Re: [PATCH net v5 1/2] virtio-net: correct hdr_len handling for VIRTIO_NET_F_GUEST_HDRLEN

["Michael S. Tsirkin" <mst@redhat.com>]

On Tue, Nov 11, 2025 at 07:12:11PM +0800, Xuan Zhuo wrote:
> The commit be50da3e9d4a ("net: virtio_net: implement exact header length
> guest feature") introduces support for the VIRTIO_NET_F_GUEST_HDRLEN
> feature in virtio-net.
> 
> This feature requires virtio-net to set hdr_len to the actual header
> length of the packet when transmitting, the number of
> bytes from the start of the packet to the beginning of the
> transport-layer payload.
> 
> However, in practice, hdr_len was being set using skb_headlen(skb),
> which is clearly incorrect. This commit fixes that issue.
> 
> Fixes: be50da3e9d4a ("net: virtio_net: implement exact header length guest feature")
> Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> ---
>  arch/um/drivers/vector_transports.c |  1 +
>  drivers/net/tun_vnet.h              |  4 ++--
>  drivers/net/virtio_net.c            |  9 +++++++--
>  include/linux/virtio_net.h          | 26 +++++++++++++++++++++-----
>  net/packet/af_packet.c              |  5 +++--
>  5 files changed, 34 insertions(+), 11 deletions(-)
> 
> diff --git a/arch/um/drivers/vector_transports.c b/arch/um/drivers/vector_transports.c
> index 0794d23f07cb..03c5baa1d0c1 100644
> --- a/arch/um/drivers/vector_transports.c
> +++ b/arch/um/drivers/vector_transports.c
> @@ -121,6 +121,7 @@ static int raw_form_header(uint8_t *header,
>  		vheader,
>  		virtio_legacy_is_little_endian(),
>  		false,
> +		false,
>  		0
>  	);
>  
> diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
> index 81662328b2c7..0d376bc70dd7 100644
> --- a/drivers/net/tun_vnet.h
> +++ b/drivers/net/tun_vnet.h
> @@ -214,7 +214,7 @@ static inline int tun_vnet_hdr_from_skb(unsigned int flags,
>  
>  	if (virtio_net_hdr_from_skb(skb, hdr,
>  				    tun_vnet_is_little_endian(flags), true,
> -				    vlan_hlen)) {
> +				    false, vlan_hlen)) {
>  		struct skb_shared_info *sinfo = skb_shinfo(skb);
>  
>  		if (net_ratelimit()) {
> @@ -244,7 +244,7 @@ tun_vnet_hdr_tnl_from_skb(unsigned int flags,
>  
>  	if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload,
>  					tun_vnet_is_little_endian(flags),
> -					vlan_hlen)) {
> +					false, vlan_hlen)) {
>  		struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr;
>  		struct skb_shared_info *sinfo = skb_shinfo(skb);
>  
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 0369dda5ed60..b335c88a8cd6 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -3317,9 +3317,13 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan)
>  	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
>  	struct virtnet_info *vi = sq->vq->vdev->priv;
>  	struct virtio_net_hdr_v1_hash_tunnel *hdr;
> -	int num_sg;
>  	unsigned hdr_len = vi->hdr_len;
> +	bool hdrlen_negotiated;
>  	bool can_push;
> +	int num_sg;
> +
> +	hdrlen_negotiated = virtio_has_feature(vi->vdev,
> +					       VIRTIO_NET_F_GUEST_HDRLEN);
>  
>  	pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
>  
> @@ -3339,7 +3343,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan)
>  		hdr = &skb_vnet_common_hdr(skb)->tnl_hdr;
>  
>  	if (virtio_net_hdr_tnl_from_skb(skb, hdr, vi->tx_tnl,
> -					virtio_is_little_endian(vi->vdev), 0))
> +					virtio_is_little_endian(vi->vdev),
> +					hdrlen_negotiated, 0))
>  		return -EPROTO;
>  
>  	if (vi->mergeable_rx_bufs)
> diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
> index b673c31569f3..3cd8b2ebc197 100644
> --- a/include/linux/virtio_net.h
> +++ b/include/linux/virtio_net.h
> @@ -211,16 +211,15 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
>  					  struct virtio_net_hdr *hdr,
>  					  bool little_endian,
>  					  bool has_data_valid,
> +					  bool hdrlen_negotiated,
>  					  int vlan_hlen)

Took me a while to figure out why does tun pass false here.

