On Mon, Nov 03, 2025 at 11:16:12AM +0100, Stefano Brivio wrote:
> For both TCP and UDP, we request vhost-user buffers that are large
> enough to reach ETH_ZLEN (60 bytes), so padding is just a matter of
> increasing the appropriate iov_len and clearing bytes in the buffer
> as needed.
> 
> Link: https://bugs.passt.top/show_bug.cgi?id=166
> Signed-off-by: Stefano Brivio <sbrivio@redhat.com>

I think this is correct, apart from the nasty bug Laurent spotted.

I'm less certain if this is the most natural way to do it.

> ---
>  tcp.c          |  2 --
>  tcp_internal.h |  1 +
>  tcp_vu.c       | 27 +++++++++++++++++++++++++++
>  udp_vu.c       | 11 ++++++++++-
>  4 files changed, 38 insertions(+), 3 deletions(-)
> 
> diff --git a/tcp.c b/tcp.c
> index e91c0cf..039688d 100644
> --- a/tcp.c
> +++ b/tcp.c
> @@ -335,8 +335,6 @@ enum {
>  };
>  #endif
>  
> -/* MSS rounding: see SET_MSS() */
> -#define MSS_DEFAULT			536
>  #define WINDOW_DEFAULT			14600		/* RFC 6928 */
>  
>  #define ACK_INTERVAL			10		/* ms */
> diff --git a/tcp_internal.h b/tcp_internal.h
> index 5f8fb35..d2295c9 100644
> --- a/tcp_internal.h
> +++ b/tcp_internal.h
> @@ -12,6 +12,7 @@
>  #define BUF_DISCARD_SIZE	(1 << 20)
>  #define DISCARD_IOV_NUM		DIV_ROUND_UP(MAX_WINDOW, BUF_DISCARD_SIZE)
>  
> +#define MSS_DEFAULT /* and minimum */	536 /* as it comes from minimum MTU */
>  #define MSS4				ROUND_DOWN(IP_MAX_MTU -		   \
>  						   sizeof(struct tcphdr) - \
>  						   sizeof(struct iphdr),   \
> diff --git a/tcp_vu.c b/tcp_vu.c
> index 1c81ce3..7239401 100644
> --- a/tcp_vu.c
> +++ b/tcp_vu.c
> @@ -60,6 +60,29 @@ static size_t tcp_vu_hdrlen(bool v6)
>  	return hdrlen;
>  }
>  
> +/**
> + * tcp_vu_pad() - Pad 802.3 frame to minimum length (60 bytes) if needed
> + * @iov:	iovec array storing 802.3 frame with TCP segment inside
> + * @cnt:	Number of entries in @iov
> + */
> +static void tcp_vu_pad(struct iovec *iov, size_t cnt)
> +{
> +	size_t l2len, pad;
> +
> +	ASSERT(iov_size(iov, cnt) >= sizeof(struct virtio_net_hdr_mrg_rxbuf));
> +	l2len = iov_size(iov, cnt) - sizeof(struct virtio_net_hdr_mrg_rxbuf);

Re-obtaining l2len from iov_size() seems kind of awkward, since the
callers should already know the length - they've just used it to
populate iov_len.

> +	if (l2len >= ETH_ZLEN)
> +		return;


> +
> +	pad = ETH_ZLEN - l2len;
> +
> +	/* tcp_vu_sock_recv() requests at least MSS-sized vhost-user buffers */
> +	static_assert(ETH_ZLEN <= MSS_DEFAULT);

So, this is true for the data path, but not AFAICT for the flags path.

There _is_ still enough space in this case, because we request space
for (tcp_vu_hdrlen() + sizeof(struct tcp_syn_opts)) which works out to:
	  ETH_HLEN	14
	+ IP header	20
	+ TCP header	20
	+ tcp_syn_opts	 8
	              ----
			62  > ETH_ZLEN

But the comment and assert are misleading.

It seems like it would make more sense to clamp ETH_ZLEN as a lower
length bound before we vu_collect() the buffers.

Or indeed, like we should be calculating l2len already including the
clamping.


> +
> +	memset(&iov[cnt - 1].iov_base + iov[cnt - 1].iov_len, 0, pad);
> +	iov[cnt - 1].iov_len += pad;
> +}
> +
>  /**
>   * tcp_vu_send_flag() - Send segment with flags to vhost-user (no payload)
>   * @c:		Execution context
> @@ -138,6 +161,8 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
>  	tcp_fill_headers(c, conn, NULL, eh, ip4h, ip6h, th, &payload,
>  			 NULL, seq, !*c->pcap);
>  
> +	tcp_vu_pad(&flags_elem[0].in_sg[0], 1);
> +
>  	if (*c->pcap) {
>  		pcap_iov(&flags_elem[0].in_sg[0], 1,
>  			 sizeof(struct virtio_net_hdr_mrg_rxbuf));
> @@ -456,6 +481,8 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
>  
>  		tcp_vu_prepare(c, conn, iov, buf_cnt, &check, !*c->pcap, push);
>  
> +		tcp_vu_pad(iov, buf_cnt);
> +
>  		if (*c->pcap) {
>  			pcap_iov(iov, buf_cnt,
>  				 sizeof(struct virtio_net_hdr_mrg_rxbuf));
> diff --git a/udp_vu.c b/udp_vu.c
> index 099677f..1b60860 100644
> --- a/udp_vu.c
> +++ b/udp_vu.c
> @@ -72,8 +72,8 @@ static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s,
>  {
>  	const struct vu_dev *vdev = c->vdev;
>  	int iov_cnt, idx, iov_used;
> +	size_t off, hdrlen, l2len;
>  	struct msghdr msg  = { 0 };
> -	size_t off, hdrlen;
>  
>  	ASSERT(!c->no_udp);
>  
> @@ -116,6 +116,15 @@ static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s,
>  		iov_vu[idx].iov_len = off;
>  	iov_used = idx + !!off;
>  
> +	/* pad 802.3 frame to 60 bytes if needed */
> +	l2len = *dlen + hdrlen - sizeof(struct virtio_net_hdr_mrg_rxbuf);
> +	if (l2len < ETH_ZLEN) {
> +		size_t pad = ETH_ZLEN - l2len;
> +
> +		iov_vu[idx].iov_len += pad;
> +		memset(&iov_vu[idx].iov_base + off, 0, pad);
> +	}
> +
>  	vu_set_vnethdr(vdev, iov_vu[0].iov_base, iov_used);
>  
>  	/* release unused buffers */
> -- 
> 2.43.0
> 

-- 
David Gibson (he or they)	| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you, not the other way
				| around.
http://www.ozlabs.org/~dgibson