This is a note to let you know that I've just added the patch titled
LOCKD: Don't call utsname()->nodename from nlmclnt_setlockargs
to the 3.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
lockd-don-t-call-utsname-nodename-from-nlmclnt_setlockargs.patch
and it can be found in the queue-3.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <[email protected]> know about it.
>From 9a1b6bf818e74bb7aabaecb59492b739f2f4d742 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <[email protected]>
Date: Mon, 5 Aug 2013 12:06:12 -0400
Subject: LOCKD: Don't call utsname()->nodename from nlmclnt_setlockargs
From: Trond Myklebust <[email protected]>
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 <[email protected]>
Cc: Toralf Förster <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Nix <[email protected]>
Cc: Jeff Layton <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
---
fs/lockd/clntlock.c | 13 +++++++++----
fs/lockd/clntproc.c | 5 +++--
2 files changed, 12 insertions(+), 6 deletions(-)
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -64,12 +64,17 @@ struct nlm_host *nlmclnt_init(const stru
nlm_init->protocol, nlm_version,
nlm_init->hostname, nlm_init->noresvport,
nlm_init->net);
- if (host == NULL) {
- lockd_down(nlm_init->net);
- return ERR_PTR(-ENOLCK);
- }
+ if (host == NULL)
+ goto out_nohost;
+ if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL)
+ goto out_nobind;
return host;
+out_nobind:
+ nlmclnt_release_host(host);
+out_nohost:
+ lockd_down(nlm_init->net);
+ return ERR_PTR(-ENOLCK);
}
EXPORT_SYMBOL_GPL(nlmclnt_init);
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -125,14 +125,15 @@ static void nlmclnt_setlockargs(struct n
{
struct nlm_args *argp = &req->a_args;
struct nlm_lock *lock = &argp->lock;
+ char *nodename = req->a_host->h_rpcclnt->cl_nodename;
nlmclnt_next_cookie(&argp->cookie);
memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct
nfs_fh));
- lock->caller = utsname()->nodename;
+ lock->caller = nodename;
lock->oh.data = req->a_owner;
lock->oh.len = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s",
(unsigned int)fl->fl_u.nfs_fl.owner->pid,
- utsname()->nodename);
+ nodename);
lock->svid = fl->fl_u.nfs_fl.owner->pid;
lock->fl.fl_start = fl->fl_start;
lock->fl.fl_end = fl->fl_end;
Patches currently in stable-queue which might be from
[email protected] are
queue-3.10/lockd-don-t-call-utsname-nodename-from-nlmclnt_setlockargs.patch
queue-3.10/sunrpc-if-the-rpcbind-channel-is-disconnected-fail-the-call-to-unregister.patch
queue-3.10/sunrpc-don-t-auto-disconnect-from-the-local-rpcbind-socket.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