The reason is that this flag is really only dealing with guest
hdrlen.  so how about guest_hdrlen to mirror spec
or if you like xmit_hdrlen?





>  {
>  	memset(hdr, 0, sizeof(*hdr));   /* no info leak */
>  
>  	if (skb_is_gso(skb)) {
>  		struct skb_shared_info *sinfo = skb_shinfo(skb);
> +		u16 hdr_len;
>  
> -		/* This is a hint as to how much should be linear. */
> -		hdr->hdr_len = __cpu_to_virtio16(little_endian,
> -						 skb_headlen(skb));
>  		hdr->gso_size = __cpu_to_virtio16(little_endian,
>  						  sinfo->gso_size);
>  		if (sinfo->gso_type & SKB_GSO_TCPV4)
> @@ -231,6 +230,21 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
>  			hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP_L4;
>  		else
>  			return -EINVAL;
> +
> +		if (hdrlen_negotiated) {
> +			hdr_len = skb_transport_offset(skb);
> +
> +			if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4)
> +				hdr_len += sizeof(struct udphdr);
> +			else
> +				hdr_len += tcp_hdrlen(skb);
> +		} else {
> +			/* This is a hint as to how much should be linear. */
> +			hdr_len = skb_headlen(skb);
> +		}
> +
> +		hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len);
> +
>  		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
>  			hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
>  	} else
> @@ -384,6 +398,7 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
>  			    struct virtio_net_hdr_v1_hash_tunnel *vhdr,
>  			    bool tnl_hdr_negotiated,
>  			    bool little_endian,
> +			    bool hdrlen_negotiated,
>  			    int vlan_hlen)
>  {
>  	struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr;
> @@ -395,7 +410,7 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
>  						    SKB_GSO_UDP_TUNNEL_CSUM);
>  	if (!tnl_gso_type)
>  		return virtio_net_hdr_from_skb(skb, hdr, little_endian, false,
> -					       vlan_hlen);
> +					       hdrlen_negotiated, vlan_hlen);
>  
>  	/* Tunnel support not negotiated but skb ask for it. */
>  	if (!tnl_hdr_negotiated)
> @@ -408,7 +423,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
>  
>  	/* Let the basic parsing deal with plain GSO features. */
>  	skb_shinfo(skb)->gso_type &= ~tnl_gso_type;
> -	ret = virtio_net_hdr_from_skb(skb, hdr, true, false, vlan_hlen);
> +	ret = virtio_net_hdr_from_skb(skb, hdr, true, false, hdrlen_negotiated,
> +				      vlan_hlen);
>  	skb_shinfo(skb)->gso_type |= tnl_gso_type;
>  	if (ret)
>  		return ret;
> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
> index 173e6edda08f..6982f4ab1c73 100644
> --- a/net/packet/af_packet.c
> +++ b/net/packet/af_packet.c
> @@ -2093,7 +2093,8 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb,
>  		return -EINVAL;
>  	*len -= vnet_hdr_sz;
>  
> -	if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)&vnet_hdr, vio_le(), true, 0))
> +	if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)&vnet_hdr,
> +				    vio_le(), true, false, 0))
>  		return -EINVAL;
>  
>  	return memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_sz);
> @@ -2361,7 +2362,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
>  	if (vnet_hdr_sz &&
>  	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
>  				    sizeof(struct virtio_net_hdr),
> -				    vio_le(), true, 0)) {
> +				    vio_le(), true, false, 0)) {
>  		if (po->tp_version == TPACKET_V3)
>  			prb_clear_blk_fill_status(&po->rx_ring);
>  		goto drop_n_account;
> -- 
> 2.32.0.3.g01195cf9f