Merge tag 'v6.17-rc3' into togreg

Linux 6.17-rc3

8 files changed, 202 insertions, 78 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 835b0deef9bb..c953297aa89a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1512,7 +1512,7 @@ out:
 
 /*
  * Return 0 if we have submitted or queued the sector for submission.
- * Return <0 for critical errors.
+ * Return <0 for critical errors, and the sector will have its dirty flag cleared.
  *
  * Caller should make sure filepos < i_size and handle filepos >= i_size case.
  */
@@ -1535,8 +1535,17 @@ static int submit_one_sector(struct btrfs_inode *inode,
 	ASSERT(filepos < i_size);
 
 	em = btrfs_get_extent(inode, NULL, filepos, sectorsize);
-	if (IS_ERR(em))
+	if (IS_ERR(em)) {
+		/*
+		 * When submission failed, we should still clear the folio dirty.
+		 * Or the folio will be written back again but without any
+		 * ordered extent.
+		 */
+		btrfs_folio_clear_dirty(fs_info, folio, filepos, sectorsize);
+		btrfs_folio_set_writeback(fs_info, folio, filepos, sectorsize);
+		btrfs_folio_clear_writeback(fs_info, folio, filepos, sectorsize);
 		return PTR_ERR(em);
+	}
 
 	extent_offset = filepos - em->start;
 	em_end = btrfs_extent_map_end(em);
@@ -1609,8 +1618,12 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
 		folio_unlock(folio);
 		return 1;
 	}
-	if (ret < 0)
+	if (ret < 0) {
+		btrfs_folio_clear_dirty(fs_info, folio, start, len);
+		btrfs_folio_set_writeback(fs_info, folio, start, len);
+		btrfs_folio_clear_writeback(fs_info, folio, start, len);
 		return ret;
+	}
 
 	for (cur = start; cur < start + len; cur += fs_info->sectorsize)
 		set_bit((cur - folio_start) >> fs_info->sectorsize_bits, &range_bitmap);
@@ -1666,8 +1679,8 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
 	 * Here we set writeback and clear for the range. If the full folio
 	 * is no longer dirty then we clear the PAGECACHE_TAG_DIRTY tag.
 	 *
-	 * If we hit any error, the corresponding sector will still be dirty
-	 * thus no need to clear PAGECACHE_TAG_DIRTY.
+	 * If we hit any error, the corresponding sector will have its dirty
+	 * flag cleared and writeback finished, thus no need to handle the error case.
 	 */
 	if (!submitted_io && !error) {
 		btrfs_folio_set_writeback(fs_info, folio, start, len);
@@ -1813,6 +1826,7 @@ static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *e
 		xas_load(&xas);
 		xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
 		xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
+		xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
 		xas_unlock_irqrestore(&xas, flags);
 
 		btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
@@ -4331,15 +4345,18 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
 	unsigned long end = index + (PAGE_SIZE >> fs_info->nodesize_bits) - 1;
 	int ret;
 
-	xa_lock_irq(&fs_info->buffer_tree);
+	rcu_read_lock();
 	xa_for_each_range(&fs_info->buffer_tree, index, eb, start, end) {
 		/*
 		 * The same as try_release_extent_buffer(), to ensure the eb
 		 * won't disappear out from under us.
 		 */
 		spin_lock(&eb->refs_lock);
+		rcu_read_unlock();
+
 		if (refcount_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
 			spin_unlock(&eb->refs_lock);
+			rcu_read_lock();
 			continue;
 		}
 
@@ -4358,11 +4375,10 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
 		 * check the folio private at the end.  And
 		 * release_extent_buffer() will release the refs_lock.
 		 */
-		xa_unlock_irq(&fs_info->buffer_tree);
 		release_extent_buffer(eb);
-		xa_lock_irq(&fs_info->buffer_tree);
+		rcu_read_lock();
 	}
-	xa_unlock_irq(&fs_info->buffer_tree);
+	rcu_read_unlock();
 
