On Fri, Nov 06, 2026 at 10:53:39AM +0100, Eric Dumazet wrote:
> virtio_net_hdr_tnl_to_skb() trusts the virtio header to describe a
> UDP tunnel over IPv4 or IPv6, but never checks that the frame actually
> carries such outer headers. Because VIRTIO_NET_HDR_F_NEEDS_CSUM is
> mandatory for tunnel GSO, __virtio_net_hdr_to_skb() skips the flow
> dissector, so virtio_net_hdr_match_proto() is never applied either.
>
> A guest (or a tap writer) can then inject a frame with an arbitrary
> outer ethertype, for example ETH_P_NSH, with SKB_GSO_UDP_TUNNEL set.
> The GSO stack then runs nsh_gso_segment() on top of the UDP tunnel
> segmentation, which assumes a different header layout. The result is
> segments with skb->data before skb->head, and a host crash in
> skb_under_panic() as soon as a later layer pushes a header:
>
> skbuff: skb_under_panic: ... put:4 ... dev:gretap1
> kernel BUG at net/core/skbuff.c:215!
> skb_push
> __gre_xmit
> gre_tap_xmit
> ...
> tun_get_user
>
> Validate the outer headers with the parsing helpers from Michael's
> series "net: resolve uncommon partial checksums at ingress":
>
> - locate the L3 header: Ethernet with optional VLAN tags, or the
> network header set by the caller. skb->protocol is not trusted when
> it disagrees with the frame.
> - require the outer L3 protocol to match the declared tunnel type.
> - require the outer UDP header exactly at outer_th_offset, after IPv4
> options or IPv6 extension headers, and reject fragments.
>
> Unlike the original helpers:
>
> - the callers tell whether the frame starts with an Ethernet header,
> with a new has_eth argument of virtio_net_hdr_tnl_to_skb(), instead
> of using the device type. tun frames packets from its IFF_TAP and
> IFF_TUN flags, and TUNSETLINK can set the device type to any value.
> virtio_net and tun_xdp_one() always pass true, tun_get_user() passes
> whether the device is IFF_TAP.
> - ipv6_find_hdr() stops at an AH header, as Willem suggested in the
> review of that series.
>
> Fixes: a2fb4bc4e2a6 ("net: implement virtio helpers to handle UDP GSO
> tunneling.")
> Reported-by: Hassan Sultan <[email protected]>
> Suggested-by: Willem de Bruijn <[email protected]>
> Link:
> https://lore.kernel.org/netdev/93d0e37c99711bebdf60c120af03010455c2f2e2.1793276116.git....@redhat.com/
> Cc: Willem de Bruijn <[email protected]>
> Cc: Michael S. Tsirkin <[email protected]>
> Co-developed-by: Michael S. Tsirkin <[email protected]>
> Signed-off-by: Michael S. Tsirkin <[email protected]>
> Reviewed-by: Willem de Bruijn <[email protected]>
> Signed-off-by: Eric Dumazet <[email protected]>
Acked-by: Michael S. Tsirkin <[email protected]>
> ---
> drivers/net/tun.c | 9 +-
> drivers/net/tun_vnet.h | 5 +-
> drivers/net/virtio_net.c | 2 +-
> include/linux/virtio_net.h | 169 +++++++++++++++++++++++++++++++++++++
> 4 files changed, 180 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index dcec7311e601..3920b3dff1e8 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -1944,7 +1944,8 @@ static ssize_t tun_get_user(struct tun_struct *tun,
> struct tun_file *tfile,
> break;
> }
>
> - if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) {
> + if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr,
> + (tun->flags & TUN_TYPE_MASK) == IFF_TAP)) {
> atomic_long_inc(&tun->rx_frame_errors);
> err = -EINVAL;
> goto free_skb;
> @@ -2621,7 +2622,11 @@ static int tun_xdp_one(struct tun_struct *tun,
> tnl_hdr = (struct virtio_net_hdr_v1_hash_tunnel *)gso;
> skb->dev = tun->dev;
> skb_set_network_header(skb, ETH_HLEN);
> - if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr)) {
> + /* Frames always start with an Ethernet header here, as the
> + * eth_type_trans() call below expects.
