Merge tag 'for-4.18-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "User visible features:

   - added support for the ioctl FS_IOC_FSGETXATTR, per-inode flags,
     successor of GET/SETFLAGS; now supports only existing flags:
     append, immutable, noatime, nodump, sync

   - 3 new unprivileged ioctls to allow users to enumerate subvolumes

   - dedupe syscall implementation does not restrict the range to 16MiB,
     though it still splits the whole range to 16MiB chunks

   - on user demand, rmdir() is able to delete an empty subvolume,
     export the capability in sysfs

   - fix inode number types in tracepoints, other cleanups

   - send: improved speed when dealing with a large removed directory,
     measurements show decrease from 2000 minutes to 2 minutes on a
     directory with 2 million entries

   - pre-commit check of superblock to detect a mysterious in-memory
     corruption

   - log message updates

  Other changes:

   - orphan inode cleanup improved, does no keep long-standing
     reservations that could lead up to early ENOSPC in some cases

   - slight improvement of handling snapshotted NOCOW files by avoiding
     some unnecessary tree searches

   - avoid OOM when dealing with many unmergeable small extents at flush
     time

   - speedup conversion of free space tree representations from/to
     bitmap/tree

   - code refactoring, deletion, cleanups:
      + delayed refs
      + delayed iput
      + redundant argument removals
      + memory barrier cleanups
      + remove a redundant mutex supposedly excluding several ioctls to
        run in parallel

   - new tracepoints for blockgroup manipulation

   - more sanity checks of compressed headers"

* tag 'for-4.18-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (183 commits)
  btrfs: Add unprivileged version of ino_lookup ioctl
  btrfs: Add unprivileged ioctl which returns subvolume's ROOT_REF
  btrfs: Add unprivileged ioctl which returns subvolume information
  Btrfs: clean up error handling in btrfs_truncate()
  btrfs: Factor out write portion of btrfs_get_blocks_direct
  btrfs: Factor out read portion of btrfs_get_blocks_direct
  btrfs: return ENOMEM if path allocation fails in btrfs_cross_ref_exist
  btrfs: raid56: Remove VLA usage
  btrfs: return error value if create_io_em failed in cow_file_range
  btrfs: drop useless member qgroup_reserved of btrfs_pending_snapshot
  btrfs: drop unused parameter qgroup_reserved
  btrfs: balance dirty metadata pages in btrfs_finish_ordered_io
  btrfs: lift some btrfs_cross_ref_exist checks in nocow path
  btrfs: Remove fs_info argument from btrfs_uuid_tree_rem
  btrfs: Remove fs_info argument from btrfs_uuid_tree_add
  Btrfs: remove unused check of skip_locking
  Btrfs: remove always true check in unlock_up
  Btrfs: grab write lock directly if write_lock_level is the max level
  Btrfs: move get root out of btrfs_search_slot to a helper
  Btrfs: use more straightforward extent_buffer_uptodate check
  ...

47 files changed, 3248 insertions, 2746 deletions

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 234bae55b85d..7e075343daa5 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -19,17 +19,17 @@
  * ordered operations list so that we make sure to flush out any
  * new data the application may have written before commit.
  */
-#define BTRFS_INODE_ORDERED_DATA_CLOSE		0
-#define BTRFS_INODE_ORPHAN_META_RESERVED	1
-#define BTRFS_INODE_DUMMY			2
-#define BTRFS_INODE_IN_DEFRAG			3
-#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
+enum {
+	BTRFS_INODE_ORDERED_DATA_CLOSE = 0,
+	BTRFS_INODE_DUMMY,
+	BTRFS_INODE_IN_DEFRAG,
+	BTRFS_INODE_HAS_ASYNC_EXTENT,
+	BTRFS_INODE_NEEDS_FULL_SYNC,
+	BTRFS_INODE_COPY_EVERYTHING,
+	BTRFS_INODE_IN_DELALLOC_LIST,
+	BTRFS_INODE_READDIO_NEED_LOCK,
+	BTRFS_INODE_HAS_PROPS,
+};
 
