btrfs: Introduce support for FSID change without metadata rewrite

This field is going to be used when the user wants to change the UUID
of the filesystem without having to rewrite all metadata blocks. This
field adds another level of indirection such that when the FSID is
changed what really happens is the current UUID (the one with which the
fs was created) is copied to the 'metadata_uuid' field in the superblock
as well as a new incompat flag is set METADATA_UUID. When the kernel
detects this flag is set it knows that the superblock in fact has 2
UUIDs:

1. Is the UUID which is user-visible, currently known as FSID.
2. Metadata UUID - this is the UUID which is stamped into all on-disk
   datastructures belonging to this file system.

When the new incompat flag is present device scanning checks whether
both fsid/metadata_uuid of the scanned device match any of the
registered filesystems. When the flag is not set then both UUIDs are
equal and only the FSID is retained on disk, metadata_uuid is set only
in-memory during mount.

Additionally a new metadata_uuid field is also added to the fs_info
struct. It's initialised either with the FSID in case METADATA_UUID
incompat flag is not set or with the metdata_uuid of the superblock
otherwise.

This commit introduces the new fields as well as the new incompat flag
and switches all users of the fsid to the new logic.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ minor updates in comments ]
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/ctree.c

@@ -224,7 +224,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 	else
 		btrfs_set_header_owner(cow, new_root_objectid);
 
-	write_extent_buffer_fsid(cow, fs_info->fsid);
+	write_extent_buffer_fsid(cow, fs_info->metadata_fsid);
 
 	WARN_ON(btrfs_header_generation(buf) > trans->transid);
 	if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
@@ -1050,7 +1050,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	else
 		btrfs_set_header_owner(cow, root->root_key.objectid);
 
-	write_extent_buffer_fsid(cow, fs_info->fsid);
+	write_extent_buffer_fsid(cow, fs_info->metadata_fsid);
 
 	ret = update_ref_for_cow(trans, root, buf, cow, &last_ref);
 	if (ret) {

fs/btrfs/ctree.h

@@ -195,9 +195,10 @@ struct btrfs_root_backup {
  * it currently lacks any block count etc etc
  */
 struct btrfs_super_block {
-	u8 csum[BTRFS_CSUM_SIZE];
 	/* the first 4 fields must match struct btrfs_header */
-	u8 fsid[BTRFS_FSID_SIZE];    /* FS specific uuid */
+	u8 csum[BTRFS_CSUM_SIZE];
+	/* FS specific UUID, visible to user */
+	u8 fsid[BTRFS_FSID_SIZE];
 	__le64 bytenr; /* this block number */
 	__le64 flags;
 
@@ -234,8 +235,11 @@ struct btrfs_super_block {
 	__le64 cache_generation;
 	__le64 uuid_tree_generation;
 
+	/* the UUID written into btree blocks */
+	u8 metadata_uuid[BTRFS_FSID_SIZE];
+
 	/* future expansion */
-	__le64 reserved[30];
+	__le64 reserved[28];
 	u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE];
 	struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS];
 } __attribute__ ((__packed__));
@@ -265,7 +269,8 @@ struct btrfs_super_block {
 	 BTRFS_FEATURE_INCOMPAT_RAID56 |		\
 	 BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF |		\
 	 BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA |	\
-	 BTRFS_FEATURE_INCOMPAT_NO_HOLES)
+	 BTRFS_FEATURE_INCOMPAT_NO_HOLES	|	\
+	 BTRFS_FEATURE_INCOMPAT_METADATA_UUID)
 
 #define BTRFS_FEATURE_INCOMPAT_SAFE_SET			\
 	(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
@@ -768,7 +773,10 @@ bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr);
 #define BTRFS_FS_BALANCE_RUNNING		18
 
 struct btrfs_fs_info {
+	/* User-visible fs UUID */
 	u8 fsid[BTRFS_FSID_SIZE];
+	/* UUID written to btree blocks */
+	u8 metadata_fsid[BTRFS_FSID_SIZE];
 	u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
 	unsigned long flags;
 	struct btrfs_root *extent_root;

fs/btrfs/disk-io.c

@@ -542,7 +542,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
 	if (WARN_ON(!PageUptodate(page)))
 		return -EUCLEAN;
 
