FAILED: patch "[PATCH] can: replace ARPHRD_CAN type checks with can_get_ml_priv()" failed to apply to 5.10-stable tree

FAILED: patch "[PATCH] can: replace ARPHRD_CAN type checks with can_get_ml_priv()" failed to apply to 5.10-stable tree

[Sasha Levin]

The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 962947b69589881167054bae5accc8abfd5aa4b6
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '20261109202741-failed-5.10-962947b69589@kernel.org' --subject-prefix 'PATCH 5.10.y' 'HEAD^..'

Thanks,
Sasha

------------------ original commit in Linus's tree ------------------

From 962947b69589881167054bae5accc8abfd5aa4b6 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Tue, 27 Oct 2026 15:31:05 +0100
Subject: [PATCH] can: replace ARPHRD_CAN type checks with can_get_ml_priv()

Commit 4e096a18867a ("net: introduce CAN specific pointer in the struct
net_device") introduced an explicit way to assign the midlayer private
pointer (dev->ml_priv) to named users like ML_PRIV_CAN. A valid pointer
returned by can_get_ml_priv() therefore identifies a real CAN device.

The referenced commit only converted the j1939 and proc code to this
check, while the other parts of the CAN subsystem still rely on
dev->type == ARPHRD_CAN.

The TUNSETLINK ioctl allows a down TUN/TAP device to set its hardware
type to ARPHRD_CAN while dev->ml_priv remains NULL. Such a repurposed
netdevice passes the ARPHRD_CAN checks.

Commit 8aa59e355949 ("can: af_can: fix NULL pointer dereference in
can_rx_register()") already made can_rx_register() reject such devices.
But can_rx_unregister() still only checks dev->type and dereferences
the NULL ml_priv when it walks the receive lists of the device.

CAN_ISOTP reaches this path: isotp_bind() ignores the return values of
can_rx_register() and binds the socket anyway. When the socket is
released or the device is unregistered, isotp_release() and
isotp_notify() remove the filters that have never been registered and
trigger the NULL pointer dereference in can_rx_unregister(). This only
requires owning a TUN/TAP device or CAP_NET_ADMIN in an unprivileged
user namespace.

Convert the remaining ARPHRD_CAN checks in af_can, bcm, gw, isotp and
raw to can_get_ml_priv().

Fixes: 4e096a18867a ("net: introduce CAN specific pointer in the struct net_device")
Cc: stable@vger.kernel.org
Cc: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20261027-can-rx-lock-v12-1-eb5afc2d8b9b@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/af_can.c | 15 ++++++---------
 net/can/bcm.c    |  7 ++++---
 net/can/gw.c     |  7 ++++---
 net/can/isotp.c  |  5 +++--
 net/can/raw.c    |  4 ++--
 5 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/net/can/af_can.c b/net/can/af_can.c
index 34fe3b28d576f..dc27ace43719d 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -226,7 +226,7 @@ int can_send(struct sk_buff *skb, int loop)
 		goto inval_skb;
 	}
 
-	if (unlikely(skb->dev->type != ARPHRD_CAN)) {
+	if (unlikely(!can_get_ml_priv(skb->dev))) {
 		err = -EPERM;
 		goto inval_skb;
 	}
@@ -452,7 +452,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id,
 
 	/* insert new receiver  (dev,canid,mask) -> (func,data) */
 
-	if (dev && (dev->type != ARPHRD_CAN || !can_get_ml_priv(dev)))
+	if (dev && !can_get_ml_priv(dev))
 		return -ENODEV;
 
 	if (dev && !net_eq(net, dev_net(dev)))
@@ -519,7 +519,7 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id,
 	struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats;
 	struct can_dev_rcv_lists *dev_rcv_lists;
 
-	if (dev && dev->type != ARPHRD_CAN)
+	if (dev && !can_get_ml_priv(dev))
 		return;
 
 	if (dev && !net_eq(net, dev_net(dev)))
@@ -684,8 +684,7 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct can_skb_ext *csx = can_skb_ext_find(skb);
 
-	if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) ||
-		     !csx || !can_is_can_skb(skb))) {
+	if (unlikely(!can_get_ml_priv(dev) || !csx || !can_is_can_skb(skb))) {
 		pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n",
 			     dev->type, skb->len);
 
