9 files changed, 321 insertions, 207 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 7eef79ece5b3..83a196521670 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1482,6 +1482,32 @@ out:
 }
 
 /*
+ * Link the block_group to a list via bg_list.
+ *
+ * @bg:       The block_group to link to the list.
+ * @list:     The list to link it to.
+ *
+ * Use this rather than list_add_tail() directly to ensure proper respect
+ * to locking and refcounting.
+ *
+ * Returns: true if the bg was linked with a refcount bump and false otherwise.
+ */
+static bool btrfs_link_bg_list(struct btrfs_block_group *bg, struct list_head *list)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+	bool added = false;
+
+	spin_lock(&fs_info->unused_bgs_lock);
+	if (list_empty(&bg->bg_list)) {
+		btrfs_get_block_group(bg);
+		list_add_tail(&bg->bg_list, list);
+		added = true;
+	}
+	spin_unlock(&fs_info->unused_bgs_lock);
+	return added;
+}
+
+/*
  * Process the unused_bgs list and remove any that don't have any allocated
  * space inside of them.
  */
@@ -1597,8 +1623,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			 * drop under the "next" label for the
 			 * fs_info->unused_bgs list.
 			 */
-			btrfs_get_block_group(block_group);
-			list_add_tail(&block_group->bg_list, &retry_list);
+			btrfs_link_bg_list(block_group, &retry_list);
 
 			trace_btrfs_skip_unused_block_group(block_group);
 			spin_unlock(&block_group->lock);
@@ -1621,8 +1646,10 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		ret = btrfs_zone_finish(block_group);
 		if (ret < 0) {
 			btrfs_dec_block_group_ro(block_group);
-			if (ret == -EAGAIN)
+			if (ret == -EAGAIN) {
+				btrfs_link_bg_list(block_group, &retry_list);
 				ret = 0;
+			}
 			goto next;
 		}
 
@@ -1971,20 +1998,8 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		spin_unlock(&space_info->lock);
 
 next:
-		if (ret && !READ_ONCE(space_info->periodic_reclaim)) {
-			/* Refcount held by the reclaim_bgs list after splice. */
-			spin_lock(&fs_info->unused_bgs_lock);
-			/*
-			 * This block group might be added to the unused list
-			 * during the above process. Move it back to the
-			 * reclaim list otherwise.
-			 */
-			if (list_empty(&bg->bg_list)) {
-				btrfs_get_block_group(bg);
-				list_add_tail(&bg->bg_list, &retry_list);
-			}
-			spin_unlock(&fs_info->unused_bgs_lock);
-		}
+		if (ret && !READ_ONCE(space_info->periodic_reclaim))
+			btrfs_link_bg_list(bg, &retry_list);
 		btrfs_put_block_group(bg);
 
 		mutex_unlock(&fs_info->reclaim_bgs_lock);
@@ -2024,13 +2039,8 @@ void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 
-	spin_lock(&fs_info->unused_bgs_lock);
-	if (list_empty(&bg->bg_list)) {
-		btrfs_get_block_group(bg);
+	if (btrfs_link_bg_list(bg, &fs_info->reclaim_bgs))
 		trace_btrfs_add_reclaim_block_group(bg);
-		list_add_tail(&bg->bg_list, &fs_info->reclaim_bgs);
-	}
-	spin_unlock(&fs_info->unused_bgs_lock);
 }
 
 static int read_bg_from_eb(struct btrfs_fs_info *fs_info, const struct btrfs_key *key,
@@ -2807,6 +2817,7 @@ next:
 		spin_lock(&fs_info->unused_bgs_lock);
 		list_del_init(&block_group->bg_list);
 		clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags);
+		btrfs_put_block_group(block_group);
 		spin_unlock(&fs_info->unused_bgs_lock);
 
 		/*
@@ -2945,7 +2956,7 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran
 	}
 #endif
 
-	list_add_tail(&cache->bg_list, &trans->new_bgs);
+	btrfs_link_bg_list(cache, &trans->new_bgs);
 	btrfs_inc_delayed_refs_rsv_bg_inserts(fs_info);
 
 	set_avail_alloc_bits(fs_info, type);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 3ba15d9c3e88..81735d19feff 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -350,7 +350,14 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 
 	write_extent_buffer_fsid(cow, fs_info->fs_devices->metadata_uuid);
 
-	WARN_ON(btrfs_header_generation(buf) > trans->transid);
+	if (unlikely(btrfs_header_generation(buf) > trans->transid)) {
+		btrfs_tree_unlock(cow);
+		free_extent_buffer(cow);
+		ret = -EUCLEAN;
+		btrfs_abort_transaction(trans, ret);
+		return ret;
+	}
+
 	if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
 		ret = btrfs_inc_ref(trans, root, cow, 1);
 	else
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 308abbf8855b..51f286d5d00a 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1379,12 +1379,17 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
 	clear_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags);
 
 	ret = add_new_free_space_info(trans, block_group, path);
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
 		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, block_group, path,
+				       block_group->start, block_group->length);
+	if (ret)
+		btrfs_abort_transaction(trans, ret);
 
