Merge remote-tracking branch 'btrfs-kdave/for-next'

36 files changed, 1258 insertions, 873 deletions

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 5982c8a71f02..06ef50712acd 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1522,12 +1522,23 @@ out:
 
 unsigned int btrfs_compress_str2level(const char *str)
 {
-	if (strncmp(str, "zlib", 4) != 0)
+	long level;
+	int max;
+
+	if (strncmp(str, "zlib", 4) == 0)
+		max = 9;
+	else if (strncmp(str, "zstd", 4) == 0)
+		max = 15; // encoded on 4 bits, real max is 22
+	else
 		return 0;
 
-	/* Accepted form: zlib:1 up to zlib:9 and nothing left after the number */
-	if (str[4] == ':' && '1' <= str[5] && str[5] <= '9' && str[6] == 0)
-		return str[5] - '0';
+	/* Accepted form: zxxx:1 up to zxxx:9 and nothing left after the number */
+	str += 4;
+	if (*str == ':')
+		str++;
+
+	if (kstrtoul(str, 10, &level))
+		return BTRFS_ZLIB_DEFAULT_LEVEL;
 
-	return BTRFS_ZLIB_DEFAULT_LEVEL;
+	return (level > max) ? BTRFS_ZLIB_DEFAULT_LEVEL : level;
 }
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 0868cc554f14..6b692903a23c 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -75,7 +75,7 @@ struct compressed_bio {
 	u32 sums;
 };
 
-void btrfs_init_compress(void);
+void __init btrfs_init_compress(void);
 void btrfs_exit_compress(void);
 
 int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 531e0a8645b0..1e74cf826532 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1032,14 +1032,17 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 		     root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) &&
 		    !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) {
 			ret = btrfs_inc_ref(trans, root, buf, 1);
-			BUG_ON(ret); /* -ENOMEM */
+			if (ret)
+				return ret;
 
 			if (root->root_key.objectid ==
 			    BTRFS_TREE_RELOC_OBJECTID) {
 				ret = btrfs_dec_ref(trans, root, buf, 0);
-				BUG_ON(ret); /* -ENOMEM */
+				if (ret)
+					return ret;
 				ret = btrfs_inc_ref(trans, root, cow, 1);
-				BUG_ON(ret); /* -ENOMEM */
+				if (ret)
+					return ret;
 			}
 			new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
 		} else {
@@ -1049,7 +1052,8 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 				ret = btrfs_inc_ref(trans, root, cow, 1);
 			else
 				ret = btrfs_inc_ref(trans, root, cow, 0);
-			BUG_ON(ret); /* -ENOMEM */
+			if (ret)
+				return ret;
 		}
 		if (new_flags != 0) {
 			int level = btrfs_header_level(buf);
@@ -1068,9 +1072,11 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 				ret = btrfs_inc_ref(trans, root, cow, 1);
 			else
 				ret = btrfs_inc_ref(trans, root, cow, 0);
-			BUG_ON(ret); /* -ENOMEM */
+			if (ret)
+				return ret;
 			ret = btrfs_dec_ref(trans, root, buf, 1);
-			BUG_ON(ret); /* -ENOMEM */
+			if (ret)
+				return ret;
 		}
 		clean_tree_block(fs_info, buf);
 		*last_ref = 1;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 13c260b525a1..09b72b6996ce 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3060,15 +3060,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
 					  struct btrfs_path *path, u64 dir,
 					  const char *name, u16 name_len,
 					  int mod);
-int verify_dir_item(struct btrfs_fs_info *fs_info,
-		    struct extent_buffer *leaf, int slot,
-		    struct btrfs_dir_item *dir_item);
 struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info,
 						 struct btrfs_path *path,
 						 const char *name,
 						 int name_len);
-bool btrfs_is_name_len_valid(struct extent_buffer *leaf, int slot,
-			     unsigned long start, u16 name_len);
 
 /* orphan.c */
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
@@ -3197,7 +3192,7 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
 struct inode *btrfs_alloc_inode(struct super_block *sb);
 void btrfs_destroy_inode(struct inode *inode);
 int btrfs_drop_inode(struct inode *inode);
-int btrfs_init_cachep(void);
+int __init btrfs_init_cachep(void);
 void btrfs_destroy_cachep(void);
 long btrfs_ioctl_trans_end(struct file *file);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
@@ -3248,7 +3243,7 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 			   struct file *dst_file, u64 dst_loff);
 
 /* file.c */
-int btrfs_auto_defrag_init(void);
+int __init btrfs_auto_defrag_init(void);
 void btrfs_auto_defrag_exit(void);
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 			   struct btrfs_inode *inode);
@@ -3283,7 +3278,7 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root);
 
 /* sysfs.c */
-int btrfs_init_sysfs(void);
+int __init btrfs_init_sysfs(void);
 void btrfs_exit_sysfs(void);
 int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info);
 void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 5d73f79ded8b..f8e59ac4967e 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1279,40 +1279,42 @@ static void btrfs_async_run_delayed_root(struct btrfs_work *work)
 	if (!path)
 		goto out;
 
-again:
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND / 2)
-		goto free_path;
+	do {
+		if (atomic_read(&delayed_root->items) <
+		    BTRFS_DELAYED_BACKGROUND / 2)
+			break;
 
-	delayed_node = btrfs_first_prepared_delayed_node(delayed_root);
-	if (!delayed_node)
-		goto free_path;
+		delayed_node = btrfs_first_prepared_delayed_node(delayed_root);
+		if (!delayed_node)
+			break;
 
-	path->leave_spinning = 1;
-	root = delayed_node->root;
+		path->leave_spinning = 1;
+		root = delayed_node->root;
 
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans))
-		goto release_path;
+		trans = btrfs_join_transaction(root);
+		if (IS_ERR(trans)) {
+			btrfs_release_path(path);
+			btrfs_release_prepared_delayed_node(delayed_node);
+			total_done++;
+			continue;
+		}
 
-	block_rsv = trans->block_rsv;
-	trans->block_rsv = &root->fs_info->delayed_block_rsv;
+		block_rsv = trans->block_rsv;
+		trans->block_rsv = &root->fs_info->delayed_block_rsv;
 
-	__btrfs_commit_inode_delayed_items(trans, path, delayed_node);
+		__btrfs_commit_inode_delayed_items(trans, path, delayed_node);
 
-	trans->block_rsv = block_rsv;
-	btrfs_end_transaction(trans);
-	btrfs_btree_balance_dirty_nodelay(root->fs_info);
+		trans->block_rsv = block_rsv;
+		btrfs_end_transaction(trans);
+		btrfs_btree_balance_dirty_nodelay(root->fs_info);
 
-release_path:
-	btrfs_release_path(path);
-	total_done++;
+		btrfs_release_path(path);
+		btrfs_release_prepared_delayed_node(delayed_node);
+		total_done++;
 
-	btrfs_release_prepared_delayed_node(delayed_node);
-	if ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK) ||
-	    total_done < async_work->nr)
-		goto again;
+	} while ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK)
+		 || total_done < async_work->nr);
 
-free_path:
 	btrfs_free_path(path);
 out:
 	wake_up(&delayed_root->wait);
@@ -1325,10 +1327,6 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 {
 	struct btrfs_async_delayed_work *async_work;
 
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND ||
-	    btrfs_workqueue_normal_congested(fs_info->delayed_workers))
-		return 0;
-
 	async_work = kmalloc(sizeof(*async_work), GFP_NOFS);
 	if (!async_work)
 		return -ENOMEM;
@@ -1364,7 +1362,8 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_delayed_root *delayed_root = fs_info->delayed_root;
 
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
+	if ((atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND) ||
+		btrfs_workqueue_normal_congested(fs_info->delayed_workers))
 		return;
 
 	if (atomic_read(&delayed_root->items) >= BTRFS_DELAYED_WRITEBACK) {
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 83be8f9fd906..a1a40cf382e3 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -937,7 +937,7 @@ void btrfs_delayed_ref_exit(void)
 	kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
 }
 
-int btrfs_delayed_ref_init(void)
+int __init btrfs_delayed_ref_init(void)
 {
 	btrfs_delayed_ref_head_cachep = kmem_cache_create(
 				"btrfs_delayed_ref_head",
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index a43af432f859..c4f625e5a691 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -203,7 +203,7 @@ extern struct kmem_cache *btrfs_delayed_tree_ref_cachep;
 extern struct kmem_cache *btrfs_delayed_data_ref_cachep;
 extern struct kmem_cache *btrfs_delayed_extent_op_cachep;
 
-int btrfs_delayed_ref_init(void);
+int __init btrfs_delayed_ref_init(void);
 void btrfs_delayed_ref_exit(void);
 
 static inline struct btrfs_delayed_extent_op *
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 41cb9196eaa8..cbe421605cd5 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -403,8 +403,6 @@ struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info,
 			btrfs_dir_data_len(leaf, dir_item);
 		name_ptr = (unsigned long)(dir_item + 1);
 
-		if (verify_dir_item(fs_info, leaf, path->slots[0], dir_item))
-			return NULL;
 		if (btrfs_dir_name_len(leaf, dir_item) == name_len &&
 		    memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0)
 			return dir_item;
@@ -450,109 +448,3 @@ int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans,
 	}
 	return ret;
 }
-
-int verify_dir_item(struct btrfs_fs_info *fs_info,
-		    struct extent_buffer *leaf,
-		    int slot,
-		    struct btrfs_dir_item *dir_item)
-{
-	u16 namelen = BTRFS_NAME_LEN;
-	int ret;
-	u8 type = btrfs_dir_type(leaf, dir_item);
-
-	if (type >= BTRFS_FT_MAX) {
-		btrfs_crit(fs_info, "invalid dir item type: %d", (int)type);
-		return 1;
-	}
-
-	if (type == BTRFS_FT_XATTR)
-		namelen = XATTR_NAME_MAX;
-
-	if (btrfs_dir_name_len(leaf, dir_item) > namelen) {
-		btrfs_crit(fs_info, "invalid dir item name len: %u",
-		       (unsigned)btrfs_dir_name_len(leaf, dir_item));
-		return 1;
-	}
-
-	namelen = btrfs_dir_name_len(leaf, dir_item);
-	ret = btrfs_is_name_len_valid(leaf, slot,
-				      (unsigned long)(dir_item + 1), namelen);
-	if (!ret)
-		return 1;
-
-	/* BTRFS_MAX_XATTR_SIZE is the same for all dir items */
-	if ((btrfs_dir_data_len(leaf, dir_item) +
-	     btrfs_dir_name_len(leaf, dir_item)) >
-					BTRFS_MAX_XATTR_SIZE(fs_info)) {
-		btrfs_crit(fs_info, "invalid dir item name + data len: %u + %u",
-			   (unsigned)btrfs_dir_name_len(leaf, dir_item),
-			   (unsigned)btrfs_dir_data_len(leaf, dir_item));
-		return 1;
-	}
-
-	return 0;
-}
-
-bool btrfs_is_name_len_valid(struct extent_buffer *leaf, int slot,
-			     unsigned long start, u16 name_len)
-{
-	struct btrfs_fs_info *fs_info = leaf->fs_info;
-	struct btrfs_key key;
-	u32 read_start;
-	u32 read_end;
-	u32 item_start;
-	u32 item_end;
-	u32 size;
-	bool ret = true;
-
-	ASSERT(start > BTRFS_LEAF_DATA_OFFSET);
-
-	read_start = start - BTRFS_LEAF_DATA_OFFSET;
-	read_end = read_start + name_len;
-	item_start = btrfs_item_offset_nr(leaf, slot);
-	item_end = btrfs_item_end_nr(leaf, slot);
-
-	btrfs_item_key_to_cpu(leaf, &key, slot);
-
-	switch (key.type) {
-	case BTRFS_DIR_ITEM_KEY:
-	case BTRFS_XATTR_ITEM_KEY:
-	case BTRFS_DIR_INDEX_KEY:
-		size = sizeof(struct btrfs_dir_item);
-		break;
-	case BTRFS_INODE_REF_KEY:
-		size = sizeof(struct btrfs_inode_ref);
-		break;
-	case BTRFS_INODE_EXTREF_KEY:
-		size = sizeof(struct btrfs_inode_extref);
-		break;
-	case BTRFS_ROOT_REF_KEY:
-	case BTRFS_ROOT_BACKREF_KEY:
-		size = sizeof(struct btrfs_root_ref);
-		break;
-	default:
-		ret = false;
-		goto out;
-	}
-
-	if (read_start < item_start) {
-		ret = false;
-		goto out;
-	}
-	if (read_end > item_end) {
-		ret = false;
-		goto out;
-	}
-
-	/* there shall be item(s) before name */
-	if (read_start - item_start < size) {
-		ret = false;
-		goto out;
-	}
-
-out:
-	if (!ret)
-		btrfs_crit(fs_info, "invalid dir item name len: %u",
-			   (unsigned int)name_len);
-	return ret;
-}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 10a2a579cc7f..82c96607fc46 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -220,7 +220,7 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
  * extents on the btree inode are pretty simple, there's one extent
  * that covers the entire device
  */
-static struct extent_map *btree_get_extent(struct btrfs_inode *inode,
+struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start, u64 len,
 		int create)
 {
@@ -285,7 +285,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
 			   int verify)
 {
 	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
-	char *result = NULL;
+	char result[BTRFS_CSUM_SIZE];
 	unsigned long len;
 	unsigned long cur_len;
 	unsigned long offset = BTRFS_CSUM_SIZE;
@@ -294,7 +294,6 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
 	unsigned long map_len;
 	int err;
 	u32 crc = ~(u32)0;
-	unsigned long inline_result;
 
 	len = buf->len - offset;
 	while (len > 0) {
@@ -308,13 +307,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
 		len -= cur_len;
 		offset += cur_len;
 	}
-	if (csum_size > sizeof(inline_result)) {
-		result = kzalloc(csum_size, GFP_NOFS);
-		if (!result)
-			return -ENOMEM;
-	} else {
-		result = (char *)&inline_result;
-	}
+	memset(result, 0, BTRFS_CSUM_SIZE);
 
 	btrfs_csum_final(crc, result);
 
@@ -329,15 +322,12 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
 				"%s checksum verify failed on %llu wanted %X found %X level %d",
 				fs_info->sb->s_id, buf->start,
 				val, found, btrfs_header_level(buf));
-			if (result != (char *)&inline_result)
-				kfree(result);
 			return -EUCLEAN;
 		}
 	} else {
 		write_extent_buffer(buf, result, 0, csum_size);
 	}
-	if (result != (char *)&inline_result)
-		kfree(result);
+
 	return 0;
 }
 
@@ -455,7 +445,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
 	io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	while (1) {
 		ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE,
-					       btree_get_extent, mirror_num);
+					       mirror_num);
 		if (!ret) {
 			if (!verify_parent_transid(io_tree, eb,
 						   parent_transid, 0))
@@ -1012,7 +1002,7 @@ void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr)
 	if (IS_ERR(buf))
 		return;
 	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
-				 buf, WAIT_NONE, btree_get_extent, 0);
+				 buf, WAIT_NONE, 0);
 	free_extent_buffer(buf);
 }
 
@@ -1031,7 +1021,7 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
 	set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
 
 	ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK,
-				       btree_get_extent, mirror_num);
+				       mirror_num);
 	if (ret) {
 		free_extent_buffer(buf);
 		return ret;
@@ -1243,7 +1233,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	struct btrfs_root *root;
 	struct btrfs_key key;
 	int ret = 0;
-	uuid_le uuid;
+	uuid_le uuid = { 0 };
 
 	root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	if (!root)
@@ -1284,7 +1274,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	btrfs_set_root_used(&root->root_item, leaf->len);
 	btrfs_set_root_last_snapshot(&root->root_item, 0);
 	btrfs_set_root_dirid(&root->root_item, 0);
-	uuid_le_gen(&uuid);
+	if (is_fstree(objectid))
+		uuid_le_gen(&uuid);
 	memcpy(root->root_item.uuid, uuid.b, BTRFS_UUID_SIZE);
 	root->root_item.drop_level = 0;
 
@@ -3396,9 +3387,10 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 	int errors_wait = 0;
 	blk_status_t ret;
 
+	lockdep_assert_held(&info->fs_devices->device_list_mutex);
 	/* send down all the barriers */
 	head = &info->fs_devices->devices;
-	list_for_each_entry_rcu(dev, head, dev_list) {
+	list_for_each_entry(dev, head, dev_list) {
 		if (dev->missing)
 			continue;
 		if (!dev->bdev)
@@ -3411,7 +3403,7 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 	}
 
 	/* wait for all the barriers */
-	list_for_each_entry_rcu(dev, head, dev_list) {
+	list_for_each_entry(dev, head, dev_list) {
 		if (dev->missing)
 			continue;
 		if (!dev->bdev) {
@@ -3510,7 +3502,7 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 		}
 	}
 
-	list_for_each_entry_rcu(dev, head, dev_list) {
+	list_for_each_entry(dev, head, dev_list) {
 		if (!dev->bdev) {
 			total_errors++;
 			continue;
@@ -3551,7 +3543,7 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 	}
 
 	total_errors = 0;
-	list_for_each_entry_rcu(dev, head, dev_list) {
+	list_for_each_entry(dev, head, dev_list) {
 		if (!dev->bdev)
 			continue;
 		if (!dev->in_fs_metadata || !dev->writeable)
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 7f7c35d6347a..301151a50ac1 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -149,6 +149,9 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 				     u64 objectid);
 int btree_lock_page_hook(struct page *page, void *data,
 				void (*flush_fn)(void *));
+struct extent_map *btree_get_extent(struct btrfs_inode *inode,
+		struct page *page, size_t pg_offset, u64 start, u64 len,
+		int create);
 int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags);
 int __init btrfs_end_io_wq_init(void);
 void btrfs_end_io_wq_exit(void);
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 3aeb5770f896..ddaccad469f8 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -283,11 +283,6 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 		name_len = btrfs_inode_ref_name_len(leaf, iref);
 	}
 
