[PATCH net v5 1/2] net: validate virtio checksum start after network header

[Paulos Yibelo <habte.yibelo@gmail.com>]

__virtio_net_hdr_to_skb() rejects a CHECKSUM_PARTIAL start smaller than
an estimated minimum network-header length. Its input offsets are relative
to skb->data.

Using skb_network_offset() here is unsafe. TUN/TAP, virtio-net, and UML
parse a received virtio header before skb->network_header is established.
On an skb with headroom, the resulting negative offset enlarges the
apparent distance to the transport header and can admit a checksum start
inside the network header.

Pass the data-relative L3 offset to the converter explicitly. IFF_TUN uses
zero, AF_PACKET supplies its established network offset, and Ethernet
receive paths parse Ethernet and nested VLAN headers with
skb_header_pointer(), without changing skb state. Use the same origin for
tunnel-offset validation, and make UML propagate conversion failures.

This does not require a virtual-machine guest. A TUN or TAP device with
virtio-net header support is sufficient to reach these paths.

Fixes: 49d14b54a527 ("net: test for not too small csum_start in virtio_net_hdr_to_skb()")
Fixes: a2fb4bc4e2a6 ("net: implement virtio helpers to handle UDP GSO tunneling.")
Reported-by: Paulos Yibelo <habte.yibelo@gmail.com>
Link: https://lore.kernel.org/netdev/20260920004733.6473-2-habte.yibelo@gmail.com/
Cc: stable@vger.kernel.org
Signed-off-by: Paulos Yibelo <habte.yibelo@gmail.com>
---
Changes in v5:
- Replace the not-yet-established skb network-header offset with an
  explicit data-relative L3 origin.
- Cover all in-tree callers, including Ethernet/VLAN receive paths,
  tunnel metadata, and UML error propagation.
- Drop the prior Acked-by and Reviewed-by tags because the code changed.

Changes in v4:
- State that a TUN device is sufficient and no guest is required, as
  noted by Michael S. Tsirkin.

Changes in v3:
- Keep the network-relative comparison on one line for readability, as
  requested by David Ahern.

Changes in v2:
- Make nh_min_len an int and remove the casts, as suggested by Michael S.
  Tsirkin.

 arch/um/drivers/vector_transports.c | 10 +++-
 drivers/net/tun_vnet.h              | 28 ++++++++++-
 drivers/net/virtio_net.c            |  8 ++-
 include/linux/virtio_net.h          | 76 +++++++++++++++++++++++------
 net/packet/af_packet.c              |  6 ++-
 5 files changed, 106 insertions(+), 22 deletions(-)

diff --git a/arch/um/drivers/vector_transports.c b/arch/um/drivers/vector_transports.c
index ddd127ee9..79bc05fc6 100644
--- a/arch/um/drivers/vector_transports.c
+++ b/arch/um/drivers/vector_transports.c
@@ -197,6 +197,7 @@ static int raw_verify_header(
 	uint8_t *header, struct sk_buff *skb, struct vector_private *vp)
 {
 	struct virtio_net_hdr *vheader = (struct virtio_net_hdr *) header;
+	int network_offset;
 
 	if ((vheader->gso_type != VIRTIO_NET_HDR_GSO_NONE) &&
 		(vp->req_size != 65536)) {
@@ -209,8 +210,13 @@ static int raw_verify_header(
 	if ((vheader->flags & VIRTIO_NET_HDR_F_DATA_VALID) > 0)
 		return 1;
 
-	virtio_net_hdr_to_skb(skb, vheader, virtio_legacy_is_little_endian());
-	return 0;
+	network_offset = virtio_net_hdr_get_l3_offset(skb, vheader);
+	if (network_offset < 0)
+		return network_offset;
+
+	return virtio_net_hdr_to_skb(skb, vheader,
+				     virtio_legacy_is_little_endian(),
+				     network_offset);
 }
 
 static bool get_uint_param(
diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
index f4c652b1f..1c83c359d 100644
--- a/drivers/net/tun_vnet.h
+++ b/drivers/net/tun_vnet.h
@@ -177,10 +177,27 @@ static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter,
 	return __tun_vnet_hdr_put(sz, 0, iter, hdr);
 }
 
