Merge branch 'for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "There are some new user features and the usual load of invisible
  enhancements or cleanups.

  New features:

   - extend mount options to specify zlib compression level, -o
     compress=zlib:9

   - v2 of ioctl "extent to inode mapping", addressing a usecase where
     we want to retrieve more but inaccurate results and do the
     postprocessing in userspace, aiding defragmentation or
     deduplication tools

   - populate compression heuristics logic, do data sampling and try to
     guess compressibility by: looking for repeated patterns, counting
     unique byte values and distribution, calculating Shannon entropy;
     this will need more benchmarking and possibly fine tuning, but the
     base should be good enough

   - enable indexing for btrfs as lower filesystem in overlayfs

   - speedup page cache readahead during send on large files

  Internal enhancements:

   - more sanity checks of b-tree items when reading them from disk

   - more EINVAL/EUCLEAN fixups, missing BLK_STS_* conversion, other
     errno or error handling fixes

   - remove some homegrown IO-related logic, that's been obsoleted by
     core block layer changes (batching, plug/unplug, own counters)

   - add ref-verify, optional debugging feature to verify extent
     reference accounting

   - simplify code handling outstanding extents, make it more clear
     where and how the accounting is done

   - make delalloc reservations per-inode, simplify the code and make
     the logic more straightforward

   - extensive cleanup of delayed refs code

  Notable fixes:

   - fix send ioctl on 32bit with 64bit kernel"

* 'for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (102 commits)
  btrfs: Fix bug for misused dev_t when lookup in dev state hash table.
  Btrfs: heuristic: add Shannon entropy calculation
  Btrfs: heuristic: add byte core set calculation
  Btrfs: heuristic: add byte set calculation
  Btrfs: heuristic: add detection of repeated data patterns
  Btrfs: heuristic: implement sampling logic
  Btrfs: heuristic: add bucket and sample counters and other defines
  Btrfs: compression: separate heuristic/compression workspaces
  btrfs: move btrfs_truncate_block out of trans handle
  btrfs: don't call btrfs_start_delalloc_roots in flushoncommit
  btrfs: track refs in a rb_tree instead of a list
  btrfs: add a comp_refs() helper
  btrfs: switch args for comp_*_refs
  btrfs: make the delalloc block rsv per inode
  btrfs: add tracepoints for outstanding extents mods
  Btrfs: rework outstanding_extents
  btrfs: increase output size for LOGICAL_INO_V2 ioctl
  btrfs: add a flags argument to LOGICAL_INO and call it LOGICAL_INO_V2
  btrfs: add a flag to iterate_inodes_from_logical to find all extent refs for uncompressed extents
  btrfs: send: remove unused code
  ...

fs/btrfs/Kconfig

@@ -91,3 +91,14 @@ config BTRFS_ASSERT
 	  any of the assertions trip.  This is meant for btrfs developers only.
 
 	  If unsure, say N.
+
+config BTRFS_FS_REF_VERIFY
+	bool "Btrfs with the ref verify tool compiled in"
+	depends on BTRFS_FS
+	default n
+	help
+	  Enable run-time extent reference verification instrumentation.  This
+	  is meant to be used by btrfs developers for tracking down extent
+	  reference problems or verifying they didn't break something.
+
+	  If unsure, say N.

fs/btrfs/Makefile

@@ -10,10 +10,11 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   export.o tree-log.o free-space-cache.o zlib.o lzo.o zstd.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
-	   uuid-tree.o props.o hash.o free-space-tree.o
+	   uuid-tree.o props.o hash.o free-space-tree.o tree-checker.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
+btrfs-$(CONFIG_BTRFS_FS_REF_VERIFY) += ref-verify.o
 
 btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \
 	tests/extent-buffer-tests.o tests/btrfs-tests.o \

fs/btrfs/async-thread.c

@@ -67,7 +67,7 @@ struct btrfs_workqueue {
 static void normal_work_helper(struct btrfs_work *work);
 
 #define BTRFS_WORK_HELPER(name)					\
-void btrfs_##name(struct work_struct *arg)				\
+noinline_for_stack void btrfs_##name(struct work_struct *arg)		\
 {									\
 	struct btrfs_work *work = container_of(arg, struct btrfs_work,	\
 					       normal_work);		\

fs/btrfs/backref.c

@@ -40,12 +40,14 @@ static int check_extent_in_eb(const struct btrfs_key *key,
 			      const struct extent_buffer *eb,
 			      const struct btrfs_file_extent_item *fi,
 			      u64 extent_item_pos,
-			      struct extent_inode_elem **eie)
+			      struct extent_inode_elem **eie,
+			      bool ignore_offset)
 {
 	u64 offset = 0;
 	struct extent_inode_elem *e;
 
-	if (!btrfs_file_extent_compression(eb, fi) &&
+	if (!ignore_offset &&
+	    !btrfs_file_extent_compression(eb, fi) &&
 	    !btrfs_file_extent_encryption(eb, fi) &&
 	    !btrfs_file_extent_other_encoding(eb, fi)) {
 		u64 data_offset;
@@ -84,7 +86,8 @@ static void free_inode_elem_list(struct extent_inode_elem *eie)
 
 static int find_extent_in_eb(const struct extent_buffer *eb,
 			     u64 wanted_disk_byte, u64 extent_item_pos,
-			     struct extent_inode_elem **eie)
+			     struct extent_inode_elem **eie,
+			     bool ignore_offset)
 {
 	u64 disk_byte;
 	struct btrfs_key key;
@@ -113,7 +116,7 @@ static int find_extent_in_eb(const struct extent_buffer *eb,
 		if (disk_byte != wanted_disk_byte)
 			continue;
 
-		ret = check_extent_in_eb(&key, eb, fi, extent_item_pos, eie);
+		ret = check_extent_in_eb(&key, eb, fi, extent_item_pos, eie, ignore_offset);
 		if (ret < 0)
 			return ret;
 	}
@@ -419,7 +422,7 @@ static int add_indirect_ref(const struct btrfs_fs_info *fs_info,
 static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 			   struct ulist *parents, struct prelim_ref *ref,
 			   int level, u64 time_seq, const u64 *extent_item_pos,
-			   u64 total_refs)
+			   u64 total_refs, bool ignore_offset)
 {
 	int ret = 0;
 	int slot;
@@ -472,7 +475,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 			if (extent_item_pos) {
 				ret = check_extent_in_eb(&key, eb, fi,
 						*extent_item_pos,
-						&eie);
+						&eie, ignore_offset);
 				if (ret < 0)
 					break;
 			}
@@ -510,7 +513,8 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 static int resolve_indirect_ref(struct btrfs_fs_info *fs_info,
 				struct btrfs_path *path, u64 time_seq,
 				struct prelim_ref *ref, struct ulist *parents,
-				const u64 *extent_item_pos, u64 total_refs)
+				const u64 *extent_item_pos, u64 total_refs,
+				bool ignore_offset)
 {
 	struct btrfs_root *root;
 	struct btrfs_key root_key;
@@ -581,7 +585,7 @@ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info,
 	}
 
 	ret = add_all_parents(root, path, parents, ref, level, time_seq,
-			      extent_item_pos, total_refs);
+			      extent_item_pos, total_refs, ignore_offset);
 out:
 	path->lowest_level = 0;
 	btrfs_release_path(path);
@@ -616,7 +620,7 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path, u64 time_seq,
 				 struct preftrees *preftrees,
 				 const u64 *extent_item_pos, u64 total_refs,
-				 struct share_check *sc)
+				 struct share_check *sc, bool ignore_offset)
 {
 	int err;
 	int ret = 0;
@@ -661,7 +665,7 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info,
 		}
 		err = resolve_indirect_ref(fs_info, path, time_seq, ref,
 					   parents, extent_item_pos,
-					   total_refs);
+					   total_refs, ignore_offset);
 		/*
 		 * we can only tolerate ENOENT,otherwise,we should catch error
 		 * and return directly.
@@ -769,6 +773,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
 	struct btrfs_key key;
 	struct btrfs_key tmp_op_key;
 	struct btrfs_key *op_key = NULL;
+	struct rb_node *n;
 	int count;
 	int ret = 0;
 
