[PATCH v8 1/7] can: proc: reset pkg_stats atomics individually

[PATCH v8 1/7] can: proc: reset pkg_stats atomics individually

[Oliver Hartkopp]

From: Runyu Xiao <runyu.xiao@seu.edu.cn>

Commit 80b5f90158d1 ("can: statistics: use atomic access in hot path")
converted several members of struct can_pkg_stats to atomic_long_t and
updated the hot TX/RX and procfs read paths to use atomic_long_*()
helpers. However, can_init_stats() still clears the whole struct with
memset().

can_init_stats() is reached from can_stat_update() in timer context and
also from the procfs reset path. Those paths can run while the TX/RX hot
paths are concurrently updating rx_frames, tx_frames, matches and their
*_delta counters. Hitting the whole-struct memset() in that window
performs plain writes to fields that otherwise follow an atomic_long_t
access contract, which can lose or mix live statistics updates.

This issue was found by source-level API-misuse analysis looking for
whole-object resets left behind after atomic_long_t conversions, then
manually audited on Linux v6.18.21.

Replace the whole-struct memset() with a helper that resets the
atomic_long_t counters via atomic_long_set() and clears the derived
scalar statistics explicitly. This preserves the existing reset
semantics for scalar fields while restoring atomic access discipline for
the live counters.

Build-tested by compiling net/can/proc.o on x86_64 netdev/main.
Runtime-tested with a QEMU + vcan setup on Linux v6.18.21 by driving
concurrent traffic and reset_stats reads, which reproduced inconsistent
exported statistics before the fix.

[Hartkopp] can_stat_update() also read the *_delta counters at the
beginning and cleared them with atomic_long_set() at the end. Increments
from the hot path in between were lost for both the current and the next
interval. Use atomic_long_xchg() to fetch and clear the *_delta counters
in one atomic step instead.

Fixes: 80b5f90158d1 ("can: statistics: use atomic access in hot path")
Cc: stable@vger.kernel.org
Signed-off-by: Runyu Xiao <runyu.xiao@seu.edu.cn>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 net/can/proc.c | 39 +++++++++++++++++++++++++++++----------
 1 file changed, 29 insertions(+), 10 deletions(-)

diff --git a/net/can/proc.c b/net/can/proc.c
index de4d05ae3459..70104f13077e 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -74,20 +74,43 @@ static const char rx_list_name[][8] = {
 
 /*
  * af_can statistics stuff
  */
 
+static void can_reset_pkg_stats(struct can_pkg_stats *pkg_stats)
+{
+	atomic_long_set(&pkg_stats->rx_frames, 0);
+	atomic_long_set(&pkg_stats->tx_frames, 0);
+	atomic_long_set(&pkg_stats->matches, 0);
+
+	pkg_stats->total_rx_rate = 0;
+	pkg_stats->total_tx_rate = 0;
+	pkg_stats->total_rx_match_ratio = 0;
+
+	pkg_stats->current_rx_rate = 0;
+	pkg_stats->current_tx_rate = 0;
+	pkg_stats->current_rx_match_ratio = 0;
+
+	pkg_stats->max_rx_rate = 0;
+	pkg_stats->max_tx_rate = 0;
+	pkg_stats->max_rx_match_ratio = 0;
+
+	atomic_long_set(&pkg_stats->rx_frames_delta, 0);
+	atomic_long_set(&pkg_stats->tx_frames_delta, 0);
+	atomic_long_set(&pkg_stats->matches_delta, 0);
+}
+
 static void can_init_stats(struct net *net)
 {
 	struct can_pkg_stats *pkg_stats = net->can.pkg_stats;
 	struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats;
 	/*
-	 * This memset function is called from a timer context (when
+	 * This stats reset is called from a timer context (when
 	 * can_stattimer is active which is the default) OR in a process
 	 * context (reading the proc_fs when can_stattimer is disabled).
 	 */
-	memset(pkg_stats, 0, sizeof(struct can_pkg_stats));
+	can_reset_pkg_stats(pkg_stats);
 	pkg_stats->jiffies_init = jiffies;
 
 	rcv_lists_stats->stats_reset++;
 
 	if (user_reset) {
@@ -119,13 +142,14 @@ void can_stat_update(struct timer_list *t)
 	unsigned long j = jiffies; /* snapshot */
 
 	long rx_frames = atomic_long_read(&pkg_stats->rx_frames);
 	long tx_frames = atomic_long_read(&pkg_stats->tx_frames);
 	long matches = atomic_long_read(&pkg_stats->matches);
-	long rx_frames_delta = atomic_long_read(&pkg_stats->rx_frames_delta);
-	long tx_frames_delta = atomic_long_read(&pkg_stats->tx_frames_delta);
-	long matches_delta = atomic_long_read(&pkg_stats->matches_delta);
+	/* fetch and clear values for 'current rate' calculation */
+	long rx_frames_delta = atomic_long_xchg(&pkg_stats->rx_frames_delta, 0);
+	long tx_frames_delta = atomic_long_xchg(&pkg_stats->tx_frames_delta, 0);
+	long matches_delta = atomic_long_xchg(&pkg_stats->matches_delta, 0);
 
 	/* restart counting in timer context on user request */
 	if (user_reset)
 		can_init_stats(net);
 
@@ -170,15 +194,10 @@ void can_stat_update(struct timer_list *t)
 		pkg_stats->max_rx_rate = pkg_stats->current_rx_rate;
 
 	if (pkg_stats->max_rx_match_ratio < pkg_stats->current_rx_match_ratio)
 		pkg_stats->max_rx_match_ratio = pkg_stats->current_rx_match_ratio;
 
-	/* clear values for 'current rate' calculation */
-	atomic_long_set(&pkg_stats->tx_frames_delta, 0);
-	atomic_long_set(&pkg_stats->rx_frames_delta, 0);
-	atomic_long_set(&pkg_stats->matches_delta, 0);
-
 	/* restart timer (one second) */
 	mod_timer(&net->can.stattimer, round_jiffies(jiffies + HZ));
 }
 
 /*
-- 
2.43.0

[PATCH v8 5/7] can: isotp: check the return values of can_rx_register() in isotp_bind()

[Oliver Hartkopp]

isotp_bind() ignores the return values of can_rx_register() for the RX
and the echo receiver and binds the socket anyway. When a receiver can
not be allocated, bind() succeeds without this receiver, so the socket
does not receive frames or its transmissions time out. isotp_release()
and isotp_notify() later try to remove the missing receiver, which
triggers the "receive list entry not found" warning in
can_rx_unregister().

As the device has been checked before and RTNL prevents a namespace
change during bind(), only -ENOMEM can be returned here.

Check the return values, remove an already registered RX receiver when
the echo receiver can not be registered and return the error.

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Cc: stable@vger.kernel.org
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 net/can/isotp.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index 1a272ce6a2bd..da80ef606ce0 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1622,20 +1622,29 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 	if (!(dev->flags & IFF_UP))
 		notify_enetdown = 1;
 
 	ifindex = dev->ifindex;
 
-	if (isotp_register_rxid(so))
-		can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id),
-				isotp_rcv, sk, sock_i_ino(sk), sk);
+	if (isotp_register_rxid(so)) {
+		err = can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id),
+				      isotp_rcv, sk, sock_i_ino(sk), sk);
+		if (err)
+			goto out_put_dev;
+	}
 
 	/* no consecutive frame echo skb in flight */
 	WRITE_ONCE(so->cfecho, 0);
 
 	/* register for echo skb's */
-	can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id),
-			isotp_rcv_echo, sk, sock_i_ino(sk), sk);
+	err = can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id),
+			      isotp_rcv_echo, sk, sock_i_ino(sk), sk);
+	if (err) {
+		if (isotp_register_rxid(so))
+			can_rx_unregister(net, dev, rx_id, SINGLE_MASK(rx_id),
+					  isotp_rcv, sk);
+		goto out_put_dev;
+	}
 
 	/* switch to new settings */
 	so->ifindex = ifindex;
 	so->rxid = rx_id;
 	so->txid = tx_id;
-- 
2.43.0

[PATCH v8 6/7] can: protect the receive lists with a per-device lock

[Oliver Hartkopp]

The receive lists of a CAN device are located in the device's
can_ml_priv and travel with the device when it is moved to another
network namespace. But they are protected by the per-netns
rcvlists_lock. So can_rx_unregister() needs dev_net(dev) to pick the
right lock and silently returns when the passed namespace does not
match dev_net(dev) anymore.

