can: j1939: prevent deadlock by changing j1939_socks_lock to rwlock

The following 3 locks would race against each other, causing the
deadlock situation in the Syzbot bug report:

- j1939_socks_lock
- active_session_list_lock
- sk_session_queue_lock

A reasonable fix is to change j1939_socks_lock to an rwlock, since in
the rare situations where a write lock is required for the linked list
that j1939_socks_lock is protecting, the code does not attempt to
acquire any more locks. This would break the circular lock dependency,
where, for example, the current thread already locks j1939_socks_lock
and attempts to acquire sk_session_queue_lock, and at the same time,
another thread attempts to acquire j1939_socks_lock while holding
sk_session_queue_lock.

NOTE: This patch along does not fix the unregister_netdevice bug
reported by Syzbot; instead, it solves a deadlock situation to prepare
for one or more further patches to actually fix the Syzbot bug, which
appears to be a reference counting problem within the j1939 codebase.

Reported-by: <syzbot+1591462f226d9cbf0564@syzkaller.appspotmail.com>
Signed-off-by: Ziqi Zhao <astrajoan@yahoo.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/all/20230721162226.8639-1-astrajoan@yahoo.com
[mkl: remove unrelated newline change]
Cc: stable@vger.kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>

diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index 16af1a7f80f60e18b5526c973f66e98821786a78..74f15592d17083f44b32d52eb706b0fb2b800534 100644 (file)
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -86,7 +86,7 @@ struct j1939_priv {
        unsigned int tp_max_packet_size;
 
        /* lock for j1939_socks list */
-       spinlock_t j1939_socks_lock;
+       rwlock_t j1939_socks_lock;
        struct list_head j1939_socks;
 
        struct kref rx_kref;

diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index ecff1c947d683b2f3e4eeff144f39a8f5ff5de1a..a6fb89fa62785121f9edc42308b052142fda5fdd 100644 (file)
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev)
                return ERR_PTR(-ENOMEM);
 
        j1939_tp_init(priv);
-       spin_lock_init(&priv->j1939_socks_lock);
+       rwlock_init(&priv->j1939_socks_lock);
        INIT_LIST_HEAD(&priv->j1939_socks);
 
        mutex_lock(&j1939_netdev_lock);

diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 14c43166323393541bc102f47a311c79199a2acd..94cfc2315e546e4a0db32a69d2bfa0b1a6275544 100644 (file)
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk)
        jsk->state |= J1939_SOCK_BOUND;
        j1939_priv_get(priv);
 
-       spin_lock_bh(&priv->j1939_socks_lock);
+       write_lock_bh(&priv->j1939_socks_lock);
        list_add_tail(&jsk->list, &priv->j1939_socks);
-       spin_unlock_bh(&priv->j1939_socks_lock);
+       write_unlock_bh(&priv->j1939_socks_lock);
 }
 
 static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk)
 {
-       spin_lock_bh(&priv->j1939_socks_lock);
+       write_lock_bh(&priv->j1939_socks_lock);
        list_del_init(&jsk->list);
-       spin_unlock_bh(&priv->j1939_socks_lock);
+       write_unlock_bh(&priv->j1939_socks_lock);
 
        j1939_priv_put(priv);
        jsk->state &= ~J1939_SOCK_BOUND;
@@ -329,13 +329,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb)
        struct j1939_sock *jsk;
        bool match = false;
 
-       spin_lock_bh(&priv->j1939_socks_lock);
+       read_lock_bh(&priv->j1939_socks_lock);
        list_for_each_entry(jsk, &priv->j1939_socks, list) {
                match = j1939_sk_recv_match_one(jsk, skcb);
                if (match)
                        break;
        }
-       spin_unlock_bh(&priv->j1939_socks_lock);
+       read_unlock_bh(&priv->j1939_socks_lock);
 
        return match;
 }
@@ -344,11 +344,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb)
 {
        struct j1939_sock *jsk;
 
-       spin_lock_bh(&priv->j1939_socks_lock);
+       read_lock_bh(&priv->j1939_socks_lock);
        list_for_each_entry(jsk, &priv->j1939_socks, list) {
                j1939_sk_recv_one(jsk, skb);
        }
-       spin_unlock_bh(&priv->j1939_socks_lock);
+       read_unlock_bh(&priv->j1939_socks_lock);
 }
 
 static void j1939_sk_sock_destruct(struct sock *sk)
@@ -1080,12 +1080,12 @@ void j1939_sk_errqueue(struct j1939_session *session,
        }
 
        /* spread RX notifications to all sockets subscribed to this session */
-       spin_lock_bh(&priv->j1939_socks_lock);
+       read_lock_bh(&priv->j1939_socks_lock);
        list_for_each_entry(jsk, &priv->j1939_socks, list) {
                if (j1939_sk_recv_match_one(jsk, &session->skcb))
                        __j1939_sk_errqueue(session, &jsk->sk, type);
        }
-       spin_unlock_bh(&priv->j1939_socks_lock);
+       read_unlock_bh(&priv->j1939_socks_lock);
 };
 
 void j1939_sk_send_loop_abort(struct sock *sk, int err)
@@ -1273,7 +1273,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
        struct j1939_sock *jsk;
        int error_code = ENETDOWN;
 
-       spin_lock_bh(&priv->j1939_socks_lock);
+       read_lock_bh(&priv->j1939_socks_lock);
        list_for_each_entry(jsk, &priv->j1939_socks, list) {
                jsk->sk.sk_err = error_code;
                if (!sock_flag(&jsk->sk, SOCK_DEAD))
@@ -1281,7 +1281,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
 
                j1939_sk_queue_drop_all(priv, jsk, error_code);
        }
-       spin_unlock_bh(&priv->j1939_socks_lock);
+       read_unlock_bh(&priv->j1939_socks_lock);
 }
 
 static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd,