[PATCH v4 0/7] can: bcm: collected fixes

[PATCH v4 0/7] can: bcm: collected fixes

[Oliver Hartkopp via B4 Relay]

Hi Marc,

as there were different patches flying arround to fix CAN_BCM issues and
AI assisted stuff pop's up again and again, I've created this collection
to be applied.

I'm not sure whether sashiko-bot takes the sequence of this series into
account when checking the last patches. So let's see.

Best regards,
Oliver

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
Changes in v4:
- incorporated more sashiko-bot concerns from v3
- patch 3: omit hrtimer_forward with zero interval
- patch 4: put bcm_update_stats() under bcm_rx_update_lock
- Link to v3: https://patch.msgid.link/20260707-bcm_fixes-v3-0-84600ca6d889@hartkopp.net

Changes in v3:
- incorporated more sashiko-bot concerns from v2
- patch 3: make snapshot of currframe
- patch 6: add error patch for memcpy_from_msg()
- patch 7: new RTR-reply validation in bcm_rx_setup() from bcm_tx_setup() 
- Link to v2: https://patch.msgid.link/20260707-bcm_fixes-v2-0-96620c534b75@hartkopp.net

Changes in v2:
- incorporated all sashiko-bot concerns from v1
- Link to v1: https://patch.msgid.link/20260612-bcm_fixes-v1-0-ca2fa07ee70f@hartkopp.net

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

Oliver Hartkopp (6):
      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

 net/can/bcm.c | 427 ++++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 323 insertions(+), 104 deletions(-)
---
base-commit: 0e35b9b6ec0ffcc5e23cbdec09f5c622ad532b53
change-id: 20260612-bcm_fixes-84fb4aa93ac2

Best regards,
--  
Oliver Hartkopp <socketcan@hartkopp.net>

[PATCH v4 1/7] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF

[Oliver Hartkopp via B4 Relay]

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()")
Signed-off-by: Lee Jones <lee@kernel.org>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 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
@@ -56,10 +56,11 @@
 #include <linux/can.h>
 #include <linux/can/core.h>
 #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>
 #include <net/net_namespace.h>
 
@@ -90,10 +91,12 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
 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
  * by the only callers in bcm_rx_cmp_to_index() bcm_rx_handler().
  */
@@ -103,10 +106,11 @@ 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;
 	unsigned long frames_abs, frames_filtered;
 	struct bcm_timeval ival1, ival2;
@@ -791,23 +795,40 @@ 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);
 
 	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);
 	hrtimer_cancel(&op->thrtimer);
 
@@ -1058,10 +1079,11 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		/* tx_ops never compare with previous received messages */
 		op->last_frames = NULL;
 
 		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
 		op->sk = sk;
+		sock_hold(sk);
 		op->ifindex = ifindex;
 
 		/* initialize uninitialized (kzalloc) structure */
 		hrtimer_setup(&op->timer, bcm_tx_timeout_handler, CLOCK_MONOTONIC,
 			      HRTIMER_MODE_REL_SOFT);
@@ -1219,10 +1241,11 @@ 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 */
 		op->rx_ifindex = ifindex;
 
@@ -1837,15 +1860,19 @@ static struct notifier_block canbcm_notifier = {
 
 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)
 		goto register_notifier_failed;
 
@@ -1859,17 +1886,21 @@ static int __init bcm_module_init(void)
 
 register_proto_failed:
 	unregister_netdevice_notifier(&canbcm_notifier);
 register_notifier_failed:
 	unregister_pernet_subsys(&canbcm_pernet_ops);
+register_pernet_failed:
+	destroy_workqueue(bcm_wq);
 	return err;
 }
 
 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);
 module_exit(bcm_module_exit);

-- 
2.53.0

[PATCH v4 2/7] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure

[Oliver Hartkopp via B4 Relay]

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.