isotp_release() and bcm_release() leave their notifier list before they
take any lock that serializes against the netdev notifier, which runs
under RTNL. When the bound device is moved to another namespace in this
window, the notifier skips the socket and the release path has to remove
the filters itself. isotp_release() passes the socket's namespace, which
does not match dev_net(dev) anymore. bcm_rx_unreg() passes dev_net(dev),
which can_rx_unregister() reads again for its check, so a namespace
change between both reads makes the check fail as well. In both cases
can_rx_unregister() silently returns. As can_rx_register() stores
rcv->sk without a reference, the remaining receivers point to the freed
socket (isotp) or the freed op (bcm):

  BUG: KASAN: use-after-free in isotp_rcv+0x1570/0x24d0
  Read of size 1 at addr ffff888118130552 by task isotp_ns_uaf/578
   can_rcv_filter+0x4af/0x8c0
   can_receive+0x28d/0x3c0
   can_rcv+0x2a9/0x310
   __netif_receive_skb_one_core+0x21a/0x260
   process_backlog+0x210/0x760

Besides this, the lists of a device are protected by the rcvlists_lock
of the namespace that is passed in. Callers which pass dev_net(dev) read
it at different times, so the same lists may be modified under the locks
of different namespaces while the device is moved.

Taking RTNL in these release paths is no option: raw_bind(),
raw_setsockopt() and raw_release() already hold RTNL while adding and
removing up to CAN_RAW_FILTER_MAX filters per socket, which unprivileged
users can trigger repeatedly and which makes RTNL a global bottleneck.

Instead fix the root cause and add a spinlock to struct
can_dev_rcv_lists, which protects the receive lists of a CAN device or
the 'any' CAN device lists of a namespace. It is initialized in
can_set_ml_priv(), which is used by all CAN network devices. With this,
can_rx_unregister() finds the subscription independently of the
current namespace of the device. The protocols keep the device valid
with their tracked references. The per-netns rcvlists_lock only protects
the receive list statistics anymore, and CAN_RAW, CAN_BCM and CAN_ISOTP
pass the namespace that has been used for can_rx_register().

So isotp_release() and bcm_release() now remove their filters correctly
without RTNL, and raw_release(), raw_setsockopt(), raw_bind() and
isotp_bind() do not need RTNL anymore and add and remove their filters
under lock_sock(). To serialize bind() with NETDEV_UNREGISTER, bind()
publishes the device inside the RCU section of its lookup, and
raw_notify() and isotp_notify() recheck the bound device under lock_sock().
As RTNL does not keep NETDEV_DOWN out of bind() anymore, bind() checks
IFF_UP after publishing the bound device, with a barrier pair against
raw_notify() and isotp_notify(), so a down transition during bind() is
still reported with ENETDOWN.

Fixes: 20bab8b88baa ("can: isotp: fix use-after-free race with concurrent NETDEV_UNREGISTER")
Fixes: 8e8cda6d737d ("can: initial support for network namespaces")
Reported-by: Norbert Szetei <norbert@doyensec.com>
Link: https://lore.kernel.org/linux-can/CEA6A38A-2646-4ADA-95B4-CBAE2F301A8E@doyensec.com/
Cc: stable@vger.kernel.org
Assisted-by: Claude:claude-opus-5-5
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
Changes in v8:
- rebased on the new patch "can: isotp: check the return values of
  can_rx_register() in isotp_bind()": isotp_bind() resets the published
  so->dev again when the registration of a receiver fails
- isotp_bind(): check IFF_UP at the end of a successful bind(), as
  raw_bind() does, so that a failing bind() does not report ENETDOWN
- isotp_notify(): report NETDEV_DOWN only for a bound socket. As
  isotp_bind() sets so->bound before its IFF_UP check, a failing
  isotp_bind() can not get a needless ENETDOWN from the notifier anymore
- isotp_sendmsg() / isotp_recvmsg(): read so->bound with READ_ONCE(), as
  it is written with WRITE_ONCE() now
- raw_setsockopt(): moved copying the user space data outside of
  lock_sock() to a separate patch to keep this patch focused on the
  locking changes and to ease review
- v7: https://lore.kernel.org/linux-can/20261022114202.180023-6-socketcan@hartkopp.net/

Changes in v7:
- raw_bind() / isotp_bind(): report ENETDOWN before release_sock(), so
  that a concurrent NETDEV_UNREGISTER waiting for lock_sock() in
  raw_notify() / isotp_notify() can not have its ENODEV overwritten by
  ENETDOWN (Sashiko review)
- raw_notify() / isotp_notify(): report ENODEV for NETDEV_UNREGISTER
  before release_sock() for consistency (Sashiko review)
- v6: https://lore.kernel.org/linux-can/20261021231130.2085690-12-mkl@pengutronix.de/

Changes in v6:
- isotp_bind(): check the device (CAN device, MTU) before publishing
  so->dev, so bind() can not fail after so->dev has become visible to
  isotp_notify(). A failing bind() can not get a needless ENETDOWN from
  a concurrent NETDEV_DOWN anymore (Sashiko review)
- v5: https://lore.kernel.org/linux-can/20261020203257.230955-6-socketcan@hartkopp.net/

Changes in v5:
- raw_bind() / isotp_bind(): check IFF_UP after publishing the bound
  device, with an smp_mb() pair against raw_notify() / isotp_notify() for
  NETDEV_DOWN, so a down transition during bind() is reported with
  ENETDOWN again, as with RTNL before (Sashiko review). isotp_bind()
  already published so->dev before the IFF_UP check, but without a
  barrier the load could still pass the store.
- raw_bind() no longer reports ENETDOWN when bind() fails
- rcvlists_lock comment names the rcv_entries(_max) stats (Sashiko review)
- can_rx_unregister() kernel-doc and commit message: @net should be the
  namespace of can_rx_register(), otherwise only the statistics become
  imprecise (j1939, Sashiko review)
- v4: https://lore.kernel.org/linux-can/20261019152741.54854-6-socketcan@hartkopp.net/

Changes in v4:
- rebased on linux-can-next/testing: the context in raw_bind() changed
  with "can: raw: remove redundant NULL check before netdev_hold()",
  which made v3 fail to apply
- added "can: proc: skip stats calculation after reset in
  can_stat_update()" from linux-can-next/testing to the base sequence
- no functional change
- v3: https://lore.kernel.org/linux-can/20261019074244.50391-5-socketcan@hartkopp.net/

Changes in v3:
- not RFC anymore, sent as new series with the patches 1-3 from the
  linux-can-next pull request to build on top of mainline (see cover letter)
- commit message: describe the isotp and bcm cases separately (bcm passes
  dev_net(dev), which can_rx_unregister() reads again for its check) and
  mention that the lists of a device could be modified under the locks of
  different namespaces
- can_rx_unregister() kernel-doc: @net also selects the 'any' CAN device
  lists for @dev == NULL
- v2: https://lore.kernel.org/linux-can/20261018180739.689750-1-socketcan@hartkopp.net/

Changes in v2:
- v1 relied on the NETDEV_UNREGISTER rebroadcast in
  netdev_wait_allrefs_any() to catch a bind() racing with the notifier,
  which is not sent on a namespace change. raw_bind() and isotp_bind() now
  publish the device inside the RCU section of dev_get_by_index_rcu()
  (CAN_RAW: new ro->bind_dev hint with smp_store_release() /
  smp_load_acquire(), CAN_ISOTP: so->dev is published early and reset
  when bind() fails)
- moved the implementation details from the commit message to the notes
- shortened the code comments
- replaced the rebind rate measurement with an RTNL latency measurement
- v1: https://lore.kernel.org/linux-can/20261017201935.399233-1-socketcan@hartkopp.net/

Notes:

- bind() vs. NETDEV_UNREGISTER: Both on unregistration and on a
  namespace change, unlist_netdevice() and synchronize_net() precede
  NETDEV_UNREGISTER. bind() publishes the device (ro->bind_dev /
  so->dev) inside the RCU section of dev_get_by_index_rcu(). So either
  the notifier sees it after synchronize_net() and handles the socket
  under lock_sock(), or the lookup does not find the unlisted device and
  bind() fails with -ENODEV. The NETDEV_UNREGISTER rebroadcast in
  netdev_wait_allrefs_any() is not relied on, as it does not happen on a
  namespace change.

