LOCKD: Don't call utsname()->nodename from nlmclnt_setlockargs
authorTrond Myklebust <Trond.Myklebust@netapp.com>
Mon, 5 Aug 2013 16:06:12 +0000 (12:06 -0400)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Thu, 15 Aug 2013 05:59:08 +0000 (22:59 -0700)
commit870bfc6b47ecf64845dbf8e5d7a09877998e1b69
tree8dbee6080950eaf16772d2fb1ac9b38f127b1178
parent31a9bd79d76026a8c8cff63c6887483e2e766ee4
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>
fs/lockd/clntlock.c
fs/lockd/clntproc.c