1193,8 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	root->objectid = objectid;
 	root->last_trans = 0;
 	root->highest_objectid = 0;
+	root->nr_delalloc_inodes = 0;
+	root->nr_ordered_extents = 0;
 	root->name = NULL;
 	root->inode_tree = RB_ROOT;
 	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
@@ -1199,10 +1203,16 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 
 	INIT_LIST_HEAD(&root->dirty_list);
 	INIT_LIST_HEAD(&root->root_list);
+	INIT_LIST_HEAD(&root->delalloc_inodes);
+	INIT_LIST_HEAD(&root->delalloc_root);
+	INIT_LIST_HEAD(&root->ordered_extents);
+	INIT_LIST_HEAD(&root->ordered_root);
 	INIT_LIST_HEAD(&root->logged_list[0]);
 	INIT_LIST_HEAD(&root->logged_list[1]);
 	spin_lock_init(&root->orphan_lock);
 	spin_lock_init(&root->inode_lock);
+	spin_lock_init(&root->delalloc_lock);
+	spin_lock_init(&root->ordered_extent_lock);
 	spin_lock_init(&root->accounting_lock);
 	spin_lock_init(&root->log_extents_lock[0]);
 	spin_lock_init(&root->log_extents_lock[1]);
@@ -1216,6 +1226,7 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	atomic_set(&root->log_writers, 0);
 	atomic_set(&root->log_batch, 0);
 	atomic_set(&root->orphan_inodes, 0);
+	atomic_set(&root->refs, 1);
 	root->log_transid = 0;
 	root->last_log_commit = 0;
 	extent_io_tree_init(&root->dirty_log_pages,
@@ -1234,39 +1245,6 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	spin_lock_init(&root->root_item_lock);
 }
 
-static int __must_check find_and_setup_root(struct btrfs_root *tree_root,
-					    struct btrfs_fs_info *fs_info,
-					    u64 objectid,
-					    struct btrfs_root *root)
-{
-	int ret;
-	u32 blocksize;
-	u64 generation;
-
-	__setup_root(tree_root->nodesize, tree_root->leafsize,
-		     tree_root->sectorsize, tree_root->stripesize,
-		     root, fs_info, objectid);
-	ret = btrfs_find_last_root(tree_root, objectid,
-				   &root->root_item, &root->root_key);
-	if (ret > 0)
-		return -ENOENT;
-	else if (ret < 0)
-		return ret;
-
-	generation = btrfs_root_generation(&root->root_item);
-	blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
-	root->commit_root = NULL;
-	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
-				     blocksize, generation);
-	if (!root->node || !btrfs_buffer_uptodate(root->node, generation, 0)) {
-		free_extent_buffer(root->node);
-		root->node = NULL;
-		return -EIO;
-	}
-	root->commit_root = btrfs_root_node(root);
-	return 0;
-}
-
 static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS);
@@ -1314,11 +1292,10 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	btrfs_set_header_owner(leaf, objectid);
 	root->node = leaf;
 
-	write_extent_buffer(leaf, fs_info->fsid,
-			    (unsigned long)btrfs_header_fsid(leaf),
+	write_extent_buffer(leaf, fs_info->fsid, btrfs_header_fsid(leaf),
 			    BTRFS_FSID_SIZE);
 	write_extent_buffer(leaf, fs_info->chunk_tree_uuid,
-			    (unsigned long)btrfs_header_chunk_tree_uuid(leaf),
+			    btrfs_header_chunk_tree_uuid(leaf),
 			    BTRFS_UUID_SIZE);
 	btrfs_mark_buffer_dirty(leaf);
 
@@ -1402,8 +1379,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	root->node = leaf;
 
 	write_extent_buffer(root->node, root->fs_info->fsid,
-			    (unsigned long)btrfs_header_fsid(root->node),
-			    BTRFS_FSID_SIZE);
+			    btrfs_header_fsid(root->node), BTRFS_FSID_SIZE);
 	btrfs_mark_buffer_dirty(root->node);
 	btrfs_tree_unlock(root->node);
 	return root;
@@ -1436,11 +1412,11 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 	log_root->root_key.offset = root->root_key.objectid;
 
 	inode_item = &log_root->root_item.inode;
-	inode_item->generation = cpu_to_le64(1);
-	inode_item->size = cpu_to_le64(3);
-	inode_item->nlink = cpu_to_le32(1);
-	inode_item->nbytes = cpu_to_le64(root->leafsize);
-	inode_item->mode = cpu_to_le32(S_IFDIR | 0755);
+	btrfs_set_stack_inode_generation(inode_item, 1);
+	btrfs_set_stack_inode_size(inode_item, 3);
+	btrfs_set_stack_inode_nlink(inode_item, 1);
+	btrfs_set_stack_inode_nbytes(inode_item, root->leafsize);
+	btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
 
 	btrfs_set_root_node(&log_root->root_item, log_root->node);
 
@@ -1451,70 +1427,73 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
-struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
-					       struct btrfs_key *location)
+static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
+					       struct btrfs_key *key)
 {
 	struct btrfs_root *root;
 	struct btrfs_fs_info *fs_info = tree_root->fs_info;
 	struct btrfs_path *path;
-	struct extent_buffer *l;
 	u64 generation;
 	u32 blocksize;
-	int ret = 0;
-	int slot;
+	int ret;
 