- raw_notify() / isotp_notify() keep a lockless READ_ONCE() fast path,
  so RTNL only waits for lock_sock() of sockets that are bound or being
  bound to the vanishing device. CAN_RAW needs the separate
  ro->bind_dev hint, as ro->dev still points to the previously bound
  device until a rebind completes. ro->bind_dev is never dereferenced;
  a stale value only causes a needless lock_sock(). raw_notify() reads
  ro->bind_dev with smp_load_acquire() before ro->dev, paired with
  smp_store_release() in raw_bind(): A later bind() can only overwrite
  ro->bind_dev after the previous bind() has set ro->dev and released
  lock_sock(). Otherwise the notifier could see a stale ro->dev and the
  ro->bind_dev of a subsequent failing rebind to another device, and
  miss the binding. CAN_ISOTP does not support rebinding and publishes
  so->dev after checking the device and resets it when the registration
  of a receiver fails. bcm_notify() always takes lock_sock() and
  bcm_rx_setup() looks up the device under lock_sock(), so bcm needs no
  extra handling.

- raw_setsockopt(): The dev->reg_state check is only a shortcut now
  (READ_ONCE()) and does not catch a namespace change. raw_notify()
  waits for lock_sock() and removes the filters set by raw_setsockopt().

- NETDEV_DOWN: raw_notify() / isotp_notify() check ro->dev / so->dev
  locklessly. They are written with WRITE_ONCE() in bind() and in the
  notifier. IFF_UP is cleared in __dev_close_many() before
  netif_close_many() or __dev_notify_flags() send NETDEV_DOWN in the
  same context, and bind() checks IFF_UP after publishing the bound
  device. With an smp_mb() on both sides, either the notifier sees the
  binding or bind() sees the cleared IFF_UP. isotp_notify() additionally
  requires so->bound, which isotp_bind() sets before its IFF_UP check, so
  a failing isotp_bind() is not reported.

- j1939 benefits as well: After a namespace change its
  can_rx_unregister() with dev_net(ndev) picked the rcvlists_lock of the
  wrong namespace. The receive list statistics may still become
  imprecise in this case, as before.

- Tested v8 on a lockdep + KASAN + failslab kernel and on a kernel
  without debug options (numbers from the debug kernel):
  - 10 min CAN_RAW / CAN_BCM / CAN_ISOTP traffic and procfs reads in two
    namespaces while moving the CAN device between them (2220 moves)
  - CAN_RAW / CAN_ISOTP bind and CAN_RAW rebind churn (incl. failing
    rebinds to a non-CAN device) against 1001 namespace moves, checking
    that no filters are left on the device in the other namespace, and
    against 609 device deletions
  - bind() vs. NETDEV_DOWN: bind() while the device is toggled down/up,
    no missed ENETDOWN in 23024 CAN_RAW and 3906 CAN_ISOTP checks
  - the same bind churn with failslab on the can_receiver cache (-ENOMEM
    in can_rx_register()): no leaks, no "receive list entry not found"
  - socket option set/get/error checks for CAN_RAW and CAN_ISOTP
  - bcm_release() with a stalled procfs reader does not block RTNL
  - RTNL latency (no-op SIOCSIFMTU on lo) under CAN_RAW 512 filter
    churn: avg ~1 us, max ~0.1 ms (before: avg ~250 us, max ~24 ms)

 include/linux/can/can-ml.h |  3 ++
 include/net/netns/can.h    |  2 +-
 net/can/af_can.c           | 39 +++++++++++------
 net/can/bcm.c              | 43 ++++++-------------
 net/can/isotp.c            | 84 ++++++++++++++++++++++--------------
 net/can/raw.c              | 88 ++++++++++++++++++++++++++++----------
 6 files changed, 159 insertions(+), 100 deletions(-)

diff --git a/include/linux/can/can-ml.h b/include/linux/can/can-ml.h
index 1e99fda2b380..cfefa4a385be 100644
--- a/include/linux/can/can-ml.h
+++ b/include/linux/can/can-ml.h
@@ -43,10 +43,11 @@
 #define CAN_ML_H
 
 #include <linux/can.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
+#include <linux/spinlock.h>
 
 /* exposed CAN device capabilities for network layer */
 #define CAN_CAP_CC BIT(0) /* CAN CC aka Classical CAN */
 #define CAN_CAP_FD BIT(1) /* CAN FD */
 #define CAN_CAP_XL BIT(2) /* CAN XL */
@@ -57,10 +58,11 @@
 #define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS)
 
 enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX };
 
 struct can_dev_rcv_lists {
+	spinlock_t lock; /* protects the receive lists and entries */
 	struct hlist_head rx[RX_MAX];
 	struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ];
 	struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ];
 	int entries;
 };
@@ -79,10 +81,11 @@ static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev)
 }
 
 static inline void can_set_ml_priv(struct net_device *dev,
 				   struct can_ml_priv *ml_priv)
 {
+	spin_lock_init(&ml_priv->dev_rcv_lists.lock);
 	netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN);
 }
 
 static inline bool can_cap_enabled(struct net_device *dev, u32 cap)
 {
diff --git a/include/net/netns/can.h b/include/net/netns/can.h
index 48b79f7e6236..54f23681e0d4 100644
--- a/include/net/netns/can.h
+++ b/include/net/netns/can.h
@@ -27,11 +27,11 @@ struct netns_can {
 	struct proc_dir_entry *bcmproc_dir;
 #endif
 
 	/* receive filters subscribed for 'all' CAN devices */
 	struct can_dev_rcv_lists *rx_alldev_list;
-	spinlock_t rcvlists_lock;
+	spinlock_t rcvlists_lock; /* protects the rcv_entries(_max) stats */
 	struct timer_list stattimer; /* timer for statistics update */
 	struct can_pkg_stats *pkg_stats;
 	struct can_rcv_lists_stats *rcv_lists_stats;
 
 	/* CAN GW per-net gateway jobs */
diff --git a/net/can/af_can.c b/net/can/af_can.c
index d97f85fc3232..0f3051a61aab 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -460,13 +460,14 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id,
 
 	rcv = kmem_cache_alloc(rcv_cache, GFP_KERNEL);
 	if (!rcv)
 		return -ENOMEM;
 
-	spin_lock_bh(&net->can.rcvlists_lock);
-
 	dev_rcv_lists = can_dev_rcv_lists_find(net, dev);
+
+	spin_lock_bh(&dev_rcv_lists->lock);
+
 	rcv_list = can_rcv_list_find(&can_id, &mask, dev_rcv_lists);
 
 	rcv->can_id = can_id;
 	rcv->mask = mask;
 	atomic_long_set(&rcv->matches, 0);
@@ -476,10 +477,13 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id,
 	rcv->sk = sk;
 
 	hlist_add_head_rcu(&rcv->list, rcv_list);
 	dev_rcv_lists->entries++;
 
+	spin_unlock_bh(&dev_rcv_lists->lock);
+
+	spin_lock_bh(&net->can.rcvlists_lock);
 	rcv_lists_stats->rcv_entries++;
 	rcv_lists_stats->rcv_entries_max = max(rcv_lists_stats->rcv_entries_max,
 					       rcv_lists_stats->rcv_entries);
 	spin_unlock_bh(&net->can.rcvlists_lock);
 
@@ -507,10 +511,18 @@ static void can_rx_delete_receiver(struct rcu_head *rp)
  * @func: callback function on filter match
  * @data: returned parameter for callback function
  *
  * Description:
  *  Removes subscription entry depending on given (subscription) values.
+ *  The receive lists of a CAN device are protected by a per-device lock,
+ *  so the subscription is found even when the device has been moved to
+ *  another network namespace after can_rx_register(). The caller has to
+ *  ensure that @dev stays valid, e.g. by holding a reference to @dev or
+ *  RTNL. @net should be the namespace that has been used for
+ *  can_rx_register(). It selects the 'any' CAN device lists for
+ *  @dev == NULL and is otherwise only used for the receive list
+ *  statistics, which become imprecise when another namespace is passed.
  */
 void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id,
 		       canid_t mask, void (*func)(struct sk_buff *, void *),
 		       void *data)
 {
@@ -520,16 +532,14 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id,
 	struct can_dev_rcv_lists *dev_rcv_lists;
 
 	if (dev && !can_get_ml_priv(dev))
 		return;
 