+static inline int
+tun_vnet_hdr_get_l3_offset(unsigned int flags, const struct sk_buff *skb,
+			   const struct virtio_net_hdr *hdr)
+{
+	if ((flags & TUN_TYPE_MASK) != IFF_TAP)
+		return 0;
+
+	return virtio_net_hdr_get_l3_offset(skb, hdr);
+}
+
 static inline int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb,
 				      const struct virtio_net_hdr *hdr)
 {
-	return virtio_net_hdr_to_skb(skb, hdr, tun_vnet_is_little_endian(flags));
+	int network_offset = tun_vnet_hdr_get_l3_offset(flags, skb, hdr);
+
+	if (network_offset < 0)
+		return network_offset;
+
+	return virtio_net_hdr_to_skb(skb, hdr,
+				     tun_vnet_is_little_endian(flags),
+				     network_offset);
 }
 
 /*
@@ -199,10 +216,17 @@ tun_vnet_hdr_tnl_to_skb(unsigned int flags, netdev_features_t features,
 			struct sk_buff *skb,
 			const struct virtio_net_hdr_v1_hash_tunnel *hdr)
 {
+	const struct virtio_net_hdr *vnet_hdr = (const struct virtio_net_hdr *)hdr;
+	int network_offset = tun_vnet_hdr_get_l3_offset(flags, skb, vnet_hdr);
+
+	if (network_offset < 0)
+		return network_offset;
+
 	return virtio_net_hdr_tnl_to_skb(skb, hdr,
 				features & NETIF_F_GSO_UDP_TUNNEL,
 				features & NETIF_F_GSO_UDP_TUNNEL_CSUM,
-				tun_vnet_is_little_endian(flags));
+				tun_vnet_is_little_endian(flags),
+				network_offset);
 }
 
 static inline int tun_vnet_hdr_from_skb(unsigned int flags,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index e34c52d05..059eeb18e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2502,6 +2502,7 @@ static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *
 {
 	struct virtio_net_common_hdr *hdr;
 	struct net_device *dev = vi->dev;
+	int network_offset;
 
 	hdr = skb_vnet_common_hdr(skb);
 	if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report)
@@ -2515,9 +2516,12 @@ static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *
 		goto frame_err;
 	}
 
-	if (virtio_net_hdr_tnl_to_skb(skb, &hdr->tnl_hdr, vi->rx_tnl,
+	network_offset = virtio_net_hdr_get_l3_offset(skb, &hdr->hdr);
+	if (network_offset < 0 ||
+	    virtio_net_hdr_tnl_to_skb(skb, &hdr->tnl_hdr, vi->rx_tnl,
 				      vi->rx_tnl_csum,
-				      virtio_is_little_endian(vi->vdev))) {
+				      virtio_is_little_endian(vi->vdev),
+				      network_offset)) {
 		net_warn_ratelimited("%s: bad gso: type: %x, size: %u, flags %x tunnel %d tnl csum %d\n",
 				     dev->name, hdr->hdr.gso_type,
 				     hdr->hdr.gso_size, hdr->hdr.flags,
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index c381b916c..a4c005796 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -48,11 +48,49 @@ static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
 	return 0;
 }
 
+/*
+ * Return the L3 offset of an Ethernet frame starting at skb->data.
+ * The offset is unused without NEEDS_CSUM, so avoid parsing and return zero.
+ */
+static inline int
+virtio_net_hdr_get_l3_offset(const struct sk_buff *skb,
+			     const struct virtio_net_hdr *hdr)
+{
+	unsigned int parse_depth = VLAN_MAX_DEPTH;
+	const struct ethhdr *eth;
+	struct ethhdr ethbuf;
+	__be16 protocol;
+	int depth = ETH_HLEN;
+
+	if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM))
+		return 0;
+
+	eth = skb_header_pointer(skb, 0, sizeof(ethbuf), &ethbuf);
+	if (!eth)
+		return -EINVAL;
+
+	protocol = eth->h_proto;
+	while (eth_type_vlan(protocol)) {
+		const struct vlan_hdr *vh;
+		struct vlan_hdr vhdr;
+
+		vh = skb_header_pointer(skb, depth, sizeof(vhdr), &vhdr);
+		if (!vh || !--parse_depth)
+			return -EINVAL;
+
+		protocol = vh->h_vlan_encapsulated_proto;
+		depth += VLAN_HLEN;
+	}
+
+	return depth;
+}
+
 static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb,
 					  const struct virtio_net_hdr *hdr,
-					  bool little_endian, u8 hdr_gso_type)
+					  bool little_endian, u8 hdr_gso_type,
+					  int network_offset)
 {
-	unsigned int nh_min_len = sizeof(struct iphdr);
+	int nh_min_len = sizeof(struct iphdr);
 	unsigned int gso_type = 0;
 	unsigned int thlen = 0;
 	unsigned int p_off = 0;
@@ -98,16 +136,20 @@ static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb,
 		u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
 		u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
 		u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
+		int transport_offset;
 
 		if (!pskb_may_pull(skb, needed))
 			return -EINVAL;
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
-		if (skb_transport_offset(skb) < nh_min_len)
+
+		transport_offset = skb_transport_offset(skb);
+		if (transport_offset < nh_min_len || network_offset < 0 ||
+		    network_offset > transport_offset - nh_min_len)
 			return -EINVAL;
 