-	return __add_to_free_space_tree(trans, block_group, path,
-					block_group->start,
-					block_group->length);
+	return 0;
 }
 
 int add_block_group_free_space(struct btrfs_trans_handle *trans,
@@ -1404,16 +1409,14 @@ int add_block_group_free_space(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
+		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
 	ret = __add_block_group_free_space(trans, block_group, path);
-
 out:
 	btrfs_free_path(path);
 	mutex_unlock(&block_group->free_space_lock);
-	if (ret)
-		btrfs_abort_transaction(trans, ret);
 	return ret;
 }
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 6b181bf9f156..530a2bab6ada 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -226,8 +226,7 @@ static struct btrfs_qgroup *add_qgroup_rb(struct btrfs_fs_info *fs_info,
 	return qgroup;
 }
 
-static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
-			    struct btrfs_qgroup *qgroup)
+static void __del_qgroup_rb(struct btrfs_qgroup *qgroup)
 {
 	struct btrfs_qgroup_list *list;
 
@@ -258,7 +257,7 @@ static int del_qgroup_rb(struct btrfs_fs_info *fs_info, u64 qgroupid)
 		return -ENOENT;
 
 	rb_erase(&qgroup->node, &fs_info->qgroup_tree);
-	__del_qgroup_rb(fs_info, qgroup);
+	__del_qgroup_rb(qgroup);
 	return 0;
 }
 
@@ -631,22 +630,30 @@ bool btrfs_check_quota_leak(const struct btrfs_fs_info *fs_info)
 
 /*
  * This is called from close_ctree() or open_ctree() or btrfs_quota_disable(),
- * first two are in single-threaded paths.And for the third one, we have set
- * quota_root to be null with qgroup_lock held before, so it is safe to clean
- * up the in-memory structures without qgroup_lock held.
+ * first two are in single-threaded paths.
  */
 void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
 {
 	struct rb_node *n;
 	struct btrfs_qgroup *qgroup;
 
+	/*
+	 * btrfs_quota_disable() can be called concurrently with
+	 * btrfs_qgroup_rescan() -> qgroup_rescan_zero_tracking(), so take the
+	 * lock.
+	 */
+	spin_lock(&fs_info->qgroup_lock);
 	while ((n = rb_first(&fs_info->qgroup_tree))) {
 		qgroup = rb_entry(n, struct btrfs_qgroup, node);
 		rb_erase(n, &fs_info->qgroup_tree);
-		__del_qgroup_rb(fs_info, qgroup);
+		__del_qgroup_rb(qgroup);
+		spin_unlock(&fs_info->qgroup_lock);
 		btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
 		kfree(qgroup);
+		spin_lock(&fs_info->qgroup_lock);
 	}
+	spin_unlock(&fs_info->qgroup_lock);
+
 	/*
 	 * We call btrfs_free_qgroup_config() when unmounting
 	 * filesystem and disabling quota, so we set qgroup_ulist
@@ -4057,12 +4064,21 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
 	qgroup_rescan_zero_tracking(fs_info);
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	fs_info->qgroup_rescan_running = true;
-	btrfs_queue_work(fs_info->qgroup_rescan_workers,
-			 &fs_info->qgroup_rescan_work);
+	/*
+	 * The rescan worker is only for full accounting qgroups, check if it's
+	 * enabled as it is pointless to queue it otherwise. A concurrent quota
+	 * disable may also have just cleared BTRFS_FS_QUOTA_ENABLED.
+	 */
+	if (btrfs_qgroup_full_accounting(fs_info)) {
+		fs_info->qgroup_rescan_running = true;
+		btrfs_queue_work(fs_info->qgroup_rescan_workers,
+				 &fs_info->qgroup_rescan_work);
+	} else {
+		ret = -ENOTCONN;
+	}
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
-	return 0;
+	return ret;
 }
 
 int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index c843b4aefb8a..41b7cbd07025 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/bsearch.h>
+#include <linux/falloc.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/sort.h>
@@ -178,6 +179,7 @@ struct send_ctx {
 	u64 cur_inode_rdev;
 	u64 cur_inode_last_extent;
 	u64 cur_inode_next_write_offset;
+	struct fs_path cur_inode_path;
 	bool cur_inode_new;
 	bool cur_inode_new_gen;
 	bool cur_inode_deleted;
@@ -436,6 +438,14 @@ static void fs_path_reset(struct fs_path *p)
 	}
 }
 
