On Mon, Sep 21, 2026 at 11:03:09PM -0400, Paulos Yibelo wrote:
> __virtio_net_hdr_to_skb() checks a minimum network-header length for
> CHECKSUM_PARTIAL packets. Its checksum start is relative to skb->data,
> but some callers have not established skb->network_header when they
> convert the virtio header.
>
> Pass the data-relative L3 origin explicitly. Ethernet receive paths
> parse the frame and nested VLAN headers without changing skb state.
> AF_PACKET uses the frame's actual L3 origin even when the socket
> protocol is ETH_P_IP and the raw frame carries VLAN tags. Non-Ethernet
> AF_PACKET devices retain their established skb network offset.
>
> Also pass the actual L3 protocol so IPv6 packets use the 40-byte base
> header minimum even without TCPv6 GSO. IFF_TUN obtains that protocol
> from the packet before skb->protocol is set. Name the Ethernet parser
> accordingly, use the same origin for tunnel validation, and propagate
> conversion failures in UML.
>
> The bound remains a minimum; fragmentation paths separately validate
> the parsed IPv4 or IPv6 header length before completing a checksum.
>
> 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 <[email protected]>
> Link:
> https://lore.kernel.org/netdev/[email protected]/
> Cc: [email protected]
> Assisted-by: LLM
> Signed-off-by: Paulos Yibelo <[email protected]>
Wow i just asked some questions, and it's getting more and more complex.
I am not sure people have time to review at this pace.
> ---
> arch/um/drivers/vector_transports.c | 13 ++++-
> drivers/net/tun_vnet.h | 52 ++++++++++++++++-
> drivers/net/virtio_net.c | 10 +++-
> include/linux/virtio_net.h | 87 ++++++++++++++++++++++++-----
> net/packet/af_packet.c | 24 +++++++-
> 5 files changed, 163 insertions(+), 23 deletions(-)
>
> diff --git a/arch/um/drivers/vector_transports.c
> b/arch/um/drivers/vector_transports.c
> index ddd127ee9..5a9d8f49a 100644
> --- a/arch/um/drivers/vector_transports.c
> +++ b/arch/um/drivers/vector_transports.c
> @@ -197,6 +197,8 @@ 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;
> + __be16 network_protocol;
> + int network_offset;
>
> if ((vheader->gso_type != VIRTIO_NET_HDR_GSO_NONE) &&
> (vp->req_size != 65536)) {
> @@ -209,8 +211,14 @@ 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_eth_get_l3_offset(skb, vheader,
> + &network_protocol);
> + if (network_offset < 0)
> + return network_offset;
> +
> + return virtio_net_hdr_to_skb(skb, vheader,
> + virtio_legacy_is_little_endian(),
> + network_offset, network_protocol);
> }
>
> static bool get_uint_param(
> @@ -491,4 +499,3 @@ int build_transport_data(struct vector_private *vp)
> return build_bess_transport_data(vp);
> return 0;
> }
> -
> diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
> index f4c652b1f..e004213fa 100644
> --- a/drivers/net/tun_vnet.h
> +++ b/drivers/net/tun_vnet.h
> @@ -177,10 +177,49 @@ 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,
> + __be16 *network_protocol)
> +{
> + if ((flags & TUN_TYPE_MASK) != IFF_TAP) {
> + u8 version, first_byte;
> + const u8 *first;
> +
> + *network_protocol = 0;
> + if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM))
> + return 0;
> +
> + first = skb_header_pointer(skb, 0, sizeof(first_byte),
> + &first_byte);
> + if (!first)
> + return -EINVAL;
> +
> + version = *first >> 4;
> + if (version == 4)
> + *network_protocol = htons(ETH_P_IP);
> + else if (version == 6)
> + *network_protocol = htons(ETH_P_IPV6);
> + return 0;
> + }
> +
> + return virtio_net_hdr_eth_get_l3_offset(skb, hdr,
> + network_protocol);
> +}
> +
> 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));
> + __be16 network_protocol;
> + int network_offset = tun_vnet_hdr_get_l3_offset(flags, skb, hdr,
> + &network_protocol);
> +
> + if (network_offset < 0)
> + return network_offset;
> +
> + return virtio_net_hdr_to_skb(skb, hdr,
> + tun_vnet_is_little_endian(flags),
> + network_offset, network_protocol);
> }
>
> /*
> @@ -199,10 +238,19 @@ 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;
> + __be16 network_protocol;
> + int network_offset = tun_vnet_hdr_get_l3_offset(flags, skb, vnet_hdr,
> + &network_protocol);
> +
> + 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, network_protocol);
> }
>
> 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..8e93dad28 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -2502,6 +2502,8 @@ static void virtnet_receive_done(struct virtnet_info
> *vi, struct receive_queue *
> {
> struct virtio_net_common_hdr *hdr;
> struct net_device *dev = vi->dev;
> + __be16 network_protocol;
> + int network_offset;
>
> hdr = skb_vnet_common_hdr(skb);
> if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report)
> @@ -2515,9 +2517,13 @@ 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_eth_get_l3_offset(skb, &hdr->hdr,
> + &network_protocol);
> + 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, network_protocol)) {
> 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..b89d821a0 100644
> --- a/include/linux/virtio_net.h
> +++ b/include/linux/virtio_net.h
> @@ -48,16 +48,61 @@ static inline int virtio_net_hdr_set_proto(struct sk_buff
> *skb,
> return 0;
> }
>
> +/*
> + * Return the L3 offset and protocol of an Ethernet frame starting at
> skb->data.