@@ -778,7 +783,9 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
 	}
 
 	spin_lock(&head->lock);
-	list_for_each_entry(node, &head->ref_list, list) {
+	for (n = rb_first(&head->ref_tree); n; n = rb_next(n)) {
+		node = rb_entry(n, struct btrfs_delayed_ref_node,
+				ref_node);
 		if (node->seq > seq)
 			continue;
 
@@ -1107,13 +1114,17 @@ static int add_keyed_refs(struct btrfs_fs_info *fs_info,
  *
  * Otherwise this returns 0 for success and <0 for an error.
  *
+ * If ignore_offset is set to false, only extent refs whose offsets match
+ * extent_item_pos are returned.  If true, every extent ref is returned
+ * and extent_item_pos is ignored.
+ *
  * FIXME some caching might speed things up
  */
 static int find_parent_nodes(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info, u64 bytenr,
 			     u64 time_seq, struct ulist *refs,
 			     struct ulist *roots, const u64 *extent_item_pos,
-			     struct share_check *sc)
+			     struct share_check *sc, bool ignore_offset)
 {
 	struct btrfs_key key;
 	struct btrfs_path *path;
@@ -1178,7 +1189,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
 		head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
 		if (head) {
 			if (!mutex_trylock(&head->mutex)) {
-				refcount_inc(&head->node.refs);
+				refcount_inc(&head->refs);
 				spin_unlock(&delayed_refs->lock);
 
 				btrfs_release_path(path);
@@ -1189,7 +1200,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
 				 */
 				mutex_lock(&head->mutex);
 				mutex_unlock(&head->mutex);
-				btrfs_put_delayed_ref(&head->node);
+				btrfs_put_delayed_ref_head(head);
 				goto again;
 			}
 			spin_unlock(&delayed_refs->lock);
@@ -1235,7 +1246,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
 	WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect_missing_keys.root));
 
 	ret = resolve_indirect_refs(fs_info, path, time_seq, &preftrees,
-				    extent_item_pos, total_refs, sc);
+				    extent_item_pos, total_refs, sc, ignore_offset);
 	if (ret)
 		goto out;
 
@@ -1282,7 +1293,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
 				btrfs_tree_read_lock(eb);
 				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 				ret = find_extent_in_eb(eb, bytenr,
-							*extent_item_pos, &eie);
+							*extent_item_pos, &eie, ignore_offset);
 				btrfs_tree_read_unlock_blocking(eb);
 				free_extent_buffer(eb);
 				if (ret < 0)
@@ -1350,7 +1361,7 @@ static void free_leaf_list(struct ulist *blocks)
 static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
 				struct btrfs_fs_info *fs_info, u64 bytenr,
 				u64 time_seq, struct ulist **leafs,
-				const u64 *extent_item_pos)
+				const u64 *extent_item_pos, bool ignore_offset)
 {
 	int ret;
 
@@ -1359,7 +1370,7 @@ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	ret = find_parent_nodes(trans, fs_info, bytenr, time_seq,
-				*leafs, NULL, extent_item_pos, NULL);
+				*leafs, NULL, extent_item_pos, NULL, ignore_offset);
 	if (ret < 0 && ret != -ENOENT) {
 		free_leaf_list(*leafs);
 		return ret;
@@ -1383,7 +1394,8 @@ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
  */
 static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans,
 				     struct btrfs_fs_info *fs_info, u64 bytenr,
-				     u64 time_seq, struct ulist **roots)
+				     u64 time_seq, struct ulist **roots,
+				     bool ignore_offset)
 {
 	struct ulist *tmp;
 	struct ulist_node *node = NULL;
@@ -1402,7 +1414,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans,
 	ULIST_ITER_INIT(&uiter);
 	while (1) {
 		ret = find_parent_nodes(trans, fs_info, bytenr, time_seq,
-					tmp, *roots, NULL, NULL);
+					tmp, *roots, NULL, NULL, ignore_offset);
 		if (ret < 0 && ret != -ENOENT) {
 			ulist_free(tmp);
 			ulist_free(*roots);
@@ -1421,14 +1433,15 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans,
 
 int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
 			 struct btrfs_fs_info *fs_info, u64 bytenr,
-			 u64 time_seq, struct ulist **roots)
+			 u64 time_seq, struct ulist **roots,
+			 bool ignore_offset)
 {
 	int ret;
 
 	if (!trans)
 		down_read(&fs_info->commit_root_sem);
 	ret = btrfs_find_all_roots_safe(trans, fs_info, bytenr,
-					time_seq, roots);
+					time_seq, roots, ignore_offset);
 	if (!trans)
 		up_read(&fs_info->commit_root_sem);
 	return ret;
@@ -1483,7 +1496,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr)
 	ULIST_ITER_INIT(&uiter);
 	while (1) {
 		ret = find_parent_nodes(trans, fs_info, bytenr, elem.seq, tmp,
-					roots, NULL, &shared);
+					roots, NULL, &shared, false);
 		if (ret == BACKREF_FOUND_SHARED) {
 			/* this is the only condition under which we return 1 */
 			ret = 1;
@@ -1877,7 +1890,8 @@ static int iterate_leaf_refs(struct btrfs_fs_info *fs_info,
 int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 				u64 extent_item_objectid, u64 extent_item_pos,
 				int search_commit_root,
-				iterate_extent_inodes_t *iterate, void *ctx)
+				iterate_extent_inodes_t *iterate, void *ctx,
+				bool ignore_offset)
 {
 	int ret;
 	struct btrfs_trans_handle *trans = NULL;
@@ -1903,14 +1917,15 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 
 	ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid,
 				   tree_mod_seq_elem.seq, &refs,
-				   &extent_item_pos);
+				   &extent_item_pos, ignore_offset);
 	if (ret)
 		goto out;
 
 	ULIST_ITER_INIT(&ref_uiter);
 	while (!ret && (ref_node = ulist_next(refs, &ref_uiter))) {
 		ret = btrfs_find_all_roots_safe(trans, fs_info, ref_node->val,
-						tree_mod_seq_elem.seq, &roots);
+						tree_mod_seq_elem.seq, &roots,
+						ignore_offset);
 		if (ret)
 			break;
 		ULIST_ITER_INIT(&root_uiter);
@@ -1943,7 +1958,8 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 
 int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 				struct btrfs_path *path,
-				iterate_extent_inodes_t *iterate, void *ctx)
+				iterate_extent_inodes_t *iterate, void *ctx,
+				bool ignore_offset)
 {
 	int ret;
 	u64 extent_item_pos;
@@ -1961,7 +1977,7 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 	extent_item_pos = logical - found_key.objectid;
 	ret = iterate_extent_inodes(fs_info, found_key.objectid,
 					extent_item_pos, search_commit_root,
-					iterate, ctx);
+					iterate, ctx, ignore_offset);
 
 	return ret;
 }

fs/btrfs/backref.h

@@ -43,17 +43,19 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 				u64 extent_item_objectid,
 				u64 extent_offset, int search_commit_root,
-				iterate_extent_inodes_t *iterate, void *ctx);
+				iterate_extent_inodes_t *iterate, void *ctx,
+				bool ignore_offset);
 
 int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 				struct btrfs_path *path,
-				iterate_extent_inodes_t *iterate, void *ctx);
+				iterate_extent_inodes_t *iterate, void *ctx,
+				bool ignore_offset);
 
 int paths_from_inode(u64 inum, struct inode_fs_paths *ipath);
 
