[PATCH v2 0/6] can: bcm: collected fixes

[PATCH v2 0/6] 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 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 (5):
      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

 net/can/bcm.c | 370 +++++++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 276 insertions(+), 94 deletions(-)
---
base-commit: 665159e246749578d4e4bfe106ee3b74edcdab18
change-id: 20260612-bcm_fixes-84fb4aa93ac2

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

[PATCH v2 1/6] 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 v2 2/6] 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 v2 3/6] 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.

Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
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 | 130 ++++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 99 insertions(+), 31 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index b612135b017d..1eabacad0b00 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 +292,27 @@ 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;
 	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);
+		cf = op->frames + op->cfsiz * op->currframe;
+		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 +461,11 @@ 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 +478,11 @@ 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 +622,12 @@ 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 +640,12 @@ 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 +690,39 @@ 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)) {
 		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 +742,25 @@ 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 +768,12 @@ 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 +805,12 @@ 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 +1145,11 @@ 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 +1159,28 @@ 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 +1211,12 @@ 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 +1224,55 @@ 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 +1310,12 @@ 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 +1339,38 @@ 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 v2 4/6] 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.

Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 net/can/bcm.c | 38 ++++++++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 14 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 1eabacad0b00..20b1bdc87414 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)
@@ -339,11 +352,11 @@ 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)
@@ -492,16 +505,13 @@ 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));
@@ -740,11 +750,11 @@ 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++;
+	bcm_update_stats(op);
 
 	/* 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

-- 
2.53.0

[PATCH v2 5/6] 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 20b1bdc87414..3609178a1367 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)
@@ -990,10 +990,11 @@ 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)
@@ -1131,12 +1132,11 @@ 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 */
@@ -1154,10 +1154,14 @@ 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);
@@ -1338,13 +1342,10 @@ 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))) */
 
@@ -1412,14 +1413,16 @@ 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;
 }
 
@@ -1749,12 +1752,14 @@ 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.
@@ -1781,12 +1786,14 @@ 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 v2 6/6] 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.

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 | 75 +++++++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 52 insertions(+), 23 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 3609178a1367..fdde25b5aa1d 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -450,16 +450,22 @@ 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;
 }
 
@@ -472,12 +478,21 @@ 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));
@@ -490,11 +505,11 @@ 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;
@@ -1009,64 +1024,76 @@ 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 (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);
@@ -1138,14 +1165,16 @@ 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

Re: [PATCH v2 1/6] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF

[sashiko-bot]

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

Pre-existing issues:
- [High] Missing list_add_rcu() when inserting into tx_ops and rx_ops causes RCU publish/subscribe rules violation, leading to data races and potential kernel panics with concurrent procfs readers.
- [High] Lockless updates to 64-bit ktime_t fields can cause torn reads on 32-bit architectures, leading to wildly incorrect timer timeouts.
- [High] Unprotected concurrent modification of `op->frames` via `memcpy_from_msg` in `bcm_rx_setup` and `bcm_tx_setup`.
--

--- Patch [1]: [PATCH v2 1/6] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF ---
commit 66477b55911323fb4b8a9cc14c9ed91e1fa4bfa5
Author: Lee Jones <lee@kernel.org>

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

Commit f1b4e32aca08 replaced synchronize_rcu() with call_rcu() but omitted a 
flag check in the fast-path, causing a use-after-free when thrtimer fires. 
This patch defers timer cancellation and memory deallocation to a dedicated 
unbound workqueue to safely sleep and drop socket references.

Fixes: f1b4e32aca08 ("can: bcm: use call_rcu() instead of costly synchronize_rcu()")

> ---
> 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 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 does the list insertion in bcm_tx_setup() 
and bcm_rx_setup() use list_add() instead of list_add_rcu()?

If a local unprivileged user repeatedly adds new TX/RX operations while 
concurrently reading /proc/net/can-bcm/<inode>, can bcm_proc_show() observe 
partially initialized bcm_op entries? 

bcm_proc_show() iterates over rx_ops using list_for_each_entry_rcu() and 
tx_ops using list_for_each_entry() without holding the socket lock. Could 
the missing smp_store_release() barrier in list_add() lead to torn reads of 
uninitialized list pointers and potential kernel panics?

[Severity: High]
This isn't a bug introduced by this patch, but are the 64-bit ktime_t 
fields (op->kt_ival1 and op->kt_ival2) updated locklessly in bcm_tx_setup() 
and bcm_rx_setup()?

