Merge branch 'vxlan-fixes-for-skb-header-pulling-cloning-and-concurrency-in-tx-path'

Eric Dumazet says:

====================
vxlan: fixes for skb header pulling, cloning, and concurrency in TX path

While working on RTNL-less fill_info for vxlan, Sashiko found annoying
pre-existing issues, adding noise to an already complex work.

This series addresses some of them in VXLAN transmit path,
primarily within route_shortcircuit(), header validation, and neighbour
lookup.

Patch 1 fixes a potential use-after-free in vxlan_xmit() caused by caching
the Ethernet header pointer ('eth') before calling route_shortcircuit(),
which can reallocate skb->head via pskb_may_pull().

Patch 2 calls skb_cow_head() in route_shortcircuit() before modifying the
Ethernet header in-place, preventing packet header corruption when the skb
is cloned (e.g., by packet sockets, tcpdump, or dev_queue_xmit).

Patch 3 replaces direct reads of n->ha in route_shortcircuit() with
neigh_ha_snapshot() to safely snapshot the neighbour hardware address
under seqlock protection, avoiding potential torn reads during
asynchronous updates.

Patch 4 changes route_shortcircuit() to use pskb_network_may_pull() instead
of pskb_may_pull(). Since skb->data points to the MAC header on transmit
(skb_network_offset(skb) == ETH_HLEN), pskb_may_pull() was only checking
6 bytes into the IP header, leaving the remainder un-pulled in non-linear
frags.

Patch 5 applies pskb_network_may_pull() to the remaining transmit-path
header pull checks in arp_reduce(), ND solicitation proxy checks, and
MDB entry lookup, where skb->data similarly points to the Ethernet header.
====================

Link: https://patch.msgid.link/20260723144249.759100-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 16 insertions, 9 deletions

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index d834a4865aec..1ded27768a97 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1850,7 +1850,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 	if (dev->flags & IFF_NOARP)
 		goto out;
 
-	if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
+	if (!pskb_network_may_pull(skb, arp_hdr_len(dev))) {
 		dev_dstats_tx_dropped(dev);
 		vxlan_vnifilter_count(vxlan, vni, NULL,
 				      VXLAN_VNI_STATS_TX_DROPS, 0);
@@ -2111,7 +2111,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	{
 		struct iphdr *pip;
 
-		if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
 			return false;
 		pip = ip_hdr(skb);
 		n = neigh_lookup(&arp_tbl, &pip->daddr, dev);
@@ -2137,7 +2137,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 		 */
 		if (!ipv6_mod_enabled())
 			return false;
-		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))
 			return false;
 		pip6 = ipv6_hdr(skb);
 		n = neigh_lookup(&nd_tbl, &pip6->daddr, dev);
@@ -2159,13 +2159,19 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	}
 
 	if (n) {
+		u8 haddr[ETH_ALEN];
 		bool diff;
 
-		diff = !ether_addr_equal(eth_hdr(skb)->h_dest, n->ha);
+		neigh_ha_snapshot(haddr, n, dev);
+		diff = !ether_addr_equal_unaligned(eth_hdr(skb)->h_dest, haddr);
 		if (diff) {
+			if (skb_cow_head(skb, 0)) {
+				neigh_release(n);
+				return false;
+			}
 			memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
 				dev->addr_len);
-			memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len);
+			memcpy(eth_hdr(skb)->h_dest, haddr, dev->addr_len);
 		}
 		neigh_release(n);
 		return diff;
@@ -2757,8 +2763,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 			return arp_reduce(dev, skb, vni);
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
-			 pskb_may_pull(skb, sizeof(struct ipv6hdr) +
-					    sizeof(struct nd_msg)) &&
+			 pskb_network_may_pull(skb, sizeof(struct ipv6hdr) +
+						    sizeof(struct nd_msg)) &&
 			 ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
 			struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1);
 
@@ -2796,6 +2802,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	    (ntohs(eth->h_proto) == ETH_P_IP ||
 	     ntohs(eth->h_proto) == ETH_P_IPV6)) {
 		did_rsc = route_shortcircuit(dev, skb);
+		eth = eth_hdr(skb);
 		if (did_rsc)
 			f = vxlan_find_mac_tx(vxlan, eth->h_dest, vni);
 	}
diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c
index af7a0d7f95a5..9a9038ae90c1 100644
--- a/drivers/net/vxlan/vxlan_mdb.c
+++ b/drivers/net/vxlan/vxlan_mdb.c
@@ -1631,7 +1631,7 @@ struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan,
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
 			return NULL;
 		group.dst.sa.sa_family = AF_INET;
 		group.dst.sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
@@ -1640,7 +1640,7 @@ struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan,
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))
 			return NULL;
 		group.dst.sa.sa_family = AF_INET6;
 		group.dst.sin6.sin6_addr = ipv6_hdr(skb)->daddr;