xfs: make quota metadata truncation behavior consistent to user space

In xfs_qm_scall_trunc_qfiles(), we ignore the error if failed to remove
the users quota metadata and proceed to remove groups and projects if
they are being there.  However, in user space, the remove operation will
break and return if failed to remove any kind of quota.
Also for v5 super block, we can enabled both group and project quota at
the same time, in this case the current error handling will cover the
group error with projects but they might failed due to different reasons.

It seems we'd better the error handling consistent to the user space and
don't trying to remove another kind of quota metadata if the previous
operation is failed.

Signed-off-by: Jie Liu <jeff.liu@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ben Myers <bpm@sgi.com>
This commit is contained in:
Jie Liu 2013-11-22 14:04:00 +08:00 committed by Ben Myers
parent ef701600fd
commit c61a9e39f6
1 changed files with 12 additions and 6 deletions

View File

@ -278,7 +278,7 @@ xfs_qm_scall_trunc_qfiles(
xfs_mount_t *mp,
uint flags)
{
int error = 0, error2 = 0;
int error;
if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0) {
xfs_debug(mp, "%s: flags=%x m_qflags=%x",
@ -286,14 +286,20 @@ xfs_qm_scall_trunc_qfiles(
return XFS_ERROR(EINVAL);
}
if (flags & XFS_DQ_USER)
if (flags & XFS_DQ_USER) {
error = xfs_qm_scall_trunc_qfile(mp, mp->m_sb.sb_uquotino);
if (flags & XFS_DQ_GROUP)
error2 = xfs_qm_scall_trunc_qfile(mp, mp->m_sb.sb_gquotino);
if (error)
return error;
}
if (flags & XFS_DQ_GROUP) {
error = xfs_qm_scall_trunc_qfile(mp, mp->m_sb.sb_gquotino);
if (error)
return error;
}
if (flags & XFS_DQ_PROJ)
error2 = xfs_qm_scall_trunc_qfile(mp, mp->m_sb.sb_pquotino);
error = xfs_qm_scall_trunc_qfile(mp, mp->m_sb.sb_pquotino);
return error ? error : error2;
return error;
}
/*