[PATCH net 0/19] pull-request: can 2026-07-16

[PATCH net 0/19] pull-request: can 2026-07-16

[Marc Kleine-Budde]

Hello netdev-team,

this is a pull request of 19 patches for net/main.

The first patch is by Alexander Hölzl and fixes the Kconfig
description of the vxcan driver.

Next patch by Fan Wu fixes the tear down order in the esd_usb driver.

Followed by a patch by Oliver Hartkopp that adds missing locking for
the raw flags in the CAN_RAW protocol.

Shuhao Fu's patch for the j1939 protocol fix lockless
local-destination check.

Stéphane Grosjean updates their email address.

The next 11 patches all target the CAM Broadcast Manager protocol. One
contributed by Lee Jones the remaining ones by Oliver Hartkopp. They
fix several concurrency and locking issues found by various bots.

The last 3 patches are also by Oliver Hartkopp fixing concurrency and
locking issues found by various bots in the CAN ISO Transport
Protocol.

regards,
Marc

---

The following changes since commit 3f1f755366687d051174739fb99f7d560202f60b:

  net: openvswitch: reject oversized nested action attrs (2026-07-11 13:09:11 +0200)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can.git tags/linux-can-fixes-for-7.2-20260716

for you to fetch changes up to 6fd9e37916b9537143a295f854fdf5e52c4c5bc1:

  Merge patch series "net: can: isotp-fixes" (2026-07-16 10:12:22 +0200)

----------------------------------------------------------------
linux-can-fixes-for-7.2-20260716

----------------------------------------------------------------
Alexander Hölzl (1):
      can: vxcan: Kconfig: fix description stating no local echo provided

Fan Wu (1):
      can: esd_usb: kill anchored URBs before freeing netdevs

Lee Jones (1):
      can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF

Marc Kleine-Budde (2):
      Merge patch series "can: bcm: collected fixes"
      Merge patch series "net: can: isotp-fixes"

Oliver Hartkopp (14):
      can: raw: add locking for raw flags bitfield
      can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure
      can: bcm: add locking when updating filter and timer values
      can: bcm: fix CAN frame rx/tx statistics
      can: bcm: add missing rcu list annotations and operations
      can: bcm: extend bcm_tx_lock usage for data and timer updates
      can: bcm: validate frame length in bcm_rx_setup() for RTR replies
      can: bcm: add missing device refcount for CAN filter removal
      can: bcm: fix stale rx/tx ops after device removal
      can: bcm: fix data race on rx_stamp/rx_ifindex in bcm_rx_handler()
      can: bcm: track a single source interface for ANYDEV timeout/throttle ops
      can: isotp: use unconditional synchronize_rcu() in isotp_release()
      can: isotp: fix use-after-free race with concurrent NETDEV_UNREGISTER
      can: isotp: serialize TX state transitions under so->rx_lock

Shuhao Fu (1):
      can: j1939: fix lockless local-destination check

Stéphane Grosjean (1):
      can: peak: Modification of references to email accounts being deleted

 .mailmap                                      |   4 +-
 drivers/net/can/Kconfig                       |   7 +-
 drivers/net/can/peak_canfd/peak_canfd.c       |   2 +-
 drivers/net/can/peak_canfd/peak_canfd_user.h  |   2 +-
 drivers/net/can/peak_canfd/peak_pciefd_main.c |   4 +-
 drivers/net/can/sja1000/peak_pci.c            |   4 +-
 drivers/net/can/sja1000/peak_pcmcia.c         |   4 +-
 drivers/net/can/usb/esd_usb.c                 |   5 +-
 drivers/net/can/usb/peak_usb/pcan_usb.c       |   2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_core.c  |   4 +-
 drivers/net/can/usb/peak_usb/pcan_usb_core.h  |   2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_fd.c    |   2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_pro.c   |   2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_pro.h   |   2 +-
 include/linux/can/dev/peak_canfd.h            |   2 +-
 net/can/bcm.c                                 | 654 +++++++++++++++++++-------
 net/can/isotp.c                               | 298 +++++++++---
 net/can/j1939/transport.c                     |  18 +-
 net/can/raw.c                                 |  66 ++-
 19 files changed, 792 insertions(+), 292 deletions(-)

[PATCH net 01/19] can: vxcan: Kconfig: fix description stating no local echo provided

[Marc Kleine-Budde]

From: Alexander Hölzl <alexander.hoelzl@gmx.net>

The Kconfig description of the vxcan kernel module erroneously states the
the vxcan interface does not provide a local echo of sent can frames.
However this behavior changed in commit 259bdba27e32 ("vxcan: enable local
echo for sent CAN frames") and vxcan interfaces now provide a local echo.

Change the description of the vxcan module in the Kconfig to reflect this
change.

Signed-off-by: Alexander Hölzl <alexander.hoelzl@gmx.net>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260619090035.17769-1-alexander.hoelzl@gmx.net
[mkl: rephrase patch description]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/Kconfig | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index e4058708ae68..a8fad6fe5302 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -40,11 +40,8 @@ config CAN_VXCAN
 	  When one end receives the packet it appears on its pair and vice
 	  versa. The vxcan can be used for cross namespace communication.
 
-	  In opposite to vcan loopback devices the vxcan only forwards CAN
-	  frames to its pair and does *not* provide a local echo of sent
-	  CAN frames. To disable a potential echo in af_can.c the vxcan driver
-	  announces IFF_ECHO in the interface flags. To have a clean start
-	  in each namespace the CAN GW hop counter is set to zero.
+	  To have a clean start in each namespace the CAN GW hop counter is
+	  set to zero.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called vxcan.

base-commit: 3f1f755366687d051174739fb99f7d560202f60b
-- 
2.53.0

[PATCH net 02/19] can: esd_usb: kill anchored URBs before freeing netdevs

[Marc Kleine-Budde]

From: Fan Wu <fanwu01@zju.edu.cn>

esd_usb_disconnect() frees each CAN netdev with free_candev() inside
its per-netdev loop and only calls unlink_all_urbs(dev) afterwards.
The per-netdev private data (struct esd_usb_net_priv) is embedded in
the net_device allocation returned by alloc_candev(), so once
free_candev() has run, dev->nets[i] points to freed memory.
unlink_all_urbs() then dereferences the freed dev->nets[i] to kill the
per-netdev TX anchor (usb_kill_anchored_urbs(&priv->tx_submitted)),
clear active_tx_jobs, and reset priv->tx_contexts[].

Reorder the teardown so the anchored URBs are killed before the netdevs
are freed, matching other CAN/USB drivers in the same directory such as
ems_usb, usb_8dev and mcba_usb, which unregister, then unlink, then
free: unregister the netdevs first (which stops their TX queues), call
unlink_all_urbs(dev) once, then free the netdevs.

This issue was found by an in-house static analysis tool.

Fixes: 96d8e90382dc ("can: Add driver for esd CAN-USB/2 device")
Cc: stable@vger.kernel.org
Assisted-by: Codex:gpt-5.5
Signed-off-by: Fan Wu <fanwu01@zju.edu.cn>
Link: https://patch.msgid.link/20260709164159.497640-1-fanwu01@zju.edu.cn
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/esd_usb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c
index d257440fa01f..f41d4a0d140f 100644
--- a/drivers/net/can/usb/esd_usb.c
+++ b/drivers/net/can/usb/esd_usb.c
@@ -1390,10 +1390,13 @@ static void esd_usb_disconnect(struct usb_interface *intf)
 				netdev = dev->nets[i]->netdev;
 				netdev_info(netdev, "unregister\n");
 				unregister_netdev(netdev);
-				free_candev(netdev);
 			}
 		}
 		unlink_all_urbs(dev);
+		for (i = 0; i < dev->net_count; i++) {
+			if (dev->nets[i])
+				free_candev(dev->nets[i]->netdev);
+		}
 		kfree(dev);
 	}
 }
-- 
2.53.0

[PATCH net 03/19] can: raw: add locking for raw flags bitfield

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

With commit 890e5198a6e5 ("can: raw: use bitfields to store flags in
struct raw_sock") the formerly separate integer values have been integrated
into a single bitfield. This led to a read-modify-write operation when
changing a flag in raw_setsockopt() which now needs a locking to prevent
concurrent access.

Instead of adding a lock/unlock hell in each of the flag manipulations this
patch introduces a wrapper for a new raw_setsockopt_locked() function
analogue to the isotp_setsockopt[_locked]() approach in net/can/isotp.c

Fixes: 890e5198a6e5 ("can: raw: use bitfields to store flags in struct raw_sock")
Reported-by: Eulgyu Kim <eulgyukim@snu.ac.kr>
Closes: https://lore.kernel.org/linux-can/20260503112200.22727-1-eulgyukim@snu.ac.kr/
Tested-by: Eulgyu Kim <eulgyukim@snu.ac.kr>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Tested-by: Vincent Mailhol <mailhol@kernel.org>
Link: https://patch.msgid.link/20260504111928.41856-1-socketcan@hartkopp.net
[mkl: use Closes tag instead of Link]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/raw.c | 66 +++++++++++++++++++++++----------------------------
 1 file changed, 30 insertions(+), 36 deletions(-)

diff --git a/net/can/raw.c b/net/can/raw.c
index a26942e78e68..82d9c0499c95 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -562,8 +562,8 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr,
 	return RAW_MIN_NAMELEN;
 }
 
-static int raw_setsockopt(struct socket *sock, int level, int optname,
-			  sockptr_t optval, unsigned int optlen)
+static int raw_setsockopt_locked(struct socket *sock, int optname,
+				 sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct raw_sock *ro = raw_sk(sk);
@@ -575,9 +575,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 	int flag;
 	int err = 0;
 
-	if (level != SOL_CAN_RAW)
-		return -EINVAL;
-
 	switch (optname) {
 	case CAN_RAW_FILTER:
 		if (optlen % sizeof(struct can_filter) != 0)
@@ -598,17 +595,11 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 				return -EFAULT;
 		}
 
-		rtnl_lock();
-		lock_sock(sk);
-
 		dev = ro->dev;
-		if (ro->bound && dev) {
-			if (dev->reg_state != NETREG_REGISTERED) {
-				if (count > 1)
-					kfree(filter);
-				err = -ENODEV;
-				goto out_fil;
-			}
+		if (ro->bound && dev && dev->reg_state != NETREG_REGISTERED) {
+			if (count > 1)
+				kfree(filter);
+			return -ENODEV;
 		}
 
 		if (ro->bound) {
@@ -622,7 +613,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 			if (err) {
 				if (count > 1)
 					kfree(filter);
-				goto out_fil;
+				return err;
 			}
 
 			/* remove old filter registrations */
@@ -642,11 +633,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		}
 		ro->filter = filter;
 		ro->count  = count;
-
- out_fil:
-		release_sock(sk);
-		rtnl_unlock();
-
 		break;
 
 	case CAN_RAW_ERR_FILTER:
@@ -658,16 +644,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 
 		err_mask &= CAN_ERR_MASK;
 
-		rtnl_lock();
-		lock_sock(sk);
-
 		dev = ro->dev;
-		if (ro->bound && dev) {
-			if (dev->reg_state != NETREG_REGISTERED) {
-				err = -ENODEV;
-				goto out_err;
-			}
-		}
+		if (ro->bound && dev && dev->reg_state != NETREG_REGISTERED)
+			return -ENODEV;
 
 		/* remove current error mask */
 		if (ro->bound) {
@@ -676,7 +655,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 						   err_mask);
 
 			if (err)
-				goto out_err;
+				return err;
 
 			/* remove old err_mask registration */
 			raw_disable_errfilter(sock_net(sk), dev, sk,
@@ -685,11 +664,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 
 		/* link new err_mask to the socket */
 		ro->err_mask = err_mask;
-
- out_err:
-		release_sock(sk);
-		rtnl_unlock();
-
 		break;
 
 	case CAN_RAW_LOOPBACK:
@@ -769,6 +743,26 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 	return err;
 }
 
+static int raw_setsockopt(struct socket *sock, int level, int optname,
+			  sockptr_t optval, unsigned int optlen)
+{
+	struct sock *sk = sock->sk;
+	int err;
+
+	if (level != SOL_CAN_RAW)
+		return -EINVAL;
+
+	rtnl_lock();
+	lock_sock(sk);
+
+	err = raw_setsockopt_locked(sock, optname, optval, optlen);
+
+	release_sock(sk);
+	rtnl_unlock();
+
+	return err;
+}
+
 static int raw_getsockopt(struct socket *sock, int level, int optname,
 			  sockopt_t *opt)
 {
-- 
2.53.0

[PATCH net 04/19] can: j1939: fix lockless local-destination check

[Marc Kleine-Budde]

From: Shuhao Fu <sfual@cse.ust.hk>

j1939_priv.ents[].nusers is documented as protected by priv->lock, and
its updates already happen under that lock. j1939_can_recv() also reads
it under read_lock_bh(). However, j1939_session_skb_queue() and
j1939_tp_send() still read priv->ents[da].nusers without taking the
lock.

Those transport-side checks decide whether to set J1939_ECU_LOCAL_DST, so
they can race with j1939_local_ecu_get() and j1939_local_ecu_put() while
userspace is binding or releasing sockets concurrently with TP traffic.
This can misclassify TP/ETP sessions as local or remote and take the wrong
transport path.

Fix both transport paths by routing the destination-locality check through
a helper that reads ents[].nusers under read_lock_bh(&priv->lock).

Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Signed-off-by: Shuhao Fu <sfual@cse.ust.hk>
Tested-by: Oleksij Rempel <o.rempel@pengutronix.de>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20260419140614.GA4041240@chcpu16
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/transport.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index df93d57907da..8a31cb23bc76 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -351,6 +351,18 @@ static void j1939_session_skb_drop_old(struct j1939_session *session)
 	}
 }
 
+static bool j1939_address_is_local(struct j1939_priv *priv, u8 addr)
+{
+	bool local = false;
+
+	read_lock_bh(&priv->lock);
+	if (j1939_address_is_unicast(addr) && priv->ents[addr].nusers)
+		local = true;
+	read_unlock_bh(&priv->lock);
+
+	return local;
+}
+
 void j1939_session_skb_queue(struct j1939_session *session,
 			     struct sk_buff *skb)
 {
@@ -359,8 +371,7 @@ void j1939_session_skb_queue(struct j1939_session *session,
 
 	j1939_ac_fixup(priv, skb);
 
-	if (j1939_address_is_unicast(skcb->addr.da) &&
-	    priv->ents[skcb->addr.da].nusers)
+	if (j1939_address_is_local(priv, skcb->addr.da))
 		skcb->flags |= J1939_ECU_LOCAL_DST;
 
 	skcb->flags |= J1939_ECU_LOCAL_SRC;
@@ -2038,8 +2049,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv,
 		return ERR_PTR(ret);
 
 	/* fix DST flags, it may be used there soon */
-	if (j1939_address_is_unicast(skcb->addr.da) &&
-	    priv->ents[skcb->addr.da].nusers)
+	if (j1939_address_is_local(priv, skcb->addr.da))
 		skcb->flags |= J1939_ECU_LOCAL_DST;
 
 	/* src is always local, I'm sending ... */
-- 
2.53.0

[PATCH net 05/19] can: peak: Modification of references to email accounts being deleted

[Marc Kleine-Budde]

From: Stéphane Grosjean <s.grosjean@peak-system.fr>

Following the sale of PEAK-System France by HMS-Networks, this update is
intended to change all my @hms-networks.com email addresses to my new
@peak-system.fr address.

Signed-off-by: Stéphane Grosjean <s.grosjean@peak-system.fr>
Link: https://patch.msgid.link/20260410124251.40506-1-stephane.grosjean@free.fr
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .mailmap                                      | 4 ++--
 drivers/net/can/peak_canfd/peak_canfd.c       | 2 +-
 drivers/net/can/peak_canfd/peak_canfd_user.h  | 2 +-
 drivers/net/can/peak_canfd/peak_pciefd_main.c | 4 ++--
 drivers/net/can/sja1000/peak_pci.c            | 4 ++--
 drivers/net/can/sja1000/peak_pcmcia.c         | 4 ++--
 drivers/net/can/usb/peak_usb/pcan_usb.c       | 2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_core.c  | 4 ++--
 drivers/net/can/usb/peak_usb/pcan_usb_core.h  | 2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_fd.c    | 2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_pro.c   | 2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_pro.h   | 2 +-
 include/linux/can/dev/peak_canfd.h            | 2 +-
 13 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/.mailmap b/.mailmap
index 12f3acdebd72..918fcd6575b1 100644
--- a/.mailmap
+++ b/.mailmap
@@ -825,8 +825,8 @@ Sriram Yagnaraman <sriram.yagnaraman@ericsson.com> <sriram.yagnaraman@est.tech>
 Stanislav Fomichev <sdf@fomichev.me> <sdf@google.com>
 Stanislav Fomichev <sdf@fomichev.me> <stfomichev@gmail.com>
 Stefan Wahren <wahrenst@gmx.net> <stefan.wahren@i2se.com>
-Stéphane Grosjean <stephane.grosjean@hms-networks.com> <s.grosjean@peak-system.com>
-Stéphane Grosjean <stephane.grosjean@hms-networks.com> <stephane.grosjean@free.fr>
+Stéphane Grosjean <s.grosjean@peak-system.fr> <s.grosjean@peak-system.com>
+Stéphane Grosjean <s.grosjean@peak-system.fr> <stephane.grosjean@free.fr>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <stephen@networkplumber.org> <shemminger@linux-foundation.org>
 Stephen Hemminger <stephen@networkplumber.org> <shemminger@osdl.org>
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index 06cb2629f66a..4fd1aefb780f 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -2,7 +2,7 @@
 /* Copyright (C) 2007, 2011 Wolfgang Grandegger <wg@grandegger.com>
  *
  * Copyright (C) 2016-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  */
 
 #include <linux/can.h>
diff --git a/drivers/net/can/peak_canfd/peak_canfd_user.h b/drivers/net/can/peak_canfd/peak_canfd_user.h
index 60c6542028cf..dc0ecb566a85 100644
--- a/drivers/net/can/peak_canfd/peak_canfd_user.h
+++ b/drivers/net/can/peak_canfd/peak_canfd_user.h
@@ -2,7 +2,7 @@
 /* CAN driver for PEAK System micro-CAN based adapters
  *
  * Copyright (C) 2003-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  */
 #ifndef PEAK_CANFD_USER_H
 #define PEAK_CANFD_USER_H
diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index 93558e33bc02..7c749301ea84 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -4,7 +4,7 @@
  * Derived from the PCAN project file driver/src/pcan_pci.c:
  *
  * Copyright (C) 2001-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  */
 
 #include <linux/kernel.h>
@@ -19,7 +19,7 @@
 
 #include "peak_canfd_user.h"
 
-MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>");
+MODULE_AUTHOR("Stéphane Grosjean <s.grosjean@peak-system.fr>");
 MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCIe/M.2 FD family cards");
 MODULE_LICENSE("GPL v2");
 
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 4cc4a1581dd1..69c61ccf621d 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -5,7 +5,7 @@
  * Derived from the PCAN project file driver/src/pcan_pci.c:
  *
  * Copyright (C) 2001-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  */
 
 #include <linux/kernel.h>
@@ -22,7 +22,7 @@
 
 #include "sja1000.h"
 
-MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>");
+MODULE_AUTHOR("Stéphane Grosjean <s.grosjean@peak-system.fr>");
 MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCI family cards");
 MODULE_LICENSE("GPL v2");
 
diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c
index 42a77d435b39..c3c2aa21da47 100644
--- a/drivers/net/can/sja1000/peak_pcmcia.c
+++ b/drivers/net/can/sja1000/peak_pcmcia.c
@@ -4,7 +4,7 @@
  * Derived from the PCAN project file driver/src/pcan_pccard.c
  *
  * Copyright (C) 2006-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -19,7 +19,7 @@
 #include <linux/can/dev.h>
 #include "sja1000.h"
 
-MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>");
+MODULE_AUTHOR("Stéphane Grosjean <s.grosjean@peak-system.fr>");
 MODULE_DESCRIPTION("CAN driver for PEAK-System PCAN-PC Cards");
 MODULE_LICENSE("GPL v2");
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 9278a1522aae..8fd058c32856 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -4,7 +4,7 @@
  * Derived from the PCAN project file driver/src/pcan_usb.c
  *
  * Copyright (C) 2003-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  *
  * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de>
  */
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index cf48bb26d46d..c7933d1acc99 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -4,7 +4,7 @@
  * Derived from the PCAN project file driver/src/pcan_usb_core.c
  *
  * Copyright (C) 2003-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  *
  * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de>
  */
@@ -24,7 +24,7 @@
 
 #include "pcan_usb_core.h"
 
-MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>");
+MODULE_AUTHOR("Stéphane Grosjean <s.grosjean@peak-system.fr>");
 MODULE_DESCRIPTION("CAN driver for PEAK-System USB adapters");
 MODULE_LICENSE("GPL v2");
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h
index d1c1897d47b9..65999f04f4b7 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h
@@ -4,7 +4,7 @@
  * Derived from the PCAN project file driver/src/pcan_usb_core.c
  *
  * Copyright (C) 2003-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  *
  * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de>
  */
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index eb4f5884ad73..ef9fd693e9bd 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -3,7 +3,7 @@
  * CAN driver for PEAK System PCAN-USB FD / PCAN-USB Pro FD adapter
  *
  * Copyright (C) 2013-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  */
 #include <linux/ethtool.h>
 #include <linux/module.h>
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 4bfa8d0fbb32..aefcded8e12a 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -4,7 +4,7 @@
  * Derived from the PCAN project file driver/src/pcan_usbpro.c
  *
  * Copyright (C) 2003-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  */
 #include <linux/ethtool.h>
 #include <linux/module.h>
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h
index 162c7546d3a8..d669c9e610c7 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h
@@ -4,7 +4,7 @@
  * Derived from the PCAN project file driver/src/pcan_usbpro_fw.h
  *
  * Copyright (C) 2003-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  */
 #ifndef PCAN_USB_PRO_H
 #define PCAN_USB_PRO_H
diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h
index d3788a3d0942..056e0efa649f 100644
--- a/include/linux/can/dev/peak_canfd.h
+++ b/include/linux/can/dev/peak_canfd.h
@@ -3,7 +3,7 @@
  * CAN driver for PEAK System micro-CAN based adapters
  *
  * Copyright (C) 2003-2025 PEAK System-Technik GmbH
- * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
+ * Author: Stéphane Grosjean <s.grosjean@peak-system.fr>
  */
 #ifndef PUCAN_H
 #define PUCAN_H
-- 
2.53.0

[PATCH net 06/19] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF

[Marc Kleine-Budde]

From: Lee Jones <lee@kernel.org>

Commit f1b4e32aca08 ("can: bcm: use call_rcu() instead of costly
synchronize_rcu()") replaced synchronize_rcu() in bcm_delete_rx_op()
with call_rcu() and introduced the RX_NO_AUTOTIMER flag.

However, this flag check was omitted for thrtimer in the packet rx
fast-path. During BCM RX operation teardown, a concurrent RCU reader
(bcm_rx_handler) can race and re-arm thrtimer via
bcm_rx_update_and_send() after call_rcu() has been scheduled.  Once
the RCU grace period elapses, bcm_op is freed.  The subsequently
firing thrtimer then dereferences the deallocated op, causing a UAF.

Adding flag checks to the rx fast-path (bcm_rx_update_and_send) does not
fully close the TOCTOU race and introduces latency for every CAN frame.
Conversely, calling hrtimer_cancel() directly inside the RCU callback
(softirq context) is fatal as hrtimer_cancel() can sleep, triggering
a "scheduling while atomic" panic.

Resolve this by deferring the timer cancellation and memory free to a
dedicated unbound workqueue (bcm_wq).  The RCU callback now queues a
work item to bcm_wq, which safely cancels both timers and deallocates
memory in sleepable process context.  A dedicated workqueue is used to
prevent system-wide WQ saturation and is cleanly flushed/destroyed
on module unload to avoid rmmod page faults.

Since the deferred work can now outlive the calling context by an
unbounded amount, also take a reference on op->sk when it is assigned
and drop it only once the deferred work has cancelled both timers, so a
socket can no longer be freed out from under a still-armed timer whose
callback (bcm_send_to_user()) dereferences op->sk.

Fixes: f1b4e32aca08 ("can: bcm: use call_rcu() instead of costly synchronize_rcu()")
Tested-by: Feng Xue <feng.xue@outlook.com>
Tested-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Lee Jones <lee@kernel.org>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-1-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 37 ++++++++++++++++++++++++++++++++++---
 1 file changed, 34 insertions(+), 3 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index a4bef2c48a55..bdf53241bd7b 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -58,6 +58,7 @@
 #include <linux/can/skb.h>
 #include <linux/can/bcm.h>
 #include <linux/slab.h>
+#include <linux/workqueue.h>
 #include <linux/spinlock.h>
 #include <net/can.h>
 #include <net/sock.h>
@@ -92,6 +93,8 @@ MODULE_ALIAS("can-proto-2");
 
 #define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex)
 
+static struct workqueue_struct *bcm_wq;
+
 /*
  * easy access to the first 64 bit of can(fd)_frame payload. cp->data is
  * 64 bit aligned so the offset has to be multiples of 8 which is ensured
@@ -105,6 +108,7 @@ static inline u64 get_u64(const struct canfd_frame *cp, int offset)
 struct bcm_op {
 	struct list_head list;
 	struct rcu_head rcu;
+	struct work_struct work;
 	int ifindex;
 	canid_t can_id;
 	u32 flags;
@@ -793,9 +797,12 @@ static struct bcm_op *bcm_find_op(struct list_head *ops,
 	return NULL;
 }
 
-static void bcm_free_op_rcu(struct rcu_head *rcu_head)
+static void bcm_free_op_work(struct work_struct *work)
 {
-	struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu);
+	struct bcm_op *op = container_of(work, struct bcm_op, work);
+
+	hrtimer_cancel(&op->timer);
+	hrtimer_cancel(&op->thrtimer);
 
 	if ((op->frames) && (op->frames != &op->sframe))
 		kfree(op->frames);
@@ -803,9 +810,23 @@ static void bcm_free_op_rcu(struct rcu_head *rcu_head)
 	if ((op->last_frames) && (op->last_frames != &op->last_sframe))
 		kfree(op->last_frames);
 
+	/* the last possible access to op->timer/op->thrtimer has now
+	 * happened above via hrtimer_cancel() - op->sk is no longer
+	 * needed by any pending timer callback, so drop our reference
+	 */
+	sock_put(op->sk);
+
 	kfree(op);
 }
 
+static void bcm_free_op_rcu(struct rcu_head *rcu_head)
+{
+	struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu);
+
+	INIT_WORK(&op->work, bcm_free_op_work);
+	queue_work(bcm_wq, &op->work);
+}
+
 static void bcm_remove_op(struct bcm_op *op)
 {
 	hrtimer_cancel(&op->timer);
@@ -1060,6 +1081,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
 		op->sk = sk;
+		sock_hold(sk);
 		op->ifindex = ifindex;
 
 		/* initialize uninitialized (kzalloc) structure */
@@ -1221,6 +1243,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
 		op->sk = sk;
+		sock_hold(sk);
 		op->ifindex = ifindex;
 
 		/* ifindex for timeout events w/o previous frame reception */
@@ -1839,11 +1862,15 @@ static int __init bcm_module_init(void)
 {
 	int err;
 
+	bcm_wq = alloc_workqueue("can-bcm-wq", WQ_UNBOUND, 0);
+	if (!bcm_wq)
+		return -ENOMEM;
+
 	pr_info("can: broadcast manager protocol\n");
 
 	err = register_pernet_subsys(&canbcm_pernet_ops);
 	if (err)
-		return err;
+		goto register_pernet_failed;
 
 	err = register_netdevice_notifier(&canbcm_notifier);
 	if (err)
@@ -1861,6 +1888,8 @@ static int __init bcm_module_init(void)
 	unregister_netdevice_notifier(&canbcm_notifier);
 register_notifier_failed:
 	unregister_pernet_subsys(&canbcm_pernet_ops);
+register_pernet_failed:
+	destroy_workqueue(bcm_wq);
 	return err;
 }
 
@@ -1869,6 +1898,8 @@ static void __exit bcm_module_exit(void)
 	can_proto_unregister(&bcm_can_proto);
 	unregister_netdevice_notifier(&canbcm_notifier);
 	unregister_pernet_subsys(&canbcm_pernet_ops);
+	rcu_barrier();
+	destroy_workqueue(bcm_wq);
 }
 
 module_init(bcm_module_init);
-- 
2.53.0

[PATCH net 07/19] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

bcm_sendmsg() reads bo->ifindex and checks bo->bound before taking
lock_sock(), while bcm_notify(), bcm_connect() and bcm_release() all
mutate both fields under that same lock. Because the lockless reads
and the locked writes are unordered with respect to each other, a
racing bcm_notify() (device unregister) or bcm_connect() (concurrent
bind on another thread sharing the socket) can make bcm_sendmsg()
observe an inconsistent combination, e.g. a stale bound=1 together
with the now-cleared ifindex=0, silently turning a socket bound to a
specific CAN interface into one that also matches "any" interface.

Keep the lockless bo->bound check purely as a fast-path reject, and
move the ifindex read (and a bo->bound re-check) into the locked
section, where every writer already serializes. This removes the
possibility of observing the two fields torn against each other,
rather than trying to fix it with more READ_ONCE()/WRITE_ONCE() pairs
on two independently updated fields. Annotate the now-purely-lockless
bo->bound accesses consistently across all its write sites.

Also fix bcm_rx_setup() silently returning success when the target
device disappears concurrently instead of reporting -ENODEV, so a
broken RX op is no longer left registered as if it had succeeded.

Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Reported-by: Ginger <ginger.jzllee@gmail.com>
Closes: https://lore.kernel.org/linux-can/CAGp+u1aBK8QVjsvAxM2Ldzep4rEbsP9x_pV3At4g=h1kVEtyhA@mail.gmail.com/
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-2-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 65 ++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 51 insertions(+), 14 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index bdf53241bd7b..b612135b017d 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1323,6 +1323,11 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 				op->rx_reg_dev = dev;
 				dev_put(dev);
+			} else {
+				/* the requested device is gone - do not
+				 * silently succeed without registering
+				 */
+				err = -ENODEV;
 			}
 
 		} else
@@ -1396,12 +1401,13 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 {
 	struct sock *sk = sock->sk;
 	struct bcm_sock *bo = bcm_sk(sk);
-	int ifindex = bo->ifindex; /* default ifindex for this bcm_op */
+	int ifindex;
 	struct bcm_msg_head msg_head;
 	int cfsiz;
 	int ret; /* read bytes or error codes as return value */
 
-	if (!bo->bound)
+	/* Lockless fast-path check for bound socket */
+	if (!READ_ONCE(bo->bound))
 		return -ENOTCONN;
 
 	/* check for valid message length from userspace */
@@ -1417,17 +1423,38 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	if ((size - MHSIZ) % cfsiz)
 		return -EINVAL;
 
+	lock_sock(sk);
+
+	/* Re-validate under the socket lock: a concurrent bcm_notify()
+	 * may have unbound this socket (device removal) after the
+	 * lockless fast-path check above. bo->ifindex is only ever
+	 * mutated under lock_sock(), so reading it here - instead of
+	 * before taking the lock - guarantees it can't be observed
+	 * torn against bo->bound.
+	 */
+	if (!bo->bound) {
+		ret = -ENOTCONN;
+		goto out_release;
+	}
+
+	/* default ifindex for this bcm_op */
+	ifindex = bo->ifindex;
+
 	/* check for alternative ifindex for this bcm_op */
 
 	if (!ifindex && msg->msg_name) {
 		/* no bound device as default => check msg_name */
 		DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
 
-		if (msg->msg_namelen < BCM_MIN_NAMELEN)
-			return -EINVAL;
+		if (msg->msg_namelen < BCM_MIN_NAMELEN) {
+			ret = -EINVAL;
+			goto out_release;
+		}
 
-		if (addr->can_family != AF_CAN)
-			return -EINVAL;
+		if (addr->can_family != AF_CAN) {
+			ret = -EINVAL;
+			goto out_release;
+		}
 
 		/* ifindex from sendto() */
 		ifindex = addr->can_ifindex;
@@ -1436,20 +1463,21 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			struct net_device *dev;
 
 			dev = dev_get_by_index(sock_net(sk), ifindex);
-			if (!dev)
-				return -ENODEV;
+			if (!dev) {
+				ret = -ENODEV;
+				goto out_release;
+			}
 
 			if (dev->type != ARPHRD_CAN) {
 				dev_put(dev);
-				return -ENODEV;
+				ret = -ENODEV;
+				goto out_release;
 			}
 
 			dev_put(dev);
 		}
 	}
 
-	lock_sock(sk);
-
 	switch (msg_head.opcode) {
 
 	case TX_SETUP:
@@ -1499,6 +1527,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		break;
 	}
 
+out_release:
 	release_sock(sk);
 
 	return ret;
@@ -1535,7 +1564,12 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
 				bo->bcm_proc_read = NULL;
 			}
 #endif
-			bo->bound   = 0;
+			/* Paired with the lockless fast-path check in
+			 * bcm_sendmsg(); bo->ifindex itself is only ever
+			 * accessed under lock_sock() so it needs no
+			 * annotation.
+			 */
+			WRITE_ONCE(bo->bound, 0);
 			bo->ifindex = 0;
 			notify_enodev = 1;
 		}
@@ -1676,7 +1710,7 @@ static int bcm_release(struct socket *sock)
 
 	/* remove device reference */
 	if (bo->bound) {
-		bo->bound   = 0;
+		WRITE_ONCE(bo->bound, 0);
 		bo->ifindex = 0;
 	}
 
@@ -1746,7 +1780,10 @@ static int bcm_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int
 	}
 #endif /* CONFIG_PROC_FS */
 
-	bo->bound = 1;
+	/* bo->ifindex above is fully assigned before this point; pairs
+	 * with the lockless fast-path check in bcm_sendmsg()
+	 */
+	WRITE_ONCE(bo->bound, 1);
 
 fail:
 	release_sock(sk);
-- 
2.53.0

[PATCH net 08/19] can: bcm: add locking when updating filter and timer values

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

KCSAN detected a simultaneous access to timer values that can be
overwritten in bcm_rx_setup() when updating timer and filter content
while bcm_rx_handler(), bcm_rx_timeout_handler() or bcm_rx_thr_handler()
run concurrently on incoming CAN traffic.

Protect the timer (ival1/ival2/kt_ival1/kt_ival2/kt_lastmsg) and filter
(nframes/flags/frames/last_frames) updates in bcm_rx_setup() with a new
per-op bcm_rx_update_lock, taken with the matching scope in the RX
handlers. memcpy_from_msg() is staged into a temporary buffer before the
lock is taken, since it can sleep and must not run under a spinlock.

hrtimer_cancel() is always called without bcm_rx_update_lock held, since
bcm_rx_timeout_handler()/bcm_rx_thr_handler() take the same lock and a
running callback would otherwise deadlock against the canceller.

Also close a related race: bcm_rx_setup() cleared the RTR flag in the
stored reply frame's can_id as a separate, unprotected step after the
frame content was already installed, so a concurrent bcm_rx_handler()
could transmit a stale reply with CAN_RTR_FLAG still set. Fold that
normalization into the initial frame preparation instead (on the staged
buffer for updates, directly on op->frames pre-registration for new
ops), so the installed frame is always atomically self-consistent.

bcm_rx_handler()'s RX_RTR_FRAME check now takes a lock-protected
snapshot of op->flags before deciding whether to call bcm_can_tx(),
but does not hold the lock across that call.

Also take a lock-protected snapshot of the currframe in bcm_can_tx()
to avoid partly overwrites by content updates in bcm_tx_setup().
Finally check if a TX_RESET_MULTI_IDX/SETTIMER might have reset
op->currframe between the two locked sections in bcm_can_tx().

Omit calling hrtimer_forward() with zero interval in bcm_rx_thr_handler().
kt_ival2 may have been concurrently cleared by bcm_rx_setup() before it
cancels this timer, so check kt_ival2 inside the bcm_rx_update_lock.