 /* in memory btrfs inode */
 struct btrfs_inode {
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 1061575a7d25..d3e447b45bf7 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -990,12 +990,7 @@ static void __free_workspace(int type, struct list_head *workspace,
 		btrfs_compress_op[idx]->free_workspace(workspace);
 	atomic_dec(total_ws);
 wake:
-	/*
-	 * Make sure counter is updated before we wake up waiters.
-	 */
-	smp_mb();
-	if (waitqueue_active(ws_wait))
-		wake_up(ws_wait);
+	cond_wake_up(ws_wait);
 }
 
 static void free_workspace(int type, struct list_head *ws)
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index cc605f7b23fb..ddda9b80bf20 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -6,6 +6,8 @@
 #ifndef BTRFS_COMPRESSION_H
 #define BTRFS_COMPRESSION_H
 
+#include <linux/sizes.h>
+
 /*
  * We want to make sure that amount of RAM required to uncompress an extent is
  * reasonable, so we limit the total size in ram of a compressed extent to
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 8c68961925b1..4bc326df472e 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2330,7 +2330,7 @@ static noinline void unlock_up(struct btrfs_path *path, int level,
 			no_skips = 1;
 
 		t = path->nodes[i];
-		if (i >= lowest_unlock && i > skip_level && path->locks[i]) {
+		if (i >= lowest_unlock && i > skip_level) {
 			btrfs_tree_unlock_rw(t, path->locks[i]);
 			path->locks[i] = 0;
 			if (write_lock_level &&
@@ -2432,7 +2432,6 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 	btrfs_unlock_up_safe(p, level + 1);
 	btrfs_set_path_blocking(p);
 
-	free_extent_buffer(tmp);
 	if (p->reada != READA_NONE)
 		reada_for_search(fs_info, p, level, slot, key->objectid);
 
@@ -2446,7 +2445,7 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 		 * and give up so that our caller doesn't loop forever
 		 * on our EAGAINs.
 		 */
-		if (!btrfs_buffer_uptodate(tmp, 0, 0))
+		if (!extent_buffer_uptodate(tmp))
 			ret = -EIO;
 		free_extent_buffer(tmp);
 	} else {
@@ -2599,6 +2598,78 @@ int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
 	return 0;
 }
 