@@ -710,8 +709,7 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct can_skb_ext *csx = can_skb_ext_find(skb);
 
-	if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) ||
-		     !csx || !can_is_canfd_skb(skb))) {
+	if (unlikely(!can_get_ml_priv(dev) || !csx || !can_is_canfd_skb(skb))) {
 		pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n",
 			     dev->type, skb->len);
 
@@ -736,8 +734,7 @@ static int canxl_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct can_skb_ext *csx = can_skb_ext_find(skb);
 
-	if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) ||
-		     !csx || !can_is_canxl_skb(skb))) {
+	if (unlikely(!can_get_ml_priv(dev) || !csx || !can_is_canxl_skb(skb))) {
 		pr_warn_once("PF_CAN: dropped non conform CAN XL skbuff: dev type %d, len %d\n",
 			     dev->type, skb->len);
 
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 3d637a1e0ac1a..60406439a13f7 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -54,6 +54,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <linux/can.h>
+#include <linux/can/can-ml.h>
 #include <linux/can/core.h>
 #include <linux/can/skb.h>
 #include <linux/can/bcm.h>
@@ -1719,7 +1720,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 				goto out_release;
 			}
 
-			if (dev->type != ARPHRD_CAN) {
+			if (!can_get_ml_priv(dev)) {
 				dev_put(dev);
 				ret = -ENODEV;
 				goto out_release;
@@ -1867,7 +1868,7 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(dev))
 		return NOTIFY_DONE;
 	if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
 		return NOTIFY_DONE;
@@ -2024,7 +2025,7 @@ static int bcm_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int
 			ret = -ENODEV;
 			goto fail;
 		}
-		if (dev->type != ARPHRD_CAN) {
+		if (!can_get_ml_priv(dev)) {
 			dev_put(dev);
 			ret = -ENODEV;
 			goto fail;
diff --git a/net/can/gw.c b/net/can/gw.c
index 5793cb2420ed3..54bb5bd3242af 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -52,6 +52,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <linux/can.h>
+#include <linux/can/can-ml.h>
 #include <linux/can/core.h>
 #include <linux/can/skb.h>
 #include <linux/can/gw.h>
@@ -612,7 +613,7 @@ static int cgw_notifier(struct notifier_block *nb,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct net *net = dev_net(dev);
 
-	if (dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(dev))
 		return NOTIFY_DONE;
 
 	if (msg == NETDEV_UNREGISTER) {
@@ -1163,7 +1164,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	if (!gwj->src.dev)
 		goto out;
 
-	if (gwj->src.dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(gwj->src.dev))
 		goto out;
 
 	gwj->dst.dev = __dev_get_by_index(net, gwj->ccgw.dst_idx);
@@ -1171,7 +1172,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	if (!gwj->dst.dev)
 		goto out;
 
-	if (gwj->dst.dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(gwj->dst.dev))
 		goto out;
 
 	/* is sending the skb back to the incoming interface intended? */
diff --git a/net/can/isotp.c b/net/can/isotp.c
index d3e43ab484258..e4957855829e6 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -65,6 +65,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <linux/can.h>
+#include <linux/can/can-ml.h>
 #include <linux/can/core.h>
 #include <linux/can/skb.h>
 #include <linux/can/isotp.h>
@@ -1618,7 +1619,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 		err = -ENODEV;
 		goto out;
 	}
-	if (dev->type != ARPHRD_CAN) {
+	if (!can_get_ml_priv(dev)) {
 		err = -ENODEV;
 		goto out_put_dev;
 	}
@@ -1905,7 +1906,7 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(dev))
 		return NOTIFY_DONE;
 	if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
 		return NOTIFY_DONE;
diff --git a/net/can/raw.c b/net/can/raw.c
index 0acd4f6c6dd67..e1d741a25be3f 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -348,7 +348,7 @@ static int raw_notifier(struct notifier_block *nb, unsigned long msg,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(dev))
 		return NOTIFY_DONE;
 	if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
 		return NOTIFY_DONE;
@@ -491,7 +491,7 @@ static int raw_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int len
 			err = -ENODEV;
 			goto out;
 		}
-		if (dev->type != ARPHRD_CAN) {
+		if (!can_get_ml_priv(dev)) {
 			err = -ENODEV;
 			goto out_put_dev;
 		}
-- 
2.53.0

[PATCH 5.10.y 1/4] can: raw: fix receiver memory leak

[Oliver Hartkopp]

From: Ziyang Xuan <william.xuanziyang@huawei.com>

commit ee8b94c8510ce64afe0b87ef548d23e00915fb10 upstream.