Fixes: c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates")
Reported-by: syzbot+75e5e4ae00c3b4bb544e@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-can/6975d5cf.a00a0220.33ccc7.0022.GAE@google.com/
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-3-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 180 +++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 135 insertions(+), 45 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index b612135b017d..1e5f8d65d351 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -129,6 +129,7 @@ struct bcm_op {
 	struct sock *sk;
 	struct net_device *rx_reg_dev;
 	spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */
+	spinlock_t bcm_rx_update_lock; /* protect filter/timer data updates */
 };
 
 struct bcm_sock {
@@ -293,22 +294,28 @@ static int bcm_proc_show(struct seq_file *m, void *v)
  * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface
  *              of the given bcm tx op
  */
-static void bcm_can_tx(struct bcm_op *op)
+static void bcm_can_tx(struct bcm_op *op, struct canfd_frame *cf)
 {
 	struct sk_buff *skb;
 	struct can_skb_ext *csx;
 	struct net_device *dev;
-	struct canfd_frame *cf;
+	struct canfd_frame cframe;
+	bool cyclic = !cf;
+	unsigned int idx = 0;
 	int err;
 
 	/* no target device? => exit */
 	if (!op->ifindex)
 		return;
 
-	/* read currframe under lock protection */
-	spin_lock_bh(&op->bcm_tx_lock);
-	cf = op->frames + op->cfsiz * op->currframe;
-	spin_unlock_bh(&op->bcm_tx_lock);
+	if (cyclic) {
+		/* read currframe under lock protection */
+		spin_lock_bh(&op->bcm_tx_lock);
+		idx = op->currframe;
+		memcpy(&cframe, op->frames + op->cfsiz * idx, op->cfsiz);
+		cf = &cframe;
+		spin_unlock_bh(&op->bcm_tx_lock);
+	}
 
 	dev = dev_get_by_index(sock_net(op->sk), op->ifindex);
 	if (!dev) {
@@ -341,14 +348,20 @@ static void bcm_can_tx(struct bcm_op *op)
 	if (!err)
 		op->frames_abs++;
 
-	op->currframe++;
+	/* only advance the cyclic sequence if nothing reset currframe while
+	 * we were sending - a concurrent TX_RESET_MULTI_IDX means this
+	 * frame's bookkeeping belongs to a sequence that no longer exists
+	 */
+	if (!cyclic || op->currframe == idx) {
+		op->currframe++;
 
-	/* reached last frame? */
-	if (op->currframe >= op->nframes)
-		op->currframe = 0;
+		/* reached last frame? */
+		if (op->currframe >= op->nframes)
+			op->currframe = 0;
 
-	if (op->count > 0)
-		op->count--;
+		if (op->count > 0)
+			op->count--;
+	}
 
 	spin_unlock_bh(&op->bcm_tx_lock);
 out:
@@ -461,7 +474,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
 	struct bcm_msg_head msg_head;
 
 	if (op->kt_ival1 && (op->count > 0)) {
-		bcm_can_tx(op);
+		bcm_can_tx(op, NULL);
 		if (!op->count && (op->flags & TX_COUNTEVT)) {
 
 			/* create notification to user */
@@ -478,7 +491,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
 		}
 
 	} else if (op->kt_ival2) {
-		bcm_can_tx(op);
+		bcm_can_tx(op, NULL);
 	}
 
 	return bcm_tx_set_expiry(op, &op->timer) ?
@@ -622,6 +635,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 	struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer);
 	struct bcm_msg_head msg_head;
 
+	spin_lock_bh(&op->bcm_rx_update_lock);
+
 	/* if user wants to be informed, when cyclic CAN-Messages come back */
 	if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) {
 		/* clear received CAN frames to indicate 'nothing received' */
@@ -638,6 +653,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 	msg_head.can_id  = op->can_id;
 	msg_head.nframes = 0;
 
+	spin_unlock_bh(&op->bcm_rx_update_lock);
+
 	bcm_send_to_user(op, &msg_head, NULL, 0);
 
 	return HRTIMER_NORESTART;
@@ -686,15 +703,26 @@ static int bcm_rx_thr_flush(struct bcm_op *op)
 static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer)
 {
 	struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer);
+	enum hrtimer_restart ret;
 
-	if (bcm_rx_thr_flush(op)) {
+	spin_lock_bh(&op->bcm_rx_update_lock);
+
+	/* kt_ival2 may have been concurrently cleared by bcm_rx_setup()
+	 * before it cancels this timer - never forward with a zero
+	 * interval in that case.
+	 */
+	if (bcm_rx_thr_flush(op) && op->kt_ival2) {
 		hrtimer_forward_now(hrtimer, op->kt_ival2);
-		return HRTIMER_RESTART;
+		ret = HRTIMER_RESTART;
 	} else {
 		/* rearm throttle handling */
 		op->kt_lastmsg = 0;
-		return HRTIMER_NORESTART;
+		ret = HRTIMER_NORESTART;
 	}
+
+	spin_unlock_bh(&op->bcm_rx_update_lock);
+
+	return ret;
 }
 
 /*
@@ -704,8 +732,10 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 {
 	struct bcm_op *op = (struct bcm_op *)data;
 	const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data;
+	struct canfd_frame rtrframe;
 	unsigned int i;
 	unsigned char traffic_flags;
+	bool rtr_frame;
 
 	if (op->can_id != rxframe->can_id)
 		return;
@@ -729,9 +759,18 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 	/* update statistics */
 	op->frames_abs++;
 
-	if (op->flags & RX_RTR_FRAME) {
+	/* snapshot the flag under lock: op->flags/op->frames may be updated
+	 * concurrently by bcm_rx_setup().
+	 */
+	spin_lock_bh(&op->bcm_rx_update_lock);
+	rtr_frame = op->flags & RX_RTR_FRAME;
+	if (rtr_frame)
+		memcpy(&rtrframe, op->frames, op->cfsiz);
+	spin_unlock_bh(&op->bcm_rx_update_lock);
+
+	if (rtr_frame) {
 		/* send reply for RTR-request (placed in op->frames[0]) */
-		bcm_can_tx(op);
+		bcm_can_tx(op, &rtrframe);
 		return;
 	}
 
@@ -743,6 +782,8 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 			traffic_flags |= RX_OWN;
 	}
 
+	spin_lock_bh(&op->bcm_rx_update_lock);
+
 	if (op->flags & RX_FILTER_ID) {
 		/* the easiest case */
 		bcm_rx_update_and_send(op, op->last_frames, rxframe,
@@ -778,6 +819,8 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 
 rx_starttimer:
 	bcm_rx_starttimer(op);
+
+	spin_unlock_bh(&op->bcm_rx_update_lock);
 }
 
 /*
@@ -1116,7 +1159,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	}
 
 	if (op->flags & TX_ANNOUNCE)
-		bcm_can_tx(op);
+		bcm_can_tx(op, NULL);
 
 	if (op->flags & STARTTIMER)
 		bcm_tx_start_timer(op);
@@ -1130,6 +1173,24 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	return err;
 }
 
+static void bcm_rx_setup_rtr_check(struct bcm_msg_head *msg_head,
+				   struct bcm_op *op, void *new_frames)
+{
+	/* funny feature in RX(!)_SETUP only for RTR-mode:
+	 * copy can_id into frame BUT without RTR-flag to
+	 * prevent a full-load-loopback-test ... ;-]
+	 * normalize this on the staged buffer, before it is
+	 * ever installed into op->frames.
+	 */
+	if (msg_head->flags & RX_RTR_FRAME) {
+		struct canfd_frame *frame0 = new_frames;
+
+		if ((msg_head->flags & TX_CP_CAN_ID) ||
+		    frame0->can_id == op->can_id)
+			frame0->can_id = op->can_id & ~CAN_RTR_FLAG;
+	}
+}
+
 /*
  * bcm_rx_setup - create or update a bcm rx op (for bcm_sendmsg)
  */
@@ -1164,6 +1225,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	/* check the given can_id */
 	op = bcm_find_op(&bo->rx_ops, msg_head, ifindex);
 	if (op) {
+		void *new_frames = NULL;
+
 		/* update existing BCM operation */
 
 		/*
@@ -1175,19 +1238,48 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			return -E2BIG;
 
 		if (msg_head->nframes) {
-			/* update CAN frames content */
-			err = memcpy_from_msg(op->frames, msg,
-					      msg_head->nframes * op->cfsiz);
-			if (err < 0)
-				return err;
+			/* get new CAN frames content before locking */
+			new_frames = kmalloc(msg_head->nframes * op->cfsiz,
+					     GFP_KERNEL);
+			if (!new_frames)
+				return -ENOMEM;
 
-			/* clear last_frames to indicate 'nothing received' */
-			memset(op->last_frames, 0, msg_head->nframes * op->cfsiz);
+			err = memcpy_from_msg(new_frames, msg,
+					      msg_head->nframes * op->cfsiz);
+			if (err < 0) {
+				kfree(new_frames);
+				return err;
+			}
+
+			bcm_rx_setup_rtr_check(msg_head, op, new_frames);
 		}
 
+		spin_lock_bh(&op->bcm_rx_update_lock);
 		op->nframes = msg_head->nframes;
 		op->flags = msg_head->flags;
 
+		if (msg_head->nframes) {
+			/* update CAN frames content */
+			memcpy(op->frames, new_frames,
+			       msg_head->nframes * op->cfsiz);
+
+			/* clear last_frames to indicate 'nothing received' */
+			memset(op->last_frames, 0,
+			       msg_head->nframes * op->cfsiz);
+		}
+
+		if (msg_head->flags & SETTIMER) {
+			op->ival1 = msg_head->ival1;
+			op->ival2 = msg_head->ival2;
+			op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
+			op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
+			op->kt_lastmsg = 0;
+		}
+		spin_unlock_bh(&op->bcm_rx_update_lock);
+
+		/* free temporary frames / kfree(NULL) is safe */
+		kfree(new_frames);
+
 		/* Only an update -> do not call can_rx_register() */
 		do_rx_register = 0;
 
@@ -1198,6 +1290,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			return -ENOMEM;
 
 		spin_lock_init(&op->bcm_tx_lock);
+		spin_lock_init(&op->bcm_rx_update_lock);
 		op->can_id = msg_head->can_id;
 		op->nframes = msg_head->nframes;
 		op->cfsiz = CFSIZ(msg_head->flags);
@@ -1239,6 +1332,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 				kfree(op);
 				return err;
 			}
+
+			bcm_rx_setup_rtr_check(msg_head, op, op->frames);
 		}
 
 		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
@@ -1266,29 +1361,22 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	/* check flags */
 
 	if (op->flags & RX_RTR_FRAME) {
-		struct canfd_frame *frame0 = op->frames;
-
 		/* no timers in RTR-mode */
 		hrtimer_cancel(&op->thrtimer);
 		hrtimer_cancel(&op->timer);
-
-		/*
-		 * funny feature in RX(!)_SETUP only for RTR-mode:
-		 * copy can_id into frame BUT without RTR-flag to
-		 * prevent a full-load-loopback-test ... ;-]
-		 */
-		if ((op->flags & TX_CP_CAN_ID) ||
-		    (frame0->can_id == op->can_id))
-			frame0->can_id = op->can_id & ~CAN_RTR_FLAG;
-
 	} else {
 		if (op->flags & SETTIMER) {
 
-			/* set timer value */
-			op->ival1 = msg_head->ival1;
-			op->ival2 = msg_head->ival2;
-			op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
-			op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
+			/* set timers (locked) for newly created op */
+			if (do_rx_register) {
+				spin_lock_bh(&op->bcm_rx_update_lock);
+				op->ival1 = msg_head->ival1;
+				op->ival2 = msg_head->ival2;
+				op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
+				op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
+				op->kt_lastmsg = 0;
+				spin_unlock_bh(&op->bcm_rx_update_lock);
+			}
 
 			/* disable an active timer due to zero value? */
 			if (!op->kt_ival1)
@@ -1298,9 +1386,11 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			 * In any case cancel the throttle timer, flush
 			 * potentially blocked msgs and reset throttle handling
 			 */
-			op->kt_lastmsg = 0;
 			hrtimer_cancel(&op->thrtimer);
+
+			spin_lock_bh(&op->bcm_rx_update_lock);
 			bcm_rx_thr_flush(op);
+			spin_unlock_bh(&op->bcm_rx_update_lock);
 		}
 
 		if ((op->flags & STARTTIMER) && op->kt_ival1)
-- 
2.53.0

[PATCH net 09/19] can: bcm: fix CAN frame rx/tx statistics

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

KCSAN detected a data race within the bcm_rx_handler() when two CAN frames
have been simultaneously received and processed in a single rx op by two
different CPUs.

Use atomic operations with (signed) long data types to access the
statistics in the hot path to fix the KCSAN complaint.

Additionally simplify the update and check of statistics overflow by
using the atomic operations in separate bcm_update_[rx|tx]_stats()
functions. The rx variant runs under bcm_rx_update_lock to prevent
races when resetting the two rx counters; the tx variant runs under
bcm_tx_lock and only needs to guard its own counter's overflow.

As the rx path resets its values already at LONG_MAX / 100, there is
no conflict between the two locking domains (bcm_rx_update_lock vs.
bcm_tx_lock) even for ops that use both paths.

The rx statistics update and the frames_filtered update in
bcm_rx_changed() were previously performed in two separate
bcm_rx_update_lock sections. For an rx op subscribed on all interfaces
(ifindex == 0), bcm_rx_handler() can run concurrently on different
CPUs, so a counter reset by one CPU between these two sections could
leave frames_filtered larger than frames_abs on another CPU, producing
a bogus (even negative) reduction percentage in procfs. Update the
statistics in the same critical section as bcm_rx_changed() to close
this gap, which also removes the now unneeded extra lock/unlock pair
around the traffic_flags calculation.

Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-4-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 71 ++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 47 insertions(+), 24 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 1e5f8d65d351..03c98e4cc677 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -112,7 +112,7 @@ struct bcm_op {
 	int ifindex;
 	canid_t can_id;
 	u32 flags;
-	unsigned long frames_abs, frames_filtered;
+	atomic_long_t frames_abs, frames_filtered;
 	struct bcm_timeval ival1, ival2;
 	struct hrtimer timer, thrtimer;
 	ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg;
@@ -229,10 +229,13 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 
 	list_for_each_entry_rcu(op, &bo->rx_ops, list) {
 
-		unsigned long reduction;
+		long reduction, frames_filtered, frames_abs;
+
+		frames_filtered = atomic_long_read(&op->frames_filtered);
+		frames_abs = atomic_long_read(&op->frames_abs);
 
 		/* print only active entries & prevent division by zero */
-		if (!op->frames_abs)
+		if (!frames_abs)
 			continue;
 
 		seq_printf(m, "rx_op: %03X %-5s ", op->can_id,
@@ -254,9 +257,9 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 				   (long long)ktime_to_us(op->kt_ival2));
 
 		seq_printf(m, "# recv %ld (%ld) => reduction: ",
-			   op->frames_filtered, op->frames_abs);
+			   frames_filtered, frames_abs);
 
-		reduction = 100 - (op->frames_filtered * 100) / op->frames_abs;
+		reduction = 100 - (frames_filtered * 100) / frames_abs;
 
 		seq_printf(m, "%s%ld%%\n",
 			   (reduction == 100) ? "near " : "", reduction);
@@ -280,7 +283,8 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 			seq_printf(m, "t2=%lld ",
 				   (long long)ktime_to_us(op->kt_ival2));
 
-		seq_printf(m, "# sent %ld\n", op->frames_abs);
+		seq_printf(m, "# sent %ld\n",
+			   atomic_long_read(&op->frames_abs));
 	}
 	seq_putc(m, '\n');
 
@@ -290,6 +294,24 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 }
 #endif /* CONFIG_PROC_FS */
 
+static void bcm_update_rx_stats(struct bcm_op *op)
+{
+	/* prevent overflow of the reduction% calculation in bcm_proc_show() */
+	if (atomic_long_inc_return(&op->frames_abs) > LONG_MAX / 100) {
+		atomic_long_set(&op->frames_filtered, 0);
+		atomic_long_set(&op->frames_abs, 0);
+	}
+}
+
+static void bcm_update_tx_stats(struct bcm_op *op)
+{
+	/* tx_op has no reduction% calculation - use the full range and
+	 * just keep the displayed counter non-negative on overflow
+	 */
+	if (atomic_long_inc_return(&op->frames_abs) == LONG_MAX)
+		atomic_long_set(&op->frames_abs, 0);
+}
+
 /*
  * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface
  *              of the given bcm tx op
@@ -346,7 +368,7 @@ static void bcm_can_tx(struct bcm_op *op, struct canfd_frame *cf)
 	spin_lock_bh(&op->bcm_tx_lock);
 
 	if (!err)
-		op->frames_abs++;
+		bcm_update_tx_stats(op);
 
 	/* only advance the cyclic sequence if nothing reset currframe while
 	 * we were sending - a concurrent TX_RESET_MULTI_IDX means this
@@ -505,12 +527,9 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data)
 {
 	struct bcm_msg_head head;
 
-	/* update statistics */
-	op->frames_filtered++;
-
-	/* prevent statistics overflow */
-	if (op->frames_filtered > ULONG_MAX/100)
-		op->frames_filtered = op->frames_abs = 0;
+	/* update statistics (frames_filtered <= frames_abs) */
+	if (atomic_long_read(&op->frames_abs))
+		atomic_long_inc(&op->frames_filtered);
 
 	/* this element is not throttled anymore */
 	data->flags &= ~RX_THR;
@@ -756,24 +775,30 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 	op->rx_stamp = skb->tstamp;
 	/* save originator for recvfrom() */
 	op->rx_ifindex = skb->dev->ifindex;
-	/* update statistics */
-	op->frames_abs++;
 
-	/* snapshot the flag under lock: op->flags/op->frames may be updated
-	 * concurrently by bcm_rx_setup().
-	 */
+	/* op->flags/op->frames may be updated concurrently by bcm_rx_setup() */
 	spin_lock_bh(&op->bcm_rx_update_lock);
-	rtr_frame = op->flags & RX_RTR_FRAME;
-	if (rtr_frame)
-		memcpy(&rtrframe, op->frames, op->cfsiz);
-	spin_unlock_bh(&op->bcm_rx_update_lock);
 
+	rtr_frame = op->flags & RX_RTR_FRAME;
 	if (rtr_frame) {
+		bcm_update_rx_stats(op);
+		/* snapshot RTR content under lock */
+		memcpy(&rtrframe, op->frames, op->cfsiz);
+		spin_unlock_bh(&op->bcm_rx_update_lock);
+
 		/* send reply for RTR-request (placed in op->frames[0]) */
 		bcm_can_tx(op, &rtrframe);
 		return;
 	}
 
+	/* update statistics in the same critical section as bcm_rx_changed()
+	 * below: frames_filtered must never be checked/incremented against a
+	 * frames_abs snapshot from a concurrent bcm_rx_handler() call on
+	 * another CPU for the same (wildcard) op, or frames_filtered can end
+	 * up larger than frames_abs.
+	 */
+	bcm_update_rx_stats(op);
+
 	/* compute flags to distinguish between own/local/remote CAN traffic */
 	traffic_flags = 0;
 	if (skb->sk) {
@@ -782,8 +807,6 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 			traffic_flags |= RX_OWN;
 	}
 
-	spin_lock_bh(&op->bcm_rx_update_lock);
-
 	if (op->flags & RX_FILTER_ID) {
 		/* the easiest case */
 		bcm_rx_update_and_send(op, op->last_frames, rxframe,
-- 
2.53.0

[PATCH net 10/19] can: bcm: add missing rcu list annotations and operations

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

sashiko-bot remarked the missing use of list_add_rcu() in
bcm_[rx|tx]_setup() to have a proper initialized bcm_op structure
when bcm_proc_show() traverses the bcm_op's under rcu_read_lock().