 	/*
 	 * Finally to check if we have cleared folio private, as if we have
@@ -4375,7 +4391,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
 		ret = 0;
 	spin_unlock(&folio->mapping->i_private_lock);
 	return ret;
-
 }
 
 int try_release_extent_buffer(struct folio *folio)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b77dd22b8cdb..9e4aec7330cb 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -401,10 +401,12 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 
 	while (index <= end_index) {
 		folio = filemap_get_folio(inode->vfs_inode.i_mapping, index);
-		index++;
-		if (IS_ERR(folio))
+		if (IS_ERR(folio)) {
+			index++;
 			continue;
+		}
 
+		index = folio_end(folio) >> PAGE_SHIFT;
 		/*
 		 * Here we just clear all Ordered bits for every page in the
 		 * range, then btrfs_mark_ordered_io_finished() will handle
@@ -2013,7 +2015,7 @@ static int nocow_one_range(struct btrfs_inode *inode, struct folio *locked_folio
 	 * cleaered by the caller.
 	 */
 	if (ret < 0)
-		btrfs_cleanup_ordered_extents(inode, file_pos, end);
+		btrfs_cleanup_ordered_extents(inode, file_pos, len);
 	return ret;
 }
 
@@ -4187,6 +4189,23 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+static void update_time_after_link_or_unlink(struct btrfs_inode *dir)
+{
+	struct timespec64 now;
+
+	/*
+	 * If we are replaying a log tree, we do not want to update the mtime
+	 * and ctime of the parent directory with the current time, since the
+	 * log replay procedure is responsible for setting them to their correct
+	 * values (the ones it had when the fsync was done).
+	 */
+	if (test_bit(BTRFS_FS_LOG_RECOVERING, &dir->root->fs_info->flags))
+		return;
+
+	now = inode_set_ctime_current(&dir->vfs_inode);
+	inode_set_mtime_to_ts(&dir->vfs_inode, now);
+}
+
 /*
  * unlink helper that gets used here in inode.c and in the tree logging
  * recovery code.  It remove a link in a directory with a given name, and
@@ -4287,7 +4306,7 @@ skip_backref:
 	inode_inc_iversion(&inode->vfs_inode);
 	inode_set_ctime_current(&inode->vfs_inode);
 	inode_inc_iversion(&dir->vfs_inode);
- 	inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode));
+	update_time_after_link_or_unlink(dir);
 
 	return btrfs_update_inode(trans, dir);
 }
@@ -6681,15 +6700,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 	btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size +
 			   name->len * 2);
 	inode_inc_iversion(&parent_inode->vfs_inode);
-	/*
-	 * If we are replaying a log tree, we do not want to update the mtime
-	 * and ctime of the parent directory with the current time, since the
-	 * log replay procedure is responsible for setting them to their correct
-	 * values (the ones it had when the fsync was done).
-	 */
-	if (!test_bit(BTRFS_FS_LOG_RECOVERING, &root->fs_info->flags))
-		inode_set_mtime_to_ts(&parent_inode->vfs_inode,
-				      inode_set_ctime_current(&parent_inode->vfs_inode));
+	update_time_after_link_or_unlink(parent_inode);
 
 	ret = btrfs_update_inode(trans, parent_inode);
 	if (ret)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 1a5972178b3a..ccaa9a3cf1ce 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1453,7 +1453,6 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
 				    struct btrfs_qgroup *src, int sign)
 {
 	struct btrfs_qgroup *qgroup;
-	struct btrfs_qgroup *cur;
 	LIST_HEAD(qgroup_list);
 	u64 num_bytes = src->excl;
 	int ret = 0;
@@ -1463,7 +1462,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
 		goto out;
 
 	qgroup_iterator_add(&qgroup_list, qgroup);
-	list_for_each_entry(cur, &qgroup_list, iterator) {
+	list_for_each_entry(qgroup, &qgroup_list, iterator) {
 		struct btrfs_qgroup_list *glist;
 
 		qgroup->rfer += sign * num_bytes;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index e58151933844..7256f6748c8f 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -602,6 +602,25 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
 	if (btrfs_root_id(root) == objectid) {
 		u64 commit_root_gen;
 