-	ret = btrfs_is_name_len_valid(leaf, path->slots[0], name_ptr, name_len);
-	if (!ret) {
-		btrfs_free_path(path);
-		return -EIO;
-	}
 	read_extent_buffer(leaf, name, name_ptr, name_len);
 	btrfs_free_path(path);
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4497f937e8fb..fa78da608ff2 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2894,7 +2894,7 @@ int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
 	struct btrfs_block_rsv *global_rsv;
 	u64 num_heads = trans->transaction->delayed_refs.num_heads_ready;
 	u64 csum_bytes = trans->transaction->delayed_refs.pending_csums;
-	u64 num_dirty_bgs = trans->transaction->num_dirty_bgs;
+	unsigned int num_dirty_bgs = trans->transaction->num_dirty_bgs;
 	u64 num_bytes, num_dirty_bgs_bytes;
 	int ret = 0;
 
@@ -4945,12 +4945,12 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 		bytes = 0;
 	else
 		bytes -= delayed_rsv->size;
+	spin_unlock(&delayed_rsv->lock);
+
 	if (percpu_counter_compare(&space_info->total_bytes_pinned,
 				   bytes) < 0) {
-		spin_unlock(&delayed_rsv->lock);
 		return -ENOSPC;
 	}
-	spin_unlock(&delayed_rsv->lock);
 
 commit:
 	trans = btrfs_join_transaction(fs_info->extent_root);
@@ -5738,8 +5738,8 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
  * or return if we already have enough space.  This will also handle the resreve
  * tracepoint for the reserved amount.
  */
-int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
-			   enum btrfs_reserve_flush_enum flush)
+static int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
+				  enum btrfs_reserve_flush_enum flush)
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 012d63870b99..ef72efef8b39 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -21,6 +21,7 @@
 #include "locking.h"
 #include "rcu-string.h"
 #include "backref.h"
+#include "disk-io.h"
 
 static struct kmem_cache *extent_state_cache;
 static struct kmem_cache *extent_buffer_cache;
@@ -109,8 +110,6 @@ struct tree_entry {
 struct extent_page_data {
 	struct bio *bio;
 	struct extent_io_tree *tree;
-	get_extent_t *get_extent;
-
 	/* tells writepage not to lock the state bits for this range
 	 * it still does the unlocking
 	 */
@@ -581,7 +580,7 @@ static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
  *
  * This takes the tree lock, and returns 0 on success and < 0 on error.
  */
-static int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 			      unsigned bits, int wake, int delete,
 			      struct extent_state **cached_state,
 			      gfp_t mask, struct extent_changeset *changeset)
@@ -1295,10 +1294,10 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 
 int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		     unsigned bits, int wake, int delete,
-		     struct extent_state **cached, gfp_t mask)
+		     struct extent_state **cached)
 {
 	return __clear_extent_bit(tree, start, end, bits, wake, delete,
-				  cached, mask, NULL);
+				  cached, GFP_NOFS, NULL);
 }
 
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
@@ -1348,7 +1347,7 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 	if (err == -EEXIST) {
 		if (failed_start > start)
 			clear_extent_bit(tree, start, failed_start - 1,
-					 EXTENT_LOCKED, 1, 0, NULL, GFP_NOFS);
+					 EXTENT_LOCKED, 1, 0, NULL);
 		return 0;
 	}
 	return 1;
@@ -1744,7 +1743,7 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				 unsigned long page_ops)
 {
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, clear_bits, 1, 0,
-			 NULL, GFP_NOFS);
+			 NULL);
 
 	__process_pages_contig(inode->i_mapping, locked_page,
 			       start >> PAGE_SHIFT, end >> PAGE_SHIFT,
@@ -3092,9 +3091,8 @@ out:
 static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 					     struct page *pages[], int nr_pages,
 					     u64 start, u64 end,
-					     get_extent_t *get_extent,
 					     struct extent_map **em_cached,
-					     struct bio **bio, int mirror_num,
+					     struct bio **bio,
 					     unsigned long *bio_flags,
 					     u64 *prev_em_start)
 {
@@ -3115,18 +3113,17 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 	}
 
 	for (index = 0; index < nr_pages; index++) {
-		__do_readpage(tree, pages[index], get_extent, em_cached, bio,
-			      mirror_num, bio_flags, 0, prev_em_start);
+		__do_readpage(tree, pages[index], btrfs_get_extent, em_cached,
+				bio, 0, bio_flags, 0, prev_em_start);
 		put_page(pages[index]);
 	}
 }
 
 static void __extent_readpages(struct extent_io_tree *tree,
 			       struct page *pages[],
-			       int nr_pages, get_extent_t *get_extent,
+			       int nr_pages,
 			       struct extent_map **em_cached,
-			       struct bio **bio, int mirror_num,
-			       unsigned long *bio_flags,
+			       struct bio **bio, unsigned long *bio_flags,
 			       u64 *prev_em_start)
 {
 	u64 start = 0;
@@ -3146,8 +3143,8 @@ static void __extent_readpages(struct extent_io_tree *tree,
 		} else {
 			__do_contiguous_readpages(tree, &pages[first_index],
 						  index - first_index, start,
-						  end, get_extent, em_cached,
-						  bio, mirror_num, bio_flags,
+						  end, em_cached,
+						  bio, bio_flags,
 						  prev_em_start);
 			start = page_start;
 			end = start + PAGE_SIZE - 1;
@@ -3158,9 +3155,8 @@ static void __extent_readpages(struct extent_io_tree *tree,
 	if (end)
 		__do_contiguous_readpages(tree, &pages[first_index],
 					  index - first_index, start,
-					  end, get_extent, em_cached, bio,
-					  mirror_num, bio_flags,
-					  prev_em_start);
+					  end, em_cached, bio,
+					  bio_flags, prev_em_start);
 }
 
 static int __extent_read_full_page(struct extent_io_tree *tree,
@@ -3375,7 +3371,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 							 page_end, NULL, 1);
 			break;
 		}
-		em = epd->get_extent(BTRFS_I(inode), page, pg_offset, cur,
+		em = btrfs_get_extent(BTRFS_I(inode), page, pg_offset, cur,
 				     end - cur + 1, 1);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
@@ -4060,14 +4056,12 @@ static noinline void flush_write_bio(void *data)
 }
 
 int extent_write_full_page(struct extent_io_tree *tree, struct page *page,
-			  get_extent_t *get_extent,
 			  struct writeback_control *wbc)
 {
 	int ret;
 	struct extent_page_data epd = {
 		.bio = NULL,
 		.tree = tree,
-		.get_extent = get_extent,
 		.extent_locked = 0,
 		.sync_io = wbc->sync_mode == WB_SYNC_ALL,
 	};
@@ -4079,8 +4073,7 @@ int extent_write_full_page(struct extent_io_tree *tree, struct page *page,
 }
 
 int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
-			      u64 start, u64 end, get_extent_t *get_extent,
-			      int mode)
+			      u64 start, u64 end, int mode)
 {
 	int ret = 0;
 	struct address_space *mapping = inode->i_mapping;
@@ -4091,7 +4084,6 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
 	struct extent_page_data epd = {
 		.bio = NULL,
 		.tree = tree,
-		.get_extent = get_extent,
 		.extent_locked = 1,
 		.sync_io = mode == WB_SYNC_ALL,
 	};
@@ -4123,14 +4115,12 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
 
 int extent_writepages(struct extent_io_tree *tree,
 		      struct address_space *mapping,
-		      get_extent_t *get_extent,
 		      struct writeback_control *wbc)
 {
 	int ret = 0;
 	struct extent_page_data epd = {
 		.bio = NULL,
 		.tree = tree,
-		.get_extent = get_extent,
 		.extent_locked = 0,
 		.sync_io = wbc->sync_mode == WB_SYNC_ALL,
 	};
@@ -4143,8 +4133,7 @@ int extent_writepages(struct extent_io_tree *tree,
 
 int extent_readpages(struct extent_io_tree *tree,
 		     struct address_space *mapping,
-		     struct list_head *pages, unsigned nr_pages,
-		     get_extent_t get_extent)
+		     struct list_head *pages, unsigned nr_pages)
 {
 	struct bio *bio = NULL;
 	unsigned page_idx;
@@ -4170,13 +4159,13 @@ int extent_readpages(struct extent_io_tree *tree,
 		pagepool[nr++] = page;
 		if (nr < ARRAY_SIZE(pagepool))
 			continue;
-		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, &prev_em_start);
+		__extent_readpages(tree, pagepool, nr, &em_cached, &bio,
+				&bio_flags, &prev_em_start);
 		nr = 0;
 	}
 	if (nr)
-		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, &prev_em_start);
+		__extent_readpages(tree, pagepool, nr, &em_cached, &bio,
+				&bio_flags, &prev_em_start);
 
 	if (em_cached)
 		free_extent_map(em_cached);
@@ -4209,7 +4198,7 @@ int extent_invalidatepage(struct extent_io_tree *tree,
 	clear_extent_bit(tree, start, end,
 			 EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
 			 EXTENT_DO_ACCOUNTING,
-			 1, 1, &cached_state, GFP_NOFS);
+			 1, 1, &cached_state);
 	return 0;
 }
 
@@ -4234,9 +4223,9 @@ static int try_release_extent_state(struct extent_map_tree *map,
 		 * at this point we can safely clear everything except the
 		 * locked bit and the nodatasum bit
 		 */
-		ret = clear_extent_bit(tree, start, end,
+		ret = __clear_extent_bit(tree, start, end,
 				 ~(EXTENT_LOCKED | EXTENT_NODATASUM),
-				 0, 0, NULL, mask);
+				 0, 0, NULL, mask, NULL);
 
 		/* if clear_extent_bit failed for enomem reasons,
 		 * we can't allow the release to continue.
@@ -4302,9 +4291,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
  * This maps until we find something past 'last'
  */
 static struct extent_map *get_extent_skip_holes(struct inode *inode,
-						u64 offset,
-						u64 last,
-						get_extent_t *get_extent)
+						u64 offset, u64 last)
 {
 	u64 sectorsize = btrfs_inode_sectorsize(inode);
 	struct extent_map *em;
@@ -4318,15 +4305,14 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode,
 		if (len == 0)
 			break;
 		len = ALIGN(len, sectorsize);
-		em = get_extent(BTRFS_I(inode), NULL, 0, offset, len, 0);
+		em = btrfs_get_extent_fiemap(BTRFS_I(inode), NULL, 0, offset,
+				len, 0);
 		if (IS_ERR_OR_NULL(em))
 			return em;
 
 		/* if this isn't a hole return it */
-		if (!test_bit(EXTENT_FLAG_VACANCY, &em->flags) &&
-		    em->block_start != EXTENT_MAP_HOLE) {
+		if (em->block_start != EXTENT_MAP_HOLE)
 			return em;
-		}
 
 		/* this is a hole, advance to the next extent */
 		offset = extent_map_end(em);
@@ -4451,7 +4437,7 @@ static int emit_last_fiemap_cache(struct btrfs_fs_info *fs_info,
 }
 
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
-		__u64 start, __u64 len, get_extent_t *get_extent)
+		__u64 start, __u64 len)
 {
 	int ret = 0;
 	u64 off = start;
@@ -4533,8 +4519,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len - 1,
 			 &cached_state);
 
-	em = get_extent_skip_holes(inode, start, last_for_get_extent,
-				   get_extent);
+	em = get_extent_skip_holes(inode, start, last_for_get_extent);
 	if (!em)
 		goto out;
 	if (IS_ERR(em)) {
@@ -4622,8 +4607,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		}
 
 		/* now scan forward to see if this is really the last extent. */
-		em = get_extent_skip_holes(inode, off, last_for_get_extent,
-					   get_extent);
+		em = get_extent_skip_holes(inode, off, last_for_get_extent);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
 			goto out;
@@ -5263,8 +5247,7 @@ int extent_buffer_uptodate(struct extent_buffer *eb)
 }
 
 int read_extent_buffer_pages(struct extent_io_tree *tree,
-			     struct extent_buffer *eb, int wait,
-			     get_extent_t *get_extent, int mirror_num)
+			     struct extent_buffer *eb, int wait, int mirror_num)
 {
 	unsigned long i;
 	struct page *page;
@@ -5324,7 +5307,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 
 			ClearPageError(page);
 			err = __extent_read_full_page(tree, page,
-						      get_extent, &bio,
+						      btree_get_extent, &bio,
 						      mirror_num, &bio_flags,
 						      REQ_META);
 			if (err) {
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 93dcae0c3183..c28f5ef88f42 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -300,19 +300,22 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 		unsigned bits, struct extent_changeset *changeset);
 int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		     unsigned bits, int wake, int delete,
-		     struct extent_state **cached, gfp_t mask);
+		     struct extent_state **cached);
+int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		     unsigned bits, int wake, int delete,
+		     struct extent_state **cached, gfp_t mask,
+		     struct extent_changeset *changeset);
 
 static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 {
-	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL,
-				GFP_NOFS);
+	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
 }
 
 static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
 		u64 end, struct extent_state **cached, gfp_t mask)
 {
-	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
-				mask);
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+				mask, NULL);
 }
 
 static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
@@ -323,8 +326,7 @@ static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
 	if (bits & EXTENT_LOCKED)
 		wake = 1;
 
-	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL,
-			GFP_NOFS);
+	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
 }
 
 int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
@@ -340,10 +342,10 @@ static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
 }
 
 static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state, gfp_t mask)
+		u64 end, struct extent_state **cached_state)
 {
-	return clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
-				cached_state, mask);
+	return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
+				cached_state, GFP_NOFS, NULL);
 }
 
 static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
@@ -358,7 +360,7 @@ static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
 {
 	return clear_extent_bit(tree, start, end,
 				EXTENT_DIRTY | EXTENT_DELALLOC |
-				EXTENT_DO_ACCOUNTING, 0, 0, NULL, GFP_NOFS);
+				EXTENT_DO_ACCOUNTING, 0, 0, NULL);
 }
 
 int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
@@ -402,23 +404,19 @@ int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
 int extent_invalidatepage(struct extent_io_tree *tree,
 			  struct page *page, unsigned long offset);
 int extent_write_full_page(struct extent_io_tree *tree, struct page *page,
-			  get_extent_t *get_extent,
 			  struct writeback_control *wbc);
 int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
-			      u64 start, u64 end, get_extent_t *get_extent,
-			      int mode);
+			      u64 start, u64 end, int mode);
 int extent_writepages(struct extent_io_tree *tree,
 		      struct address_space *mapping,
-		      get_extent_t *get_extent,
 		      struct writeback_control *wbc);
 int btree_write_cache_pages(struct address_space *mapping,
 			    struct writeback_control *wbc);
 int extent_readpages(struct extent_io_tree *tree,
 		     struct address_space *mapping,
-		     struct list_head *pages, unsigned nr_pages,
-		     get_extent_t get_extent);
+		     struct list_head *pages, unsigned nr_pages);
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
-		__u64 start, __u64 len, get_extent_t *get_extent);
+		__u64 start, __u64 len);
 void set_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
@@ -437,7 +435,7 @@ void free_extent_buffer_stale(struct extent_buffer *eb);
 #define WAIT_PAGE_LOCK	2
 int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     struct extent_buffer *eb, int wait,
-			     get_extent_t *get_extent, int mirror_num);
+			     int mirror_num);
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
 
 static inline unsigned long num_extent_pages(u64 start, u64 len)
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 64365bbc9b16..e9e285d45c7e 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -13,7 +13,6 @@
 /* bits for the flags field */
 #define EXTENT_FLAG_PINNED 0 /* this entry not yet on disk, don't free it */
 #define EXTENT_FLAG_COMPRESSED 1
-#define EXTENT_FLAG_VACANCY 2 /* no file extent item found */
 #define EXTENT_FLAG_PREALLOC 3 /* pre-allocated extent */
 #define EXTENT_FLAG_LOGGING 4 /* Logging this extent */
 #define EXTENT_FLAG_FILLING 5 /* Filling in a preallocated extent */
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index eb1bac7c8553..1589961f7bba 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1519,7 +1519,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 		clear_extent_bit(&inode->io_tree, start_pos, last_pos,
 				 EXTENT_DIRTY | EXTENT_DELALLOC |
 				 EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
-				 0, 0, cached_state, GFP_NOFS);
+				 0, 0, cached_state);
 		*lockstart = start_pos;
 		*lockend = last_pos;
 		ret = 1;
@@ -1755,7 +1755,7 @@ again:
 
 		if (copied > 0)
 			ret = btrfs_dirty_pages(inode, pages, dirty_pages,
-						pos, copied, NULL);
+						pos, copied, &cached_state);
 		if (extents_locked)
 			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 					     lockstart, lockend, &cached_state,
@@ -2019,10 +2019,19 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
 static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
 {
 	int ret;
+	struct blk_plug plug;
 
+	/*
+	 * This is only called in fsync, which would do synchronous writes, so
+	 * a plug can merge adjacent IOs as much as possible.  Esp. in case of
+	 * multiple disks using raid profile, a large IO can be split to
+	 * several segments of stripe length (currently 64K).
+	 */
+	blk_start_plug(&plug);
 	atomic_inc(&BTRFS_I(inode)->sync_writers);
 	ret = btrfs_fdatawrite_range(inode, start, end);
 	atomic_dec(&BTRFS_I(inode)->sync_writers);
+	blk_finish_plug(&plug);
 
 	return ret;
 }
@@ -2450,6 +2459,46 @@ static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len)
 	return ret;
 }
 
+static int btrfs_punch_hole_lock_range(struct inode *inode,
+				       const u64 lockstart,
+				       const u64 lockend,
+				       struct extent_state **cached_state)
+{
+	while (1) {
+		struct btrfs_ordered_extent *ordered;
+		int ret;
+
+		truncate_pagecache_range(inode, lockstart, lockend);
+
+		lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
+				 cached_state);
+		ordered = btrfs_lookup_first_ordered_extent(inode, lockend);
+
+		/*
+		 * We need to make sure we have no ordered extents in this range
+		 * and nobody raced in and read a page in this range, if we did
+		 * we need to try again.
+		 */
+		if ((!ordered ||
+		    (ordered->file_offset + ordered->len <= lockstart ||
+		     ordered->file_offset > lockend)) &&
+		     !btrfs_page_exists_in_range(inode, lockstart, lockend)) {
+			if (ordered)
+				btrfs_put_ordered_extent(ordered);
+			break;
+		}
+		if (ordered)
+			btrfs_put_ordered_extent(ordered);
+		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
+				     lockend, cached_state, GFP_NOFS);
+		ret = btrfs_wait_ordered_range(inode, lockstart,
+					       lockend - lockstart + 1);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
 static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -2566,38 +2615,11 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		goto out_only_mutex;
 	}
 