To cover all initial settings of the bcm_op's the list_add_rcu() calls
are moved to the end of the setup code.

While at it, also fix the mirroring removal side: bcm_release() called
bcm_remove_op() - which frees the op via call_rcu() - on ops that were
still linked in bo->tx_ops/bo->rx_ops, without list_del_rcu() first.
Unlink each op with list_del_rcu() before handing it to bcm_remove_op(),
matching the existing pattern in bcm_delete_tx_op()/bcm_delete_rx_op().

Reported-by: sashiko-reviews@lists.linux.dev
Closes: https://lore.kernel.org/linux-can/20260610094654.A1FFE1F00893@smtp.kernel.org/
Fixes: dac5e6249159 ("can: bcm: add missing rcu read protection for procfs content")
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-5-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 03c98e4cc677..5c1e83eeb4ff 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -265,7 +265,7 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 			   (reduction == 100) ? "near " : "", reduction);
 	}
 
-	list_for_each_entry(op, &bo->tx_ops, list) {
+	list_for_each_entry_rcu(op, &bo->tx_ops, list) {
 
 		seq_printf(m, "tx_op: %03X %s ", op->can_id,
 			   bcm_proc_getifname(net, ifname, op->ifindex));
@@ -1017,6 +1017,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	struct bcm_sock *bo = bcm_sk(sk);
 	struct bcm_op *op;
 	struct canfd_frame *cf;
+	bool add_op_to_list = false;
 	unsigned int i;
 	int err;
 
@@ -1158,8 +1159,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		hrtimer_setup(&op->thrtimer, hrtimer_dummy_timeout, CLOCK_MONOTONIC,
 			      HRTIMER_MODE_REL_SOFT);
 
-		/* add this bcm_op to the list of the tx_ops */
-		list_add(&op->list, &bo->tx_ops);
+		add_op_to_list = true;
 
 	} /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */
 
@@ -1181,6 +1181,10 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		op->flags |= TX_ANNOUNCE;
 	}
 
+	/* add this bcm_op to the list of the tx_ops? */
+	if (add_op_to_list)
+		list_add_rcu(&op->list, &bo->tx_ops);
+
 	if (op->flags & TX_ANNOUNCE)
 		bcm_can_tx(op, NULL);
 
@@ -1373,9 +1377,6 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		hrtimer_setup(&op->thrtimer, bcm_rx_thr_handler, CLOCK_MONOTONIC,
 			      HRTIMER_MODE_REL_SOFT);
 
-		/* add this bcm_op to the list of the rx_ops */
-		list_add(&op->list, &bo->rx_ops);
-
 		/* call can_rx_register() */
 		do_rx_register = 1;
 
@@ -1449,10 +1450,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 					      bcm_rx_handler, op, "bcm", sk);
 		if (err) {
 			/* this bcm rx op is broken -> remove it */
-			list_del_rcu(&op->list);
 			bcm_remove_op(op);
 			return err;
 		}
+
+		/* add this bcm_op to the list of the rx_ops */
+		list_add_rcu(&op->list, &bo->rx_ops);
 	}
 
 	return msg_head->nframes * op->cfsiz + MHSIZ;
@@ -1786,8 +1789,10 @@ static int bcm_release(struct socket *sock)
 		remove_proc_entry(bo->procname, net->can.bcmproc_dir);
 #endif /* CONFIG_PROC_FS */
 
-	list_for_each_entry_safe(op, next, &bo->tx_ops, list)
+	list_for_each_entry_safe(op, next, &bo->tx_ops, list) {
+		list_del_rcu(&op->list);
 		bcm_remove_op(op);
+	}
 
 	list_for_each_entry_safe(op, next, &bo->rx_ops, list) {
 		/*
@@ -1818,8 +1823,10 @@ static int bcm_release(struct socket *sock)
 
 	synchronize_rcu();
 
-	list_for_each_entry_safe(op, next, &bo->rx_ops, list)
+	list_for_each_entry_safe(op, next, &bo->rx_ops, list) {
+		list_del_rcu(&op->list);
 		bcm_remove_op(op);
+	}
 
 	/* remove device reference */
 	if (bo->bound) {
-- 
2.53.0

[PATCH net 11/19] can: bcm: extend bcm_tx_lock usage for data and timer updates

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

Stage new CAN frame content for an existing tx op into a kmalloc()'d
buffer and validate it there, mirroring the approach already used in
bcm_rx_setup(). Only copy the validated data into op->frames while
holding op->bcm_tx_lock, so bcm_can_tx() and bcm_tx_timeout_handler()
can no longer observe a partially updated or unvalidated frame.

Add a missing error path for memcpy_from_msg() when copying CAN frame
data from userspace.

Also move the kt_ival1/kt_ival2/ival1/ival2 updates in bcm_tx_setup()
under op->bcm_tx_lock, and read kt_ival1/kt_ival2/count under the same
lock in bcm_tx_set_expiry() and bcm_tx_timeout_handler(), closing the
torn 64-bit ktime_t read on 32-bit platforms.

Fixes: c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates")
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-6-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 108 +++++++++++++++++++++++++++++++++++---------------
 1 file changed, 77 insertions(+), 31 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 5c1e83eeb4ff..68a62f605432 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -128,7 +128,7 @@ struct bcm_op {
 	struct canfd_frame last_sframe;
 	struct sock *sk;
 	struct net_device *rx_reg_dev;
-	spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */
+	spinlock_t bcm_tx_lock; /* protect tx data and timer updates */
 	spinlock_t bcm_rx_update_lock; /* protect filter/timer data updates */
 };
 
@@ -472,12 +472,18 @@ static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt)
 {
 	ktime_t ival;
 
+	spin_lock_bh(&op->bcm_tx_lock);
+
 	if (op->kt_ival1 && op->count)
 		ival = op->kt_ival1;
-	else if (op->kt_ival2)
+	else if (op->kt_ival2) {
 		ival = op->kt_ival2;
-	else
+	} else {
+		spin_unlock_bh(&op->bcm_tx_lock);
 		return false;
+	}
+
+	spin_unlock_bh(&op->bcm_tx_lock);
 
 	hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival));
 	return true;
@@ -494,25 +500,47 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
 {
 	struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer);
 	struct bcm_msg_head msg_head;
+	bool tx_ival1, tx_ival2;
+
+	/* snapshot kt_ival1/kt_ival2/count under lock to avoid torn
+	 * ktime_t reads racing with concurrent bcm_tx_setup() updates
+	 */
+	spin_lock_bh(&op->bcm_tx_lock);
+	tx_ival1 = op->kt_ival1 && (op->count > 0);
+	tx_ival2 = !!op->kt_ival2;
+	spin_unlock_bh(&op->bcm_tx_lock);
+
+	if (tx_ival1) {
+		u32 flags, count;
+		struct bcm_timeval ival1, ival2;
 
-	if (op->kt_ival1 && (op->count > 0)) {
 		bcm_can_tx(op, NULL);
-		if (!op->count && (op->flags & TX_COUNTEVT)) {
 
+		/* snapshot variables under lock to avoid torn reads racing
+		 * with concurrent bcm_tx_setup() updates
+		 */
+		spin_lock_bh(&op->bcm_tx_lock);
+		flags = op->flags;
+		count = op->count;
+		ival1 = op->ival1;
+		ival2 = op->ival2;
+		spin_unlock_bh(&op->bcm_tx_lock);
+
+		if (!count && (flags & TX_COUNTEVT)) {
 			/* create notification to user */
 			memset(&msg_head, 0, sizeof(msg_head));
 			msg_head.opcode  = TX_EXPIRED;
-			msg_head.flags   = op->flags;
-			msg_head.count   = op->count;
-			msg_head.ival1   = op->ival1;
-			msg_head.ival2   = op->ival2;
+			msg_head.flags   = flags;
+			msg_head.count   = count;
+			msg_head.ival1   = ival1;
+			msg_head.ival2   = ival2;
 			msg_head.can_id  = op->can_id;
 			msg_head.nframes = 0;
 
 			bcm_send_to_user(op, &msg_head, NULL, 0);
 		}
 
-	} else if (op->kt_ival2) {
+	} else if (tx_ival2) {
 		bcm_can_tx(op, NULL);
 	}
 
@@ -1036,6 +1064,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	/* check the given can_id */
 	op = bcm_find_op(&bo->tx_ops, msg_head, ifindex);
 	if (op) {
+		void *new_frames;
+
 		/* update existing BCM operation */
 
 		/*
@@ -1046,11 +1076,23 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (msg_head->nframes > op->nframes)
 			return -E2BIG;
 
-		/* update CAN frames content */
+		/* get new CAN frames content into a staging buffer before
+		 * locking: validate and normalize the frames there so that
+		 * bcm_can_tx() / bcm_tx_timeout_handler() never observe a
+		 * partially updated or unvalidated frame in op->frames
+		 */
+		new_frames = kmalloc(msg_head->nframes * op->cfsiz, GFP_KERNEL);
+		if (!new_frames)
+			return -ENOMEM;
+
 		for (i = 0; i < msg_head->nframes; i++) {
 
-			cf = op->frames + op->cfsiz * i;
+			cf = new_frames + op->cfsiz * i;
 			err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);
+			if (err < 0) {
+				kfree(new_frames);
+				return err;
+			}
 
 			if (op->flags & CAN_FD_FRAME) {
 				if (cf->len > 64)
@@ -1060,37 +1102,39 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 					err = -EINVAL;
 			}
 
-			if (err < 0)
+			if (err < 0) {
+				kfree(new_frames);
 				return err;
+			}
 
 			if (msg_head->flags & TX_CP_CAN_ID) {
 				/* copy can_id into frame */
 				cf->can_id = msg_head->can_id;
 			}
 		}
+
+		spin_lock_bh(&op->bcm_tx_lock);
+
+		/* update CAN frames content */
+		memcpy(op->frames, new_frames, msg_head->nframes * op->cfsiz);
+
 		op->flags = msg_head->flags;
 
-		/* only lock for unlikely count/nframes/currframe changes */
 		if (op->nframes != msg_head->nframes ||
-		    op->flags & TX_RESET_MULTI_IDX ||
-		    op->flags & SETTIMER) {
-
-			spin_lock_bh(&op->bcm_tx_lock);
-
-			if (op->nframes != msg_head->nframes ||
-			    op->flags & TX_RESET_MULTI_IDX) {
-				/* potentially update changed nframes */
-				op->nframes = msg_head->nframes;
-				/* restart multiple frame transmission */
-				op->currframe = 0;
-			}
-
-			if (op->flags & SETTIMER)
-				op->count = msg_head->count;
-
-			spin_unlock_bh(&op->bcm_tx_lock);
+		    op->flags & TX_RESET_MULTI_IDX) {
+			/* potentially update changed nframes */
+			op->nframes = msg_head->nframes;
+			/* restart multiple frame transmission */
+			op->currframe = 0;
 		}
 
+		if (op->flags & SETTIMER)
+			op->count = msg_head->count;
+
+		spin_unlock_bh(&op->bcm_tx_lock);
+
+		kfree(new_frames);
+
 	} else {
 		/* insert new BCM operation for the given can_id */
 
@@ -1165,10 +1209,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 	if (op->flags & SETTIMER) {
 		/* set timer values */
+		spin_lock_bh(&op->bcm_tx_lock);
 		op->ival1 = msg_head->ival1;
 		op->ival2 = msg_head->ival2;
 		op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
 		op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
+		spin_unlock_bh(&op->bcm_tx_lock);
 
 		/* disable an active timer due to zero values? */
 		if (!op->kt_ival1 && !op->kt_ival2)
-- 
2.53.0

[PATCH net 12/19] can: bcm: validate frame length in bcm_rx_setup() for RTR replies

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

bcm_tx_setup() validates cf->len against the CAN/CAN FD DLC limits
before installing frames for TX_SETUP, but bcm_rx_setup() never did
the same for the RTR-reply frame configured via RX_SETUP with
RX_RTR_FRAME.

Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-7-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 59 +++++++++++++++++++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 18 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 68a62f605432..2d9c9cd74536 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1246,22 +1246,37 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	return err;
 }
 
-static void bcm_rx_setup_rtr_check(struct bcm_msg_head *msg_head,
-				   struct bcm_op *op, void *new_frames)
+static int bcm_rx_setup_rtr_check(struct bcm_msg_head *msg_head,
+				  struct bcm_op *op, void *new_frames)
 {
+	struct canfd_frame *frame0 = new_frames;
+
+	if (!(msg_head->flags & RX_RTR_FRAME))
+		return 0;
+
+	/* this frame is sent out as-is by bcm_can_tx() whenever a matching
+	 * remote request is received, so validate its length the same way
+	 * bcm_tx_setup() validates TX_SETUP frames before installing it
+	 */
+	if (msg_head->flags & CAN_FD_FRAME) {
+		if (frame0->len > 64)
+			return -EINVAL;
+	} else {
+		if (frame0->len > 8)
+			return -EINVAL;
+	}
+
 	/* funny feature in RX(!)_SETUP only for RTR-mode:
 	 * copy can_id into frame BUT without RTR-flag to
 	 * prevent a full-load-loopback-test ... ;-]
 	 * normalize this on the staged buffer, before it is
 	 * ever installed into op->frames.
 	 */
-	if (msg_head->flags & RX_RTR_FRAME) {
-		struct canfd_frame *frame0 = new_frames;
+	if ((msg_head->flags & TX_CP_CAN_ID) ||
+	    frame0->can_id == op->can_id)
+		frame0->can_id = op->can_id & ~CAN_RTR_FLAG;
 
-		if ((msg_head->flags & TX_CP_CAN_ID) ||
-		    frame0->can_id == op->can_id)
-			frame0->can_id = op->can_id & ~CAN_RTR_FLAG;
-	}
+	return 0;
 }
 
 /*
@@ -1324,7 +1339,11 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 				return err;
 			}
 
-			bcm_rx_setup_rtr_check(msg_head, op, new_frames);
+			err = bcm_rx_setup_rtr_check(msg_head, op, new_frames);
+			if (err < 0) {
+				kfree(new_frames);
+				return err;
+			}
 		}
 
 		spin_lock_bh(&op->bcm_rx_update_lock);
@@ -1397,16 +1416,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (msg_head->nframes) {
 			err = memcpy_from_msg(op->frames, msg,
 					      msg_head->nframes * op->cfsiz);
-			if (err < 0) {
-				if (op->frames != &op->sframe)
-					kfree(op->frames);
-				if (op->last_frames != &op->last_sframe)
-					kfree(op->last_frames);
-				kfree(op);
-				return err;
-			}
+			if (err < 0)
+				goto free_op;
 
-			bcm_rx_setup_rtr_check(msg_head, op, op->frames);
+			err = bcm_rx_setup_rtr_check(msg_head, op, op->frames);
+			if (err < 0)
+				goto free_op;
 		}
 
 		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
@@ -1505,6 +1520,14 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	}
 
 	return msg_head->nframes * op->cfsiz + MHSIZ;
+
+free_op:
+	if (op->frames != &op->sframe)
+		kfree(op->frames);
+	if (op->last_frames != &op->last_sframe)
+		kfree(op->last_frames);
+	kfree(op);
+	return err;
 }
 
 /*
-- 
2.53.0

[PATCH net 13/19] can: bcm: add missing device refcount for CAN filter removal

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

sashiko-bot remarked a problem with a concurrent device unregistration
in isotp.c which also is present in the bcm.c code. A former fix for raw.c
commit c275a176e4b6 ("can: raw: add missing refcount for memory leak fix")
introduced a netdevice_tracker which solves the issue for bcm.c too.

bcm_release(), bcm_delete_rx_op() and bcm_notifier() relied on
dev_get_by_index(ifindex) to re-find the device for an rx_op before
unregistering its filter. If a concurrent NETDEV_UNREGISTER has already
unlisted the device from the ifindex table, that lookup fails and
can_rx_unregister() is silently skipped, leaving a stale CAN filter
pointing at the soon-to-be-freed bcm_op/socket.

Hold a netdev_hold()/netdev_put() tracked reference on op->rx_reg_dev
from the moment the rx filter is registered in bcm_rx_setup() until it
is unregistered in bcm_rx_unreg(), and use that reference directly in
bcm_release() and bcm_delete_rx_op() instead of re-looking the device
up by ifindex.

Reported-by: sashiko-bot@kernel.org
Closes: https://sashiko.dev/#/patchset/20260707094716.63578-1-socketcan@hartkopp.net
Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-8-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 47 +++++++++++++++++++++++++++--------------------
 1 file changed, 27 insertions(+), 20 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 2d9c9cd74536..25842061800b 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -128,6 +128,7 @@ struct bcm_op {
 	struct canfd_frame last_sframe;
 	struct sock *sk;
 	struct net_device *rx_reg_dev;
+	netdevice_tracker rx_reg_dev_tracker;
 	spinlock_t bcm_tx_lock; /* protect tx data and timer updates */
 	spinlock_t bcm_rx_update_lock; /* protect filter/timer data updates */
 };
@@ -937,6 +938,7 @@ static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
 
 		/* mark as removed subscription */
 		op->rx_reg_dev = NULL;
+		netdev_put(dev, &op->rx_reg_dev_tracker);
 	} else
 		printk(KERN_ERR "can-bcm: bcm_rx_unreg: registered device "
 		       "mismatch %p %p\n", op->rx_reg_dev, dev);
@@ -967,17 +969,14 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
 				 * Only remove subscriptions that had not
 				 * been removed due to NETDEV_UNREGISTER
 				 * in bcm_notifier()
+				 *
+				 * op->rx_reg_dev is a tracked reference taken
+				 * when the subscription was registered, so it
+				 * stays valid here even if a concurrent
+				 * NETDEV_UNREGISTER already unlisted the dev.
 				 */
-				if (op->rx_reg_dev) {
-					struct net_device *dev;
-
-					dev = dev_get_by_index(sock_net(op->sk),
-							       op->ifindex);
-					if (dev) {
-						bcm_rx_unreg(dev, op);
-						dev_put(dev);
-					}
-				}
+				if (op->rx_reg_dev)
+					bcm_rx_unreg(op->rx_reg_dev, op);
 			} else
 				can_rx_unregister(sock_net(op->sk), NULL,
 						  op->can_id,
@@ -1496,7 +1495,17 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 						      bcm_rx_handler, op,
 						      "bcm", sk);
 
-				op->rx_reg_dev = dev;
+				/* keep a tracked reference so that a later
+				 * unregister can safely reach the device even
+				 * if a concurrent NETDEV_UNREGISTER has
+				 * already unlisted it by ifindex
+				 */
+				if (!err) {
+					op->rx_reg_dev = dev;
+					netdev_hold(dev,
+						    &op->rx_reg_dev_tracker,
+						    GFP_KERNEL);
+				}
 				dev_put(dev);
 			} else {
 				/* the requested device is gone - do not
@@ -1873,16 +1882,14 @@ static int bcm_release(struct socket *sock)
 			 * Only remove subscriptions that had not
 			 * been removed due to NETDEV_UNREGISTER
 			 * in bcm_notifier()
+			 *
+			 * op->rx_reg_dev is a tracked reference taken
+			 * when the subscription was registered, so it
+			 * stays valid here even if a concurrent
+			 * NETDEV_UNREGISTER already unlisted the device.
 			 */
-			if (op->rx_reg_dev) {
-				struct net_device *dev;
-
-				dev = dev_get_by_index(net, op->ifindex);
-				if (dev) {
-					bcm_rx_unreg(dev, op);
-					dev_put(dev);
-				}
-			}
+			if (op->rx_reg_dev)
+				bcm_rx_unreg(op->rx_reg_dev, op);
 		} else
 			can_rx_unregister(net, NULL, op->can_id,
 					  REGMASK(op->can_id),
-- 
2.53.0

[PATCH net 14/19] can: bcm: fix stale rx/tx ops after device removal

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

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 <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-9-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 54 +++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 44 insertions(+), 10 deletions(-)

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)
-- 
2.53.0

[PATCH net 15/19] can: bcm: fix data race on rx_stamp/rx_ifindex in bcm_rx_handler()

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

For an rx op subscribed on all interfaces (ifindex == 0), the same op
is registered once in the shared per-netns wildcard filter list, so
bcm_rx_handler() can run concurrently on different CPUs for frames
arriving on different net devices.

op->rx_stamp and op->rx_ifindex were written before bcm_rx_update_lock was
taken, allowing concurrent writers to race each other - including a torn
store of the 64-bit rx_stamp on 32-bit platforms.

Beyond a torn store bcm_send_to_user() must report the timestamp/ifindex
of the very same frame whose content it is delivering. So the assignment
is placed in the same unbroken bcm_rx_update_lock section as the content
comparison.

As a side effect, the RTR-request frame feature (which never reach
bcm_send_to_user()) no longer updates rx_stamp/rx_ifindex, since only
the notification path needs them.

Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Reported-by: sashiko-bot@kernel.org
Closes: https://lore.kernel.org/linux-can/20260707145135.5BC831F00A3A@smtp.kernel.org/
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-10-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index a53dba6ab8b8..f213a0b37791 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -800,11 +800,6 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 	/* disable timeout */
 	hrtimer_cancel(&op->timer);
 
-	/* save rx timestamp */
-	op->rx_stamp = skb->tstamp;
-	/* save originator for recvfrom() */
-	op->rx_ifindex = skb->dev->ifindex;
-
 	/* op->flags/op->frames may be updated concurrently by bcm_rx_setup() */
 	spin_lock_bh(&op->bcm_rx_update_lock);
 
@@ -836,6 +831,14 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 			traffic_flags |= RX_OWN;
 	}
 
+	/* save rx timestamp and originator for recvfrom() under lock.
+	 * For an op subscribed on all interfaces (ifindex == 0)
+	 * bcm_rx_handler() can run concurrently on different CPUs so
+	 * the CAN content and the meta data must be bundled correctly.
+	 */
+	op->rx_stamp = skb->tstamp;
+	op->rx_ifindex = skb->dev->ifindex;
+
 	if (op->flags & RX_FILTER_ID) {
 		/* the easiest case */
 		bcm_rx_update_and_send(op, op->last_frames, rxframe,
-- 
2.53.0

[PATCH net 16/19] can: bcm: track a single source interface for ANYDEV timeout/throttle ops

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

An ANYDEV rx op (ifindex == 0) with an active RX timeout and/or
throttle timer has no defined semantics when matching frames arrive
from several interfaces: bcm_rx_handler() can run concurrently for
the same op on different CPUs, racing hrtimer_cancel()/
bcm_rx_starttimer() against bcm_rx_timeout_handler() and causing
spurious RX_TIMEOUT notifications and last_frames corruption. The
same concurrency lets throttled multiplex frames from different
interfaces clobber the single rx_ifindex/rx_stamp fields shared by
the op.

Add op->if_detected to track the first interface that delivers a
matching frame while a timeout/throttle timer is configured, and
reject frames from any other interface for that op. The claim is
decided in bcm_rx_handler() before hrtimer_cancel() touches
op->timer, so a rejected frame can never disturb the claimed
interface's watchdog. RTR-mode ops are excluded via RX_RTR_FRAME,
independent of kt_ival1/kt_ival2, since those may briefly hold a
stale value from an earlier non-RTR configuration.

The claim is released in bcm_notify() on NETDEV_UNREGISTER and in
bcm_rx_setup() when SETTIMER reconfigures the timer values.

A (re-)claim is only possible on CAN devices in NETREG_REGISTERED
dev->reg_state to cover the release in bcm_notify() where reg_state
becomes NETREG_UNREGISTERING until synchronize_net().

Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Reported-by: sashiko-bot@kernel.org
Closes: https://lore.kernel.org/linux-can/20260709105031.1A39C1F000E9@smtp.kernel.org/
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260714-bcm_fixes-v15-11-562f7e3e42da@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 49 ++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 44 insertions(+), 5 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index f213a0b37791..3d637a1e0ac1 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -117,6 +117,7 @@ struct bcm_op {
 	struct hrtimer timer, thrtimer;
 	ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg;
 	int rx_ifindex;
+	int if_detected; /* first received ifindex in ANYDEV rx_op mode */
 	int cfsiz;
 	u32 count;
 	u32 nframes;
@@ -797,6 +798,33 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 			return;
 	}
 
+	/* An ANYDEV op with an active RX timeout and/or throttle timer
+	 * tracks a single source interface: claim the first interface that
+	 * delivers a matching frame and reject frames from any other one,
+	 * before hrtimer_cancel() below can touch op->timer - this avoids
+	 * racing bcm_rx_timeout_handler() across concurrent interfaces.
+	 * RX_RTR_FRAME ops are excluded, as kt_ival1/kt_ival2 may briefly
+	 * hold a stale value from an earlier non-RTR configuration.
+	 */
+	if (!op->ifindex) {
+		spin_lock_bh(&op->bcm_rx_update_lock);
+
+		if (!(op->flags & RX_RTR_FRAME) &&
+		    (op->kt_ival1 || op->kt_ival2)) {
+			/* don't claim to vanishing interface */
+			if (!op->if_detected &&
+			    READ_ONCE(skb->dev->reg_state) == NETREG_REGISTERED)
+				op->if_detected = skb->dev->ifindex;
+
+			if (op->if_detected != skb->dev->ifindex) {
+				spin_unlock_bh(&op->bcm_rx_update_lock);
+				return;
+			}
+		}
+
+		spin_unlock_bh(&op->bcm_rx_update_lock);
+	}
+
 	/* disable timeout */
 	hrtimer_cancel(&op->timer);
 
@@ -831,10 +859,9 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 			traffic_flags |= RX_OWN;
 	}
 
-	/* save rx timestamp and originator for recvfrom() under lock.
-	 * For an op subscribed on all interfaces (ifindex == 0)
-	 * bcm_rx_handler() can run concurrently on different CPUs so
-	 * the CAN content and the meta data must be bundled correctly.
+	/* save rx timestamp and originator for recvfrom() under lock: an
+	 * ANYDEV op without an active timer can still run concurrently on
+	 * different CPUs, so content and meta data must be bundled here.
 	 */
 	op->rx_stamp = skb->tstamp;
 	op->rx_ifindex = skb->dev->ifindex;
@@ -1369,6 +1396,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
 			op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
 			op->kt_lastmsg = 0;
+			op->if_detected = 0; /* reclaim ifindex in ANYDEV mode */
 		}
 		spin_unlock_bh(&op->bcm_rx_update_lock);
 
@@ -1775,10 +1803,21 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
 		lock_sock(sk);
 
 		/* rx_ops: remove device specific receive entries */
-		list_for_each_entry(op, &bo->rx_ops, list)
+		list_for_each_entry(op, &bo->rx_ops, list) {
 			if (op->rx_reg_dev == dev)
 				bcm_rx_unreg(dev, op);
 
+			/* release an ANYDEV op's claim (see bcm_rx_handler())
+			 * on this now confirmed-gone interface.
+			 */
+			if (!op->ifindex) {
+				spin_lock_bh(&op->bcm_rx_update_lock);
+				if (op->if_detected == dev->ifindex)
+					op->if_detected = 0;
+				spin_unlock_bh(&op->bcm_rx_update_lock);
+			}
+		}
+
 		/* 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.
-- 
2.53.0

[PATCH net 17/19] can: isotp: use unconditional synchronize_rcu() in isotp_release()

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

isotp_notify() unregisters the (RCU) CAN filters via can_rx_unregister()
and clears so->bound without waiting for a grace period. isotp_release()
uses so->bound to decide whether it needs to call synchronize_rcu()
before cancelling so->rxtimer, so when NETDEV_UNREGISTER runs first it
skips that synchronize_rcu() and can cancel the timer while an
in-flight isotp_rcv() is still executing and about to re-arm it via
isotp_send_fc(), leading to a use-after-free timer callback on the
freed socket.

sakisho-bot remarked a problem with rtnl_lock held in isotp_notify(),
therefore make isotp_release() always call synchronize_rcu() before
cancelling the timers, regardless of so->bound. This still closes the
original race (isotp_notify() clearing so->bound without waiting for
in-flight isotp_rcv() callers before isotp_release() cancels the RX
timer) without adding any RCU wait to the netdevice notifier path.

Fixes: 14a4696bc311 ("can: isotp: isotp_release(): omit unintended hrtimer restart on socket release")
Closes: https://lore.kernel.org/linux-can/20260707085210.6B6C01F000E9@smtp.kernel.org/
Reported-by: Nico Yip <zdi-disclosures@trendmicro.com>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260712-isotp-fixes-v10-1-793a1b1ce17f@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index c48b4a818297..d30937345bcd 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1237,11 +1237,18 @@ static int isotp_release(struct socket *sock)
 						  SINGLE_MASK(so->txid),
 						  isotp_rcv_echo, sk);
 				dev_put(dev);
-				synchronize_rcu();
 			}
 		}
 	}
 
+	/* 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.
+	 */
+	synchronize_rcu();
+
 	hrtimer_cancel(&so->txfrtimer);
 	hrtimer_cancel(&so->txtimer);
 	hrtimer_cancel(&so->rxtimer);
-- 
2.53.0

[PATCH net 18/19] can: isotp: fix use-after-free race with concurrent NETDEV_UNREGISTER

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

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: sashiko-bot@kernel.org
Closes: https://lore.kernel.org/linux-can/20260707101420.47F261F000E9@smtp.kernel.org/
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260712-isotp-fixes-v10-2-793a1b1ce17f@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 85 +++++++++++++++++++++++++++++++++----------------
 1 file changed, 58 insertions(+), 27 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
@@ -152,6 +152,8 @@ 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;
@@ -978,6 +980,14 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			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);
@@ -1219,28 +1229,30 @@ static int isotp_release(struct socket *sock)
 	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;
+	/* 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);
 
-			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);
-			}
-		}
+		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
@@ -1253,9 +1265,6 @@ static int isotp_release(struct socket *sock)
 	hrtimer_cancel(&so->txtimer);
 	hrtimer_cancel(&so->rxtimer);
 
-	so->ifindex = 0;
-	so->bound = 0;
-
 	sock_orphan(sk);
 	sock->sk = NULL;
 
@@ -1310,6 +1319,7 @@ 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) {
@@ -1317,6 +1327,17 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 		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;
@@ -1329,14 +1350,12 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 		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;
@@ -1354,16 +1373,25 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 	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;
@@ -1566,7 +1594,7 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg,
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		return;
 
-	if (so->ifindex != dev->ifindex)
+	if (so->dev != dev)
 		return;
 
 	switch (msg) {
@@ -1582,10 +1610,12 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg,
 			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;
@@ -1645,6 +1675,7 @@ static int isotp_init(struct sock *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;
-- 
2.53.0

[PATCH net 19/19] can: isotp: serialize TX state transitions under so->rx_lock

[Marc Kleine-Budde]

From: Oliver Hartkopp <socketcan@hartkopp.net>

The TX state machine (so->tx.state) is driven from three contexts:
sendmsg() claiming and progressing a transfer, the RX path consuming
Flow Control/echo frames, and two hrtimers timing out a stalled
transfer. Mixing a lock-free cmpxchg() claim in sendmsg() with
hrtimer_cancel() calls made under so->rx_lock elsewhere left windows
where a frame or timer callback could act on a state that had already
moved on, corrupting an unrelated transfer.

so->rx_lock now covers the full lifecycle of a TX claim: sendmsg()
takes it to check so->tx.state is ISOTP_IDLE, switch it to
ISOTP_SENDING, bump so->tx_gen and drain the previous transfer's
timers - all as one critical section. isotp_rcv_fc()/isotp_rcv_cf()
already run under this lock via isotp_rcv(), and isotp_rcv_echo() now
takes it itself, so none of them can ever observe a transfer mid-claim.
This also means a transfer can no longer be handed to sendmsg()'s
cleanup paths (signal or send error) while another thread is
concurrently claiming or finishing it, so those paths can cancel
timers and reset the state unconditionally.

isotp_release() claims the socket the same way, so a racing sendmsg()
sees a consistent ISOTP_SHUTDOWN and skips arming its timer or sending.

Only the hrtimer callbacks stay outside so->rx_lock, since they run
under so->rx_lock's cancellation elsewhere and taking it themselves
would deadlock. so->tx_gen lets them recognize whether the transfer
they timed out is still the one currently active, so they don't
report an error against a transfer that has since completed or been
superseded.

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Reported-by: sashiko-bot@kernel.org
Closes: https://lore.kernel.org/linux-can/20260710142146.BDAE61F000E9@smtp.kernel.org/
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260712-isotp-fixes-v10-3-793a1b1ce17f@hartkopp.net
Cc: stable@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 202 ++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 160 insertions(+), 42 deletions(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index 44c044eb83e1..54becaf6898f 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -158,7 +158,7 @@ struct isotp_sock {
 	canid_t rxid;
 	ktime_t tx_gap;
 	ktime_t lastrxcf_tstamp;
-	struct hrtimer rxtimer, txtimer, txfrtimer;
+	struct hrtimer rxtimer, txtimer, txfrtimer, echotimer;
 	struct can_isotp_options opt;
 	struct can_isotp_fc_options rxfc, txfc;
 	struct can_isotp_ll_options ll;
@@ -166,6 +166,7 @@ struct isotp_sock {
 	u32 force_tx_stmin;
 	u32 force_rx_stmin;
 	u32 cfecho; /* consecutive frame echo tag */
+	u32 tx_gen; /* generation, bumped per new tx transfer */
 	struct tpcon rx, tx;
 	struct list_head notifier;
 	wait_queue_head_t wait;
@@ -378,6 +379,15 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)
 
 	hrtimer_cancel(&so->txtimer);
 
+	/* isotp_tx_timeout() may have given up on this job while
+	 * hrtimer_cancel() above waited for it to finish; so->rx_lock
+	 * (held by our caller isotp_rcv()) rules out a concurrent claim,
+	 * so a plain recheck is enough here.
+	 */
+	if (so->tx.state != ISOTP_WAIT_FC &&
+	    so->tx.state != ISOTP_WAIT_FIRST_FC)
+		return 1;
+
 	if ((cf->len < ae + FC_CONTENT_SZ) ||
 	    ((so->opt.flags & ISOTP_CHECK_PADDING) &&
 	     check_pad(so, cf, ae + FC_CONTENT_SZ, so->opt.rxpad_content))) {
@@ -424,7 +434,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)
 		so->tx.bs = 0;
 		so->tx.state = ISOTP_SENDING;
 		/* send CF frame and enable echo timeout handling */
-		hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
+		hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
 			      HRTIMER_MODE_REL_SOFT);
 		isotp_send_cframe(so);
 		break;
@@ -577,6 +587,14 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,
 
 	hrtimer_cancel(&so->rxtimer);
 
+	/* isotp_rx_timer_handler() may have raced us for so->rx.state
+	 * while hrtimer_cancel() above waited for it to finish, already
+	 * reporting ETIMEDOUT and resetting the reception; don't process
+	 * this CF into a reassembly that has already been given up on.
+	 */
+	if (so->rx.state != ISOTP_WAIT_DATA)
+		return 1;
+
 	/* CFs are never longer than the FF */
 	if (cf->len > so->rx.ll_dl)
 		return 1;
@@ -872,20 +890,36 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data)
 	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
 
 	/* only handle my own local echo CF/SF skb's (no FF!) */
-	if (skb->sk != sk || so->cfecho != *(u32 *)cf->data)
+	if (skb->sk != sk)
 		return;
 
+	/* unlike isotp_rcv_fc()/isotp_rcv_cf(), not already under so->rx_lock
+	 * (no isotp_rcv() caller here), so take it ourselves
+	 */
+	spin_lock(&so->rx_lock);
+
+	/* so->cfecho may since belong to a new transfer; recheck under lock */
+	if (so->cfecho != *(u32 *)cf->data)
+		goto out_unlock;
+
 	/* cancel local echo timeout */
-	hrtimer_cancel(&so->txtimer);
+	hrtimer_cancel(&so->echotimer);
 
 	/* local echo skb with consecutive frame has been consumed */
 	so->cfecho = 0;
 
+	/* claiming a transfer also takes so->rx_lock, so a plain recheck
+	 * is enough: so->tx.state can't have flipped to ISOTP_SENDING for
+	 * a new claim while we're still in here
+	 */
+	if (so->tx.state != ISOTP_SENDING)
+		goto out_unlock;
+
 	if (so->tx.idx >= so->tx.len) {
 		/* we are done */
 		so->tx.state = ISOTP_IDLE;
 		wake_up_interruptible(&so->wait);
-		return;
+		goto out_unlock;
 	}
 
 	if (so->txfc.bs && so->tx.bs >= so->txfc.bs) {
@@ -893,53 +927,83 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data)
 		so->tx.state = ISOTP_WAIT_FC;
 		hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0),
 			      HRTIMER_MODE_REL_SOFT);
-		return;
+		goto out_unlock;
 	}
 
 	/* no gap between data frames needed => use burst mode */
 	if (!so->tx_gap) {
 		/* enable echo timeout handling */
-		hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
+		hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
 			      HRTIMER_MODE_REL_SOFT);
 		isotp_send_cframe(so);
-		return;
+		goto out_unlock;
 	}
 