+static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
+							struct btrfs_path *p,
+							int write_lock_level)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct extent_buffer *b;
+	int root_lock;
+	int level = 0;
+
+	/* We try very hard to do read locks on the root */
+	root_lock = BTRFS_READ_LOCK;
+
+	if (p->search_commit_root) {
+		/* The commit roots are read only so we always do read locks */
+		if (p->need_commit_sem)
+			down_read(&fs_info->commit_root_sem);
+		b = root->commit_root;
+		extent_buffer_get(b);
+		level = btrfs_header_level(b);
+		if (p->need_commit_sem)
+			up_read(&fs_info->commit_root_sem);
+		/*
+		 * Ensure that all callers have set skip_locking when
+		 * p->search_commit_root = 1.
+		 */
+		ASSERT(p->skip_locking == 1);
+
+		goto out;
+	}
+
+	if (p->skip_locking) {
+		b = btrfs_root_node(root);
+		level = btrfs_header_level(b);
+		goto out;
+	}
+
+	/*
+	 * If the level is set to maximum, we can skip trying to get the read
+	 * lock.
+	 */
+	if (write_lock_level < BTRFS_MAX_LEVEL) {
+		/*
+		 * We don't know the level of the root node until we actually
+		 * have it read locked
+		 */
+		b = btrfs_read_lock_root_node(root);
+		level = btrfs_header_level(b);
+		if (level > write_lock_level)
+			goto out;
+
+		/* Whoops, must trade for write lock */
+		btrfs_tree_read_unlock(b);
+		free_extent_buffer(b);
+	}
+
+	b = btrfs_lock_root_node(root);
+	root_lock = BTRFS_WRITE_LOCK;
+
+	/* The level might have changed, check again */
+	level = btrfs_header_level(b);
+
+out:
+	p->nodes[level] = b;
+	if (!p->skip_locking)
+		p->locks[level] = root_lock;
+	/*
+	 * Callers are responsible for dropping b's references.
+	 */
+	return b;
+}
+
+
 /*
  * btrfs_search_slot - look for a key in a tree and perform necessary
  * modifications to preserve tree invariants.
@@ -2635,7 +2706,6 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	int err;
 	int level;
 	int lowest_unlock = 1;
-	int root_lock;
 	/* everything at write_lock_level or lower must be write locked */
 	int write_lock_level = 0;
 	u8 lowest_level = 0;
@@ -2673,50 +2743,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 again:
 	prev_cmp = -1;
-	/*
-	 * we try very hard to do read locks on the root
-	 */
-	root_lock = BTRFS_READ_LOCK;
-	level = 0;
-	if (p->search_commit_root) {
-		/*
-		 * the commit roots are read only
-		 * so we always do read locks
-		 */
-		if (p->need_commit_sem)
-			down_read(&fs_info->commit_root_sem);
-		b = root->commit_root;
-		extent_buffer_get(b);
-		level = btrfs_header_level(b);
-		if (p->need_commit_sem)
-			up_read(&fs_info->commit_root_sem);
-		if (!p->skip_locking)
-			btrfs_tree_read_lock(b);
-	} else {
-		if (p->skip_locking) {
-			b = btrfs_root_node(root);
-			level = btrfs_header_level(b);
-		} else {
-			/* we don't know the level of the root node
-			 * until we actually have it read locked
-			 */
-			b = btrfs_read_lock_root_node(root);
-			level = btrfs_header_level(b);
-			if (level <= write_lock_level) {
-				/* whoops, must trade for write lock */
-				btrfs_tree_read_unlock(b);
-				free_extent_buffer(b);
-				b = btrfs_lock_root_node(root);
-				root_lock = BTRFS_WRITE_LOCK;
-
-				/* the level might have changed, check again */
-				level = btrfs_header_level(b);
-			}
-		}
-	}
-	p->nodes[level] = b;
-	if (!p->skip_locking)
-		p->locks[level] = root_lock;
+	b = btrfs_search_slot_get_root(root, p, write_lock_level);
 
 	while (b) {
 		level = btrfs_header_level(b);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0d422c9908b8..f4bf7874c24a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -739,6 +739,12 @@ struct btrfs_delayed_root;
  */
 #define BTRFS_FS_NEED_ASYNC_COMMIT		17
 
+/*
+ * Indicate that balance has been set up from the ioctl and is in the main
+ * phase. The fs_info::balance_ctl is initialized.
+ */
+#define BTRFS_FS_BALANCE_RUNNING		18
+
 struct btrfs_fs_info {
 	u8 fsid[BTRFS_FSID_SIZE];
 	u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
@@ -838,7 +844,6 @@ struct btrfs_fs_info {
 	struct mutex transaction_kthread_mutex;
 	struct mutex cleaner_mutex;
 	struct mutex chunk_mutex;
-	struct mutex volume_mutex;
 
 	/*
 	 * this is taken to make sure we don't set block groups ro after
@@ -1004,7 +1009,6 @@ struct btrfs_fs_info {
 	/* restriper state */
 	spinlock_t balance_lock;
 	struct mutex balance_mutex;
-	atomic_t balance_running;
 	atomic_t balance_pause_req;
 	atomic_t balance_cancel_req;
 	struct btrfs_balance_control *balance_ctl;
@@ -1219,9 +1223,6 @@ struct btrfs_root {
 	spinlock_t log_extents_lock[2];
 	struct list_head logged_list[2];
 