+		/*
+		 * Relocation will wait for cleaner thread, and any half-dropped
+		 * subvolume will be fully cleaned up at mount time.
+		 * So here we shouldn't hit a subvolume with non-zero drop_progress.
+		 *
+		 * If this isn't the case, error out since it can make us attempt to
+		 * drop references for extents that were already dropped before.
+		 */
+		if (unlikely(btrfs_disk_key_objectid(&root->root_item.drop_progress))) {
+			struct btrfs_key cpu_key;
+
+			btrfs_disk_key_to_cpu(&cpu_key, &root->root_item.drop_progress);
+			btrfs_err(fs_info,
+	"cannot relocate partially dropped subvolume %llu, drop progress key (%llu %u %llu)",
+				  objectid, cpu_key.objectid, cpu_key.type, cpu_key.offset);
+			ret = -EUCLEAN;
+			goto fail;
+		}
+
 		/* called by btrfs_init_reloc_root */
 		ret = btrfs_copy_root(trans, root, root->commit_root, &eb,
 				      BTRFS_TREE_RELOC_OBJECTID);
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index c9b3821957f7..cb4f97833dc3 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -448,8 +448,25 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
 
 	spin_lock_irqsave(&bfs->lock, flags);
 	bitmap_set(bfs->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(&bfs->lock, flags);
 }
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 68e35a3700ff..a262b494a89f 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,
@@ -698,12 +701,9 @@ 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;
@@ -980,6 +980,8 @@ static int btrfs_fill_super(struct super_block *sb,
 		return ret;
 	}
 
+	btrfs_emit_options(fs_info, NULL);
+
 	inode = btrfs_iget(BTRFS_FIRST_FREE_OBJECTID, fs_info->fs_root);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
@@ -1437,7 +1439,7 @@ 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");
@@ -1459,10 +1461,11 @@ 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/tree-log.c b/fs/btrfs/tree-log.c
index 2186e87fb61b..69e11557fd13 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2605,14 +2605,14 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 /*
  * Correctly adjust the reserved bytes occupied by a log tree extent buffer
  */
-static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
+static int unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
 {
 	struct btrfs_block_group *cache;
 
 	cache = btrfs_lookup_block_group(fs_info, start);
 	if (!cache) {
 		btrfs_err(fs_info, "unable to find block group for %llu", start);
-		return;
+		return -ENOENT;
 	}
 
 	spin_lock(&cache->space_info->lock);
@@ -2623,27 +2623,22 @@ static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
 	spin_unlock(&cache->space_info->lock);
 
 	btrfs_put_block_group(cache);
+
+	return 0;
 }
 
 static int clean_log_buffer(struct btrfs_trans_handle *trans,
 			    struct extent_buffer *eb)
 {
-	int ret;
-
 	btrfs_tree_lock(eb);
 	btrfs_clear_buffer_dirty(trans, eb);
 	wait_on_extent_buffer_writeback(eb);
 	btrfs_tree_unlock(eb);
 
-	if (trans) {
-		ret = btrfs_pin_reserved_extent(trans, eb);
-		if (ret)
-			return ret;
-	} else {
-		unaccount_log_buffer(eb->fs_info, eb->start);
-	}
+	if (trans)
+		return btrfs_pin_reserved_extent(trans, eb);
 
-	return 0;
+	return unaccount_log_buffer(eb->fs_info, eb->start);
 }
 
 static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 245e813ecd78..ea662036f441 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -17,6 +17,7 @@
 #include "accessors.h"
 #include "bio.h"
 #include "transaction.h"
+#include "sysfs.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
@@ -42,6 +43,9 @@
 /* Number of superblock log zones */
 #define BTRFS_NR_SB_LOG_ZONES 2
 