On 32-bit architectures, can these lockless updates cause torn reads when 
bcm_tx_timeout_handler() or bcm_rx_timeout_handler() concurrently read 
these fields in softirq context to arm the hrtimer? 

Could this lead to wildly incorrect timer expirations, potentially stalling 
CAN transmissions indefinitely or flooding the bus?

[ ... ]

> @@ -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 */

[Severity: High]
This is a pre-existing issue, but is it safe to write directly into the 
active op->frames using memcpy_from_msg() without holding a lock?

When updating an existing BCM operation, bcm_tx_setup() and bcm_rx_setup() 
appear to copy user data directly into op->frames locklessly. Because 
memcpy_from_msg() can sleep on user faults, is there a significant race 
window here?

Concurrently, bcm_can_tx() reads op->frames to transmit data, and 
bcm_rx_cmp_to_index() reads op->frames to filter incoming packets. Could 
this allow partially updated or torn CAN frames to be transmitted onto the 
physical CAN bus?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v2-0-96620c534b75@hartkopp.net?part=1

Re: [PATCH v2 2/6] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure

[sashiko-bot]

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

Pre-existing issues:
- [High] Unsafe list insertions and non-RCU traversals in BCM operations lists.
- [High] Data Race and Data Corruption due to Lockless Modification of Active BCM Operations.
- [High] Corrupted BCM Operation State upon Validation Failure.
- [Medium] Unannotated lockless read of `bo->bound` and `bo->ifindex` in `bcm_notify()` during `NETDEV_DOWN`.
--

--- Patch [2]: [PATCH v2 2/6] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure ---
commit 0cd66671e00a6a20f593dd001c30f331b9c4d5d8
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 device
notification/connection by modifying the lockless fast-path and reading
ifindex under the socket lock. It also fixes a silent failure in
bcm_rx_setup() when the target device disappears.

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

> 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.

[Severity: Medium]
This is a pre-existing issue, but is the commit message accurate about
bo->ifindex only being accessed under lock_sock()?

Looking at bcm_notify(), when processing NETDEV_DOWN, it reads bo->bound
and bo->ifindex locklessly:

    case NETDEV_DOWN:
        if (bo->bound && bo->ifindex == dev->ifindex) {

Since bcm_connect() mutates these while holding lock_sock(sk), could this
cause torn reads?

> 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 is a pre-existing issue, but are the list insertions for rx_ops and
tx_ops safe for concurrent lockless readers?

bcm_rx_setup() and bcm_tx_setup() insert into bo->rx_ops and bo->tx_ops.
Concurrently, bcm_proc_show() locklessly traverses bo->tx_ops under
rcu_read_lock() using the non-rcu list_for_each_entry() instead of
list_for_each_entry_rcu():

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

Could this lead to observing uninitialized list nodes and a system crash
during procfs traversal?

[Severity: High]
This is a pre-existing issue, but does bcm_rx_setup() safely modify active
filter frames?

When updating an existing bcm operation, it appears to directly overwrite
op->frames using memcpy_from_msg() without synchronizing against softirq
routines:

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

Since bcm_rx_handler() reads op->frames in softirq context, can it observe
partially written or torn can frames during the update?

[Severity: High]
This is a pre-existing issue, but what happens if validation fails during
an update?

In bcm_tx_setup() and bcm_rx_setup(), op->frames is directly overwritten.
If a subsequent frame fails validation (such as cf->len > 64 in
bcm_tx_setup()) or memcpy_from_msg() fails, the function returns an error
without reverting the state:

    if (err < 0)
        return err;

Does this leave the operation actively running on a corrupted buffer?

[ ... ]

> @@ -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;
>  		}

[Severity: Medium]
This is a pre-existing issue, but the comment here makes the same claim
that bo->ifindex is only accessed under lock_sock().

As noted above, does bcm_notify() read bo->bound and bo->ifindex locklessly
during the NETDEV_DOWN case?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v2-0-96620c534b75@hartkopp.net?part=2

Re: [PATCH v2 3/6] can: bcm: add locking when updating filter and timer values

[sashiko-bot]

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

Pre-existing issues:
- [High] The TX timeout handler reads 64-bit ktime_t variables and 32-bit state variables locklessly, creating data races that can lead to torn ktime_t reads and erratic timer behavior.
- [High] The CAN frame payload on the transmission side is copied into the SKB locklessly, allowing a concurrent update from userspace to overwrite the frame while it is being transmitted, resulting in torn CAN frames.
--

--- Patch [3]: [PATCH v2 3/6] can: bcm: add locking when updating filter and timer values ---
commit 5cea5eef9652435aa644979477f4e925e5e24c8f
Author: Oliver Hartkopp <socketcan@hartkopp.net>

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

This commit adds a new per-op bcm_rx_update_lock to protect timer and
filter data updates in the RX handlers against concurrent execution. It
also addresses an RTR flag clearing race by normalizing the frame content
during initial preparation instead of modifying the live frame.