 int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
 			 struct btrfs_fs_info *fs_info, u64 bytenr,
-			 u64 time_seq, struct ulist **roots);
+			 u64 time_seq, struct ulist **roots, bool ignore_offset);
 char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			u32 name_len, unsigned long name_off,
 			struct extent_buffer *eb_in, u64 parent,

fs/btrfs/btrfs_inode.h

@@ -36,14 +36,13 @@
 #define BTRFS_INODE_ORPHAN_META_RESERVED	1
 #define BTRFS_INODE_DUMMY			2
 #define BTRFS_INODE_IN_DEFRAG			3
-#define BTRFS_INODE_DELALLOC_META_RESERVED	4
-#define BTRFS_INODE_HAS_ORPHAN_ITEM		5
-#define BTRFS_INODE_HAS_ASYNC_EXTENT		6
-#define BTRFS_INODE_NEEDS_FULL_SYNC		7
-#define BTRFS_INODE_COPY_EVERYTHING		8
-#define BTRFS_INODE_IN_DELALLOC_LIST		9
-#define BTRFS_INODE_READDIO_NEED_LOCK		10
-#define BTRFS_INODE_HAS_PROPS		        11
+#define BTRFS_INODE_HAS_ORPHAN_ITEM		4
+#define BTRFS_INODE_HAS_ASYNC_EXTENT		5
+#define BTRFS_INODE_NEEDS_FULL_SYNC		6
+#define BTRFS_INODE_COPY_EVERYTHING		7
+#define BTRFS_INODE_IN_DELALLOC_LIST		8
+#define BTRFS_INODE_READDIO_NEED_LOCK		9
+#define BTRFS_INODE_HAS_PROPS		        10
 
 /* in memory btrfs inode */
 struct btrfs_inode {
@@ -176,7 +175,8 @@ struct btrfs_inode {
 	 * of extent items we've reserved metadata for.
 	 */
 	unsigned outstanding_extents;
-	unsigned reserved_extents;
+
+	struct btrfs_block_rsv block_rsv;
 
 	/*
 	 * Cached values of inode properties
@@ -267,6 +267,17 @@ static inline bool btrfs_is_free_space_inode(struct btrfs_inode *inode)
 	return false;
 }
 
+static inline void btrfs_mod_outstanding_extents(struct btrfs_inode *inode,
+						 int mod)
+{
+	lockdep_assert_held(&inode->lock);
+	inode->outstanding_extents += mod;
+	if (btrfs_is_free_space_inode(inode))
+		return;
+	trace_btrfs_inode_mod_outstanding_extents(inode->root, btrfs_ino(inode),
+						  mod);
+}
+
 static inline int btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation)
 {
 	int ret = 0;

fs/btrfs/check-integrity.c

@@ -613,7 +613,7 @@ static void btrfsic_dev_state_hashtable_add(
 		struct btrfsic_dev_state_hashtable *h)
 {
 	const unsigned int hashval =
-	    (((unsigned int)((uintptr_t)ds->bdev)) &
+	    (((unsigned int)((uintptr_t)ds->bdev->bd_dev)) &
 	     (BTRFSIC_DEV2STATE_HASHTABLE_SIZE - 1));
 
 	list_add(&ds->collision_resolving_node, h->table + hashval);
@@ -2803,7 +2803,7 @@ static void __btrfsic_submit_bio(struct bio *bio)
 	mutex_lock(&btrfsic_mutex);
 	/* since btrfsic_submit_bio() is also called before
 	 * btrfsic_mount(), this might return NULL */
-	dev_state = btrfsic_dev_state_lookup(bio_dev(bio));
+	dev_state = btrfsic_dev_state_lookup(bio_dev(bio) + bio->bi_partno);
 	if (NULL != dev_state &&
 	    (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) {
 		unsigned int i = 0;
@@ -2913,7 +2913,7 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info,
 	state = kvzalloc(sizeof(*state), GFP_KERNEL);
 	if (!state) {
 		pr_info("btrfs check-integrity: allocation failed!\n");
-		return -1;
+		return -ENOMEM;
 	}
 
 	if (!btrfsic_is_initialized) {
@@ -2945,7 +2945,7 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info,
 		if (NULL == ds) {
 			pr_info("btrfs check-integrity: kmalloc() failed!\n");
 			mutex_unlock(&btrfsic_mutex);
-			return -1;
+			return -ENOMEM;
 		}
 		ds->bdev = device->bdev;
 		ds->state = state;

fs/btrfs/compression.h

@@ -76,7 +76,7 @@ struct compressed_bio {
 void btrfs_init_compress(void);
 void btrfs_exit_compress(void);
 
-int btrfs_compress_pages(int type, struct address_space *mapping,
+int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
 			 u64 start, struct page **pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
@@ -95,6 +95,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags);
 
+unsigned btrfs_compress_str2level(const char *str);
+
 enum btrfs_compression_type {
 	BTRFS_COMPRESS_NONE  = 0,
 	BTRFS_COMPRESS_ZLIB  = 1,
@@ -124,6 +126,8 @@ struct btrfs_compress_op {
 			  struct page *dest_page,
 			  unsigned long start_byte,
 			  size_t srclen, size_t destlen);
+
+	void (*set_level)(struct list_head *ws, unsigned int type);
 };
 
 extern const struct btrfs_compress_op btrfs_zlib_compress;

fs/btrfs/ctree.c

@@ -192,7 +192,7 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
  * tree until you end up with a lock on the root.  A locked buffer
  * is returned, with a reference held.
  */
-static struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
+struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
 {
 	struct extent_buffer *eb;
 
@@ -5496,8 +5496,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 			goto out;
 		} else if (left_end_reached) {
 			if (right_level == 0) {
-				ret = changed_cb(left_root, right_root,
-						left_path, right_path,
+				ret = changed_cb(left_path, right_path,
 						&right_key,
 						BTRFS_COMPARE_TREE_DELETED,
 						ctx);
@@ -5508,8 +5507,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 			continue;
 		} else if (right_end_reached) {
 			if (left_level == 0) {
-				ret = changed_cb(left_root, right_root,
-						left_path, right_path,
+				ret = changed_cb(left_path, right_path,
 						&left_key,
 						BTRFS_COMPARE_TREE_NEW,
 						ctx);
@@ -5523,8 +5521,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 		if (left_level == 0 && right_level == 0) {
 			cmp = btrfs_comp_cpu_keys(&left_key, &right_key);
 			if (cmp < 0) {
-				ret = changed_cb(left_root, right_root,
-						left_path, right_path,
+				ret = changed_cb(left_path, right_path,
 						&left_key,
 						BTRFS_COMPARE_TREE_NEW,
 						ctx);
@@ -5532,8 +5529,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 					goto out;
 				advance_left = ADVANCE;
 			} else if (cmp > 0) {
-				ret = changed_cb(left_root, right_root,
-						left_path, right_path,
+				ret = changed_cb(left_path, right_path,
 						&right_key,
 						BTRFS_COMPARE_TREE_DELETED,
 						ctx);
@@ -5550,8 +5546,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 					result = BTRFS_COMPARE_TREE_CHANGED;
 				else
 					result = BTRFS_COMPARE_TREE_SAME;
-				ret = changed_cb(left_root, right_root,
-						 left_path, right_path,
+				ret = changed_cb(left_path, right_path,
 						 &left_key, result, ctx);
 				if (ret < 0)
 					goto out;

fs/btrfs/ctree.h

@@ -523,7 +523,7 @@ struct btrfs_caching_control {
 };
 
