Merge branch 'vxlan-fix-npds-when-using-nexthop-objects'

Ido Schimmel says:

====================
vxlan: Fix NPDs when using nexthop objects

With FDB nexthop groups, VXLAN FDB entries do not necessarily point to
a remote destination but rather to an FDB nexthop group. This means that
first_remote_{rcu,rtnl}() can return NULL and a few places in the driver
were not ready for that, resulting in NULL pointer dereferences.
Patches #1-#2 fix these NPDs.

Note that vxlan_fdb_find_uc() still dereferences the remote returned by
first_remote_rcu() without checking that it is not NULL, but this
function is only invoked by a single driver which vetoes the creation of
FDB nexthop groups. I will patch this in net-next to make the code less
fragile.

Patch #3 adds a selftests which exercises these code paths and tests
basic Tx functionality with FDB nexthop groups. I verified that the test
crashes the kernel without the first two patches.
====================

Link: https://patch.msgid.link/20250901065035.159644-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 12 insertions, 6 deletions

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index f32be2e301f2..dab864bc733c 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1445,6 +1445,10 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 		if (READ_ONCE(f->updated) != now)
 			WRITE_ONCE(f->updated, now);
 
+		/* Don't override an fdb with nexthop with a learnt entry */
+		if (rcu_access_pointer(f->nh))
+			return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS;
+
 		if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) &&
 			   rdst->remote_ifindex == ifindex))
 			return SKB_NOT_DROPPED_YET;
@@ -1453,10 +1457,6 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 		if (f->state & (NUD_PERMANENT | NUD_NOARP))
 			return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS;
 
-		/* Don't override an fdb with nexthop with a learnt entry */
-		if (rcu_access_pointer(f->nh))
-			return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS;
-
 		if (net_ratelimit())
 			netdev_info(dev,
 				    "%pM migrated from %pIS to %pIS\n",
@@ -1877,6 +1877,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 	n = neigh_lookup(&arp_tbl, &tip, dev);
 
 	if (n) {
+		struct vxlan_rdst *rdst = NULL;
 		struct vxlan_fdb *f;
 		struct sk_buff	*reply;
 
@@ -1887,7 +1888,9 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 
 		rcu_read_lock();
 		f = vxlan_find_mac_tx(vxlan, n->ha, vni);
-		if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
+		if (f)
+			rdst = first_remote_rcu(f);
+		if (rdst && vxlan_addr_any(&rdst->remote_ip)) {
 			/* bridge-local neighbor */
 			neigh_release(n);
 			rcu_read_unlock();
@@ -2044,6 +2047,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 	n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev);
 
 	if (n) {
+		struct vxlan_rdst *rdst = NULL;
 		struct vxlan_fdb *f;
 		struct sk_buff *reply;
 
@@ -2053,7 +2057,9 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 		}
 
 		f = vxlan_find_mac_tx(vxlan, n->ha, vni);
-		if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
+		if (f)
+			rdst = first_remote_rcu(f);
+		if (rdst && vxlan_addr_any(&rdst->remote_ip)) {
 			/* bridge-local neighbor */
 			neigh_release(n);
 			goto out;