From: Laurent Vivier <lvivier@redhat.com>
To: passt-dev@passt.top
Cc: Laurent Vivier <lvivier@redhat.com>
Subject: [PATCH 3/3] vu_common: Move iovec management into vu_collect()
Date: Fri, 13 Mar 2026 08:21:36 +0100 [thread overview]
Message-ID: <20260313072136.4075535-4-lvivier@redhat.com> (raw)
In-Reply-To: <20260313072136.4075535-1-lvivier@redhat.com>
Previously, callers had to pre-initialize virtqueue elements with iovec
entries using vu_set_element() or vu_init_elem() before calling
vu_collect(). This meant each element owned a fixed, pre-assigned iovec
slot.
Move the iovec array into vu_collect() as explicit parameters (in_sg,
max_in_sg, and in_num), letting it pass the remaining iovec capacity
directly to vu_queue_pop(). A running current_iov counter tracks
consumed entries across elements, so multiple elements share a single
iovec pool. The optional in_num output parameter reports how many iovec
entries were consumed, allowing callers to track usage across multiple
vu_collect() calls.
This removes vu_set_element() and vu_init_elem() which are no longer
needed, and is a prerequisite for multi-buffer support where a single
virtqueue element can use more than one iovec entry. For now, callers
assert the current single-iovec-per-element invariant until they are
updated to handle multiple iovecs.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
tcp_vu.c | 23 ++++++++++--------
udp_vu.c | 21 ++++++++++-------
vu_common.c | 68 ++++++++++++++++++++++++-----------------------------
vu_common.h | 22 +++--------------
4 files changed, 59 insertions(+), 75 deletions(-)
diff --git a/tcp_vu.c b/tcp_vu.c
index fd734e857b3b..ff826e53355f 100644
--- a/tcp_vu.c
+++ b/tcp_vu.c
@@ -87,13 +87,13 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
hdrlen = tcp_vu_hdrlen(CONN_V6(conn));
- vu_set_element(&flags_elem[0], NULL, &flags_iov[0]);
-
elem_cnt = vu_collect(vdev, vq, &flags_elem[0], 1,
+ &flags_iov[0], 1, NULL,
MAX(hdrlen + sizeof(*opts), ETH_ZLEN + VNET_HLEN), NULL);
if (elem_cnt != 1)
return -1;
+ ASSERT(flags_elem[0].in_num == 1);
ASSERT(flags_elem[0].in_sg[0].iov_len >=
MAX(hdrlen + sizeof(*opts), ETH_ZLEN + VNET_HLEN));
@@ -148,9 +148,8 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
nb_ack = 1;
if (flags & DUP_ACK) {
- vu_set_element(&flags_elem[1], NULL, &flags_iov[1]);
-
elem_cnt = vu_collect(vdev, vq, &flags_elem[1], 1,
+ &flags_iov[1], 1, NULL,
flags_elem[0].in_sg[0].iov_len, NULL);
if (elem_cnt == 1 &&
flags_elem[1].in_sg[0].iov_len >=
@@ -191,8 +190,8 @@ static ssize_t tcp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq,
const struct vu_dev *vdev = c->vdev;
struct msghdr mh_sock = { 0 };
uint16_t mss = MSS_GET(conn);
+ size_t hdrlen, iov_used;
int s = conn->sock;
- size_t hdrlen;
int elem_cnt;
ssize_t ret;
int i;
@@ -201,22 +200,26 @@ static ssize_t tcp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq,
hdrlen = tcp_vu_hdrlen(v6);
- vu_init_elem(elem, &iov_vu[DISCARD_IOV_NUM], VIRTQUEUE_MAX_SIZE);
-
+ iov_used = 0;
elem_cnt = 0;
*head_cnt = 0;
- while (fillsize > 0 && elem_cnt < VIRTQUEUE_MAX_SIZE) {
+ while (fillsize > 0 && elem_cnt < ARRAY_SIZE(elem) &&
+ iov_used < VIRTQUEUE_MAX_SIZE) {
+ size_t frame_size, dlen, in_num;
struct iovec *iov;
- size_t frame_size, dlen;
int cnt;
cnt = vu_collect(vdev, vq, &elem[elem_cnt],
- VIRTQUEUE_MAX_SIZE - elem_cnt,
+ ARRAY_SIZE(elem) - elem_cnt,
+ &iov_vu[DISCARD_IOV_NUM + iov_used],
+ VIRTQUEUE_MAX_SIZE - iov_used, &in_num,
MAX(MIN(mss, fillsize) + hdrlen, ETH_ZLEN + VNET_HLEN),
&frame_size);
if (cnt == 0)
break;
+ ASSERT((size_t)cnt == in_num); /* one iovec per element */
+ iov_used += in_num;
dlen = frame_size - hdrlen;
/* reserve space for headers in iov */
diff --git a/udp_vu.c b/udp_vu.c
