Re: [PATCH 4.19 011/191] nfsd4: avoid NULL deference on strange COPY compounds

[Sasha Levin]

On Fri, Feb 21, 2020 at 11:51:04AM +0100, Pavel Machek wrote:
> Hi!
>
> > With cross-server COPY we've introduced the possibility that the current
> > or saved filehandle might not have fh_dentry/fh_export filled in, but we
> > missed a place that assumed it was.  I think this could be triggered by
> > a compound like:
> >
> > 	PUTFH(foreign filehandle)
> > 	GETATTR
> > 	SAVEFH
> > 	COPY
> >
> > First, check_if_stalefh_allowed sets no_verify on the first (PUTFH) op.
> > Then op_func = nfsd4_putfh runs and leaves current_fh->fh_export NULL.
> > need_wrongsec_check returns true, since this PUTFH has OP_IS_PUTFH_LIKE
> > set and GETATTR does not have OP_HANDLES_WRONGSEC set.
> >
> > We should probably also consider tightening the checks in
> > check_if_stalefh_allowed and double-checking that we don't assume the
> > filehandle is verified elsewhere in the compound.  But I think this
> > fixes the immediate issue.
> >
> > Reported-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
> > Fixes: 4e48f1cccab3 "NFSD: allow inter server COPY to have... "
>
> AFAICT 4e48f1cccab3 "NFSD: allow inter server COPY to have... " is not
> part of 4.19 series, so this should not be needed in 4.19.

Not only 4e48f1cccab3 isn't in 4.19, it isn't in any tree! :)

Looks like an error in the patch, I'll drop this commit from everywhere.

--
Thanks,
Sasha