> + */
> + if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr,
> + true)) {
> atomic_long_inc(&tun->rx_frame_errors);
> kfree_skb(skb);
> ret = -EINVAL;
> diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
> index f4c652b1fa44..3364e08dd6e0 100644
> --- a/drivers/net/tun_vnet.h
> +++ b/drivers/net/tun_vnet.h
> @@ -197,9 +197,10 @@ static inline netdev_features_t
> tun_vnet_hdr_guest_features(int vnet_hdr_sz)
> static inline int
> 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_v1_hash_tunnel *hdr,
> + bool has_eth)
> {
> - return virtio_net_hdr_tnl_to_skb(skb, hdr,
> + return virtio_net_hdr_tnl_to_skb(skb, hdr, has_eth,
> features & NETIF_F_GSO_UDP_TUNNEL,
> features & NETIF_F_GSO_UDP_TUNNEL_CSUM,
> tun_vnet_is_little_endian(flags));
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index dd2c41ef6fbe..ed20e76fbc4c 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -2533,7 +2533,7 @@ static void virtnet_receive_done(struct virtnet_info
> *vi, struct receive_queue *
>
> skb->dev = dev;
> skb_set_network_header(skb, ETH_HLEN);
> - if (virtio_net_hdr_tnl_to_skb(skb, &hdr->tnl_hdr, vi->rx_tnl,
> + if (virtio_net_hdr_tnl_to_skb(skb, &hdr->tnl_hdr, true, vi->rx_tnl,
> vi->rx_tnl_csum,
> virtio_is_little_endian(vi->vdev))) {
> net_warn_ratelimited("%s: bad gso: type: %x, size: %u, flags %x
> tunnel %d tnl csum %d\n",
> diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
> index d6466f96cdd0..b7b6b542f476 100644
> --- a/include/linux/virtio_net.h
> +++ b/include/linux/virtio_net.h
> @@ -5,7 +5,10 @@
> #include <linux/if_vlan.h>
> #include <linux/ip.h>
> #include <linux/ipv6.h>
> +#include <linux/netdevice.h>
> #include <linux/udp.h>
> +#include <net/ip.h>
> +#include <net/ipv6.h>
> #include <net/tcp.h>
> #include <uapi/linux/tcp.h>
> #include <uapi/linux/virtio_net.h>
> @@ -48,6 +51,145 @@ static inline int virtio_net_hdr_set_proto(struct sk_buff
> *skb,
> return 0;
> }
>
> +/* TODO: nothing virtio specific here, move to ip.h */
> +
> +/*
> + * Pull and minimally validate the IPv4 header at @nhoff.
> + * Returns the header and stores the transport header offset in
> + * @thoff, or NULL if truncated or malformed. The whole header,
> + * options included, is guaranteed linear on return.
> + */
> +static inline struct iphdr *virtio_net_ip4_parse(struct sk_buff *skb,
> + unsigned int nhoff,
> + unsigned int *thoff)
> +{
> + unsigned int ihl;
> + struct iphdr *iph;
> +
> + if (!pskb_may_pull(skb, nhoff + sizeof(struct iphdr)))
> + return NULL;
> +
> + iph = (struct iphdr *)(skb->data + nhoff);
> + if (iph->version != 4 ||
> + iph->ihl < sizeof(struct iphdr) / sizeof(u32))
> + return NULL;
> +
> + ihl = iph->ihl * sizeof(u32);
> + *thoff = nhoff + ihl;
> + /* Pull the options as well: the transport header offset
> + * returned above must be within the linear data. iph goes
> + * stale across the pull.
> + */
> + if (!pskb_may_pull(skb, nhoff + ihl))
> + return NULL;
> +
> + return (struct iphdr *)(skb->data + nhoff);
> +}
> +
> +/* Where does the L3 header start, and what protocol is it?
> + * With @has_eth, the frame starts with an Ethernet header, possibly
> + * followed by VLAN tags. Otherwise the L3 header starts at the network
> + * header offset the caller set up.
> + *
> + * The caller knows how the frame will be parsed later: the device
> + * type does not tell, as tun can change it with TUNSETLINK.
> + */
> +static inline bool
> +virtio_net_l3_start(struct sk_buff *skb, bool has_eth, int *nhoff,
> + __be16 *proto)
> +{
> + if (has_eth) {
> + __be16 h_proto;
> +
> + if (!pskb_may_pull(skb, ETH_HLEN))
> + return false;
> + h_proto = eth_hdr(skb)->h_proto;
> + /* skb->protocol is a sender claim, and parts of the
> + * stack parse the packet per it: when it disagrees with
> + * the frame we do not know which view the packet will
> + * be parsed as, so do not validate.