-	spinlock_t orphan_lock;
-	atomic_t orphan_inodes;
-	struct btrfs_block_rsv *orphan_block_rsv;
 	int orphan_cleanup_state;
 
 	spinlock_t inode_lock;
@@ -2764,13 +2765,9 @@ void btrfs_delalloc_release_space(struct inode *inode,
 void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 					    u64 len);
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
-int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
-				  struct btrfs_inode *inode);
-void btrfs_orphan_release_metadata(struct btrfs_inode *inode);
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
-				     int nitems,
-				     u64 *qgroup_reserved, bool use_global_rsv);
+				     int nitems, 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,
@@ -2828,7 +2825,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
 void check_system_chunk(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info, const u64 type);
 u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
-		       struct btrfs_fs_info *info, u64 start, u64 end);
+		       u64 start, u64 end);
 
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
@@ -3042,11 +3039,9 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root);
 
 /* uuid-tree.c */
-int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 			u64 subid);
-int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 			u64 subid);
 int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info,
 			    int (*check_func)(struct btrfs_fs_info *, u8 *, u8,
@@ -3163,18 +3158,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     struct extent_map *em);
 
 /* inode.c */
-struct btrfs_delalloc_work {
-	struct inode *inode;
-	int delay_iput;
-	struct completion completion;
-	struct list_head list;
-	struct btrfs_work work;
-};
-
-struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
-						    int delay_iput);
-void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work);
-
 struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start,
 		u64 len, int create);
@@ -3193,10 +3176,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 int btrfs_add_link(struct btrfs_trans_handle *trans,
 		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index);
-int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root,
-			struct inode *dir, u64 objectid,
-			const char *name, int name_len);
+int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry);
 int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 			int front);
 int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
@@ -3204,9 +3184,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       struct inode *inode, u64 new_size,
 			       u32 min_type);
 
-int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
-			       int nr);
+int btrfs_start_delalloc_inodes(struct btrfs_root *root);
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr);
 int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 			      unsigned int extra_bits,
 			      struct extent_state **cached_state, int dedupe);
@@ -3240,10 +3219,7 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
 int btrfs_orphan_add(struct btrfs_trans_handle *trans,
 		struct btrfs_inode *inode);
 int btrfs_orphan_cleanup(struct btrfs_root *root);
-void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root);
 int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
-void btrfs_invalidate_inodes(struct btrfs_root *root);
 void btrfs_add_delayed_iput(struct inode *inode);
 void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
 int btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -3262,14 +3238,14 @@ void btrfs_test_inode_set_ops(struct inode *inode);
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int btrfs_ioctl_get_supported_features(void __user *arg);
-void btrfs_update_iflags(struct inode *inode);
+void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
 int btrfs_is_empty_uuid(u8 *uuid);
 int btrfs_defrag_file(struct inode *inode, struct file *file,
 		      struct btrfs_ioctl_defrag_range_args *range,
 		      u64 newer_than, unsigned long max_pages);
 void btrfs_get_block_group_info(struct list_head *groups_list,
 				struct btrfs_ioctl_space_info *space);
-void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
 			       struct btrfs_ioctl_balance_args *bargs);
 ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 			   struct file *dst_file, u64 dst_loff);
@@ -3767,4 +3743,26 @@ static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
+static inline void cond_wake_up(struct wait_queue_head *wq)
+{
+	/*
+	 * This implies a full smp_mb barrier, see comments for
+	 * waitqueue_active why.
+	 */
+	if (wq_has_sleeper(wq))
+		wake_up(wq);
+}
+
+static inline void cond_wake_up_nomb(struct wait_queue_head *wq)
+{
+	/*
+	 * Special case for conditional wakeup where the barrier required for
+	 * waitqueue_active is implied by some of the preceding code. Eg. one
+	 * of such atomic operations (atomic_dec_and_return, ...), or a
+	 * unlock/lock sequence, etc.
+	 */
+	if (waitqueue_active(wq))
+		wake_up(wq);
+}
+
 #endif
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index a8d492dbd3e7..fe6caa7e698b 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -460,13 +460,10 @@ static void finish_one_item(struct btrfs_delayed_root *delayed_root)
 {
 	int seq = atomic_inc_return(&delayed_root->items_seq);
 