-	while (1) {
-		struct btrfs_ordered_extent *ordered;
-
-		truncate_pagecache_range(inode, lockstart, lockend);
-
-		lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				 &cached_state);
-		ordered = btrfs_lookup_first_ordered_extent(inode, lockend);
-
-		/*
-		 * We need to make sure we have no ordered extents in this range
-		 * and nobody raced in and read a page in this range, if we did
-		 * we need to try again.
-		 */
-		if ((!ordered ||
-		    (ordered->file_offset + ordered->len <= lockstart ||
-		     ordered->file_offset > lockend)) &&
-		     !btrfs_page_exists_in_range(inode, lockstart, lockend)) {
-			if (ordered)
-				btrfs_put_ordered_extent(ordered);
-			break;
-		}
-		if (ordered)
-			btrfs_put_ordered_extent(ordered);
-		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
-				     lockend, &cached_state, GFP_NOFS);
-		ret = btrfs_wait_ordered_range(inode, lockstart,
-					       lockend - lockstart + 1);
-		if (ret) {
-			inode_unlock(inode);
-			return ret;
-		}
+	ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend,
+					  &cached_state);
+	if (ret) {
+		inode_unlock(inode);
+		goto out_only_mutex;
 	}
 
 	path = btrfs_alloc_path();
@@ -2806,6 +2828,217 @@ insert:
 	return 0;
 }
 
+static int btrfs_fallocate_update_isize(struct inode *inode,
+					const u64 end,
+					const int mode)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	int ret;
+	int ret2;
+
+	if (mode & FALLOC_FL_KEEP_SIZE || end <= i_size_read(inode))
+		return 0;
+
+	trans = btrfs_start_transaction(root, 1);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	inode->i_ctime = current_time(inode);
+	i_size_write(inode, end);
+	btrfs_ordered_update_i_size(inode, end, NULL);
+	ret = btrfs_update_inode(trans, root, inode);
+	ret2 = btrfs_end_transaction(trans);
+
+	return ret ? ret : ret2;
+}
+
+static int btrfs_zero_range_check_range_boundary(struct inode *inode,
+						 u64 offset)
+{
+	const u64 sectorsize = btrfs_inode_sectorsize(inode);
+	struct extent_map *em;
+	int ret = 0;
+
+	offset = round_down(offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
+	if (IS_ERR(em))
+		return PTR_ERR(em);
+
+	if (em->block_start == EXTENT_MAP_HOLE)
+		ret = 1;
+
+	free_extent_map(em);
+	return ret;
+}
+
+static int btrfs_zero_range(struct inode *inode,
+			    loff_t offset,
+			    loff_t len,
+			    const int mode)
+{
+	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+	struct extent_map *em;
+	struct extent_changeset *data_reserved = NULL;
+	int ret;
+	u64 alloc_hint = 0;
+	const u64 sectorsize = btrfs_inode_sectorsize(inode);
+	u64 alloc_start = round_down(offset, sectorsize);
+	u64 alloc_end = round_up(offset + len, sectorsize);
+	u64 bytes_to_reserve = 0;
+	bool space_reserved = false;
+
+	inode_dio_wait(inode);
+
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0,
+			      alloc_start, alloc_end - alloc_start, 0);
+	if (IS_ERR(em)) {
+		ret = PTR_ERR(em);
+		goto out;
+	}
+
+	/*
+	 * Avoid hole punching and extent allocation for some cases. More cases
+	 * could be considered, but these are unlikely common and we keep things
+	 * as simple as possible for now. Also, intentionally, if the target
+	 * range contains one or more prealloc extents together with regular
+	 * extents and holes, we drop all the existing extents and allocate a
+	 * new prealloc extent, so that we get a larger contiguous disk extent.
+	 */
+	if (em->start <= alloc_start &&
+	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+		const u64 em_end = em->start + em->len;
+
+		if (em_end >= offset + len) {
+			/*
+			 * The whole range is already a prealloc extent,
+			 * do nothing except updating the inode's i_size if
+			 * needed.
+			 */
+			free_extent_map(em);
+			ret = btrfs_fallocate_update_isize(inode, offset + len,
+							   mode);
+			goto out;
+		}
+		/*
+		 * Part of the range is already a prealloc extent, so operate
+		 * only on the remaining part of the range.
+		 */
+		alloc_start = em_end;
+		ASSERT(IS_ALIGNED(alloc_start, sectorsize));
+		len = offset + len - alloc_start;
+		offset = alloc_start;
+		alloc_hint = em->block_start + em->len;
+	}
+	free_extent_map(em);
+
+	if (BTRFS_BYTES_TO_BLKS(fs_info, offset) ==
+	    BTRFS_BYTES_TO_BLKS(fs_info, offset + len - 1)) {
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0,
+				      alloc_start, sectorsize, 0);
+		if (IS_ERR(em)) {
+			ret = PTR_ERR(em);
+			goto out;
+		}
+
+		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+			free_extent_map(em);
+			ret = btrfs_fallocate_update_isize(inode, offset + len,
+							   mode);
+			goto out;
+		}
+		if (len < sectorsize && em->block_start != EXTENT_MAP_HOLE) {
+			free_extent_map(em);
+			ret = btrfs_truncate_block(inode, offset, len, 0);
+			if (!ret)
+				ret = btrfs_fallocate_update_isize(inode,
+								   offset + len,
+								   mode);
+			return ret;
+		}
+		free_extent_map(em);
+		alloc_start = round_down(offset, sectorsize);
+		alloc_end = alloc_start + sectorsize;
+		goto reserve_space;
+	}
+
+	alloc_start = round_up(offset, sectorsize);
+	alloc_end = round_down(offset + len, sectorsize);
+
+	/*
+	 * For unaligned ranges, check the pages at the boundaries, they might
+	 * map to an extent, in which case we need to partially zero them, or
+	 * they might map to a hole, in which case we need our allocation range
+	 * to cover them.
+	 */
+	if (!IS_ALIGNED(offset, sectorsize)) {
+		ret = btrfs_zero_range_check_range_boundary(inode, offset);
+		if (ret < 0)
+			goto out;
+		if (ret) {
+			alloc_start = round_down(offset, sectorsize);
+			ret = 0;
+		} else {
+			ret = btrfs_truncate_block(inode, offset, 0, 0);
+			if (ret)
+				goto out;
+		}
+	}
+
+	if (!IS_ALIGNED(offset + len, sectorsize)) {
+		ret = btrfs_zero_range_check_range_boundary(inode,
+							    offset + len);
+		if (ret < 0)
+			goto out;
+		if (ret) {
+			alloc_end = round_up(offset + len, sectorsize);
+			ret = 0;
+		} else {
+			ret = btrfs_truncate_block(inode, offset + len, 0, 1);
+			if (ret)
+				goto out;
+		}
+	}
+
+reserve_space:
+	if (alloc_start < alloc_end) {
+		struct extent_state *cached_state = NULL;
+		const u64 lockstart = alloc_start;
+		const u64 lockend = alloc_end - 1;
+
+		bytes_to_reserve = alloc_end - alloc_start;
+		ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode),
+						      bytes_to_reserve);
+		if (ret < 0)
+			goto out;
+		space_reserved = true;
+		ret = btrfs_qgroup_reserve_data(inode, &data_reserved,
+						alloc_start, bytes_to_reserve);
+		if (ret)
+			goto out;
+		ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend,
+						  &cached_state);
+		if (ret)
+			goto out;
+		ret = btrfs_prealloc_file_range(inode, mode, alloc_start,
+						alloc_end - alloc_start,
+						i_blocksize(inode),
+						offset + len, &alloc_hint);
+		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
+				     lockend, &cached_state, GFP_KERNEL);
+		/* btrfs_prealloc_file_range releases reserved space on error */
+		if (ret)
+			space_reserved = false;
+	}
+ out:
+	if (ret && space_reserved)
+		btrfs_free_reserved_data_space(inode, data_reserved,
+					       alloc_start, bytes_to_reserve);
+	extent_changeset_free(data_reserved);
+
+	return ret;
+}
+
 static long btrfs_fallocate(struct file *file, int mode,
 			    loff_t offset, loff_t len)
 {
@@ -2831,7 +3064,8 @@ static long btrfs_fallocate(struct file *file, int mode,
 	cur_offset = alloc_start;
 
 	/* Make sure we aren't being give some crap mode */
-	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+		     FALLOC_FL_ZERO_RANGE))
 		return -EOPNOTSUPP;
 
 	if (mode & FALLOC_FL_PUNCH_HOLE)
@@ -2842,10 +3076,12 @@ static long btrfs_fallocate(struct file *file, int mode,
 	 *
 	 * For qgroup space, it will be checked later.
 	 */
-	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode),
-			alloc_end - alloc_start);
-	if (ret < 0)
-		return ret;
+	if (!(mode & FALLOC_FL_ZERO_RANGE)) {
+		ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode),
+						      alloc_end - alloc_start);
+		if (ret < 0)
+			return ret;
+	}
 
 	inode_lock(inode);
 
@@ -2887,6 +3123,12 @@ static long btrfs_fallocate(struct file *file, int mode,
 	if (ret)
 		goto out;
 
+	if (mode & FALLOC_FL_ZERO_RANGE) {
+		ret = btrfs_zero_range(inode, offset, len, mode);
+		inode_unlock(inode);
+		return ret;
+	}
+
 	locked_end = alloc_end - 1;
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
@@ -2896,8 +3138,8 @@ static long btrfs_fallocate(struct file *file, int mode,
 		 */
 		lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
 				 locked_end, &cached_state);
-		ordered = btrfs_lookup_first_ordered_extent(inode,
-							    alloc_end - 1);
+		ordered = btrfs_lookup_first_ordered_extent(inode, locked_end);
+
 		if (ordered &&
 		    ordered->file_offset + ordered->len > alloc_start &&
 		    ordered->file_offset < alloc_end) {
@@ -2922,7 +3164,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 
 	/* First, check if we exceed the qgroup limit */
 	INIT_LIST_HEAD(&reserve_list);
-	while (1) {
+	while (cur_offset < alloc_end) {
 		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
 				      alloc_end - cur_offset, 0);
 		if (IS_ERR(em)) {
@@ -2958,8 +3200,6 @@ static long btrfs_fallocate(struct file *file, int mode,
 		}
 		free_extent_map(em);
 		cur_offset = last_byte;
-		if (cur_offset >= alloc_end)
-			break;
 	}
 
 	/*
@@ -2982,37 +3222,18 @@ static long btrfs_fallocate(struct file *file, int mode,
 	if (ret < 0)
 		goto out_unlock;
 
-	if (actual_end > inode->i_size &&
-	    !(mode & FALLOC_FL_KEEP_SIZE)) {
-		struct btrfs_trans_handle *trans;
-		struct btrfs_root *root = BTRFS_I(inode)->root;
-
-		/*
-		 * We didn't need to allocate any more space, but we
-		 * still extended the size of the file so we need to
-		 * update i_size and the inode item.
-		 */
-		trans = btrfs_start_transaction(root, 1);
-		if (IS_ERR(trans)) {
-			ret = PTR_ERR(trans);
-		} else {
-			inode->i_ctime = current_time(inode);
-			i_size_write(inode, actual_end);
-			btrfs_ordered_update_i_size(inode, actual_end, NULL);
-			ret = btrfs_update_inode(trans, root, inode);
-			if (ret)
-				btrfs_end_transaction(trans);
-			else
-				ret = btrfs_end_transaction(trans);
-		}
-	}
+	/*
+	 * We didn't need to allocate any more space, but we still extended the
+	 * size of the file so we need to update i_size and the inode item.
+	 */
+	ret = btrfs_fallocate_update_isize(inode, actual_end, mode);
 out_unlock:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
 			     &cached_state, GFP_KERNEL);
 out:
 	inode_unlock(inode);
 	/* Let go of our reservation. */
-	if (ret != 0)
+	if (ret != 0 && !(mode & FALLOC_FL_ZERO_RANGE))
 		btrfs_free_reserved_data_space(inode, data_reserved,
 				alloc_start, alloc_end - cur_offset);
 	extent_changeset_free(data_reserved);
@@ -3145,7 +3366,7 @@ void btrfs_auto_defrag_exit(void)
 	kmem_cache_destroy(btrfs_inode_defrag_cachep);
 }
 
-int btrfs_auto_defrag_init(void)
+int __init btrfs_auto_defrag_init(void)
 {
 	btrfs_inode_defrag_cachep = kmem_cache_create("btrfs_inode_defrag",
 					sizeof(struct inode_defrag), 0,
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 4426d1c73e50..b8ab90c9a9fb 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -993,8 +993,7 @@ update_cache_item(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
 	if (ret < 0) {
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1,
-				 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL,
-				 GFP_NOFS);
+				 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL);
 		goto fail;
 	}
 	leaf = path->nodes[0];
@@ -1008,7 +1007,7 @@ update_cache_item(struct btrfs_trans_handle *trans,
 			clear_extent_bit(&BTRFS_I(inode)->io_tree, 0,
 					 inode->i_size - 1,
 					 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0,
-					 NULL, GFP_NOFS);
+					 NULL);
 			btrfs_release_path(path);
 			goto fail;
 		}
@@ -1105,8 +1104,7 @@ static int flush_dirty_cache(struct inode *inode)
 	ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
 	if (ret)
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1,
-				 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL,
-				 GFP_NOFS);
+				 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL);
 
 	return ret;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 993061f83067..57785eadb95c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -769,7 +769,6 @@ retry:
 						  inode, async_extent->start,
 						  async_extent->start +
 						  async_extent->ram_size - 1,
-						  btrfs_get_extent,
 						  WB_SYNC_ALL);
 			else if (ret)
 				unlock_page(async_cow->locked_page);
@@ -1203,7 +1202,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 	u64 cur_end;
 
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED,
-			 1, 0, NULL, GFP_NOFS);
+			 1, 0, NULL);
 	while (start < end) {
 		async_cow = kmalloc(sizeof(*async_cow), GFP_NOFS);
 		BUG_ON(!async_cow); /* -ENOMEM */
@@ -1951,7 +1950,21 @@ static blk_status_t __btrfs_submit_bio_done(void *private_data, struct bio *bio,
 
 /*
  * extent_io.c submission hook. This does the right thing for csum calculation
- * on write, or reading the csums from the tree before a read
+ * on write, or reading the csums from the tree before a read.
+ *
+ * Rules about async/sync submit,
+ * a) read:				sync submit
+ *
+ * b) write without checksum:		sync submit
+ *
+ * c) write with checksum:
+ *    c-1) if bio is issued by fsync:	sync submit
+ *         (sync_writers != 0)
+ *
+ *    c-2) if root is reloc root:	sync submit
+ *         (only in case of buffered IO)
+ *
+ *    c-3) otherwise:			async submit
  */
 static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags,
@@ -2023,10 +2036,10 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
 	struct btrfs_ordered_sum *sum;
 
 	list_for_each_entry(sum, list, list) {
-		trans->adding_csums = 1;
+		trans->adding_csums = true;
 		btrfs_csum_file_blocks(trans,
 		       BTRFS_I(inode)->root->fs_info->csum_root, sum);
-		trans->adding_csums = 0;
+		trans->adding_csums = false;
 	}
 	return 0;
 }
@@ -2986,7 +2999,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 
 		clear_extent_bit(io_tree, ordered_extent->file_offset,
 			ordered_extent->file_offset + ordered_extent->len - 1,
-			EXTENT_DEFRAG, 0, 0, &cached_state, GFP_NOFS);
+			EXTENT_DEFRAG, 0, 0, &cached_state);
 	}
 
 	if (nolock)
@@ -3005,6 +3018,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		compress_type = ordered_extent->compress_type;
 	if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
 		BUG_ON(compress_type);
+		btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
+				       ordered_extent->len);
 		ret = btrfs_mark_extent_written(trans, BTRFS_I(inode),
 						ordered_extent->file_offset,
 						ordered_extent->file_offset +
@@ -3054,7 +3069,7 @@ out:
 				 ordered_extent->len - 1,
 				 clear_bits,
 				 (clear_bits & EXTENT_LOCKED) ? 1 : 0,
-				 0, &cached_state, GFP_NOFS);
+				 0, &cached_state);
 	}
 
 	if (trans)
@@ -3068,7 +3083,7 @@ out:
 		else
 			start = ordered_extent->file_offset;
 		end = ordered_extent->file_offset + ordered_extent->len - 1;
-		clear_extent_uptodate(io_tree, start, end, NULL, GFP_NOFS);
+		clear_extent_uptodate(io_tree, start, end, NULL);
 
 		/* Drop the cache for the part of the extent we didn't write. */
 		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0);
@@ -4796,7 +4811,7 @@ again:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, block_start, block_end,
 			  EXTENT_DIRTY | EXTENT_DELALLOC |
 			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
-			  0, 0, &cached_state, GFP_NOFS);
+			  0, 0, &cached_state);
 
 	ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0,
 					&cached_state, 0);
@@ -5232,8 +5247,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 		clear_extent_bit(io_tree, start, end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
 				 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
-				 EXTENT_DEFRAG, 1, 1,
-				 &cached_state, GFP_NOFS);
+				 EXTENT_DEFRAG, 1, 1, &cached_state);
 
 		cond_resched();
 		spin_lock(&io_tree->lock);
@@ -5892,7 +5906,6 @@ static int btrfs_filldir(void *addr, int entries, struct dir_context *ctx)
 static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_file_private *private = file->private_data;
 	struct btrfs_dir_item *di;
@@ -5960,9 +5973,6 @@ again:
 		if (btrfs_should_delete_dir_index(&del_list, found_key.offset))
 			goto next;
 		di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
-		if (verify_dir_item(fs_info, leaf, slot, di))
-			goto next;
-
 		name_len = btrfs_dir_name_len(leaf, di);
 		if ((total_len + sizeof(struct dir_entry) + name_len) >=
 		    PAGE_SIZE) {
@@ -6558,7 +6568,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 
 out_unlock:
 	btrfs_end_transaction(trans);
-	btrfs_balance_delayed_items(fs_info);
 	btrfs_btree_balance_dirty(fs_info);
 	if (drop_inode) {
 		inode_dec_link_count(inode);
@@ -6639,7 +6648,6 @@ out_unlock:
 		inode_dec_link_count(inode);
 		iput(inode);
 	}
-	btrfs_balance_delayed_items(fs_info);
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
 