-	root = btrfs_alloc_root(fs_info);
-	if (!root)
+	path = btrfs_alloc_path();
+	if (!path)
 		return ERR_PTR(-ENOMEM);
-	if (location->offset == (u64)-1) {
-		ret = find_and_setup_root(tree_root, fs_info,
-					  location->objectid, root);
-		if (ret) {
-			kfree(root);
-			return ERR_PTR(ret);
-		}
-		goto out;
+
+	root = btrfs_alloc_root(fs_info);
+	if (!root) {
+		ret = -ENOMEM;
+		goto alloc_fail;
 	}
 
 	__setup_root(tree_root->nodesize, tree_root->leafsize,
 		     tree_root->sectorsize, tree_root->stripesize,
-		     root, fs_info, location->objectid);
+		     root, fs_info, key->objectid);
 
-	path = btrfs_alloc_path();
-	if (!path) {
-		kfree(root);
-		return ERR_PTR(-ENOMEM);
-	}
-	ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0);
-	if (ret == 0) {
-		l = path->nodes[0];
-		slot = path->slots[0];
-		btrfs_read_root_item(l, slot, &root->root_item);
-		memcpy(&root->root_key, location, sizeof(*location));
-	}
-	btrfs_free_path(path);
+	ret = btrfs_find_root(tree_root, key, path,
+			      &root->root_item, &root->root_key);
 	if (ret) {
-		kfree(root);
 		if (ret > 0)
 			ret = -ENOENT;
-		return ERR_PTR(ret);
+		goto find_fail;
 	}
 
 	generation = btrfs_root_generation(&root->root_item);
 	blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
 	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
 				     blocksize, generation);
-	if (!root->node || !extent_buffer_uptodate(root->node)) {
-		ret = (!root->node) ? -ENOMEM : -EIO;
-
-		free_extent_buffer(root->node);
-		kfree(root);
-		return ERR_PTR(ret);
+	if (!root->node) {
+		ret = -ENOMEM;
+		goto find_fail;
+	} else if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
+		ret = -EIO;
+		goto read_fail;
 	}
-
 	root->commit_root = btrfs_root_node(root);
 out:
-	if (location->objectid != BTRFS_TREE_LOG_OBJECTID) {
+	btrfs_free_path(path);
+	return root;
+
+read_fail:
+	free_extent_buffer(root->node);
+find_fail:
+	kfree(root);
+alloc_fail:
+	root = ERR_PTR(ret);
+	goto out;
+}
+
+struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
+				      struct btrfs_key *location)
+{
+	struct btrfs_root *root;
+
+	root = btrfs_read_tree_root(tree_root, location);
+	if (IS_ERR(root))
+		return root;
+
+	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
 		root->ref_cows = 1;
 		btrfs_check_and_init_root_item(&root->root_item);
 	}
@@ -1522,8 +1501,69 @@ out:
 	return root;
 }
 
-struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
-					      struct btrfs_key *location)
+int btrfs_init_fs_root(struct btrfs_root *root)
+{
+	int ret;
+
+	root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
+	root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
+					GFP_NOFS);
+	if (!root->free_ino_pinned || !root->free_ino_ctl) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	btrfs_init_free_ino_ctl(root);
+	mutex_init(&root->fs_commit_mutex);
+	spin_lock_init(&root->cache_lock);
+	init_waitqueue_head(&root->cache_wait);
+
+	ret = get_anon_bdev(&root->anon_dev);
+	if (ret)
+		goto fail;
+	return 0;
+fail:
+	kfree(root->free_ino_ctl);
+	kfree(root->free_ino_pinned);
+	return ret;
+}
+
+static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+					       u64 root_id)
+{
+	struct btrfs_root *root;
+
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	root = radix_tree_lookup(&fs_info->fs_roots_radix,
+				 (unsigned long)root_id);
+	spin_unlock(&fs_info->fs_roots_radix_lock);
+	return root;
+}
+
+int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
+			 struct btrfs_root *root)
+{
+	int ret;
+
+	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+	if (ret)
+		return ret;
+
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	ret = radix_tree_insert(&fs_info->fs_roots_radix,
+				(unsigned long)root->root_key.objectid,
+				root);
+	if (ret == 0)
+		root->in_radix = 1;
+	spin_unlock(&fs_info->fs_roots_radix_lock);
+	radix_tree_preload_end();
+
+	return ret;
+}
+
+struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
+				     struct btrfs_key *location,
+				     bool check_ref)
 {
 	struct btrfs_root *root;
 	int ret;
@@ -1541,59 +1581,37 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
 	if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID)
 		return fs_info->quota_root ? fs_info->quota_root :
 					     ERR_PTR(-ENOENT);
+	if (location->objectid == BTRFS_UUID_TREE_OBJECTID)
+		return fs_info->uuid_root ? fs_info->uuid_root :
+					    ERR_PTR(-ENOENT);
 again:
-	spin_lock(&fs_info->fs_roots_radix_lock);
-	root = radix_tree_lookup(&fs_info->fs_roots_radix,
-				 (unsigned long)location->objectid);
-	spin_unlock(&fs_info->fs_roots_radix_lock);
-	if (root)
+	root = btrfs_lookup_fs_root(fs_info, location->objectid);
+	if (root) {
+		if (check_ref && btrfs_root_refs(&root->root_item) == 0)
+			return ERR_PTR(-ENOENT);
 		return root;
+	}
 
-	root = btrfs_read_fs_root_no_radix(fs_info->tree_root, location);
+	root = btrfs_read_fs_root(fs_info->tree_root, location);
 	if (IS_ERR(root))
 		return root;
 