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>
---
 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
@@ -1321,10 +1321,15 @@ 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;
 				dev_put(dev);
+			} else {
+				/* the requested device is gone - do not
+				 * silently succeed without registering
+				 */
+				err = -ENODEV;
 			}
 
 		} else
 			err = can_rx_register(sock_net(sk), NULL, op->can_id,
 					      REGMASK(op->can_id),
@@ -1394,16 +1399,17 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk,
  */
 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 */
 	if (size < MHSIZ)
 		return -EINVAL;
@@ -1415,43 +1421,65 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 
 	cfsiz = CFSIZ(msg_head.flags);
 	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;
 
 		if (ifindex) {
 			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:
 		ret = bcm_tx_setup(&msg_head, msg, ifindex, sk);
 		break;
@@ -1497,10 +1525,11 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	default:
 		ret = -EINVAL;
 		break;
 	}
 
+out_release:
 	release_sock(sk);
 
 	return ret;
 }
 
@@ -1533,11 +1562,16 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
 			if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read) {
 				remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir);
 				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;
 		}
 
 		release_sock(sk);
@@ -1674,11 +1708,11 @@ static int bcm_release(struct socket *sock)
 	list_for_each_entry_safe(op, next, &bo->rx_ops, list)
 		bcm_remove_op(op);
 
 	/* remove device reference */
 	if (bo->bound) {
-		bo->bound   = 0;
+		WRITE_ONCE(bo->bound, 0);
 		bo->ifindex = 0;
 	}
 
 	sock_orphan(sk);
 	sock->sk = NULL;
@@ -1744,11 +1778,14 @@ static int bcm_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int
 			goto fail;
 		}
 	}
 #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);
 
 	return ret;

-- 
2.53.0

[PATCH v4 3/7] can: bcm: add locking when updating filter and timer values

[Oliver Hartkopp via B4 Relay]

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: CAN loopback on
echo-capable interfaces (e.g. vcan) can deliver the transmitted skb
back into bcm_rx_handler() synchronously from within dev_queue_xmit(),
which would self-deadlock on the per-op lock if it were still held.

Also take a lock-protected snapshot of the currframe in bcm_can_tx()
to avoid partly overwrites by content updates in bcm_tx_setup().

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>
---
 net/can/bcm.c | 139 ++++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 107 insertions(+), 32 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index b612135b017d..b9b6f1b7bb03 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -127,10 +127,11 @@ struct bcm_op {
 	struct canfd_frame sframe;
 	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_rx_update_lock; /* protect filter/timer data updates */
 };
 
 struct bcm_sock {
 	struct sock sk;
 	int bound;
@@ -291,26 +292,30 @@ 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;
 	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 (!cf) {
+		/* read currframe under lock protection */
+		spin_lock_bh(&op->bcm_tx_lock);
+		memcpy(&cframe, op->frames + op->cfsiz * op->currframe,
+		       op->cfsiz);
+		cf = &cframe;
+		spin_unlock_bh(&op->bcm_tx_lock);
+	}
 
 	dev = dev_get_by_index(sock_net(op->sk), op->ifindex);
 	if (!dev) {
 		/* RFC: should this bcm_op remove itself here? */
 		return;
@@ -459,11 +464,11 @@ 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;
 
 	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 */
 			memset(&msg_head, 0, sizeof(msg_head));
 			msg_head.opcode  = TX_EXPIRED;
@@ -476,11 +481,11 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
 
 			bcm_send_to_user(op, &msg_head, NULL, 0);
 		}
 
 	} else if (op->kt_ival2) {
-		bcm_can_tx(op);
+		bcm_can_tx(op, NULL);
 	}
 
 	return bcm_tx_set_expiry(op, &op->timer) ?
 		HRTIMER_RESTART : HRTIMER_NORESTART;
 }
@@ -620,10 +625,12 @@ static void bcm_rx_starttimer(struct bcm_op *op)
 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' */
 		memset(op->last_frames, 0, op->nframes * op->cfsiz);
 	}
@@ -636,10 +643,12 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 	msg_head.ival1   = op->ival1;
 	msg_head.ival2   = op->ival2;
 	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;
 }
 
@@ -684,30 +693,43 @@ static int bcm_rx_thr_flush(struct bcm_op *op)
  *                      Check for throttled data and send it to the userspace
  */
 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;
+
+	spin_lock_bh(&op->bcm_rx_update_lock);
 
-	if (bcm_rx_thr_flush(op)) {
+	/* 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;
 }
 
 /*
  * bcm_rx_handler - handle a CAN frame reception
  */
 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;
 