-	if (dev && !net_eq(net, dev_net(dev)))
-		return;
+	dev_rcv_lists = can_dev_rcv_lists_find(net, dev);
 
-	spin_lock_bh(&net->can.rcvlists_lock);
+	spin_lock_bh(&dev_rcv_lists->lock);
 
-	dev_rcv_lists = can_dev_rcv_lists_find(net, dev);
 	rcv_list = can_rcv_list_find(&can_id, &mask, dev_rcv_lists);
 
 	/* Search the receiver list for the item to delete.  This should
 	 * exist, since no receiver may be unregistered that hasn't
 	 * been registered before.
@@ -545,30 +555,30 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id,
 	 * As this case may potentially happen when closing a socket while
 	 * the notifier for removing the CAN netdev is running we just print
 	 * a warning here.
 	 */
 	if (!rcv) {
+		spin_unlock_bh(&dev_rcv_lists->lock);
 		pr_warn("can: receive list entry not found for dev %s, id %03X, mask %03X\n",
 			DNAME(dev), can_id, mask);
-		goto out;
+		return;
 	}
 
 	hlist_del_rcu(&rcv->list);
 	dev_rcv_lists->entries--;
 
+	spin_unlock_bh(&dev_rcv_lists->lock);
+
+	spin_lock_bh(&net->can.rcvlists_lock);
 	if (rcv_lists_stats->rcv_entries > 0)
 		rcv_lists_stats->rcv_entries--;
-
- out:
 	spin_unlock_bh(&net->can.rcvlists_lock);
 
 	/* schedule the receiver item for deletion */
-	if (rcv) {
-		if (rcv->sk)
-			sock_hold(rcv->sk);
-		call_rcu(&rcv->rcu, can_rx_delete_receiver);
-	}
+	if (rcv->sk)
+		sock_hold(rcv->sk);
+	call_rcu(&rcv->rcu, can_rx_delete_receiver);
 }
 EXPORT_SYMBOL(can_rx_unregister);
 
 static inline void deliver(struct sk_buff *skb, struct receiver *rcv)
 {
@@ -821,10 +831,11 @@ static int can_pernet_init(struct net *net)
 {
 	spin_lock_init(&net->can.rcvlists_lock);
 	net->can.rx_alldev_list = kzalloc_obj(*net->can.rx_alldev_list);
 	if (!net->can.rx_alldev_list)
 		goto out;
+	spin_lock_init(&net->can.rx_alldev_list->lock);
 	net->can.pkg_stats = kzalloc_obj(*net->can.pkg_stats);
 	if (!net->can.pkg_stats)
 		goto out_free_rx_alldev_list;
 	net->can.rcv_lists_stats = kzalloc_obj(*net->can.rcv_lists_stats);
 	if (!net->can.rcv_lists_stats)
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 6759662e024c..7bd2aa39777a 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -960,11 +960,11 @@ static void bcm_remove_op(struct bcm_op *op)
 }
 
 static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
 {
 	if (op->rx_reg_dev == dev) {
-		can_rx_unregister(dev_net(dev), dev, op->can_id,
+		can_rx_unregister(sock_net(op->sk), dev, op->can_id,
 				  REGMASK(op->can_id), bcm_rx_handler, op);
 
 		/* mark as removed subscription */
 		op->rx_reg_dev = NULL;
 		netdev_put(dev, &op->rx_reg_dev_tracker);
@@ -986,25 +986,14 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
 		    (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
 
 			/* disable automatic timer on frame reception */
 			op->flags |= RX_NO_AUTOTIMER;
 
-			/*
-			 * Don't care if we're bound or not (due to netdev
-			 * problems) can_rx_unregister() is always a save
-			 * thing to do here.
-			 */
 			if (op->ifindex) {
-				/*
-				 * Only remove subscriptions that had not
-				 * been removed due to NETDEV_UNREGISTER
-				 * in bcm_notifier()
-				 *
-				 * op->rx_reg_dev is a tracked reference taken
-				 * when the subscription was registered, so it
-				 * stays valid here even if a concurrent
-				 * NETDEV_UNREGISTER already unlisted the dev.
+				/* Only remove subscriptions that had not been
+				 * removed in bcm_notify(). op->rx_reg_dev keeps
+				 * the device's receive lists accessible.
 				 */
 				if (op->rx_reg_dev)
 					bcm_rx_unreg(op->rx_reg_dev, op);
 			} else
 				can_rx_unregister(sock_net(op->sk), NULL,
@@ -1933,10 +1922,11 @@ static int bcm_release(struct socket *sock)
 		spin_lock(&bcm_notifier_lock);
 	}
 	list_del(&bo->notifier);
 	spin_unlock(&bcm_notifier_lock);
 
+	/* bcm_notify() can not access this socket anymore */
 	lock_sock(sk);
 
 #if IS_ENABLED(CONFIG_PROC_FS)
 	/* remove procfs entry */
 	if (net->can.bcmproc_dir && bo->bcm_proc_read)
@@ -1946,33 +1936,24 @@ static int bcm_release(struct socket *sock)
 	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.
-		 */
+	list_for_each_entry(op, &bo->rx_ops, list) {
 		if (op->ifindex) {
-			/*
-			 * Only remove subscriptions that had not
-			 * been removed due to NETDEV_UNREGISTER
-			 * in bcm_notifier()
-			 *
-			 * op->rx_reg_dev is a tracked reference taken
-			 * when the subscription was registered, so it
-			 * stays valid here even if a concurrent
-			 * NETDEV_UNREGISTER already unlisted the device.
+			/* Only remove subscriptions that had not been removed
+			 * in bcm_notify(). op->rx_reg_dev keeps the device's
+			 * receive lists accessible.
 			 */
 			if (op->rx_reg_dev)
 				bcm_rx_unreg(op->rx_reg_dev, op);
-		} else
+		} else {
 			can_rx_unregister(net, NULL, op->can_id,
 					  REGMASK(op->can_id),
 					  bcm_rx_handler, op);
-
+		}
+		cond_resched();
 	}
 
 	synchronize_rcu();
 
 	list_for_each_entry_safe(op, next, &bo->rx_ops, list) {
diff --git a/net/can/isotp.c b/net/can/isotp.c
index da80ef606ce0..649a3446c4f1 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1122,11 +1122,11 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	u32 my_gen;
 	u32 old_cfecho;
 	int off;
 	int err;
 
-	if (!so->bound || READ_ONCE(so->tx.state) == ISOTP_SHUTDOWN)
+	if (!READ_ONCE(so->bound) || READ_ONCE(so->tx.state) == ISOTP_SHUTDOWN)
 		return -EADDRNOTAVAIL;
 
 	/* claim the socket under so->rx_lock: this serializes the claim
 	 * with the RX path and with sendmsg()'s own error paths below, so
 	 * none of them can ever see a transfer mid-claim
@@ -1167,11 +1167,11 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	spin_unlock_bh(&so->rx_lock);
 
 	/* so->bound is only checked once above - a wakeup may have
 	 * unbound/rebound the socket meanwhile => recheck
 	 */
-	if (!so->bound) {
+	if (!READ_ONCE(so->bound)) {
 		err = -EADDRNOTAVAIL;
 		goto err_out_drop;
 	}
 
 	/* PDU size > default => try max_pdu_size */
@@ -1413,11 +1413,11 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	int ret = 0;
 
 	if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK | MSG_CMSG_COMPAT))
 		return -EINVAL;
 
-	if (!so->bound)
+	if (!READ_ONCE(so->bound))
 		return -EADDRNOTAVAIL;
 
 	skb = skb_recv_datagram(sk, flags, &ret);
 	if (!skb)
 		return ret;
@@ -1487,15 +1487,15 @@ static int isotp_release(struct socket *sock)
 		spin_lock(&isotp_notifier_lock);
 	}
 	list_del(&so->notifier);
 	spin_unlock(&isotp_notifier_lock);
 
-	rtnl_lock();
 	lock_sock(sk);
 
 	/* remove current filters & unregister
-	 * tracked reference so->dev is taken at bind() time with rtnl_lock
+	 * the tracked reference so->dev keeps the device's receive lists
+	 * accessible, even after a namespace change
 	 */
 	if (so->bound && so->dev) {
 		if (isotp_register_rxid(so))
 			can_rx_unregister(net, so->dev, so->rxid,
 					  SINGLE_MASK(so->rxid),
@@ -1506,15 +1506,13 @@ static int isotp_release(struct socket *sock)
 				  isotp_rcv_echo, sk);
 		netdev_put(so->dev, &so->dev_tracker);
 	}
 
 	so->ifindex = 0;
-	so->bound = 0;
+	WRITE_ONCE(so->bound, 0);
 	so->dev = NULL;
 