 	/* start timer to send next consecutive frame with correct delay */
 	hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT);
+
+out_unlock:
+	spin_unlock(&so->rx_lock);
 }
 
-static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer)
+/* shared by so->txtimer's and so->echotimer's callbacks. Both timers get
+ * cancelled under so->rx_lock elsewhere, so this must stay lock-free to
+ * avoid deadlocking with that; uses so->tx_gen instead to avoid tainting
+ * a new transfer with an error from the one that just timed out.
+ */
+static enum hrtimer_restart isotp_tx_timeout(struct isotp_sock *so)
 {
-	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
-					     txtimer);
 	struct sock *sk = &so->sk;
+	u32 gen = READ_ONCE(so->tx_gen);
+	u32 old_state = READ_ONCE(so->tx.state);
 
 	/* don't handle timeouts in IDLE or SHUTDOWN state */
-	if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN)
+	if (old_state == ISOTP_IDLE || old_state == ISOTP_SHUTDOWN)
+		return HRTIMER_NORESTART;
+
+	/* only claim the timeout if the state is still unchanged */
+	if (cmpxchg(&so->tx.state, old_state, ISOTP_IDLE) != old_state)
 		return HRTIMER_NORESTART;
 
 	/* we did not get any flow control or echo frame in time */
 
-	/* report 'communication error on send' */
-	sk->sk_err = ECOMM;
-	if (!sock_flag(sk, SOCK_DEAD))
-		sk_error_report(sk);
+	if (READ_ONCE(so->tx_gen) == gen) {
+		/* report 'communication error on send' */
+		sk->sk_err = ECOMM;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk_error_report(sk);
+	}
 
-	/* reset tx state */
-	so->tx.state = ISOTP_IDLE;
 	wake_up_interruptible(&so->wait);
 
 	return HRTIMER_NORESTART;
 }
 
+/* so->txtimer: fires when a Flow Control frame does not arrive in time */
+static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer)
+{
+	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
+					     txtimer);
+
+	return isotp_tx_timeout(so);
+}
+
+/* so->echotimer: fires when a sent CF/SF's local echo does not arrive */
+static enum hrtimer_restart isotp_echo_timer_handler(struct hrtimer *hrtimer)
+{
+	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
+					     echotimer);
+
+	return isotp_tx_timeout(so);
+}
+
 static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer)
 {
 	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
 					     txfrtimer);
 
 	/* start echo timeout handling and cover below protocol error */
-	hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
+	hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
 		      HRTIMER_MODE_REL_SOFT);
 
 	/* cfecho should be consumed by isotp_rcv_echo() here */
@@ -960,13 +1024,24 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
 	int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0;
 	s64 hrtimer_sec = ISOTP_ECHO_TIMEOUT;
+	struct hrtimer *tx_hrt = &so->echotimer;
+	u32 new_state = ISOTP_SENDING;
 	int off;
 	int err;
 
 	if (!so->bound || so->tx.state == ISOTP_SHUTDOWN)
 		return -EADDRNOTAVAIL;
 
-	while (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) {
+	/* claim the socket under so->rx_lock: this serializes the claim
+	 * with the RX path and with sendmsg()'s own error paths below, so
+	 * none of them can ever see a transfer mid-claim
+	 */
+	for (;;) {
+		spin_lock_bh(&so->rx_lock);
+		if (READ_ONCE(so->tx.state) == ISOTP_IDLE)
+			break;
+		spin_unlock_bh(&so->rx_lock);
+
 		/* we do not support multiple buffers - for now */
 		if (msg->msg_flags & MSG_DONTWAIT)
 			return -EAGAIN;
@@ -975,11 +1050,23 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			return -EADDRNOTAVAIL;
 
 		/* wait for complete transmission of current pdu */
-		err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+		err = wait_event_interruptible(so->wait,
+					       so->tx.state == ISOTP_IDLE);
 		if (err)
-			goto err_event_drop;
+			return err;
 	}
 
+	/* new transfer: bump so->tx_gen and drain the old one's timers,
+	 * still under the so->rx_lock we just claimed the socket with
+	 */
+	WRITE_ONCE(so->tx.state, ISOTP_SENDING);
+	WRITE_ONCE(so->tx_gen, READ_ONCE(so->tx_gen) + 1);
+	hrtimer_cancel(&so->txtimer);
+	hrtimer_cancel(&so->echotimer);
+	hrtimer_cancel(&so->txfrtimer);
+	so->cfecho = 0;
+	spin_unlock_bh(&so->rx_lock);
+
 	/* so->bound is only checked once above - a wakeup may have
 	 * unbound/rebound the socket meanwhile, so re-validate it
 	 */
@@ -1096,18 +1183,33 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			so->cfecho = *(u32 *)cf->data;
 		} else {
 			/* standard flow control check */
-			so->tx.state = ISOTP_WAIT_FIRST_FC;
+			new_state = ISOTP_WAIT_FIRST_FC;
 
 			/* start timeout for FC */
 			hrtimer_sec = ISOTP_FC_TIMEOUT;
+			tx_hrt = &so->txtimer;
 
 			/* no CF echo tag for isotp_rcv_echo() (FF-mode) */
 			so->cfecho = 0;
 		}
 	}
 
-	hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0),
+	spin_lock_bh(&so->rx_lock);
+	if (so->tx.state == ISOTP_SHUTDOWN) {
+		/* isotp_release() has since taken over and already drained
+		 * our timers - don't send into a socket that's going away
+		 */
+		spin_unlock_bh(&so->rx_lock);
+		kfree_skb(skb);
+		dev_put(dev);
+		wake_up_interruptible(&so->wait);
+		return -EADDRNOTAVAIL;
+	}
+	/* WAIT_FIRST_FC for standard FF, else stays ISOTP_SENDING */
+	so->tx.state = new_state;
+	hrtimer_start(tx_hrt, ktime_set(hrtimer_sec, 0),
 		      HRTIMER_MODE_REL_SOFT);
+	spin_unlock_bh(&so->rx_lock);
 
 	/* send the first or only CAN frame */
 	cf->flags = so->ll.tx_flags;
@@ -1120,13 +1222,10 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
 			       __func__, ERR_PTR(err));
 
+		spin_lock_bh(&so->rx_lock);
 		/* no transmission -> no timeout monitoring */
-		hrtimer_cancel(&so->txtimer);
-
-		/* reset consecutive frame echo tag */
-		so->cfecho = 0;
-
-		goto err_out_drop;
+		hrtimer_cancel(tx_hrt);
+		goto err_out_drop_locked;
 	}
 
 	if (wait_tx_done) {
@@ -1142,14 +1241,21 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 
 	return size;
 
+err_out_drop:
+	/* claimed but nothing sent yet - no timer to cancel */
+	spin_lock_bh(&so->rx_lock);
+	goto err_out_drop_locked;
 err_event_drop:
-	/* got signal: force tx state machine to be idle */
-	so->tx.state = ISOTP_IDLE;
+	/* interrupted waiting on our own transfer - drain its timers */
+	spin_lock_bh(&so->rx_lock);
 	hrtimer_cancel(&so->txfrtimer);
 	hrtimer_cancel(&so->txtimer);
-err_out_drop:
-	/* drop this PDU and unlock a potential wait queue */
+	hrtimer_cancel(&so->echotimer);
+err_out_drop_locked:
+	/* release the claim; so->rx_lock still held from above */
+	so->cfecho = 0;
 	so->tx.state = ISOTP_IDLE;
+	spin_unlock_bh(&so->rx_lock);
 	wake_up_interruptible(&so->wait);
 
 	return err;
@@ -1211,13 +1317,20 @@ static int isotp_release(struct socket *sock)
 	so = isotp_sk(sk);
 	net = sock_net(sk);
 
-	/* wait for complete transmission of current pdu */
-	while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 &&
-	       cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE)
+	/* best-effort: wait for a running pdu to finish, but don't block on
+	 * it forever - give up after the first signal
+	 */
+	while (so->tx.state != ISOTP_IDLE &&
+	       wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0)
 		;
 
-	/* force state machines to be idle also when a signal occurred */
+	/* claim the socket under so->rx_lock like sendmsg() does, so its
+	 * claim can't race the forced ISOTP_SHUTDOWN below; force it
+	 * unconditionally, even when a signal cut the wait above short
+	 */
+	spin_lock_bh(&so->rx_lock);
 	so->tx.state = ISOTP_SHUTDOWN;
+	spin_unlock_bh(&so->rx_lock);
 	so->rx.state = ISOTP_IDLE;
 
 	spin_lock(&isotp_notifier_lock);
@@ -1263,6 +1376,7 @@ static int isotp_release(struct socket *sock)
 
 	hrtimer_cancel(&so->txfrtimer);
 	hrtimer_cancel(&so->txtimer);
+	hrtimer_cancel(&so->echotimer);
 	hrtimer_cancel(&so->rxtimer);
 
 	sock_orphan(sk);
@@ -1702,10 +1816,14 @@ static int isotp_init(struct sock *sk)
 	so->rx.buflen = ARRAY_SIZE(so->rx.sbuf);
 	so->tx.buflen = ARRAY_SIZE(so->tx.sbuf);
 
-	hrtimer_setup(&so->rxtimer, isotp_rx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	hrtimer_setup(&so->txtimer, isotp_tx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	hrtimer_setup(&so->txfrtimer, isotp_txfr_timer_handler, CLOCK_MONOTONIC,
-		      HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->rxtimer, isotp_rx_timer_handler,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->txtimer, isotp_tx_timer_handler,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->echotimer, isotp_echo_timer_handler,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->txfrtimer, isotp_txfr_timer_handler,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
 
 	init_waitqueue_head(&so->wait);
 	spin_lock_init(&so->rx_lock);
-- 
2.53.0

Re: [PATCH net 01/19] can: vxcan: Kconfig: fix description stating no local echo provided

[patchwork-bot+netdevbpf]

Hello:

This series was applied to netdev/net.git (main)
by Marc Kleine-Budde <mkl@pengutronix.de>:

On Thu, 16 Jul 2026 17:47:26 +0200 you wrote:
> From: Alexander Hölzl <alexander.hoelzl@gmx.net>
> 
> The Kconfig description of the vxcan kernel module erroneously states the
> the vxcan interface does not provide a local echo of sent can frames.
> However this behavior changed in commit 259bdba27e32 ("vxcan: enable local
> echo for sent CAN frames") and vxcan interfaces now provide a local echo.
> 
> [...]

Here is the summary with links:
  - [net,01/19] can: vxcan: Kconfig: fix description stating no local echo provided
    https://git.kernel.org/netdev/net/c/79adf48fb091
  - [net,02/19] can: esd_usb: kill anchored URBs before freeing netdevs
    https://git.kernel.org/netdev/net/c/c43122fef328
  - [net,03/19] can: raw: add locking for raw flags bitfield
    https://git.kernel.org/netdev/net/c/1e5185c09058
  - [net,04/19] can: j1939: fix lockless local-destination check
    https://git.kernel.org/netdev/net/c/e4e8af62adab
  - [net,05/19] can: peak: Modification of references to email accounts being deleted
    https://git.kernel.org/netdev/net/c/d83762005c13
  - [net,06/19] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF
    https://git.kernel.org/netdev/net/c/68973f9db761
  - [net,07/19] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure
    https://git.kernel.org/netdev/net/c/d9b091d9d22f
  - [net,08/19] can: bcm: add locking when updating filter and timer values
    https://git.kernel.org/netdev/net/c/749179c2e25b
  - [net,09/19] can: bcm: fix CAN frame rx/tx statistics
    https://git.kernel.org/netdev/net/c/e6c24ba95fc3
  - [net,10/19] can: bcm: add missing rcu list annotations and operations
    https://git.kernel.org/netdev/net/c/7b2c3eabc4da
  - [net,11/19] can: bcm: extend bcm_tx_lock usage for data and timer updates
    https://git.kernel.org/netdev/net/c/12ce799f7ab1
  - [net,12/19] can: bcm: validate frame length in bcm_rx_setup() for RTR replies
    https://git.kernel.org/netdev/net/c/62ec41f36464
  - [net,13/19] can: bcm: add missing device refcount for CAN filter removal
    https://git.kernel.org/netdev/net/c/d59948293ea3
  - [net,14/19] can: bcm: fix stale rx/tx ops after device removal
    https://git.kernel.org/netdev/net/c/3b762c0d9503
  - [net,15/19] can: bcm: fix data race on rx_stamp/rx_ifindex in bcm_rx_handler()
    https://git.kernel.org/netdev/net/c/58fd6cbc8541
  - [net,16/19] can: bcm: track a single source interface for ANYDEV timeout/throttle ops
    https://git.kernel.org/netdev/net/c/2f5976f54a04
  - [net,17/19] can: isotp: use unconditional synchronize_rcu() in isotp_release()
    https://git.kernel.org/netdev/net/c/9b1a02e0d980
  - [net,18/19] can: isotp: fix use-after-free race with concurrent NETDEV_UNREGISTER
    https://git.kernel.org/netdev/net/c/20bab8b88baa
  - [net,19/19] can: isotp: serialize TX state transitions under so->rx_lock
    https://git.kernel.org/netdev/net/c/cf070fe33bfb

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html

Re: [PATCH net 06/19] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:

Pre-existing issues:
- [High] Unprotected concurrent modification of `op->frames` in `bcm_tx_setup` can lead to corrupted or torn CAN frames being transmitted.
- [High] Unprotected modification of `op->frames` and `op->flags` in `bcm_rx_setup` races with `bcm_rx_handler` in softirq context.
- [High] The `tx_ops` and `rx_ops` lists are updated without RCU list primitives, creating a data race with concurrent readers in `bcm_proc_show()`.
- [Medium] Concurrent execution of `bcm_rx_handler` on multiple CPUs causes data corruption for `op->last_frames` and statistics.
--

--- Patch [6]: [PATCH net 06/19] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF ---
commit 542011e18159cf5ca68d911f15d0136be9c07cb9
Author: Lee Jones <lee@kernel.org>
Subject: can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF

This commit resolves a use-after-free by deferring timer cancellation and 
memory deallocation to a dedicated unbound workqueue. It also takes a 
reference on op->sk to ensure the socket is not freed while timers are 
still armed.

Link: https://patch.msgid.link/20260714-bcm_fixes-v15-1-562f7e3e42da@hartkopp.net

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index a4bef2c48a559..bdf53241bd7b3 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c
[ ... ]
> @@ -1060,6 +1081,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
>  
>  		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
>  		op->sk = sk;
> +		sock_hold(sk);
>  		op->ifindex = ifindex;

[Severity: High]
This isn't a bug introduced by this patch, but does the unprotected 
modification of op->frames in bcm_tx_setup() allow torn CAN frames to be 
transmitted?

When updating an existing operation, the code copies data from userspace:

bcm_tx_setup() {
    ...
    err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);
    ...
}

Could a concurrent bcm_can_tx() executed by the TX timer read from 
op->frames while the copy is happening, since the timer drops the 
bcm_tx_lock before calling skb_put_data(skb, cf, op->cfsiz)?

[Severity: High]
This is a pre-existing issue, but does adding new elements to the ops 
lists create a data race with concurrent readers?

When adding a new element, the setup functions call list_add():

bcm_tx_setup() {
    ...
    list_add(&op->list, &bo->tx_ops);
    ...
}

Since list_add() lacks RCU write barriers, could concurrent readers in 
bcm_proc_show() observe torn list pointers when iterating over tx_ops 
under rcu_read_lock()?

[ ... ]
> @@ -1221,6 +1243,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
>  
>  		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
>  		op->sk = sk;
> +		sock_hold(sk);
>  		op->ifindex = ifindex;

[Severity: High]
This is a pre-existing issue, but can bcm_rx_setup() race with 
bcm_rx_handler() in softirq context when modifying op->frames?

When bcm_rx_setup() updates an existing operation, it copies frame data:

bcm_rx_setup() {
    ...
    err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz);
    ...
}

Since this is only protected by lock_sock() and not serialized against 
softirq, could an incoming CAN frame trigger bcm_rx_handler() 
concurrently, leading to inconsistent filter configurations and 
out-of-bounds array accesses when op->nframes changes?

[Severity: Medium]
This isn't a bug introduced by this patch, but are the shared RX 
statistics and op->last_frames vulnerable to data corruption?

If bcm_rx_handler() runs concurrently on multiple CPUs for the same 
bcm_op, it performs non-atomic updates:

bcm_rx_handler() {
    ...
    op->frames_abs++;
    ...
    bcm_rx_update_and_send(op, op->last_frames, rxframe, traffic_flags);
    ...
}

Does modifying op->last_frames and op->frames_abs without holding a 
spinlock allow torn writes and lost increments?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=6

Re: [PATCH net 09/19] can: bcm: fix CAN frame rx/tx statistics

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] Unsynchronized concurrent updates to rx_stamp and rx_ifindex in bcm_rx_handler()
- [High] Missing RCU memory barriers for BCM operations lists (rx_ops and tx_ops)
--

--- Patch [9]: [PATCH net 09/19] can: bcm: fix CAN frame rx/tx statistics ---
commit d8d928a86f45beee426bc4e5b96d4a141f67ddbb
Author: Oliver Hartkopp <socketcan@hartkopp.net>
Subject: can: bcm: fix CAN frame rx/tx statistics

KCSAN detected a data race within the bcm_rx_handler() when two CAN frames
have been simultaneously received and processed in a single rx op by two
different CPUs. This patch uses atomic operations with (signed) long data types
to access the statistics in the hot path.

Link: https://patch.msgid.link/20260714-bcm_fixes-v15-4-562f7e3e42da@hartkopp.net

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index 1e5f8d65d351b..03c98e4cc677d 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c
[ ... ]
> @@ -229,10 +229,13 @@ static int bcm_proc_show(struct seq_file *m, void *v)
>  
>  	list_for_each_entry_rcu(op, &bo->rx_ops, list) {
>  
> -		unsigned long reduction;
> +		long reduction, frames_filtered, frames_abs;
> +
> +		frames_filtered = atomic_long_read(&op->frames_filtered);
> +		frames_abs = atomic_long_read(&op->frames_abs);

[Severity: High]
This isn't a bug introduced by this patch, but while we're in bcm_proc_show(),
does this function safely traverse both operation lists?

Looking further down in bcm_proc_show(), tx_ops is traversed holding only
rcu_read_lock():

	list_for_each_entry(op, &bo->tx_ops, list) {

However, this uses list_for_each_entry() instead of list_for_each_entry_rcu(),
which misses the necessary load-acquire operations.