 /* Once caching_thread() finds this much free space, it will wake up waiters. */
-#define CACHING_CTL_WAKE_UP (1024 * 1024 * 2)
+#define CACHING_CTL_WAKE_UP SZ_2M
 
 struct btrfs_io_ctl {
 	void *cur, *orig;
@@ -763,8 +763,6 @@ struct btrfs_fs_info {
 	 * delayed dir index item
 	 */
 	struct btrfs_block_rsv global_block_rsv;
-	/* block reservation for delay allocation */
-	struct btrfs_block_rsv delalloc_block_rsv;
 	/* block reservation for metadata operations */
 	struct btrfs_block_rsv trans_block_rsv;
 	/* block reservation for chunk tree */
@@ -790,6 +788,7 @@ struct btrfs_fs_info {
 	 */
 	unsigned long pending_changes;
 	unsigned long compress_type:4;
+	unsigned int compress_level;
 	int commit_interval;
 	/*
 	 * It is a suggestive number, the read side is safe even it gets a
@@ -878,9 +877,6 @@ struct btrfs_fs_info {
 	rwlock_t tree_mod_log_lock;
 	struct rb_root tree_mod_log;
 
-	atomic_t nr_async_submits;
-	atomic_t async_submit_draining;
-	atomic_t nr_async_bios;
 	atomic_t async_delalloc_pages;
 	atomic_t open_ioctl_trans;
 
@@ -1100,6 +1096,11 @@ struct btrfs_fs_info {
 	u32 nodesize;
 	u32 sectorsize;
 	u32 stripesize;
+
+#ifdef CONFIG_BTRFS_FS_REF_VERIFY
+	spinlock_t ref_verify_lock;
+	struct rb_root block_tree;
+#endif
 };
 
 static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
@@ -1338,6 +1339,7 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
 #define BTRFS_MOUNT_FRAGMENT_METADATA	(1 << 25)
 #define BTRFS_MOUNT_FREE_SPACE_TREE	(1 << 26)
 #define BTRFS_MOUNT_NOLOGREPLAY		(1 << 27)
+#define BTRFS_MOUNT_REF_VERIFY		(1 << 28)
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
 #define BTRFS_DEFAULT_MAX_INLINE	(2048)
@@ -2639,7 +2641,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   struct extent_buffer *buf,
 			   u64 parent, int last_ref);
 int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
-				     u64 root_objectid, u64 owner,
+				     struct btrfs_root *root, u64 owner,
 				     u64 offset, u64 ram_bytes,
 				     struct btrfs_key *ins);
 int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
@@ -2658,7 +2660,7 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
 				u64 bytenr, u64 num_bytes, u64 flags,
 				int level, int is_data);
 int btrfs_free_extent(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info,
+		      struct btrfs_root *root,
 		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
 		      u64 owner, u64 offset);
 
@@ -2670,7 +2672,7 @@ void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info);
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 			       struct btrfs_fs_info *fs_info);
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info,
+			 struct btrfs_root *root,
 			 u64 bytenr, u64 num_bytes, u64 parent,
 			 u64 root_objectid, u64 owner, u64 offset);
 
@@ -2744,6 +2746,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     u64 *qgroup_reserved, bool use_global_rsv);
 void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_rsv *rsv);
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
+
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
 void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes);
 int btrfs_delalloc_reserve_space(struct inode *inode,
@@ -2751,6 +2755,9 @@ int btrfs_delalloc_reserve_space(struct inode *inode,
 void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
 struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info,
 					      unsigned short type);
+void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info,
+				   struct btrfs_block_rsv *rsv,
+				   unsigned short type);
 void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
 			  struct btrfs_block_rsv *rsv);
 void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv);
@@ -2809,6 +2816,7 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
 			     const struct btrfs_key *new_key);
 struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
 struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
+struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root);
 int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path,
 			struct btrfs_key *key, int lowest_level,
 			u64 min_trans);
@@ -2821,9 +2829,7 @@ enum btrfs_compare_tree_result {
 	BTRFS_COMPARE_TREE_CHANGED,
 	BTRFS_COMPARE_TREE_SAME,
 };
-typedef int (*btrfs_changed_cb_t)(struct btrfs_root *left_root,
-				  struct btrfs_root *right_root,
-				  struct btrfs_path *left_path,
+typedef int (*btrfs_changed_cb_t)(struct btrfs_path *left_path,
 				  struct btrfs_path *right_path,
 				  struct btrfs_key *key,
 				  enum btrfs_compare_tree_result result,

fs/btrfs/delayed-inode.c

@@ -581,36 +581,12 @@ static int btrfs_delayed_inode_reserve_metadata(
 	struct btrfs_block_rsv *dst_rsv;
 	u64 num_bytes;
 	int ret;
-	bool release = false;
 
 	src_rsv = trans->block_rsv;
 	dst_rsv = &fs_info->delayed_block_rsv;
 
 	num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
 
-	/*
-	 * If our block_rsv is the delalloc block reserve then check and see if
-	 * we have our extra reservation for updating the inode.  If not fall
-	 * through and try to reserve space quickly.
-	 *
-	 * We used to try and steal from the delalloc block rsv or the global
-	 * reserve, but we'd steal a full reservation, which isn't kind.  We are
-	 * here through delalloc which means we've likely just cowed down close
-	 * to the leaf that contains the inode, so we would steal less just
-	 * doing the fallback inode update, so if we do end up having to steal
-	 * from the global block rsv we hopefully only steal one or two blocks
-	 * worth which is less likely to hurt us.
-	 */
-	if (src_rsv && src_rsv->type == BTRFS_BLOCK_RSV_DELALLOC) {
-		spin_lock(&inode->lock);
-		if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-				       &inode->runtime_flags))
-			release = true;
-		else
-			src_rsv = NULL;
-		spin_unlock(&inode->lock);
-	}
-
 	/*
 	 * btrfs_dirty_inode will update the inode under btrfs_join_transaction
 	 * which doesn't reserve space for speed.  This is a problem since we
@@ -618,7 +594,7 @@ static int btrfs_delayed_inode_reserve_metadata(
 	 * space.
 	 *
 	 * Now if src_rsv == delalloc_block_rsv we'll let it just steal since
-	 * we're accounted for.
+	 * we always reserve enough to update the inode item.
 	 */
 	if (!src_rsv || (!trans->bytes_reserved &&
 			 src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) {
@@ -643,32 +619,12 @@ static int btrfs_delayed_inode_reserve_metadata(
 	}
 
 	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
-
-	/*
-	 * Migrate only takes a reservation, it doesn't touch the size of the
-	 * block_rsv.  This is to simplify people who don't normally have things
-	 * migrated from their block rsv.  If they go to release their
-	 * reservation, that will decrease the size as well, so if migrate
-	 * reduced size we'd end up with a negative size.  But for the
-	 * delalloc_meta_reserved stuff we will only know to drop 1 reservation,
-	 * but we could in fact do this reserve/migrate dance several times
-	 * between the time we did the original reservation and we'd clean it
-	 * up.  So to take care of this, release the space for the meta
-	 * reservation here.  I think it may be time for a documentation page on
-	 * how block rsvs. work.
-	 */
 	if (!ret) {
 		trace_btrfs_space_reservation(fs_info, "delayed_inode",
 					      btrfs_ino(inode), num_bytes, 1);
 		node->bytes_reserved = num_bytes;
 	}
 
-	if (release) {
-		trace_btrfs_space_reservation(fs_info, "delalloc",
-					      btrfs_ino(inode), num_bytes, 0);
-		btrfs_block_rsv_release(fs_info, src_rsv, num_bytes);
-	}
-
 	return ret;
 }
 

fs/btrfs/delayed-ref.h

@@ -26,18 +26,8 @@
 #define BTRFS_ADD_DELAYED_EXTENT 3 /* record a full extent allocation */
 #define BTRFS_UPDATE_DELAYED_HEAD 4 /* not changing ref count on head ref */
 
