diff options
author | Trond Myklebust <Trond.Myklebust@netapp.com> | 2013-08-05 12:06:12 -0400 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2013-08-14 22:59:08 -0700 |
commit | 870bfc6b47ecf64845dbf8e5d7a09877998e1b69 (patch) | |
tree | 8dbee6080950eaf16772d2fb1ac9b38f127b1178 /fs/read_write.c | |
parent | 31a9bd79d76026a8c8cff63c6887483e2e766ee4 (diff) | |
download | kernel-common-870bfc6b47ecf64845dbf8e5d7a09877998e1b69.tar.gz kernel-common-870bfc6b47ecf64845dbf8e5d7a09877998e1b69.tar.bz2 kernel-common-870bfc6b47ecf64845dbf8e5d7a09877998e1b69.zip |
LOCKD: Don't call utsname()->nodename from nlmclnt_setlockargs
commit 9a1b6bf818e74bb7aabaecb59492b739f2f4d742 upstream.
Firstly, nlmclnt_setlockargs can be called from a reclaimer thread, in
which case we're in entirely the wrong namespace.
Secondly, commit 8aac62706adaaf0fab02c4327761561c8bda9448 (move
exit_task_namespaces() outside of exit_notify()) now means that
exit_task_work() is called after exit_task_namespaces(), which
triggers an Oops when we're freeing up the locks.
Fix this by ensuring that we initialise the nlm_host's rpc_client at mount
time, so that the cl_nodename field is initialised to the value of
utsname()->nodename that the net namespace uses. Then replace the
lockd callers of utsname()->nodename.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Toralf Förster <toralf.foerster@gmx.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Nix <nix@esperi.org.uk>
Cc: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'fs/read_write.c')
0 files changed, 0 insertions, 0 deletions