@@ -6714,7 +6722,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent);
 	}
 
-	btrfs_balance_delayed_items(fs_info);
 fail:
 	if (trans)
 		btrfs_end_transaction(trans);
@@ -6792,7 +6799,6 @@ out_fail:
 		inode_dec_link_count(inode);
 		iput(inode);
 	}
-	btrfs_balance_delayed_items(fs_info);
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
 
@@ -6940,7 +6946,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 	struct btrfs_trans_handle *trans = NULL;
 	const bool new_inline = !page || create;
 
-again:
 	read_lock(&em_tree->lock);
 	em = lookup_extent_mapping(em_tree, start, len);
 	if (em)
@@ -7081,7 +7086,7 @@ next:
 		em->orig_block_len = em->len;
 		em->orig_start = em->start;
 		ptr = btrfs_file_extent_inline_start(item) + extent_offset;
-		if (create == 0 && !PageUptodate(page)) {
+		if (!PageUptodate(page)) {
 			if (btrfs_file_extent_compression(leaf, item) !=
 			    BTRFS_COMPRESS_NONE) {
 				ret = uncompress_inline(path, page, pg_offset,
@@ -7102,25 +7107,6 @@ next:
 				kunmap(page);
 			}
 			flush_dcache_page(page);
-		} else if (create && PageUptodate(page)) {
-			BUG();
-			if (!trans) {
-				kunmap(page);
-				free_extent_map(em);
-				em = NULL;
-
-				btrfs_release_path(path);
-				trans = btrfs_join_transaction(root);
-
-				if (IS_ERR(trans))
-					return ERR_CAST(trans);
-				goto again;
-			}
-			map = kmap(page);
-			write_extent_buffer(leaf, map + pg_offset, ptr,
-					    copy_size);
-			kunmap(page);
-			btrfs_mark_buffer_dirty(leaf);
 		}
 		set_extent_uptodate(io_tree, em->start,
 				    extent_map_end(em) - 1, NULL, GFP_NOFS);
@@ -7132,7 +7118,6 @@ not_found:
 	em->len = len;
 not_found_em:
 	em->block_start = EXTENT_MAP_HOLE;
-	set_bit(EXTENT_FLAG_VACANCY, &em->flags);
 insert:
 	btrfs_release_path(path);
 	if (em->start > start || extent_map_end(em) <= start) {
@@ -7924,7 +7909,7 @@ unlock:
 	if (lockstart < lockend) {
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
 				 lockend, unlock_bits, 1, 0,
-				 &cached_state, GFP_NOFS);
+				 &cached_state);
 	} else {
 		free_extent_state(cached_state);
 	}
@@ -7935,7 +7920,7 @@ unlock:
 
 unlock_err:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-			 unlock_bits, 1, 0, &cached_state, GFP_NOFS);
+			 unlock_bits, 1, 0, &cached_state);
 err:
 	if (dio_data)
 		current->journal_info = dio_data;
@@ -8458,6 +8443,7 @@ __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, u64 file_offset,
 	bool write = bio_op(bio) == REQ_OP_WRITE;
 	blk_status_t ret;
 
+	/* Check btrfs_submit_bio_hook() for rules about async submit. */
 	if (async_submit)
 		async_submit = !atomic_read(&BTRFS_I(inode)->sync_writers);
 
@@ -8852,7 +8838,7 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (ret)
 		return ret;
 
-	return extent_fiemap(inode, fieinfo, start, len, btrfs_get_extent_fiemap);
+	return extent_fiemap(inode, fieinfo, start, len);
 }
 
 int btrfs_readpage(struct file *file, struct page *page)
@@ -8884,7 +8870,7 @@ static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
 		return AOP_WRITEPAGE_ACTIVATE;
 	}
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
-	ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+	ret = extent_write_full_page(tree, page, wbc);
 	btrfs_add_delayed_iput(inode);
 	return ret;
 }
@@ -8895,7 +8881,7 @@ static int btrfs_writepages(struct address_space *mapping,
 	struct extent_io_tree *tree;
 
 	tree = &BTRFS_I(mapping->host)->io_tree;
-	return extent_writepages(tree, mapping, btrfs_get_extent, wbc);
+	return extent_writepages(tree, mapping, wbc);
 }
 
 static int
@@ -8904,8 +8890,7 @@ btrfs_readpages(struct file *file, struct address_space *mapping,
 {
 	struct extent_io_tree *tree;
 	tree = &BTRFS_I(mapping->host)->io_tree;
-	return extent_readpages(tree, mapping, pages, nr_pages,
-				btrfs_get_extent);
+	return extent_readpages(tree, mapping, pages, nr_pages);
 }
 static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
 {
@@ -8976,8 +8961,7 @@ again:
 					 EXTENT_DIRTY | EXTENT_DELALLOC |
 					 EXTENT_DELALLOC_NEW |
 					 EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
-					 EXTENT_DEFRAG, 1, 0, &cached_state,
-					 GFP_NOFS);
+					 EXTENT_DEFRAG, 1, 0, &cached_state);
 		/*
 		 * whoever cleared the private bit is responsible
 		 * for the finish_ordered_io
@@ -9034,7 +9018,7 @@ again:
 				 EXTENT_LOCKED | EXTENT_DIRTY |
 				 EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
 				 EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 1,
-				 &cached_state, GFP_NOFS);
+				 &cached_state);
 
 		__btrfs_releasepage(page, GFP_NOFS);
 	}
@@ -9162,7 +9146,7 @@ again:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
 			  EXTENT_DIRTY | EXTENT_DELALLOC |
 			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
-			  0, 0, &cached_state, GFP_NOFS);
+			  0, 0, &cached_state);
 
 	ret = btrfs_set_extent_delalloc(inode, page_start, end, 0,
 					&cached_state, 0);
@@ -9419,7 +9403,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	struct btrfs_inode *ei;
 	struct inode *inode;
 
-	ei = kmem_cache_alloc(btrfs_inode_cachep, GFP_NOFS);
+	ei = kmem_cache_alloc(btrfs_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
 
@@ -9571,7 +9555,7 @@ void btrfs_destroy_cachep(void)
 	kmem_cache_destroy(btrfs_free_space_cachep);
 }
 
-int btrfs_init_cachep(void)
+int __init btrfs_init_cachep(void)
 {
 	btrfs_inode_cachep = kmem_cache_create("btrfs_inode",
 			sizeof(struct btrfs_inode), 0,
@@ -10686,7 +10670,6 @@ out:
 	btrfs_end_transaction(trans);
 	if (ret)
 		iput(inode);
-	btrfs_balance_delayed_items(fs_info);
 	btrfs_btree_balance_dirty(fs_info);
 	return ret;
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index d748ad1c3620..2f7562b1e349 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1190,7 +1190,7 @@ again:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
 			  page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
 			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0,
-			  &cached_state, GFP_NOFS);
+			  &cached_state);
 
 	if (i_done != page_cnt) {
 		spin_lock(&BTRFS_I(inode)->lock);
@@ -1760,6 +1760,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 	struct btrfs_trans_handle *trans;
 	u64 root_flags;
 	u64 flags;
+	bool clear_received_uuid = false;
 	int ret = 0;
 
 	if (!inode_owner_or_capable(inode))
@@ -1809,6 +1810,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 			btrfs_set_root_flags(&root->root_item,
 				     root_flags & ~BTRFS_ROOT_SUBVOL_RDONLY);
 			spin_unlock(&root->root_item_lock);
+			clear_received_uuid = true;
 		} else {
 			spin_unlock(&root->root_item_lock);
 			btrfs_warn(fs_info,
@@ -1825,6 +1827,24 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 		goto out_reset;
 	}
 
+	if (clear_received_uuid) {
+	        if (!btrfs_is_empty_uuid(root->root_item.received_uuid)) {
+	                ret = btrfs_uuid_tree_rem(trans, fs_info,
+	                                root->root_item.received_uuid,
+	                                BTRFS_UUID_KEY_RECEIVED_SUBVOL,
+	                                root->root_key.objectid);
+
+	                if (ret && ret != -ENOENT) {
+	                        btrfs_abort_transaction(trans, ret);
+	                        btrfs_end_transaction(trans);
+	                        goto out_reset;
+	                }
+
+	                memset(root->root_item.received_uuid, 0,
+	                                BTRFS_UUID_SIZE);
+	        }
+	}
+
 	ret = btrfs_update_root(trans, fs_info->tree_root,
 				&root->root_key, &root->root_item);
 	if (ret < 0) {
@@ -2675,14 +2695,12 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		goto out;
 	}
 
-	mutex_lock(&fs_info->volume_mutex);
 	if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) {
 		ret = btrfs_rm_device(fs_info, NULL, vol_args->devid);
 	} else {
 		vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
 		ret = btrfs_rm_device(fs_info, vol_args->name, 0);
 	}
-	mutex_unlock(&fs_info->volume_mutex);
 	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 
 	if (!ret) {
@@ -2726,9 +2744,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	}
 
 	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
-	mutex_lock(&fs_info->volume_mutex);
 	ret = btrfs_rm_device(fs_info, vol_args->name, 0);
-	mutex_unlock(&fs_info->volume_mutex);
 
 	if (!ret)
 		btrfs_info(fs_info, "disk deleted %s", vol_args->name);
@@ -2753,16 +2769,16 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
 	if (!fi_args)
 		return -ENOMEM;
 
-	mutex_lock(&fs_devices->device_list_mutex);
+	rcu_read_lock();
 	fi_args->num_devices = fs_devices->num_devices;
-	memcpy(&fi_args->fsid, fs_info->fsid, sizeof(fi_args->fsid));
 
-	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+	list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
 		if (device->devid > fi_args->max_id)
 			fi_args->max_id = device->devid;
 	}
-	mutex_unlock(&fs_devices->device_list_mutex);
+	rcu_read_unlock();
 
+	memcpy(&fi_args->fsid, fs_info->fsid, sizeof(fi_args->fsid));
 	fi_args->nodesize = fs_info->nodesize;
 	fi_args->sectorsize = fs_info->sectorsize;
 	fi_args->clone_alignment = fs_info->sectorsize;
@@ -2779,7 +2795,6 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_ioctl_dev_info_args *di_args;
 	struct btrfs_device *dev;
-	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	int ret = 0;
 	char *s_uuid = NULL;
 
@@ -2790,7 +2805,7 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info,
 	if (!btrfs_is_empty_uuid(di_args->uuid))
 		s_uuid = di_args->uuid;
 
-	mutex_lock(&fs_devices->device_list_mutex);
+	rcu_read_lock();
 	dev = btrfs_find_device(fs_info, di_args->devid, s_uuid, NULL);
 
 	if (!dev) {
@@ -2805,17 +2820,15 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info,
 	if (dev->name) {
 		struct rcu_string *name;
 
-		rcu_read_lock();
 		name = rcu_dereference(dev->name);
 		strncpy(di_args->path, name->str, sizeof(di_args->path));
-		rcu_read_unlock();
 		di_args->path[sizeof(di_args->path) - 1] = 0;
 	} else {
 		di_args->path[0] = '\0';
 	}
 
 out:
-	mutex_unlock(&fs_devices->device_list_mutex);
+	rcu_read_unlock();
 	if (ret == 0 && copy_to_user(arg, di_args, sizeof(*di_args)))
 		ret = -EFAULT;
 
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index f6a05f836629..4f23ff00c8b3 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -164,7 +164,6 @@ static int iterate_object_props(struct btrfs_root *root,
 						 size_t),
 				void *ctx)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
 	char *name_buf = NULL;
 	char *value_buf = NULL;
@@ -215,12 +214,6 @@ static int iterate_object_props(struct btrfs_root *root,
 			name_ptr = (unsigned long)(di + 1);
 			data_ptr = name_ptr + name_len;
 
-			if (verify_dir_item(fs_info, leaf,
-					    path->slots[0], di)) {
-				ret = -EIO;
-				goto out;
-			}
-
 			if (name_len <= XATTR_BTRFS_PREFIX_LEN ||
 			    memcmp_extent_buffer(leaf, XATTR_BTRFS_PREFIX,
 						 name_ptr,
@@ -414,7 +407,7 @@ static int prop_compression_apply(struct inode *inode,
 		type = BTRFS_COMPRESS_LZO;
 	else if (!strncmp("zlib", value, 4))
 		type = BTRFS_COMPRESS_ZLIB;
-	else if (!strncmp("zstd", value, len))
+	else if (!strncmp("zstd", value, 4))
 		type = BTRFS_COMPRESS_ZSTD;
 	else
 		return -EINVAL;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 168fd03ca3ac..c02670d5aa13 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -47,6 +47,80 @@
  *  - check all ioctl parameters
  */
 
+/*
+ * Helpers to access qgroup reservation
+ *
+ * Callers should ensure the lock context and type are valid
+ */
+
+static u64 qgroup_rsv_total(const struct btrfs_qgroup *qgroup)
+{
+	u64 ret = 0;
+	int i;
+
+	for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++)
+		ret += qgroup->rsv.values[i];
+
+	return ret;
+}
+
+#ifdef CONFIG_BTRFS_DEBUG
+static const char *qgroup_rsv_type_str(enum btrfs_qgroup_rsv_type type)
+{
+	if (type == BTRFS_QGROUP_RSV_DATA)
+		return "data";
+	if (type == BTRFS_QGROUP_RSV_META)
+		return "meta";
+	return NULL;
+}
+#endif
+
+static void qgroup_rsv_add(struct btrfs_fs_info *fs_info,
+			   struct btrfs_qgroup *qgroup, u64 num_bytes,
+			   enum btrfs_qgroup_rsv_type type)
+{
+	trace_qgroup_update_reserve(fs_info, qgroup, num_bytes, type);
+	qgroup->rsv.values[type] += num_bytes;
+}
+
+static void qgroup_rsv_release(struct btrfs_fs_info *fs_info,
+			       struct btrfs_qgroup *qgroup, u64 num_bytes,
+			       enum btrfs_qgroup_rsv_type type)
+{
+	trace_qgroup_update_reserve(fs_info, qgroup, -(s64)num_bytes, type);
+	if (qgroup->rsv.values[type] >= num_bytes) {
+		qgroup->rsv.values[type] -= num_bytes;
+		return;
+	}
+#ifdef CONFIG_BTRFS_DEBUG
+	WARN_RATELIMIT(1,
+		"qgroup %llu %s reserved space underflow, have %llu to free %llu",
+		qgroup->qgroupid, qgroup_rsv_type_str(type),
+		qgroup->rsv.values[type], num_bytes);
+#endif
+	qgroup->rsv.values[type] = 0;
+}
+
+static void qgroup_rsv_add_by_qgroup(struct btrfs_fs_info *fs_info,
+				     struct btrfs_qgroup *dest,
+				     struct btrfs_qgroup *src)
+{
+	int i;
+
+	for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++)
+		qgroup_rsv_add(fs_info, dest, src->rsv.values[i], i);
+}
+
+static void qgroup_rsv_release_by_qgroup(struct btrfs_fs_info *fs_info,
+					 struct btrfs_qgroup *dest,
+					  struct btrfs_qgroup *src)
+{
+	int i;
+
+	for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++)
+		qgroup_rsv_release(fs_info, dest, src->rsv.values[i], i);
+}
+
 static void btrfs_qgroup_update_old_refcnt(struct btrfs_qgroup *qg, u64 seq,
 					   int mod)
 {
@@ -991,33 +1065,29 @@ static void qgroup_dirty(struct btrfs_fs_info *fs_info,
 		list_add(&qgroup->dirty, &fs_info->dirty_qgroups);
 }
 
-static void report_reserved_underflow(struct btrfs_fs_info *fs_info,
-				      struct btrfs_qgroup *qgroup,
-				      u64 num_bytes)
-{
-#ifdef CONFIG_BTRFS_DEBUG
-	WARN_ON(qgroup->reserved < num_bytes);
-	btrfs_debug(fs_info,
-		"qgroup %llu reserved space underflow, have: %llu, to free: %llu",
-		qgroup->qgroupid, qgroup->reserved, num_bytes);
-#endif
-	qgroup->reserved = 0;
-}
 /*
- * The easy accounting, if we are adding/removing the only ref for an extent
- * then this qgroup and all of the parent qgroups get their reference and
- * exclusive counts adjusted.
+ * The easy accounting, we're updating qgroup relationship whose child qgroup
+ * only has exclusive extents.
+ *
+ * In this case, all exclsuive extents will also be exlusive for parent, so
+ * excl/rfer just get added/removed.
+ *
+ * So is qgroup reservation space, which should also be added/removed to
+ * parent.
+ * Or when child tries to release reservation space, parent will underflow its
+ * reservation (for relationship adding case).
  *
  * Caller should hold fs_info->qgroup_lock.
  */
 static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 				    struct ulist *tmp, u64 ref_root,
-				    u64 num_bytes, int sign)
+				    struct btrfs_qgroup *src, int sign)
 {
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_qgroup_list *glist;
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
+	u64 num_bytes = src->excl;
 	int ret = 0;
 
 	qgroup = find_qgroup_rb(fs_info, ref_root);
@@ -1030,13 +1100,11 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 	WARN_ON(sign < 0 && qgroup->excl < num_bytes);
 	qgroup->excl += sign * num_bytes;
 	qgroup->excl_cmpr += sign * num_bytes;
-	if (sign > 0) {
-		trace_qgroup_update_reserve(fs_info, qgroup, -(s64)num_bytes);
-		if (qgroup->reserved < num_bytes)
-			report_reserved_underflow(fs_info, qgroup, num_bytes);
-		else
-			qgroup->reserved -= num_bytes;
-	}
+
+	if (sign > 0)
+		qgroup_rsv_add_by_qgroup(fs_info, qgroup, src);
+	else
+		qgroup_rsv_release_by_qgroup(fs_info, qgroup, src);
 
 	qgroup_dirty(fs_info, qgroup);
 
@@ -1056,15 +1124,10 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 		qgroup->rfer_cmpr += sign * num_bytes;
 		WARN_ON(sign < 0 && qgroup->excl < num_bytes);
 		qgroup->excl += sign * num_bytes;
-		if (sign > 0) {
-			trace_qgroup_update_reserve(fs_info, qgroup,
-						    -(s64)num_bytes);
-			if (qgroup->reserved < num_bytes)
-				report_reserved_underflow(fs_info, qgroup,
-							  num_bytes);
-			else
-				qgroup->reserved -= num_bytes;
-		}
+		if (sign > 0)
+			qgroup_rsv_add_by_qgroup(fs_info, qgroup, src);
+		else
+			qgroup_rsv_release_by_qgroup(fs_info, qgroup, src);
 		qgroup->excl_cmpr += sign * num_bytes;
 		qgroup_dirty(fs_info, qgroup);
 