-/*
- * XXX: Qu: I really hate the design that ref_head and tree/data ref shares the
- * same ref_node structure.
- * Ref_head is in a higher logic level than tree/data ref, and duplicated
- * bytenr/num_bytes in ref_node is really a waste or memory, they should be
- * referred from ref_head.
- * This gets more disgusting after we use list to store tree/data ref in
- * ref_head. Must clean this mess up later.
- */
 struct btrfs_delayed_ref_node {
-	/*data/tree ref use list, stored in ref_head->ref_list. */
-	struct list_head list;
+	struct rb_node ref_node;
 	/*
 	 * If action is BTRFS_ADD_DELAYED_REF, also link this node to
 	 * ref_head->ref_add_list, then we do not need to iterate the
@@ -91,8 +81,9 @@ struct btrfs_delayed_extent_op {
  * reference count modifications we've queued up.
  */
 struct btrfs_delayed_ref_head {
-	struct btrfs_delayed_ref_node node;
-
+	u64 bytenr;
+	u64 num_bytes;
+	refcount_t refs;
 	/*
 	 * the mutex is held while running the refs, and it is also
 	 * held when checking the sum of reference modifications.
@@ -100,7 +91,7 @@ struct btrfs_delayed_ref_head {
 	struct mutex mutex;
 
 	spinlock_t lock;
-	struct list_head ref_list;
+	struct rb_root ref_tree;
 	/* accumulate add BTRFS_ADD_DELAYED_REF nodes to this ref_add_list. */
 	struct list_head ref_add_list;
 
@@ -115,6 +106,14 @@ struct btrfs_delayed_ref_head {
 	 */
 	int total_ref_mod;
 
+	/*
+	 * This is the current outstanding mod references for this bytenr.  This
+	 * is used with lookup_extent_info to get an accurate reference count
+	 * for a bytenr, so it is adjusted as delayed refs are run so that any
+	 * on disk reference count + ref_mod is accurate.
+	 */
+	int ref_mod;
+
 	/*
 	 * For qgroup reserved space freeing.
 	 *
@@ -234,15 +233,18 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
 		case BTRFS_SHARED_DATA_REF_KEY:
 			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
 			break;
-		case 0:
-			kmem_cache_free(btrfs_delayed_ref_head_cachep, ref);
-			break;
 		default:
 			BUG();
 		}
 	}
 }
 
+static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *head)
+{
+	if (refcount_dec_and_test(&head->refs))
+		kmem_cache_free(btrfs_delayed_ref_head_cachep, head);
+}
+
 int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 			       struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
@@ -282,36 +284,18 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
 			    struct btrfs_delayed_ref_root *delayed_refs,
 			    u64 seq);
 
-/*
- * a node might live in a head or a regular ref, this lets you
- * test for the proper type to use.
- */
-static int btrfs_delayed_ref_is_head(struct btrfs_delayed_ref_node *node)
-{
-	return node->is_head;
-}
-
 /*
  * helper functions to cast a node into its container
  */
 static inline struct btrfs_delayed_tree_ref *
 btrfs_delayed_node_to_tree_ref(struct btrfs_delayed_ref_node *node)
 {
-	WARN_ON(btrfs_delayed_ref_is_head(node));
 	return container_of(node, struct btrfs_delayed_tree_ref, node);
 }
 
 static inline struct btrfs_delayed_data_ref *
 btrfs_delayed_node_to_data_ref(struct btrfs_delayed_ref_node *node)
 {
-	WARN_ON(btrfs_delayed_ref_is_head(node));
 	return container_of(node, struct btrfs_delayed_data_ref, node);
 }
-
-static inline struct btrfs_delayed_ref_head *
-btrfs_delayed_node_to_head(struct btrfs_delayed_ref_node *node)
-{
-	WARN_ON(!btrfs_delayed_ref_is_head(node));
-	return container_of(node, struct btrfs_delayed_ref_head, node);
-}
 #endif

fs/btrfs/extent_io.c

@@ -110,7 +110,6 @@ struct extent_page_data {
 	struct bio *bio;
 	struct extent_io_tree *tree;
 	get_extent_t *get_extent;
-	unsigned long bio_flags;
 
 	/* tells writepage not to lock the state bits for this range
 	 * it still does the unlocking
@@ -2762,8 +2761,8 @@ static int merge_bio(struct extent_io_tree *tree, struct page *page,
  */
 static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 			      struct writeback_control *wbc,
-			      struct page *page, sector_t sector,
-			      size_t size, unsigned long offset,
+			      struct page *page, u64 offset,
+			      size_t size, unsigned long pg_offset,
 			      struct block_device *bdev,
 			      struct bio **bio_ret,
 			      bio_end_io_t end_io_func,
@@ -2777,6 +2776,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 	int contig = 0;
 	int old_compressed = prev_bio_flags & EXTENT_BIO_COMPRESSED;
 	size_t page_size = min_t(size_t, size, PAGE_SIZE);
+	sector_t sector = offset >> 9;
 
 	if (bio_ret && *bio_ret) {
 		bio = *bio_ret;
@@ -2787,8 +2787,8 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 
 		if (prev_bio_flags != bio_flags || !contig ||
 		    force_bio_submit ||
-		    merge_bio(tree, page, offset, page_size, bio, bio_flags) ||
-		    bio_add_page(bio, page, page_size, offset) < page_size) {
+		    merge_bio(tree, page, pg_offset, page_size, bio, bio_flags) ||
+		    bio_add_page(bio, page, page_size, pg_offset) < page_size) {
 			ret = submit_one_bio(bio, mirror_num, prev_bio_flags);
 			if (ret < 0) {
 				*bio_ret = NULL;
@@ -2802,8 +2802,8 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 		}
 	}
 
-	bio = btrfs_bio_alloc(bdev, (u64)sector << 9);
-	bio_add_page(bio, page, page_size, offset);
+	bio = btrfs_bio_alloc(bdev, offset);
+	bio_add_page(bio, page, page_size, pg_offset);
 	bio->bi_end_io = end_io_func;
 	bio->bi_private = tree;
 	bio->bi_write_hint = page->mapping->host->i_write_hint;
@@ -2893,7 +2893,6 @@ static int __do_readpage(struct extent_io_tree *tree,
 	u64 last_byte = i_size_read(inode);
 	u64 block_start;
 	u64 cur_end;
-	sector_t sector;
 	struct extent_map *em;
 	struct block_device *bdev;
 	int ret = 0;
@@ -2929,6 +2928,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 	}
 	while (cur <= end) {
 		bool force_bio_submit = false;
+		u64 offset;
 
 		if (cur >= last_byte) {
 			char *userpage;
@@ -2968,9 +2968,9 @@ static int __do_readpage(struct extent_io_tree *tree,
 		iosize = ALIGN(iosize, blocksize);
 		if (this_bio_flag & EXTENT_BIO_COMPRESSED) {
 			disk_io_size = em->block_len;
-			sector = em->block_start >> 9;
+			offset = em->block_start;
 		} else {
-			sector = (em->block_start + extent_offset) >> 9;
+			offset = em->block_start + extent_offset;
 			disk_io_size = iosize;
 		}
 		bdev = em->bdev;
@@ -3063,8 +3063,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 		}
 
 		ret = submit_extent_page(REQ_OP_READ | read_flags, tree, NULL,
-					 page, sector, disk_io_size, pg_offset,
-					 bdev, bio,
+					 page, offset, disk_io_size,
+					 pg_offset, bdev, bio,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
 					 this_bio_flag,
@@ -3325,7 +3325,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	u64 extent_offset;
 	u64 block_start;
 	u64 iosize;
-	sector_t sector;
 	struct extent_map *em;
 	struct block_device *bdev;
 	size_t pg_offset = 0;
@@ -3368,6 +3367,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 
 	while (cur <= end) {
 		u64 em_end;
+		u64 offset;
 
 		if (cur >= i_size) {
 			if (tree->ops && tree->ops->writepage_end_io_hook)
@@ -3389,7 +3389,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 		BUG_ON(end < cur);
 		iosize = min(em_end - cur, end - cur + 1);
 		iosize = ALIGN(iosize, blocksize);
-		sector = (em->block_start + extent_offset) >> 9;
+		offset = em->block_start + extent_offset;
 		bdev = em->bdev;
 		block_start = em->block_start;
 		compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
@@ -3432,7 +3432,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 		}
 
