From: Mark Fasheh Date: Mon, 18 Aug 2014 21:01:17 +0000 (-0700) Subject: btrfs: don't go readonly on existing qgroup items X-Git-Tag: v3.18-rc1~91^2~62 X-Git-Url: https://openfabrics.org/gitweb/?a=commitdiff_plain;h=0b4699dcb65c2cff793210b07f40b98c2d423a43;p=~emulex%2Finfiniband.git btrfs: don't go readonly on existing qgroup items btrfs_drop_snapshot() leaves subvolume qgroup items on disk after completion. This can cause problems with snapshot creation. If a new snapshot tries to claim the deleted subvolumes id, btrfs will get -EEXIST from add_qgroup_item() and go read-only. The following commands will reproduce this problem (assume btrfs is on /dev/sda and is mounted at /btrfs) mkfs.btrfs -f /dev/sda mount -t btrfs /dev/sda /btrfs/ btrfs quota enable /btrfs/ btrfs su sna /btrfs/ /btrfs/snap btrfs su de /btrfs/snap sleep 45 umount /btrfs/ mount -t btrfs /dev/sda /btrfs/ We can fix this by catching -EEXIST in add_qgroup_item() and initializing the existing items. We have the problem of orphaned relation items being on disk from an old snapshot but that is outside the scope of this patch. Signed-off-by: Mark Fasheh Signed-off-by: Chris Mason --- diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1e4c6e95ab5..cd9717ea8c9 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -551,9 +551,15 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, key.type = BTRFS_QGROUP_INFO_KEY; key.offset = qgroupid; + /* + * Avoid a transaction abort by catching -EEXIST here. In that + * case, we proceed by re-initializing the existing structure + * on disk. + */ + ret = btrfs_insert_empty_item(trans, quota_root, path, &key, sizeof(*qgroup_info)); - if (ret) + if (ret && ret != -EEXIST) goto out; leaf = path->nodes[0]; @@ -572,7 +578,7 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, key.type = BTRFS_QGROUP_LIMIT_KEY; ret = btrfs_insert_empty_item(trans, quota_root, path, &key, sizeof(*qgroup_limit)); - if (ret) + if (ret && ret != -EEXIST) goto out; leaf = path->nodes[0];