[PATCH v10 2/3] can: isotp: fix use-after-free race with concurrent NETDEV_UNREGISTER

From: Oliver Hartkopp <[email protected]>

isotp_release() looked up the bound network device via dev_get_by_index()
using the stored ifindex. During device unregistration the device is
unlisted from the ifindex hash before the NETDEV_UNREGISTER notifier
chain runs, so a concurrent isotp_release() could find no device, skip
can_rx_unregister() entirely, and still proceed to free the socket.
Since isotp_release() had already removed itself from the isotp
notifier list at that point, isotp_notify() would never get a chance to
clean up either, leaving a stale CAN filter that keeps pointing at the
freed socket.

Fix this the same way raw.c already does: hold a tracked reference to
the bound net_device in the socket (so->dev/so->dev_tracker) from
bind() onward instead of re-resolving it from the ifindex, and
serialize bind()/release() with rtnl_lock() so that so->dev is always
consistent with what the NETDEV_UNREGISTER notifier sees. so->dev
stays valid regardless of ifindex-hash unlisting, and is only ever
cleared by whichever of isotp_release()/isotp_notify() gets there
first, so the filter is always removed exactly once.

isotp_bind() now rejects a (re)bind with -EAGAIN while so->[tx|rx].state
isn't ISOTP_IDLE yet, so a timer left running by a prior
NETDEV_UNREGISTER can't act on a newly bound so->ifindex. Both checks
share the same lock_sock() section, so there is no window in which a
concurrent isotp_notify() clearing so->bound could be missed.

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Reported-by: [email protected]
Link: https://lore.kernel.org/linux-can/[email protected]/
Signed-off-by: Oliver Hartkopp <[email protected]>
---
 net/can/isotp.c | 87 ++++++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 59 insertions(+), 28 deletions(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index d30937345bcd..44c044eb83e1 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -150,10 +150,12 @@ struct tpcon {
 
 struct isotp_sock {
 	struct sock sk;
 	int bound;
 	int ifindex;
+	struct net_device *dev;
+	netdevice_tracker dev_tracker;
 	canid_t txid;
 	canid_t rxid;
 	ktime_t tx_gap;
 	ktime_t lastrxcf_tstamp;
 	struct hrtimer rxtimer, txtimer, txfrtimer;
@@ -976,10 +978,18 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
 		if (err)
 			goto err_event_drop;
 	}
 
+	/* so->bound is only checked once above - a wakeup may have
+	 * unbound/rebound the socket meanwhile, so re-validate it
+	 */
+	if (!so->bound) {
+		err = -EADDRNOTAVAIL;
+		goto err_out_drop;
+	}
+
 	/* PDU size > default => try max_pdu_size */
 	if (size > so->tx.buflen && so->tx.buflen < max_pdu_size) {
 		u8 *newbuf = kmalloc(max_pdu_size, GFP_KERNEL);
 
 		if (newbuf) {
@@ -1217,32 +1227,34 @@ static int isotp_release(struct socket *sock)
 		spin_lock(&isotp_notifier_lock);
 	}
 	list_del(&so->notifier);
 	spin_unlock(&isotp_notifier_lock);
 
+	rtnl_lock();
 	lock_sock(sk);
 
-	/* remove current filters & unregister */
-	if (so->bound) {
-		if (so->ifindex) {
-			struct net_device *dev;
-
-			dev = dev_get_by_index(net, so->ifindex);
-			if (dev) {
-				if (isotp_register_rxid(so))
-					can_rx_unregister(net, dev, so->rxid,
-							  SINGLE_MASK(so->rxid),
-							  isotp_rcv, sk);
-
-				can_rx_unregister(net, dev, so->txid,
-						  SINGLE_MASK(so->txid),
-						  isotp_rcv_echo, sk);
-				dev_put(dev);
-			}
-		}
+	/* remove current filters & unregister
+	 * tracked reference so->dev is taken at bind() time with rtnl_lock
+	 */
+	if (so->bound && so->dev) {
+		if (isotp_register_rxid(so))
+			can_rx_unregister(net, so->dev, so->rxid,
+					  SINGLE_MASK(so->rxid),
+					  isotp_rcv, sk);
+
+		can_rx_unregister(net, so->dev, so->txid,
+				  SINGLE_MASK(so->txid),
+				  isotp_rcv_echo, sk);
+		netdev_put(so->dev, &so->dev_tracker);
 	}
 