@@ -1107,7 +1170,7 @@ static int quick_update_accounting(struct btrfs_fs_info *fs_info,
 	if (qgroup->excl == qgroup->rfer) {
 		ret = 0;
 		err = __qgroup_excl_accounting(fs_info, tmp, dst,
-					       qgroup->excl, sign);
+					       qgroup, sign);
 		if (err < 0) {
 			ret = err;
 			goto out;
@@ -2333,17 +2396,18 @@ out:
 static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes)
 {
 	if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
-	    qg->reserved + (s64)qg->rfer + num_bytes > qg->max_rfer)
+	    qgroup_rsv_total(qg) + (s64)qg->rfer + num_bytes > qg->max_rfer)
 		return false;
 
 	if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) &&
-	    qg->reserved + (s64)qg->excl + num_bytes > qg->max_excl)
+	    qgroup_rsv_total(qg) + (s64)qg->excl + num_bytes > qg->max_excl)
 		return false;
 
 	return true;
 }
 
-static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce)
+static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce,
+			  enum btrfs_qgroup_rsv_type type)
 {
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
@@ -2395,7 +2459,7 @@ retry:
 			 * Commit the tree and retry, since we may have
 			 * deletions which would free up space.
 			 */
-			if (!retried && qg->reserved > 0) {
+			if (!retried && qgroup_rsv_total(qg) > 0) {
 				struct btrfs_trans_handle *trans;
 
 				spin_unlock(&fs_info->qgroup_lock);
@@ -2434,8 +2498,8 @@ retry:
 
 		qg = unode_aux_to_qgroup(unode);
 
-		trace_qgroup_update_reserve(fs_info, qg, num_bytes);
-		qg->reserved += num_bytes;
+		trace_qgroup_update_reserve(fs_info, qg, num_bytes, type);
+		qgroup_rsv_add(fs_info, qg, num_bytes, type);
 	}
 
 out:
@@ -2444,7 +2508,8 @@ out:
 }
 
 void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
-			       u64 ref_root, u64 num_bytes)
+			       u64 ref_root, u64 num_bytes,
+			       enum btrfs_qgroup_rsv_type type)
 {
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
@@ -2480,11 +2545,8 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 
 		qg = unode_aux_to_qgroup(unode);
 
-		trace_qgroup_update_reserve(fs_info, qg, -(s64)num_bytes);
-		if (qg->reserved < num_bytes)
-			report_reserved_underflow(fs_info, qg, num_bytes);
-		else
-			qg->reserved -= num_bytes;
+		trace_qgroup_update_reserve(fs_info, qg, -(s64)num_bytes, type);
+		qgroup_rsv_release(fs_info, qg, num_bytes, type);
 
 		list_for_each_entry(glist, &qg->groups, next_group) {
 			ret = ulist_add(fs_info->qgroup_ulist,
@@ -2872,7 +2934,7 @@ int btrfs_qgroup_reserve_data(struct inode *inode,
 					to_reserve, QGROUP_RESERVE);
 	if (ret < 0)
 		goto cleanup;
-	ret = qgroup_reserve(root, to_reserve, true);
+	ret = qgroup_reserve(root, to_reserve, true, BTRFS_QGROUP_RSV_DATA);
 	if (ret < 0)
 		goto cleanup;
 
@@ -2883,8 +2945,7 @@ cleanup:
 	ULIST_ITER_INIT(&uiter);
 	while ((unode = ulist_next(&reserved->range_changed, &uiter)))
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val,
-				 unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL,
-				 GFP_NOFS);
+				 unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL);
 	extent_changeset_release(reserved);
 	return ret;
 }
@@ -2936,7 +2997,8 @@ static int qgroup_free_reserved_data(struct inode *inode,
 			goto out;
 		freed += changeset.bytes_changed;
 	}
-	btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed);
+	btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed,
+				  BTRFS_QGROUP_RSV_DATA);
 	ret = freed;
 out:
 	extent_changeset_release(&changeset);
@@ -2968,7 +3030,7 @@ static int __btrfs_qgroup_release_data(struct inode *inode,
 	if (free)
 		btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
 				BTRFS_I(inode)->root->objectid,
-				changeset.bytes_changed);
+				changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
 	ret = changeset.bytes_changed;
 out:
 	extent_changeset_release(&changeset);
@@ -3025,7 +3087,7 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
 	trace_qgroup_meta_reserve(root, (s64)num_bytes);
-	ret = qgroup_reserve(root, num_bytes, enforce);
+	ret = qgroup_reserve(root, num_bytes, enforce, BTRFS_QGROUP_RSV_META);
 	if (ret < 0)
 		return ret;
 	atomic64_add(num_bytes, &root->qgroup_meta_rsv);
@@ -3045,7 +3107,8 @@ void btrfs_qgroup_free_meta_all(struct btrfs_root *root)
 	if (reserved == 0)
 		return;
 	trace_qgroup_meta_reserve(root, -(s64)reserved);
-	btrfs_qgroup_free_refroot(fs_info, root->objectid, reserved);
+	btrfs_qgroup_free_refroot(fs_info, root->objectid, reserved,
+				  BTRFS_QGROUP_RSV_META);
 }
 
 void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
@@ -3060,7 +3123,8 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
 	WARN_ON(atomic64_read(&root->qgroup_meta_rsv) < num_bytes);
 	atomic64_sub(num_bytes, &root->qgroup_meta_rsv);
 	trace_qgroup_meta_reserve(root, -(s64)num_bytes);
-	btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes);
+	btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes,
+				  BTRFS_QGROUP_RSV_META);
 }
 
 /*
@@ -3088,7 +3152,7 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode)
 		}
 		btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
 				BTRFS_I(inode)->root->objectid,
-				changeset.bytes_changed);
+				changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
 
 	}
 	extent_changeset_release(&changeset);
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index d9984e87cddf..c8c81b923674 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -61,6 +61,26 @@ struct btrfs_qgroup_extent_record {
 	struct ulist *old_roots;
 };
 
+enum btrfs_qgroup_rsv_type {
+	BTRFS_QGROUP_RSV_DATA = 0,
+	BTRFS_QGROUP_RSV_META,
+	BTRFS_QGROUP_RSV_LAST,
+};
+
+/*
+ * Represents how many bytes we have reserved for this qgroup.
+ *
+ * Each type should have different reservation behavior.
+ * E.g, data follows its io_tree flag modification, while
+ * *currently* meta is just reserve-and-clear during transcation.
+ *
+ * TODO: Add new type for reservation which can survive transaction commit.
+ * Currect metadata reservation behavior is not suitable for such case.
+ */
+struct btrfs_qgroup_rsv {
+	u64 values[BTRFS_QGROUP_RSV_LAST];
+};
+
 /*
  * one struct for each qgroup, organized in fs_info->qgroup_tree.
  */
@@ -87,7 +107,7 @@ struct btrfs_qgroup {
 	/*
 	 * reservation tracking
 	 */
-	u64 reserved;
+	struct btrfs_qgroup_rsv rsv;
 
 	/*
 	 * lists
@@ -228,12 +248,14 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
 			 struct btrfs_qgroup_inherit *inherit);
 void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
-			       u64 ref_root, u64 num_bytes);
+			       u64 ref_root, u64 num_bytes,
+			       enum btrfs_qgroup_rsv_type type);
 static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info,
 						 u64 ref_root, u64 num_bytes)
 {
 	trace_btrfs_qgroup_free_delayed_ref(fs_info, ref_root, num_bytes);
-	btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes);
+	btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes,
+				  BTRFS_QGROUP_RSV_DATA);
 }
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 34878699d363..171f3cce30e6 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -606,8 +606,7 @@ static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path,
 }
 
 /* Walk up to the next node that needs to be processed */
-static int walk_up_tree(struct btrfs_root *root, struct btrfs_path *path,
-			int *level)
+static int walk_up_tree(struct btrfs_path *path, int *level)
 {
 	int l;
 
@@ -984,7 +983,6 @@ void btrfs_free_ref_tree_range(struct btrfs_fs_info *fs_info, u64 start,
 int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_path *path;
-	struct btrfs_root *root;
 	struct extent_buffer *eb;
 	u64 bytenr = 0, num_bytes = 0;
 	int ret, level;
@@ -1014,7 +1012,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info)
 				     &bytenr, &num_bytes);
 		if (ret)
 			break;
-		ret = walk_up_tree(root, path, &level);
+		ret = walk_up_tree(path, &level);
 		if (ret < 0)
 			break;
 		if (ret > 0) {
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 3338407ef0f0..aab0194efe46 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -387,13 +387,6 @@ again:
 		WARN_ON(btrfs_root_ref_dirid(leaf, ref) != dirid);
 		WARN_ON(btrfs_root_ref_name_len(leaf, ref) != name_len);
 		ptr = (unsigned long)(ref + 1);
-		ret = btrfs_is_name_len_valid(leaf, path->slots[0], ptr,
-					      name_len);
-		if (!ret) {
-			err = -EIO;
-			goto out;
-		}
-
 		WARN_ON(memcmp_extent_buffer(leaf, name, ptr, name_len));
 		*sequence = btrfs_root_ref_sequence(leaf, ref);
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 20d3300bd268..f306c608dc28 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1059,12 +1059,6 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 			}
 		}
 
-		ret = btrfs_is_name_len_valid(eb, path->slots[0],
-			  (unsigned long)(di + 1), name_len + data_len);
-		if (!ret) {
-			ret = -EIO;
-			goto out;
-		}
 		if (name_len + data_len > buf_len) {
 			buf_len = name_len + data_len;
 			if (is_vmalloc_addr(buf)) {
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 3a4dce153645..138ff32c39b9 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -67,6 +67,7 @@
 
 static const struct super_operations btrfs_super_ops;
 static struct file_system_type btrfs_fs_type;
+static struct file_system_type btrfs_root_fs_type;
 
 static int btrfs_remount(struct super_block *sb, int *flags, char *data);
 
@@ -454,7 +455,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_subvolrootid:
 		case Opt_device:
 			/*
-			 * These are parsed by btrfs_parse_early_options
+			 * These are parsed by btrfs_parse_subvol_options
+			 * and btrfs_parse_early_options
 			 * and can be happily ignored here.
 			 */
 			break;
@@ -531,9 +533,10 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 				btrfs_clear_opt(info->mount_opt, NODATASUM);
 				btrfs_set_fs_incompat(info, COMPRESS_LZO);
 				no_compress = 0;
-			} else if (strcmp(args[0].from, "zstd") == 0) {
+			} else if (strncmp(args[0].from, "zstd", 4) == 0) {
 				compress_type = "zstd";
 				info->compress_type = BTRFS_COMPRESS_ZSTD;
+				info->compress_level = btrfs_compress_str2level(args[0].from);
 				btrfs_set_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, NODATACOW);
 				btrfs_clear_opt(info->mount_opt, NODATASUM);
@@ -888,11 +891,63 @@ out:
  * only when we need to allocate a new super block.
  */
 static int btrfs_parse_early_options(const char *options, fmode_t flags,
-		void *holder, char **subvol_name, u64 *subvol_objectid,
-		struct btrfs_fs_devices **fs_devices)
+		void *holder, struct btrfs_fs_devices **fs_devices)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *device_name, *opts, *orig, *p;
+	int error = 0;
+
+	if (!options)
+		return 0;
+
+	/*
+	 * strsep changes the string, duplicate it because btrfs_parse_options
+	 * gets called later
+	 */
+	opts = kstrdup(options, GFP_KERNEL);
+	if (!opts)
+		return -ENOMEM;
+	orig = opts;
+
+	while ((p = strsep(&opts, ",")) != NULL) {
+		int token;
+		if (!*p)
+			continue;
+
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_device:
+			device_name = match_strdup(&args[0]);
+			if (!device_name) {
+				error = -ENOMEM;
+				goto out;
+			}
+			error = btrfs_scan_one_device(device_name,
+					flags, holder, fs_devices);
+			kfree(device_name);
+			if (error)
+				goto out;
+			break;
+		default:
+			break;
+		}
+	}
+
+out:
+	kfree(orig);
+	return error;
+}
+
+/*
+ * Parse mount options that are related to subvolume id
+ *
+ * The value is later passed to mount_subvol()
+ */
+static int btrfs_parse_subvol_options(const char *options, fmode_t flags,
+		void *holder, char **subvol_name, u64 *subvol_objectid)
+{
+	substring_t args[MAX_OPT_ARGS];
+	char *opts, *orig, *p;
 	char *num = NULL;
 	int error = 0;
 
@@ -900,8 +955,8 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		return 0;
 
 	/*
-	 * strsep changes the string, duplicate it because parse_options
-	 * gets called twice
+	 * strsep changes the string, duplicate it because
+	 * btrfs_parse_early_options gets called later
 	 */
 	opts = kstrdup(options, GFP_KERNEL);
 	if (!opts)
@@ -940,18 +995,6 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		case Opt_subvolrootid:
 			pr_warn("BTRFS: 'subvolrootid' mount option is deprecated and has no effect\n");
 			break;
-		case Opt_device:
-			device_name = match_strdup(&args[0]);
-			if (!device_name) {
-				error = -ENOMEM;
-				goto out;
-			}
-			error = btrfs_scan_one_device(device_name,
-					flags, holder, fs_devices);
-			kfree(device_name);
-			if (error)
-				goto out;
-			break;
 		default:
 			break;
 		}
@@ -1365,86 +1408,13 @@ static inline int is_subvolume_inode(struct inode *inode)
 	return 0;
 }
 
-/*
- * This will add subvolid=0 to the argument string while removing any subvol=
- * and subvolid= arguments to make sure we get the top-level root for path
- * walking to the subvol we want.
- */
-static char *setup_root_args(char *args)
-{
-	char *buf, *dst, *sep;
-
-	if (!args)
-		return kstrdup("subvolid=0", GFP_KERNEL);
-
-	/* The worst case is that we add ",subvolid=0" to the end. */
-	buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1,
-			GFP_KERNEL);
-	if (!buf)
-		return NULL;
-
-	while (1) {
-		sep = strchrnul(args, ',');
-		if (!strstarts(args, "subvol=") &&
-		    !strstarts(args, "subvolid=")) {
-			memcpy(dst, args, sep - args);
-			dst += sep - args;
-			*dst++ = ',';
-		}
-		if (*sep)
-			args = sep + 1;
-		else
-			break;
-	}
-	strcpy(dst, "subvolid=0");
-
-	return buf;
-}
-
 static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
 				   int flags, const char *device_name,
-				   char *data)
+				   char *data, struct vfsmount *mnt)
 {
 	struct dentry *root;
-	struct vfsmount *mnt = NULL;
-	char *newargs;
 	int ret;
 
-	newargs = setup_root_args(data);
-	if (!newargs) {
-		root = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, newargs);
-	if (PTR_ERR_OR_ZERO(mnt) == -EBUSY) {
-		if (flags & SB_RDONLY) {
-			mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~SB_RDONLY,
-					     device_name, newargs);
-		} else {
-			mnt = vfs_kern_mount(&btrfs_fs_type, flags | SB_RDONLY,
-					     device_name, newargs);
-			if (IS_ERR(mnt)) {
-				root = ERR_CAST(mnt);
-				mnt = NULL;
-				goto out;
-			}
-
-			down_write(&mnt->mnt_sb->s_umount);
-			ret = btrfs_remount(mnt->mnt_sb, &flags, NULL);
-			up_write(&mnt->mnt_sb->s_umount);
-			if (ret < 0) {
-				root = ERR_PTR(ret);
-				goto out;
-			}
-		}
-	}
-	if (IS_ERR(mnt)) {
-		root = ERR_CAST(mnt);
-		mnt = NULL;
-		goto out;
-	}
-
 	if (!subvol_name) {
 		if (!subvol_objectid) {
 			ret = get_default_subvol_objectid(btrfs_sb(mnt->mnt_sb),
@@ -1500,7 +1470,6 @@ static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
 
 out:
 	mntput(mnt);
-	kfree(newargs);
 	kfree(subvol_name);
 	return root;
 }
@@ -1558,10 +1527,10 @@ static int setup_security_options(struct btrfs_fs_info *fs_info,
 /*
  * Find a superblock for the given device / mount point.
  *
- * Note:  This is based on get_sb_bdev from fs/super.c with a few additions
+ * Note:  This is based on mount_bdev from fs/super.c with a few additions
  *	  for multiple device setup.  Make sure to keep it in sync.
  */
-static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
+static struct dentry *mount_root(struct file_system_type *fs_type, int flags,
 		const char *device_name, void *data)
 {
 	struct block_device *bdev = NULL;
@@ -1570,27 +1539,17 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	struct btrfs_fs_info *fs_info = NULL;
 	struct security_mnt_opts new_sec_opts;
 	fmode_t mode = FMODE_READ;
-	char *subvol_name = NULL;
-	u64 subvol_objectid = 0;
 	int error = 0;
 
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
 
 	error = btrfs_parse_early_options(data, mode, fs_type,
-					  &subvol_name, &subvol_objectid,
 					  &fs_devices);
 	if (error) {
-		kfree(subvol_name);
 		return ERR_PTR(error);
 	}
 
-	if (subvol_name || subvol_objectid != BTRFS_FS_TREE_OBJECTID) {
-		/* mount_subvol() will free subvol_name. */
-		return mount_subvol(subvol_name, subvol_objectid, flags,
-				    device_name, data);
-	}
-
 	security_init_mnt_opts(&new_sec_opts);
 	if (data) {
 		error = parse_security_options(data, &new_sec_opts);
@@ -1608,7 +1567,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	 * it for searching for existing supers, so this lets us do that and
 	 * then open_ctree will properly initialize everything later.
 	 */
-	fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL);
+	fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS);
 	if (!fs_info) {
 		error = -ENOMEM;
 		goto error_sec_opts;
@@ -1616,8 +1575,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 
 	fs_info->fs_devices = fs_devices;
 
-	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
-	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
+	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
+	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
 	security_init_mnt_opts(&fs_info->security_opts);
 	if (!fs_info->super_copy || !fs_info->super_for_commit) {
 		error = -ENOMEM;
@@ -1674,6 +1633,84 @@ error_sec_opts:
 	return ERR_PTR(error);
 }
 
