Re: [PATCH v2 04/10] udp_vu: Move virtqueue management from udp_vu_sock_recv() to its caller

[David Gibson <david@gibson.dropbear.id.au>]

[-- Attachment #1: Type: text/plain, Size: 6321 bytes --]

On Fri, Apr 03, 2026 at 06:38:05PM +0200, Laurent Vivier wrote:
> udp_vu_sock_recv() currently mixes two concerns: receiving data from the
> socket and managing virtqueue buffers (collecting, rewinding, releasing).
> This makes the function harder to reason about and couples socket I/O
> with virtqueue state.
> 
> Move all virtqueue operations, vu_collect(), vu_init_elem(),
> vu_queue_rewind(), vu_set_vnethdr(), and the queue-readiness check, into
> udp_vu_sock_to_tap(), which is the only caller.  This turns
> udp_vu_sock_recv() into a pure socket receive function that simply reads
> into the provided iov array and adjusts its length.
> 
> Signed-off-by: Laurent Vivier <lvivier@redhat.com>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

Minor clarity note, only worth addressing if you respin anyway.

> ---
>  udp_vu.c | 97 ++++++++++++++++++++++++++++----------------------------
>  1 file changed, 49 insertions(+), 48 deletions(-)
> 
> diff --git a/udp_vu.c b/udp_vu.c
> index f8629af58ab5..34f39e1256f8 100644
> --- a/udp_vu.c
> +++ b/udp_vu.c
> @@ -58,46 +58,22 @@ static size_t udp_vu_hdrlen(bool v6)
>  
>  /**
>   * udp_vu_sock_recv() - Receive datagrams from socket into vhost-user buffers
> - * @c:		Execution context
> - * @vq:		virtqueue to use to receive data
>   * @s:		Socket to receive from
>   * @v6:		Set for IPv6 connections
> - * @dlen:	Size of received data (output)
> + * @iov_cnt:	Number of collected iov in iov_vu (input)
> + * 		Number of iov entries used to store the datagram (output)

Nit: might be worth clarifying that *@iov_cnt is unchanged on failure.