-	ASSERT(memcmp_extent_buffer(eb, fs_info->fsid,
+	ASSERT(memcmp_extent_buffer(eb, fs_info->metadata_fsid,
 			btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0);
 
 	return csum_tree_block(fs_info, eb, 0);
@@ -557,7 +557,20 @@ static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
 
 	read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE);
 	while (fs_devices) {
-		if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) {
+		u8 *metadata_uuid;
+
+		/*
+		 * Checking the incompat flag is only valid for the current
+		 * fs. For seed devices it's forbidden to have their uuid
+		 * changed so reading ->fsid in this case is fine
+		 */
+		if (fs_devices == fs_info->fs_devices &&
+		    btrfs_fs_incompat(fs_info, METADATA_UUID))
+			metadata_uuid = fs_devices->metadata_uuid;
+		else
+			metadata_uuid = fs_devices->fsid;
+
+		if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) {
 			ret = 0;
 			break;
 		}
@@ -2443,10 +2456,11 @@ static int validate_super(struct btrfs_fs_info *fs_info,
 		ret = -EINVAL;
 	}
 
-	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) {
+	if (memcmp(fs_info->metadata_fsid, sb->dev_item.fsid,
+		   BTRFS_FSID_SIZE) != 0) {
 		btrfs_err(fs_info,
-			   "dev_item UUID does not match fsid: %pU != %pU",
-			   fs_info->fsid, sb->dev_item.fsid);
+			"dev_item UUID does not match metadata fsid: %pU != %pU",
+			fs_info->metadata_fsid, sb->dev_item.fsid);
 		ret = -EINVAL;
 	}
 
@@ -2790,6 +2804,12 @@ int open_ctree(struct super_block *sb,
 	brelse(bh);
 
 	memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE);
+	if (btrfs_fs_incompat(fs_info, METADATA_UUID)) {
+		memcpy(fs_info->metadata_fsid,
+		       fs_info->super_copy->metadata_uuid, BTRFS_FSID_SIZE);
+	} else {
+		memcpy(fs_info->metadata_fsid, fs_info->fsid, BTRFS_FSID_SIZE);
+	}
 
 	ret = btrfs_validate_mount_super(fs_info);
 	if (ret) {
@@ -3728,7 +3748,8 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 		btrfs_set_stack_device_io_width(dev_item, dev->io_width);
 		btrfs_set_stack_device_sector_size(dev_item, dev->sector_size);
 		memcpy(dev_item->uuid, dev->uuid, BTRFS_UUID_SIZE);
-		memcpy(dev_item->fsid, dev->fs_devices->fsid, BTRFS_FSID_SIZE);
+		memcpy(dev_item->fsid, dev->fs_devices->metadata_uuid,
+		       BTRFS_FSID_SIZE);
 
 		flags = btrfs_super_flags(sb);
 		btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN);

fs/btrfs/extent-tree.c

@@ -8312,7 +8312,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_header_backref_rev(buf, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(buf, owner);
-	write_extent_buffer_fsid(buf, fs_info->fsid);
+	write_extent_buffer_fsid(buf, fs_info->metadata_fsid);
 	write_extent_buffer_chunk_tree_uuid(buf, fs_info->chunk_tree_uuid);
 	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
 		buf->log_index = root->log_transid % 2;

fs/btrfs/volumes.c

@@ -245,13 +245,15 @@ struct list_head *btrfs_get_fs_uuids(void)
 
 /*
  * alloc_fs_devices - allocate struct btrfs_fs_devices
- * @fsid:	if not NULL, copy the uuid to fs_devices::fsid
+ * @fsid:		if not NULL, copy the UUID to fs_devices::fsid
+ * @metadata_fsid:	if not NULL, copy the UUID to fs_devices::metadata_fsid
  *
  * Return a pointer to a new struct btrfs_fs_devices on success, or ERR_PTR().
  * The returned struct is not linked onto any lists and can be destroyed with
  * kfree() right away.
  */
-static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid)
+static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid,
+						 const u8 *metadata_fsid)
 {
 	struct btrfs_fs_devices *fs_devs;
 