-	root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
-	root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
-					GFP_NOFS);
-	if (!root->free_ino_pinned || !root->free_ino_ctl) {
-		ret = -ENOMEM;
+	if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
+		ret = -ENOENT;
 		goto fail;
 	}
 
-	btrfs_init_free_ino_ctl(root);
-	mutex_init(&root->fs_commit_mutex);
-	spin_lock_init(&root->cache_lock);
-	init_waitqueue_head(&root->cache_wait);
-
-	ret = get_anon_bdev(&root->anon_dev);
+	ret = btrfs_init_fs_root(root);
 	if (ret)
 		goto fail;
 
-	if (btrfs_root_refs(&root->root_item) == 0) {
-		ret = -ENOENT;
-		goto fail;
-	}
-
 	ret = btrfs_find_orphan_item(fs_info->tree_root, location->objectid);
 	if (ret < 0)
 		goto fail;
 	if (ret == 0)
 		root->orphan_item_inserted = 1;
 
-	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
-	if (ret)
-		goto fail;
-
-	spin_lock(&fs_info->fs_roots_radix_lock);
-	ret = radix_tree_insert(&fs_info->fs_roots_radix,
-				(unsigned long)root->root_key.objectid,
-				root);
-	if (ret == 0)
-		root->in_radix = 1;
-
-	spin_unlock(&fs_info->fs_roots_radix_lock);
-	radix_tree_preload_end();
+	ret = btrfs_insert_fs_root(fs_info, root);
 	if (ret) {
 		if (ret == -EEXIST) {
 			free_fs_root(root);
@@ -1601,10 +1619,6 @@ again:
 		}
 		goto fail;
 	}
-
-	ret = btrfs_find_dead_roots(fs_info->tree_root,
-				    root->root_key.objectid);
-	WARN_ON(ret);
 	return root;
 fail:
 	free_fs_root(root);
@@ -1676,21 +1690,37 @@ static void end_workqueue_fn(struct btrfs_work *work)
 static int cleaner_kthread(void *arg)
 {
 	struct btrfs_root *root = arg;
+	int again;
 
 	do {
-		int again = 0;
-
-		if (!(root->fs_info->sb->s_flags & MS_RDONLY) &&
-		    down_read_trylock(&root->fs_info->sb->s_umount)) {
-			if (mutex_trylock(&root->fs_info->cleaner_mutex)) {
-				btrfs_run_delayed_iputs(root);
-				again = btrfs_clean_one_deleted_snapshot(root);
-				mutex_unlock(&root->fs_info->cleaner_mutex);
-			}
-			btrfs_run_defrag_inodes(root->fs_info);
-			up_read(&root->fs_info->sb->s_umount);
+		again = 0;
+
+		/* Make the cleaner go to sleep early. */
+		if (btrfs_need_cleaner_sleep(root))
+			goto sleep;
+
+		if (!mutex_trylock(&root->fs_info->cleaner_mutex))
+			goto sleep;
+
+		/*
+		 * Avoid the problem that we change the status of the fs
+		 * during the above check and trylock.
+		 */
+		if (btrfs_need_cleaner_sleep(root)) {
+			mutex_unlock(&root->fs_info->cleaner_mutex);
+			goto sleep;
 		}
 
+		btrfs_run_delayed_iputs(root);
+		again = btrfs_clean_one_deleted_snapshot(root);
+		mutex_unlock(&root->fs_info->cleaner_mutex);
+
+		/*
+		 * The defragger has dealt with the R/O remount and umount,
+		 * needn't do anything special here.
+		 */
+		btrfs_run_defrag_inodes(root->fs_info);
+sleep:
 		if (!try_to_freeze() && !again) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			if (!kthread_should_stop())
@@ -1713,7 +1743,7 @@ static int transaction_kthread(void *arg)
 
 	do {
 		cannot_commit = false;
-		delay = HZ * 30;
+		delay = HZ * root->fs_info->commit_interval;
 		mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
 		spin_lock(&root->fs_info->trans_lock);
@@ -1724,8 +1754,9 @@ static int transaction_kthread(void *arg)
 		}
 
 		now = get_seconds();
-		if (!cur->blocked &&
-		    (now < cur->start_time || now - cur->start_time < 30)) {
+		if (cur->state < TRANS_STATE_BLOCKED &&
+		    (now < cur->start_time ||
+		     now - cur->start_time < root->fs_info->commit_interval)) {
 			spin_unlock(&root->fs_info->trans_lock);
 			delay = HZ * 5;
 			goto sleep;
@@ -2014,6 +2045,12 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
 		info->quota_root->node = NULL;
 		info->quota_root->commit_root = NULL;
 	}
+	if (info->uuid_root) {
+		free_extent_buffer(info->uuid_root->node);
+		free_extent_buffer(info->uuid_root->commit_root);
+		info->uuid_root->node = NULL;
+		info->uuid_root->commit_root = NULL;
+	}
 	if (chunk_root) {
 		free_extent_buffer(info->chunk_root->node);
 		free_extent_buffer(info->chunk_root->commit_root);
@@ -2034,11 +2071,11 @@ static void del_fs_roots(struct btrfs_fs_info *fs_info)
 		list_del(&gang[0]->root_list);
 
 		if (gang[0]->in_radix) {
-			btrfs_free_fs_root(fs_info, gang[0]);
+			btrfs_drop_and_free_fs_root(fs_info, gang[0]);
 		} else {
 			free_extent_buffer(gang[0]->node);
 			free_extent_buffer(gang[0]->commit_root);
-			kfree(gang[0]);
+			btrfs_put_fs_root(gang[0]);
 		}
 	}
 