Got kmemleak errors with the following ltp can_filter testcase:

for ((i=1; i<=100; i++))
do
        ./can_filter &
        sleep 0.1
done

==============================================================
[<00000000db4a4943>] can_rx_register+0x147/0x360 [can]
[<00000000a289549d>] raw_setsockopt+0x5ef/0x853 [can_raw]
[<000000006d3d9ebd>] __sys_setsockopt+0x173/0x2c0
[<00000000407dbfec>] __x64_sys_setsockopt+0x61/0x70
[<00000000fd468496>] do_syscall_64+0x33/0x40
[<00000000b7e47d51>] entry_SYSCALL_64_after_hwframe+0x61/0xc6

It's a bug in the concurrent scenario of unregister_netdevice_many()
and raw_release() as following:

             cpu0                                        cpu1
unregister_netdevice_many(can_dev)
  unlist_netdevice(can_dev) // dev_get_by_index() return NULL after this
  net_set_todo(can_dev)
						raw_release(can_socket)
						  dev = dev_get_by_index(, ro->ifindex); // dev == NULL
						  if (dev) { // receivers in dev_rcv_lists not free because dev is NULL
						    raw_disable_allfilters(, dev, );
						    dev_put(dev);
						  }
						  ...
						  ro->bound = 0;
						  ...

call_netdevice_notifiers(NETDEV_UNREGISTER, )
  raw_notify(, NETDEV_UNREGISTER, )
    if (ro->bound) // invalid because ro->bound has been set 0
      raw_disable_allfilters(, dev, ); // receivers in dev_rcv_lists will never be freed

Add a net_device pointer member in struct raw_sock to record bound
can_dev, and use rtnl_lock to serialize raw_socket members between
raw_bind(), raw_release(), raw_setsockopt() and raw_notify(). Use
ro->dev to decide whether to free receivers in dev_rcv_lists.

Fixes: 8d0caedb7596 ("can: bcm/raw/isotp: use per module netdevice notifier")
Reviewed-by: Oliver Hartkopp <socketcan@hartkopp.net>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Link: https://lore.kernel.org/all/20230711011737.1969582-1-william.xuanziyang@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Stable-dep-of: 962947b69589 ("can: replace ARPHRD_CAN type checks with can_get_ml_priv()")
[ backport to 5.10: Adapt the raw_release() context as
  free_percpu(ro->uniq) has already been moved out of raw_release() in
  this tree. ]
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 net/can/raw.c | 57 ++++++++++++++++++++++-----------------------------
 1 file changed, 24 insertions(+), 33 deletions(-)

diff --git a/net/can/raw.c b/net/can/raw.c
index 8bbbd9092e3a..7df3086e9f91 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -83,6 +83,7 @@ struct raw_sock {
 	struct sock sk;
 	int bound;
 	int ifindex;
+	struct net_device *dev;
 	struct list_head notifier;
 	int loopback;
 	int recv_own_msgs;
@@ -275,7 +276,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg,
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		return;
 
-	if (ro->ifindex != dev->ifindex)
+	if (ro->dev != dev)
 		return;
 
 	switch (msg) {
@@ -290,6 +291,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg,
 
 		ro->ifindex = 0;
 		ro->bound = 0;
+		ro->dev = NULL;
 		ro->count = 0;
 		release_sock(sk);
 
@@ -343,6 +345,7 @@ static int raw_init(struct sock *sk)
 
 	ro->bound            = 0;
 	ro->ifindex          = 0;
+	ro->dev              = NULL;
 
 	/* set default filter to single entry dfilter */
 	ro->dfilter.can_id   = 0;
@@ -392,19 +395,13 @@ static int raw_release(struct socket *sock)
 
 	lock_sock(sk);
 
