@@ -8134,6 +8134,27 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
return ret;
}
+/*
+ * have_mirrored_block_group - check if we have at least one writable
+ * mirrored Block Group
+ */
+static bool have_mirrored_block_group(struct btrfs_space_info *space_info)
+{
+ struct btrfs_block_group_cache *cache;
+ int i;
+
+ for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+ if (i == BTRFS_RAID_RAID0 || i == BTRFS_RAID_SINGLE)
+ continue;
+ list_for_each_entry(cache, &space_info->block_groups[i],
+ list) {
+ if (!cache->ro)
+ return true;
+ }
+ }
+ return false;
+}
+
int btrfs_read_block_groups(struct btrfs_fs_info *info)
{
struct btrfs_path *path;
@@ -8321,6 +8342,10 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
BTRFS_BLOCK_GROUP_RAID56_MASK |
BTRFS_BLOCK_GROUP_DUP)))
continue;
+
+ if (!have_mirrored_block_group(space_info))
+ continue;
+
/*
* avoid allocating from un-mirrored block group if there are
* mirrored block groups.
If the btrfs volume has mirrored block groups, it unconditionally makes un-mirrored block groups read only. When we have mirrored block groups, but don't have writable block groups, this will drop all writable block groups. So, check if we have at least one writable mirrored block group before setting un-mirrored block groups read only. This change is necessary to handle e.g. xfstests btrfs/124 case. When we mount degraded RAID1 FS and write to it, and then re-mount with full device, the write pointers of corresponding zones of written BG differ. We mark such block group as "wp_broken" and make it read only. In this situation, we only have read only RAID1 BGs because of "wp_broken" and un-mirrored BGs are also marked read only, because we have RAID1 BGs. As a result, all the BGs are now read only, so that we cannot even start the rebalance to fix the situation. Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com> --- fs/btrfs/extent-tree.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+)