 	/* make sure to handle the correct frame type (CAN / CAN FD) */
@@ -727,13 +749,25 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 	/* save originator for recvfrom() */
 	op->rx_ifindex = skb->dev->ifindex;
 	/* 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(). Do not call bcm_can_tx() while
+	 * holding bcm_rx_update_lock: CAN loopback on echo-capable
+	 * interfaces (e.g. vcan) can deliver the transmitted skb back into
+	 * bcm_rx_handler() synchronously from within dev_queue_xmit().
+	 */
+	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;
 	}
 
 	/* compute flags to distinguish between own/local/remote CAN traffic */
 	traffic_flags = 0;
@@ -741,10 +775,12 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 		traffic_flags |= RX_LOCAL;
 		if (skb->sk == op->sk)
 			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,
 				       traffic_flags);
 		goto rx_starttimer;
@@ -776,10 +812,12 @@ 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);
 }
 
 /*
  * helpers for bcm_op handling: find & delete bcm [rx|tx] op elements
  */
@@ -1114,11 +1152,11 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		/* spec: send CAN frame when starting timer */
 		op->flags |= TX_ANNOUNCE;
 	}
 
 	if (op->flags & TX_ANNOUNCE)
-		bcm_can_tx(op);
+		bcm_can_tx(op, NULL);
 
 	if (op->flags & STARTTIMER)
 		bcm_tx_start_timer(op);
 
 	return msg_head->nframes * op->cfsiz + MHSIZ;
@@ -1128,10 +1166,28 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		kfree(op->frames);
 	kfree(op);
 	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)
  */
 static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			int ifindex, struct sock *sk)
@@ -1162,10 +1218,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		return -EINVAL;
 
 	/* 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 */
 
 		/*
 		 * Do we need more space for the CAN frames than currently
 		 * allocated? -> This is a _really_ unusual use-case and
@@ -1173,33 +1231,55 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		 */
 		if (msg_head->nframes > op->nframes)
 			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;
 
+		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);
+		}
+		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;
 
 	} else {
 		/* insert new BCM operation for the given can_id */
 		op = kzalloc(OPSIZ, GFP_KERNEL);
 		if (!op)
 			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);
 		op->flags = msg_head->flags;
 
@@ -1237,10 +1317,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 				if (op->last_frames != &op->last_sframe)
 					kfree(op->last_frames);
 				kfree(op);
 				return err;
 			}
+
+			bcm_rx_setup_rtr_check(msg_head, op, op->frames);
 		}
 
 		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
 		op->sk = sk;
 		sock_hold(sk);
@@ -1264,45 +1346,38 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	} /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */
 
 	/* 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 */
+			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)
 				hrtimer_cancel(&op->timer);
 
 			/*
 			 * 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)
 			hrtimer_start(&op->timer, op->kt_ival1,
 				      HRTIMER_MODE_REL_SOFT);

-- 
2.53.0

[PATCH v4 4/7] can: bcm: fix CAN frame rx/tx statistics

[Oliver Hartkopp via B4 Relay]

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 a separate bcm_update_stats() function and
put this function under bcm_rx_update_lock to prevent races when resetting
the counters.

Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 net/can/bcm.c | 49 +++++++++++++++++++++++++++++++------------------
 1 file changed, 31 insertions(+), 18 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index b9b6f1b7bb03..0b53dbb64dd1 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -110,11 +110,11 @@ struct bcm_op {
 	struct rcu_head rcu;
 	struct work_struct work;
 	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;
 	int rx_ifindex;
 	int cfsiz;
@@ -227,14 +227,17 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 
 	rcu_read_lock();
 
 	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,
 			   bcm_proc_getifname(net, ifname, op->ifindex));
 
@@ -252,13 +255,13 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 		if (op->kt_ival2)
 			seq_printf(m, "thr=%lld ",
 				   (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);
 	}
 
@@ -278,20 +281,30 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 
 		if (op->kt_ival2)
 			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');
 
 	rcu_read_unlock();
 
 	return 0;
 }
 #endif /* CONFIG_PROC_FS */
 
+static void bcm_update_stats(struct bcm_op *op)
+{
+	/* prevent statistics overflow */
+	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);
+	}
+}
+
 /*
  * 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, struct canfd_frame *cf)
@@ -342,11 +355,11 @@ static void bcm_can_tx(struct bcm_op *op, struct canfd_frame *cf)
 
 	/* update currframe and count under lock protection */
 	spin_lock_bh(&op->bcm_tx_lock);
 
 	if (!err)
-		op->frames_abs++;
+		bcm_update_stats(op);
 
 	op->currframe++;
 
 	/* reached last frame? */
 	if (op->currframe >= op->nframes)
@@ -495,16 +508,13 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
  */
 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;
 
 	memset(&head, 0, sizeof(head));
@@ -746,23 +756,26 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 
 	/* save rx timestamp */
 	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(). Do not call bcm_can_tx() while
-	 * holding bcm_rx_update_lock: CAN loopback on echo-capable
+	/* snapshot RTR content under lock: op->flags/op->frames may be updated
+	 * concurrently by bcm_rx_setup(). But do not call bcm_can_tx() while
+	 * holding the bcm_rx_update_lock: CAN loopback on echo-capable
 	 * interfaces (e.g. vcan) can deliver the transmitted skb back into
 	 * bcm_rx_handler() synchronously from within dev_queue_xmit().
 	 */
 	spin_lock_bh(&op->bcm_rx_update_lock);
+
+	/* update statistics with lock analogue to bcm_rx_changed() callers */
+	bcm_update_stats(op);
+
 	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, &rtrframe);

-- 
2.53.0

[PATCH v4 5/7] can: bcm: add missing rcu list annotations and operations

[Oliver Hartkopp via B4 Relay]

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>
---
 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 0b53dbb64dd1..5ca684cd0819 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -263,11 +263,11 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 
 		seq_printf(m, "%s%ld%%\n",
 			   (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));
 
 		if (op->flags & CAN_FD_FRAME)
@@ -1000,10 +1000,11 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			int ifindex, struct sock *sk)
 {
 	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;
 
 	/* we need a real device to send frames */
 	if (!ifindex)
@@ -1141,12 +1142,11 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		/* currently unused in tx_ops */
 		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))) */
 
 	if (op->flags & SETTIMER) {
 		/* set timer values */
@@ -1164,10 +1164,14 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		hrtimer_cancel(&op->timer);
 		/* spec: send CAN frame when starting timer */
 		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);
 
 	if (op->flags & STARTTIMER)
 		bcm_tx_start_timer(op);
@@ -1348,13 +1352,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		hrtimer_setup(&op->timer, bcm_rx_timeout_handler, CLOCK_MONOTONIC,
 			      HRTIMER_MODE_REL_SOFT);
 		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;
 
 	} /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */
 
@@ -1422,14 +1423,16 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			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 */
-			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;
 }
 
@@ -1759,12 +1762,14 @@ static int bcm_release(struct socket *sock)
 	/* remove procfs entry */
 	if (net->can.bcmproc_dir && bo->bcm_proc_read)
 		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) {
 		/*
 		 * Don't care if we're bound or not (due to netdev problems)
 		 * can_rx_unregister() is always a save thing to do here.
@@ -1791,12 +1796,14 @@ 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) {
 		WRITE_ONCE(bo->bound, 0);
 		bo->ifindex = 0;

-- 
2.53.0

[PATCH v4 6/7] can: bcm: extend bcm_tx_lock usage for data and timer updates

[Oliver Hartkopp via B4 Relay]

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>
---
 net/can/bcm.c | 79 ++++++++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 23 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 5ca684cd0819..f04216723e0f 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -453,16 +453,22 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
 
 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;
 }
 
@@ -475,12 +481,21 @@ static void bcm_tx_start_timer(struct bcm_op *op)
 /* bcm_tx_timeout_handler - performs cyclic CAN frame transmissions */
 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;
 
-	if (op->kt_ival1 && (op->count > 0)) {
+	/* 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) {
 		bcm_can_tx(op, NULL);
 		if (!op->count && (op->flags & TX_COUNTEVT)) {
 
 			/* create notification to user */
 			memset(&msg_head, 0, sizeof(msg_head));
@@ -493,11 +508,11 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
 			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);
 	}
 
 	return bcm_tx_set_expiry(op, &op->timer) ?
 		HRTIMER_RESTART : HRTIMER_NORESTART;
@@ -1019,64 +1034,80 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		return -EINVAL;
 
 	/* check the given can_id */
 	op = bcm_find_op(&bo->tx_ops, msg_head, ifindex);
 	if (op) {
+		void *new_frames;
+
 		/* update existing BCM operation */
 