+	rtnl_lock();
 	/* remove current filters & unregister */
 	if (ro->bound) {
-		if (ro->ifindex) {
-			struct net_device *dev;
-
-			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
-			if (dev) {
-				raw_disable_allfilters(dev_net(dev), dev, sk);
-				dev_put(dev);
-			}
-		} else {
+		if (ro->dev)
+			raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk);
+		else
 			raw_disable_allfilters(sock_net(sk), NULL, sk);
-		}
 	}
 
 	if (ro->count > 1)
@@ -412,7 +409,9 @@ static int raw_release(struct socket *sock)
 
 	ro->ifindex = 0;
 	ro->bound = 0;
+	ro->dev = NULL;
 	ro->count = 0;
+	rtnl_unlock();
 
 	sock_orphan(sk);
 	sock->sk = NULL;
@@ -428,6 +427,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
 	struct sock *sk = sock->sk;
 	struct raw_sock *ro = raw_sk(sk);
+	struct net_device *dev = NULL;
 	int ifindex;
 	int err = 0;
 	int notify_enetdown = 0;
@@ -437,14 +437,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	if (addr->can_family != AF_CAN)
 		return -EINVAL;
 
+	rtnl_lock();
 	lock_sock(sk);
 
 	if (ro->bound && addr->can_ifindex == ro->ifindex)
 		goto out;
 
 	if (addr->can_ifindex) {
-		struct net_device *dev;
-
 		dev = dev_get_by_index(sock_net(sk), addr->can_ifindex);
 		if (!dev) {
 			err = -ENODEV;
@@ -473,26 +472,20 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	if (!err) {
 		if (ro->bound) {
 			/* unregister old filters */
-			if (ro->ifindex) {
-				struct net_device *dev;
-
-				dev = dev_get_by_index(sock_net(sk),
-						       ro->ifindex);
-				if (dev) {
-					raw_disable_allfilters(dev_net(dev),
-							       dev, sk);
-					dev_put(dev);
-				}
-			} else {
+			if (ro->dev)
+				raw_disable_allfilters(dev_net(ro->dev),
+						       ro->dev, sk);
+			else
 				raw_disable_allfilters(sock_net(sk), NULL, sk);
-			}
 		}
 		ro->ifindex = ifindex;
 		ro->bound = 1;
+		ro->dev = dev;
 	}
 
  out:
 	release_sock(sk);
+	rtnl_unlock();
 
 	if (notify_enetdown) {
 		sk->sk_err = ENETDOWN;
@@ -558,9 +551,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		rtnl_lock();
 		lock_sock(sk);
 
-		if (ro->bound && ro->ifindex) {
-			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
-			if (!dev) {
+		dev = ro->dev;
+		if (ro->bound && dev) {
+			if (dev->reg_state != NETREG_REGISTERED) {
 				if (count > 1)
 					kfree(filter);
 				err = -ENODEV;
@@ -601,7 +594,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		ro->count  = count;
 
  out_fil:
-		dev_put(dev);
 		release_sock(sk);
 		rtnl_unlock();
 
@@ -619,9 +611,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		rtnl_lock();
 		lock_sock(sk);
 
-		if (ro->bound && ro->ifindex) {
-			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
-			if (!dev) {
+		dev = ro->dev;
+		if (ro->bound && dev) {
+			if (dev->reg_state != NETREG_REGISTERED) {
 				err = -ENODEV;
 				goto out_err;
 			}
@@ -645,7 +637,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		ro->err_mask = err_mask;
 
  out_err:
-		dev_put(dev);
 		release_sock(sk);
 		rtnl_unlock();
 

[PATCH 5.10.y 2/4] can: raw: fix lockdep issue in raw_release()

[Oliver Hartkopp]

From: Eric Dumazet <edumazet@google.com>

commit 11c9027c983e9e4b408ee5613b6504d24ebd85be upstream.

syzbot complained about a lockdep issue [1]

Since raw_bind() and raw_setsockopt() first get RTNL
before locking the socket, we must adopt the same order in raw_release()

[1]
WARNING: possible circular locking dependency detected
6.5.0-rc1-syzkaller-00192-g78adb4bcf99e #0 Not tainted
------------------------------------------------------
syz-executor.0/14110 is trying to acquire lock:
ffff88804e4b6130 (sk_lock-AF_CAN){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1708 [inline]
ffff88804e4b6130 (sk_lock-AF_CAN){+.+.}-{0:0}, at: raw_bind+0xb1/0xab0 net/can/raw.c:435

but task is already holding lock:
ffffffff8e3df368 (rtnl_mutex){+.+.}-{3:3}, at: raw_bind+0xa7/0xab0 net/can/raw.c:434