@@ -268,6 +270,11 @@ static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid)
 	if (fsid)
 		memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE);
 
+	if (metadata_fsid)
+		memcpy(fs_devs->metadata_uuid, metadata_fsid, BTRFS_FSID_SIZE);
+	else if (fsid)
+		memcpy(fs_devs->metadata_uuid, fsid, BTRFS_FSID_SIZE);
+
 	return fs_devs;
 }
 
@@ -375,14 +382,24 @@ static struct btrfs_device *find_device(struct btrfs_fs_devices *fs_devices,
 	return NULL;
 }
 
-static noinline struct btrfs_fs_devices *find_fsid(u8 *fsid)
+static noinline struct btrfs_fs_devices *find_fsid(
+		const u8 *fsid, const u8 *metadata_fsid)
 {
 	struct btrfs_fs_devices *fs_devices;
 
+	ASSERT(fsid);
+
 	list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+		if (metadata_fsid) {
+			if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0
+			    && memcmp(metadata_fsid, fs_devices->metadata_uuid,
+				      BTRFS_FSID_SIZE) == 0)
+				return fs_devices;
+		} else {
 			if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0)
 				return fs_devices;
 		}
+	}
 	return NULL;
 }
 
@@ -716,6 +733,13 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 	device->generation = btrfs_super_generation(disk_super);
 
 	if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING) {
+		if (btrfs_super_incompat_flags(disk_super) &
+		    BTRFS_FEATURE_INCOMPAT_METADATA_UUID) {
+			pr_err(
+		"BTRFS: Invalid seeding and uuid-changed device detected\n");
+			goto error_brelse;
+		}
+
 		clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 		fs_devices->seeding = 1;
 	} else {
@@ -766,10 +790,21 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 	struct rcu_string *name;
 	u64 found_transid = btrfs_super_generation(disk_super);
 	u64 devid = btrfs_stack_device_id(&disk_super->dev_item);
+	bool has_metadata_uuid = (btrfs_super_incompat_flags(disk_super) &
+		BTRFS_FEATURE_INCOMPAT_METADATA_UUID);
+
+	if (has_metadata_uuid)
+		fs_devices = find_fsid(disk_super->fsid, disk_super->metadata_uuid);
+	else
+		fs_devices = find_fsid(disk_super->fsid, NULL);
 
-	fs_devices = find_fsid(disk_super->fsid);
 	if (!fs_devices) {
-		fs_devices = alloc_fs_devices(disk_super->fsid);
+		if (has_metadata_uuid)
+			fs_devices = alloc_fs_devices(disk_super->fsid,
+						      disk_super->metadata_uuid);
+		else
+			fs_devices = alloc_fs_devices(disk_super->fsid, NULL);
+
 		if (IS_ERR(fs_devices))
 			return ERR_CAST(fs_devices);
 
@@ -920,7 +955,7 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 	struct btrfs_device *device;
 	struct btrfs_device *orig_dev;
 
-	fs_devices = alloc_fs_devices(orig->fsid);
+	fs_devices = alloc_fs_devices(orig->fsid, NULL);
 	if (IS_ERR(fs_devices))
 		return fs_devices;
 
@@ -1745,7 +1780,8 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 	ptr = btrfs_device_uuid(dev_item);
 	write_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
 	ptr = btrfs_device_fsid(dev_item);
-	write_extent_buffer(leaf, trans->fs_info->fsid, ptr, BTRFS_FSID_SIZE);
+	write_extent_buffer(leaf, trans->fs_info->metadata_fsid, ptr,
+			    BTRFS_FSID_SIZE);
 	btrfs_mark_buffer_dirty(leaf);
 
 	ret = 0;
@@ -2176,7 +2212,13 @@ static struct btrfs_device *btrfs_find_device_by_path(
 	disk_super = (struct btrfs_super_block *)bh->b_data;
 	devid = btrfs_stack_device_id(&disk_super->dev_item);
 	dev_uuid = disk_super->dev_item.uuid;
-	device = btrfs_find_device(fs_info, devid, dev_uuid, disk_super->fsid);
+	if (btrfs_fs_incompat(fs_info, METADATA_UUID))
+		device = btrfs_find_device(fs_info, devid, dev_uuid,
+				disk_super->metadata_uuid);
+	else
+		device = btrfs_find_device(fs_info, devid,
+				dev_uuid, disk_super->fsid);
+
 	brelse(bh);
 	if (!device)
 		device = ERR_PTR(-ENOENT);
@@ -2246,7 +2288,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	if (!fs_devices->seeding)
 		return -EINVAL;
 