-	/*
-	 * atomic_dec_return implies a barrier for waitqueue_active
-	 */
+	/* atomic_dec_return implies a barrier */
 	if ((atomic_dec_return(&delayed_root->items) <
-	    BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0) &&
-	    waitqueue_active(&delayed_root->wait))
-		wake_up(&delayed_root->wait);
+	    BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0))
+		cond_wake_up_nomb(&delayed_root->wait);
 }
 
 static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index e1b0651686f7..03dec673d12a 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -286,10 +286,10 @@ static bool merge_ref(struct btrfs_trans_handle *trans,
 }
 
 void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info,
 			      struct btrfs_delayed_ref_root *delayed_refs,
 			      struct btrfs_delayed_ref_head *head)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_ref_node *ref;
 	struct rb_node *node;
 	u64 seq = 0;
@@ -323,9 +323,7 @@ again:
 	}
 }
 
-int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
-			    struct btrfs_delayed_ref_root *delayed_refs,
-			    u64 seq)
+int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq)
 {
 	struct seq_list *elem;
 	int ret = 0;
@@ -336,10 +334,9 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
 					struct seq_list, list);
 		if (seq >= elem->seq) {
 			btrfs_debug(fs_info,
-				"holding back delayed_ref %#x.%x, lowest is %#x.%x (%p)",
+				"holding back delayed_ref %#x.%x, lowest is %#x.%x",
 				(u32)(seq >> 32), (u32)seq,
-				(u32)(elem->seq >> 32), (u32)elem->seq,
-				delayed_refs);
+				(u32)(elem->seq >> 32), (u32)elem->seq);
 			ret = 1;
 		}
 	}
@@ -529,33 +526,20 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
 	spin_unlock(&existing->lock);
 }
 
-/*
- * helper function to actually insert a head node into the rbtree.
- * this does all the dirty work in terms of maintaining the correct
- * overall modification count.
- */
-static noinline struct btrfs_delayed_ref_head *
-add_delayed_ref_head(struct btrfs_fs_info *fs_info,
-		     struct btrfs_trans_handle *trans,
-		     struct btrfs_delayed_ref_head *head_ref,
-		     struct btrfs_qgroup_extent_record *qrecord,
-		     u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved,
-		     int action, int is_data, int is_system,
-		     int *qrecord_inserted_ret,
-		     int *old_ref_mod, int *new_ref_mod)
-
+static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
+				  struct btrfs_qgroup_extent_record *qrecord,
+				  u64 bytenr, u64 num_bytes, u64 ref_root,
+				  u64 reserved, int action, bool is_data,
+				  bool is_system)
 {
-	struct btrfs_delayed_ref_head *existing;
-	struct btrfs_delayed_ref_root *delayed_refs;
 	int count_mod = 1;
 	int must_insert_reserved = 0;
-	int qrecord_inserted = 0;
 
 	/* If reserved is provided, it must be a data extent. */
 	BUG_ON(!is_data && reserved);
 
 	/*
-	 * the head node stores the sum of all the mods, so dropping a ref
+	 * The head node stores the sum of all the mods, so dropping a ref
 	 * should drop the sum in the head node by one.
 	 */
 	if (action == BTRFS_UPDATE_DELAYED_HEAD)
@@ -564,12 +548,11 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		count_mod = -1;
 
 	/*
-	 * BTRFS_ADD_DELAYED_EXTENT means that we need to update
-	 * the reserved accounting when the extent is finally added, or
-	 * if a later modification deletes the delayed ref without ever
-	 * inserting the extent into the extent allocation tree.
-	 * ref->must_insert_reserved is the flag used to record
-	 * that accounting mods are required.
+	 * BTRFS_ADD_DELAYED_EXTENT means that we need to update the reserved
+	 * accounting when the extent is finally added, or if a later
+	 * modification deletes the delayed ref without ever inserting the
+	 * extent into the extent allocation tree.  ref->must_insert_reserved
+	 * is the flag used to record that accounting mods are required.
 	 *
 	 * Once we record must_insert_reserved, switch the action to
 	 * BTRFS_ADD_DELAYED_REF because other special casing is not required.
@@ -579,8 +562,6 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	else
 		must_insert_reserved = 0;
 