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (rtnl_mutex){+.+.}-{3:3}:
__mutex_lock_common kernel/locking/mutex.c:603 [inline]
__mutex_lock+0x181/0x1340 kernel/locking/mutex.c:747
raw_release+0x1c6/0x9b0 net/can/raw.c:391
__sock_release+0xcd/0x290 net/socket.c:654
sock_close+0x1c/0x20 net/socket.c:1386
__fput+0x3fd/0xac0 fs/file_table.c:384
task_work_run+0x14d/0x240 kernel/task_work.c:179
resume_user_mode_work include/linux/resume_user_mode.h:49 [inline]
exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
exit_to_user_mode_prepare+0x210/0x240 kernel/entry/common.c:204
__syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline]
syscall_exit_to_user_mode+0x1d/0x50 kernel/entry/common.c:297
do_syscall_64+0x44/0xb0 arch/x86/entry/common.c:86
entry_SYSCALL_64_after_hwframe+0x63/0xcd

-> #0 (sk_lock-AF_CAN){+.+.}-{0:0}:
check_prev_add kernel/locking/lockdep.c:3142 [inline]
check_prevs_add kernel/locking/lockdep.c:3261 [inline]
validate_chain kernel/locking/lockdep.c:3876 [inline]
__lock_acquire+0x2e3d/0x5de0 kernel/locking/lockdep.c:5144
lock_acquire kernel/locking/lockdep.c:5761 [inline]
lock_acquire+0x1ae/0x510 kernel/locking/lockdep.c:5726
lock_sock_nested+0x3a/0xf0 net/core/sock.c:3492
lock_sock include/net/sock.h:1708 [inline]
raw_bind+0xb1/0xab0 net/can/raw.c:435
__sys_bind+0x1ec/0x220 net/socket.c:1792
__do_sys_bind net/socket.c:1803 [inline]
__se_sys_bind net/socket.c:1801 [inline]
__x64_sys_bind+0x72/0xb0 net/socket.c:1801
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

other info that might help us debug this:

Possible unsafe locking scenario:

CPU0 CPU1
---- ----
lock(rtnl_mutex);
        lock(sk_lock-AF_CAN);
        lock(rtnl_mutex);
lock(sk_lock-AF_CAN);

*** DEADLOCK ***

1 lock held by syz-executor.0/14110:

stack backtrace:
CPU: 0 PID: 14110 Comm: syz-executor.0 Not tainted 6.5.0-rc1-syzkaller-00192-g78adb4bcf99e #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/03/2023
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xd9/0x1b0 lib/dump_stack.c:106
check_noncircular+0x311/0x3f0 kernel/locking/lockdep.c:2195
check_prev_add kernel/locking/lockdep.c:3142 [inline]
check_prevs_add kernel/locking/lockdep.c:3261 [inline]
validate_chain kernel/locking/lockdep.c:3876 [inline]
__lock_acquire+0x2e3d/0x5de0 kernel/locking/lockdep.c:5144
lock_acquire kernel/locking/lockdep.c:5761 [inline]
lock_acquire+0x1ae/0x510 kernel/locking/lockdep.c:5726
lock_sock_nested+0x3a/0xf0 net/core/sock.c:3492
lock_sock include/net/sock.h:1708 [inline]
raw_bind+0xb1/0xab0 net/can/raw.c:435
__sys_bind+0x1ec/0x220 net/socket.c:1792
__do_sys_bind net/socket.c:1803 [inline]
__se_sys_bind net/socket.c:1801 [inline]
__x64_sys_bind+0x72/0xb0 net/socket.c:1801
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7fd89007cb29
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fd890d2a0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000031
RAX: ffffffffffffffda RBX: 00007fd89019bf80 RCX: 00007fd89007cb29
RDX: 0000000000000010 RSI: 0000000020000040 RDI: 0000000000000003
RBP: 00007fd8900c847a R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007fd89019bf80 R15: 00007ffebf8124f8
</TASK>