+static void init_path(struct fs_path *p)
+{
+	p->reversed = 0;
+	p->buf = p->inline_buf;
+	p->buf_len = FS_PATH_INLINE_SIZE;
+	fs_path_reset(p);
+}
+
 static struct fs_path *fs_path_alloc(void)
 {
 	struct fs_path *p;
@@ -443,10 +453,7 @@ static struct fs_path *fs_path_alloc(void)
 	p = kmalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return NULL;
-	p->reversed = 0;
-	p->buf = p->inline_buf;
-	p->buf_len = FS_PATH_INLINE_SIZE;
-	fs_path_reset(p);
+	init_path(p);
 	return p;
 }
 
@@ -471,7 +478,7 @@ static void fs_path_free(struct fs_path *p)
 	kfree(p);
 }
 
-static int fs_path_len(struct fs_path *p)
+static inline int fs_path_len(const struct fs_path *p)
 {
 	return p->end - p->start;
 }
@@ -624,6 +631,14 @@ static void fs_path_unreverse(struct fs_path *p)
 	p->reversed = 0;
 }
 
+static inline bool is_current_inode_path(const struct send_ctx *sctx,
+					 const struct fs_path *path)
+{
+	const struct fs_path *cur = &sctx->cur_inode_path;
+
+	return (strncmp(path->start, cur->start, fs_path_len(cur)) == 0);
+}
+
 static struct btrfs_path *alloc_path_for_send(void)
 {
 	struct btrfs_path *path;
@@ -2450,6 +2465,14 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen,
 	u64 parent_inode = 0;
 	u64 parent_gen = 0;
 	int stop = 0;
+	const bool is_cur_inode = (ino == sctx->cur_ino && gen == sctx->cur_inode_gen);
+
+	if (is_cur_inode && fs_path_len(&sctx->cur_inode_path) > 0) {
+		if (dest != &sctx->cur_inode_path)
+			return fs_path_copy(dest, &sctx->cur_inode_path);
+
+		return 0;
+	}
 
 	name = fs_path_alloc();
 	if (!name) {
@@ -2501,8 +2524,12 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen,
 
 out:
 	fs_path_free(name);
-	if (!ret)
+	if (!ret) {
 		fs_path_unreverse(dest);
+		if (is_cur_inode && dest != &sctx->cur_inode_path)
+			ret = fs_path_copy(&sctx->cur_inode_path, dest);
+	}
+
 	return ret;
 }
 
@@ -2597,6 +2624,47 @@ out:
 	return ret;
 }
 
+static struct fs_path *get_cur_inode_path(struct send_ctx *sctx)
+{
+	if (fs_path_len(&sctx->cur_inode_path) == 0) {
+		int ret;
+
+		ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen,
+				   &sctx->cur_inode_path);
+		if (ret < 0)
+			return ERR_PTR(ret);
+	}
+
+	return &sctx->cur_inode_path;
+}
+
+static struct fs_path *get_path_for_command(struct send_ctx *sctx, u64 ino, u64 gen)
+{
+	struct fs_path *path;
+	int ret;
+
+	if (ino == sctx->cur_ino && gen == sctx->cur_inode_gen)
+		return get_cur_inode_path(sctx);
+
+	path = fs_path_alloc();
+	if (!path)
+		return ERR_PTR(-ENOMEM);
+
+	ret = get_cur_path(sctx, ino, gen, path);
+	if (ret < 0) {
+		fs_path_free(path);
+		return ERR_PTR(ret);
+	}
+
+	return path;
+}
+
+static void free_path_for_command(const struct send_ctx *sctx, struct fs_path *path)
+{
+	if (path != &sctx->cur_inode_path)
+		fs_path_free(path);
+}
+
 static int send_truncate(struct send_ctx *sctx, u64 ino, u64 gen, u64 size)
 {
 	struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
@@ -2605,17 +2673,14 @@ static int send_truncate(struct send_ctx *sctx, u64 ino, u64 gen, u64 size)
 
 	btrfs_debug(fs_info, "send_truncate %llu size=%llu", ino, size);
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
+	p = get_path_for_command(sctx, ino, gen);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
 	ret = begin_cmd(sctx, BTRFS_SEND_C_TRUNCATE);
 	if (ret < 0)
 		goto out;
 
-	ret = get_cur_path(sctx, ino, gen, p);
-	if (ret < 0)
-		goto out;
 	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_SIZE, size);
 
@@ -2623,7 +2688,7 @@ static int send_truncate(struct send_ctx *sctx, u64 ino, u64 gen, u64 size)
 
 tlv_put_failure:
 out:
-	fs_path_free(p);
+	free_path_for_command(sctx, p);
 	return ret;
 }
 
@@ -2635,17 +2700,14 @@ static int send_chmod(struct send_ctx *sctx, u64 ino, u64 gen, u64 mode)
 
 	btrfs_debug(fs_info, "send_chmod %llu mode=%llu", ino, mode);
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
+	p = get_path_for_command(sctx, ino, gen);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
 	ret = begin_cmd(sctx, BTRFS_SEND_C_CHMOD);
 	if (ret < 0)
 		goto out;
 