@@ -2049,7 +2086,7 @@ static void del_fs_roots(struct btrfs_fs_info *fs_info)
 		if (!ret)
 			break;
 		for (i = 0; i < ret; i++)
-			btrfs_free_fs_root(fs_info, gang[i]);
+			btrfs_drop_and_free_fs_root(fs_info, gang[i]);
 	}
 }
 
@@ -2074,21 +2111,18 @@ int open_ctree(struct super_block *sb,
 	struct btrfs_root *chunk_root;
 	struct btrfs_root *dev_root;
 	struct btrfs_root *quota_root;
+	struct btrfs_root *uuid_root;
 	struct btrfs_root *log_tree_root;
 	int ret;
 	int err = -EINVAL;
 	int num_backups_tried = 0;
 	int backup_index = 0;
+	bool create_uuid_tree;
+	bool check_uuid_tree;
 
 	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info);
-	extent_root = fs_info->extent_root = btrfs_alloc_root(fs_info);
-	csum_root = fs_info->csum_root = btrfs_alloc_root(fs_info);
 	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info);
-	dev_root = fs_info->dev_root = btrfs_alloc_root(fs_info);
-	quota_root = fs_info->quota_root = btrfs_alloc_root(fs_info);
-
-	if (!tree_root || !extent_root || !csum_root ||
-	    !chunk_root || !dev_root || !quota_root) {
+	if (!tree_root || !chunk_root) {
 		err = -ENOMEM;
 		goto fail;
 	}
@@ -2131,9 +2165,9 @@ int open_ctree(struct super_block *sb,
 	INIT_LIST_HEAD(&fs_info->trans_list);
 	INIT_LIST_HEAD(&fs_info->dead_roots);
 	INIT_LIST_HEAD(&fs_info->delayed_iputs);
-	INIT_LIST_HEAD(&fs_info->delalloc_inodes);
+	INIT_LIST_HEAD(&fs_info->delalloc_roots);
 	INIT_LIST_HEAD(&fs_info->caching_block_groups);
-	spin_lock_init(&fs_info->delalloc_lock);
+	spin_lock_init(&fs_info->delalloc_root_lock);
 	spin_lock_init(&fs_info->trans_lock);
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
@@ -2169,9 +2203,9 @@ int open_ctree(struct super_block *sb,
 	fs_info->max_inline = 8192 * 1024;
 	fs_info->metadata_ratio = 0;
 	fs_info->defrag_inodes = RB_ROOT;
-	fs_info->trans_no_join = 0;
 	fs_info->free_chunk_space = 0;
 	fs_info->tree_mod_log = RB_ROOT;
+	fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
 
 	/* readahead state */
 	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
@@ -2180,8 +2214,8 @@ int open_ctree(struct super_block *sb,
 	fs_info->thread_pool_size = min_t(unsigned long,
 					  num_online_cpus() + 2, 8);
 
-	INIT_LIST_HEAD(&fs_info->ordered_extents);
-	spin_lock_init(&fs_info->ordered_extent_lock);
+	INIT_LIST_HEAD(&fs_info->ordered_roots);
+	spin_lock_init(&fs_info->ordered_root_lock);
 	fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
 					GFP_NOFS);
 	if (!fs_info->delayed_root) {
@@ -2253,6 +2287,7 @@ int open_ctree(struct super_block *sb,
 
 
 	mutex_init(&fs_info->ordered_operations_mutex);
+	mutex_init(&fs_info->ordered_extent_flush_mutex);
 	mutex_init(&fs_info->tree_log_mutex);
 	mutex_init(&fs_info->chunk_mutex);
 	mutex_init(&fs_info->transaction_kthread_mutex);
@@ -2261,6 +2296,7 @@ int open_ctree(struct super_block *sb,
 	init_rwsem(&fs_info->extent_commit_sem);
 	init_rwsem(&fs_info->cleanup_work_sem);
 	init_rwsem(&fs_info->subvol_sem);
+	sema_init(&fs_info->uuid_tree_rescan_sem, 1);
 	fs_info->dev_replace.lock_owner = 0;
 	atomic_set(&fs_info->dev_replace.nesting_level, 0);
 	mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
@@ -2274,6 +2310,7 @@ int open_ctree(struct super_block *sb,
 	fs_info->qgroup_seq = 1;
 	fs_info->quota_enabled = 0;
 	fs_info->pending_quota_state = 0;
+	fs_info->qgroup_ulist = NULL;
 	mutex_init(&fs_info->qgroup_rescan_lock);
 
 	btrfs_init_free_cluster(&fs_info->meta_alloc_cluster);
@@ -2365,7 +2402,7 @@ int open_ctree(struct super_block *sb,
 	if (features) {
 		printk(KERN_ERR "BTRFS: couldn't mount because of "
 		       "unsupported optional features (%Lx).\n",
-		       (unsigned long long)features);
+		       features);
 		err = -EINVAL;
 		goto fail_alloc;
 	}
@@ -2435,7 +2472,7 @@ int open_ctree(struct super_block *sb,
 	if (!(sb->s_flags & MS_RDONLY) && features) {
 		printk(KERN_ERR "BTRFS: couldn't mount RDWR because of "
 		       "unsupported option features (%Lx).\n",
-		       (unsigned long long)features);
+		       features);
 		err = -EINVAL;
 		goto fail_alloc;
 	}
@@ -2448,20 +2485,17 @@ int open_ctree(struct super_block *sb,
 			   &fs_info->generic_worker);
 