 		/*
 		 * Do we need more space for the CAN frames than currently
 		 * allocated? -> This is a _really_ unusual use-case and
 		 * therefore (complexity / locking) it is not supported.
 		 */
 		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)
 					err = -EINVAL;
 			} else {
 				if (cf->len > 8)
 					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);
+		    op->flags & TX_RESET_MULTI_IDX) {
+			/* potentially update changed nframes */
+			op->nframes = msg_head->nframes;
+			/* restart multiple frame transmission */
+			op->currframe = 0;
+		}
 
-			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;
 
-			if (op->flags & SETTIMER)
-				op->count = msg_head->count;
+		spin_unlock_bh(&op->bcm_tx_lock);
 
-			spin_unlock_bh(&op->bcm_tx_lock);
-		}
+		kfree(new_frames);
 
 	} else {
 		/* insert new BCM operation for the given can_id */
 
 		op = kzalloc(OPSIZ, GFP_KERNEL);
@@ -1148,14 +1179,16 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 	} /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */
 
 	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)
 			hrtimer_cancel(&op->timer);
 	}

-- 
2.53.0

[PATCH v4 7/7] can: bcm: validate frame length in bcm_rx_setup() for RTR replies

[Oliver Hartkopp via B4 Relay]

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>
---
 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 f04216723e0f..d4d2c89dc400 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1216,26 +1216,41 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		kfree(op->frames);
 	kfree(op);
 	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;
 }
 
 /*
  * bcm_rx_setup - create or update a bcm rx op (for bcm_sendmsg)
  */
@@ -1294,11 +1309,15 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			if (err < 0) {
 				kfree(new_frames);
 				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);
 		op->nframes = msg_head->nframes;
 		op->flags = msg_head->flags;
@@ -1359,20 +1378,16 @@ 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 */
 		op->sk = sk;
 		sock_hold(sk);
@@ -1465,10 +1480,18 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		/* 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;
+
+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;
 }
 
 /*
  * bcm_tx_send - send a single CAN frame to the CAN interface (for bcm_sendmsg)
  */

-- 
2.53.0

Re: [PATCH v4 6/7] can: bcm: extend bcm_tx_lock usage for data and timer updates

[Marc Kleine-Budde]

[-- Attachment #1: Type: text/plain, Size: 1251 bytes --]

On 07.07.2026 16:32:18, Oliver Hartkopp via B4 Relay wrote:
> 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.

Can you please update the comment for struct bcm_op::bcm_tx_lock, it
still reads: /* protect currframe/count in runtime updates */

Marc

-- 
Pengutronix e.K.                 | Marc Kleine-Budde          |
Embedded Linux                   | https://www.pengutronix.de |
Vertretung Nürnberg              | Phone: +49-5121-206917-129 |
Amtsgericht Hildesheim, HRA 2686 | Fax:   +49-5121-206917-9   |

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]

Re: [PATCH v4 1/7] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF

[sashiko-bot]

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

Pre-existing issues:
- [High] Concurrent procfs reads can crash the kernel due to unsafe lockless list operations on `bo->rx_ops` and `bo->tx_ops`.
--

--- Patch [1]: [PATCH v4 1/7] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF ---
commit 784fd8a5d6989051af26ae5075b37f80eb5ecce7
Author: Lee Jones <lee@kernel.org>

can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF

This commit resolves a use-after-free issue by deferring the cancellation
of timers and the deallocation of BCM operations to an unbound workqueue.
It takes an additional socket reference to ensure the socket outlives the
deferred work.

> 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;
>  
>  		/* initialize uninitialized (kzalloc) structure */

[Severity: High]
This is a pre-existing issue, but can concurrent procfs reads crash the kernel
due to unsafe lockless list operations on bo->tx_ops?

Later in bcm_tx_setup(), the new op is added to the list:

    list_add(&op->list, &bo->tx_ops);

However, bcm_proc_show() locklessly iterates bo->tx_ops using the non-RCU
macro list_for_each_entry() instead of list_for_each_entry_rcu(), and
bcm_tx_setup() uses list_add() instead of list_add_rcu(). Because list_add()
lacks the smp_store_release() memory barrier of list_add_rcu(), and because
the tx_ops traversal lacks rcu_dereference() to enforce data dependencies,
the reader CPU can observe the new list node before its fields or next
pointer are initialized.