Link: 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..1eabacad0b001 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c
> @@ -293,22 +294,23 @@ 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;
>  	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);
> +		cf = op->frames + op->cfsiz * op->currframe;
> +		spin_unlock_bh(&op->bcm_tx_lock);
> +	}

[Severity: High]
This isn't a bug introduced by this patch, but can this lead to torn CAN
frames during transmission?

While the bcm_tx_lock protects the calculation of the cf pointer here, the
lock is dropped before calling skb_put_data(skb, cf, op->cfsiz) further
down in bcm_can_tx().

Concurrently, bcm_tx_setup() can overwrite the active op->frames buffer
using memcpy_from_msg() directly from userspace locklessly:

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

Could this allow a partially updated CAN frame to be copied into the skb and
transmitted onto the network while the data is being mutated?

[ ... ]
> @@ -461,7 +463,7 @@ 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 can the lockless read of op->kt_ival1
result in a torn read on 32-bit platforms?

In bcm_tx_setup(), the 64-bit ktime_t variables kt_ival1 and kt_ival2 can
be updated concurrently from user space data. Evaluating these values
in bcm_tx_timeout_handler() and bcm_tx_set_expiry() without holding
bcm_tx_lock could yield arbitrary timer intervals.

Could this cause the hrtimer to stall indefinitely or fire in an immediate
tight loop?

> -		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-v2-0-96620c534b75@hartkopp.net?part=3

Re: [PATCH v2 4/6] 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] Concurrent execution of bcm_rx_handler() leads to unprotected data races and potential 64-bit torn writes on op->rx_stamp and op->rx_ifindex, causing metadata corruption.
--

--- Patch [4]: [PATCH v2 4/6] can: bcm: fix CAN frame rx/tx statistics ---
commit c40daefa12b560d84d208b978162b5b62f34aade
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: fix CAN frame rx/tx statistics

This commit fixes a KCSAN-detected data race in bcm_rx_handler() when multiple
CAN frames are processed concurrently. It transitions the statistics counters
to atomic long operations and consolidates overflow checking into a new
bcm_update_stats() function.

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c

[ ... ]

> @@ -742,7 +752,7 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
>  	/* save originator for recvfrom() */
>  	op->rx_ifindex = skb->dev->ifindex;

[Severity: High]
This is a pre-existing issue, but can concurrent execution of bcm_rx_handler()
lead to unprotected data races on op->rx_stamp and op->rx_ifindex here?

If an application creates a BCM socket listening on all interfaces (ifindex=0),
and multiple CAN frames arrive concurrently from different interfaces matching
the same bcm_op, bcm_rx_handler() can be invoked concurrently on multiple CPUs.

CPU A and CPU B could both write op->rx_stamp and op->rx_ifindex outside of
any lock. If CPU A then acquires the lock and reads these values later in
bcm_send_to_user():

net/can/bcm.c:bcm_send_to_user() {
    ...
		/* restore rx timestamp */
		skb->tstamp = op->rx_stamp;
    ...
	addr->can_ifindex = op->rx_ifindex;
    ...
}

Could CPU A pick up CPU B's ifindex or a torn timestamp? This might lead to
CAN frames being delivered to userspace with mismatched interface indices or
corrupted 64-bit timestamps on 32-bit systems, potentially breaking
time-sensitive control loops.

>  	/* update statistics */
> -	op->frames_abs++;
> +	bcm_update_stats(op);
>  
>  	/* snapshot the flag under lock: op->flags/op->frames may be updated
>  	 * concurrently by bcm_rx_setup(). Do not call bcm_can_tx() while

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v2-0-96620c534b75@hartkopp.net?part=4

Re: [PATCH v2 5/6] 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] Concurrent updates to CAN frames and timers in bcm_tx_setup() race with bcm_tx_timeout_handler() and bcm_can_tx().
--

--- Patch [5]: [PATCH v2 5/6] can: bcm: add missing rcu list annotations and operations ---
commit 6cbc186daf031268589b88c789ab291e31165918
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: add missing rcu list annotations and operations

This commit adds missing list_add_rcu() calls in bcm_tx_setup() and
bcm_rx_setup() to ensure proper initialization of bcm_op structures during
RCU traversal. It also fixes the removal side in bcm_release() by properly
unlinking ops with list_del_rcu() before freeing them via call_rcu().