 	btrfs_init_workers(&fs_info->delalloc_workers, "delalloc",
-			   fs_info->thread_pool_size,
-			   &fs_info->generic_worker);
+			   fs_info->thread_pool_size, NULL);
 
 	btrfs_init_workers(&fs_info->flush_workers, "flush_delalloc",
-			   fs_info->thread_pool_size,
-			   &fs_info->generic_worker);
+			   fs_info->thread_pool_size, NULL);
 
 	btrfs_init_workers(&fs_info->submit_workers, "submit",
 			   min_t(u64, fs_devices->num_devices,
-			   fs_info->thread_pool_size),
-			   &fs_info->generic_worker);
+			   fs_info->thread_pool_size), NULL);
 
 	btrfs_init_workers(&fs_info->caching_workers, "cache",
-			   2, &fs_info->generic_worker);
+			   fs_info->thread_pool_size, NULL);
 
 	/* a higher idle thresh on the submit workers makes it much more
 	 * likely that bios will be send down in a sane order to the
@@ -2557,7 +2591,7 @@ int open_ctree(struct super_block *sb,
 	sb->s_blocksize = sectorsize;
 	sb->s_blocksize_bits = blksize_bits(sectorsize);
 
-	if (disk_super->magic != cpu_to_le64(BTRFS_MAGIC)) {
+	if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
 		printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id);
 		goto fail_sb_buffer;
 	}
@@ -2597,8 +2631,7 @@ int open_ctree(struct super_block *sb,
 	chunk_root->commit_root = btrfs_root_node(chunk_root);
 
 	read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid,
-	   (unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node),
-	   BTRFS_UUID_SIZE);
+	   btrfs_header_chunk_tree_uuid(chunk_root->node), BTRFS_UUID_SIZE);
 
 	ret = btrfs_read_chunk_tree(chunk_root);
 	if (ret) {
@@ -2638,33 +2671,60 @@ retry_root_backup:
 	btrfs_set_root_node(&tree_root->root_item, tree_root->node);
 	tree_root->commit_root = btrfs_root_node(tree_root);
 
-	ret = find_and_setup_root(tree_root, fs_info,
-				  BTRFS_EXTENT_TREE_OBJECTID, extent_root);
-	if (ret)
+	location.objectid = BTRFS_EXTENT_TREE_OBJECTID;
+	location.type = BTRFS_ROOT_ITEM_KEY;
+	location.offset = 0;
+
+	extent_root = btrfs_read_tree_root(tree_root, &location);
+	if (IS_ERR(extent_root)) {
+		ret = PTR_ERR(extent_root);
 		goto recovery_tree_root;
+	}
 	extent_root->track_dirty = 1;
+	fs_info->extent_root = extent_root;
 
-	ret = find_and_setup_root(tree_root, fs_info,
-				  BTRFS_DEV_TREE_OBJECTID, dev_root);
-	if (ret)
+	location.objectid = BTRFS_DEV_TREE_OBJECTID;
+	dev_root = btrfs_read_tree_root(tree_root, &location);
+	if (IS_ERR(dev_root)) {
+		ret = PTR_ERR(dev_root);
 		goto recovery_tree_root;
+	}
 	dev_root->track_dirty = 1;
+	fs_info->dev_root = dev_root;
+	btrfs_init_devices_late(fs_info);
 
-	ret = find_and_setup_root(tree_root, fs_info,
-				  BTRFS_CSUM_TREE_OBJECTID, csum_root);
-	if (ret)
+	location.objectid = BTRFS_CSUM_TREE_OBJECTID;
+	csum_root = btrfs_read_tree_root(tree_root, &location);
+	if (IS_ERR(csum_root)) {
+		ret = PTR_ERR(csum_root);
 		goto recovery_tree_root;
+	}
 	csum_root->track_dirty = 1;
+	fs_info->csum_root = csum_root;
 
-	ret = find_and_setup_root(tree_root, fs_info,
-				  BTRFS_QUOTA_TREE_OBJECTID, quota_root);
-	if (ret) {
-		kfree(quota_root);
-		quota_root = fs_info->quota_root = NULL;
-	} else {
+	location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
+	quota_root = btrfs_read_tree_root(tree_root, &location);
+	if (!IS_ERR(quota_root)) {
 		quota_root->track_dirty = 1;
 		fs_info->quota_enabled = 1;
 		fs_info->pending_quota_state = 1;
+		fs_info->quota_root = quota_root;
+	}
+
+	location.objectid = BTRFS_UUID_TREE_OBJECTID;
+	uuid_root = btrfs_read_tree_root(tree_root, &location);
+	if (IS_ERR(uuid_root)) {
+		ret = PTR_ERR(uuid_root);
+		if (ret != -ENOENT)
+			goto recovery_tree_root;
+		create_uuid_tree = true;
+		check_uuid_tree = false;
+	} else {
+		uuid_root->track_dirty = 1;
+		fs_info->uuid_root = uuid_root;
+		create_uuid_tree = false;
+		check_uuid_tree =
+		    generation != btrfs_super_uuid_tree_generation(disk_super);
 	}
 
 	fs_info->generation = generation;
@@ -2817,11 +2877,9 @@ retry_root_backup:
 
 	location.objectid = BTRFS_FS_TREE_OBJECTID;
 	location.type = BTRFS_ROOT_ITEM_KEY;
-	location.offset = (u64)-1;
+	location.offset = 0;
 
 	fs_info->fs_root = btrfs_read_fs_root_no_name(fs_info, &location);
-	if (!fs_info->fs_root)
-		goto fail_qgroup;
 	if (IS_ERR(fs_info->fs_root)) {
 		err = PTR_ERR(fs_info->fs_root);
 		goto fail_qgroup;
@@ -2853,6 +2911,31 @@ retry_root_backup:
 		return ret;
 	}
 