Fixes: ee8b94c8510c ("can: raw: fix receiver memory leak")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ziyang Xuan <william.xuanziyang@huawei.com>
Cc: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: stable@vger.kernel.org
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/all/20230720114438.172434-1-edumazet@google.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Stable-dep-of: 962947b69589 ("can: replace ARPHRD_CAN type checks with can_get_ml_priv()")
[ backport to 5.10: Adapt the raw_release() context as
  free_percpu(ro->uniq) has already been moved out of raw_release() in
  this tree. ]
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 net/can/raw.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/can/raw.c b/net/can/raw.c
index 7df3086e9f91..c9513dca8fc9 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -393,9 +393,9 @@ static int raw_release(struct socket *sock)
 	list_del(&ro->notifier);
 	spin_unlock(&raw_notifier_lock);
 
+	rtnl_lock();
 	lock_sock(sk);
 
-	rtnl_lock();
 	/* remove current filters & unregister */
 	if (ro->bound) {
 		if (ro->dev)
@@ -411,12 +411,13 @@ static int raw_release(struct socket *sock)
 	ro->bound = 0;
 	ro->dev = NULL;
 	ro->count = 0;
-	rtnl_unlock();
 
 	sock_orphan(sk);
 	sock->sk = NULL;
 
 	release_sock(sk);
+	rtnl_unlock();
+
 	sock_put(sk);
 
 	return 0;

[PATCH 5.10.y 3/4] can: raw: add missing refcount for memory leak fix

[Oliver Hartkopp]

commit c275a176e4b69868576e543409927ae75e3a3288 upstream.

Commit ee8b94c8510c ("can: raw: fix receiver memory leak") introduced
a new reference to the CAN netdevice that has assigned CAN filters.
But this new ro->dev reference did not maintain its own refcount which
lead to another KASAN use-after-free splat found by Eric Dumazet.

This patch ensures a proper refcount for the CAN nedevice.

Fixes: ee8b94c8510c ("can: raw: fix receiver memory leak")
Reported-by: Eric Dumazet <edumazet@google.com>
Cc: Ziyang Xuan <william.xuanziyang@huawei.com>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20230821144547.6658-3-socketcan@hartkopp.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 962947b69589 ("can: replace ARPHRD_CAN type checks with can_get_ml_priv()")
[ backport to 5.10: Use dev_hold()/dev_put() as in the 5.15-stable
  backport, as this tree has no netdevice reference tracker. ]
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 net/can/raw.c | 34 +++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)

diff --git a/net/can/raw.c b/net/can/raw.c
index c9513dca8fc9..3e2822707ed8 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -283,8 +283,10 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg,
 	case NETDEV_UNREGISTER:
 		lock_sock(sk);
 		/* remove current filters & unregister */
-		if (ro->bound)
+		if (ro->bound) {
 			raw_disable_allfilters(dev_net(dev), dev, sk);
+			dev_put(dev);
+		}
 
 		if (ro->count > 1)
 			kfree(ro->filter);
@@ -398,10 +400,12 @@ static int raw_release(struct socket *sock)
 
 	/* remove current filters & unregister */
 	if (ro->bound) {
-		if (ro->dev)
+		if (ro->dev) {
 			raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk);
-		else
+			dev_put(ro->dev);
+		} else {
 			raw_disable_allfilters(sock_net(sk), NULL, sk);
+		}
 	}
 
 	if (ro->count > 1)
@@ -451,10 +455,10 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 			goto out;
 		}
 		if (dev->type != ARPHRD_CAN) {
-			dev_put(dev);
 			err = -ENODEV;
-			goto out;
+			goto out_put_dev;
 		}
+
 		if (!(dev->flags & IFF_UP))
 			notify_enetdown = 1;
 
@@ -462,7 +466,9 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 
 		/* filters set by default/setsockopt */
 		err = raw_enable_allfilters(sock_net(sk), dev, sk);
-		dev_put(dev);
+		if (err)
+			goto out_put_dev;
+
 	} else {
 		ifindex = 0;
 
@@ -473,18 +479,28 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	if (!err) {
 		if (ro->bound) {
 			/* unregister old filters */
-			if (ro->dev)
+			if (ro->dev) {
 				raw_disable_allfilters(dev_net(ro->dev),
 						       ro->dev, sk);
-			else
+				/* drop reference to old ro->dev */
+				dev_put(ro->dev);
+			} else {
 				raw_disable_allfilters(sock_net(sk), NULL, sk);
+			}
 		}
 		ro->ifindex = ifindex;
 		ro->bound = 1;
+		/* bind() ok -> hold a reference for new ro->dev */
 		ro->dev = dev;
+		if (ro->dev)
+			dev_hold(ro->dev);
 	}
 
