From: Oliver Hartkopp Date: Tue, 14 Jul 2026 16:55:31 +0000 (+0200) Subject: can: bcm: fix stale rx/tx ops after device removal X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=3b762c0d950383ab7a002686c9136b9aa55d2d70;p=thirdparty%2Fkernel%2Flinux.git can: bcm: fix stale rx/tx ops after device removal RX: an RX_SETUP update(!) for an existing op skipped can_rx_register() unconditionally, even when a concurrent NETDEV_UNREGISTER had already torn down its registration (op->rx_reg_dev == NULL). This silently did not re-enable frame delivery for that updated filter. bcm_rx_setup() now re-registers in that case, while leaving rx_ops with ifindex = 0 (all CAN devices) which never carry a tracked rx_reg_dev registered as-is. TX: bcm_notify() only handled bo->rx_ops on NETDEV_UNREGISTER, leaving tx_ops with an active cyclic transmission re-arming its hrtimer indefinitely to execute bcm_tx_timeout_handler(). Cancelling the hrtimer prevents the runaway timer and any injection into a later reused ifindex, since nothing else calls bcm_can_tx() for the op until an explicit TX_SETUP update re-arms it. Unlike bcm_rx_unreg(), which clears the tracked rx_reg_dev for rx_ops, the ifindex is intentionally left unchanged for tx_ops. bcm_tx_setup() always rejects ifindex 0, so clearing it would strand the op: neither a later TX_SETUP (bcm_find_op()) nor TX_DELETE (bcm_delete_tx_op()) could ever find it again, since both require an exact ifindex match. Reported-by: sashiko-bot@kernel.org Closes: https://lore.kernel.org/linux-can/20260708094536.DDF821F00A3A@smtp.kernel.org/ Closes: https://lore.kernel.org/linux-can/20260708154039.347ED1F000E9@smtp.kernel.org/ Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol") Signed-off-by: Oliver Hartkopp Link: https://patch.msgid.link/20260714-bcm_fixes-v15-9-562f7e3e42da@hartkopp.net Cc: stable@kernel.org Signed-off-by: Marc Kleine-Budde --- diff --git a/net/can/bcm.c b/net/can/bcm.c index 25842061800b..a53dba6ab8b8 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1287,6 +1287,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; int do_rx_register; + int new_op = 0; int err = 0; if ((msg_head->flags & RX_FILTER_ID) || (!(msg_head->nframes))) { @@ -1371,8 +1372,15 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* free temporary frames / kfree(NULL) is safe */ kfree(new_frames); - /* Only an update -> do not call can_rx_register() */ - do_rx_register = 0; + /* Don't register a new CAN filter for the rx_op update unless + * a concurrent NETDEV_UNREGISTER notifier already tore down + * the previous registration. In this case the receiver needs + * to be re-registered here so that this update doesn't + * silently stop delivering frames for the given ifindex. + * Ops with ifindex = 0 (all CAN interfaces) never carry a + * tracked rx_reg_dev and stay registered as-is. + */ + do_rx_register = (ifindex && !op->rx_reg_dev) ? 1 : 0; } else { /* insert new BCM operation for the given can_id */ @@ -1439,6 +1447,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* call can_rx_register() */ do_rx_register = 1; + new_op = 1; } /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */ @@ -1452,7 +1461,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (op->flags & SETTIMER) { /* set timers (locked) for newly created op */ - if (do_rx_register) { + if (new_op) { spin_lock_bh(&op->bcm_rx_update_lock); op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; @@ -1482,7 +1491,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, HRTIMER_MODE_REL_SOFT); } - /* now we can register for can_ids, if we added a new bcm_op */ + /* now we can register for can_ids, if we added a new bcm_op + * or need to re-register after a NETDEV_UNREGISTER tore down + * the previous registration of an existing op + */ if (do_rx_register) { if (ifindex) { struct net_device *dev; @@ -1514,18 +1526,32 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, err = -ENODEV; } - } else + } else { err = can_rx_register(sock_net(sk), NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); + } + if (err) { - /* this bcm rx op is broken -> remove it */ - bcm_remove_op(op); + /* newly created bcm rx op is broken -> remove it */ + if (new_op) { + bcm_remove_op(op); + return err; + } + + /* an existing op just stays unregistered. + * Cancel op->timer and (defensively) op->thrtimer. + * Other settings can't be reached until the next + * successful RX_SETUP. + */ + hrtimer_cancel(&op->timer); + hrtimer_cancel(&op->thrtimer); return err; } - /* add this bcm_op to the list of the rx_ops */ - list_add_rcu(&op->list, &bo->rx_ops); + /* add a new bcm_op to the list of the rx_ops */ + if (new_op) + list_add_rcu(&op->list, &bo->rx_ops); } return msg_head->nframes * op->cfsiz + MHSIZ; @@ -1745,11 +1771,19 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); - /* remove device specific receive entries */ + /* rx_ops: remove device specific receive entries */ list_for_each_entry(op, &bo->rx_ops, list) if (op->rx_reg_dev == dev) bcm_rx_unreg(dev, op); + /* tx_ops: stop device specific cyclic transmissions on the + * vanishing ifindex. Cancelling the timer is enough to stop + * cyclic bcm_can_tx() calls as there is no re-arming. + */ + list_for_each_entry(op, &bo->tx_ops, list) + if (op->ifindex == dev->ifindex) + hrtimer_cancel(&op->timer); + /* remove device reference, if this is our bound device */ if (bo->bound && bo->ifindex == dev->ifindex) { #if IS_ENABLED(CONFIG_PROC_FS)