+/* Default number of max active zones when the device has no limits. */
+#define BTRFS_DEFAULT_MAX_ACTIVE_ZONES	128
+
 /*
  * Minimum of active zones we need:
  *
@@ -416,7 +420,10 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 	if (!IS_ALIGNED(nr_sectors, zone_sectors))
 		zone_info->nr_zones++;
 
-	max_active_zones = bdev_max_active_zones(bdev);
+	max_active_zones = min_not_zero(bdev_max_active_zones(bdev),
+					bdev_max_open_zones(bdev));
+	if (!max_active_zones && zone_info->nr_zones > BTRFS_DEFAULT_MAX_ACTIVE_ZONES)
+		max_active_zones = BTRFS_DEFAULT_MAX_ACTIVE_ZONES;
 	if (max_active_zones && max_active_zones < BTRFS_MIN_ACTIVE_ZONES) {
 		btrfs_err(fs_info,
 "zoned: %s: max active zones %u is too small, need at least %u active zones",
@@ -2168,10 +2175,15 @@ 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++) {
@@ -2230,7 +2242,7 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group)
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	const u64 end = block_group->start + block_group->length;
 	struct extent_buffer *eb;
-	unsigned long index, start = (block_group->start >> fs_info->sectorsize_bits);
+	unsigned long index, start = (block_group->start >> fs_info->nodesize_bits);
 
 	rcu_read_lock();
 	xa_for_each_start(&fs_info->buffer_tree, index, eb, start) {
@@ -2245,6 +2257,40 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group)
 	rcu_read_unlock();
 }
 
+static int call_zone_finish(struct btrfs_block_group *block_group,
+			    struct btrfs_io_stripe *stripe)
+{
+	struct btrfs_device *device = stripe->dev;
+	const u64 physical = stripe->physical;
+	struct btrfs_zoned_device_info *zinfo = device->zone_info;
+	int ret;
+
+	if (!device->bdev)
+		return 0;
+
+	if (zinfo->max_active_zones == 0)
+		return 0;
+
+	if (btrfs_dev_is_sequential(device, physical)) {
+		unsigned int nofs_flags;
+
+		nofs_flags = memalloc_nofs_save();
+		ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
+				       physical >> SECTOR_SHIFT,
+				       zinfo->zone_size >> SECTOR_SHIFT);
+		memalloc_nofs_restore(nofs_flags);
+
+		if (ret)
+			return ret;
+	}
+
+	if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA))
+		zinfo->reserved_active_zones++;
+	btrfs_dev_clear_active_zone(device, physical);
+
+	return 0;
+}
+
 static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -2329,31 +2375,12 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 	down_read(&dev_replace->rwsem);
 	map = block_group->physical_map;
 	for (i = 0; i < map->num_stripes; i++) {
-		struct btrfs_device *device = map->stripes[i].dev;
-		const u64 physical = map->stripes[i].physical;
-		struct btrfs_zoned_device_info *zinfo = device->zone_info;
-		unsigned int nofs_flags;
-
-		if (!device->bdev)
-			continue;
-
-		if (zinfo->max_active_zones == 0)
-			continue;
-
-		nofs_flags = memalloc_nofs_save();
-		ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
-				       physical >> SECTOR_SHIFT,
-				       zinfo->zone_size >> SECTOR_SHIFT);
-		memalloc_nofs_restore(nofs_flags);
 
+		ret = call_zone_finish(block_group, &map->stripes[i]);
 		if (ret) {
 			up_read(&dev_replace->rwsem);
 			return ret;
 		}
-
-		if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA))
-			zinfo->reserved_active_zones++;
-		btrfs_dev_clear_active_zone(device, physical);
 	}
 	up_read(&dev_replace->rwsem);
 