+/*
+ * Mount function which is called by VFS layer.
+ *
+ * In order to allow mounting a subvolume directly, btrfs uses
+ * mount_subtree() which needs vfsmount* of device's root (/).
+ * This means device's root has to be mounted internally in any case.
+ *
+ * Operation flow:
+ *   1. Parse subvol id related options for later use in mount_subvol().
+ *
+ *   2. Mount device's root (/) by calling vfs_kern_mount().
+ *
+ *      NOTE: vfs_kern_mount() is used by VFS to call btrfs_mount() in the
+ *      first place. In order to avoid calling btrfs_mount() again, we use
+ *      different file_system_type which is not registered to VFS by
+ *      register_filesystem(). As a result, mount_root() is called.
+ *      The return value will be used by mount_subtree() in mount_subvol().
+ *
+ *   3. Call mount_subvol() to get the dentry of subvolume. Since there is
+ *      "btrfs subvolume set-default", mount_subvol() is called always.
+ */
+static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
+		const char *device_name, void *data)
+{
+	struct vfsmount *mnt_root;
+	struct dentry *root;
+	fmode_t mode = FMODE_READ;
+	char *subvol_name = NULL;
+	u64 subvol_objectid = 0;
+	int error = 0;
+
+	if (!(flags & SB_RDONLY))
+		mode |= FMODE_WRITE;
+
+	error = btrfs_parse_subvol_options(data, mode, fs_type,
+					  &subvol_name, &subvol_objectid);
+	if (error) {
+		kfree(subvol_name);
+		return ERR_PTR(error);
+	}
+
+	/* mount device's root (/) */
+	mnt_root = vfs_kern_mount(&btrfs_root_fs_type, flags, device_name, data);
+	if (PTR_ERR_OR_ZERO(mnt_root) == -EBUSY) {
+		if (flags & SB_RDONLY) {
+			mnt_root = vfs_kern_mount(&btrfs_root_fs_type, flags & ~SB_RDONLY,
+					     device_name, data);
+		} else {
+			mnt_root = vfs_kern_mount(&btrfs_root_fs_type, flags | SB_RDONLY,
+					     device_name, data);
+			if (IS_ERR(mnt_root)) {
+				root = ERR_CAST(mnt_root);
+				goto out;
+			}
+
+			down_write(&mnt_root->mnt_sb->s_umount);
+			error = btrfs_remount(mnt_root->mnt_sb, &flags, NULL);
+			up_write(&mnt_root->mnt_sb->s_umount);
+			if (error < 0) {
+				root = ERR_PTR(error);
+				mntput(mnt_root);
+				goto out;
+			}
+		}
+	}
+	if (IS_ERR(mnt_root)) {
+		root = ERR_CAST(mnt_root);
+		goto out;
+	}
+
+	/* mount_subvol() will free subvol_name and mnt_root */
+	root = mount_subvol(subvol_name, subvol_objectid, flags,
+				    device_name, data, mnt_root);
+
+out:
+	return root;
+}
+
 static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
 				     int new_pool_size, int old_pool_size)
 {
@@ -2174,6 +2211,15 @@ static struct file_system_type btrfs_fs_type = {
 	.kill_sb	= btrfs_kill_super,
 	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA,
 };
+
+static struct file_system_type btrfs_root_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "btrfs",
+	.mount		= mount_root,
+	.kill_sb	= btrfs_kill_super,
+	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA,
+};
+
 MODULE_ALIAS_FS("btrfs");
 
 static int btrfs_control_open(struct inode *inode, struct file *file)
@@ -2324,7 +2370,7 @@ static struct miscdevice btrfs_misc = {
 MODULE_ALIAS_MISCDEV(BTRFS_MINOR);
 MODULE_ALIAS("devname:btrfs-control");
 
-static int btrfs_interface_init(void)
+static int __init btrfs_interface_init(void)
 {
 	return misc_register(&btrfs_misc);
 }
@@ -2334,7 +2380,7 @@ static void btrfs_interface_exit(void)
 	misc_deregister(&btrfs_misc);
 }
 
-static void btrfs_print_mod_info(void)
+static void __init btrfs_print_mod_info(void)
 {
 	pr_info("Btrfs loaded, crc32c=%s"
 #ifdef CONFIG_BTRFS_DEBUG
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index a28bba801264..a8bafed931f4 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -897,7 +897,7 @@ static int btrfs_init_debugfs(void)
 	return 0;
 }
 
-int btrfs_init_sysfs(void)
+int __init btrfs_init_sysfs(void)
 {
 	int ret;
 
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 30affb60da51..13420cd19ef0 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -288,10 +288,6 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		test_msg("Expected a hole, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (!test_bit(EXTENT_FLAG_VACANCY, &em->flags)) {
-		test_msg("Vacancy flag wasn't set properly\n");
-		goto out;
-	}
 	free_extent_map(em);
 	btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
 
@@ -1001,8 +997,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 			       BTRFS_MAX_EXTENT_SIZE >> 1,
 			       (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1,
 			       EXTENT_DELALLOC | EXTENT_DIRTY |
-			       EXTENT_UPTODATE, 0, 0,
-			       NULL, GFP_KERNEL);
+			       EXTENT_UPTODATE, 0, 0, NULL);
 	if (ret) {
 		test_msg("clear_extent_bit returned %d\n", ret);
 		goto out;
@@ -1070,8 +1065,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 			       BTRFS_MAX_EXTENT_SIZE + sectorsize,
 			       BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1,
 			       EXTENT_DIRTY | EXTENT_DELALLOC |
-			       EXTENT_UPTODATE, 0, 0,
-			       NULL, GFP_KERNEL);
+			       EXTENT_UPTODATE, 0, 0, NULL);
 	if (ret) {
 		test_msg("clear_extent_bit returned %d\n", ret);
 		goto out;
@@ -1104,8 +1098,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 	/* Empty */
 	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
 			       EXTENT_DIRTY | EXTENT_DELALLOC |
-			       EXTENT_UPTODATE, 0, 0,
-			       NULL, GFP_KERNEL);
+			       EXTENT_UPTODATE, 0, 0, NULL);
 	if (ret) {
 		test_msg("clear_extent_bit returned %d\n", ret);
 		goto out;
@@ -1121,8 +1114,7 @@ out:
 	if (ret)
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
 				 EXTENT_DIRTY | EXTENT_DELALLOC |
-				 EXTENT_UPTODATE, 0, 0,
-				 NULL, GFP_KERNEL);
+				 EXTENT_UPTODATE, 0, 0, NULL);
 	iput(inode);
 	btrfs_free_dummy_root(root);
 	btrfs_free_dummy_fs_info(fs_info);
@@ -1134,7 +1126,6 @@ int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
 	int ret;
 
 	set_bit(EXTENT_FLAG_COMPRESSED, &compressed_only);
-	set_bit(EXTENT_FLAG_VACANCY, &vacancy_only);
 	set_bit(EXTENT_FLAG_PREALLOC, &prealloc_only);
 
 	test_msg("Running btrfs_get_extent tests\n");
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5a8c2649af2f..6348573e26a7 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -495,8 +495,8 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
 	if (current->journal_info) {
 		WARN_ON(type & TRANS_EXTWRITERS);
 		h = current->journal_info;
-		h->use_count++;
-		WARN_ON(h->use_count > 2);
+		refcount_inc(&h->use_count);
+		WARN_ON(refcount_read(&h->use_count) > 2);
 		h->orig_rsv = h->block_rsv;
 		h->block_rsv = NULL;
 		goto got_it;
@@ -567,7 +567,7 @@ again:
 	h->transid = cur_trans->transid;
 	h->transaction = cur_trans;
 	h->root = root;
-	h->use_count = 1;
+	refcount_set(&h->use_count, 1);
 	h->fs_info = root->fs_info;
 
 	h->type = type;
@@ -837,8 +837,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	int err = 0;
 	int must_run_delayed_refs = 0;
 
-	if (trans->use_count > 1) {
-		trans->use_count--;
+	if (refcount_read(&trans->use_count) > 1) {
+		refcount_dec(&trans->use_count);
 		trans->block_rsv = trans->orig_rsv;
 		return 0;
 	}
@@ -1016,8 +1016,7 @@ static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info,
 		 * it's safe to do it (through clear_btree_io_tree()).
 		 */
 		err = clear_extent_bit(dirty_pages, start, end,
-				       EXTENT_NEED_WAIT,
-				       0, 0, &cached_state, GFP_NOFS);
+				       EXTENT_NEED_WAIT, 0, 0, &cached_state);
 		if (err == -ENOMEM)
 			err = 0;
 		if (!err)
@@ -1869,7 +1868,7 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans,
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	DEFINE_WAIT(wait);
 
-	WARN_ON(trans->use_count > 1);
+	WARN_ON(refcount_read(&trans->use_count) > 1);
 
 	btrfs_abort_transaction(trans, err);
 
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index c55e44560103..6beee072b1bd 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -58,6 +58,7 @@ struct btrfs_transaction {
 
 	/* Be protected by fs_info->trans_lock when we want to change it. */
 	enum btrfs_trans_state state;
+	int aborted;
 	struct list_head list;
 	struct extent_io_tree dirty_pages;
 	unsigned long start_time;
@@ -70,7 +71,6 @@ struct btrfs_transaction {
 	struct list_head dirty_bgs;
 	struct list_head io_bgs;
 	struct list_head dropped_roots;
-	u64 num_dirty_bgs;
 
 	/*
 	 * we need to make sure block group deletion doesn't race with
@@ -79,11 +79,11 @@ struct btrfs_transaction {
 	 */
 	struct mutex cache_write_mutex;
 	spinlock_t dirty_bgs_lock;
+	unsigned int num_dirty_bgs;
 	/* Protected by spin lock fs_info->unused_bgs_lock. */
 	struct list_head deleted_bgs;
 	spinlock_t dropped_roots_lock;
 	struct btrfs_delayed_ref_root delayed_refs;
-	int aborted;
 	struct btrfs_fs_info *fs_info;
 };
 
@@ -111,20 +111,19 @@ struct btrfs_trans_handle {
 	u64 transid;
 	u64 bytes_reserved;
 	u64 chunk_bytes_reserved;
-	unsigned long use_count;
-	unsigned long blocks_reserved;
 	unsigned long delayed_ref_updates;
 	struct btrfs_transaction *transaction;
 	struct btrfs_block_rsv *block_rsv;
 	struct btrfs_block_rsv *orig_rsv;
+	refcount_t use_count;
+	unsigned int type;
 	short aborted;
-	short adding_csums;
+	bool adding_csums;
 	bool allocating_chunk;
 	bool can_flush_pending_bgs;
 	bool reloc_reserved;
 	bool sync;
 	bool dirty;
-	unsigned int type;
 	struct btrfs_root *root;
 	struct btrfs_fs_info *fs_info;
 	struct list_head new_bgs;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index ce4ed6ec8f39..66dac0a4b01f 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -30,6 +30,7 @@
 #include "tree-checker.h"
 #include "disk-io.h"
 #include "compression.h"
+#include "hash.h"
 
 /*
  * Error message should follow the following format:
@@ -223,6 +224,141 @@ static int check_csum_item(struct btrfs_root *root, struct extent_buffer *leaf,
 }
 
 /*
+ * Customized reported for dir_item, only important new info is key->objectid,
+ * which represents inode number
+ */
+__printf(4, 5)
+static void dir_item_err(const struct btrfs_root *root,
+			 const struct extent_buffer *eb, int slot,
+			 const char *fmt, ...)
+{
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(root->fs_info,
+	"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node", root->objectid,
+		btrfs_header_bytenr(eb), slot, key.objectid, &vaf);
+	va_end(args);
+}
+
+static int check_dir_item(struct btrfs_root *root,
+			  struct extent_buffer *leaf,
+			  struct btrfs_key *key, int slot)
+{
+	struct btrfs_dir_item *di;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+	u32 cur = 0;
+
+	di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
+	while (cur < item_size) {
+		char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
+		u32 name_len;
+		u32 data_len;
+		u32 max_name_len;
+		u32 total_size;
+		u32 name_hash;
+		u8 dir_type;
+
+		/* header itself should not cross item boundary */
+		if (cur + sizeof(*di) > item_size) {
+			dir_item_err(root, leaf, slot,
+		"dir item header crosses item boundary, have %lu boundary %u",
+				cur + sizeof(*di), item_size);
+			return -EUCLEAN;
+		}
+
+		/* dir type check */
+		dir_type = btrfs_dir_type(leaf, di);
+		if (dir_type >= BTRFS_FT_MAX) {
+			dir_item_err(root, leaf, slot,
+			"invalid dir item type, have %u expect [0, %u)",
+				dir_type, BTRFS_FT_MAX);
+			return -EUCLEAN;
+		}
+
+		if (key->type == BTRFS_XATTR_ITEM_KEY &&
+		    dir_type != BTRFS_FT_XATTR) {
+			dir_item_err(root, leaf, slot,
+		"invalid dir item type for XATTR key, have %u expect %u",
+				dir_type, BTRFS_FT_XATTR);
+			return -EUCLEAN;
+		}
+		if (dir_type == BTRFS_FT_XATTR &&
+		    key->type != BTRFS_XATTR_ITEM_KEY) {
+			dir_item_err(root, leaf, slot,
+			"xattr dir type found for non-XATTR key");
+			return -EUCLEAN;
+		}
+		if (dir_type == BTRFS_FT_XATTR)
+			max_name_len = XATTR_NAME_MAX;
+		else
+			max_name_len = BTRFS_NAME_LEN;
+
+		/* Name/data length check */
+		name_len = btrfs_dir_name_len(leaf, di);
+		data_len = btrfs_dir_data_len(leaf, di);
+		if (name_len > max_name_len) {
+			dir_item_err(root, leaf, slot,
+			"dir item name len too long, have %u max %u",
+				name_len, max_name_len);
+			return -EUCLEAN;
+		}
+		if (name_len + data_len > BTRFS_MAX_XATTR_SIZE(root->fs_info)) {
+			dir_item_err(root, leaf, slot,
+			"dir item name and data len too long, have %u max %u",
+				name_len + data_len,
+				BTRFS_MAX_XATTR_SIZE(root->fs_info));
+			return -EUCLEAN;
+		}
+
+		if (data_len && dir_type != BTRFS_FT_XATTR) {
+			dir_item_err(root, leaf, slot,
+			"dir item with invalid data len, have %u expect 0",
+				data_len);
+			return -EUCLEAN;
+		}
+
+		total_size = sizeof(*di) + name_len + data_len;
+
+		/* header and name/data should not cross item boundary */
+		if (cur + total_size > item_size) {
+			dir_item_err(root, leaf, slot,
+		"dir item data crosses item boundary, have %u boundary %u",
+				cur + total_size, item_size);
+			return -EUCLEAN;
+		}
+
+		/*
+		 * Special check for XATTR/DIR_ITEM, as key->offset is name
+		 * hash, should match its name
+		 */
+		if (key->type == BTRFS_DIR_ITEM_KEY ||
+		    key->type == BTRFS_XATTR_ITEM_KEY) {
+			read_extent_buffer(leaf, namebuf,
+					(unsigned long)(di + 1), name_len);
+			name_hash = btrfs_name_hash(namebuf, name_len);
+			if (key->offset != name_hash) {
+				dir_item_err(root, leaf, slot,
+		"name hash mismatch with key, have 0x%016x expect 0x%016llx",
+					name_hash, key->offset);
+				return -EUCLEAN;
+			}
+		}
+		cur += total_size;
+		di = (struct btrfs_dir_item *)((void *)di + total_size);
+	}
+	return 0;
+}
+
+/*
  * Common point to switch the item-specific validation.
  */
 static int check_leaf_item(struct btrfs_root *root,
@@ -238,6 +374,11 @@ static int check_leaf_item(struct btrfs_root *root,
 	case BTRFS_EXTENT_CSUM_KEY:
 		ret = check_csum_item(root, leaf, key, slot);
 		break;
+	case BTRFS_DIR_ITEM_KEY:
+	case BTRFS_DIR_INDEX_KEY:
+	case BTRFS_XATTR_ITEM_KEY:
+		ret = check_dir_item(root, leaf, key, slot);
+		break;
 	}
 	return ret;
 }
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 7bf9b31561db..ee1aaed1330e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1173,19 +1173,15 @@ next:
 	return 0;
 }
 
-static int extref_get_fields(struct extent_buffer *eb, int slot,
-			     unsigned long ref_ptr, u32 *namelen, char **name,
-			     u64 *index, u64 *parent_objectid)
+static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
+			     u32 *namelen, char **name, u64 *index,
+			     u64 *parent_objectid)
 {
 	struct btrfs_inode_extref *extref;
 
 	extref = (struct btrfs_inode_extref *)ref_ptr;
 
 	*namelen = btrfs_inode_extref_name_len(eb, extref);
-	if (!btrfs_is_name_len_valid(eb, slot, (unsigned long)&extref->name,
-				     *namelen))
-		return -EIO;
-
 	*name = kmalloc(*namelen, GFP_NOFS);
 	if (*name == NULL)
 		return -ENOMEM;
@@ -1200,19 +1196,14 @@ static int extref_get_fields(struct extent_buffer *eb, int slot,
 	return 0;
 }
 
-static int ref_get_fields(struct extent_buffer *eb, int slot,
-			  unsigned long ref_ptr, u32 *namelen, char **name,
-			  u64 *index)
+static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
+			  u32 *namelen, char **name, u64 *index)
 {
 	struct btrfs_inode_ref *ref;
 
 	ref = (struct btrfs_inode_ref *)ref_ptr;
 