-	ret = get_cur_path(sctx, ino, gen, p);
-	if (ret < 0)
-		goto out;
 	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_MODE, mode & 07777);
 
@@ -2653,7 +2715,7 @@ static int send_chmod(struct send_ctx *sctx, u64 ino, u64 gen, u64 mode)
 
 tlv_put_failure:
 out:
-	fs_path_free(p);
+	free_path_for_command(sctx, p);
 	return ret;
 }
 
@@ -2668,17 +2730,14 @@ static int send_fileattr(struct send_ctx *sctx, u64 ino, u64 gen, u64 fileattr)
 
 	btrfs_debug(fs_info, "send_fileattr %llu fileattr=%llu", ino, fileattr);
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
+	p = get_path_for_command(sctx, ino, gen);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
 	ret = begin_cmd(sctx, BTRFS_SEND_C_FILEATTR);
 	if (ret < 0)
 		goto out;
 
-	ret = get_cur_path(sctx, ino, gen, p);
-	if (ret < 0)
-		goto out;
 	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_FILEATTR, fileattr);
 
@@ -2686,7 +2745,7 @@ static int send_fileattr(struct send_ctx *sctx, u64 ino, u64 gen, u64 fileattr)
 
 tlv_put_failure:
 out:
-	fs_path_free(p);
+	free_path_for_command(sctx, p);
 	return ret;
 }
 
@@ -2699,17 +2758,14 @@ static int send_chown(struct send_ctx *sctx, u64 ino, u64 gen, u64 uid, u64 gid)
 	btrfs_debug(fs_info, "send_chown %llu uid=%llu, gid=%llu",
 		    ino, uid, gid);
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
+	p = get_path_for_command(sctx, ino, gen);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
 	ret = begin_cmd(sctx, BTRFS_SEND_C_CHOWN);
 	if (ret < 0)
 		goto out;
 
-	ret = get_cur_path(sctx, ino, gen, p);
-	if (ret < 0)
-		goto out;
 	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_UID, uid);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_GID, gid);
@@ -2718,7 +2774,7 @@ static int send_chown(struct send_ctx *sctx, u64 ino, u64 gen, u64 uid, u64 gid)
 
 tlv_put_failure:
 out:
-	fs_path_free(p);
+	free_path_for_command(sctx, p);
 	return ret;
 }
 
@@ -2735,9 +2791,9 @@ static int send_utimes(struct send_ctx *sctx, u64 ino, u64 gen)
 
 	btrfs_debug(fs_info, "send_utimes %llu", ino);
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
+	p = get_path_for_command(sctx, ino, gen);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
 	path = alloc_path_for_send();
 	if (!path) {
@@ -2762,9 +2818,6 @@ static int send_utimes(struct send_ctx *sctx, u64 ino, u64 gen)
 	if (ret < 0)
 		goto out;
 
-	ret = get_cur_path(sctx, ino, gen, p);
-	if (ret < 0)
-		goto out;
 	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
 	TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_ATIME, eb, &ii->atime);
 	TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_MTIME, eb, &ii->mtime);
@@ -2776,7 +2829,7 @@ static int send_utimes(struct send_ctx *sctx, u64 ino, u64 gen)
 
 tlv_put_failure:
 out:
-	fs_path_free(p);
+	free_path_for_command(sctx, p);
 	btrfs_free_path(path);
 	return ret;
 }
@@ -3112,6 +3165,11 @@ static int orphanize_inode(struct send_ctx *sctx, u64 ino, u64 gen,
 		goto out;
 
 	ret = send_rename(sctx, path, orphan);
+	if (ret < 0)
+		goto out;
+
+	if (ino == sctx->cur_ino && gen == sctx->cur_inode_gen)
+		ret = fs_path_copy(&sctx->cur_inode_path, orphan);
 