> + * The offset is unused without NEEDS_CSUM, so avoid parsing and return zero.
> + */
for networking code multiline comments:
/* always
* look like this
*/
/*
* never
* like this
*/
> +static inline int
> +virtio_net_hdr_eth_get_l3_offset(const struct sk_buff *skb,
> + const struct virtio_net_hdr *hdr,
> + __be16 *network_protocol)
> +{
> + unsigned int parse_depth = VLAN_MAX_DEPTH;
> + const struct ethhdr *eth;
> + struct ethhdr ethbuf;
> + __be16 protocol;
> + int depth = ETH_HLEN;
> +
> + *network_protocol = 0;
> + if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM))
> + return 0;
> +
> + eth = skb_header_pointer(skb, 0, sizeof(ethbuf), ðbuf);
> + 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;
> + }
> +
> + *network_protocol = protocol;
> + 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,
> + __be16 network_protocol)
> {
> - 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;
> unsigned int ip_proto;
>
> + if (network_protocol == htons(ETH_P_IPV6))
> + nh_min_len = sizeof(struct ipv6hdr);
I'd prefer this inside the initializer:
unsigned int nh_min_len = (network_protocol == htons(ETH_P_IPV6))?
sizeof(struct ipv6hdr) : sizeof(struct iphdr);
> +
> if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) {
> switch (hdr_gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
> case VIRTIO_NET_HDR_GSO_TCPV4:
> @@ -98,16 +143,20 @@ 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 +255,12 @@ 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,
> + __be16 network_protocol)
>From API POV, what is network_protocol here, exactly? I suspect it is
really af packet with IP protocol specific? So maybe it's really min_hdr
and then everyone except AF_PACKET can just pass 0? or do I
misunderstand?
> {
> - 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, network_protocol);
> }
>
> /* This function must be called after virtio_net_hdr_from_skb(). */
> @@ -287,7 +339,7 @@ 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 +349,20 @@ 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,
> + __be16 network_protocol)
> {
> 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, network_protocol);
>
> /* Tunnel not supported/negotiated, but the hdr asks for it. */
> if (!tnl_hdr_negotiated)
> @@ -332,19 +386,24 @@ 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);
> + if (network_protocol == htons(ETH_P_IPV6))
> + outer_l3min = sizeof(struct ipv6hdr);
So I vaguely understand that "network_protocol" is something af_packet
specific? because we already have inner_isv6 and outer_isv6
so this is neither? or do I misunderstand?
> 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, network_protocol);
> if (ret)
> return ret;
>
> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
> index 50cae32ae..0b37d5474 100644
> --- a/net/packet/af_packet.c
> +++ b/net/packet/af_packet.c
> @@ -2550,6 +2550,26 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
> sock_wfree(skb);
> }
>
> +static int packet_vnet_hdr_to_skb(struct sk_buff *skb,
> + const struct virtio_net_hdr *vnet_hdr)
> +{
> + __be16 network_protocol = 0;
> + int network_offset;
> +
> + if (skb->dev->type == ARPHRD_ETHER) {
> + network_offset = virtio_net_hdr_eth_get_l3_offset(skb, vnet_hdr,
> +
> &network_protocol);
> + } else {
> + network_offset = skb_network_offset(skb);
> + network_protocol = skb->protocol;
> + }
> + if (network_offset < 0)
> + return network_offset;
> +
> + return virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le(),
> + network_offset, network_protocol);
> +}
> +
> static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t
> len)
> {
> if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
> @@ -2901,7 +2921,7 @@ 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 (packet_vnet_hdr_to_skb(skb, &vnet_hdr)) {
> tp_len = -EINVAL;
> goto tpacket_error;
> }
> @@ -3103,7 +3123,7 @@ 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 = packet_vnet_hdr_to_skb(skb, &vnet_hdr);
> if (err)
> goto out_free;
> len += vnet_hdr_sz;
>
> base-commit: 1e24c4f2ee44be0eee94092b5d13cbdb4bdf0d60
> --
> 2.46.0
