[PATCH 7/7] NLM: Add reference counting to lockd

[Jeff Layton]

...and only have lockd exit when the last reference is dropped.

The problem is this:

When a lock that a client is blocking on comes free, lockd does this in
nlmsvc_grant_blocked():

    nlm_async_call(block->b_call, NLMPROC_GRANTED_MSG, &nlmsvc_grant_ops);

the callback from this call is nlmsvc_grant_callback(). That function
does this at the end to wake up lockd:

    svc_wake_up(block->b_daemon);

However there is no guarantee that lockd will be up when this happens.
If someone shuts down or restarts lockd before the async call completes,
then the b_daemon pointer will point to freed memory and the kernel may
oops.

I first noticed this on older kernels and had mistakenly thought that
newer kernels weren't susceptible, but that's not correct. There's a bit
of a race to make sure that the nlm_host is bound when the async call is
done, but I can now reproduce this at will on current kernels.

This patch is based on Trond's suggestion to add a new reference counter
to lockd, and only allows lockd to go down when it reaches 0. With this
change we can't use kthread_stop here. nlmsvc_unlink_block is called by
lockd and a kthread can't call kthread_stop on itself. So the patch
changes lockd to check the refcount itself and to return if it goes to
0. We do the checking and exit while holding the nlmsvc_mutex to make
sure that a new lockd is not started until the old one is down.

Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxx>
---
 fs/lockd/svc.c              |   51 ++++++++++++++++++++++++++++++++----------
 fs/lockd/svclock.c          |    5 ++++
 include/linux/lockd/lockd.h |    1 +
 3 files changed, 45 insertions(+), 12 deletions(-)

diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 28c290c..3c56827 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -51,6 +51,7 @@ static DEFINE_MUTEX(nlmsvc_mutex);
 static unsigned int		nlmsvc_users;
 static struct task_struct *	nlmsvc_task;
 static struct svc_serv *	nlmsvc_serv;
+atomic_t			nlmsvc_ref = ATOMIC_INIT(0);
 int				nlmsvc_grace_period;
 unsigned long			nlmsvc_timeout;
 
@@ -134,7 +135,10 @@ lockd(struct svc_rqst *rqstp)
 
 	set_freezable();
 
-	/* Process request with signals blocked, but allow SIGKILL.  */
+	/*
+	 * Process request with signals blocked, but allow SIGKILL which
+	 * signifies that lockd should drop all of its locks.
+	 */
 	allow_signal(SIGKILL);
 
 	dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n");
@@ -147,15 +151,19 @@ lockd(struct svc_rqst *rqstp)
 
 	/*
 	 * The main request loop. We don't terminate until the last
-	 * NFS mount or NFS daemon has gone away, and we've been sent a
-	 * signal, or else another process has taken over our job.
+	 * NFS mount or NFS daemon has gone away, and the nlm_blocked
+	 * list is empty. The nlmsvc_mutex ensures that we prevent a
+	 * new lockd from being started before the old one is down.
 	 */
-	while (!kthread_should_stop()) {
+	mutex_lock(&nlmsvc_mutex);
+	while (atomic_read(&nlmsvc_ref) != 0) {
 		long timeout = MAX_SCHEDULE_TIMEOUT;
 		char buf[RPC_MAX_ADDRBUFLEN];
 
+		mutex_unlock(&nlmsvc_mutex);
+
 		if (try_to_freeze())
-			continue;
+			goto again;
 
 		if (signalled()) {
 			flush_signals(current);
@@ -182,11 +190,12 @@ lockd(struct svc_rqst *rqstp)
 		 */
 		err = svc_recv(rqstp, timeout);
 		if (err == -EAGAIN || err == -EINTR)
-			continue;
+			goto again;
 		if (err < 0) {
 			printk(KERN_WARNING
 			       "lockd: terminating on error %d\n",
 			       -err);
+			mutex_lock(&nlmsvc_mutex);
 			break;
 		}
 
@@ -194,19 +203,22 @@ lockd(struct svc_rqst *rqstp)
 				svc_print_addr(rqstp, buf, sizeof(buf)));
 
 		svc_process(rqstp);
+again:
+		mutex_lock(&nlmsvc_mutex);
 	}
 
-	flush_signals(current);
-
 	/*
-	 * Check whether there's a new lockd process before
-	 * shutting down the hosts and clearing the slot.
-	 */
+	 * at this point lockd is committed to going down. We hold the
+	 * nlmsvc_mutex until just before exit to prevent a new one
+	 * from starting before it's down.
+ 	 */
+	flush_signals(current);
 	if (nlmsvc_ops)
 		nlmsvc_invalidate_all();
 	nlm_shutdown_hosts();
 	nlmsvc_task = NULL;
 	nlmsvc_serv = NULL;
+	mutex_unlock(&nlmsvc_mutex);
 
 	/* Exit the RPC thread */
 	svc_exit_thread(rqstp);
@@ -268,6 +280,10 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
 	int			error = 0;
 
 	mutex_lock(&nlmsvc_mutex);
+
+	if (!nlmsvc_users)
+		atomic_inc(&nlmsvc_ref);
+
 	/*
 	 * Check whether we're already up and running.
 	 */
@@ -324,6 +340,8 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
 destroy_and_out:
 	svc_destroy(serv);
 out:
+	if (!nlmsvc_users && error)
+		atomic_dec(&nlmsvc_ref);
 	if (!error)
 		nlmsvc_users++;
 	mutex_unlock(&nlmsvc_mutex);
@@ -352,7 +370,16 @@ lockd_down(void)
 		goto out;
 	}
 	warned = 0;
-	kthread_stop(nlmsvc_task);
+	atomic_dec(&nlmsvc_ref);
+
+	/*
+	 * Sending a signal is necessary here. If we get to this point and
+	 * nlm_blocked isn't empty then lockd may be held hostage by clients
+	 * that are still blocking. Sending the signal makes sure that lockd
+	 * invalidates all of its locks so that it's just waiting on RPC
+	 * callbacks to complete
+	 */
+	kill_proc(nlmsvc_task->pid, SIGKILL, 1);
 out:
 	mutex_unlock(&nlmsvc_mutex);
 }
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index d120ec3..b8fbda3 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -61,6 +61,9 @@ nlmsvc_insert_block(struct nlm_block *block, unsigned long when)
 	struct list_head *pos;
 
 	dprintk("lockd: nlmsvc_insert_block(%p, %ld)\n", block, when);
+	if (list_empty(&nlm_blocked))
+		atomic_inc(&nlmsvc_ref);
+
 	if (list_empty(&block->b_list)) {
 		kref_get(&block->b_count);
 	} else {
@@ -239,6 +242,8 @@ static int nlmsvc_unlink_block(struct nlm_block *block)
 	/* Remove block from list */
 	status = posix_unblock_lock(block->b_file->f_file, &block->b_call->a_args.lock.fl);
 	nlmsvc_remove_block(block);
+	if (list_empty(&nlm_blocked))
+		atomic_dec(&nlmsvc_ref);
 	return status;
 }
 
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index e2d1ce3..7389553 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -154,6 +154,7 @@ extern struct svc_procedure	nlmsvc_procedures4[];
 extern int			nlmsvc_grace_period;
 extern unsigned long		nlmsvc_timeout;
 extern int			nsm_use_hostnames;
+extern atomic_t			nlmsvc_ref;
 
 /*
  * Lockd client functions
-- 
1.5.3.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/