+	btrfs_qgroup_rescan_resume(fs_info);
+
+	if (create_uuid_tree) {
+		pr_info("btrfs: creating UUID tree\n");
+		ret = btrfs_create_uuid_tree(fs_info);
+		if (ret) {
+			pr_warn("btrfs: failed to create the UUID tree %d\n",
+				ret);
+			close_ctree(tree_root);
+			return ret;
+		}
+	} else if (check_uuid_tree ||
+		   btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) {
+		pr_info("btrfs: checking UUID tree\n");
+		ret = btrfs_check_uuid_tree(fs_info);
+		if (ret) {
+			pr_warn("btrfs: failed to check the UUID tree %d\n",
+				ret);
+			close_ctree(tree_root);
+			return ret;
+		}
+	} else {
+		fs_info->update_uuid_tree_gen = 1;
+	}
+
 	return 0;
 
 fail_qgroup:
@@ -2954,15 +3037,17 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev)
 	 */
 	for (i = 0; i < 1; i++) {
 		bytenr = btrfs_sb_offset(i);
-		if (bytenr + 4096 >= i_size_read(bdev->bd_inode))
+		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+					i_size_read(bdev->bd_inode))
 			break;
-		bh = __bread(bdev, bytenr / 4096, 4096);
+		bh = __bread(bdev, bytenr / 4096,
+					BTRFS_SUPER_INFO_SIZE);
 		if (!bh)
 			continue;
 
 		super = (struct btrfs_super_block *)bh->b_data;
 		if (btrfs_super_bytenr(super) != bytenr ||
-		    super->magic != cpu_to_le64(BTRFS_MAGIC)) {
+		    btrfs_super_magic(super) != BTRFS_MAGIC) {
 			brelse(bh);
 			continue;
 		}
@@ -3258,7 +3343,7 @@ int btrfs_calc_num_tolerated_disk_barrier_failures(
 					    BTRFS_BLOCK_GROUP_RAID10)) {
 						num_tolerated_disk_barrier_failures = 1;
 					} else if (flags &
-						   BTRFS_BLOCK_GROUP_RAID5) {
+						   BTRFS_BLOCK_GROUP_RAID6) {
 						num_tolerated_disk_barrier_failures = 2;
 					}
 				}
@@ -3282,7 +3367,6 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 	int total_errors = 0;
 	u64 flags;
 
-	max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1;
 	do_barriers = !btrfs_test_opt(root, NOBARRIER);
 	backup_super_roots(root->fs_info);
 
@@ -3291,6 +3375,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	head = &root->fs_info->fs_devices->devices;
+	max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1;
 
 	if (do_barriers) {
 		ret = barrier_all_devices(root->fs_info);
@@ -3332,9 +3417,12 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 	if (total_errors > max_errors) {
 		printk(KERN_ERR "btrfs: %d errors while writing supers\n",
 		       total_errors);
+		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
-		/* This shouldn't happen. FUA is masked off if unsupported */
-		BUG();
+		/* FUA is masked off if unsupported and can't be the reason */
+		btrfs_error(root->fs_info, -EIO,
+			    "%d errors while writing supers", total_errors);
+		return -EIO;
 	}
 
 	total_errors = 0;
@@ -3366,7 +3454,9 @@ int write_ctree_super(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
+/* Drop a fs root from the radix tree and free it. */
+void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
+				  struct btrfs_root *root)
 {
 	spin_lock(&fs_info->fs_roots_radix_lock);
 	radix_tree_delete(&fs_info->fs_roots_radix,
@@ -3390,6 +3480,8 @@ static void free_fs_root(struct btrfs_root *root)
 {
 	iput(root->cache_inode);
 	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
+	btrfs_free_block_rsv(root, root->orphan_block_rsv);
+	root->orphan_block_rsv = NULL;
 	if (root->anon_dev)
 		free_anon_bdev(root->anon_dev);
 	free_extent_buffer(root->node);
@@ -3397,7 +3489,12 @@ static void free_fs_root(struct btrfs_root *root)
 	kfree(root->free_ino_ctl);
 	kfree(root->free_ino_pinned);
 	kfree(root->name);
-	kfree(root);
+	btrfs_put_fs_root(root);
+}
+
+void btrfs_free_fs_root(struct btrfs_root *root)
+{
+	free_fs_root(root);
 }
 
 int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
@@ -3474,6 +3571,11 @@ int close_ctree(struct btrfs_root *root)
 	fs_info->closing = 1;
 	smp_mb();
 
+	/* wait for the uuid_scan task to finish */
+	down(&fs_info->uuid_tree_rescan_sem);
+	/* avoid complains from lockdep et al., set sem back to initial state */
+	up(&fs_info->uuid_tree_rescan_sem);
+
 	/* pause restriper - we want to resume on mount */
 	btrfs_pause_balance(fs_info);
 
@@ -3537,6 +3639,9 @@ int close_ctree(struct btrfs_root *root)
 
 	btrfs_free_stripe_hash_table(fs_info);
 