index 5effca777e0a..acc18d375a0f 100644
--- a/udp_vu.c
+++ b/udp_vu.c
@@ -71,9 +71,10 @@ static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s,
bool v6, ssize_t *dlen)
{
const struct vu_dev *vdev = c->vdev;
+ int elem_cnt, elem_used, iov_used;
struct msghdr msg = { 0 };
- int iov_cnt, iov_used;
size_t hdrlen, l2len;
+ size_t iov_cnt;
ASSERT(!c->no_udp);
@@ -89,13 +90,14 @@ static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s,
/* compute L2 header length */
hdrlen = udp_vu_hdrlen(v6);
- vu_init_elem(elem, iov_vu, VIRTQUEUE_MAX_SIZE);
-
- iov_cnt = vu_collect(vdev, vq, elem, VIRTQUEUE_MAX_SIZE,
- IP_MAX_MTU + ETH_HLEN + VNET_HLEN, NULL);
- if (iov_cnt == 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)
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;
@@ -107,7 +109,7 @@ static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s,
*dlen = recvmsg(s, &msg, 0);
if (*dlen < 0) {
- vu_queue_rewind(vq, iov_cnt);
+ vu_queue_rewind(vq, elem_cnt);
return -1;
}
@@ -116,15 +118,16 @@ static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s,
iov_vu[0].iov_len += hdrlen;
iov_used = iov_truncate(iov_vu, iov_cnt, *dlen + hdrlen);
+ elem_used = iov_used; /* one iovec per element */
/* pad frame to 60 bytes: first buffer is at least ETH_ZLEN long */
l2len = *dlen + hdrlen - VNET_HLEN;
vu_pad(&iov_vu[0], l2len);
- vu_set_vnethdr(iov_vu[0].iov_base, iov_used);
+ vu_set_vnethdr(iov_vu[0].iov_base, elem_used);
/* release unused buffers */
- vu_queue_rewind(vq, iov_cnt - iov_used);
+ vu_queue_rewind(vq, elem_cnt - elem_used);
return iov_used;
}
diff --git a/vu_common.c b/vu_common.c
index ed0033d6bb11..d5fca9e52004 100644
--- a/vu_common.c
+++ b/vu_common.c
@@ -51,28 +51,15 @@ int vu_packet_check_range(struct vdev_memory *memory,
return -1;
}
-/**
- * vu_init_elem() - initialize an array of virtqueue elements with 1 iov in each
- * @elem: Array of virtqueue elements to initialize
- * @iov: Array of iovec to assign to virtqueue element
- * @elem_cnt: Number of virtqueue element
- */
-void vu_init_elem(struct vu_virtq_element *elem, struct iovec *iov, int elem_cnt)
-{
- int i;
-
- for (i = 0; i < elem_cnt; i++)
- vu_set_element(&elem[i], NULL, &iov[i]);
-}
-
/**
* vu_collect() - collect virtio buffers from a given virtqueue
* @vdev: vhost-user device
* @vq: virtqueue to collect from
- * @elem: Array of virtqueue element
- * each element must be initialized with one iovec entry
- * in the in_sg array.
+ * @elem: Array of @max_elem virtqueue elements
* @max_elem: Number of virtqueue elements in the array
+ * @in_sg: Incoming iovec array for device-writable descriptors
+ * @max_in_sg: Maximum number of entries in @in_sg
+ * @in_num: Number of collected entries from @in_sg (output)
* @size: Maximum size of the data in the frame
* @collected: Collected buffer length, up to @size, set on return
*
@@ -80,20 +67,21 @@ void vu_init_elem(struct vu_virtq_element *elem, struct iovec *iov, int elem_cnt
*/
int vu_collect(const struct vu_dev *vdev, struct vu_virtq *vq,
struct vu_virtq_element *elem, int max_elem,
+ struct iovec *in_sg, size_t max_in_sg, size_t *in_num,
size_t size, size_t *collected)
{
size_t current_size = 0;
+ size_t current_iov = 0;
int elem_cnt = 0;
- while (current_size < size && elem_cnt < max_elem) {
- struct iovec *iov;
+ while (current_size < size && elem_cnt < max_elem &&
+ current_iov < max_in_sg) {
int ret;
ret = vu_queue_pop(vdev, vq, &elem[elem_cnt],
- elem[elem_cnt].in_sg,
- elem[elem_cnt].in_num,
- elem[elem_cnt].out_sg,
- elem[elem_cnt].out_num);
+ &in_sg[current_iov],
+ max_in_sg - current_iov,
+ NULL, 0);
if (ret < 0)
break;
@@ -103,18 +91,22 @@ int vu_collect(const struct vu_dev *vdev, struct vu_virtq *vq,
break;
}
- iov = &elem[elem_cnt].in_sg[0];
-