Could this lead to dereferencing uninitialized memory or a corrupted next
pointer if a local user repeatedly reads /proc/net/can-bcm/<inode> while a
thread creates new TX operations via sendmsg()?

[ ... ]

> @@ -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 also a pre-existing issue, but a similar hazard exists for bo->rx_ops.

Later in bcm_rx_setup(), the code inserts into the list without RCU barriers:

    list_add(&op->list, &bo->rx_ops);

While bcm_proc_show() does use list_for_each_entry_rcu() for rx_ops (unlike
tx_ops), bcm_rx_setup() still uses list_add() instead of list_add_rcu().
Without the smp_store_release() memory barrier provided by list_add_rcu(),
concurrent procfs reads can still observe the new node before its contents
are fully initialized.

Should these insertions be upgraded to use list_add_rcu() to match the
lockless RCU iteration in procfs?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v4-0-aa87b8b9d33f@hartkopp.net?part=1

Re: [PATCH v4 6/7] can: bcm: extend bcm_tx_lock usage for data and timer updates

[Oliver Hartkopp]

On 07.07.26 16:38, Marc Kleine-Budde wrote:
> On 07.07.2026 16:32:18, Oliver Hartkopp via B4 Relay wrote:
>> 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.
> 
> Can you please update the comment for struct bcm_op::bcm_tx_lock, it
> still reads: /* protect currframe/count in runtime updates */
> 

Ah, I got that wrong as I only focused on the commit messages.

I'll wait for sakoshi-bot once more and send a V5 then.

Best regards,
Oliver

Re: [PATCH v4 3/7] can: bcm: add locking when updating filter and timer values

[sashiko-bot]

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

Pre-existing issues:
- [High] Lockless reads of timer and state variables in `bcm_tx_timeout_handler()` cause torn reads and TOCTOU bugs.
--

--- Patch [3]: [PATCH v4 3/7] can: bcm: add locking when updating filter and timer values ---
commit 59929132ac1eda994b23441375ebf1eecf8fc14d
Author: Oliver Hartkopp <socketcan@hartkopp.net>

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

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.

Reported-by: syzbot+75e5e4ae00c3b4bb544e@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-can/6975d5cf.a00a0220.33ccc7.0022.GAE@google.com/

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index b612135b017d1..b9b6f1b7bb03b 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c
> @@ -461,7 +466,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
>  	struct bcm_msg_head msg_head;
>  
>  	if (op->kt_ival1 && (op->count > 0)) {

[Severity: High]
This is a pre-existing issue, but while the patch adds locking to protect
timers in the RX path, it looks like a similar data race might exist here
in the TX path.

Can lockless reads of op->kt_ival1, op->kt_ival2, and op->count in
bcm_tx_timeout_handler() lead to torn reads on 32-bit systems?

Since bcm_tx_setup() updates these 64-bit timer intervals locklessly:

net/can/bcm.c:bcm_tx_setup() {
    ...
    if (op->flags & SETTIMER) {
        ...
        op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
        op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
    }
    ...
}

And bcm_tx_set_expiry() also reads them locklessly:

net/can/bcm.c:bcm_tx_set_expiry() {
    ...
    if (op->kt_ival1 && op->count)
        ival = op->kt_ival1;
    else if (op->kt_ival2)
        ival = op->kt_ival2;
    ...
}

Would it be possible for the hrtimer softirq context to see torn ktime_t
values if it preempts or runs concurrently with bcm_tx_setup()?

Could this lead to wildly incorrect timer expiry values that might stall
the cyclic transmission, or corrupt user notifications?

> -		bcm_can_tx(op);
> +		bcm_can_tx(op, NULL);
>  		if (!op->count && (op->flags & TX_COUNTEVT)) {
>  
>  			/* create notification to user */

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v4-0-aa87b8b9d33f@hartkopp.net?part=3

Re: [PATCH v4 5/7] 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:

Pre-existing issues:
- [High] Updating an existing TX operation in `bcm_tx_setup()` directly modifies `op->frames` and 64-bit timers without holding `op->bcm_tx_lock`, creating a data race and potential state corruption.
--

--- Patch [5]: [PATCH v4 5/7] can: bcm: add missing rcu list annotations and operations ---
commit 2ff2c9594c9d6ef4f6013f749b0066b1081603e0
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: add missing rcu list annotations and operations

This patch adds missing list_add_rcu() and list_del_rcu() operations
when setting up or releasing BCM operations. It ensures proper
RCU list initialization to safely support bcm_proc_show() traverses.

