[PATCH net-next v3 1/2] 8021q: Fix data race when publishing vlan net_device pointers

A plain C read and assignment of the net_device pointer
in the vlan_devices_arrays leaf entries lack proper atomicity
and ordering barriers. A concurrent lockless reader on the packet
receive fast-path could observe a torn or partially initialized
net_device pointer, leading to a potential out-of-bounds read or kernel
panic.

The data race occurs between the netlink/ioctl configuration paths
(holding the per-netns rtnl_nets_lock or RTNL lock) and the softirq
receive fast-path (holding rcu_read_lock()):

  CPU 0 (Writer, rtnl_nets_lock/RTNL)      CPU 1 (Reader, rcu_read_lock())
  -----------------------------------      -------------------------------
   rtnetlink_rcv_msg()
     // RTM_NEWLINK handler with RTNL_FLAG_DOIT_PERNET
     rtnl_newlink()
       ops->newlink() == vlan_newlink()
   OR
   vlan_ioctl_handler()
     [ADD_VLAN_CMD] -> register_vlan_device()

     register_vlan_dev()
       vlan_group_set_device()
                                      netif_receive_skb_core()
                                          vlan_do_receive()
                                              vlan_find_dev()
                                                 __vlan_group_get_device()
                                                  // Speculative / torn read
                                                  [Loads bad net_device *]
           [Plain C store]
           array[vlan_id] = dev;
                                                  // Dereferences bad pointer
                                                  // during device status check
                                                  vlan_dev->flags (PANIC!)

Fix this by using rcu_assign_pointer() in vlan_group_set_device()
and rcu_dereference_raw() in __vlan_group_get_device() to enforce
proper ordering and memory atomicity for the leaf entry traversal.

Cc: stable@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Stanislav Fomichev <sdf@fomichev.me>
Cc: Kuniyuki Iwashima <kuniyu@google.com>
Cc: Nicolai Buchwitz <redacted>
Cc: Dan Aloni <redacted>
Cc: Jeff Garzik <redacted>
Fixes: 5c15bdec5c38 ("[VLAN]: Avoid a 4-order allocation.")
Link: https://sashiko.dev/#/patchset/20260825095422.3166067-1-ruanjinjie%40huawei.com
Signed-off-by: Jinjie Ruan <redacted>
---
 net/8021q/vlan.c |  2 +-
 net/8021q/vlan.h | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 2d2efb877975..6df80cad40a2 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c

@@ -49,7 +49,7 @@ const char vlan_version[] = DRV_VERSION;
 static int vlan_group_prealloc_vid(struct vlan_group *vg,
 				   __be16 vlan_proto, u16 vlan_id)
 {
-	struct net_device **array;
+	struct net_device __rcu **array;
 	unsigned int vidx;
 	unsigned int size;
 	int pidx;

diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index c41caaf94095..3cb4c8294130 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h

@@ -22,8 +22,8 @@ enum vlan_protos {
 struct vlan_group {
 	unsigned int		nr_vlan_devs;
 	struct hlist_node	hlist;	/* linked list */
-	struct net_device **vlan_devices_arrays[VLAN_PROTO_NUM]
-					       [VLAN_GROUP_ARRAY_SPLIT_PARTS];
+	struct net_device __rcu **vlan_devices_arrays[VLAN_PROTO_NUM]
+						     [VLAN_GROUP_ARRAY_SPLIT_PARTS];
 };
 
 struct vlan_info {

@@ -54,7 +54,7 @@ static inline struct net_device *__vlan_group_get_device(struct vlan_group *vg,
 							 unsigned int pidx,
 							 u16 vlan_id)
 {
-	struct net_device **array;
+	struct net_device __rcu **array;
 
 	array = vg->vlan_devices_arrays[pidx]
 				       [vlan_id / VLAN_GROUP_ARRAY_PART_LEN];

@@ -62,7 +62,7 @@ static inline struct net_device *__vlan_group_get_device(struct vlan_group *vg,
 	/* paired with smp_wmb() in vlan_group_prealloc_vid() */
 	smp_rmb();
 
-	return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL;
+	return array ? rcu_dereference_raw(array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN]) : NULL;
 }
 
 static inline struct net_device *vlan_group_get_device(struct vlan_group *vg,

@@ -82,13 +82,13 @@ static inline void vlan_group_set_device(struct vlan_group *vg,
 					 struct net_device *dev)
 {
 	int pidx = vlan_proto_idx(vlan_proto);
-	struct net_device **array;
+	struct net_device __rcu **array;
 
 	if (!vg || pidx < 0)
 		return;
 	array = vg->vlan_devices_arrays[pidx]
 				       [vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
-	array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev;
+	rcu_assign_pointer(array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN], dev);
 }
 
 /* Must be invoked with rcu_read_lock or with RTNL. */

-- 
2.34.1