 	*namelen = btrfs_inode_ref_name_len(eb, ref);
-	if (!btrfs_is_name_len_valid(eb, slot, (unsigned long)(ref + 1),
-				     *namelen))
-		return -EIO;
-
 	*name = kmalloc(*namelen, GFP_NOFS);
 	if (*name == NULL)
 		return -ENOMEM;
@@ -1287,8 +1278,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 
 	while (ref_ptr < ref_end) {
 		if (log_ref_ver) {
-			ret = extref_get_fields(eb, slot, ref_ptr, &namelen,
-					  &name, &ref_index, &parent_objectid);
+			ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
+						&ref_index, &parent_objectid);
 			/*
 			 * parent object can change from one array
 			 * item to another.
@@ -1300,8 +1291,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				goto out;
 			}
 		} else {
-			ret = ref_get_fields(eb, slot, ref_ptr, &namelen,
-					     &name, &ref_index);
+			ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
+					     &ref_index);
 		}
 		if (ret)
 			goto out;
@@ -1835,7 +1826,6 @@ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans,
 					struct extent_buffer *eb, int slot,
 					struct btrfs_key *key)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret = 0;
 	u32 item_size = btrfs_item_size_nr(eb, slot);
 	struct btrfs_dir_item *di;
@@ -1848,8 +1838,6 @@ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans,
 	ptr_end = ptr + item_size;
 	while (ptr < ptr_end) {
 		di = (struct btrfs_dir_item *)ptr;
-		if (verify_dir_item(fs_info, eb, slot, di))
-			return -EIO;
 		name_len = btrfs_dir_name_len(eb, di);
 		ret = replay_one_name(trans, root, path, eb, di, key);
 		if (ret < 0)
@@ -2024,11 +2012,6 @@ again:
 	ptr_end = ptr + item_size;
 	while (ptr < ptr_end) {
 		di = (struct btrfs_dir_item *)ptr;
-		if (verify_dir_item(fs_info, eb, slot, di)) {
-			ret = -EIO;
-			goto out;
-		}
-
 		name_len = btrfs_dir_name_len(eb, di);
 		name = kmalloc(name_len, GFP_NOFS);
 		if (!name) {
@@ -2109,7 +2092,6 @@ static int replay_xattr_deletes(struct btrfs_trans_handle *trans,
 			      struct btrfs_path *path,
 			      const u64 ino)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_key search_key;
 	struct btrfs_path *log_path;
 	int i;
@@ -2151,11 +2133,6 @@ process_leaf:
 			u32 this_len = sizeof(*di) + name_len + data_len;
 			char *name;
 
-			ret = verify_dir_item(fs_info, path->nodes[0], i, di);
-			if (ret) {
-				ret = -EIO;
-				goto out;
-			}
 			name = kmalloc(name_len, GFP_NOFS);
 			if (!name) {
 				ret = -ENOMEM;
@@ -4572,12 +4549,6 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb,
 			this_len = sizeof(*extref) + this_name_len;
 		}
 
-		ret = btrfs_is_name_len_valid(eb, slot, name_ptr,
-					      this_name_len);
-		if (!ret) {
-			ret = -EIO;
-			goto out;
-		}
 		if (this_name_len > name_len) {
 			char *new_name;
 
@@ -5432,11 +5403,10 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 				  struct dentry *parent,
 				  const loff_t start,
 				  const loff_t end,
-				  int exists_only,
+				  int inode_only,
 				  struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	int inode_only = exists_only ? LOG_INODE_EXISTS : LOG_INODE_ALL;
 	struct super_block *sb;
 	struct dentry *old_parent = NULL;
 	int ret = 0;
@@ -5602,7 +5572,7 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
 	int ret;
 
 	ret = btrfs_log_inode_parent(trans, root, BTRFS_I(d_inode(dentry)),
-			parent, start, end, 0, ctx);
+			parent, start, end, LOG_INODE_ALL, ctx);
 	dput(parent);
 
 	return ret;
@@ -5865,6 +5835,6 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 		return 0;
 
 	return btrfs_log_inode_parent(trans, root, inode, parent, 0,
-				      LLONG_MAX, 1, NULL);
+				      LLONG_MAX, LOG_INODE_EXISTS, NULL);
 }
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 49810b70afd3..a999848e745f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -145,6 +145,71 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 			     struct btrfs_bio **bbio_ret,
 			     int mirror_num, int need_raid_map);
 
+/*
+ * Device locking
+ * ==============
+ *
+ * There are several mutexes that protect manipulation of devices and low-level
+ * structures like chunks but not block groups, extents or files
+ *
+ * uuid_mutex (global lock)
+ * ------------------------
+ * protects the fs_uuids list that tracks all per-fs fs_devices, resulting from
+ * the SCAN_DEV ioctl registration or from mount either implicitly (the first
+ * device) or requested by the device= mount option
+ *
+ * the mutex can be very coarse and can cover long-running operations
+ *
+ * protects: updates to fs_devices counters like missing devices, rw devices,
+ * seeding, structure cloning, openning/closing devices at mount/umount time
+ *
+ * global::fs_devs - add, remove, updates to the global list
+ *
+ * does not protect: manipulation of the fs_devices::devices list!
+ *
+ * btrfs_device::name - renames (write side), read is RCU
+ *
+ * fs_devices::device_list_mutex (per-fs, with RCU)
+ * ------------------------------------------------
+ * protects updates to fs_devices::devices, ie. adding and deleting
+ *
+ * simple list traversal with read-only actions can be done with RCU protection
+ *
+ * may be used to exclude some operations from running concurrently without any
+ * modifications to the list (see write_all_supers)
+ *
+ * volume_mutex
+ * ------------
+ * coarse lock owned by a mounted filesystem; used to exclude some operations
+ * that cannot run in parallel and affect the higher-level properties of the
+ * filesystem like: device add/deleting/resize/replace, or balance
+ *
+ * balance_mutex
+ * -------------
+ * protects balance structures (status, state) and context accessed from
+ * several places (internally, ioctl)
+ *
+ * chunk_mutex
+ * -----------
+ * protects chunks, adding or removing during allocation, trim or when a new
+ * device is added/removed
+ *
+ * cleaner_mutex
+ * -------------
+ * a big lock that is held by the cleaner thread and prevents running subvolume
+ * cleaning together with relocation or delayed iputs
+ *
+ *
+ * Lock nesting
+ * ============
+ *
+ * uuid_mutex
+ *   volume_mutex
+ *     device_list_mutex
+ *       chunk_mutex
+ *     balance_mutex
+ */
+
 DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
 struct list_head *btrfs_get_fs_uuids(void)
@@ -180,6 +245,13 @@ static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid)
 	return fs_devs;
 }
 
+static void free_device(struct btrfs_device *device)
+{
+	rcu_string_free(device->name);
+	bio_put(device->flush_bio);
+	kfree(device);
+}
+
 static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *device;
@@ -188,9 +260,7 @@ static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
 		device = list_entry(fs_devices->devices.next,
 				    struct btrfs_device, dev_list);
 		list_del(&device->dev_list);
-		rcu_string_free(device->name);
-		bio_put(device->flush_bio);
-		kfree(device);
+		free_device(device);
 	}
 	kfree(fs_devices);
 }
@@ -220,6 +290,11 @@ void btrfs_cleanup_fs_uuids(void)
 	}
 }
 
+/*
+ * Returns a pointer to a new btrfs_device on success; ERR_PTR() on error.
+ * Returned struct is not linked onto any lists and must be destroyed using
+ * free_device.
+ */
 static struct btrfs_device *__alloc_device(void)
 {
 	struct btrfs_device *dev;
@@ -578,15 +653,77 @@ static void btrfs_free_stale_device(struct btrfs_device *cur_dev)
 			} else {
 				fs_devs->num_devices--;
 				list_del(&dev->dev_list);
-				rcu_string_free(dev->name);
-				bio_put(dev->flush_bio);
-				kfree(dev);
+				free_device(dev);
 			}
 			break;
 		}
 	}
 }
 
+static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
+			struct btrfs_device *device, fmode_t flags,
+			void *holder)
+{
+	struct request_queue *q;
+	struct block_device *bdev;
+	struct buffer_head *bh;
+	struct btrfs_super_block *disk_super;
+	u64 devid;
+	int ret;
+
+	if (device->bdev)
+		return -EINVAL;
+	if (!device->name)
+		return -EINVAL;
+
+	ret = btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1,
+				    &bdev, &bh);
+	if (ret)
+		return ret;
+
+	disk_super = (struct btrfs_super_block *)bh->b_data;
+	devid = btrfs_stack_device_id(&disk_super->dev_item);
+	if (devid != device->devid)
+		goto error_brelse;
+
+	if (memcmp(device->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE))
+		goto error_brelse;
+
+	device->generation = btrfs_super_generation(disk_super);
+
+	if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING) {
+		device->writeable = 0;
+		fs_devices->seeding = 1;
+	} else {
+		device->writeable = !bdev_read_only(bdev);
+	}
+
+	q = bdev_get_queue(bdev);
+	if (blk_queue_discard(q))
+		device->can_discard = 1;
+	if (!blk_queue_nonrot(q))
+		fs_devices->rotating = 1;
+
+	device->bdev = bdev;
+	device->in_fs_metadata = 0;
+	device->mode = flags;
+
+	fs_devices->open_devices++;
+	if (device->writeable && device->devid != BTRFS_DEV_REPLACE_DEVID) {
+		fs_devices->rw_devices++;
+		list_add(&device->dev_alloc_list, &fs_devices->alloc_list);
+	}
+	brelse(bh);
+
+	return 0;
+
+error_brelse:
+	brelse(bh);
+	blkdev_put(bdev, flags);
+
+	return -EINVAL;
+}
+
 /*
  * Add new device to list of registered devices
  *
@@ -632,8 +769,7 @@ static noinline int device_list_add(const char *path,
 
 		name = rcu_string_strdup(path, GFP_NOFS);
 		if (!name) {
-			bio_put(device->flush_bio);
-			kfree(device);
+			free_device(device);
 			return -ENOMEM;
 		}
 		rcu_assign_pointer(device->name, name);
@@ -745,8 +881,7 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 			name = rcu_string_strdup(orig_dev->name->str,
 					GFP_KERNEL);
 			if (!name) {
-				bio_put(device->flush_bio);
-				kfree(device);
+				free_device(device);
 				goto error;
 			}
 			rcu_assign_pointer(device->name, name);
@@ -810,9 +945,7 @@ again:
 		}
 		list_del_init(&device->dev_list);
 		fs_devices->num_devices--;
-		rcu_string_free(device->name);
-		bio_put(device->flush_bio);
-		kfree(device);
+		free_device(device);
 	}
 
 	if (fs_devices->seed) {
@@ -825,35 +958,25 @@ again:
 	mutex_unlock(&uuid_mutex);
 }
 
-static void __free_device(struct work_struct *work)
-{
-	struct btrfs_device *device;
-
-	device = container_of(work, struct btrfs_device, rcu_work);
-	rcu_string_free(device->name);
-	bio_put(device->flush_bio);
-	kfree(device);
-}
-
-static void free_device(struct rcu_head *head)
+static void free_device_rcu(struct rcu_head *head)
 {
 	struct btrfs_device *device;
 
 	device = container_of(head, struct btrfs_device, rcu);
-
-	INIT_WORK(&device->rcu_work, __free_device);
-	schedule_work(&device->rcu_work);
+	free_device(device);
 }
 
 static void btrfs_close_bdev(struct btrfs_device *device)
 {
-	if (device->bdev && device->writeable) {
+	if (!device->bdev)
+		return;
+
+	if (device->writeable) {
 		sync_blockdev(device->bdev);
 		invalidate_bdev(device->bdev);
 	}
 
-	if (device->bdev)
-		blkdev_put(device->bdev, device->mode);
+	blkdev_put(device->bdev, device->mode);
 }
 
 static void btrfs_prepare_close_one_device(struct btrfs_device *device)
@@ -917,7 +1040,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 				struct btrfs_device, dev_list);
 		list_del(&device->dev_list);
 		btrfs_close_bdev(device);
-		call_rcu(&device->rcu, free_device);
+		call_rcu(&device->rcu, free_device_rcu);
 	}
 
 	WARN_ON(fs_devices->open_devices);
@@ -947,93 +1070,33 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 		__btrfs_close_devices(fs_devices);
 		free_fs_devices(fs_devices);
 	}
-	/*
-	 * Wait for rcu kworkers under __btrfs_close_devices
-	 * to finish all blkdev_puts so device is really
-	 * free when umount is done.
-	 */
-	rcu_barrier();
 	return ret;
 }
 
 static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 				fmode_t flags, void *holder)
 {
-	struct request_queue *q;
-	struct block_device *bdev;
 	struct list_head *head = &fs_devices->devices;
 	struct btrfs_device *device;
 	struct btrfs_device *latest_dev = NULL;
-	struct buffer_head *bh;
-	struct btrfs_super_block *disk_super;
-	u64 devid;
-	int seeding = 1;
 	int ret = 0;
 
 	flags |= FMODE_EXCL;
 
 	list_for_each_entry(device, head, dev_list) {
-		if (device->bdev)
-			continue;
-		if (!device->name)
-			continue;
-
 		/* Just open everything we can; ignore failures here */
-		if (btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1,
-					    &bdev, &bh))
+		ret = btrfs_open_one_device(fs_devices, device, flags, holder);
+		if (ret)
 			continue;
 
-		disk_super = (struct btrfs_super_block *)bh->b_data;
-		devid = btrfs_stack_device_id(&disk_super->dev_item);
-		if (devid != device->devid)
-			goto error_brelse;
-
-		if (memcmp(device->uuid, disk_super->dev_item.uuid,
-			   BTRFS_UUID_SIZE))
-			goto error_brelse;
-
-		device->generation = btrfs_super_generation(disk_super);
 		if (!latest_dev ||
 		    device->generation > latest_dev->generation)
 			latest_dev = device;
-
-		if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING) {
-			device->writeable = 0;
-		} else {
-			device->writeable = !bdev_read_only(bdev);
-			seeding = 0;
-		}
-
-		q = bdev_get_queue(bdev);
-		if (blk_queue_discard(q))
-			device->can_discard = 1;
-		if (!blk_queue_nonrot(q))
-			fs_devices->rotating = 1;
-
-		device->bdev = bdev;
-		device->in_fs_metadata = 0;
-		device->mode = flags;
-
-		fs_devices->open_devices++;
-		if (device->writeable &&
-		    device->devid != BTRFS_DEV_REPLACE_DEVID) {
-			fs_devices->rw_devices++;
-			list_add(&device->dev_alloc_list,
-				 &fs_devices->alloc_list);
-		}
-		brelse(bh);
-		continue;
-
-error_brelse:
-		brelse(bh);
-		blkdev_put(bdev, flags);
-		continue;
 	}
 	if (fs_devices->open_devices == 0) {
 		ret = -EINVAL;
 		goto out;
 	}
-	fs_devices->seeding = seeding;
 	fs_devices->opened = 1;
 	fs_devices->latest_bdev = latest_dev->bdev;
 	fs_devices->total_rw_bytes = 0;
@@ -1662,7 +1725,7 @@ error:
  * the device information is stored in the chunk root
  * the btrfs_device struct should be fully filled in
  */
-static int btrfs_add_device(struct btrfs_trans_handle *trans,
+static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 			    struct btrfs_fs_info *fs_info,
 			    struct btrfs_device *device)
 {
@@ -1859,6 +1922,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 	u64 num_devices;
 	int ret = 0;
 
+	mutex_lock(&fs_info->volume_mutex);
 	mutex_lock(&uuid_mutex);
 
 	num_devices = fs_info->fs_devices->num_devices;
@@ -1954,7 +2018,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 		btrfs_scratch_superblocks(device->bdev, device->name->str);
 
 	btrfs_close_bdev(device);
-	call_rcu(&device->rcu, free_device);
+	call_rcu(&device->rcu, free_device_rcu);
 
 	if (cur_devices->open_devices == 0) {
 		struct btrfs_fs_devices *fs_devices;
@@ -1973,6 +2037,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 
 out:
 	mutex_unlock(&uuid_mutex);
+	mutex_unlock(&fs_info->volume_mutex);
 	return ret;
 
 error_undo:
@@ -2025,7 +2090,7 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 	}
 
 	btrfs_close_bdev(srcdev);
-	call_rcu(&srcdev->rcu, free_device);
+	call_rcu(&srcdev->rcu, free_device_rcu);
 
 	/* if this is no devs we rather delete the fs_devices */
 	if (!fs_devices->num_devices) {
@@ -2084,7 +2149,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
 
 	btrfs_close_bdev(tgtdev);
-	call_rcu(&tgtdev->rcu, free_device);
+	call_rcu(&tgtdev->rcu, free_device_rcu);
 }
 
 static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info,
@@ -2358,20 +2423,15 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 	name = rcu_string_strdup(device_path, GFP_KERNEL);
 	if (!name) {
-		bio_put(device->flush_bio);
-		kfree(device);
 		ret = -ENOMEM;
-		goto error;
+		goto error_free_device;
 	}
 	rcu_assign_pointer(device->name, name);
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
-		rcu_string_free(device->name);
-		bio_put(device->flush_bio);
-		kfree(device);
 		ret = PTR_ERR(trans);
-		goto error;
+		goto error_free_device;
 	}
 
 	q = bdev_get_queue(bdev);
@@ -2450,7 +2510,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		}
 	}
 
-	ret = btrfs_add_device(trans, fs_info, device);
+	ret = btrfs_add_dev_item(trans, fs_info, device);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto error_sysfs;
@@ -2511,9 +2571,8 @@ error_trans:
 		sb->s_flags |= SB_RDONLY;
 	if (trans)
 		btrfs_end_transaction(trans);
-	rcu_string_free(device->name);
-	bio_put(device->flush_bio);
-	kfree(device);
+error_free_device:
+	free_device(device);
 error:
 	blkdev_put(bdev, FMODE_EXCL);
 	if (seeding_dev && !unlocked) {
@@ -2579,8 +2638,7 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 
 	name = rcu_string_strdup(device_path, GFP_KERNEL);
 	if (!name) {
-		bio_put(device->flush_bio);
-		kfree(device);
+		free_device(device);
 		ret = -ENOMEM;
 		goto error;
 	}
@@ -6004,15 +6062,14 @@ static void btrfs_end_bio(struct bio *bio)
 			dev = bbio->stripes[stripe_index].dev;
 			if (dev->bdev) {
 				if (bio_op(bio) == REQ_OP_WRITE)
-					btrfs_dev_stat_inc(dev,
+					btrfs_dev_stat_inc_and_print(dev,
 						BTRFS_DEV_STAT_WRITE_ERRS);
 				else
-					btrfs_dev_stat_inc(dev,
+					btrfs_dev_stat_inc_and_print(dev,
 						BTRFS_DEV_STAT_READ_ERRS);
 				if (bio->bi_opf & REQ_PREFLUSH)
-					btrfs_dev_stat_inc(dev,
+					btrfs_dev_stat_inc_and_print(dev,
 						BTRFS_DEV_STAT_FLUSH_ERRS);
-				btrfs_dev_stat_print_on_error(dev);
 			}
 		}
 	}
@@ -6273,8 +6330,8 @@ static struct btrfs_device *add_missing_dev(struct btrfs_fs_devices *fs_devices,
  *		is generated.
  *
  * Return: a pointer to a new &struct btrfs_device on success; ERR_PTR()
- * on error.  Returned struct is not linked onto any lists and can be
- * destroyed with kfree() right away.
+ * on error.  Returned struct is not linked onto any lists and must be
+ * destroyed with free_device.
  */
 struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 					const u64 *devid,
@@ -6297,8 +6354,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 
 		ret = find_next_devid(fs_info, &tmp);
 		if (ret) {
-			bio_put(dev->flush_bio);
-			kfree(dev);
+			free_device(dev);
 			return ERR_PTR(ret);
 		}
 	}
@@ -7092,10 +7148,24 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&fs_devices->device_list_mutex);
 	list_for_each_entry(device, &fs_devices->devices, dev_list) {
-		if (!device->dev_stats_valid || !btrfs_dev_stats_dirty(device))
+		stats_cnt = atomic_read(&device->dev_stats_ccnt);
+		if (!device->dev_stats_valid || stats_cnt == 0)
 			continue;
 