@@ -2504,12 +2531,12 @@ void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg)
 void btrfs_zoned_reserve_data_reloc_bg(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_space_info *data_sinfo = fs_info->data_sinfo;
-	struct btrfs_space_info *space_info = data_sinfo->sub_group[0];
+	struct btrfs_space_info *space_info = data_sinfo;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_block_group *bg;
 	struct list_head *bg_list;
 	u64 alloc_flags;
-	bool initial = false;
+	bool first = true;
 	bool did_chunk_alloc = false;
 	int index;
 	int ret;
@@ -2523,21 +2550,52 @@ void btrfs_zoned_reserve_data_reloc_bg(struct btrfs_fs_info *fs_info)
 	if (sb_rdonly(fs_info->sb))
 		return;
 
-	ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC);
 	alloc_flags = btrfs_get_alloc_profile(fs_info, space_info->flags);
 	index = btrfs_bg_flags_to_raid_index(alloc_flags);
 
-	bg_list = &data_sinfo->block_groups[index];
+	/* Scan the data space_info to find empty block groups. Take the second one. */
 again:
+	bg_list = &space_info->block_groups[index];
 	list_for_each_entry(bg, bg_list, list) {
-		if (bg->used > 0)
+		if (bg->alloc_offset != 0)
 			continue;
 
-		if (!initial) {
-			initial = true;
+		if (first) {
+			first = false;
 			continue;
 		}
 
+		if (space_info == data_sinfo) {
+			/* Migrate the block group to the data relocation space_info. */
+			struct btrfs_space_info *reloc_sinfo = data_sinfo->sub_group[0];
+			int factor;
+
+			ASSERT(reloc_sinfo->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC);
+			factor = btrfs_bg_type_to_factor(bg->flags);
+
+			down_write(&space_info->groups_sem);
+			list_del_init(&bg->list);
+			/* We can assume this as we choose the second empty one. */
+			ASSERT(!list_empty(&space_info->block_groups[index]));
+			up_write(&space_info->groups_sem);
+
+			spin_lock(&space_info->lock);
+			space_info->total_bytes -= bg->length;
+			space_info->disk_total -= bg->length * factor;
+			/* There is no allocation ever happened. */
+			ASSERT(bg->used == 0);
+			ASSERT(bg->zone_unusable == 0);
+			/* No super block in a block group on the zoned setup. */
+			ASSERT(bg->bytes_super == 0);
+			spin_unlock(&space_info->lock);
+
+			bg->space_info = reloc_sinfo;
+			if (reloc_sinfo->block_group_kobjs[index] == NULL)
+				btrfs_sysfs_add_block_group_type(bg);
+
+			btrfs_add_bg_to_space_info(fs_info, bg);
+		}
+
 		fs_info->data_reloc_bg = bg->start;
 		set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &bg->runtime_flags);
 		btrfs_zone_activate(bg);
@@ -2552,11 +2610,18 @@ again:
 	if (IS_ERR(trans))
 		return;
 
+	/* Allocate new BG in the data relocation space_info. */
+	space_info = data_sinfo->sub_group[0];
+	ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC);
 	ret = btrfs_chunk_alloc(trans, space_info, alloc_flags, CHUNK_ALLOC_FORCE);
 	btrfs_end_transaction(trans);
 	if (ret == 1) {
+		/*
+		 * We allocated a new block group in the data relocation space_info. We
+		 * can take that one.
+		 */
+		first = false;
 		did_chunk_alloc = true;
-		bg_list = &space_info->block_groups[index];
 		goto again;
 	}
 }
@@ -2650,7 +2715,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info)
 
 		spin_lock(&block_group->lock);
 		if (block_group->reserved || block_group->alloc_offset == 0 ||
-		    (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) ||
+		    !(block_group->flags & BTRFS_BLOCK_GROUP_DATA) ||
 		    test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) {
 			spin_unlock(&block_group->lock);
 			continue;