Link: https://lore.kernel.org/linux-can/20260610094654.A1FFE1F00893@smtp.kernel.org/

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index 0b53dbb64dd19..5ca684cd08194 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c

[ ... ]

> @@ -1143,8 +1144,7 @@ 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))) */
>  

[Severity: High]
This is a pre-existing issue, but does bcm_tx_setup() safely update
existing TX operations?

It appears that bcm_tx_setup() updates existing operations by directly
overwriting live CAN frames (op->frames) via memcpy_from_msg() without
holding op->bcm_tx_lock:

net/can/bcm.c:bcm_tx_setup() {
    ...
		err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);

		if (op->flags & CAN_FD_FRAME) {
			if (cf->len > 64)
				err = -EINVAL;
		} else {
			if (cf->len > 8)
				err = -EINVAL;
		}

		if (err < 0)
			return err;
    ...
}

If the updated data violates CAN constraints (e.g., cf->len > 64 or a memcpy
failure), it returns early. However, the existing active op continues to
run and transmit via bcm_tx_timeout_handler(). Can this lead to the blind
cyclic broadcast of corrupted or oversized CAN frames on the bus?

Additionally, 64-bit timers are updated without locking right below this
block, which could cause data races and torn reads on 32-bit platforms
with bcm_tx_timeout_handler():

net/can/bcm.c:bcm_tx_setup() {
    ...
		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);
    ...
}

Could these updates be guarded by op->bcm_tx_lock to prevent state
corruption?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v4-0-aa87b8b9d33f@hartkopp.net?part=5

Re: [PATCH v4 7/7] can: bcm: validate frame length in bcm_rx_setup() for RTR replies

[sashiko-bot]

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

Pre-existing issues:
- [High] Data race on `op->rx_ifindex` and `op->rx_stamp` in `bcm_rx_handler` leading to incorrect metadata being reported to userspace.
--

--- Patch [7]: [PATCH v4 7/7] can: bcm: validate frame length in bcm_rx_setup() for RTR replies ---
commit 1023235e0f18b95b00bedbafd97f5943d8506566
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: validate frame length in bcm_rx_setup() for RTR replies

This commit fixes a missing frame length check in bcm_rx_setup() for
RTR-reply frames configured via RX_SETUP with RX_RTR_FRAME. It ensures
cf->len is validated against CAN and CAN FD limits before installation.

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index f04216723e0fc..d4d2c89dc4009 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c
[ ... ]
> @@ -1467,6 +1482,14 @@ 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;
>  }

[Severity: High]
This is a pre-existing issue, but I noticed a potential data race in
bcm_rx_handler() involving op->rx_ifindex and op->rx_stamp.

When a user creates a BCM socket listening on all interfaces (ifindex=0),
and CAN frames matching the filter arrive concurrently on multiple
interfaces (e.g., handled by different CPUs in softirq), bcm_rx_handler()
can execute concurrently. Both CPUs appear to write to op->rx_stamp and
op->rx_ifindex without synchronization before acquiring 
op->bcm_rx_update_lock:

net/can/bcm.c:bcm_rx_handler() {
	...
	op->rx_stamp = skb->tstamp;
	/* save originator for recvfrom() */
	op->rx_ifindex = skb->dev->ifindex;
	...
}

Later, bcm_send_to_user() reads these fields to send metadata to userspace:

net/can/bcm.c:bcm_send_to_user() {
	...
	skb->tstamp = op->rx_stamp;
	...
	addr = (struct sockaddr_can *)skb->cb;
	memset(addr, 0, sizeof(*addr));
	addr->can_family  = AF_CAN;
	addr->can_ifindex = op->rx_ifindex;
	...
}

Could this lead to torn reads of the 64-bit rx_stamp on 32-bit platforms
and incorrect rx_ifindex values being reported to userspace?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v4-0-aa87b8b9d33f@hartkopp.net?part=7

Re: [PATCH v4 2/7] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure

[sashiko-bot]

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

Pre-existing issues:
- [High] Unprotected modification of RX operation buffers from process context races with softirq receive handlers.
--

--- Patch [2]: [PATCH v4 2/7] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure ---
commit 9ced6bfc5d2fbc4191944246b0050dabfa00318e
Author: Oliver Hartkopp <socketcan@hartkopp.net>

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

This commit fixes a race condition between bcm_sendmsg() and socket state
modifications by moving the ifindex read inside the socket lock. It also
fixes a silent failure when a target device disappears concurrently during
RX_SETUP.

