From fb855e9f3b6b42c72af3f1eb0b288998fe0d5ebb Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 1 Dec 2022 08:34:26 +0100 Subject: can: slcan: fix freed work crash The LTP test pty03 is causing a crash in slcan: BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 348 Comm: kworker/0:3 Not tainted 6.0.8-1-default #1 openSUSE Tumbleweed 9d20364b934f5aab0a9bdf84e8f45cfdfae39dab Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b-rebuilt.opensuse.org 04/01/2014 Workqueue: 0x0 (events) RIP: 0010:process_one_work (/home/rich/kernel/linux/kernel/workqueue.c:706 /home/rich/kernel/linux/kernel/workqueue.c:2185) Code: 49 89 ff 41 56 41 55 41 54 55 53 48 89 f3 48 83 ec 10 48 8b 06 48 8b 6f 48 49 89 c4 45 30 e4 a8 04 b8 00 00 00 00 4c 0f 44 e0 <49> 8b 44 24 08 44 8b a8 00 01 00 00 41 83 e5 20 f6 45 10 04 75 0e RSP: 0018:ffffaf7b40f47e98 EFLAGS: 00010046 RAX: 0000000000000000 RBX: ffff9d644e1b8b48 RCX: ffff9d649e439968 RDX: 00000000ffff8455 RSI: ffff9d644e1b8b48 RDI: ffff9d64764aa6c0 RBP: ffff9d649e4335c0 R08: 0000000000000c00 R09: ffff9d64764aa734 R10: 0000000000000007 R11: 0000000000000001 R12: 0000000000000000 R13: ffff9d649e4335e8 R14: ffff9d64490da780 R15: ffff9d64764aa6c0 FS: 0000000000000000(0000) GS:ffff9d649e400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 0000000036424000 CR4: 00000000000006f0 Call Trace: worker_thread (/home/rich/kernel/linux/kernel/workqueue.c:2436) kthread (/home/rich/kernel/linux/kernel/kthread.c:376) ret_from_fork (/home/rich/kernel/linux/arch/x86/entry/entry_64.S:312) Apparently, the slcan's tx_work is freed while being scheduled. While slcan_netdev_close() (netdev side) calls flush_work(&sl->tx_work), slcan_close() (tty side) does not. So when the netdev is never set UP, but the tty is stuffed with bytes and forced to wakeup write, the work is scheduled, but never flushed. So add an additional flush_work() to slcan_close() to be sure the work is flushed under all circumstances. The Fixes commit below moved flush_work() from slcan_close() to slcan_netdev_close(). What was the rationale behind it? Maybe we can drop the one in slcan_netdev_close()? I see the same pattern in can327. So it perhaps needs the very same fix. Fixes: cfcb4465e992 ("can: slcan: remove legacy infrastructure") Link: https://bugzilla.suse.com/show_bug.cgi?id=1205597 Reported-by: Richard Palethorpe Tested-by: Petr Vorel Cc: Dario Binacchi Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: linux-can@vger.kernel.org Cc: netdev@vger.kernel.org Cc: stable@vger.kernel.org Cc: Max Staudt Signed-off-by: Jiri Slaby (SUSE) Reviewed-by: Max Staudt Link: https://lore.kernel.org/all/20221201073426.17328-1-jirislaby@kernel.org Signed-off-by: Marc Kleine-Budde --- drivers/net/can/slcan/slcan-core.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c index fbb34139daa1..f4db77007c13 100644 --- a/drivers/net/can/slcan/slcan-core.c +++ b/drivers/net/can/slcan/slcan-core.c @@ -864,12 +864,14 @@ static void slcan_close(struct tty_struct *tty) { struct slcan *sl = (struct slcan *)tty->disc_data; - /* unregister_netdev() calls .ndo_stop() so we don't have to. - * Our .ndo_stop() also flushes the TTY write wakeup handler, - * so we can safely set sl->tty = NULL after this. - */ unregister_candev(sl->dev); + /* + * The netdev needn't be UP (so .ndo_stop() is not called). Hence make + * sure this is not running before freeing it up. + */ + flush_work(&sl->tx_work); + /* Mark channel as dead */ spin_lock_bh(&sl->lock); tty->disc_data = NULL; -- cgit v1.2.3 From f4a4d121ebecaa6f396f21745ce97de014281ccc Mon Sep 17 00:00:00 2001 From: Max Staudt Date: Sat, 3 Dec 2022 01:01:48 +0900 Subject: can: can327: flush TX_work on ldisc .close() Additionally, remove it from .ndo_stop(). This ensures that the worker is not called after being freed, and that the UART TX