 out:
 	fs_path_free(orphan);
@@ -4165,6 +4223,23 @@ out:
 	return ret;
 }
 
+static int rename_current_inode(struct send_ctx *sctx,
+				struct fs_path *current_path,
+				struct fs_path *new_path)
+{
+	int ret;
+
+	ret = send_rename(sctx, current_path, new_path);
+	if (ret < 0)
+		return ret;
+
+	ret = fs_path_copy(&sctx->cur_inode_path, new_path);
+	if (ret < 0)
+		return ret;
+
+	return fs_path_copy(current_path, new_path);
+}
+
 /*
  * This does all the move/link/unlink/rmdir magic.
  */
@@ -4179,9 +4254,9 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	u64 ow_inode = 0;
 	u64 ow_gen;
 	u64 ow_mode;
-	int did_overwrite = 0;
-	int is_orphan = 0;
 	u64 last_dir_ino_rm = 0;
+	bool did_overwrite = false;
+	bool is_orphan = false;
 	bool can_rename = true;
 	bool orphanized_dir = false;
 	bool orphanized_ancestor = false;
@@ -4223,14 +4298,14 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 		if (ret < 0)
 			goto out;
 		if (ret)
-			did_overwrite = 1;
+			did_overwrite = true;
 	}
 	if (sctx->cur_inode_new || did_overwrite) {
 		ret = gen_unique_name(sctx, sctx->cur_ino,
 				sctx->cur_inode_gen, valid_path);
 		if (ret < 0)
 			goto out;
-		is_orphan = 1;
+		is_orphan = true;
 	} else {
 		ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen,
 				valid_path);
@@ -4355,6 +4430,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				if (ret > 0) {
 					orphanized_ancestor = true;
 					fs_path_reset(valid_path);
+					fs_path_reset(&sctx->cur_inode_path);
 					ret = get_cur_path(sctx, sctx->cur_ino,
 							   sctx->cur_inode_gen,
 							   valid_path);
@@ -4450,13 +4526,10 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 		 * it depending on the inode mode.
 		 */
 		if (is_orphan && can_rename) {
-			ret = send_rename(sctx, valid_path, cur->full_path);
-			if (ret < 0)
-				goto out;
-			is_orphan = 0;
-			ret = fs_path_copy(valid_path, cur->full_path);
+			ret = rename_current_inode(sctx, valid_path, cur->full_path);
 			if (ret < 0)
 				goto out;
+			is_orphan = false;
 		} else if (can_rename) {
 			if (S_ISDIR(sctx->cur_inode_mode)) {
 				/*
@@ -4464,10 +4537,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				 * dirs, we always have one new and one deleted
 				 * ref. The deleted ref is ignored later.
 				 */
-				ret = send_rename(sctx, valid_path,
-						  cur->full_path);
-				if (!ret)
-					ret = fs_path_copy(valid_path,
+				ret = rename_current_inode(sctx, valid_path,
 							   cur->full_path);
 				if (ret < 0)
 					goto out;
@@ -4514,7 +4584,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 					sctx->cur_inode_gen, valid_path);
 			if (ret < 0)
 				goto out;
-			is_orphan = 1;
+			is_orphan = true;
 		}
 
 		list_for_each_entry(cur, &sctx->deleted_refs, list) {
@@ -4560,6 +4630,8 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				ret = send_unlink(sctx, cur->full_path);
 				if (ret < 0)
 					goto out;
+				if (is_current_inode_path(sctx, cur->full_path))
+					fs_path_reset(&sctx->cur_inode_path);
 			}
 			ret = dup_ref(cur, &check_dirs);
 			if (ret < 0)
@@ -4878,11 +4950,15 @@ out:
 }
 
 static int send_set_xattr(struct send_ctx *sctx,
-			  struct fs_path *path,
 			  const char *name, int name_len,
 			  const char *data, int data_len)
 {
-	int ret = 0;
+	struct fs_path *path;
+	int ret;
+
+	path = get_cur_inode_path(sctx);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
 
 	ret = begin_cmd(sctx, BTRFS_SEND_C_SET_XATTR);
 	if (ret < 0)
@@ -4923,19 +4999,13 @@ static int __process_new_xattr(int num, struct btrfs_key *di_key,
 			       const char *name, int name_len, const char *data,
 			       int data_len, void *ctx)
 {
-	int ret;
 	struct send_ctx *sctx = ctx;
-	struct fs_path *p;
 	struct posix_acl_xattr_header dummy_acl;
 
 	/* Capabilities are emitted by finish_inode_if_needed */
 	if (!strncmp(name, XATTR_NAME_CAPS, name_len))
 		return 0;
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
-
 	/*
 	 * This hack is needed because empty acls are stored as zero byte
 	 * data in xattrs. Problem with that is, that receiving these zero byte
@@ -4952,38 +5022,21 @@ static int __process_new_xattr(int num, struct btrfs_key *di_key,
 		}
 	}
 
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
-	if (ret < 0)
-		goto out;
-
-	ret = send_set_xattr(sctx, p, name, name_len, data, data_len);
-
-out:
-	fs_path_free(p);
-	return ret;
+	return send_set_xattr(sctx, name, name_len, data, data_len);
 }
 
 static int __process_deleted_xattr(int num, struct btrfs_key *di_key,
 				   const char *name, int name_len,
 				   const char *data, int data_len, void *ctx)
 {
-	int ret;
 	struct send_ctx *sctx = ctx;
 	struct fs_path *p;
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
-
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
-	if (ret < 0)
-		goto out;
-
-	ret = send_remove_xattr(sctx, p, name, name_len);
+	p = get_cur_inode_path(sctx);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
-out:
-	fs_path_free(p);
-	return ret;
+	return send_remove_xattr(sctx, p, name, name_len);
 }
 
 static int process_new_xattr(struct send_ctx *sctx)
@@ -5216,21 +5269,13 @@ static int process_verity(struct send_ctx *sctx)
 	if (ret < 0)
 		goto iput;
 
