On Fri, Dec 6, 2019 at 4:15 PM J. Bruce Fields <bfields@xxxxxxxxxxxx> wrote: > > On Fri, Dec 06, 2019 at 04:14:42PM -0500, bfields wrote: > > On Wed, Dec 04, 2019 at 09:38:26PM -0500, J. Bruce Fields wrote: > > > So, stuff we could do: > > > > > > - add an extra check of fh_export or something here. > > > > So, I'm applying the following for now. > > + if (current->fh->fh_export && > ^^^ > > Um, maybe with a typo or two fixed. > > > > + need_wrongsec_check(rqstp)) > > op->status = check_nfsd_access(current_fh->fh_export, rqstp); > > } > > encode_op: Sure thing. But I just finished up and have hacked up the client to send a GETATTR after the 1st PUTFH in the COPY compound of the inter copy. The server doesn't croak but returns an ERR_STALE on the 1st PUTFH (I believe this is due to the logic that it's not a valid inter COPY compound.. so logic works). but I have nothing against adding the check.