 		ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
-					 page, sector, iosize, pg_offset,
+					 page, offset, iosize, pg_offset,
 					 bdev, &epd->bio,
 					 end_bio_extent_writepage,
 					 0, 0, 0, false);
@@ -3716,7 +3716,6 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	u64 offset = eb->start;
 	u32 nritems;
 	unsigned long i, num_pages;
-	unsigned long bio_flags = 0;
 	unsigned long start, end;
 	unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
 	int ret = 0;
@@ -3724,8 +3723,6 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
 	num_pages = num_extent_pages(eb->start, eb->len);
 	atomic_set(&eb->io_pages, num_pages);
-	if (btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID)
-		bio_flags = EXTENT_BIO_TREE_LOG;
 
 	/* set btree blocks beyond nritems with 0 to avoid stale content. */
 	nritems = btrfs_header_nritems(eb);
@@ -3749,11 +3746,10 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		clear_page_dirty_for_io(p);
 		set_page_writeback(p);
 		ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
-					 p, offset >> 9, PAGE_SIZE, 0, bdev,
+					 p, offset, PAGE_SIZE, 0, bdev,
 					 &epd->bio,
 					 end_bio_extent_buffer_writepage,
-					 0, epd->bio_flags, bio_flags, false);
-		epd->bio_flags = bio_flags;
+					 0, 0, 0, false);
 		if (ret) {
 			set_btree_ioerr(p);
 			if (PageWriteback(p))
@@ -3790,7 +3786,6 @@ int btree_write_cache_pages(struct address_space *mapping,
 		.tree = tree,
 		.extent_locked = 0,
 		.sync_io = wbc->sync_mode == WB_SYNC_ALL,
-		.bio_flags = 0,
 	};
 	int ret = 0;
 	int done = 0;
@@ -4063,7 +4058,7 @@ static void flush_epd_write_bio(struct extent_page_data *epd)
 	if (epd->bio) {
 		int ret;
 
-		ret = submit_one_bio(epd->bio, 0, epd->bio_flags);
+		ret = submit_one_bio(epd->bio, 0, 0);
 		BUG_ON(ret < 0); /* -ENOMEM */
 		epd->bio = NULL;
 	}
@@ -4086,7 +4081,6 @@ int extent_write_full_page(struct extent_io_tree *tree, struct page *page,
 		.get_extent = get_extent,
 		.extent_locked = 0,
 		.sync_io = wbc->sync_mode == WB_SYNC_ALL,
-		.bio_flags = 0,
 	};
 
 	ret = __extent_writepage(page, wbc, &epd);
@@ -4111,7 +4105,6 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
 		.get_extent = get_extent,
 		.extent_locked = 1,
 		.sync_io = mode == WB_SYNC_ALL,
-		.bio_flags = 0,
 	};
 	struct writeback_control wbc_writepages = {
 		.sync_mode	= mode,
@@ -4151,7 +4144,6 @@ int extent_writepages(struct extent_io_tree *tree,
 		.get_extent = get_extent,
 		.extent_locked = 0,
 		.sync_io = wbc->sync_mode == WB_SYNC_ALL,
-		.bio_flags = 0,
 	};
 
 	ret = extent_write_cache_pages(mapping, wbc, __extent_writepage, &epd,

fs/btrfs/extent_io.h

@@ -34,7 +34,6 @@
  * type for this bio
  */
 #define EXTENT_BIO_COMPRESSED 1
-#define EXTENT_BIO_TREE_LOG 2
 #define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */

fs/btrfs/file.c

@@ -856,7 +856,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 			btrfs_mark_buffer_dirty(leaf);
 
 			if (update_refs && disk_bytenr > 0) {
-				ret = btrfs_inc_extent_ref(trans, fs_info,
+				ret = btrfs_inc_extent_ref(trans, root,
 						disk_bytenr, num_bytes, 0,
 						root->root_key.objectid,
 						new_key.objectid,
@@ -940,7 +940,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 				extent_end = ALIGN(extent_end,
 						   fs_info->sectorsize);
 			} else if (update_refs && disk_bytenr > 0) {
-				ret = btrfs_free_extent(trans, fs_info,
+				ret = btrfs_free_extent(trans, root,
 						disk_bytenr, num_bytes, 0,
 						root->root_key.objectid,
 						key.objectid, key.offset -
@@ -1234,7 +1234,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 						extent_end - split);
 		btrfs_mark_buffer_dirty(leaf);
 
-		ret = btrfs_inc_extent_ref(trans, fs_info, bytenr, num_bytes,
+		ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes,
 					   0, root->root_key.objectid,
 					   ino, orig_offset);
 		if (ret) {
@@ -1268,7 +1268,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 		extent_end = other_end;
 		del_slot = path->slots[0] + 1;
 		del_nr++;
-		ret = btrfs_free_extent(trans, fs_info, bytenr, num_bytes,
+		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
 					ino, orig_offset);
 		if (ret) {
@@ -1288,7 +1288,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 		key.offset = other_start;
 		del_slot = path->slots[0];
 		del_nr++;
-		ret = btrfs_free_extent(trans, fs_info, bytenr, num_bytes,
+		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
 					ino, orig_offset);
 		if (ret) {
@@ -1590,7 +1590,6 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	int ret = 0;
 	bool only_release_metadata = false;
 	bool force_page_uptodate = false;
-	bool need_unlock;
 
 	nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE),
 			PAGE_SIZE / (sizeof(struct page *)));
@@ -1613,6 +1612,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		size_t copied;
 		size_t dirty_sectors;
 		size_t num_sectors;
+		int extents_locked;
 
 		WARN_ON(num_pages > nrptrs);
 
@@ -1656,6 +1656,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			}
 		}
 
+		WARN_ON(reserve_bytes == 0);
 		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
 				reserve_bytes);
 		if (ret) {
@@ -1669,7 +1670,6 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		}
 
 		release_bytes = reserve_bytes;
-		need_unlock = false;
 again:
 		/*
 		 * This is going to setup the pages array with the number of
@@ -1679,19 +1679,23 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		ret = prepare_pages(inode, pages, num_pages,
 				    pos, write_bytes,
 				    force_page_uptodate);
-		if (ret)
+		if (ret) {
+			btrfs_delalloc_release_extents(BTRFS_I(inode),
+						       reserve_bytes);
 			break;
+		}
 
-		ret = lock_and_cleanup_extent_if_need(BTRFS_I(inode), pages,
+		extents_locked = lock_and_cleanup_extent_if_need(
+				BTRFS_I(inode), pages,
 				num_pages, pos, write_bytes, &lockstart,
 				&lockend, &cached_state);
-		if (ret < 0) {
-			if (ret == -EAGAIN)
+		if (extents_locked < 0) {
+			if (extents_locked == -EAGAIN)
 				goto again;
+			btrfs_delalloc_release_extents(BTRFS_I(inode),
+						       reserve_bytes);
+			ret = extents_locked;
 			break;
-		} else if (ret > 0) {
-			need_unlock = true;
-			ret = 0;
 		}
 
 		copied = btrfs_copy_from_user(pos, write_bytes, pages, i);
@@ -1718,23 +1722,10 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 						   PAGE_SIZE);
 		}
 