Additionally, in bcm_tx_setup() and bcm_rx_setup(), new BCM operations are
added to these lists without RCU barriers:

net/can/bcm.c:bcm_tx_setup() {
    ...
	/* add this bcm_op to the list of the tx_ops */
	list_add(&op->list, &bo->tx_ops);
    ...
}

and:

net/can/bcm.c:bcm_rx_setup() {
    ...
	/* add this bcm_op to the list of the rx_ops */
	list_add(&op->list, &bo->rx_ops);
    ...
}

Could using list_add() instead of list_add_rcu() miss the store-release memory
barriers required to safely publish the newly initialized node to concurrent
RCU readers? This could allow the procfs reader to observe uninitialized
or partially initialized list nodes.

[ ... ]
> @@ -756,24 +775,30 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
>  	op->rx_stamp = skb->tstamp;
>  	/* save originator for recvfrom() */
>  	op->rx_ifindex = skb->dev->ifindex;
> -	/* update statistics */
> -	op->frames_abs++;
>  
> -	/* snapshot the flag under lock: op->flags/op->frames may be updated
> -	 * concurrently by bcm_rx_setup().
> -	 */
> +	/* op->flags/op->frames may be updated concurrently by bcm_rx_setup() */
>  	spin_lock_bh(&op->bcm_rx_update_lock);

[Severity: High]
This is a pre-existing issue, but while the statistics updates are moved into
the locked section, rx_stamp and rx_ifindex appear to remain unprotected.

For an RX operation subscribed to all interfaces (ifindex == 0),
bcm_rx_handler() can execute concurrently on different CPUs for the same
op.

Because op->rx_stamp and op->rx_ifindex are updated before acquiring
bcm_rx_update_lock, if two frames arrive concurrently on different CPUs,
could the first CPU waiting for the lock have its metadata overwritten by
the second CPU?

The first CPU would then process its payload but bundle it with the timestamp
and interface index of the second CPU's frame, returning corrupted metadata
to userspace. On 32-bit systems, could this concurrent unsynchronized write to
the 64-bit ktime_t also cause a torn read?

Should these metadata assignments be moved inside the spin_lock_bh() section?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=9

Re: [PATCH net 02/19] can: esd_usb: kill anchored URBs before freeing netdevs

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:

Pre-existing issues:
- [Critical] This problem wasn't introduced by this patch, but a missing bounds check on `dev->net_count` derived from the USB device response leads to a critical heap buffer overflow.
- [High] This problem wasn't introduced by this patch, but a malicious USB device can cause an infinite loop and CPU hard lockup by sending a message with length 0.
- [High] This problem wasn't introduced by this patch, but a malicious USB device can trigger an out-of-bounds memory read by sending a malformed or truncated message payload.
- [High] This problem wasn't introduced by this patch, but a missing NULL check on partially initialized network interfaces allows a malicious USB device to crash the kernel via NULL pointer dereference.
- [High] This problem wasn't introduced by this patch, but there is a permanent leakage of TX contexts on URB submission failure, leading to a permanent DoS of the interface.
--

--- Patch [2]: [PATCH net 02/19] can: esd_usb: kill anchored URBs before freeing netdevs ---
commit 1a29cc039e833667b5ba86f653b2a7b3b73983e1
Author: Fan Wu <fanwu01@zju.edu.cn>

can: esd_usb: kill anchored URBs before freeing netdevs

esd_usb_disconnect() frees each CAN netdev with free_candev() inside
its per-netdev loop and only calls unlink_all_urbs() afterwards.
The per-netdev private data is embedded in the net_device allocation,
so once free_candev() has run, dev->nets points to freed memory.
Reordering the teardown to match other CAN/USB drivers avoids this.

Link: https://patch.msgid.link/20260709164159.497640-1-fanwu01@zju.edu.cn

> diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c
> index d257440fa01ff..f41d4a0d140f7 100644
> --- a/drivers/net/can/usb/esd_usb.c
> +++ b/drivers/net/can/usb/esd_usb.c
[ ... ]
> @@ -1390,10 +1390,13 @@ static void esd_usb_disconnect(struct usb_interface *intf)
>  				netdev = dev->nets[i]->netdev;
>  				netdev_info(netdev, "unregister\n");
>  				unregister_netdev(netdev);
> -				free_candev(netdev);
>  			}
>  		}
>  		unlink_all_urbs(dev);
> +		for (i = 0; i < dev->net_count; i++) {
> +			if (dev->nets[i])
> +				free_candev(dev->nets[i]->netdev);
> +		}
>  		kfree(dev);
>  	}
>  }

[Severity: High]
This isn't a bug introduced by this patch, but while reviewing the driver 
code I noticed a potential CPU hard lockup in esd_usb_read_bulk_callback() in 
drivers/net/can/usb/esd_usb.c:

    while (pos < urb->actual_length) {
        ...
        pos += msg->hdr.len * sizeof(u32); 

If a USB device sends a message where len is set to 0, won't this loop run 
infinitely since pos is never advanced?

[Severity: High]
This is a pre-existing issue, but could a USB device trigger an out-of-bounds 
memory read by sending a malformed message payload? 

In esd_usb_read_bulk_callback() in drivers/net/can/usb/esd_usb.c:

    msg = (union esd_usb_msg *)(urb->transfer_buffer + pos);
    switch (msg->hdr.cmd) {
    ...

Are the message fields dereferenced here before verifying if the remaining 
bytes in the transfer buffer are sufficient to back the structure?

[Severity: High]
This problem wasn't introduced by this patch, but could a USB device crash 
the kernel via a NULL pointer dereference? 

In esd_usb_probe() in drivers/net/can/usb/esd_usb.c, we have:

    for (i = 0; i < dev->net_count; i++)
        esd_usb_probe_one_net(intf, i);

If esd_usb_probe_one_net() fails, it returns an error but the driver ignores
the return value, leaving dev->nets[i] as NULL. 

Later, if esd_usb_read_bulk_callback() receives a message targeted at this 
failed index:

    case ESD_USB_CMD_CAN_RX:
        ...
        esd_usb_rx_can_msg(dev->nets[msg->rx.net], msg);

Is it possible this unconditionally dereferences dev->nets[msg->rx.net] without 
checking if it is NULL first?

[Severity: Critical]
This isn't a bug introduced by this patch, but is there a missing bounds 
check on dev->net_count in drivers/net/can/usb/esd_usb.c?

In esd_usb_probe():

    dev->net_count = (int)msg->version_reply.nets;

The array upper bound is set based on untrusted USB input with no validation 
against the structural maximum (ESD_USB_MAX_NETS). 

Later in esd_usb_probe_one_net():

    dev->nets[index] = priv;

Could a USB device claim a large number of nets and cause a heap buffer 
overflow by writing past the end of the dev->nets array?

[Severity: High]
This is a pre-existing issue, but does the error handling in 
esd_usb_start_xmit() in drivers/net/can/usb/esd_usb.c leak TX contexts?

    err = usb_submit_urb(urb, GFP_ATOMIC);
    if (err) {
        can_free_echo_skb(netdev, context->echo_index, NULL);
        atomic_dec(&priv->active_tx_jobs);
        usb_unanchor_urb(urb);
        stats->tx_dropped++;

If the URB submission fails, the path drops the SKB and untracks the job, but 
forgets to reset context->echo_index (e.g. to ESD_USB_MAX_TX_URBS). 

Could this permanently leak the context slot, eventually exhausting all 
available contexts and leading to a denial of service?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=2

Re: [PATCH net 08/19] can: bcm: add locking when updating filter and timer values

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

New issues:
- [Medium] A race condition in bcm_can_tx's new heuristic skips the first frame of a restarted multi-frame sequence if the concurrent transmission happens to be at index 0.

Pre-existing issues:
- [High] Missing payload length validation for RX_RTR_FRAME operations allows out-of-bounds memory reads when transmitting replies.
- [High] Modifying the CAN_FD_FRAME flag on an existing BCM RX operation creates a mismatch between op->flags and op->cfsiz, leading to out-of-bounds reads and an information leak.
--

--- Patch [8]: [PATCH net 08/19] can: bcm: add locking when updating filter and timer values ---
commit c6674a9f75532d12e818868002b6c50a902d8b3e
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: add locking when updating filter and timer values

This patch introduces a new per-op lock (bcm_rx_update_lock) to protect
concurrent accesses to timer and filter data during CAN traffic reception.
It also addresses race conditions related to modifying frames and ensures
consistent RTR frame preparation.

Link: https://patch.msgid.link/20260714-bcm_fixes-v15-3-562f7e3e42da@hartkopp.net

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index b612135b017d1..1e5f8d65d351b 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c

[ ... ]

> @@ -341,14 +348,20 @@ static void bcm_can_tx(struct bcm_op *op)
>  	if (!err)
>  		op->frames_abs++;
>  
> -	op->currframe++;
> +	/* only advance the cyclic sequence if nothing reset currframe while
> +	 * we were sending - a concurrent TX_RESET_MULTI_IDX means this
> +	 * frame's bookkeeping belongs to a sequence that no longer exists
> +	 */
> +	if (!cyclic || op->currframe == idx) {
> +		op->currframe++;

[Severity: Medium]
Does this new heuristic skip the first frame of a restarted multi-frame
sequence if the concurrent transmission happens to be at index 0?

If a concurrent bcm_tx_setup() resets the sequence by setting
op->currframe = 0 while bcm_can_tx() is actively transmitting frame
index 0 (where idx == 0), the condition will evaluate to true.
This would increment op->currframe to 1, causing the newly configured
sequence to incorrectly skip the first frame.

> -	/* reached last frame? */
> -	if (op->currframe >= op->nframes)
> -		op->currframe = 0;
> +		/* reached last frame? */
> +		if (op->currframe >= op->nframes)
> +			op->currframe = 0;

[ ... ]

> @@ -1130,6 +1173,24 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
>  	return err;
>  }
>  
> +static void bcm_rx_setup_rtr_check(struct bcm_msg_head *msg_head,
> +				   struct bcm_op *op, void *new_frames)
> +{
> +	/* funny feature in RX(!)_SETUP only for RTR-mode:
> +	 * copy can_id into frame BUT without RTR-flag to
> +	 * prevent a full-load-loopback-test ... ;-]
> +	 * normalize this on the staged buffer, before it is
> +	 * ever installed into op->frames.
> +	 */
> +	if (msg_head->flags & RX_RTR_FRAME) {

[Severity: High]
This is a pre-existing issue, but does bcm_rx_setup_rtr_check() fail to
validate the len field of the user-supplied RTR frame?

If a user configures an RX_RTR_FRAME operation without providing a valid
len field (for example, passing a payload length larger than the CAN limits
of 8 or 64), it appears the length goes unchecked before installation.
When a matching RTR request is received, bcm_rx_handler() will trigger
bcm_can_tx() to send this stored frame. The underlying CAN driver might
then trust the user-supplied length to read the payload from the buffer,
which could result in an out-of-bounds memory read.

> +		struct canfd_frame *frame0 = new_frames;
> +
> +		if ((msg_head->flags & TX_CP_CAN_ID) ||
> +		    frame0->can_id == op->can_id)
> +			frame0->can_id = op->can_id & ~CAN_RTR_FLAG;
> +	}
> +}

[ ... ]

> @@ -1175,19 +1238,48 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
>  			return -E2BIG;
>  
>  		if (msg_head->nframes) {
> -			/* update CAN frames content */
> -			err = memcpy_from_msg(op->frames, msg,
> +			/* get new CAN frames content before locking */
> +			new_frames = kmalloc(msg_head->nframes * op->cfsiz,
> +					     GFP_KERNEL);
> +			if (!new_frames)
> +				return -ENOMEM;
> +
> +			err = memcpy_from_msg(new_frames, msg,
>  					      msg_head->nframes * op->cfsiz);
> -			if (err < 0)
> +			if (err < 0) {
> +				kfree(new_frames);
>  				return err;
> +			}
>  
> -			/* clear last_frames to indicate 'nothing received' */
> -			memset(op->last_frames, 0, msg_head->nframes * op->cfsiz);
> +			bcm_rx_setup_rtr_check(msg_head, op, new_frames);
>  		}
>  
> +		spin_lock_bh(&op->bcm_rx_update_lock);
>  		op->nframes = msg_head->nframes;
>  		op->flags = msg_head->flags;

[Severity: High]
This is a pre-existing issue, but can updating an existing operation's
flags create a dangerous mismatch between op->flags and op->cfsiz?

By overwriting op->flags with the newly supplied flags while leaving
op->cfsiz at its previously configured value, the CAN_FD_FRAME state can
diverge from its statically determined allocation size.

For instance, if a user modifies an existing standard operation to include
the CAN_FD_FRAME flag, later checks like the one in bcm_rx_cmp_to_index()
might assume a larger layout and perform an out-of-bounds read past the
end of the heap-allocated op->frames buffer. Conversely, dropping the flag
could cause functions like bcm_rx_update_and_send() to copy an excessive
number of bytes from a smaller SKB buffer.

> +		if (msg_head->nframes) {
> +			/* update CAN frames content */
> +			memcpy(op->frames, new_frames,
> +			       msg_head->nframes * op->cfsiz);

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=8

Re: [PATCH net 03/19] can: raw: add locking for raw flags bitfield

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Holding `rtnl_lock()` across user-space memory copies enables a system-wide Denial of Service.
--

--- Patch [3]: [PATCH net 03/19] can: raw: add locking for raw flags bitfield ---
commit 64cfa8c3c841a4b23931e54d2dfb767381bcd986
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: raw: add locking for raw flags bitfield

This commit integrates separate integer values into a single bitfield and
adds locking to prevent concurrent access during read-modify-write
operations in raw_setsockopt. It introduces a raw_setsockopt_locked
function wrapped by a new raw_setsockopt to handle the locking.

Closes: https://lore.kernel.org/linux-can/20260503112200.22727-1-eulgyukim@snu.ac.kr/
Link: https://patch.msgid.link/20260504111928.41856-1-socketcan@hartkopp.net

> diff --git a/net/can/raw.c b/net/can/raw.c
> index a26942e78e688..82d9c0499c95f 100644
> --- a/net/can/raw.c
> +++ b/net/can/raw.c

[ ... ]

> @@ -769,6 +743,26 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
>  	return err;
>  }
>  
> +static int raw_setsockopt(struct socket *sock, int level, int optname,
> +			  sockptr_t optval, unsigned int optlen)
> +{
> +	struct sock *sk = sock->sk;
> +	int err;
> +
> +	if (level != SOL_CAN_RAW)
> +		return -EINVAL;
> +
> +	rtnl_lock();
> +	lock_sock(sk);
> +
> +	err = raw_setsockopt_locked(sock, optname, optval, optlen);

[Severity: High]
Does holding rtnl_lock() across raw_setsockopt_locked() allow a system-wide
Denial of Service?

Inside raw_setsockopt_locked(), user-space memory copies are performed
before rtnl_lock() was historically taken:

	case CAN_RAW_FILTER:
		...
		if (count > 1) {
			filter = memdup_sockptr(optval, optlen);
			...
		} else if (count == 1) {
			if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter)))
				...
		}

Could a local user pass a memory pointer backed by userfaultfd or a slow FUSE
mount, intentionally stalling the page fault during memdup_sockptr() or
copy_from_sockptr(), and freeze network configuration for the whole system by
holding the global rtnl_lock?

It seems the isotp.c example cited in the commit message only takes
lock_sock() in its wrapper, not rtnl_lock().

> +
> +	release_sock(sk);
> +	rtnl_unlock();
> +
> +	return err;
> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=3

Re: [PATCH net 10/19] can: bcm: add missing rcu list annotations and operations

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Critical] List corruption and Use-After-Free in bcm_rx_setup() due to unconditional list_add_rcu() and missing list_del_rcu() on existing operations.
--

--- Patch [10]: [PATCH net 10/19] can: bcm: add missing rcu list annotations and operations ---
commit 920bd90c8dec1b6179ef18a6d82400e3e89b0659
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: add missing rcu list annotations and operations

This commit aims to fix RCU list annotations for CAN BCM sockets so that
bcm_proc_show() can safely traverse the operation lists. It moves the
list_add_rcu() calls to the end of the bcm_tx_setup() and bcm_rx_setup()
routines to ensure structures are fully initialized when published. It also
adds list_del_rcu() before freeing operations in bcm_release().

Link: https://patch.msgid.link/20260714-bcm_fixes-v15-5-562f7e3e42da@hartkopp.net

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index 03c98e4cc677d..5c1e83eeb4ff3 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c

[ ... ]

> @@ -1449,10 +1450,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
>  					      bcm_rx_handler, op, "bcm", sk);
>  		if (err) {
>  			/* this bcm rx op is broken -> remove it */
> -			list_del_rcu(&op->list);
>  			bcm_remove_op(op);
>  			return err;
>  		}
> +
> +		/* add this bcm_op to the list of the rx_ops */
> +		list_add_rcu(&op->list, &bo->rx_ops);
>  	}
>  
>  	return msg_head->nframes * op->cfsiz + MHSIZ;

[Severity: Critical]
If an existing operation is updated after an interface bounce, could this
cause list corruption or a use-after-free?

When a CAN interface goes down, bcm_notify() unregisters the receive
operation but intentionally leaves the bcm_op linked in bo->rx_ops. If
userspace later updates this existing operation via a new RX_SETUP message,
bcm_rx_setup() finds the existing operation and sets do_rx_register = 1.

If the subsequent re-registration fails (err != 0), it looks like removing
list_del_rcu() here means bcm_remove_op() will free the operation via
call_rcu() while it is still linked in the bo->rx_ops list.

Conversely, if re-registration succeeds, won't the unconditional call to
list_add_rcu() corrupt the list pointers since the operation is already
linked in the list?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=10

Re: [PATCH net 07/19] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:

Pre-existing issues:
- [Critical] `bcm_delete_rx_op()` and `bcm_release()` silently skip unregistering CAN receivers when `dev_get_by_index()` fails, leading to a leaked receiver and Use-After-Free.
- [High] Missing RCU protection and barrier for `bo->tx_ops` and `bo->rx_ops` list modifications.
- [High] Unprotected state modifications on CAN frames in the TX path causing a data race.
- [High] Unprotected state modifications on CAN frames in the RX path causing a data race.
- [Medium] Lockless reads of `bo->ifindex` contradict the patch's assumption and cause data races.
--

--- Patch [7]: [PATCH net 07/19] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure ---
commit a163b4c749b944874d23ca2a810e83a4afdbe1b5
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure

This patch addresses a race condition between bcm_sendmsg and concurrent
bcm_notify or bcm_connect calls by moving the ifindex read under the
socket lock. It also fixes a bug where bcm_rx_setup would silently
return success if the target device disappeared concurrently.