-	rtnl_unlock();
-
 	/* Always wait for a grace period before touching the timers below.
 	 * A concurrent NETDEV_UNREGISTER may have already unregistered our
 	 * filters and cleared so->bound in isotp_notify() without waiting
 	 * for in-flight isotp_rcv() callers to finish, so this call must not
 	 * be skipped just because so->bound is already 0 here.
@@ -1578,11 +1576,11 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 	}
 
 	if (!addr->can_ifindex)
 		return -ENODEV;
 
-	rtnl_lock();
+	/* lock_sock() serializes the binding with isotp_notify() */
 	lock_sock(sk);
 
 	if (so->bound) {
 		err = -EINVAL;
 		goto out;
@@ -1604,25 +1602,28 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 	if (isotp_register_rxid(so) && rx_id == tx_id) {
 		err = -EADDRNOTAVAIL;
 		goto out;
 	}
 
-	dev = dev_get_by_index(net, addr->can_ifindex);
-	if (!dev) {
-		err = -ENODEV;
-		goto out;
-	}
-	if (!can_get_ml_priv(dev)) {
+	/* Publish the device inside the RCU section of the lookup: When it
+	 * is unlisted concurrently, either isotp_notify() sees so->dev after
+	 * synchronize_net() or the lookup fails. Check the device before
+	 * publishing it.
+	 */
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(net, addr->can_ifindex);
+	if (!dev || !can_get_ml_priv(dev))
 		err = -ENODEV;
-		goto out_put_dev;
-	}
-	if (READ_ONCE(dev->mtu) < so->ll.mtu) {
+	else if (READ_ONCE(dev->mtu) < so->ll.mtu)
 		err = -EINVAL;
-		goto out_put_dev;
+	if (!err) {
+		dev_hold(dev);
+		WRITE_ONCE(so->dev, dev);
 	}
-	if (!(dev->flags & IFF_UP))
-		notify_enetdown = 1;
+	rcu_read_unlock();
+	if (err)
+		goto out;
 
 	ifindex = dev->ifindex;
 
 	if (isotp_register_rxid(so)) {
 		err = can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id),
@@ -1646,32 +1647,41 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 
 	/* switch to new settings */
 	so->ifindex = ifindex;
 	so->rxid = rx_id;
 	so->txid = tx_id;
-	so->bound = 1;
+	WRITE_ONCE(so->bound, 1);
 
 	/* bind() ok -> hold a reference for so->dev so that isotp_release()
 	 * can safely reach the device later, even if a concurrent
 	 * NETDEV_UNREGISTER has already unlisted it by ifindex.
 	 */
-	so->dev = dev;
 	netdev_hold(so->dev, &so->dev_tracker, GFP_KERNEL);
 
+	/* Either isotp_notify() sees so->dev on NETDEV_DOWN or we see the
+	 * cleared IFF_UP, pairs with isotp_notify()
+	 */
+	smp_mb();
+	if (!(READ_ONCE(dev->flags) & IFF_UP))
+		notify_enetdown = 1;
+
 out_put_dev:
-	/* remove potential reference from dev_get_by_index() */
+	/* the published so->dev is only valid for a successful bind() */
+	if (err)
+		WRITE_ONCE(so->dev, NULL);
+
+	/* remove reference from the device lookup */
 	dev_put(dev);
 out:
-	release_sock(sk);
-	rtnl_unlock();
-
 	if (notify_enetdown) {
 		sk->sk_err = ENETDOWN;
 		if (!sock_flag(sk, SOCK_DEAD))
 			sk_error_report(sk);
 	}
 
+	release_sock(sk);
+
 	return err;
 }
 
 static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 {
@@ -1863,16 +1873,25 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg,
 	struct sock *sk = &so->sk;
 
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		return;
 
-	if (so->dev != dev)
+	if (msg == NETDEV_DOWN)
+		smp_mb(); /* pairs with isotp_bind(), see raw_notify() */
+
+	/* lockless fast path, see raw_notify() */
+	if (READ_ONCE(so->dev) != dev)
 		return;
 
 	switch (msg) {
 	case NETDEV_UNREGISTER:
 		lock_sock(sk);
+		if (so->dev != dev) {
+			release_sock(sk);
+			break;
+		}
+
 		/* remove current filters & unregister */
 		if (so->bound) {
 			if (isotp_register_rxid(so))
 				can_rx_unregister(dev_net(dev), dev, so->rxid,
 						  SINGLE_MASK(so->rxid),
@@ -1883,20 +1902,23 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg,
 					  isotp_rcv_echo, sk);
 			netdev_put(so->dev, &so->dev_tracker);
 		}
 
 		so->ifindex = 0;
-		so->bound  = 0;
-		so->dev = NULL;
-		release_sock(sk);
+		WRITE_ONCE(so->bound, 0);
+		WRITE_ONCE(so->dev, NULL);
 
 		sk->sk_err = ENODEV;
 		if (!sock_flag(sk, SOCK_DEAD))
 			sk_error_report(sk);
+		release_sock(sk);
 		break;
 
 	case NETDEV_DOWN:
+		if (!READ_ONCE(so->bound))
+			break;
+
 		sk->sk_err = ENETDOWN;
 		if (!sock_flag(sk, SOCK_DEAD))
 			sk_error_report(sk);
 		break;
 	}
diff --git a/net/can/raw.c b/net/can/raw.c
index dfea48768b23..0267b4300c24 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -83,10 +83,11 @@ struct uniqframe {
 
 struct raw_sock {
 	struct sock sk;
 	struct net_device *dev;
 	netdevice_tracker dev_tracker;
+	struct net_device *bind_dev; /* hint for raw_notify(), no reference */
 	struct list_head notifier;
 	int ifindex;
 	unsigned int bound:1;
 	unsigned int loopback:1;
 	unsigned int recv_own_msgs:1;
@@ -222,10 +223,11 @@ static int raw_enable_filters(struct net *net, struct net_device *dev,
 {
 	int err = 0;
 	int i;
 
 	for (i = 0; i < count; i++) {
+		cond_resched();
 		err = can_rx_register(net, dev, filter[i].can_id,
 				      filter[i].can_mask,
 				      raw_rcv, sk, sock_i_ino(sk), sk);
 		if (err) {
 			/* clean up successfully registered filters */
@@ -256,13 +258,15 @@ static void raw_disable_filters(struct net *net, struct net_device *dev,
 				struct sock *sk, struct can_filter *filter,
 				int count)
 {
 	int i;
 
-	for (i = 0; i < count; i++)
+	for (i = 0; i < count; i++) {
 		can_rx_unregister(net, dev, filter[i].can_id,
 				  filter[i].can_mask, raw_rcv, sk);
+		cond_resched();
+	}
 }
 
 static inline void raw_disable_errfilter(struct net *net,
 					 struct net_device *dev,
 					 struct sock *sk,
@@ -303,20 +307,35 @@ static int raw_enable_allfilters(struct net *net, struct net_device *dev,
 
 static void raw_notify(struct raw_sock *ro, unsigned long msg,
 		       struct net_device *dev)
 {
 	struct sock *sk = &ro->sk;
+	struct net_device *bind_dev;
 
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		return;
 