-		/*
-		 * If we had a short copy we need to release the excess delaloc
-		 * bytes we reserved.  We need to increment outstanding_extents
-		 * because btrfs_delalloc_release_space and
-		 * btrfs_delalloc_release_metadata will decrement it, but
-		 * we still have an outstanding extent for the chunk we actually
-		 * managed to copy.
-		 */
 		if (num_sectors > dirty_sectors) {
 			/* release everything except the sectors we dirtied */
 			release_bytes -= dirty_sectors <<
 						fs_info->sb->s_blocksize_bits;
-			if (copied > 0) {
-				spin_lock(&BTRFS_I(inode)->lock);
-				BTRFS_I(inode)->outstanding_extents++;
-				spin_unlock(&BTRFS_I(inode)->lock);
-			}
 			if (only_release_metadata) {
 				btrfs_delalloc_release_metadata(BTRFS_I(inode),
 								release_bytes);
@@ -1756,10 +1747,11 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		if (copied > 0)
 			ret = btrfs_dirty_pages(inode, pages, dirty_pages,
 						pos, copied, NULL);
-		if (need_unlock)
+		if (extents_locked)
 			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 					     lockstart, lockend, &cached_state,
 					     GFP_NOFS);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes);
 		if (ret) {
 			btrfs_drop_pages(pages, num_pages);
 			break;
@@ -2046,7 +2038,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_log_ctx ctx;
 	int ret = 0, err;
-	bool full_sync = 0;
+	bool full_sync = false;
 	u64 len;
 
 	/*

fs/btrfs/free-space-tree.c

@@ -1286,12 +1286,8 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
 					struct btrfs_block_group_cache *block_group,
 					struct btrfs_path *path)
 {
-	u64 start, end;
 	int ret;
 
-	start = block_group->key.objectid;
-	end = block_group->key.objectid + block_group->key.offset;
-
 	block_group->needs_free_space = 0;
 
 	ret = add_new_free_space_info(trans, fs_info, block_group, path);

fs/btrfs/inode-map.c

@@ -500,11 +500,12 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
 					      prealloc, prealloc, &alloc_hint);
 	if (ret) {
-		btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
 		goto out_put;
 	}
 
 	ret = btrfs_write_out_ino_cache(root, trans, path, inode);
+	btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
 out_put:
 	iput(inode);
 out_release:

fs/btrfs/ioctl.c

@@ -86,6 +86,19 @@ struct btrfs_ioctl_received_subvol_args_32 {
 				struct btrfs_ioctl_received_subvol_args_32)
 #endif
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)
+struct btrfs_ioctl_send_args_32 {
+	__s64 send_fd;			/* in */
+	__u64 clone_sources_count;	/* in */
+	compat_uptr_t clone_sources;	/* in */
+	__u64 parent_root;		/* in */
+	__u64 flags;			/* in */
+	__u64 reserved[4];		/* in */
+} __attribute__ ((__packed__));
+
+#define BTRFS_IOC_SEND_32 _IOW(BTRFS_IOCTL_MAGIC, 38, \
+			       struct btrfs_ioctl_send_args_32)
+#endif
 
 static int btrfs_clone(struct inode *src, struct inode *inode,
 		       u64 off, u64 olen, u64 olen_aligned, u64 destoff,
@@ -609,23 +622,6 @@ static noinline int create_subvol(struct inode *dir,
 	return ret;
 }
 
-static void btrfs_wait_for_no_snapshotting_writes(struct btrfs_root *root)
-{
-	s64 writers;
-	DEFINE_WAIT(wait);
-
-	do {
-		prepare_to_wait(&root->subv_writers->wait, &wait,
-				TASK_UNINTERRUPTIBLE);
-
-		writers = percpu_counter_sum(&root->subv_writers->counter);
-		if (writers)
-			schedule();
-
-		finish_wait(&root->subv_writers->wait, &wait);
-	} while (writers);
-}
-
 static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 			   struct dentry *dentry,
 			   u64 *async_transid, bool readonly,
@@ -654,7 +650,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 
 	atomic_inc(&root->will_be_snapshotted);
 	smp_mb__after_atomic();
-	btrfs_wait_for_no_snapshotting_writes(root);
+	/* wait for no snapshot writes */
+	wait_event(root->subv_writers->wait,
+		   percpu_counter_sum(&root->subv_writers->counter) == 0);
 
 	ret = btrfs_start_delalloc_inodes(root, 0);
 	if (ret)
@@ -1219,6 +1217,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 		unlock_page(pages[i]);
 		put_page(pages[i]);
 	}
+	btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
 	extent_changeset_free(data_reserved);
 	return i_done;
 out:
@@ -1229,6 +1228,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	btrfs_delalloc_release_space(inode, data_reserved,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT);
+	btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
 	extent_changeset_free(data_reserved);
 	return ret;
 
@@ -1420,21 +1420,6 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			filemap_flush(inode->i_mapping);
 	}
 
-	if (do_compress) {
-		/* the filemap_flush will queue IO into the worker threads, but
-		 * we have to make sure the IO is actually started and that
-		 * ordered extents get created before we return
-		 */
-		atomic_inc(&fs_info->async_submit_draining);
-		while (atomic_read(&fs_info->nr_async_submits) ||
-		       atomic_read(&fs_info->async_delalloc_pages)) {
-			wait_event(fs_info->async_submit_wait,
-				   (atomic_read(&fs_info->nr_async_submits) == 0 &&
-				    atomic_read(&fs_info->async_delalloc_pages) == 0));
-		}
-		atomic_dec(&fs_info->async_submit_draining);
-	}
-
 	if (range->compress_type == BTRFS_COMPRESS_LZO) {
 		btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
 	} else if (range->compress_type == BTRFS_COMPRESS_ZSTD) {
@@ -1842,8 +1827,13 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 
 	ret = btrfs_update_root(trans, fs_info->tree_root,
 				&root->root_key, &root->root_item);
+	if (ret < 0) {
+		btrfs_end_transaction(trans);
+		goto out_reset;
+	}
+
+	ret = btrfs_commit_transaction(trans);
 
-	btrfs_commit_transaction(trans);
 out_reset:
 	if (ret)
 		btrfs_set_root_flags(&root->root_item, root_flags);
@@ -2179,7 +2169,7 @@ static noinline int btrfs_ioctl_tree_search_v2(struct file *file,
 
 	inode = file_inode(file);
 	ret = search_ioctl(inode, &args.key, &buf_size,
-			   (char *)(&uarg->buf[0]));
+			   (char __user *)(&uarg->buf[0]));
 	if (ret == 0 && copy_to_user(&uarg->key, &args.key, sizeof(args.key)))
 		ret = -EFAULT;
 	else if (ret == -EOVERFLOW &&
@@ -3706,7 +3696,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 				if (disko) {
 					inode_add_bytes(inode, datal);
 					ret = btrfs_inc_extent_ref(trans,
-							fs_info,
+							root,
 							disko, diskl, 0,
 							root->root_key.objectid,
 							btrfs_ino(BTRFS_I(inode)),
@@ -4129,10 +4119,12 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info,
 	struct btrfs_ioctl_space_info *dest_orig;
 	struct btrfs_ioctl_space_info __user *user_dest;
 	struct btrfs_space_info *info;
-	u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
-		       BTRFS_BLOCK_GROUP_SYSTEM,
-		       BTRFS_BLOCK_GROUP_METADATA,
-		       BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA};
+	static const u64 types[] = {
+		BTRFS_BLOCK_GROUP_DATA,
+		BTRFS_BLOCK_GROUP_SYSTEM,
+		BTRFS_BLOCK_GROUP_METADATA,
+		BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA
+	};
 	int num_types = 4;
 	int alloc_size;
 	int ret = 0;
@@ -4504,8 +4496,8 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg)
 		ipath->fspath->val[i] = rel_ptr;
 	}
 
