btrfs: Fix split-brain handling when changing FSID to metadata uuid

[ Upstream commit 1362089d2ad7e20d16371b39d3c11990d4ec23e4 ]

Current code doesn't correctly handle the situation which arises when
a file system that has METADATA_UUID_INCOMPAT flag set and has its FSID
changed to the one in metadata uuid. This causes the incompat flag to
disappear.

In case of a power failure we could end up in a situation where part of
the disks in a multi-disk filesystem are correctly reverted to
METADATA_UUID_INCOMPAT flag unset state, while others have
METADATA_UUID_INCOMPAT set and CHANGING_FSID_V2_IN_PROGRESS.

This patch corrects the behavior required to handle the case where a
disk of the second type is scanned first, creating the necessary
btrfs_fs_devices. Subsequently, when a disk which has already completed
the transition is scanned it should overwrite the data in
btrfs_fs_devices.

Reported-by: Su Yue <Damenly_Su@gmx.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 38 insertions, 4 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9ab3ae5df300..3e64f49c394b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -907,6 +907,32 @@ static struct btrfs_fs_devices *find_fsid_changed(
 
 	return NULL;
 }
+
+static struct btrfs_fs_devices *find_fsid_reverted_metadata(
+				struct btrfs_super_block *disk_super)
+{
+	struct btrfs_fs_devices *fs_devices;
+
+	/*
+	 * Handle the case where the scanned device is part of an fs whose last
+	 * metadata UUID change reverted it to the original FSID. At the same
+	 * time * fs_devices was first created by another constitutent device
+	 * which didn't fully observe the operation. This results in an
+	 * btrfs_fs_devices created with metadata/fsid different AND
+	 * btrfs_fs_devices::fsid_change set AND the metadata_uuid of the
+	 * fs_devices equal to the FSID of the disk.
+	 */
+	list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+		if (memcmp(fs_devices->fsid, fs_devices->metadata_uuid,
+			   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
  *
@@ -946,7 +972,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		fs_devices = find_fsid(disk_super->fsid,
 				       disk_super->metadata_uuid);
 	} else {
-		fs_devices = find_fsid(disk_super->fsid, NULL);
+		fs_devices = find_fsid_reverted_metadata(disk_super);
+		if (!fs_devices)
+			fs_devices = find_fsid(disk_super->fsid, NULL);
 	}
 
 
@@ -976,12 +1004,18 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		 * 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 &&
+		if (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);
+
+			if (has_metadata_uuid)
+				memcpy(fs_devices->metadata_uuid,
+				       disk_super->metadata_uuid,
+				       BTRFS_FSID_SIZE);
+			else
+				memcpy(fs_devices->metadata_uuid,
+				       disk_super->fsid, BTRFS_FSID_SIZE);
 
 			fs_devices->fsid_change = false;
 		}