btrfs: Handle one more split-brain scenario during fsid change

This commit continues hardening the scanning code to handle cases where
power loss could have caused disks in a multi-disk filesystem to be
in inconsistent state. Namely handle the situation that can occur when
some of the disks in multi-disk fs have completed their fsid change i.e
they have METADATA_UUID incompat flag set, have cleared the
CHANGING_FSID_V2 flag and their fsid/metadata_uuid are different. At
the same time the other half of the disks will have their
fsid/metadata_uuid unchanged and will only have CHANGING_FSID_V2 flag.

This is handled by introducing code in the scan path which:

 a) Handles the case when a device with CHANGING_FSID_V2 flag is
 scanned and as a result btrfs_fs_devices is created with matching
 fsid/metdata_uuid. Subsequently, when a device with completed fsid
 change is scanned it will detect this via the new code in find_fsid
 i.e that such an fs_devices exist that fsid_change flag is set to true,
 it's metadata_uuid/fsid match and the metadata_uuid of the scanned
 device matches that of the fs_devices. In this case, it's important to
 note that the devices which has its fsid change completed will have a
 higher generation number than the device with FSID_CHANGING_V2 flag
 set, so its superblock block will be used during mount. To prevent an
 assertion triggering because the sb used for mounting will have
 differing fsid/metadata_uuid than the ones in the fs_devices struct
 also add code in device_list_add which overwrites the values in
 fs_devices.

 b) Alternatively we can end up with a device that completed its
 fsid change be scanned first which will create the respective
 btrfs_fs_devices struct with differing fsid/metadata_uuid. In this
 case when a device with FSID_CHANGING_V2 flag set is scanned it will
 call the newly added find_fsid_inprogress function which will return
 the correct fs_devices.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/volumes.c

@@ -389,6 +389,25 @@ static noinline struct btrfs_fs_devices *find_fsid(
 
 	ASSERT(fsid);
 
+	if (metadata_fsid) {
+		/*
+		 * Handle scanned device having completed its fsid change but
+		 * belonging to a fs_devices that was created by first scanning
+		 * a device which didn't have its fsid/metadata_uuid changed
+		 * at all and the CHANGING_FSID_V2 flag set.
+		 */
+		list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+			if (fs_devices->fsid_change &&
+			    memcmp(metadata_fsid, fs_devices->fsid,
+				   BTRFS_FSID_SIZE) == 0 &&
+			    memcmp(fs_devices->fsid, fs_devices->metadata_uuid,
+				   BTRFS_FSID_SIZE) == 0) {
+				return fs_devices;
+			}
+		}
+	}
+
+	/* Handle non-split brain cases */
 	list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
 		if (metadata_fsid) {
 			if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0
@@ -774,6 +793,27 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 	return -EINVAL;
 }
 
+/*
+ * Handle scanned device having its CHANGING_FSID_V2 flag set and the fs_devices
+ * being created with a disk that has already completed its fsid change.
+ */
+static struct btrfs_fs_devices *find_fsid_inprogress(
+					struct btrfs_super_block *disk_super)
+{
+	struct btrfs_fs_devices *fs_devices;
+
+	list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+		if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid,
+			   BTRFS_FSID_SIZE) != 0 &&
+		    memcmp(fs_devices->metadata_uuid, disk_super->fsid,
+			   BTRFS_FSID_SIZE) == 0 && !fs_devices->fsid_change) {
+			return fs_devices;
+		}
+	}
+
+	return NULL;
+}
+
 /*
  * Add new device to list of registered devices
  *
@@ -786,7 +826,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 			   bool *new_device_added)
 {
 	struct btrfs_device *device;
-	struct btrfs_fs_devices *fs_devices;
+	struct btrfs_fs_devices *fs_devices = NULL;
 	struct rcu_string *name;
 	u64 found_transid = btrfs_super_generation(disk_super);
 	u64 devid = btrfs_stack_device_id(&disk_super->dev_item);
@@ -795,11 +835,25 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 	bool fsid_change_in_progress = (btrfs_super_flags(disk_super) &
 					BTRFS_SUPER_FLAG_CHANGING_FSID_V2);
 
-	if (has_metadata_uuid)
+	if (fsid_change_in_progress && !has_metadata_uuid) {
-		fs_devices = find_fsid(disk_super->fsid, disk_super->metadata_uuid);
+		/*
-	else
+		 * When we have an image which has CHANGING_FSID_V2 set it might
+		 * belong to either a filesystem which has disks with completed
+		 * fsid change or it might belong to fs with no UUID changes in
+		 * effect, handle both.
+		 */
+		fs_devices = find_fsid_inprogress(disk_super);
+		if (!fs_devices)
 			fs_devices = find_fsid(disk_super->fsid, NULL);
 
+	} else if (has_metadata_uuid) {
+		fs_devices = find_fsid(disk_super->fsid,
+				       disk_super->metadata_uuid);
+	} else {
+		fs_devices = find_fsid(disk_super->fsid, NULL);
+	}
+
+
 	if (!fs_devices) {
 		if (has_metadata_uuid)
 			fs_devices = alloc_fs_devices(disk_super->fsid,
@@ -820,6 +874,21 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		mutex_lock(&fs_devices->device_list_mutex);
 		device = find_device(fs_devices, devid,
 				disk_super->dev_item.uuid);
+
+		/*
+		 * If this disk has been pulled into an fs devices created by
+		 * a device which had the CHANGING_FSID_V2 flag then replace the
+		 * metadata_uuid/fsid values of the fs_devices.
+		 */
+		if (has_metadata_uuid && fs_devices->fsid_change &&
+		    found_transid > fs_devices->latest_generation) {
+			memcpy(fs_devices->fsid, disk_super->fsid,
+					BTRFS_FSID_SIZE);
+			memcpy(fs_devices->metadata_uuid,
+					disk_super->metadata_uuid, BTRFS_FSID_SIZE);
+
+			fs_devices->fsid_change = false;
+		}
 	}
 
 	if (!device) {