From 7fcbe5b2c6a4b5407bf2241fdb71e0a390f6ab9a Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 25 Aug 2025 23:07:24 +0900 Subject: 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 25fe97cb7620 ("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 Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84 Tested-by: syzbot Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Fixes: 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct callback") Signed-off-by: Tetsuo Handa Tested-by: Oleksij Rempel Acked-by: Oleksij Rempel Link: https://patch.msgid.link/ac9db9a4-6c30-416e-8b94-96e6559d55b2@I-love.SAKURA.ne.jp [mkl: remove space in front of label] Signed-off-by: Marc Kleine-Budde --- net/can/j1939/j1939-priv.h | 1 + net/can/j1939/main.c | 3 +++ net/can/j1939/socket.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 53 insertions(+) (limited to 'net') diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 31a93cae5111..81f58924b4ac 100644 --- a/net/can/j1939/j1939-priv.h +++ b/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); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 7e8a20f2fc42..3706a872ecaf 100644 --- a/net/can/j1939/main.c +++ b/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); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 3d8b588822f9..70ebc861ea2a 100644 --- a/net/can/j1939/socket.c +++ b/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) { -- cgit v1.2.3 From f214744c8a27c3c1da6b538c232da22cd027530e Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sun, 24 Aug 2025 19:30:09 +0900 Subject: can: j1939: j1939_sk_bind(): call j1939_priv_put() immediately when j1939_local_ecu_get() failed Commit 25fe97cb7620 ("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 a refcount leak will happen when j1939_sk_bind() is called again after j1939_local_ecu_get() from previous j1939_sk_bind() call returned an error. We need to call j1939_priv_put() before j1939_sk_bind() returns an error. Fixes: 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct callback") Signed-off-by: Tetsuo Handa Tested-by: Oleksij Rempel Acked-by: Oleksij Rempel Link: https://patch.msgid.link/4f49a1bc-a528-42ad-86c0-187268ab6535@I-love.SAKURA.ne.jp Signed-off-by: Marc Kleine-Budde --- net/can/j1939/socket.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 70ebc861ea2a..88e7160d4248 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -521,6 +521,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa); if (ret) { j1939_netdev_stop(priv); + jsk->priv = NULL; + synchronize_rcu(); + j1939_priv_put(priv); goto out_release_sock; } -- cgit v1.2.3 From 06e02da29f6f1a45fc07bd60c7eaf172dc21e334 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sun, 24 Aug 2025 19:27:40 +0900 Subject: can: j1939: j1939_local_ecu_get(): undo increment when j1939_local_ecu_get() fails Since j1939_sk_bind() and j1939_sk_release() call j1939_local_ecu_put() when J1939_SOCK_BOUND was already set, but the error handling path for j1939_sk_bind() will not set J1939_SOCK_BOUND when j1939_local_ecu_get() fails, j1939_local_ecu_get() needs to undo priv->ents[sa].nusers++ when j1939_local_ecu_get() returns an error. Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Signed-off-by: Tetsuo Handa Tested-by: Oleksij Rempel Acked-by: Oleksij Rempel Link: https://patch.msgid.link/e7f80046-4ff7-4ce2-8ad8-7c3c678a42c9@I-love.SAKURA.ne.jp Signed-off-by: Marc Kleine-Budde --- net/can/j1939/bus.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c index 39844f14eed8..797719cb227e 100644 --- a/net/can/j1939/bus.c +++ b/net/can/j1939/bus.c @@ -290,8 +290,11 @@ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa) if (!ecu) ecu = j1939_ecu_create_locked(priv, name); err = PTR_ERR_OR_ZERO(ecu); - if (err) + if (err) { + if (j1939_address_is_unicast(sa)) + priv->ents[sa].nusers--; goto done; + } ecu->nusers++; /* TODO: do we care if ecu->addr != sa? */ -- cgit v1.2.3