- out:
+out_put_dev:
+	/* remove potential reference from dev_get_by_index() */
+	if (dev)
+		dev_put(dev);
+out:
 	release_sock(sk);
 	rtnl_unlock();
 

[PATCH 5.10.y 4/4] can: replace ARPHRD_CAN type checks with can_get_ml_priv()

[Oliver Hartkopp]

commit 962947b69589881167054bae5accc8abfd5aa4b6 upstream.

Commit 4e096a18867a ("net: introduce CAN specific pointer in the struct
net_device") introduced an explicit way to assign the midlayer private
pointer (dev->ml_priv) to named users like ML_PRIV_CAN. A valid pointer
returned by can_get_ml_priv() therefore identifies a real CAN device.

The referenced commit only converted the j1939 and proc code to this
check, while the other parts of the CAN subsystem still rely on
dev->type == ARPHRD_CAN.

The TUNSETLINK ioctl allows a down TUN/TAP device to set its hardware
type to ARPHRD_CAN while dev->ml_priv remains NULL. Such a repurposed
netdevice passes the ARPHRD_CAN checks.

Commit 8aa59e355949 ("can: af_can: fix NULL pointer dereference in
can_rx_register()") already made can_rx_register() reject such devices.
But can_rx_unregister() still only checks dev->type and dereferences
the NULL ml_priv when it walks the receive lists of the device.

CAN_ISOTP reaches this path: isotp_bind() ignores the return values of
can_rx_register() and binds the socket anyway. When the socket is
released or the device is unregistered, isotp_release() and
isotp_notify() remove the filters that have never been registered and
trigger the NULL pointer dereference in can_rx_unregister(). This only
requires owning a TUN/TAP device or CAP_NET_ADMIN in an unprivileged
user namespace.

Convert the remaining ARPHRD_CAN checks in af_can, bcm, gw, isotp and
raw to can_get_ml_priv().

Fixes: 4e096a18867a ("net: introduce CAN specific pointer in the struct net_device")
Cc: stable@vger.kernel.org
Cc: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20261027-can-rx-lock-v12-1-eb5afc2d8b9b@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
[ backport to 5.10: This tree has no can_skb_ext, so only the ARPHRD_CAN
  check is removed from the conditions in can_rcv() and canfd_rcv().
  There is no canxl_rcv() in this tree. Add the <linux/can/can-ml.h>
  include to raw.c, which upstream got with commit faba5860fcf9 ("can:
  raw: instantly reject disabled CAN frames"). ]
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 net/can/af_can.c | 10 +++++-----
 net/can/bcm.c    |  7 ++++---
 net/can/gw.c     |  7 ++++---
 net/can/isotp.c  |  5 +++--
 net/can/raw.c    |  5 +++--
 5 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/net/can/af_can.c b/net/can/af_can.c
index 05066662279d..8131992809bb 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -225,7 +225,7 @@ int can_send(struct sk_buff *skb, int loop)
 		goto inval_skb;
 	}
 
-	if (unlikely(skb->dev->type != ARPHRD_CAN)) {
+	if (unlikely(!can_get_ml_priv(skb->dev))) {
 		err = -EPERM;
 		goto inval_skb;
 	}
@@ -452,7 +452,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id,
 
 	/* insert new receiver  (dev,canid,mask) -> (func,data) */
 
-	if (dev && (dev->type != ARPHRD_CAN || !can_get_ml_priv(dev)))
+	if (dev && !can_get_ml_priv(dev))
 		return -ENODEV;
 
 	if (dev && !net_eq(net, dev_net(dev)))
@@ -519,7 +519,7 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id,
 	struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats;
 	struct can_dev_rcv_lists *dev_rcv_lists;
 
