diff options
author | 2019-12-06 16:07:32 -0500 | |
---|---|---|
committer | 2019-12-09 11:44:07 -0500 | |
commit | d781e3df710745fbbaee4eb07fd5b64331a1b175 (patch) | |
tree | b9b95fce122ce1041e0aa379944d3c2eb6912f9b /tools/perf/scripts/python/export-to-postgresql.py | |
parent | NFSD fixing possible null pointer derefering in copy offload (diff) | |
download | linux-dev-d781e3df710745fbbaee4eb07fd5b64331a1b175.tar.xz linux-dev-d781e3df710745fbbaee4eb07fd5b64331a1b175.zip |
nfsd4: avoid NULL deference on strange COPY compounds
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@oracle.com>
Fixes: 4e48f1cccab3 "NFSD: allow inter server COPY to have... "
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Diffstat (limited to 'tools/perf/scripts/python/export-to-postgresql.py')
0 files changed, 0 insertions, 0 deletions