-	if (ro->dev != dev)
+	if (msg == NETDEV_DOWN)
+		smp_mb(); /* IFF_UP is cleared before, pairs with raw_bind() */
+
+	/* Lockless fast path, ro->bind_dev covers a concurrent bind().
+	 * Read it before ro->dev, pairs with smp_store_release() in
+	 * raw_bind(). A stale ro->bind_dev only costs a lock_sock().
+	 */
+	bind_dev = smp_load_acquire(&ro->bind_dev);
+	if (READ_ONCE(ro->dev) != dev &&
+	    (msg != NETDEV_UNREGISTER || bind_dev != dev))
 		return;
 
 	switch (msg) {
 	case NETDEV_UNREGISTER:
 		lock_sock(sk);
+		if (ro->dev != dev) {
+			release_sock(sk);
+			break;
+		}
+
 		/* remove current filters & unregister */
 		if (ro->bound) {
 			raw_disable_allfilters(dev_net(dev), dev, sk);
 			netdev_put(dev, &ro->dev_tracker);
 		}
@@ -324,17 +343,17 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg,
 		if (ro->count > 1)
 			kfree(ro->filter);
 
 		ro->ifindex = 0;
 		ro->bound = 0;
-		ro->dev = NULL;
+		WRITE_ONCE(ro->dev, NULL);
 		ro->count = 0;
-		release_sock(sk);
 
 		sk->sk_err = ENODEV;
 		if (!sock_flag(sk, SOCK_DEAD))
 			sk_error_report(sk);
+		release_sock(sk);
 		break;
 
 	case NETDEV_DOWN:
 		sk->sk_err = ENETDOWN;
 		if (!sock_flag(sk, SOCK_DEAD))
@@ -379,10 +398,11 @@ static int raw_init(struct sock *sk)
 	struct raw_sock *ro = raw_sk(sk);
 
 	ro->bound            = 0;
 	ro->ifindex          = 0;
 	ro->dev              = NULL;
+	ro->bind_dev         = NULL;
 
 	/* set default filter to single entry dfilter */
 	ro->dfilter.can_id   = 0;
 	ro->dfilter.can_mask = MASK_ALL;
 	ro->filter           = &ro->dfilter;
@@ -429,17 +449,19 @@ static int raw_release(struct socket *sock)
 		spin_lock(&raw_notifier_lock);
 	}
 	list_del(&ro->notifier);
 	spin_unlock(&raw_notifier_lock);
 
-	rtnl_lock();
 	lock_sock(sk);
 
-	/* remove current filters & unregister */
+	/* remove current filters & unregister
+	 * the tracked reference ro->dev keeps the device's receive lists
+	 * accessible, even after a namespace change
+	 */
 	if (ro->bound) {
 		if (ro->dev) {
-			raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk);
+			raw_disable_allfilters(net, ro->dev, sk);
 			netdev_put(ro->dev, &ro->dev_tracker);
 		} else {
 			raw_disable_allfilters(net, NULL, sk);
 		}
 	}
@@ -454,11 +476,10 @@ static int raw_release(struct socket *sock)
 
 	sock_orphan(sk);
 	sock->sk = NULL;
 
 	release_sock(sk);
-	rtnl_unlock();
 
 	sock_prot_inuse_add(net, sk->sk_prot, -1);
 	sock_put(sk);
 
 	return 0;
@@ -477,30 +498,38 @@ static int raw_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int len
 	if (len < RAW_MIN_NAMELEN)
 		return -EINVAL;
 	if (addr->can_family != AF_CAN)
 		return -EINVAL;
 
-	rtnl_lock();
+	/* lock_sock() serializes the binding with raw_notify() */
 	lock_sock(sk);
 
 	if (ro->bound && addr->can_ifindex == ro->ifindex)
 		goto out;
 
 	if (addr->can_ifindex) {
-		dev = dev_get_by_index(sock_net(sk), addr->can_ifindex);
+		/* Publish the device inside the RCU section of the lookup:
+		 * When it is unlisted concurrently, either raw_notify() sees
+		 * ro->bind_dev after synchronize_net() or the lookup fails.
+		 */
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(sock_net(sk), addr->can_ifindex);
+		if (dev) {
+			dev_hold(dev);
+			/* pairs with smp_load_acquire() in raw_notify() */
+			smp_store_release(&ro->bind_dev, dev);
+		}
+		rcu_read_unlock();
 		if (!dev) {
 			err = -ENODEV;
 			goto out;
 		}
 		if (!can_get_ml_priv(dev)) {
 			err = -ENODEV;
 			goto out_put_dev;
 		}
 
-		if (!(dev->flags & IFF_UP))
-			notify_enetdown = 1;
-
 		ifindex = dev->ifindex;
 
 		/* filters set by default/setsockopt */
 		err = raw_enable_allfilters(sock_net(sk), dev, sk);
 		if (err)
@@ -515,38 +544,46 @@ static int raw_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int len
 
 	if (!err) {
 		if (ro->bound) {
 			/* unregister old filters */
 			if (ro->dev) {
-				raw_disable_allfilters(dev_net(ro->dev),
+				raw_disable_allfilters(sock_net(sk),
 						       ro->dev, sk);
 				/* drop reference to old ro->dev */
 				netdev_put(ro->dev, &ro->dev_tracker);
 			} 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;
+		WRITE_ONCE(ro->dev, dev);
 		netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL);
+
+		if (dev) {
+			/* Either raw_notify() sees ro->dev on NETDEV_DOWN or
+			 * we see the cleared IFF_UP, pairs with raw_notify()
+			 */
+			smp_mb();
+			if (!(READ_ONCE(dev->flags) & IFF_UP))
+				notify_enetdown = 1;
+		}
 	}
 
 out_put_dev:
-	/* remove potential reference from dev_get_by_index() */
+	/* remove reference from the device lookup */
 	dev_put(dev);
 out:
-	release_sock(sk);
-	rtnl_unlock();
-
 	if (notify_enetdown) {
 		sk->sk_err = ENETDOWN;
 		if (!sock_flag(sk, SOCK_DEAD))
 			sk_error_report(sk);
 	}
 
+	release_sock(sk);
+
 	return err;
 }
 
 static int raw_getname(struct socket *sock, struct sockaddr *uaddr,
 		       int peer)
@@ -596,12 +633,17 @@ static int raw_setsockopt_locked(struct socket *sock, int optname,
 		} else if (count == 1) {
 			if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter)))
 				return -EFAULT;
 		}
 
+		/* The reg_state check is only a shortcut: On a concurrent
+		 * unregistration or namespace change raw_notify() waits for
+		 * lock_sock() and removes the filters set here.
+		 */
 		dev = ro->dev;
-		if (ro->bound && dev && dev->reg_state != NETREG_REGISTERED) {
+		if (ro->bound && dev &&
+		    READ_ONCE(dev->reg_state) != NETREG_REGISTERED) {
 			if (count > 1)
 				kfree(filter);
 			return -ENODEV;
 		}
 
@@ -645,12 +687,14 @@ static int raw_setsockopt_locked(struct socket *sock, int optname,
 		if (copy_from_sockptr(&err_mask, optval, optlen))
 			return -EFAULT;
 
 		err_mask &= CAN_ERR_MASK;
 
+		/* lockless shortcut, see CAN_RAW_FILTER */
 		dev = ro->dev;
-		if (ro->bound && dev && dev->reg_state != NETREG_REGISTERED)
+		if (ro->bound && dev &&
+		    READ_ONCE(dev->reg_state) != NETREG_REGISTERED)
 			return -ENODEV;
 
 		/* remove current error mask */
 		if (ro->bound) {
 			/* (try to) register the new err_mask */
@@ -753,17 +797,15 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 	int err;
 
 	if (level != SOL_CAN_RAW)
 		return -EINVAL;
 
-	rtnl_lock();
 	lock_sock(sk);
 
 	err = raw_setsockopt_locked(sock, optname, optval, optlen);
 
 	release_sock(sk);
-	rtnl_unlock();
 
 	return err;
 }
 
 static int raw_getsockopt(struct socket *sock, int level, int optname,
-- 
2.43.0

[PATCH v8 7/7] can: raw, isotp: copy socket options outside of lock_sock()

[Oliver Hartkopp]

The CAN_RAW and CAN_ISOTP specific socket options are copied from and
to user space while holding lock_sock(). A copy that faults or stalls,
e.g. on a userfaultfd or FUSE backed mapping, holds lock_sock() for its
whole duration.

Since CAN_RAW and CAN_ISOTP do not take RTNL in bind() anymore,
raw_notify() and isotp_notify() wait for lock_sock() of a socket that
is bound to the vanishing device while holding RTNL. As the CAN_RAW
options can be changed on a bound socket, such a stalled copy can block
RTNL on an unregistration or namespace change of the bound device.
CAN_ISOTP only copies its options for unbound sockets, which
isotp_notify() skips without taking lock_sock().

Keep the user space copies out of the locked sections: Check the option
name and length and copy the option values, including the CAN_RAW_FILTER
filters, to kernel memory before lock_sock(). raw_setsockopt_locked()
and isotp_setsockopt_locked() get the copied values directly and drop
their now redundant length checks and copies. As a side effect, a
failing copy can not leave partially overwritten options behind
anymore. In raw_getsockopt() duplicate the filters under lock_sock() and
copy them to user space after release_sock().