+	so->ifindex = 0;
+	so->bound = 0;
+	so->dev = NULL;
+
+	rtnl_unlock();
+
 	/* Always wait for a grace period before touching the timers below.
 	 * A concurrent NETDEV_UNREGISTER may have already unregistered our
 	 * filters and cleared so->bound in isotp_notify() without waiting
 	 * for in-flight isotp_rcv() callers to finish, so this call must not
 	 * be skipped just because so->bound is already 0 here.
@@ -1251,13 +1263,10 @@ static int isotp_release(struct socket *sock)
 
 	hrtimer_cancel(&so->txfrtimer);
 	hrtimer_cancel(&so->txtimer);
 	hrtimer_cancel(&so->rxtimer);
 
-	so->ifindex = 0;
-	so->bound = 0;
-
 	sock_orphan(sk);
 	sock->sk = NULL;
 
 	release_sock(sk);
 	sock_prot_inuse_add(net, sk->sk_prot, -1);
@@ -1308,17 +1317,29 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 	}
 
 	if (!addr->can_ifindex)
 		return -ENODEV;
 
+	rtnl_lock();
 	lock_sock(sk);
 
 	if (so->bound) {
 		err = -EINVAL;
 		goto out;
 	}
 
+	/* A transmission or reception that outlived a previous binding
+	 * (unbound by NETDEV_UNREGISTER) may still be draining; the FC/echo
+	 * and RX watchdog timers bound how long this takes. Checked together
+	 * with so->bound in the same lock_sock() section above, so there is
+	 * no window in which a concurrent isotp_notify() could be missed.
+	 */
+	if (so->tx.state != ISOTP_IDLE || so->rx.state != ISOTP_IDLE) {
+		err = -EAGAIN;
+		goto out;
+	}
+
 	/* ensure different CAN IDs when the rx_id is to be registered */
 	if (isotp_register_rxid(so) && rx_id == tx_id) {
 		err = -EADDRNOTAVAIL;
 		goto out;
 	}
@@ -1327,18 +1348,16 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 	if (!dev) {
 		err = -ENODEV;
 		goto out;
 	}
 	if (dev->type != ARPHRD_CAN) {
-		dev_put(dev);
 		err = -ENODEV;
-		goto out;
+		goto out_put_dev;
 	}
 	if (READ_ONCE(dev->mtu) < so->ll.mtu) {
-		dev_put(dev);
 		err = -EINVAL;
-		goto out;
+		goto out_put_dev;
 	}
 	if (!(dev->flags & IFF_UP))
 		notify_enetdown = 1;
 
 	ifindex = dev->ifindex;
@@ -1352,20 +1371,29 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 
 	/* register for echo skb's */
 	can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id),
 			isotp_rcv_echo, sk, "isotpe", sk);
 
-	dev_put(dev);
-
 	/* switch to new settings */
 	so->ifindex = ifindex;
 	so->rxid = rx_id;
 	so->txid = tx_id;
 	so->bound = 1;
 
+	/* bind() ok -> hold a reference for so->dev so that isotp_release()
+	 * can safely reach the device later, even if a concurrent
+	 * NETDEV_UNREGISTER has already unlisted it by ifindex.
+	 */
+	so->dev = dev;
+	netdev_hold(so->dev, &so->dev_tracker, GFP_KERNEL);
+
+out_put_dev:
+	/* remove potential reference from dev_get_by_index() */
+	dev_put(dev);
 out:
 	release_sock(sk);
+	rtnl_unlock();
 
 	if (notify_enetdown) {
 		sk->sk_err = ENETDOWN;
 		if (!sock_flag(sk, SOCK_DEAD))
 			sk_error_report(sk);
@@ -1564,11 +1592,11 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg,
 	struct sock *sk = &so->sk;
 
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		return;
 
-	if (so->ifindex != dev->ifindex)
+	if (so->dev != dev)
 		return;
 
 	switch (msg) {
 	case NETDEV_UNREGISTER:
 		lock_sock(sk);
@@ -1580,14 +1608,16 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg,
 						  isotp_rcv, sk);
 
 			can_rx_unregister(dev_net(dev), dev, so->txid,
 					  SINGLE_MASK(so->txid),
 					  isotp_rcv_echo, sk);
+			netdev_put(so->dev, &so->dev_tracker);
 		}
 
 		so->ifindex = 0;
 		so->bound  = 0;
+		so->dev = NULL;
 		release_sock(sk);
 
 		sk->sk_err = ENODEV;
 		if (!sock_flag(sk, SOCK_DEAD))
 			sk_error_report(sk);
@@ -1643,10 +1673,11 @@ static int isotp_init(struct sock *sk)
 {
 	struct isotp_sock *so = isotp_sk(sk);
 
 	so->ifindex = 0;
 	so->bound = 0;
+	so->dev = NULL;
 
 	so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS;
 	so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS;
 	so->opt.rx_ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS;
 	so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT;

-- 
2.53.0