Link: https://lore.kernel.org/linux-can/CAGp+u1aBK8QVjsvAxM2Ldzep4rEbsP9x_pV3At4g=h1kVEtyhA@mail.gmail.com/

> 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;
>  			}

[Severity: High]
This isn't a bug introduced by this patch, but since we are modifying
bcm_rx_setup(), I noticed a potential race condition. Does the process
context modification of RX buffers race with the softirq receive handlers?

When a user application repeatedly updates a BCM RX_SETUP filter via
sendmsg(), it modifies op->frames and resets op->last_frames directly in
process context:

net/can/bcm.c:bcm_rx_setup() {
    ...
			err = memcpy_from_msg(op->frames, msg,
					      msg_head->nframes * op->cfsiz);
			if (err < 0)
				return err;

			/* clear last_frames to indicate 'nothing received' */
			memset(op->last_frames, 0, msg_head->nframes * op->cfsiz);
    ...
}

Concurrently, if a matching CAN frame arrives, will bcm_rx_handler() in
softirq context locklessly read op->frames and update op->last_frames?

net/can/bcm.c:bcm_rx_handler() {
    ...
		for (i = 1; i < op->nframes; i++) {
			if ((get_u64(op->frames, 0) & get_u64(rxframe, 0)) ==
			    (get_u64(op->frames, 0) &
			     get_u64(op->frames + op->cfsiz * i, 0))) {
				bcm_rx_cmp_to_index(op, i, rxframe,
						    traffic_flags);
				break;
    ...
}

Could this lead to torn reads or writes if the filter logic misfires while
these buffers are observed in an inconsistent state, potentially delivering
corrupted or duplicate CAN frames to userspace?

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v4-0-aa87b8b9d33f@hartkopp.net?part=2

Re: [PATCH v4 4/7] can: bcm: fix CAN frame rx/tx statistics

[sashiko-bot]

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

Pre-existing issues:
- [High] Missing RCU memory barriers when inserting new bcm_op entries into rx_ops and tx_ops, and incorrect list traversal macro for tx_ops in a lockless reader.
--

--- Patch [4]: [PATCH v4 4/7] can: bcm: fix CAN frame rx/tx statistics ---
commit 55dc712979cc536660202ae53cf4b6529bfdf948
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: fix CAN frame rx/tx statistics

This commit fixes a data race detected by KCSAN in bcm_rx_handler by
using atomic types for frame statistics, and adds a lock-protected
helper for updates to avoid races during resets.

> --- 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) {

[Severity: High]
This isn't a bug introduced by this patch, but there appears to be a
missing RCU barrier when traversing and modifying the bcm_op lists.

Can the lockless reader in bcm_proc_show() observe uninitialized memory
here?

While the reader correctly uses list_for_each_entry_rcu() for rx_ops, the
writer in bcm_rx_setup() adds new entries using the non-RCU list_add():

net/can/bcm.c:bcm_rx_setup() {
    ...
    list_add(&op->list, &bo->rx_ops);
    ...
}

Without list_add_rcu(), the CPU could reorder the initialization of the
bcm_op struct to occur after the node becomes visible in the list.

Similarly, does the tx_ops list traversal lack both writer and reader
RCU protection?

net/can/bcm.c:bcm_tx_setup() {
    ...
    list_add(&op->list, &bo->tx_ops);
    ...
}

And later in bcm_proc_show():

net/can/bcm.c:bcm_proc_show() {
    ...
    list_for_each_entry(op, &bo->tx_ops, list) {
    ...
}

Should these lists be updated to use list_add_rcu() and
list_for_each_entry_rcu() to ensure safe concurrent iteration via procfs?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v4-0-aa87b8b9d33f@hartkopp.net?part=4