-	p = fs_path_alloc();
-	if (!p) {
-		ret = -ENOMEM;
+	p = get_cur_inode_path(sctx);
+	if (IS_ERR(p)) {
+		ret = PTR_ERR(p);
 		goto iput;
 	}
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
-	if (ret < 0)
-		goto free_path;
 
 	ret = send_verity(sctx, p, sctx->verity_descriptor);
-	if (ret < 0)
-		goto free_path;
-
-free_path:
-	fs_path_free(p);
 iput:
 	iput(inode);
 	return ret;
@@ -5352,31 +5397,25 @@ static int send_write(struct send_ctx *sctx, u64 offset, u32 len)
 	int ret = 0;
 	struct fs_path *p;
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
-
 	btrfs_debug(fs_info, "send_write offset=%llu, len=%d", offset, len);
 
-	ret = begin_cmd(sctx, BTRFS_SEND_C_WRITE);
-	if (ret < 0)
-		goto out;
+	p = get_cur_inode_path(sctx);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
+	ret = begin_cmd(sctx, BTRFS_SEND_C_WRITE);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
 	ret = put_file_data(sctx, offset, len);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	ret = send_cmd(sctx);
 
 tlv_put_failure:
-out:
-	fs_path_free(p);
 	return ret;
 }
 
@@ -5389,6 +5428,7 @@ static int send_clone(struct send_ctx *sctx,
 {
 	int ret = 0;
 	struct fs_path *p;
+	struct fs_path *cur_inode_path;
 	u64 gen;
 
 	btrfs_debug(sctx->send_root->fs_info,
@@ -5396,6 +5436,10 @@ static int send_clone(struct send_ctx *sctx,
 		    offset, len, btrfs_root_id(clone_root->root),
 		    clone_root->ino, clone_root->offset);
 
+	cur_inode_path = get_cur_inode_path(sctx);
+	if (IS_ERR(cur_inode_path))
+		return PTR_ERR(cur_inode_path);
+
 	p = fs_path_alloc();
 	if (!p)
 		return -ENOMEM;
@@ -5404,13 +5448,9 @@ static int send_clone(struct send_ctx *sctx,
 	if (ret < 0)
 		goto out;
 
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
-	if (ret < 0)
-		goto out;
-
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_LEN, len);
-	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
+	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, cur_inode_path);
 
 	if (clone_root->root == sctx->send_root) {
 		ret = get_inode_gen(sctx->send_root, clone_root->ino, &gen);
@@ -5461,27 +5501,45 @@ static int send_update_extent(struct send_ctx *sctx,
 	int ret = 0;
 	struct fs_path *p;
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
+	p = get_cur_inode_path(sctx);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
 	ret = begin_cmd(sctx, BTRFS_SEND_C_UPDATE_EXTENT);
 	if (ret < 0)
-		goto out;
+		return ret;
+
+	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
+	TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
+	TLV_PUT_U64(sctx, BTRFS_SEND_A_SIZE, len);
+
+	ret = send_cmd(sctx);
 
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
+tlv_put_failure:
+	return ret;
+}
+
+static int send_fallocate(struct send_ctx *sctx, u32 mode, u64 offset, u64 len)
+{
+	struct fs_path *path;
+	int ret;
+
+	path = get_cur_inode_path(sctx);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	ret = begin_cmd(sctx, BTRFS_SEND_C_FALLOCATE);
 	if (ret < 0)
-		goto out;
+		return ret;
 
-	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
+	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, path);
+	TLV_PUT_U32(sctx, BTRFS_SEND_A_FALLOCATE_MODE, mode);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_SIZE, len);
 
 	ret = send_cmd(sctx);
 
 tlv_put_failure:
-out:
-	fs_path_free(p);
 	return ret;
 }
 
@@ -5493,6 +5551,14 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 	int ret = 0;
 
 	/*
+	 * Starting with send stream v2 we have fallocate and can use it to
+	 * punch holes instead of sending writes full of zeroes.
+	 */
+	if (proto_cmd_ok(sctx, BTRFS_SEND_C_FALLOCATE))
+		return send_fallocate(sctx, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+				      offset, end - offset);
+
+	/*
 	 * A hole that starts at EOF or beyond it. Since we do not yet support
 	 * fallocate (for extent preallocation and hole punching), sending a
 	 * write of zeroes starting at EOF or beyond would later require issuing
@@ -5510,12 +5576,10 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 	if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
 		return send_update_extent(sctx, offset, end - offset);
 
-	p = fs_path_alloc();
-	if (!p)
-		return -ENOMEM;
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
-	if (ret < 0)
-		goto tlv_put_failure;
+	p = get_cur_inode_path(sctx);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+
 	while (offset < end) {
 		u64 len = min(end - offset, read_size);
 