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

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index 20b1bdc87414a..3609178a1367d 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c
[ ... ]
> @@ -1156,6 +1156,10 @@ 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);
> +

[Severity: High]
This is a pre-existing issue, but can concurrent updates to CAN frames and
timers in bcm_tx_setup() race with bcm_tx_timeout_handler() and
bcm_can_tx()?

While a previous commit in the series fixed this exact issue for RX ops by
using a staging buffer and lock, the TX path appears to be left unprotected.

When an existing BCM TX op is running its cyclic transmission via the
hrtimer bcm_tx_timeout_handler(), and user-space calls sendmsg() with
TX_SETUP to update the op's frames or timers, bcm_tx_setup() directly
copies new data into op->frames using memcpy_from_msg() without holding
bcm_tx_lock or using a staging buffer. It also updates op->kt_ival1 and
op->kt_ival2 without locking.

Concurrently, bcm_tx_timeout_handler() reads the unprotected timer values
and invokes bcm_can_tx().

bcm_can_tx() acquires bcm_tx_lock only to resolve the cf pointer to the
current frame, but drops the lock before calling skb_put_data().

Could this allow skb_put_data(skb, cf, op->cfsiz) to copy the frame payload
out of op->frames simultaneously with memcpy_from_msg() writing to it,
resulting in a torn read that transmits corrupt or partially updated CAN
frames onto the network?

>  	if (op->flags & TX_ANNOUNCE)
>  		bcm_can_tx(op, NULL);
>

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v2-0-96620c534b75@hartkopp.net?part=5

Re: [PATCH v2 6/6] can: bcm: extend bcm_tx_lock usage for data and timer updates

[sashiko-bot]

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

New issues:
- [Medium] Reading `cf->len` after a failed `memcpy_from_msg()` accesses uninitialized heap memory and can incorrectly overwrite the returned error code.

Pre-existing issues:
- [High] The patch fails to fix the data race on `op->frames` because `bcm_can_tx()` still copies frame data locklessly, allowing the transmission of torn CAN frames.
--

--- Patch [6]: [PATCH v2 6/6] can: bcm: extend bcm_tx_lock usage for data and timer updates ---
commit 9fb191cdc2eb3086cb7c75f76d0a1d693042a43b
Author: Oliver Hartkopp <socketcan@hartkopp.net>

can: bcm: extend bcm_tx_lock usage for data and timer updates

This commit stages new CAN frame content into an allocated buffer to validate
it before updating the existing bcm_op under a lock. It also moves time
value updates under the same lock to avoid torn reads.

> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index 3609178a1367d..fdde25b5aa1d7 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c

[ ... ]

> @@ -1021,10 +1038,18 @@ 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 (op->flags & CAN_FD_FRAME) {
> @@ -1035,36 +1060,38 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
>  					err = -EINVAL;
>  			}

[Severity: Medium]
If memcpy_from_msg() fails (e.g. returning -EFAULT), will this read cf->len
from uninitialized heap memory before the error check?

Since new_frames is allocated via kmalloc(), reading cf->len might read
garbage. If the garbage value happens to be > 64, it could incorrectly
overwrite the -EFAULT in err with -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);
> +

[Severity: High]
This is a pre-existing issue, but does this still leave a data race where
bcm_can_tx() can read partially updated frames?

The commit message states that bcm_can_tx() can no longer observe a
partially updated frame. However, looking at bcm_can_tx(), it calculates
the cf pointer under the lock but then reads the frame data locklessly:

net/can/bcm.c:bcm_can_tx() {
    if (!cf) {
        spin_lock_bh(&op->bcm_tx_lock);
        cf = op->frames + op->cfsiz * op->currframe;
        spin_unlock_bh(&op->bcm_tx_lock);
    }
    ...
    skb_put_data(skb, cf, op->cfsiz);
}

Doesn't skb_put_data() read from cf locklessly, potentially racing with
the memcpy() here in bcm_tx_setup() and copying a torn frame?

>  		op->flags = msg_head->flags;

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707-bcm_fixes-v2-0-96620c534b75@hartkopp.net?part=6