+	btrfs_free_block_rsv(root, root->orphan_block_rsv);
+	root->orphan_block_rsv = NULL;
+
 	return 0;
 }
 
@@ -3572,9 +3677,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 	if (transid != root->fs_info->generation)
 		WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, "
 		       "found %llu running %llu\n",
-			(unsigned long long)buf->start,
-			(unsigned long long)transid,
-			(unsigned long long)root->fs_info->generation);
+			buf->start, transid, root->fs_info->generation);
 	was_dirty = set_extent_buffer_dirty(buf);
 	if (!was_dirty)
 		__percpu_counter_add(&root->fs_info->dirty_metadata_bytes,
@@ -3653,7 +3756,7 @@ static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
 	INIT_LIST_HEAD(&splice);
 
 	mutex_lock(&root->fs_info->ordered_operations_mutex);
-	spin_lock(&root->fs_info->ordered_extent_lock);
+	spin_lock(&root->fs_info->ordered_root_lock);
 
 	list_splice_init(&t->ordered_operations, &splice);
 	while (!list_empty(&splice)) {
@@ -3661,14 +3764,14 @@ static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
 					 ordered_operations);
 
 		list_del_init(&btrfs_inode->ordered_operations);
-		spin_unlock(&root->fs_info->ordered_extent_lock);
+		spin_unlock(&root->fs_info->ordered_root_lock);
 
 		btrfs_invalidate_inodes(btrfs_inode->root);
 
-		spin_lock(&root->fs_info->ordered_extent_lock);
+		spin_lock(&root->fs_info->ordered_root_lock);
 	}
 
-	spin_unlock(&root->fs_info->ordered_extent_lock);
+	spin_unlock(&root->fs_info->ordered_root_lock);
 	mutex_unlock(&root->fs_info->ordered_operations_mutex);
 }
 
@@ -3676,19 +3779,40 @@ static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
 {
 	struct btrfs_ordered_extent *ordered;
 
-	spin_lock(&root->fs_info->ordered_extent_lock);
+	spin_lock(&root->ordered_extent_lock);
 	/*
 	 * This will just short circuit the ordered completion stuff which will
 	 * make sure the ordered extent gets properly cleaned up.
 	 */
-	list_for_each_entry(ordered, &root->fs_info->ordered_extents,
+	list_for_each_entry(ordered, &root->ordered_extents,
 			    root_extent_list)
 		set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
-	spin_unlock(&root->fs_info->ordered_extent_lock);
+	spin_unlock(&root->ordered_extent_lock);
 }
 
-int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
-			       struct btrfs_root *root)
+static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_root *root;
+	struct list_head splice;
+
+	INIT_LIST_HEAD(&splice);
+
+	spin_lock(&fs_info->ordered_root_lock);
+	list_splice_init(&fs_info->ordered_roots, &splice);
+	while (!list_empty(&splice)) {
+		root = list_first_entry(&splice, struct btrfs_root,
+					ordered_root);
+		list_del_init(&root->ordered_root);
+
+		btrfs_destroy_ordered_extents(root);
+
+		cond_resched_lock(&fs_info->ordered_root_lock);
+	}
+	spin_unlock(&fs_info->ordered_root_lock);
+}
+
+static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
+				      struct btrfs_root *root)
 {
 	struct rb_node *node;
 	struct btrfs_delayed_ref_root *delayed_refs;
@@ -3706,6 +3830,7 @@ int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 
 	while ((node = rb_first(&delayed_refs->root)) != NULL) {
 		struct btrfs_delayed_ref_head *head = NULL;
+		bool pin_bytes = false;
 
 		ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
 		atomic_set(&ref->refs, 1);
@@ -3726,8 +3851,7 @@ int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 			}
 
 			if (head->must_insert_reserved)
-				btrfs_pin_extent(root, ref->bytenr,
-						 ref->num_bytes, 1);
+				pin_bytes = true;
 			btrfs_free_delayed_extent_op(head->extent_op);
 			delayed_refs->num_heads--;
 			if (list_empty(&head->cluster))
@@ -3738,9 +3862,13 @@ int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 		ref->in_tree = 0;
 		rb_erase(&ref->rb_node, &delayed_refs->root);
 		delayed_refs->num_entries--;
-		if (head)
-			mutex_unlock(&head->mutex);
 		spin_unlock(&delayed_refs->lock);
+		if (head) {
+			if (pin_bytes)
+				btrfs_pin_extent(root, ref->bytenr,
+						 ref->num_bytes, 1);
+			mutex_unlock(&head->mutex);
+		}
 		btrfs_put_delayed_ref(ref);
 
 		cond_resched();
@@ -3777,24 +3905,49 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
 
 	INIT_LIST_HEAD(&splice);
 
-	spin_lock(&root->fs_info->delalloc_lock);
-	list_splice_init(&root->fs_info->delalloc_inodes, &splice);
+	spin_lock(&root->delalloc_lock);
+	list_splice_init(&root->delalloc_inodes, &splice);
 
 	while (!list_empty(&splice)) {
-		btrfs_inode = list_entry(splice.next, struct btrfs_inode,
-				    delalloc_inodes);
+		btrfs_inode = list_first_entry(&splice, struct btrfs_inode,
+					       delalloc_inodes);
 
 		list_del_init(&btrfs_inode->delalloc_inodes);
 		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
 			  &btrfs_inode->runtime_flags);
-		spin_unlock(&root->fs_info->delalloc_lock);
+		spin_unlock(&root->delalloc_lock);
 
 		btrfs_invalidate_inodes(btrfs_inode->root);
 
