btrfs: separate BLOCK_GROUP_TREE compat RO flag from EXTENT_TREE_V2

The problem of long mount time caused by block group item search is
already known for some time, and the solution of block group tree has
been proposed.

There is really no need to bound this feature into extent tree v2, just
introduce compat RO flag, BLOCK_GROUP_TREE, to correctly solve the
problem.

All the code handling block group root is already in the upstream
kernel, thus this patch really only needs to introduce the new compat RO
flag.

This patch introduces one extra artificial limitation on block group
tree feature, that free space cache v2 and no-holes feature must be
enabled to use this new compat RO feature.

This artificial requirement is mostly to reduce the test combinations,
and can be a guideline for future features, to mostly rely on the latest
default features.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

5 files changed, 25 insertions, 14 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2c38daa822ef..7007c7974a2e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -302,7 +302,8 @@ static_assert(sizeof(struct btrfs_super_block) == BTRFS_SUPER_INFO_SIZE);
 #define BTRFS_FEATURE_COMPAT_RO_SUPP			\
 	(BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE |	\
 	 BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID | \
-	 BTRFS_FEATURE_COMPAT_RO_VERITY)
+	 BTRFS_FEATURE_COMPAT_RO_VERITY |		\
+	 BTRFS_FEATURE_COMPAT_RO_BLOCK_GROUP_TREE)
 
 #define BTRFS_FEATURE_COMPAT_RO_SAFE_SET	0ULL
 #define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR	0ULL
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index dfc9b3aea76a..120b7697ab42 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1981,7 +1981,7 @@ static void backup_super_roots(struct btrfs_fs_info *info)
 	btrfs_set_backup_chunk_root_level(root_backup,
 			       btrfs_header_level(info->chunk_root->node));
 
-	if (!btrfs_fs_incompat(info, EXTENT_TREE_V2)) {
+	if (!btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) {
 		struct btrfs_root *extent_root = btrfs_extent_root(info, 0);
 		struct btrfs_root *csum_root = btrfs_csum_root(info, 0);
 
@@ -2526,7 +2526,7 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	location.type = BTRFS_ROOT_ITEM_KEY;
 	location.offset = 0;
 
-	if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) {
+	if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE)) {
 		location.objectid = BTRFS_BLOCK_GROUP_TREE_OBJECTID;
 		root = btrfs_read_tree_root(tree_root, &location);
 		if (IS_ERR(root)) {
@@ -2711,6 +2711,18 @@ int btrfs_validate_super(struct btrfs_fs_info *fs_info,
 		ret = -EINVAL;
 	}
 
+	/*
+	 * Artificial requirement for block-group-tree to force newer features
+	 * (free-space-tree, no-holes) so the test matrix is smaller.
+	 */
+	if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE) &&
+	    (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID) ||
+	     !btrfs_fs_incompat(fs_info, NO_HOLES))) {
+		btrfs_err(fs_info,
+		"block-group-tree feature requires fres-space-tree and no-holes");
+		ret = -EINVAL;
+	}
+
 	if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid,
 		   BTRFS_FSID_SIZE) != 0) {
 		btrfs_err(fs_info,
@@ -2880,16 +2892,6 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 	int ret = 0;
 	int i;
 
-	if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) {
-		struct btrfs_root *root;
-
-		root = btrfs_alloc_root(fs_info, BTRFS_BLOCK_GROUP_TREE_OBJECTID,
-					GFP_KERNEL);
-		if (!root)
-			return -ENOMEM;
-		fs_info->block_group_root = root;
-	}
-
 	for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
 		if (handle_error) {
 			if (!IS_ERR(tree_root->node))
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index aef981de672c..7e545ec09a10 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -105,7 +105,7 @@ static inline struct btrfs_root *btrfs_grab_root(struct btrfs_root *root)
 
 static inline struct btrfs_root *btrfs_block_group_root(struct btrfs_fs_info *fs_info)
 {
-	if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
+	if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE))
 		return fs_info->block_group_root;
 	return btrfs_extent_root(fs_info, 0);
 }
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 84a992681801..6816bc41c228 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -286,6 +286,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
 BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
 BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID);
 BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
+BTRFS_FEAT_ATTR_COMPAT_RO(block_group_tree, BLOCK_GROUP_TREE);
 BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34);
 #ifdef CONFIG_BLK_DEV_ZONED
 BTRFS_FEAT_ATTR_INCOMPAT(zoned, ZONED);
@@ -317,6 +318,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(metadata_uuid),
 	BTRFS_FEAT_ATTR_PTR(free_space_tree),
 	BTRFS_FEAT_ATTR_PTR(raid1c34),
+	BTRFS_FEAT_ATTR_PTR(block_group_tree),
 #ifdef CONFIG_BLK_DEV_ZONED
 	BTRFS_FEAT_ATTR_PTR(zoned),
 #endif
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 7ada84e4a3ed..5655e89b962b 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -290,6 +290,12 @@ struct btrfs_ioctl_fs_info_args {
 #define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID	(1ULL << 1)
 #define BTRFS_FEATURE_COMPAT_RO_VERITY			(1ULL << 2)
 
+/*
+ * Put all block group items into a dedicated block group tree, greatly
+ * reducing mount time for large filesystem due to better locality.
+ */
+#define BTRFS_FEATURE_COMPAT_RO_BLOCK_GROUP_TREE	(1ULL << 3)
+
 #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
 #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS	(1ULL << 2)