can: j1939: implement NETDEV_UNREGISTER notification handler

syzbot is reporting

  unregister_netdevice: waiting for vcan0 to become free. Usage count = 2

problem, for j1939 protocol did not have NETDEV_UNREGISTER notification
handler for undoing changes made by j1939_sk_bind().

Commit 25fe97c ("can: j1939: move j1939_priv_put() into sk_destruct
callback") expects that a call to j1939_priv_put() can be unconditionally
delayed until j1939_sk_sock_destruct() is called. But we need to call
j1939_priv_put() against an extra ref held by j1939_sk_bind() call
(as a part of undoing changes made by j1939_sk_bind()) as soon as
NETDEV_UNREGISTER notification fires (i.e. before j1939_sk_sock_destruct()
is called via j1939_sk_release()). Otherwise, the extra ref on "struct
j1939_priv" held by j1939_sk_bind() call prevents "struct net_device" from
dropping the usage count to 1; making it impossible for
unregister_netdevice() to continue.

Reported-by: syzbot <[email protected]>
Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84
Tested-by: syzbot <[email protected]>
Fixes: 9d71dd0 ("can: add support of SAE J1939 protocol")
Fixes: 25fe97c ("can: j1939: move j1939_priv_put() into sk_destruct callback")
Signed-off-by: Tetsuo Handa <[email protected]>
Tested-by: Oleksij Rempel <[email protected]>
Acked-by: Oleksij Rempel <[email protected]>
Link: https://patch.msgid.link/[email protected]
[mkl: remove space in front of label]
Signed-off-by: Marc Kleine-Budde <[email protected]>

Author: Tetsuo Handa

net/can/j1939/j1939-priv.h

@@ -212,6 +212,7 @@ void j1939_priv_get(struct j1939_priv *priv);
 
 /* notify/alert all j1939 sockets bound to ifindex */
 void j1939_sk_netdev_event_netdown(struct j1939_priv *priv);
+void j1939_sk_netdev_event_unregister(struct j1939_priv *priv);
 int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk);
 void j1939_tp_init(struct j1939_priv *priv);
 

net/can/j1939/main.c

@@ -377,6 +377,9 @@ static int j1939_netdev_notify(struct notifier_block *nb,
 		j1939_sk_netdev_event_netdown(priv);
 		j1939_ecu_unmap_all(priv);
 		break;
+	case NETDEV_UNREGISTER:
+		j1939_sk_netdev_event_unregister(priv);
+		break;
 	}
 
 	j1939_priv_put(priv);

net/can/j1939/socket.c

@@ -1300,6 +1300,55 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
 	read_unlock_bh(&priv->j1939_socks_lock);
 }
 
+void j1939_sk_netdev_event_unregister(struct j1939_priv *priv)
+{
+	struct sock *sk;
+	struct j1939_sock *jsk;
+	bool wait_rcu = false;
+
+rescan: /* The caller is holding a ref on this "priv" via j1939_priv_get_by_ndev(). */
+	read_lock_bh(&priv->j1939_socks_lock);
+	list_for_each_entry(jsk, &priv->j1939_socks, list) {
+		/* Skip if j1939_jsk_add() is not called on this socket. */
+		if (!(jsk->state & J1939_SOCK_BOUND))
+			continue;
+		sk = &jsk->sk;
+		sock_hold(sk);
+		read_unlock_bh(&priv->j1939_socks_lock);
+		/* Check if j1939_jsk_del() is not yet called on this socket after holding
+		 * socket's lock, for both j1939_sk_bind() and j1939_sk_release() call
+		 * j1939_jsk_del() with socket's lock held.
+		 */
+		lock_sock(sk);
+		if (jsk->state & J1939_SOCK_BOUND) {
+			/* Neither j1939_sk_bind() nor j1939_sk_release() called j1939_jsk_del().
+			 * Make this socket no longer bound, by pretending as if j1939_sk_bind()
+			 * dropped old references but did not get new references.
+			 */
+			j1939_jsk_del(priv, jsk);
+			j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa);
+			j1939_netdev_stop(priv);
+			/* Call j1939_priv_put() now and prevent j1939_sk_sock_destruct() from
+			 * calling the corresponding j1939_priv_put().
+			 *
+			 * j1939_sk_sock_destruct() is supposed to call j1939_priv_put() after
+			 * an RCU grace period. But since the caller is holding a ref on this
+			 * "priv", we can defer synchronize_rcu() until immediately before
+			 * the caller calls j1939_priv_put().
+			 */
+			j1939_priv_put(priv);
+			jsk->priv = NULL;
+			wait_rcu = true;
+		}
+		release_sock(sk);
+		sock_put(sk);
+		goto rescan;
+	}
+	read_unlock_bh(&priv->j1939_socks_lock);
+	if (wait_rcu)
+		synchronize_rcu();
+}
+
 static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd,
 				unsigned long arg)
 {