-		stats_cnt = atomic_read(&device->dev_stats_ccnt);
+
+		/*
+		 * There is a LOAD-LOAD control dependency between the value of
+		 * dev_stats_ccnt and updating the on-disk values which requires
+		 * reading the in-memory counters. Such control dependencies
+		 * require explicit read memory barriers.
+		 *
+		 * This memory barriers pairs with smp_mb__before_atomic in
+		 * btrfs_dev_stat_inc/btrfs_dev_stat_set and with the full
+		 * barrier implied by atomic_xchg in
+		 * btrfs_dev_stats_read_and_reset
+		 */
+		smp_rmb();
+
 		ret = update_dev_stat_item(trans, fs_info, device);
 		if (!ret)
 			atomic_sub(stats_cnt, &device->dev_stats_ccnt);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index ff15208344a7..294c4eb6a272 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -133,7 +133,6 @@ struct btrfs_device {
 
 	struct btrfs_work work;
 	struct rcu_head rcu;
-	struct work_struct rcu_work;
 
 	/* readahead state */
 	spinlock_t reada_lock;
@@ -489,15 +488,16 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 		       struct btrfs_fs_info *fs_info, u64 chunk_offset);
 
-static inline int btrfs_dev_stats_dirty(struct btrfs_device *dev)
-{
-	return atomic_read(&dev->dev_stats_ccnt);
-}
-
 static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
 				      int index)
 {
 	atomic_inc(dev->dev_stat_values + index);
+	/*
+	 * This memory barrier orders stores updating statistics before stores
+	 * updating dev_stats_ccnt.
+	 *
+	 * It pairs with smp_rmb() in btrfs_run_dev_stats().
+	 */
 	smp_mb__before_atomic();
 	atomic_inc(&dev->dev_stats_ccnt);
 }
@@ -514,7 +514,13 @@ static inline int btrfs_dev_stat_read_and_reset(struct btrfs_device *dev,
 	int ret;
 
 	ret = atomic_xchg(dev->dev_stat_values + index, 0);
-	smp_mb__before_atomic();
+	/*
+	 * atomic_xchg implies a full memory barriers as per atomic_t.txt:
+	 * - RMW operations that have a return value are fully ordered;
+	 *
+	 * This implicit memory barriers is paired with the smp_rmb in
+	 * btrfs_run_dev_stats
+	 */
 	atomic_inc(&dev->dev_stats_ccnt);
 	return ret;
 }
@@ -523,6 +529,12 @@ static inline void btrfs_dev_stat_set(struct btrfs_device *dev,
 				      int index, unsigned long val)
 {
 	atomic_set(dev->dev_stat_values + index, val);
+	/*
+	 * This memory barrier orders stores updating statistics before stores
+	 * updating dev_stats_ccnt.
+	 *
+	 * It pairs with smp_rmb() in btrfs_run_dev_stats().
+	 */
 	smp_mb__before_atomic();
 	atomic_inc(&dev->dev_stats_ccnt);
 }
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 2c7e53f9ff1b..ad298c248da4 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -267,7 +267,6 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 {
 	struct btrfs_key key;
 	struct inode *inode = d_inode(dentry);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path;
 	int ret = 0;
@@ -336,11 +335,6 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 			u32 this_len = sizeof(*di) + name_len + data_len;
 			unsigned long name_ptr = (unsigned long)(di + 1);
 
-			if (verify_dir_item(fs_info, leaf, slot, di)) {
-				ret = -EIO;
-				goto err;
-			}
-
 			total_size += name_len + 1;
 			/*
 			 * We are just looking for how big our buffer needs to
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 17f2dd8fddb8..eb3e39012658 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -26,11 +26,14 @@
 #define ZSTD_BTRFS_MAX_WINDOWLOG 17
 #define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG)
 #define ZSTD_BTRFS_DEFAULT_LEVEL 3
+// Max supported by the algorithm is 22, but gains for small blocks (128KB)
+// are limited, thus we cap at 15.
+#define ZSTD_BTRFS_MAX_LEVEL 15
 
-static ZSTD_parameters zstd_get_btrfs_parameters(size_t src_len)
+static ZSTD_parameters zstd_get_btrfs_parameters(size_t src_len, int level)
 {
-	ZSTD_parameters params = ZSTD_getParams(ZSTD_BTRFS_DEFAULT_LEVEL,
-						src_len, 0);
+	ZSTD_parameters params = ZSTD_getParams(level, src_len, 0);
+	BUG_ON(level > ZSTD_maxCLevel());
 
 	if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG)
 		params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG;
@@ -43,6 +46,9 @@ struct workspace {
 	size_t size;
 	char *buf;
 	struct list_head list;
+	ZSTD_inBuffer in_buf;
+	ZSTD_outBuffer out_buf;
+	int level;
 };
 
 static void zstd_free_workspace(struct list_head *ws)
@@ -57,7 +63,8 @@ static void zstd_free_workspace(struct list_head *ws)
 static struct list_head *zstd_alloc_workspace(void)
 {
 	ZSTD_parameters params =
-			zstd_get_btrfs_parameters(ZSTD_BTRFS_MAX_INPUT);
+			zstd_get_btrfs_parameters(ZSTD_BTRFS_MAX_INPUT,
+						  ZSTD_BTRFS_MAX_LEVEL);
 	struct workspace *workspace;
 
 	workspace = kzalloc(sizeof(*workspace), GFP_KERNEL);
@@ -94,14 +101,12 @@ static int zstd_compress_pages(struct list_head *ws,
 	int nr_pages = 0;
 	struct page *in_page = NULL;  /* The current page to read */
 	struct page *out_page = NULL; /* The current page to write to */
-	ZSTD_inBuffer in_buf = { NULL, 0, 0 };
-	ZSTD_outBuffer out_buf = { NULL, 0, 0 };
 	unsigned long tot_in = 0;
 	unsigned long tot_out = 0;
 	unsigned long len = *total_out;
 	const unsigned long nr_dest_pages = *out_pages;
 	unsigned long max_out = nr_dest_pages * PAGE_SIZE;
-	ZSTD_parameters params = zstd_get_btrfs_parameters(len);
+	ZSTD_parameters params = zstd_get_btrfs_parameters(len, workspace->level);
 
 	*out_pages = 0;
 	*total_out = 0;
@@ -118,9 +123,9 @@ static int zstd_compress_pages(struct list_head *ws,
 
 	/* map in the first page of input data */
 	in_page = find_get_page(mapping, start >> PAGE_SHIFT);
-	in_buf.src = kmap(in_page);
-	in_buf.pos = 0;
-	in_buf.size = min_t(size_t, len, PAGE_SIZE);
+	workspace->in_buf.src = kmap(in_page);
+	workspace->in_buf.pos = 0;
+	workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
 
 
 	/* Allocate and map in the output buffer */
@@ -130,14 +135,15 @@ static int zstd_compress_pages(struct list_head *ws,
 		goto out;
 	}
 	pages[nr_pages++] = out_page;
-	out_buf.dst = kmap(out_page);
-	out_buf.pos = 0;
-	out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
+	workspace->out_buf.dst = kmap(out_page);
+	workspace->out_buf.pos = 0;
+	workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
 
 	while (1) {
 		size_t ret2;
 
-		ret2 = ZSTD_compressStream(stream, &out_buf, &in_buf);
+		ret2 = ZSTD_compressStream(stream, &workspace->out_buf,
+				&workspace->in_buf);
 		if (ZSTD_isError(ret2)) {
 			pr_debug("BTRFS: ZSTD_compressStream returned %d\n",
 					ZSTD_getErrorCode(ret2));
@@ -146,22 +152,22 @@ static int zstd_compress_pages(struct list_head *ws,
 		}
 
 		/* Check to see if we are making it bigger */
-		if (tot_in + in_buf.pos > 8192 &&
-				tot_in + in_buf.pos <
-				tot_out + out_buf.pos) {
+		if (tot_in + workspace->in_buf.pos > 8192 &&
+				tot_in + workspace->in_buf.pos <
+				tot_out + workspace->out_buf.pos) {
 			ret = -E2BIG;
 			goto out;
 		}
 
 		/* We've reached the end of our output range */
-		if (out_buf.pos >= max_out) {
-			tot_out += out_buf.pos;
+		if (workspace->out_buf.pos >= max_out) {
+			tot_out += workspace->out_buf.pos;
 			ret = -E2BIG;
 			goto out;
 		}
 
 		/* Check if we need more output space */
-		if (out_buf.pos == out_buf.size) {
+		if (workspace->out_buf.pos == workspace->out_buf.size) {
 			tot_out += PAGE_SIZE;
 			max_out -= PAGE_SIZE;
 			kunmap(out_page);
@@ -176,19 +182,20 @@ static int zstd_compress_pages(struct list_head *ws,
 				goto out;
 			}
 			pages[nr_pages++] = out_page;
-			out_buf.dst = kmap(out_page);
-			out_buf.pos = 0;
-			out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
+			workspace->out_buf.dst = kmap(out_page);
+			workspace->out_buf.pos = 0;
+			workspace->out_buf.size = min_t(size_t, max_out,
+							PAGE_SIZE);
 		}
 
 		/* We've reached the end of the input */
-		if (in_buf.pos >= len) {
-			tot_in += in_buf.pos;
+		if (workspace->in_buf.pos >= len) {
+			tot_in += workspace->in_buf.pos;
 			break;
 		}
 
 		/* Check if we need more input */
-		if (in_buf.pos == in_buf.size) {
+		if (workspace->in_buf.pos == workspace->in_buf.size) {
 			tot_in += PAGE_SIZE;
 			kunmap(in_page);
 			put_page(in_page);
@@ -196,15 +203,15 @@ static int zstd_compress_pages(struct list_head *ws,
 			start += PAGE_SIZE;
 			len -= PAGE_SIZE;
 			in_page = find_get_page(mapping, start >> PAGE_SHIFT);
-			in_buf.src = kmap(in_page);
-			in_buf.pos = 0;
-			in_buf.size = min_t(size_t, len, PAGE_SIZE);
+			workspace->in_buf.src = kmap(in_page);
+			workspace->in_buf.pos = 0;
+			workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
 		}
 	}
 	while (1) {
 		size_t ret2;
 
-		ret2 = ZSTD_endStream(stream, &out_buf);
+		ret2 = ZSTD_endStream(stream, &workspace->out_buf);
 		if (ZSTD_isError(ret2)) {
 			pr_debug("BTRFS: ZSTD_endStream returned %d\n",
 					ZSTD_getErrorCode(ret2));
@@ -212,11 +219,11 @@ static int zstd_compress_pages(struct list_head *ws,
 			goto out;
 		}
 		if (ret2 == 0) {
-			tot_out += out_buf.pos;
+			tot_out += workspace->out_buf.pos;
 			break;
 		}
-		if (out_buf.pos >= max_out) {
-			tot_out += out_buf.pos;
+		if (workspace->out_buf.pos >= max_out) {
+			tot_out += workspace->out_buf.pos;
 			ret = -E2BIG;
 			goto out;
 		}
@@ -235,9 +242,9 @@ static int zstd_compress_pages(struct list_head *ws,
 			goto out;
 		}
 		pages[nr_pages++] = out_page;
-		out_buf.dst = kmap(out_page);
-		out_buf.pos = 0;
-		out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
+		workspace->out_buf.dst = kmap(out_page);
+		workspace->out_buf.pos = 0;
+		workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
 	}
 
 	if (tot_out >= tot_in) {
@@ -273,8 +280,6 @@ static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
 	unsigned long total_out = 0;
-	ZSTD_inBuffer in_buf = { NULL, 0, 0 };
-	ZSTD_outBuffer out_buf = { NULL, 0, 0 };
 
 	stream = ZSTD_initDStream(
 			ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
@@ -284,18 +289,19 @@ static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 		goto done;
 	}
 
-	in_buf.src = kmap(pages_in[page_in_index]);
-	in_buf.pos = 0;
-	in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
+	workspace->in_buf.src = kmap(pages_in[page_in_index]);
+	workspace->in_buf.pos = 0;
+	workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
 
-	out_buf.dst = workspace->buf;
-	out_buf.pos = 0;
-	out_buf.size = PAGE_SIZE;
+	workspace->out_buf.dst = workspace->buf;
+	workspace->out_buf.pos = 0;
+	workspace->out_buf.size = PAGE_SIZE;
 
 	while (1) {
 		size_t ret2;
 
-		ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf);
+		ret2 = ZSTD_decompressStream(stream, &workspace->out_buf,
+				&workspace->in_buf);
 		if (ZSTD_isError(ret2)) {
 			pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
 					ZSTD_getErrorCode(ret2));
@@ -303,38 +309,38 @@ static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 			goto done;
 		}
 		buf_start = total_out;
-		total_out += out_buf.pos;
-		out_buf.pos = 0;
+		total_out += workspace->out_buf.pos;
+		workspace->out_buf.pos = 0;
 
-		ret = btrfs_decompress_buf2page(out_buf.dst, buf_start,
-				total_out, disk_start, orig_bio);
+		ret = btrfs_decompress_buf2page(workspace->out_buf.dst,
+				buf_start, total_out, disk_start, orig_bio);
 		if (ret == 0)
 			break;
 
-		if (in_buf.pos >= srclen)
+		if (workspace->in_buf.pos >= srclen)
 			break;
 
 		/* Check if we've hit the end of a frame */
 		if (ret2 == 0)
 			break;
 
-		if (in_buf.pos == in_buf.size) {
+		if (workspace->in_buf.pos == workspace->in_buf.size) {
 			kunmap(pages_in[page_in_index++]);
 			if (page_in_index >= total_pages_in) {
-				in_buf.src = NULL;
+				workspace->in_buf.src = NULL;
 				ret = -EIO;
 				goto done;
 			}
 			srclen -= PAGE_SIZE;
-			in_buf.src = kmap(pages_in[page_in_index]);
-			in_buf.pos = 0;
-			in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
+			workspace->in_buf.src = kmap(pages_in[page_in_index]);
+			workspace->in_buf.pos = 0;
+			workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
 		}
 	}
 	ret = 0;
 	zero_fill_bio(orig_bio);
 done:
-	if (in_buf.src)
+	if (workspace->in_buf.src)
 		kunmap(pages_in[page_in_index]);
 	return ret;
 }
@@ -348,8 +354,6 @@ static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
 	ZSTD_DStream *stream;
 	int ret = 0;
 	size_t ret2;
-	ZSTD_inBuffer in_buf = { NULL, 0, 0 };
-	ZSTD_outBuffer out_buf = { NULL, 0, 0 };
 	unsigned long total_out = 0;
 	unsigned long pg_offset = 0;
 	char *kaddr;
@@ -364,16 +368,17 @@ static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
 
 	destlen = min_t(size_t, destlen, PAGE_SIZE);
 
-	in_buf.src = data_in;
-	in_buf.pos = 0;
-	in_buf.size = srclen;
+	workspace->in_buf.src = data_in;
+	workspace->in_buf.pos = 0;
+	workspace->in_buf.size = srclen;
 
-	out_buf.dst = workspace->buf;
-	out_buf.pos = 0;
-	out_buf.size = PAGE_SIZE;
+	workspace->out_buf.dst = workspace->buf;
+	workspace->out_buf.pos = 0;
+	workspace->out_buf.size = PAGE_SIZE;
 
 	ret2 = 1;
-	while (pg_offset < destlen && in_buf.pos < in_buf.size) {
+	while (pg_offset < destlen
+	       && workspace->in_buf.pos < workspace->in_buf.size) {
 		unsigned long buf_start;
 		unsigned long buf_offset;
 		unsigned long bytes;
@@ -384,7 +389,8 @@ static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
 			ret = -EIO;
 			goto finish;
 		}
-		ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf);
+		ret2 = ZSTD_decompressStream(stream, &workspace->out_buf,
+				&workspace->in_buf);
 		if (ZSTD_isError(ret2)) {
 			pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
 					ZSTD_getErrorCode(ret2));
@@ -393,8 +399,8 @@ static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
 		}
 
 		buf_start = total_out;
-		total_out += out_buf.pos;
-		out_buf.pos = 0;
+		total_out += workspace->out_buf.pos;
+		workspace->out_buf.pos = 0;
 
 		if (total_out <= start_byte)
 			continue;
@@ -405,10 +411,11 @@ static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
 			buf_offset = 0;
 
 		bytes = min_t(unsigned long, destlen - pg_offset,
-				out_buf.size - buf_offset);
+				workspace->out_buf.size - buf_offset);
 
 		kaddr = kmap_atomic(dest_page);
-		memcpy(kaddr + pg_offset, out_buf.dst + buf_offset, bytes);
+		memcpy(kaddr + pg_offset, workspace->out_buf.dst + buf_offset,
+				bytes);
 		kunmap_atomic(kaddr);
 
 		pg_offset += bytes;
@@ -425,6 +432,10 @@ finish:
 
 static void zstd_set_level(struct list_head *ws, unsigned int type)
 {
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	unsigned level = (type & 0xF0) >> 4;
+
+	workspace->level = level > 0 ? level : ZSTD_BTRFS_DEFAULT_LEVEL;
 }
 
 const struct btrfs_compress_op btrfs_zstd_compress = {