-	seed_devices = alloc_fs_devices(NULL);
+	seed_devices = alloc_fs_devices(NULL, NULL);
 	if (IS_ERR(seed_devices))
 		return PTR_ERR(seed_devices);
 
@@ -2283,6 +2325,8 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 
 	generate_random_uuid(fs_devices->fsid);
 	memcpy(fs_info->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
+	memcpy(fs_devices->metadata_uuid, fs_devices->fsid, BTRFS_FSID_SIZE);
+	memcpy(fs_info->metadata_fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
 	memcpy(disk_super->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
 	mutex_unlock(&fs_devices->device_list_mutex);
 
@@ -6294,7 +6338,7 @@ struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
 	cur_devices = fs_info->fs_devices;
 	while (cur_devices) {
 		if (!fsid ||
-		    !memcmp(cur_devices->fsid, fsid, BTRFS_FSID_SIZE)) {
+		    !memcmp(cur_devices->metadata_uuid, fsid, BTRFS_FSID_SIZE)) {
 			device = find_device(cur_devices, devid, uuid);
 			if (device)
 				return device;
@@ -6623,12 +6667,12 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 		fs_devices = fs_devices->seed;
 	}
 
-	fs_devices = find_fsid(fsid);
+	fs_devices = find_fsid(fsid, NULL);
 	if (!fs_devices) {
 		if (!btrfs_test_opt(fs_info, DEGRADED))
 			return ERR_PTR(-ENOENT);
 
-		fs_devices = alloc_fs_devices(fsid);
+		fs_devices = alloc_fs_devices(fsid, NULL);
 		if (IS_ERR(fs_devices))
 			return fs_devices;
 
@@ -6678,7 +6722,7 @@ static int read_one_dev(struct btrfs_fs_info *fs_info,
 	read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item),
 			   BTRFS_FSID_SIZE);
 
-	if (memcmp(fs_uuid, fs_info->fsid, BTRFS_FSID_SIZE)) {
+	if (memcmp(fs_uuid, fs_info->metadata_fsid, BTRFS_FSID_SIZE)) {
 		fs_devices = open_seed_devices(fs_info, fs_uuid);
 		if (IS_ERR(fs_devices))
 			return PTR_ERR(fs_devices);

fs/btrfs/volumes.h

@@ -210,6 +210,7 @@ BTRFS_DEVICE_GETSET_FUNCS(bytes_used);
 
 struct btrfs_fs_devices {
 	u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
+	u8 metadata_uuid[BTRFS_FSID_SIZE];
 	struct list_head fs_list;
 
 	u64 num_devices;

include/uapi/linux/btrfs.h

@@ -269,6 +269,7 @@ struct btrfs_ioctl_fs_info_args {
 #define BTRFS_FEATURE_INCOMPAT_RAID56		(1ULL << 7)
 #define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA	(1ULL << 8)
 #define BTRFS_FEATURE_INCOMPAT_NO_HOLES		(1ULL << 9)
+#define BTRFS_FEATURE_INCOMPAT_METADATA_UUID	(1ULL << 10)
 
 struct btrfs_ioctl_feature_flags {
 	__u64 compat_flags;

include/uapi/linux/btrfs_tree.h

@@ -458,6 +458,7 @@ struct btrfs_free_space_header {
 #define BTRFS_SUPER_FLAG_METADUMP	(1ULL << 33)
 #define BTRFS_SUPER_FLAG_METADUMP_V2	(1ULL << 34)
 #define BTRFS_SUPER_FLAG_CHANGING_FSID	(1ULL << 35)
+#define BTRFS_SUPER_FLAG_CHANGING_FSID_V2 (1ULL << 36)
 
 
 /*