btrfs: qgroups: Retry after commit on getting EDQUOT

We are facing the same problem with EDQUOT which was experienced with
ENOSPC. Not sure if we require a full ticketing system such as ENOSPC, but
here is a quick fix, which may be too big a hammer.

Quotas are reserved during the start of an operation, incrementing
qg->reserved. However, it is written to disk in a commit_transaction
which could take as long as commit_interval. In the meantime there
could be deletions which are not accounted for because deletions are
accounted for only while committed (free_refroot). So, when we get
a EDQUOT flush the data to disk and try again.

This fixes fstests btrfs/139.

Here is a sample script which shows this issue.

DEVICE=/dev/vdb
MOUNTPOINT=/mnt
TESTVOL=$MOUNTPOINT/tmp
QUOTA=5
PROG=btrfs
DD_BS="4k"
DD_COUNT="256"
RUN_TIMES=5000

mkfs.btrfs -f $DEVICE
mount -o commit=240 $DEVICE $MOUNTPOINT
$PROG subvolume create $TESTVOL
$PROG quota enable $TESTVOL
$PROG qgroup limit ${QUOTA}G $TESTVOL

typeset -i DD_RUN_GOOD
typeset -i QUOTA

function _check_cmd() {
        if [[ ${?} > 0 ]]; then
                echo -n "$(date) E: Running previous command"
                echo ${*}
                echo "Without sync"
                $PROG qgroup show -pcreFf ${TESTVOL}
                echo "With sync"
                $PROG qgroup show -pcreFf --sync ${TESTVOL}
                exit 1
        fi
}

while true; do
  DD_RUN_GOOD=$RUN_TIMES

  while (( ${DD_RUN_GOOD} != 0 )); do
        dd if=/dev/zero of=${TESTVOL}/quotatest${DD_RUN_GOOD} bs=${DD_BS} count=${DD_COUNT}
        _check_cmd "dd if=/dev/zero of=${TESTVOL}/quotatest${DD_RUN_GOOD} bs=${DD_BS} count=${DD_COUNT}"
        DD_RUN_GOOD=(${DD_RUN_GOOD}-1)
  done

  $PROG qgroup show -pcref $TESTVOL
  echo "----------- Cleanup ---------- "
  rm $TESTVOL/quotatest*

done

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/qgroup.c

@@ -2367,6 +2367,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce)
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 ref_root = root->root_key.objectid;
 	int ret = 0;
+	int retried = 0;
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
 
@@ -2375,7 +2376,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce)
 
 	if (num_bytes == 0)
 		return 0;
-
+retry:
 	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
 	if (!quota_root)
@@ -2402,6 +2403,27 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce)
 		qg = unode_aux_to_qgroup(unode);
 
 		if (enforce && !qgroup_check_limits(qg, num_bytes)) {
+			/*
+			 * Commit the tree and retry, since we may have
+			 * deletions which would free up space.
+			 */
+			if (!retried && qg->reserved > 0) {
+				struct btrfs_trans_handle *trans;
+
+				spin_unlock(&fs_info->qgroup_lock);
+				ret = btrfs_start_delalloc_inodes(root, 0);
+				if (ret)
+					return ret;
+				btrfs_wait_ordered_extents(root, -1, 0, (u64)-1);
+				trans = btrfs_join_transaction(root);
+				if (IS_ERR(trans))
+					return PTR_ERR(trans);
+				ret = btrfs_commit_transaction(trans);
+				if (ret)
+					return ret;
+				retried++;
+				goto retry;
+			}
 			ret = -EDQUOT;
 			goto out;
 		}