As the option name and length are now checked before lock_sock(), the
order of the checks in isotp_setsockopt() and accordingly the order of
the returned error values changes. This is in line with POSIX, which
does not define an order in which multiple error conditions are
detected and reported.

The generic SOL_SOCKET options in sk_setsockopt() are not affected by
this patch.

Fixes: ee8b94c8510c ("can: raw: fix receiver memory leak")
Cc: stable@vger.kernel.org # depends on "can: protect the receive lists with a per-device lock"
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
 net/can/isotp.c | 100 +++++++++++++++-----------
 net/can/raw.c   | 186 +++++++++++++++++++++++++-----------------------
 2 files changed, 155 insertions(+), 131 deletions(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index 649a3446c4f1..ad4996f29007 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1699,27 +1699,23 @@ static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 	addr->can_addr.tp.tx_id = so->txid;
 
 	return ISOTP_MIN_NAMELEN;
 }
 
-static int isotp_setsockopt_locked(struct socket *sock, int level, int optname,
-			    sockptr_t optval, unsigned int optlen)
+static int isotp_setsockopt_locked(struct socket *sock, int optname,
+				   const void *val)
 {
 	struct sock *sk = sock->sk;
 	struct isotp_sock *so = isotp_sk(sk);
 	int ret = 0;
 
 	if (so->bound)
 		return -EISCONN;
 
 	switch (optname) {
 	case CAN_ISOTP_OPTS:
-		if (optlen != sizeof(struct can_isotp_options))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&so->opt, optval, optlen))
-			return -EFAULT;
+		memcpy(&so->opt, val, sizeof(so->opt));
 
 		/* no separate rx_ext_address is given => use ext_address */
 		if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR))
 			so->opt.rx_ext_address = so->opt.ext_address;
 
@@ -1740,59 +1736,41 @@ static int isotp_setsockopt_locked(struct socket *sock, int level, int optname,
 				so->frame_txtime = so->opt.frame_txtime;
 		}
 		break;
 
 	case CAN_ISOTP_RECV_FC:
-		if (optlen != sizeof(struct can_isotp_fc_options))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&so->rxfc, optval, optlen))
-			return -EFAULT;
+		memcpy(&so->rxfc, val, sizeof(so->rxfc));
 		break;
 
 	case CAN_ISOTP_TX_STMIN:
-		if (optlen != sizeof(u32))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&so->force_tx_stmin, optval, optlen))
-			return -EFAULT;
+		so->force_tx_stmin = *(const u32 *)val;
 		break;
 
 	case CAN_ISOTP_RX_STMIN:
-		if (optlen != sizeof(u32))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&so->force_rx_stmin, optval, optlen))
-			return -EFAULT;
+		so->force_rx_stmin = *(const u32 *)val;
 		break;
 
-	case CAN_ISOTP_LL_OPTS:
-		if (optlen == sizeof(struct can_isotp_ll_options)) {
-			struct can_isotp_ll_options ll;
-
-			if (copy_from_sockptr(&ll, optval, optlen))
-				return -EFAULT;
+	case CAN_ISOTP_LL_OPTS: {
+		const struct can_isotp_ll_options *ll = val;
 
-			/* check for correct ISO 11898-1 DLC data length */
-			if (ll.tx_dl != padlen(ll.tx_dl))
-				return -EINVAL;
+		/* check for correct ISO 11898-1 DLC data length */
+		if (ll->tx_dl != padlen(ll->tx_dl))
+			return -EINVAL;
 
-			if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU)
-				return -EINVAL;
+		if (ll->mtu != CAN_MTU && ll->mtu != CANFD_MTU)
+			return -EINVAL;
 
-			if (ll.mtu == CAN_MTU &&
-			    (ll.tx_dl > CAN_MAX_DLEN || ll.tx_flags != 0))
-				return -EINVAL;
+		if (ll->mtu == CAN_MTU &&
+		    (ll->tx_dl > CAN_MAX_DLEN || ll->tx_flags != 0))
+			return -EINVAL;
 
-			memcpy(&so->ll, &ll, sizeof(ll));
+		memcpy(&so->ll, ll, sizeof(*ll));
 
-			/* set ll_dl for tx path to similar place as for rx */
-			so->tx.ll_dl = ll.tx_dl;
-		} else {
-			return -EINVAL;
-		}
+		/* set ll_dl for tx path to similar place as for rx */
+		so->tx.ll_dl = ll->tx_dl;
 		break;
+	}
 
 	default:
 		ret = -ENOPROTOOPT;
 	}
 
@@ -1802,17 +1780,53 @@ static int isotp_setsockopt_locked(struct socket *sock, int level, int optname,
 static int isotp_setsockopt(struct socket *sock, int level, int optname,
 			    sockptr_t optval, unsigned int optlen)
 
 {
 	struct sock *sk = sock->sk;
+	union {
+		struct can_isotp_options opt;
+		struct can_isotp_fc_options rxfc;
+		struct can_isotp_ll_options ll;
+		u32 stmin;
+	} val;
+	unsigned int size;
 	int ret;
 
 	if (level != SOL_CAN_ISOTP)
 		return -EINVAL;
 
+	/* copy the option values from user space before lock_sock() */
+	switch (optname) {
+	case CAN_ISOTP_OPTS:
+		size = sizeof(val.opt);
+		break;
+
+	case CAN_ISOTP_RECV_FC:
+		size = sizeof(val.rxfc);
+		break;
+
+	case CAN_ISOTP_TX_STMIN:
+	case CAN_ISOTP_RX_STMIN:
+		size = sizeof(val.stmin);
+		break;
+
+	case CAN_ISOTP_LL_OPTS:
+		size = sizeof(val.ll);
+		break;
+
+	default:
+		return -ENOPROTOOPT;
+	}
+
+	if (optlen != size)
+		return -EINVAL;
+
+	if (copy_from_sockptr(&val, optval, size))
+		return -EFAULT;
+
 	lock_sock(sk);
-	ret = isotp_setsockopt_locked(sock, level, optname, optval, optlen);
+	ret = isotp_setsockopt_locked(sock, optname, &val);
 	release_sock(sk);
 	return ret;
 }
 
 static int isotp_getsockopt(struct socket *sock, int level, int optname,
diff --git a/net/can/raw.c b/net/can/raw.c
index 0267b4300c24..66e41bf9db3e 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -601,67 +601,40 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr,
 
 	return RAW_MIN_NAMELEN;
 }
 
 static int raw_setsockopt_locked(struct socket *sock, int optname,
-				 sockptr_t optval, unsigned int optlen)
+				 const void *val, struct can_filter *filter,
+				 int count)
 {
 	struct sock *sk = sock->sk;
 	struct raw_sock *ro = raw_sk(sk);
-	struct can_filter *filter = NULL;  /* dyn. alloc'ed filters */
-	struct can_filter sfilter;         /* single filter */
 	struct net_device *dev = NULL;
-	can_err_mask_t err_mask = 0;
-	int count = 0;
+	can_err_mask_t err_mask;
 	int flag;
 	int err = 0;
 
 	switch (optname) {
 	case CAN_RAW_FILTER:
-		if (optlen % sizeof(struct can_filter) != 0)
-			return -EINVAL;
-
-		if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter))
-			return -EINVAL;
-
-		count = optlen / sizeof(struct can_filter);
-
-		if (count > 1) {
-			/* filter does not fit into dfilter => alloc space */
-			filter = memdup_sockptr(optval, optlen);
-			if (IS_ERR(filter))
-				return PTR_ERR(filter);
-		} else if (count == 1) {
-			if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter)))
-				return -EFAULT;
-		}
-
-		/* The reg_state check is only a shortcut: On a concurrent
+		/* @filter has been copied by raw_setsockopt(). It is linked
+		 * to the socket on success and freed by the caller on error.
+		 *
+		 * The reg_state check is only a shortcut: On a concurrent
 		 * unregistration or namespace change raw_notify() waits for
 		 * lock_sock() and removes the filters set here.
 		 */
 		dev = ro->dev;
 		if (ro->bound && dev &&
-		    READ_ONCE(dev->reg_state) != NETREG_REGISTERED) {
-			if (count > 1)
-				kfree(filter);
+		    READ_ONCE(dev->reg_state) != NETREG_REGISTERED)
 			return -ENODEV;
-		}
 
 		if (ro->bound) {
 			/* (try to) register the new filters */
-			if (count == 1)
-				err = raw_enable_filters(sock_net(sk), dev, sk,
-							 &sfilter, 1);
-			else
-				err = raw_enable_filters(sock_net(sk), dev, sk,
-							 filter, count);
-			if (err) {
-				if (count > 1)
-					kfree(filter);
+			err = raw_enable_filters(sock_net(sk), dev, sk, filter,
+						 count);
+			if (err)
 				return err;
-			}
 