> + */
> + if (skb->protocol && skb->protocol != h_proto)
> + return false;
> + *nhoff = ETH_HLEN;
> + *proto = h_proto;
> + if (eth_type_vlan(*proto)) {
> + *proto = __vlan_get_protocol(skb, *proto, nhoff);
> + if (!*proto)
> + return false;
> + }
> + } else {
> + const struct iphdr *iph;
> +
> + *nhoff = skb_network_offset(skb);
> + /* An unset network header shows up as an offset
> + * outside of the packet.
> + */
> + if (*nhoff < 0 || (unsigned int)*nhoff >= skb->len)
> + return false;
> + /* No L2 header to cross-check with: take the protocol
> + * from the IP version at the network header.
> + */
> + if (!pskb_may_pull(skb, *nhoff + 1))
> + return false;
> + iph = (const struct iphdr *)(skb->data + *nhoff);
> + if (iph->version == 4)
> + *proto = htons(ETH_P_IP);
> + else if (iph->version == 6)
> + *proto = htons(ETH_P_IPV6);
> + else
> + return false;
> + if (skb->protocol && skb->protocol != *proto)
> + return false;
> + }
> + return true;
> +}
> +
> +/* Walk the L3 header at @nhoff: where does its transport header
> + * start, and which protocol is it? Returns false if the header
> + * is truncated, malformed or fragmented.
> + */
> +static inline bool
> +virtio_net_l4_start(struct sk_buff *skb, unsigned int nhoff, __be16 proto,
> + unsigned int *thoff, int *ip_proto)
> +{
> + if (proto == htons(ETH_P_IP)) {
> + const struct iphdr *iph = virtio_net_ip4_parse(skb, nhoff,
> thoff);
> +
> + if (!iph || ip_is_fragment(iph))
> + return false;
> + *ip_proto = iph->protocol;
> + return true;
> + }
> +
> + if (proto == htons(ETH_P_IPV6)) {
> + const struct ipv6hdr *iph;
> + int flags = IP6_FH_F_AUTH;
> +
> + if (!pskb_may_pull(skb, nhoff + sizeof(*iph)))
> + return false;
> + iph = (const void *)(skb->data + nhoff);
> + if (iph->version != 6)
> + return false;
> + *thoff = nhoff + sizeof(*iph);
> + *ip_proto = iph->nexthdr;
> + if (*ip_proto != IPPROTO_TCP && *ip_proto != IPPROTO_UDP) {
> + *thoff = nhoff;
> + /* Find the transport header behind any
> + * extension headers. IP6_FH_F_AUTH stops
> + * the walk at AH, so frames with AH are rejected.
> + */
> + *ip_proto = ipv6_find_hdr(skb, thoff, -1, NULL,
> + &flags);
> + if (*ip_proto < 0 || flags & IP6_FH_F_FRAG)
> + return false;
> + }
> + return true;
> + }
> +
> + return false;
> +}
> +
> 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)
> @@ -282,9 +424,33 @@ static inline unsigned int virtio_l3min(bool is_ipv6)
> return is_ipv6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr);
> }
>
> +/* Do the tunnel offsets match the outer headers in the frame?
> + * The L3 header the tunnel claims must be the one the frame
> + * carries, with UDP following it at @outer_th.
> + */
> +static inline bool
> +virtio_net_tnl_offsets_ok(struct sk_buff *skb, bool has_eth, bool outer_isv6,
> + unsigned int outer_th)
> +{
> + int nhoff;
> + __be16 proto;
> + unsigned int thoff;
> + int ip_proto;
> +
> + if (!virtio_net_l3_start(skb, has_eth, &nhoff, &proto))
> + return false;
> + if (outer_isv6 != (proto == htons(ETH_P_IPV6)))
> + return false;
> + if (!virtio_net_l4_start(skb, nhoff, proto, &thoff, &ip_proto))
> + return false;
> +
> + return ip_proto == IPPROTO_UDP && outer_th == thoff;
> +}
> +
> static inline int
> virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
> const struct virtio_net_hdr_v1_hash_tunnel *vhdr,
> + bool has_eth,
> bool tnl_hdr_negotiated,
> bool tnl_csum_negotiated,
> bool little_endian)
> @@ -338,6 +504,9 @@ virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
> if (ret)
> return ret;
>
> + if (!virtio_net_tnl_offsets_ok(skb, has_eth, outer_isv6, outer_th))
> + return -EINVAL;
> +
> /* In case of USO, the inner protocol is still unknown and
> * `inner_isv6` is just a guess, additional parsing is needed.
> * The previous validation ensures that accessing an ipv4 inner
> --
> 2.53.0