@@ -5536,7 +5600,6 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 	}
 	sctx->cur_inode_next_write_offset = offset;
 tlv_put_failure:
-	fs_path_free(p);
 	return ret;
 }
 
@@ -5559,9 +5622,9 @@ static int send_encoded_inline_extent(struct send_ctx *sctx,
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
-	fspath = fs_path_alloc();
-	if (!fspath) {
-		ret = -ENOMEM;
+	fspath = get_cur_inode_path(sctx);
+	if (IS_ERR(fspath)) {
+		ret = PTR_ERR(fspath);
 		goto out;
 	}
 
@@ -5569,10 +5632,6 @@ static int send_encoded_inline_extent(struct send_ctx *sctx,
 	if (ret < 0)
 		goto out;
 
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, fspath);
-	if (ret < 0)
-		goto out;
-
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item);
 	ram_bytes = btrfs_file_extent_ram_bytes(leaf, ei);
@@ -5601,7 +5660,6 @@ static int send_encoded_inline_extent(struct send_ctx *sctx,
 
 tlv_put_failure:
 out:
-	fs_path_free(fspath);
 	iput(inode);
 	return ret;
 }
@@ -5626,9 +5684,9 @@ static int send_encoded_extent(struct send_ctx *sctx, struct btrfs_path *path,
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
-	fspath = fs_path_alloc();
-	if (!fspath) {
-		ret = -ENOMEM;
+	fspath = get_cur_inode_path(sctx);
+	if (IS_ERR(fspath)) {
+		ret = PTR_ERR(fspath);
 		goto out;
 	}
 
@@ -5636,10 +5694,6 @@ static int send_encoded_extent(struct send_ctx *sctx, struct btrfs_path *path,
 	if (ret < 0)
 		goto out;
 
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, fspath);
-	if (ret < 0)
-		goto out;
-
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item);
 	disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei);
@@ -5706,7 +5760,6 @@ static int send_encoded_extent(struct send_ctx *sctx, struct btrfs_path *path,
 
 tlv_put_failure:
 out:
-	fs_path_free(fspath);
 	iput(inode);
 	return ret;
 }
@@ -5836,7 +5889,6 @@ static int send_extent_data(struct send_ctx *sctx, struct btrfs_path *path,
  */
 static int send_capabilities(struct send_ctx *sctx)
 {
-	struct fs_path *fspath = NULL;
 	struct btrfs_path *path;
 	struct btrfs_dir_item *di;
 	struct extent_buffer *leaf;
@@ -5862,25 +5914,19 @@ static int send_capabilities(struct send_ctx *sctx)
 	leaf = path->nodes[0];
 	buf_len = btrfs_dir_data_len(leaf, di);
 
-	fspath = fs_path_alloc();
 	buf = kmalloc(buf_len, GFP_KERNEL);
-	if (!fspath || !buf) {
+	if (!buf) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, fspath);
-	if (ret < 0)
-		goto out;
-
 	data_ptr = (unsigned long)(di + 1) + btrfs_dir_name_len(leaf, di);
 	read_extent_buffer(leaf, buf, data_ptr, buf_len);
 
-	ret = send_set_xattr(sctx, fspath, XATTR_NAME_CAPS,
+	ret = send_set_xattr(sctx, XATTR_NAME_CAPS,
 			strlen(XATTR_NAME_CAPS), buf, buf_len);
 out:
 	kfree(buf);
-	fs_path_free(fspath);
 	btrfs_free_path(path);
 	return ret;
 }
@@ -6906,6 +6952,7 @@ static int changed_inode(struct send_ctx *sctx,
 	sctx->cur_inode_last_extent = (u64)-1;
 	sctx->cur_inode_next_write_offset = 0;
 	sctx->ignore_cur_inode = false;
+	fs_path_reset(&sctx->cur_inode_path);
 
 	/*
 	 * Set send_progress to current inode. This will tell all get_cur_xxx
@@ -8178,6 +8225,7 @@ long btrfs_ioctl_send(struct btrfs_inode *inode, const struct btrfs_ioctl_send_a
 		goto out;
 	}
 
+	init_path(&sctx->cur_inode_path);
 	INIT_LIST_HEAD(&sctx->new_refs);
 	INIT_LIST_HEAD(&sctx->deleted_refs);
 
@@ -8463,6 +8511,9 @@ out:
 		btrfs_lru_cache_clear(&sctx->dir_created_cache);
 		btrfs_lru_cache_clear(&sctx->dir_utimes_cache);
 
+		if (sctx->cur_inode_path.buf != sctx->cur_inode_path.inline_buf)
+			kfree(sctx->cur_inode_path.buf);
+
 		kfree(sctx);
 	}
 