queue remains active to send final commands when the netdev is stopped. Thanks to Jiri Slaby for finding this in slcan: https://lore.kernel.org/linux-can/20221201073426.17328-1-jirislaby@kernel.org/ A variant of this patch for slcan, with the flush in .ndo_stop() still present, has been tested successfully on physical hardware: https://bugzilla.suse.com/show_bug.cgi?id=1205597 Fixes: 43da2f07622f ("can: can327: CAN/ldisc driver for ELM327 based OBD-II adapters") Cc: "Jiri Slaby (SUSE)" Cc: Max Staudt Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: linux-can@vger.kernel.org Cc: netdev@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Max Staudt Link: https://lore.kernel.org/all/20221202160148.282564-1-max@enpas.org Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- drivers/net/can/can327.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'drivers') diff --git a/drivers/net/can/can327.c b/drivers/net/can/can327.c index ed3d0b8989a0..dc7192ecb001 100644 --- a/drivers/net/can/can327.c +++ b/drivers/net/can/can327.c @@ -796,9 +796,9 @@ static int can327_netdev_close(struct net_device *dev) netif_stop_queue(dev); - /* Give UART one final chance to flush. */ - clear_bit(TTY_DO_WRITE_WAKEUP, &elm->tty->flags); - flush_work(&elm->tx_work); + /* We don't flush the UART TX queue here, as we want final stop + * commands (like the above dummy char) to be flushed out. + */ can_rx_offload_disable(&elm->offload); elm->can.state = CAN_STATE_STOPPED; @@ -1069,12 +1069,15 @@ static void can327_ldisc_close(struct tty_struct *tty) { struct can327 *elm = (struct can327 *)tty->disc_data; - /* unregister_netdev() calls .ndo_stop() so we don't have to. - * Our .ndo_stop() also flushes the TTY write wakeup handler, - * so we can safely set elm->tty = NULL after this. - */ + /* unregister_netdev() calls .ndo_stop() so we don't have to. */ unregister_candev(elm->dev); + /* Give UART one final chance to flush. + * No need to clear TTY_DO_WRITE_WAKEUP since .write_wakeup() is + * serialised against .close() and will not be called once we return. + */ + flush_work(&elm->tx_work); + /* Mark channel as dead */ spin_lock_bh(&elm->lock); tty->disc_data = NULL; -- cgit v1.2.3 From 918ee4911f7a41fb4505dff877c1d7f9f64eb43e Mon Sep 17 00:00:00 2001 From: Frank Jungclaus Date: Wed, 30 Nov 2022 21:22:42 +0100 Subject: can: esd_usb: Allow REC and TEC to return to zero We don't get any further EVENT from an esd CAN USB device for changes on REC or TEC while those counters converge to 0 (with ecc == 0). So when handling the "Back to Error Active"-event force txerr = rxerr = 0, otherwise the berr-counters might stay on values like 95 forever. Also, to make life easier during the ongoing development a netdev_dbg() has been introduced to allow dumping error events send by an esd CAN USB device. Fixes: 96d8e90382dc ("can: Add driver for esd CAN-USB/2 device") Signed-off-by: Frank Jungclaus Link: https://lore.kernel.org/all/20221130202242.3998219-2-frank.jungclaus@esd.eu Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/esd_usb.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers') diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 81b88e9e5bdc..42323f5e6f3a 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -234,6 +234,10 @@ static void esd_usb_rx_event(struct esd_usb_net_priv *priv, u8 rxerr = msg->msg.rx.data[2]; u8 txerr = msg->msg.rx.data[3]; + netdev_dbg(priv->netdev, + "CAN_ERR_EV_EXT: dlc=%#02x state=%02x ecc=%02x rec=%02x tec=%02x\n", + msg->msg.rx.dlc, state, ecc, rxerr, txerr); + skb = alloc_can_err_skb(priv->netdev, &cf); if (skb == NULL) { stats->rx_dropped++; @@ -260,6 +264,8 @@ static void esd_usb_rx_event(struct esd_usb_net_priv *priv, break; default: priv->can.state = CAN_STATE_ERROR_ACTIVE; + txerr = 0; + rxerr = 0; break; } } else { -- cgit v1.2.3