-	ret = copy_to_user((void *)(unsigned long)ipa->fspath,
-			   (void *)(unsigned long)ipath->fspath, size);
+	ret = copy_to_user((void __user *)(unsigned long)ipa->fspath,
+			   ipath->fspath, size);
 	if (ret) {
 		ret = -EFAULT;
 		goto out;
@@ -4540,13 +4532,14 @@ static int build_ino_list(u64 inum, u64 offset, u64 root, void *ctx)
 }
 
 static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
-					void __user *arg)
+					void __user *arg, int version)
 {
 	int ret = 0;
 	int size;
 	struct btrfs_ioctl_logical_ino_args *loi;
 	struct btrfs_data_container *inodes = NULL;
 	struct btrfs_path *path = NULL;
+	bool ignore_offset;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -4555,13 +4548,30 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
 	if (IS_ERR(loi))
 		return PTR_ERR(loi);
 
+	if (version == 1) {
+		ignore_offset = false;
+		size = min_t(u32, loi->size, SZ_64K);
+	} else {
+		/* All reserved bits must be 0 for now */
+		if (memchr_inv(loi->reserved, 0, sizeof(loi->reserved))) {
+			ret = -EINVAL;
+			goto out_loi;
+		}
+		/* Only accept flags we have defined so far */
+		if (loi->flags & ~(BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET)) {
+			ret = -EINVAL;
+			goto out_loi;
+		}
+		ignore_offset = loi->flags & BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET;
+		size = min_t(u32, loi->size, SZ_16M);
+	}
+
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	size = min_t(u32, loi->size, SZ_64K);
 	inodes = init_data_container(size);
 	if (IS_ERR(inodes)) {
 		ret = PTR_ERR(inodes);
@@ -4570,20 +4580,21 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
 	}
 
 	ret = iterate_inodes_from_logical(loi->logical, fs_info, path,
-					  build_ino_list, inodes);
+					  build_ino_list, inodes, ignore_offset);
 	if (ret == -EINVAL)
 		ret = -ENOENT;
 	if (ret < 0)
 		goto out;
 
-	ret = copy_to_user((void *)(unsigned long)loi->inodes,
-			   (void *)(unsigned long)inodes, size);
+	ret = copy_to_user((void __user *)(unsigned long)loi->inodes, inodes,
+			   size);
 	if (ret)
 		ret = -EFAULT;
 
 out:
 	btrfs_free_path(path);
 	kvfree(inodes);
+out_loi:
 	kfree(loi);
 
 	return ret;
@@ -5160,15 +5171,11 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 					  root->root_key.objectid);
 		if (ret < 0 && ret != -EEXIST) {
 			btrfs_abort_transaction(trans, ret);
+			btrfs_end_transaction(trans);
 			goto out;
 		}
 	}
 	ret = btrfs_commit_transaction(trans);
-	if (ret < 0) {
-		btrfs_abort_transaction(trans, ret);
-		goto out;
-	}
-
 out:
 	up_write(&fs_info->subvol_sem);
 	mnt_drop_write_file(file);
@@ -5490,6 +5497,41 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
 	return ret;
 }
 
+static int _btrfs_ioctl_send(struct file *file, void __user *argp, bool compat)
+{
+	struct btrfs_ioctl_send_args *arg;
+	int ret;
+
+	if (compat) {
+#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)
+		struct btrfs_ioctl_send_args_32 args32;
+
+		ret = copy_from_user(&args32, argp, sizeof(args32));
+		if (ret)
+			return -EFAULT;
+		arg = kzalloc(sizeof(*arg), GFP_KERNEL);
+		if (!arg)
+			return -ENOMEM;
+		arg->send_fd = args32.send_fd;
+		arg->clone_sources_count = args32.clone_sources_count;
+		arg->clone_sources = compat_ptr(args32.clone_sources);
+		arg->parent_root = args32.parent_root;
+		arg->flags = args32.flags;
+		memcpy(arg->reserved, args32.reserved,
+		       sizeof(args32.reserved));
+#else
+		return -ENOTTY;
+#endif
+	} else {
+		arg = memdup_user(argp, sizeof(*arg));
+		if (IS_ERR(arg))
+			return PTR_ERR(arg);
+	}
+	ret = btrfs_ioctl_send(file, arg);
+	kfree(arg);
+	return ret;
+}
+
 long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
 {
@@ -5554,7 +5596,9 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_INO_PATHS:
 		return btrfs_ioctl_ino_to_path(root, argp);
 	case BTRFS_IOC_LOGICAL_INO:
-		return btrfs_ioctl_logical_to_ino(fs_info, argp);
+		return btrfs_ioctl_logical_to_ino(fs_info, argp, 1);
+	case BTRFS_IOC_LOGICAL_INO_V2:
+		return btrfs_ioctl_logical_to_ino(fs_info, argp, 2);
 	case BTRFS_IOC_SPACE_INFO:
 		return btrfs_ioctl_space_info(fs_info, argp);
 	case BTRFS_IOC_SYNC: {
@@ -5595,7 +5639,11 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_set_received_subvol_32(file, argp);
 #endif
 	case BTRFS_IOC_SEND:
-		return btrfs_ioctl_send(file, argp);
+		return _btrfs_ioctl_send(file, argp, false);
+#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)
+	case BTRFS_IOC_SEND_32:
+		return _btrfs_ioctl_send(file, argp, true);
+#endif
 	case BTRFS_IOC_GET_DEV_STATS:
 		return btrfs_ioctl_get_dev_stats(fs_info, argp);
 	case BTRFS_IOC_QUOTA_CTL:

fs/btrfs/lzo.c

@@ -430,10 +430,15 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
 	return ret;
 }
 
+static void lzo_set_level(struct list_head *ws, unsigned int type)
+{
+}
+
 const struct btrfs_compress_op btrfs_lzo_compress = {
 	.alloc_workspace	= lzo_alloc_workspace,
 	.free_workspace		= lzo_free_workspace,
 	.compress_pages		= lzo_compress_pages,
 	.decompress_bio		= lzo_decompress_bio,
 	.decompress		= lzo_decompress,
+	.set_level		= lzo_set_level,
 };

fs/btrfs/ordered-data.c

@@ -242,6 +242,15 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	}
 	spin_unlock(&root->ordered_extent_lock);
 
+	/*
+	 * We don't need the count_max_extents here, we can assume that all of
+	 * that work has been done at higher layers, so this is truly the
+	 * smallest the extent is going to get.
+	 */
+	spin_lock(&BTRFS_I(inode)->lock);
+	btrfs_mod_outstanding_extents(BTRFS_I(inode), 1);
+	spin_unlock(&BTRFS_I(inode)->lock);
+
 	return 0;
 }
 
@@ -591,11 +600,19 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_inode_tree *tree;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
+	struct btrfs_root *root = btrfs_inode->root;
 	struct rb_node *node;
 	bool dec_pending_ordered = false;
 
-	tree = &BTRFS_I(inode)->ordered_tree;
+	/* This is paired with btrfs_add_ordered_extent. */
+	spin_lock(&btrfs_inode->lock);
+	btrfs_mod_outstanding_extents(btrfs_inode, -1);
+	spin_unlock(&btrfs_inode->lock);
+	if (root != fs_info->tree_root)
+		btrfs_delalloc_release_metadata(btrfs_inode, entry->len);
+
+	tree = &btrfs_inode->ordered_tree;
 	spin_lock_irq(&tree->lock);
 	node = &entry->rb_node;
 	rb_erase(node, &tree->tree);

fs/btrfs/root-tree.c

@@ -226,10 +226,6 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info)
 	struct btrfs_root *root;
 	int err = 0;
 	int ret;
-	bool can_recover = true;
-
-	if (sb_rdonly(fs_info->sb))
-		can_recover = false;
 
 	path = btrfs_alloc_path();
 	if (!path)