 			/* remove old filter registrations */
 			raw_disable_filters(sock_net(sk), dev, sk, ro->filter,
 					    ro->count);
 		}
@@ -671,25 +644,19 @@ static int raw_setsockopt_locked(struct socket *sock, int optname,
 			kfree(ro->filter);
 
 		/* link new filters to the socket */
 		if (count == 1) {
 			/* copy filter data for single filter */
-			ro->dfilter = sfilter;
+			ro->dfilter = *filter;
 			filter = &ro->dfilter;
 		}
 		ro->filter = filter;
 		ro->count  = count;
 		break;
 
 	case CAN_RAW_ERR_FILTER:
-		if (optlen != sizeof(err_mask))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&err_mask, optval, optlen))
-			return -EFAULT;
-
-		err_mask &= CAN_ERR_MASK;
+		err_mask = *(const can_err_mask_t *)val & CAN_ERR_MASK;
 
 		/* lockless shortcut, see CAN_RAW_FILTER */
 		dev = ro->dev;
 		if (ro->bound && dev &&
 		    READ_ONCE(dev->reg_state) != NETREG_REGISTERED)
@@ -712,78 +679,46 @@ static int raw_setsockopt_locked(struct socket *sock, int optname,
 		/* link new err_mask to the socket */
 		ro->err_mask = err_mask;
 		break;
 
 	case CAN_RAW_LOOPBACK:
-		if (optlen != sizeof(flag))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&flag, optval, optlen))
-			return -EFAULT;
-
-		ro->loopback = !!flag;
+		ro->loopback = !!*(const int *)val;
 		break;
 
 	case CAN_RAW_RECV_OWN_MSGS:
-		if (optlen != sizeof(flag))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&flag, optval, optlen))
-			return -EFAULT;
-
-		ro->recv_own_msgs = !!flag;
+		ro->recv_own_msgs = !!*(const int *)val;
 		break;
 
 	case CAN_RAW_FD_FRAMES:
-		if (optlen != sizeof(flag))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&flag, optval, optlen))
-			return -EFAULT;
+		flag = *(const int *)val;
 
 		/* Enabling CAN XL includes CAN FD */
 		if (ro->xl_frames && !flag)
 			return -EINVAL;
 
 		ro->fd_frames = !!flag;
 		break;
 
 	case CAN_RAW_XL_FRAMES:
-		if (optlen != sizeof(flag))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&flag, optval, optlen))
-			return -EFAULT;
-
-		ro->xl_frames = !!flag;
+		ro->xl_frames = !!*(const int *)val;
 
 		/* Enabling CAN XL includes CAN FD */
 		if (ro->xl_frames)
 			ro->fd_frames = ro->xl_frames;
 		break;
 
 	case CAN_RAW_XL_VCID_OPTS:
-		if (optlen != sizeof(ro->raw_vcid_opts))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&ro->raw_vcid_opts, optval, optlen))
-			return -EFAULT;
+		memcpy(&ro->raw_vcid_opts, val, sizeof(ro->raw_vcid_opts));
 
 		/* prepare 32 bit values for handling in hot path */
 		ro->tx_vcid_shifted = ro->raw_vcid_opts.tx_vcid << CANXL_VCID_OFFSET;
 		ro->rx_vcid_shifted = ro->raw_vcid_opts.rx_vcid << CANXL_VCID_OFFSET;
 		ro->rx_vcid_mask_shifted = ro->raw_vcid_opts.rx_vcid_mask << CANXL_VCID_OFFSET;
 		break;
 
 	case CAN_RAW_JOIN_FILTERS:
-		if (optlen != sizeof(flag))
-			return -EINVAL;
-
-		if (copy_from_sockptr(&flag, optval, optlen))
-			return -EFAULT;
-
-		ro->join_filters = !!flag;
+		ro->join_filters = !!*(const int *)val;
 		break;
 
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -792,21 +727,88 @@ static int raw_setsockopt_locked(struct socket *sock, int optname,
 
 static int raw_setsockopt(struct socket *sock, int level, int optname,
 			  sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
+	struct can_filter *filter = NULL;  /* dyn. alloc'ed filters */
+	struct can_filter sfilter;         /* single filter */
+	union {
+		can_err_mask_t err_mask;
+		int flag;
+		struct can_raw_vcid_options vcid_opts;
+	} val;
+	unsigned int size = 0;
+	int count = 0;
 	int err;
 
 	if (level != SOL_CAN_RAW)
 		return -EINVAL;
 
+	/* Copy the option values from user space before lock_sock(), so a
+	 * stalled copy can not block raw_notify() waiting for lock_sock()
+	 * under RTNL.
+	 */
+	switch (optname) {
+	case CAN_RAW_FILTER:
+		if (optlen % sizeof(struct can_filter) != 0)
+			return -EINVAL;
+
+		if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter))
+			return -EINVAL;
+
+		count = optlen / sizeof(struct can_filter);
+
+		if (count > 1) {
+			/* filter does not fit into dfilter => alloc space */
+			filter = memdup_sockptr(optval, optlen);
+			if (IS_ERR(filter))
+				return PTR_ERR(filter);
+		} else if (count == 1) {
+			if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter)))
+				return -EFAULT;
+			filter = &sfilter;
+		}
+		break;
+
+	case CAN_RAW_ERR_FILTER:
+		size = sizeof(val.err_mask);
+		break;
+
+	case CAN_RAW_XL_VCID_OPTS:
+		size = sizeof(val.vcid_opts);
+		break;
+
+	case CAN_RAW_LOOPBACK:
+	case CAN_RAW_RECV_OWN_MSGS:
+	case CAN_RAW_FD_FRAMES:
+	case CAN_RAW_XL_FRAMES:
+	case CAN_RAW_JOIN_FILTERS:
+		size = sizeof(val.flag);
+		break;
+
+	default:
+		return -ENOPROTOOPT;
+	}
+
+	if (size) {
+		if (optlen != size)
+			return -EINVAL;
+
+		if (copy_from_sockptr(&val, optval, size))
+			return -EFAULT;
+	}
+
 	lock_sock(sk);
 
-	err = raw_setsockopt_locked(sock, optname, optval, optlen);
+	err = raw_setsockopt_locked(sock, optname, &val, filter, count);
 
 	release_sock(sk);
 
+	/* on error free the filters allocated for CAN_RAW_FILTER above */
+	if (err && count > 1)
+		kfree(filter);
+
 	return err;
 }
 
 static int raw_getsockopt(struct socket *sock, int level, int optname,
 			  sockopt_t *opt)
@@ -823,10 +825,11 @@ static int raw_getsockopt(struct socket *sock, int level, int optname,
 	if (len < 0)
 		return -EINVAL;
 
 	switch (optname) {
 	case CAN_RAW_FILTER: {
+		struct can_filter *filter = NULL;
 		int err = 0;
 
 		lock_sock(sk);
 		if (ro->count > 0) {
 			int fsize = ro->count * sizeof(struct can_filter);
@@ -837,19 +840,26 @@ static int raw_getsockopt(struct socket *sock, int level, int optname,
 				err = -ERANGE;
 				opt->optlen = fsize;
 			} else {
 				if (len > fsize)
 					len = fsize;
-				if (copy_to_iter(ro->filter, len,
-						 &opt->iter_out) != len)
-					err = -EFAULT;
+				/* copy to user space after release_sock() */
+				filter = kmemdup(ro->filter, len, GFP_KERNEL);
+				if (!filter)
+					err = -ENOMEM;
 			}
 		} else {
 			len = 0;
 		}
 		release_sock(sk);
 
+		if (filter) {
+			if (copy_to_iter(filter, len, &opt->iter_out) != len)
+				err = -EFAULT;
+			kfree(filter);
+		}
+
 		if (!err)
 			opt->optlen = len;
 		return err;
 	}
 	case CAN_RAW_ERR_FILTER:
-- 
2.43.0