Link: https://patch.msgid.link/20260714-bcm_fixes-v15-2-562f7e3e42da@hartkopp.net

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index bdf53241bd7b3..b612135b017d1 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c
> @@ -1323,6 +1323,11 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
>  
>  				op->rx_reg_dev = dev;
>  				dev_put(dev);
> +			} else {
> +				/* the requested device is gone - do not
> +				 * silently succeed without registering
> +				 */
> +				err = -ENODEV;
>  			}
>  
>  		} else

[Severity: High]
This is a pre-existing issue, but does this code safely manage list updates
for the transmit and receive operations?

In bcm_rx_setup() and bcm_tx_setup(), the code uses the standard list_add()
function rather than list_add_rcu():

bcm_rx_setup() {
    ...
    list_add(&op->list, &bo->rx_ops);
}

This means there is no smp_store_release() barrier to ensure newly populated
fields of the bcm_op structure are visible before the node is linked.

Concurrently, bcm_proc_show() locklessly traverses bo->tx_ops using
list_for_each_entry() instead of the rcu variant:

bcm_proc_show() {
    ...
    list_for_each_entry(op, &bo->tx_ops, list) {

Could this data race cause a procfs reader to observe torn pointers or
uninitialized memory during traversal?

[Severity: High]
This is also a pre-existing issue, but is it safe to overwrite the
comparison frames directly from userspace?

In bcm_rx_setup(), op->frames is updated directly from process context:

bcm_rx_setup() {
    ...
    err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz);

Since this can sleep, it cannot disable softirqs. Concurrently, CAN packet
reception can trigger bcm_rx_handler() in softirq (NAPI) context.

The handler locklessly compares the incoming frame against the actively
overwritten op->frames:

bcm_rx_handler() {
    ...
    if ((get_u64(op->frames, 0) & get_u64(rxframe, 0)) ==

Could this lead to incorrect filtering logic and misclassified or wrongly
accepted CAN frames?

[ ... ]
> @@ -1396,12 +1401,13 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
[ ... ]
> -	lock_sock(sk);
> -
>  	switch (msg_head.opcode) {
>  
>  	case TX_SETUP:

[Severity: High]
This is a pre-existing issue, but does this code protect the CAN frames
against concurrent transmission?

When bcm_sendmsg() calls bcm_tx_setup(), it directly modifies the
op->frames buffer from userspace:

bcm_tx_setup() {
    ...
    err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz);

Because copying from userspace can sleep, this happens without holding the
bcm_tx_lock spinlock. Concurrently, the transmission timer can fire and
invoke bcm_can_tx(), which computes a pointer to op->frames while holding
the lock, but drops the lock before calling skb_put_data():

bcm_can_tx() {
    ...
    skb_put_data(skb, cf, op->cfsiz);

Can this race condition result in partially updated or torn CAN frames
being transmitted on the CAN bus?

[ ... ]
> @@ -1535,7 +1564,12 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
>  				bo->bcm_proc_read = NULL;
>  			}
>  #endif
> -			bo->bound   = 0;
> +			/* Paired with the lockless fast-path check in
> +			 * bcm_sendmsg(); bo->ifindex itself is only ever
> +			 * accessed under lock_sock() so it needs no
> +			 * annotation.
> +			 */

[Severity: Medium]
Is this comment accurate?

The comment states bo->ifindex is only ever accessed under lock_sock(),
which justifies skipping memory barriers for lockless fast-path accesses.

However, bcm_notify() reads it locklessly when handling a NETDEV_DOWN
event:

bcm_notify() {
    ...
    if (bo->bound && bo->ifindex == dev->ifindex) {

And bcm_proc_show() also reads bo->ifindex locklessly for procfs output
generation:

bcm_proc_show() {
    ...
    seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex));

Because bcm_connect() uses WRITE_ONCE(bo->bound, 1) without a paired CPU
memory barrier for bo->ifindex, couldn't concurrent paths observe an
inconsistent torn state?

> +			WRITE_ONCE(bo->bound, 0);
>  			bo->ifindex = 0;
>  			notify_enodev = 1;
>  		}
> @@ -1676,7 +1710,7 @@ static int bcm_release(struct socket *sock)
>  
>  	/* remove device reference */
>  	if (bo->bound) {
> -		bo->bound   = 0;
> +		WRITE_ONCE(bo->bound, 0);
>  		bo->ifindex = 0;
>  	}

[Severity: Critical]
This isn't a bug introduced by this patch, but could this teardown path
skip unregistering CAN receivers and cause a use-after-free?

When a network device is unregistered, it is removed from the network
namespace index before the NETDEV_UNREGISTER notifiers run. If a socket
is closed during this exact window, dev_get_by_index() fails and returns
NULL:

bcm_release() {
    ...
    dev = dev_get_by_index(net, op->ifindex);
    if (dev) {
        bcm_rx_unreg(dev, op);
        dev_put(dev);
    }

As a result, bcm_rx_unreg() is silently skipped, but the bcm_op is
removed from bo->rx_ops and freed via RCU. The bcm_rx_handler remains
registered in the CAN core pointing to the freed memory.

A similar issue exists in bcm_delete_rx_op(). Could a subsequent packet
reception trigger the handler and corrupt memory?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=7

Re: [PATCH net 15/19] can: bcm: fix data race on rx_stamp/rx_ifindex in bcm_rx_handler()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Unconditional update of `op->rx_stamp` and `op->rx_ifindex` corrupts metadata for throttled or multiplexed CAN frames.
--

--- Patch [15]: [PATCH net 15/19] can: bcm: fix data race on rx_stamp/rx_ifindex in bcm_rx_handler() ---
commit e05fd3b3c775fc8bd3bab9bce2bc9f1a23e5fc07
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: fix data race on rx_stamp/rx_ifindex in bcm_rx_handler()

This patch fixes a data race on op->rx_stamp and op->rx_ifindex in
bcm_rx_handler() by moving their assignments into the bcm_rx_update_lock
critical section. This ensures the CAN content and metadata are bundled
correctly without torn stores on 32-bit platforms. As a side effect,
RTR-request frames no longer update these fields since only the notification
path needs them.

Link: https://patch.msgid.link/20260714-bcm_fixes-v15-10-562f7e3e42da@hartkopp.net

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index a53dba6ab8b89..f213a0b377915 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c
[ ... ]
> @@ -836,6 +831,14 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
>  			traffic_flags |= RX_OWN;
>  	}
>  
> +	/* save rx timestamp and originator for recvfrom() under lock.
> +	 * For an op subscribed on all interfaces (ifindex == 0)
> +	 * bcm_rx_handler() can run concurrently on different CPUs so
> +	 * the CAN content and the meta data must be bundled correctly.
> +	 */
> +	op->rx_stamp = skb->tstamp;
> +	op->rx_ifindex = skb->dev->ifindex;
> +

[Severity: High]
This is a pre-existing issue, but since the commit message states the goal
is to report the timestamp/ifindex of the very same frame whose content it
is delivering, does the unconditional assignment here still leave the
metadata vulnerable to being corrupted by subsequent frames?

If a CAN frame matches a BCM filter and is throttled, it is queued and the
throttle timer starts. Before the timer expires, if another CAN frame with
the same CAN ID arrives, it will unconditionally overwrite op->rx_stamp and
op->rx_ifindex here.

If this new frame is discarded by multiplex filters, won't
bcm_rx_thr_flush() end up sending the previously throttled frame to
userspace using the overwritten metadata of the discarded frame?

>  	if (op->flags & RX_FILTER_ID) {
>  		/* the easiest case */
>  		bcm_rx_update_and_send(op, op->last_frames, rxframe,

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=15

Re: [PATCH net 17/19] can: isotp: use unconditional synchronize_rcu() in isotp_release()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] If a CAN ISOTP socket is closed concurrently with the unregistration of its bound netdevice, `dev_get_by_index()` fails, causing `isotp_release()` to skip CAN RX filter unregistration. This permanently leaks the filter and leaves it active, leading to a Use-After-Free.
- [High] isotp_sendmsg() arbitrarily aborts an ongoing concurrent transmission if interrupted by a signal while waiting.
--

--- Patch [17]: [PATCH net 17/19] can: isotp: use unconditional synchronize_rcu() in isotp_release() ---
commit c0a31977a8d3b86aee8a7406999fdf381f2bbded
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: isotp: use unconditional synchronize_rcu() in isotp_release()

isotp_notify() unregisters the CAN filters without waiting for a grace
period. This patch makes isotp_release() always call synchronize_rcu()
before cancelling the timers, closing a race condition where a timer
could be cancelled while an in-flight isotp_rcv() is still executing.

Closes: https://lore.kernel.org/linux-can/20260707085210.6B6C01F000E9@smtp.kernel.org/
Link: https://patch.msgid.link/20260712-isotp-fixes-v10-1-793a1b1ce17f@hartkopp.net

> diff --git a/net/can/isotp.c b/net/can/isotp.c
> index c48b4a818297e..d30937345bcdc 100644
> --- a/net/can/isotp.c
> +++ b/net/can/isotp.c
> @@ -1237,11 +1237,18 @@ static int isotp_release(struct socket *sock)
>  						  SINGLE_MASK(so->txid),
>  						  isotp_rcv_echo, sk);
>  				dev_put(dev);
> -				synchronize_rcu();
>  			}
>  		}
>  	}
>  
> +	/* 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.
> +	 */
> +	synchronize_rcu();
> +

[Severity: High]
This is a pre-existing issue, but I have a question about how the socket
teardown handles missing network devices.

If unlist_netdevice() removes the device from the index before isotp_release()
calls dev_get_by_index(), will the lookup fail?

net/can/isotp.c:isotp_release() {
    ...
    dev = dev_get_by_index(net, so->ifindex);
    if (dev) {
        ...
        can_rx_unregister(...);
        ...
    }
    ...
    synchronize_rcu();
}

If dev_get_by_index() fails, can_rx_unregister() is skipped. Since
isotp_release() also removes the socket from the notifier list, will the
subsequent NETDEV_UNREGISTER event also fail to unregister the filter?

If the filter remains active in the device's RCU-protected lists, does
synchronize_rcu() adequately protect against new readers? While it waits for
existing readers, could a new softirq reader start after synchronize_rcu()
returns, find the leaked filter, and cause a use-after-free by accessing the
freed socket?

Could this be mitigated by tracking the net_device directly with
netdevice_tracker?

>  	hrtimer_cancel(&so->txfrtimer);
>  	hrtimer_cancel(&so->txtimer);
>  	hrtimer_cancel(&so->rxtimer);

I also noticed another pre-existing issue in this file.

[Severity: High]
This isn't a bug introduced by this patch, but does the error handling in
isotp_sendmsg() safely manage concurrent senders?

If multiple threads attempt to send on the same socket, one thread may acquire
the ISOTP_SENDING state while another thread waits in
wait_event_interruptible(). If the waiting thread receives a signal:

net/can/isotp.c:isotp_sendmsg() {
    ...
    err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
    if (err)
        goto err_event_drop;
    ...
err_event_drop:
    so->tx.state = ISOTP_IDLE;
    hrtimer_cancel(&so->txfrtimer);
    ...
}

Does jumping to err_event_drop unconditionally force so->tx.state to ISOTP_IDLE
and cancel the transmission timers, directly aborting the active thread's
transmission?

If the socket state is reset, new transmissions could start, but could hardware
echoes or FC frames from the aborted transmission still arrive and corrupt the
new transmission's state, since so->cfecho is not cleared?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=17

Re: [PATCH net 18/19] can: isotp: fix use-after-free race with concurrent NETDEV_UNREGISTER

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

Pre-existing issues:
- [High] Concurrent `setsockopt(CAN_ISOTP_LL_OPTS)` and `isotp_sendmsg()` can cause `skb_over_panic` due to unlocked reads of `so->ll.mtu`.
- [High] Receiving a First Frame (FF) triggers a `kmalloc` with `GFP_ATOMIC` up to `max_pdu_size` (defaults to 8300 bytes, up to 1MB), which can exhaust the kernel's atomic memory pool.
- [Medium] The return values of `can_rx_register()` are ignored in `isotp_bind()`, leading to silently dropped packets and kernel log warnings on socket release.
--

--- Patch [18]: [PATCH net 18/19] can: isotp: fix use-after-free race with concurrent NETDEV_UNREGISTER ---
commit 9321d1d072ae2c3d91c2e9ffaeeff213350e562d
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: isotp: fix use-after-free race with concurrent NETDEV_UNREGISTER

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.

Link: https://patch.msgid.link/20260712-isotp-fixes-v10-2-793a1b1ce17f@hartkopp.net

> diff --git a/net/can/isotp.c b/net/can/isotp.c
> index d30937345bcdc..44c044eb83e12 100644
> --- a/net/can/isotp.c
> +++ b/net/can/isotp.c
> @@ -978,6 +980,14 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
>  			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;
> +	}
> +

[Severity: High]
This is a pre-existing issue, but can this lead to an skb_over_panic due to
unlocked reads of so->ll.mtu?

If isotp_sendmsg() is called and passes the so->bound check, and a
concurrent NETDEV_UNREGISTER notifier clears so->bound:

CPU1                                CPU2
isotp_sendmsg()                     
  // passes so->bound check
                                    NETDEV_UNREGISTER notifier
                                      so->bound = 0;
                                    
                                    setsockopt(CAN_ISOTP_LL_OPTS)
                                      // passes !so->bound check
                                      memcpy(&so->ll, &ll, sizeof(ll));

Could isotp_sendmsg() then execute sock_alloc_send_skb() with the old
so->ll.mtu, and later call skb_put_zero() with the newly modified, larger
so->ll.mtu, causing a buffer overflow panic?

>  	/* PDU size > default => try max_pdu_size */
>  	if (size > so->tx.buflen && so->tx.buflen < max_pdu_size) {

[ ... ]

> @@ -1354,16 +1373,25 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
>  	can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id),
>  			isotp_rcv_echo, sk, "isotpe", sk);
>  

[Severity: Medium]
This isn't a bug introduced by this patch, but should we be checking the
return values of can_rx_register() here?

If can_rx_register() fails (e.g., due to memory pressure returning -ENOMEM),
the error appears to be ignored, and the socket is incorrectly marked as
successfully bound.

When the socket is later closed, isotp_release() calls can_rx_unregister(),
which would fail to find the receiver entry and trigger a kernel warning.

> -	dev_put(dev);
> -
>  	/* switch to new settings */
>  	so->ifindex = ifindex;
>  	so->rxid = rx_id;

[ ... ]

Also, regarding a separate pre-existing issue in isotp_rcv_ff():

[Severity: High]
This is a pre-existing issue, but does receiving a First Frame (FF) trigger
a potentially large allocation in atomic context?

net/can/isotp.c:isotp_rcv_ff() {
    ...
    u8 *newbuf = kmalloc(max_pdu_size, GFP_ATOMIC);
    if (newbuf) {
        so->rx.buf = newbuf;
        so->rx.buflen = max_pdu_size;
    }
    ...
}

Since max_pdu_size can be up to 1MB, could an attacker broadcasting First
Frames with large PDU sizes rapidly exhaust the kernel's atomic memory pool?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=18

Re: [PATCH net 19/19] can: isotp: serialize TX state transitions under so->rx_lock

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Racy evaluation of `so->tx_gen` in `isotp_tx_timeout` suppresses legitimate timeout errors and forces waiters to block on subsequent transfers.
--

--- Patch [19]: [PATCH net 19/19] can: isotp: serialize TX state transitions under so->rx_lock ---
commit d815650c77b9d2ce6acff4c164869dfbfb037f2e
Author: Oliver Hartkopp <socketcan@hartkopp.net>
can: isotp: serialize TX state transitions under so->rx_lock

This commit reorganizes the locking and state machine in the CAN ISOTP
transmit path, making sendmsg() operations fully serialized under
so->rx_lock. It introduces a generation counter (so->tx_gen) to handle
timer callbacks racing with new transfers.

Link: https://patch.msgid.link/20260712-isotp-fixes-v10-3-793a1b1ce17f@hartkopp.net

> --- a/net/can/isotp.c
> +++ b/net/can/isotp.c

[ ... ]

> +static enum hrtimer_restart isotp_tx_timeout(struct isotp_sock *so)
>  {
>  	struct sock *sk = &so->sk;
> +	u32 gen = READ_ONCE(so->tx_gen);
> +	u32 old_state = READ_ONCE(so->tx.state);
>  
>  	/* don't handle timeouts in IDLE or SHUTDOWN state */
> +	if (old_state == ISOTP_IDLE || old_state == ISOTP_SHUTDOWN)
> +		return HRTIMER_NORESTART;
> +
> +	/* only claim the timeout if the state is still unchanged */
> +	if (cmpxchg(&so->tx.state, old_state, ISOTP_IDLE) != old_state)
>  		return HRTIMER_NORESTART;
>  
>  	/* we did not get any flow control or echo frame in time */
>  
> -	/* report 'communication error on send' */
> -	sk->sk_err = ECOMM;
> -	if (!sock_flag(sk, SOCK_DEAD))
> -		sk_error_report(sk);
> +	if (READ_ONCE(so->tx_gen) == gen) {

[Severity: High]
Does setting the state to ISOTP_IDLE before checking the generation
counter introduce a race condition?

If cmpxchg() successfully sets the state to ISOTP_IDLE, a concurrent
isotp_sendmsg() thread could immediately acquire the socket, set the state
to ISOTP_SENDING, and bump so->tx_gen.

If this occurs before we evaluate READ_ONCE(so->tx_gen) here, the timer
callback will incorrectly assume the transfer was superseded and skip
setting the ECOMM error. Could this lead to silent data loss?

> +		/* report 'communication error on send' */
> +		sk->sk_err = ECOMM;
> +		if (!sock_flag(sk, SOCK_DEAD))
> +			sk_error_report(sk);
> +	}
>  
> -	/* reset tx state */
> -	so->tx.state = ISOTP_IDLE;
>  	wake_up_interruptible(&so->wait);
>  
>  	return HRTIMER_NORESTART;
>  }

[ ... ]

> @@ -960,13 +1024,24 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)

[ ... ]

> +	/* new transfer: bump so->tx_gen and drain the old one's timers,
> +	 * still under the so->rx_lock we just claimed the socket with
> +	 */
> +	WRITE_ONCE(so->tx.state, ISOTP_SENDING);
> +	WRITE_ONCE(so->tx_gen, READ_ONCE(so->tx_gen) + 1);

[Severity: High]
If the timeout callback races with the state transition above, a
concurrent sender updating so->tx_gen here will poison the check in the
interrupted timer callback.

Could this also cause the sender thread to block waiting for an unrelated
concurrent transmission to finish, rather than handling the timeout?

> +	hrtimer_cancel(&so->txtimer);
> +	hrtimer_cancel(&so->echotimer);
> +	hrtimer_cancel(&so->txfrtimer);
> +	so->cfecho = 0;
> +	spin_unlock_bh(&so->rx_lock);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716155528.809908-1-mkl@pengutronix.de?part=19