-		spin_lock(&root->fs_info->delalloc_lock);
+		spin_lock(&root->delalloc_lock);
 	}
 
-	spin_unlock(&root->fs_info->delalloc_lock);
+	spin_unlock(&root->delalloc_lock);
+}
+
+static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_root *root;
+	struct list_head splice;
+
+	INIT_LIST_HEAD(&splice);
+
+	spin_lock(&fs_info->delalloc_root_lock);
+	list_splice_init(&fs_info->delalloc_roots, &splice);
+	while (!list_empty(&splice)) {
+		root = list_first_entry(&splice, struct btrfs_root,
+					 delalloc_root);
+		list_del_init(&root->delalloc_root);
+		root = btrfs_grab_fs_root(root);
+		BUG_ON(!root);
+		spin_unlock(&fs_info->delalloc_root_lock);
+
+		btrfs_destroy_delalloc_inodes(root);
+		btrfs_put_fs_root(root);
+
+		spin_lock(&fs_info->delalloc_root_lock);
+	}
+	spin_unlock(&fs_info->delalloc_root_lock);
 }
 
 static int btrfs_destroy_marked_extents(struct btrfs_root *root,
@@ -3878,19 +4031,14 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 	btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv,
 				cur_trans->dirty_pages.dirty_bytes);
 
-	/* FIXME: cleanup wait for commit */
-	cur_trans->in_commit = 1;
-	cur_trans->blocked = 1;
+	cur_trans->state = TRANS_STATE_COMMIT_START;
 	wake_up(&root->fs_info->transaction_blocked_wait);
 
 	btrfs_evict_pending_snapshots(cur_trans);
 
-	cur_trans->blocked = 0;
+	cur_trans->state = TRANS_STATE_UNBLOCKED;
 	wake_up(&root->fs_info->transaction_wait);
 
-	cur_trans->commit_done = 1;
-	wake_up(&cur_trans->commit_wait);
-
 	btrfs_destroy_delayed_inodes(root);
 	btrfs_assert_delayed_root_empty(root);
 
@@ -3899,6 +4047,9 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 	btrfs_destroy_pinned_extent(root,
 				    root->fs_info->pinned_extents);
 
+	cur_trans->state =TRANS_STATE_COMPLETED;
+	wake_up(&cur_trans->commit_wait);
+
 	/*
 	memset(cur_trans, 0, sizeof(*cur_trans));
 	kmem_cache_free(btrfs_transaction_cachep, cur_trans);
@@ -3914,7 +4065,7 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 
 	spin_lock(&root->fs_info->trans_lock);
 	list_splice_init(&root->fs_info->trans_list, &list);
-	root->fs_info->trans_no_join = 1;
+	root->fs_info->running_transaction = NULL;
 	spin_unlock(&root->fs_info->trans_lock);
 
 	while (!list_empty(&list)) {
@@ -3922,37 +4073,31 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 
 		btrfs_destroy_ordered_operations(t, root);
 
-		btrfs_destroy_ordered_extents(root);
+		btrfs_destroy_all_ordered_extents(root->fs_info);
 
 		btrfs_destroy_delayed_refs(t, root);
 
-		/* FIXME: cleanup wait for commit */
-		t->in_commit = 1;
-		t->blocked = 1;
+		/*
+		 *  FIXME: cleanup wait for commit
+		 *  We needn't acquire the lock here, because we are during
+		 *  the umount, there is no other task which will change it.
+		 */
+		t->state = TRANS_STATE_COMMIT_START;
 		smp_mb();
 		if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
 			wake_up(&root->fs_info->transaction_blocked_wait);
 
 		btrfs_evict_pending_snapshots(t);
 
-		t->blocked = 0;
+		t->state = TRANS_STATE_UNBLOCKED;
 		smp_mb();
 		if (waitqueue_active(&root->fs_info->transaction_wait))
 			wake_up(&root->fs_info->transaction_wait);
 
-		t->commit_done = 1;
-		smp_mb();
-		if (waitqueue_active(&t->commit_wait))
-			wake_up(&t->commit_wait);
-
 		btrfs_destroy_delayed_inodes(root);
 		btrfs_assert_delayed_root_empty(root);
 
-		btrfs_destroy_delalloc_inodes(root);
-
-		spin_lock(&root->fs_info->trans_lock);
-		root->fs_info->running_transaction = NULL;
-		spin_unlock(&root->fs_info->trans_lock);
+		btrfs_destroy_all_delalloc_inodes(root->fs_info);
 
 		btrfs_destroy_marked_extents(root, &t->dirty_pages,
 					     EXTENT_DIRTY);
@@ -3960,15 +4105,17 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 		btrfs_destroy_pinned_extent(root,
 					    root->fs_info->pinned_extents);
 
+		t->state = TRANS_STATE_COMPLETED;
+		smp_mb();
+		if (waitqueue_active(&t->commit_wait))
+			wake_up(&t->commit_wait);
+
 		atomic_set(&t->use_count, 0);
 		list_del_init(&t->list);
 		memset(t, 0, sizeof(*t));
 		kmem_cache_free(btrfs_transaction_cachep, t);
 	}
 
-	spin_lock(&root->fs_info->trans_lock);
-	root->fs_info->trans_no_join = 0;
-	spin_unlock(&root->fs_info->trans_lock);
 	mutex_unlock(&root->fs_info->transaction_kthread_mutex);
 
 	return 0;