-		nh_min_len = skb_transport_offset(skb);
+		nh_min_len = transport_offset;
 		p_off = nh_min_len + thlen;
 		if (!pskb_may_pull(skb, p_off))
 			return -EINVAL;
@@ -206,9 +248,11 @@ static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					const struct virtio_net_hdr *hdr,
-					bool little_endian)
+					bool little_endian,
+					int network_offset)
 {
-	return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type);
+	return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type,
+				       network_offset);
 }
 
 /* This function must be called after virtio_net_hdr_from_skb(). */
@@ -287,7 +331,7 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 	return 0;
 }
 
-static inline unsigned int virtio_l3min(bool is_ipv6)
+static inline int virtio_l3min(bool is_ipv6)
 {
 	return is_ipv6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr);
 }
@@ -297,18 +341,19 @@ virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
 			  const struct virtio_net_hdr_v1_hash_tunnel *vhdr,
 			  bool tnl_hdr_negotiated,
 			  bool tnl_csum_negotiated,
-			  bool little_endian)
+			  bool little_endian, int network_offset)
 {
 	const struct virtio_net_hdr *hdr = (const struct virtio_net_hdr *)vhdr;
-	unsigned int inner_nh, outer_th, inner_th;
-	unsigned int inner_l3min, outer_l3min;
 	u8 gso_inner_type, gso_tunnel_type;
 	bool outer_isv6, inner_isv6;
+	int inner_nh, outer_th, inner_th;
+	int inner_l3min, outer_l3min;
 	int ret;
 
 	gso_tunnel_type = hdr->gso_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL;
 	if (!gso_tunnel_type)
-		return virtio_net_hdr_to_skb(skb, hdr, little_endian);
+		return virtio_net_hdr_to_skb(skb, hdr, little_endian,
+					     network_offset);
 
 	/* Tunnel not supported/negotiated, but the hdr asks for it. */
 	if (!tnl_hdr_negotiated)
@@ -332,19 +377,22 @@ virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
 	outer_isv6 = gso_tunnel_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6;
 	inner_isv6 = gso_inner_type == VIRTIO_NET_HDR_GSO_TCPV6;
 	inner_l3min = virtio_l3min(inner_isv6);
-	outer_l3min = ETH_HLEN + virtio_l3min(outer_isv6);
+	outer_l3min = virtio_l3min(outer_isv6);
 
 	inner_th = __virtio16_to_cpu(little_endian, hdr->csum_start);
 	inner_nh = le16_to_cpu(vhdr->inner_nh_offset);
 	outer_th = le16_to_cpu(vhdr->outer_th_offset);
-	if (outer_th < outer_l3min ||
+	if (network_offset < 0 ||
+	    outer_th < outer_l3min ||
+	    network_offset > outer_th - outer_l3min ||
 	    inner_nh < outer_th + sizeof(struct udphdr) ||
 	    inner_th < inner_nh + inner_l3min)
 		return -EINVAL;
 
 	/* Let the basic parsing deal with plain GSO features. */
 	ret = __virtio_net_hdr_to_skb(skb, hdr, true,
-				      hdr->gso_type & ~gso_tunnel_type);
+				      hdr->gso_type & ~gso_tunnel_type,
+				      network_offset);
 	if (ret)
 		return ret;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 50cae32ae..04c80e23d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2901,7 +2901,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		}
 
 		if (has_vnet_hdr) {
-			if (virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le())) {
+			if (virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le(),
+						  skb_network_offset(skb))) {
 				tp_len = -EINVAL;
 				goto tpacket_error;
 			}
@@ -3103,7 +3104,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	packet_parse_headers(skb, sock);
 
 	if (vnet_hdr_sz) {
-		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
+		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le(),
+					    skb_network_offset(skb));
 		if (err)
 			goto out_free;
 		len += vnet_hdr_sz;
-- 
2.46.0