-	delayed_refs = &trans->transaction->delayed_refs;
-
 	refcount_set(&head_ref->refs, 1);
 	head_ref->bytenr = bytenr;
 	head_ref->num_bytes = num_bytes;
@@ -598,7 +579,6 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	spin_lock_init(&head_ref->lock);
 	mutex_init(&head_ref->mutex);
 
-	/* Record qgroup extent info if provided */
 	if (qrecord) {
 		if (ref_root && reserved) {
 			head_ref->qgroup_ref_root = ref_root;
@@ -608,20 +588,44 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		qrecord->bytenr = bytenr;
 		qrecord->num_bytes = num_bytes;
 		qrecord->old_roots = NULL;
+	}
+}
+
+/*
+ * helper function to actually insert a head node into the rbtree.
+ * this does all the dirty work in terms of maintaining the correct
+ * overall modification count.
+ */
+static noinline struct btrfs_delayed_ref_head *
+add_delayed_ref_head(struct btrfs_trans_handle *trans,
+		     struct btrfs_delayed_ref_head *head_ref,
+		     struct btrfs_qgroup_extent_record *qrecord,
+		     int action, int *qrecord_inserted_ret,
+		     int *old_ref_mod, int *new_ref_mod)
+{
+	struct btrfs_delayed_ref_head *existing;
+	struct btrfs_delayed_ref_root *delayed_refs;
+	int qrecord_inserted = 0;
 
-		if(btrfs_qgroup_trace_extent_nolock(fs_info,
+	delayed_refs = &trans->transaction->delayed_refs;
+
+	/* Record qgroup extent info if provided */
+	if (qrecord) {
+		if (btrfs_qgroup_trace_extent_nolock(trans->fs_info,
 					delayed_refs, qrecord))
 			kfree(qrecord);
 		else
 			qrecord_inserted = 1;
 	}
 
-	trace_add_delayed_ref_head(fs_info, head_ref, action);
+	trace_add_delayed_ref_head(trans->fs_info, head_ref, action);
 
 	existing = htree_insert(&delayed_refs->href_root,
 				&head_ref->href_node);
 	if (existing) {
-		WARN_ON(ref_root && reserved && existing->qgroup_ref_root
+		WARN_ON(qrecord && head_ref->qgroup_ref_root
+			&& head_ref->qgroup_reserved
+			&& existing->qgroup_ref_root
 			&& existing->qgroup_reserved);
 		update_existing_head_ref(delayed_refs, existing, head_ref,
 					 old_ref_mod);
@@ -634,8 +638,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	} else {
 		if (old_ref_mod)
 			*old_ref_mod = 0;
-		if (is_data && count_mod < 0)
-			delayed_refs->pending_csums += num_bytes;
+		if (head_ref->is_data && head_ref->ref_mod < 0)
+			delayed_refs->pending_csums += head_ref->num_bytes;
 		delayed_refs->num_heads++;
 		delayed_refs->num_heads_ready++;
 		atomic_inc(&delayed_refs->num_entries);
@@ -645,90 +649,48 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		*qrecord_inserted_ret = qrecord_inserted;
 	if (new_ref_mod)
 		*new_ref_mod = head_ref->total_ref_mod;
-	return head_ref;
-}
-
-/*
- * helper to insert a delayed tree ref into the rbtree.
- */
-static noinline void
-add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
-		     struct btrfs_trans_handle *trans,
-		     struct btrfs_delayed_ref_head *head_ref,
-		     struct btrfs_delayed_ref_node *ref, u64 bytenr,
-		     u64 num_bytes, u64 parent, u64 ref_root, int level,
-		     int action)
-{
-	struct btrfs_delayed_tree_ref *full_ref;
-	struct btrfs_delayed_ref_root *delayed_refs;
-	u64 seq = 0;
-	int ret;
-
-	if (action == BTRFS_ADD_DELAYED_EXTENT)
-		action = BTRFS_ADD_DELAYED_REF;
 
-	if (is_fstree(ref_root))