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 88a01d51ab11..71a56aaac7ad 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -452,8 +452,25 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
+
+	/*
+	 * Don't clear the TOWRITE tag when starting writeback on a still-dirty
+	 * folio. Doing so can cause WB_SYNC_ALL writepages() to overlook it,
+	 * assume writeback is complete, and exit too early — violating sync
+	 * ordering guarantees.
+	 */
 	if (!folio_test_writeback(folio))
-		folio_start_writeback(folio);
+		__folio_start_writeback(folio, true);
+	if (!folio_test_dirty(folio)) {
+		struct address_space *mapping = folio_mapping(folio);
+		XA_STATE(xas, &mapping->i_pages, folio->index);
+		unsigned long flags;
+
+		xas_lock_irqsave(&xas, flags);
+		xas_load(&xas);
+		xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
+		xas_unlock_irqrestore(&xas, flags);
+	}
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 6119a06b0569..69f9d5f5cc3c 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -88,6 +88,9 @@ struct btrfs_fs_context {
 	refcount_t refs;
 };
 
+static void btrfs_emit_options(struct btrfs_fs_info *info,
+			       struct btrfs_fs_context *old);
+
 enum {
 	Opt_acl,
 	Opt_clear_cache,
@@ -697,12 +700,9 @@ bool btrfs_check_options(const struct btrfs_fs_info *info,
 
 	if (!test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state)) {
 		if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) {
-			btrfs_info(info, "disk space caching is enabled");
 			btrfs_warn(info,
 "space cache v1 is being deprecated and will be removed in a future release, please use -o space_cache=v2");
 		}
-		if (btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE))
-			btrfs_info(info, "using free-space-tree");
 	}
 
 	return ret;
@@ -979,6 +979,8 @@ static int btrfs_fill_super(struct super_block *sb,
 		return err;
 	}
 
+	btrfs_emit_options(fs_info, NULL);
+
 	inode = btrfs_iget(BTRFS_FIRST_FREE_OBJECTID, fs_info->fs_root);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
@@ -1436,7 +1438,7 @@ static void btrfs_emit_options(struct btrfs_fs_info *info,
 {
 	btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum");
 	btrfs_info_if_set(info, old, DEGRADED, "allowing degraded mounts");
-	btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum");
+	btrfs_info_if_set(info, old, NODATACOW, "setting nodatacow");
 	btrfs_info_if_set(info, old, SSD, "enabling ssd optimizations");
 	btrfs_info_if_set(info, old, SSD_SPREAD, "using spread ssd allocation scheme");
 	btrfs_info_if_set(info, old, NOBARRIER, "turning off barriers");
@@ -1458,10 +1460,11 @@ static void btrfs_emit_options(struct btrfs_fs_info *info,
 	btrfs_info_if_set(info, old, IGNOREMETACSUMS, "ignoring meta csums");
 	btrfs_info_if_set(info, old, IGNORESUPERFLAGS, "ignoring unknown super block flags");
 
+	btrfs_info_if_unset(info, old, NODATASUM, "setting datasum");
 	btrfs_info_if_unset(info, old, NODATACOW, "setting datacow");
 	btrfs_info_if_unset(info, old, SSD, "not using ssd optimizations");
 	btrfs_info_if_unset(info, old, SSD_SPREAD, "not using spread ssd allocation scheme");
-	btrfs_info_if_unset(info, old, NOBARRIER, "turning off barriers");
+	btrfs_info_if_unset(info, old, NOBARRIER, "turning on barriers");
 	btrfs_info_if_unset(info, old, NOTREELOG, "enabling tree log");
 	btrfs_info_if_unset(info, old, SPACE_CACHE, "disabling disk space caching");
 	btrfs_info_if_unset(info, old, FREE_SPACE_TREE, "disabling free space tree");
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index dbef80cd5a9f..1a029392eac5 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2113,6 +2113,7 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
 		*/
 	       spin_lock(&fs_info->unused_bgs_lock);
                list_del_init(&block_group->bg_list);
+	       btrfs_put_block_group(block_group);
 	       spin_unlock(&fs_info->unused_bgs_lock);
        }
 }
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 53d8c49ec058..2fdb2987c83a 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2092,10 +2092,15 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 		goto out_unlock;
 	}
 
-	/* No space left */
-	if (btrfs_zoned_bg_is_full(block_group)) {
-		ret = false;
-		goto out_unlock;
+	if (block_group->flags & BTRFS_BLOCK_GROUP_DATA) {
+		/* The caller should check if the block group is full. */
+		if (WARN_ON_ONCE(btrfs_zoned_bg_is_full(block_group))) {
+			ret = false;
+			goto out_unlock;
+		}
+	} else {
+		/* Since it is already written, it should have been active. */
+		WARN_ON_ONCE(block_group->meta_write_pointer != block_group->start);
 	}
 
 	for (i = 0; i < map->num_stripes; i++) {