btrfs: Handle final split-brain possibility during fsid change

This patch lands the last case which needs to be handled by the fsid
change code. Namely, this is the case where a multidisk filesystem has
already undergone at least one successful fsid change i.e all disks
have the METADATA_UUID incompat bit and power failure occurs as another
fsid change is in progress. When such an event occurs, disks could be
split in 2 groups. One of the groups will have both METADATA_UUID and
CHANGING_FSID_V2 flags set coupled with old fsid/metadata_uuid pairs.
The other group of disks will have only METADATA_UUID bit set and their
fsid will be different than the one in disks in the first group. Here
we look at the following cases:

  a) A disk from the first group is scanned first, so fs_devices is
  created with stale fsid/metdata_uuid. Then when a disk from the
  second group is scanned it needs to first check whether there exists
  such an fs_devices that has fsid_change set to true (because it was
  created with a disk having the CHANGING_FSID_V2 flag), the
  metadata_uuid and fsid of the fs_devices will be different (since it was
  created by a disk which already has had at least 1 successful fsid change)
  and finally the metadata_uuid of the fs_devices will equal that of the
  currently scanned disk (because metadata_uuid never really changes).
  When the correct fs_devices is found the information from the scanned
  disk will replace the current one in fs_devices since the scanned disk
  will have higher generation number.

  b) A disk from the second group is scanned so fs_devices is created
  as usual with differing fsid/metdata_uid. Then when a disk from the
  first group is scanned the code detects that it has both
  CHANGING_FSID_V2 and METADATA_UUID flags set and will search for
  fs_devices that has differing metadata_uuid/fsid and whose
  metadata_uuid is the same as that of the scanned device.

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

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ce14ce068a847211f41b9190e12e9a402db1e498..a89596c3de56b0ba5e68521b10d412b7a50c3fdb 100644 (file)
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -405,6 +405,21 @@ static noinline struct btrfs_fs_devices *find_fsid(
                                return fs_devices;
                        }
                }
+               /*
+                * Handle scanned device having completed its fsid change but
+                * belonging to a fs_devices that was created by a device that
+                * has an outdated pair of fsid/metadata_uuid and
+                * CHANGING_FSID_V2 flag set.
+                */
+               list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+                       if (fs_devices->fsid_change &&
+                           memcmp(fs_devices->metadata_uuid,
+                                  fs_devices->fsid, BTRFS_FSID_SIZE) != 0 &&
+                           memcmp(metadata_fsid, fs_devices->metadata_uuid,
+                                  BTRFS_FSID_SIZE) == 0) {
+                               return fs_devices;
+                       }
+               }
        }
 
        /* Handle non-split brain cases */
@@ -814,6 +829,30 @@ static struct btrfs_fs_devices *find_fsid_inprogress(
        return NULL;
 }
 
+
+static struct btrfs_fs_devices *find_fsid_changed(
+                                       struct btrfs_super_block *disk_super)
+{
+       struct btrfs_fs_devices *fs_devices;
+
+       /*
+        * Handles the case where scanned device is part of an fs that had
+        * multiple successful changes of FSID but curently device didn't
+        * observe it. Meaning our fsid will be different than theirs.
+        */
+       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->metadata_uuid,
+                          BTRFS_FSID_SIZE) == 0 &&
+                   memcmp(fs_devices->fsid, disk_super->fsid,
+                          BTRFS_FSID_SIZE) != 0) {
+                       return fs_devices;
+               }
+       }
+
+       return NULL;
+}
 /*
  * Add new device to list of registered devices
  *
@@ -835,17 +874,20 @@ 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 (fsid_change_in_progress && !has_metadata_uuid) {
-               /*
-                * 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);
-
+       if (fsid_change_in_progress) {
+               if (!has_metadata_uuid) {
+                       /*
+                        * 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 {
+                       fs_devices = find_fsid_changed(disk_super);
+               }
        } else if (has_metadata_uuid) {
                fs_devices = find_fsid(disk_super->fsid,
                                       disk_super->metadata_uuid);