>   *
> - * Return: number of iov entries used to store the datagram, 0 if the datagram
> - *         was discarded because the virtqueue is not ready, -1 on error
> + * Return: size of received data, -1 on error
>   */
> -static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s,
> -			    bool v6, ssize_t *dlen)
> +static ssize_t udp_vu_sock_recv(int s, bool v6, size_t *iov_cnt)
>  {
> -	const struct vu_dev *vdev = c->vdev;
> -	int elem_cnt, elem_used, iov_used;
>  	struct msghdr msg  = { 0 };
>  	size_t hdrlen, l2len;
> -	size_t iov_cnt;
> -
> -	assert(!c->no_udp);
> -
> -	if (!vu_queue_enabled(vq) || !vu_queue_started(vq)) {
> -		debug("Got UDP packet, but RX virtqueue not usable yet");
> -
> -		if (recvmsg(s, &msg, MSG_DONTWAIT) < 0)
> -			debug_perror("Failed to discard datagram");
> -
> -		return 0;
> -	}
> +	ssize_t dlen;
>  
>  	/* compute L2 header length */
>  	hdrlen = udp_vu_hdrlen(v6);
>  
> -	elem_cnt = vu_collect(vdev, vq, elem, ARRAY_SIZE(elem),
> -			      iov_vu, ARRAY_SIZE(iov_vu), &iov_cnt,
> -			      IP_MAX_MTU + ETH_HLEN + VNET_HLEN, NULL);
> -	if (elem_cnt == 0)
> -		return -1;
> -
> -	assert((size_t)elem_cnt == iov_cnt);	/* one iovec per element */
> -
>  	/* reserve space for the headers */
>  	assert(iov_vu[0].iov_len >= MAX(hdrlen, ETH_ZLEN + VNET_HLEN));
>  	iov_vu[0].iov_base = (char *)iov_vu[0].iov_base + hdrlen;
> @@ -105,29 +81,23 @@ static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s,
>  
>  	/* read data from the socket */
>  	msg.msg_iov = iov_vu;
> -	msg.msg_iovlen = iov_cnt;
> +	msg.msg_iovlen = *iov_cnt;
>  
> -	*dlen = recvmsg(s, &msg, 0);
> -	if (*dlen < 0) {
> -		vu_queue_rewind(vq, elem_cnt);
> +	dlen = recvmsg(s, &msg, 0);
> +	if (dlen < 0)
>  		return -1;
> -	}
>  
>  	/* restore the pointer to the headers address */
>  	iov_vu[0].iov_base = (char *)iov_vu[0].iov_base - hdrlen;
>  	iov_vu[0].iov_len += hdrlen;
>  
> -	iov_used = iov_truncate(iov_vu, iov_cnt, *dlen + hdrlen);
> -	elem_used = iov_used; /* one iovec per element */
> +	*iov_cnt = iov_truncate(iov_vu, *iov_cnt, dlen + hdrlen);
>  
>  	/* pad frame to 60 bytes: first buffer is at least ETH_ZLEN long */
> -	l2len = *dlen + hdrlen - VNET_HLEN;
> +	l2len = dlen + hdrlen - VNET_HLEN;
>  	vu_pad(&iov_vu[0], l2len);
>  
> -	/* release unused buffers */
> -	vu_queue_rewind(vq, elem_cnt - elem_used);
> -
> -	return iov_used;
> +	return dlen;
>  }
>  
>  /**
> @@ -213,21 +183,52 @@ void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx)
>  	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
>  	int i;
>  
> +	assert(!c->no_udp);
> +
> +	if (!vu_queue_enabled(vq) || !vu_queue_started(vq)) {
> +		struct msghdr msg = { 0 };
> +
> +		debug("Got UDP packet, but RX virtqueue not usable yet");
> +
> +		for (i = 0; i < n; i++) {
> +			if (recvmsg(s, &msg, MSG_DONTWAIT) < 0)
> +				debug_perror("Failed to discard datagram");
> +		}
> +
> +		return;
> +	}
> +
>  	for (i = 0; i < n; i++) {
> +		unsigned elem_cnt, elem_used;
> +		size_t iov_cnt;
>  		ssize_t dlen;
> -		int iov_used;
>  
> -		iov_used = udp_vu_sock_recv(c, vq, s, v6, &dlen);
> -		if (iov_used < 0)
> +		elem_cnt = vu_collect(vdev, vq, elem, ARRAY_SIZE(elem),
> +				      iov_vu, ARRAY_SIZE(iov_vu), &iov_cnt,
> +				      IP_MAX_MTU + ETH_HLEN + VNET_HLEN, NULL);
> +		if (elem_cnt == 0)
> +			break;
> +
> +		assert((size_t)elem_cnt == iov_cnt);	/* one iovec per element */
> +
> +		dlen = udp_vu_sock_recv(s, v6, &iov_cnt);
> +		if (dlen < 0) {
> +			vu_queue_rewind(vq, iov_cnt);
>  			break;
> +		}
> +
> +		elem_used = iov_cnt; /* one iovec per element */
> +
> +		/* release unused buffers */
> +		vu_queue_rewind(vq, elem_cnt - elem_used);

Specifically, working out why the vu_queue_rewind() is correct on both
the success and failure paths requires thinking about what iov_cnt is
when udp_vu_sock_recv() fails.

>  
> -		if (iov_used > 0) {
> +		if (iov_cnt > 0) {
>  			udp_vu_prepare(c, toside, dlen);
>  			if (*c->pcap) {
> -				udp_vu_csum(toside, iov_used);
> -				pcap_iov(iov_vu, iov_used, VNET_HLEN);
> +				udp_vu_csum(toside, iov_cnt);
> +				pcap_iov(iov_vu, iov_cnt, VNET_HLEN);
>  			}
> -			vu_flush(vdev, vq, elem, iov_used);
> +			vu_flush(vdev, vq, elem, iov_cnt);
>  			vu_queue_notify(vdev, vq);
>  		}
>  	}
> -- 
> 2.53.0
> 

-- 
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

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]