-	if (dev && dev->type != ARPHRD_CAN)
+	if (dev && !can_get_ml_priv(dev))
 		return;
 
 	if (dev && !net_eq(net, dev_net(dev)))
@@ -687,7 +687,7 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || skb->len != CAN_MTU)) {
+	if (unlikely(!can_get_ml_priv(dev) || skb->len != CAN_MTU)) {
 		pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n",
 			     dev->type, skb->len);
 		goto free_skb;
@@ -713,7 +713,7 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || skb->len != CANFD_MTU)) {
+	if (unlikely(!can_get_ml_priv(dev) || skb->len != CANFD_MTU)) {
 		pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n",
 			     dev->type, skb->len);
 		goto free_skb;
diff --git a/net/can/bcm.c b/net/can/bcm.c
index f655764aae83..99abdd11f107 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -54,6 +54,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <linux/can.h>
+#include <linux/can/can-ml.h>
 #include <linux/can/core.h>
 #include <linux/can/skb.h>
 #include <linux/can/bcm.h>
@@ -1663,7 +1664,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 				goto out_release;
 			}
 
-			if (dev->type != ARPHRD_CAN) {
+			if (!can_get_ml_priv(dev)) {
 				dev_put(dev);
 				ret = -ENODEV;
 				goto out_release;
@@ -1811,7 +1812,7 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(dev))
 		return NOTIFY_DONE;
 	if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
 		return NOTIFY_DONE;
@@ -1967,7 +1968,7 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
 			ret = -ENODEV;
 			goto fail;
 		}
-		if (dev->type != ARPHRD_CAN) {
+		if (!can_get_ml_priv(dev)) {
 			dev_put(dev);
 			ret = -ENODEV;
 			goto fail;
diff --git a/net/can/gw.c b/net/can/gw.c
index c6efa4830ce9..55605135ca58 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -52,6 +52,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <linux/can.h>
+#include <linux/can/can-ml.h>
 #include <linux/can/core.h>
 #include <linux/can/skb.h>
 #include <linux/can/gw.h>
@@ -541,7 +542,7 @@ static int cgw_notifier(struct notifier_block *nb,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct net *net = dev_net(dev);
 
-	if (dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(dev))
 		return NOTIFY_DONE;
 
 	if (msg == NETDEV_UNREGISTER) {
@@ -1092,7 +1093,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	if (!gwj->src.dev)
 		goto out;
 
-	if (gwj->src.dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(gwj->src.dev))
 		goto out;
 
 	gwj->dst.dev = __dev_get_by_index(net, gwj->ccgw.dst_idx);
@@ -1100,7 +1101,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	if (!gwj->dst.dev)
 		goto out;
 
-	if (gwj->dst.dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(gwj->dst.dev))
 		goto out;
 
 	ASSERT_RTNL();
diff --git a/net/can/isotp.c b/net/can/isotp.c
index d06a99ce8413..e4542fdf8431 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -65,6 +65,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <linux/can.h>
+#include <linux/can/can-ml.h>
 #include <linux/can/core.h>
 #include <linux/can/skb.h>
 #include <linux/can/isotp.h>
@@ -1550,7 +1551,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 		err = -ENODEV;
 		goto out;
 	}
-	if (dev->type != ARPHRD_CAN) {
+	if (!can_get_ml_priv(dev)) {
 		err = -ENODEV;
 		goto out_put_dev;
 	}
@@ -1850,7 +1851,7 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(dev))
 		return NOTIFY_DONE;
 	if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
 		return NOTIFY_DONE;
diff --git a/net/can/raw.c b/net/can/raw.c
index 3e2822707ed8..293e79aadd32 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -49,6 +49,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <linux/can.h>
+#include <linux/can/can-ml.h>
 #include <linux/can/core.h>
 #include <linux/can/skb.h>
 #include <linux/can/raw.h>
@@ -315,7 +316,7 @@ static int raw_notifier(struct notifier_block *nb, unsigned long msg,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (dev->type != ARPHRD_CAN)
+	if (!can_get_ml_priv(dev))
 		return NOTIFY_DONE;
 	if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
 		return NOTIFY_DONE;
@@ -454,7 +455,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 			err = -ENODEV;
 			goto out;
 		}
-		if (dev->type != ARPHRD_CAN) {
+		if (!can_get_ml_priv(dev)) {
 			err = -ENODEV;
 			goto out_put_dev;
 		}

Re: [PATCH 5.10.y 1/4] can: raw: fix receiver memory leak

[Sasha Levin]

> can: raw: fix receiver memory leak

Queued the series for 5.10, thanks.

-- 
Thanks,
Sasha