- if (iov->iov_len > size - current_size)
- iov->iov_len = size - current_size;
+ elem[elem_cnt].in_num = iov_truncate(elem[elem_cnt].in_sg,
+ elem[elem_cnt].in_num,
+ size - current_size);
- current_size += iov->iov_len;
+ current_size += iov_size(elem[elem_cnt].in_sg,
+ elem[elem_cnt].in_num);
+ current_iov += elem[elem_cnt].in_num;
elem_cnt++;
if (!vu_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
break;
}
+ if (in_num)
+ *in_num = current_iov;
+
if (collected)
*collected = current_size;
@@ -147,8 +139,11 @@ void vu_flush(const struct vu_dev *vdev, struct vu_virtq *vq,
{
int i;
- for (i = 0; i < elem_cnt; i++)
- vu_queue_fill(vdev, vq, &elem[i], elem[i].in_sg[0].iov_len, i);
+ for (i = 0; i < elem_cnt; i++) {
+ size_t elem_size = iov_size(elem[i].in_sg, elem[i].in_num);
+
+ vu_queue_fill(vdev, vq, &elem[i], elem_size, i);
+ }
vu_queue_flush(vdev, vq, elem_cnt);
vu_queue_notify(vdev, vq);
@@ -246,7 +241,7 @@ int vu_send_single(const struct ctx *c, const void *buf, size_t size)
struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
struct vu_virtq_element elem[VIRTQUEUE_MAX_SIZE];
struct iovec in_sg[VIRTQUEUE_MAX_SIZE];
- size_t total;
+ size_t total, in_num;
int elem_cnt;
int i;
@@ -257,11 +252,10 @@ int vu_send_single(const struct ctx *c, const void *buf, size_t size)
return -1;
}
- vu_init_elem(elem, in_sg, VIRTQUEUE_MAX_SIZE);
-
size += VNET_HLEN;
- elem_cnt = vu_collect(vdev, vq, elem, VIRTQUEUE_MAX_SIZE, size, &total);
- if (total < size) {
+ elem_cnt = vu_collect(vdev, vq, elem, ARRAY_SIZE(elem), in_sg,
+ ARRAY_SIZE(in_sg), &in_num, size, &total);
+ if (elem_cnt == 0 || total < size) {
debug("vu_send_single: no space to send the data "
"elem_cnt %d size %zd", elem_cnt, total);
goto err;
@@ -272,10 +266,10 @@ int vu_send_single(const struct ctx *c, const void *buf, size_t size)
total -= VNET_HLEN;
/* copy data from the buffer to the iovec */
- iov_from_buf(in_sg, elem_cnt, VNET_HLEN, buf, total);
+ iov_from_buf(in_sg, in_num, VNET_HLEN, buf, total);
if (*c->pcap)
- pcap_iov(in_sg, elem_cnt, VNET_HLEN);
+ pcap_iov(in_sg, in_num, VNET_HLEN);
vu_flush(vdev, vq, elem, elem_cnt);
diff --git a/vu_common.h b/vu_common.h
index 865d9771fa89..6c31630e8712 100644
--- a/vu_common.h
+++ b/vu_common.h
@@ -35,26 +35,10 @@ static inline void *vu_payloadv6(void *base)
return (struct ipv6hdr *)vu_ip(base) + 1;
}
-/**
- * vu_set_element() - Initialize a vu_virtq_element
- * @elem: Element to initialize
- * @out_sg: One out iovec entry to set in elem
- * @in_sg: One in iovec entry to set in elem
- */
-static inline void vu_set_element(struct vu_virtq_element *elem,
- struct iovec *out_sg, struct iovec *in_sg)
-{
- elem->out_num = !!out_sg;
- elem->out_sg = out_sg;
- elem->in_num = !!in_sg;
- elem->in_sg = in_sg;
-}
-
-void vu_init_elem(struct vu_virtq_element *elem, struct iovec *iov,
- int elem_cnt);
int vu_collect(const struct vu_dev *vdev, struct vu_virtq *vq,
- struct vu_virtq_element *elem, int max_elem, size_t size,
- size_t *collected);
+ struct vu_virtq_element *elem, int max_elem,
+ struct iovec *in_sg, size_t max_in_sg, size_t *in_num,
+ size_t size, size_t *collected);
void vu_set_vnethdr(struct virtio_net_hdr_mrg_rxbuf *vnethdr, int num_buffers);
void vu_flush(const struct vu_dev *vdev, struct vu_virtq *vq,
struct vu_virtq_element *elem, int elem_cnt);
--
2.53.0
prev parent reply other threads:[~2026-03-13 7:21 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-13 7:21 [PATCH 0/3] Decouple iovec management from virtqueue elements Laurent Vivier
2026-03-13 7:21 ` [PATCH 1/3] virtio: Pass iovec arrays as separate parameters to vu_queue_pop() Laurent Vivier
2026-03-13 7:21 ` [PATCH 2/3] vu_handle_tx: Pass actual remaining out_sg capacity " Laurent Vivier
2026-03-13 7:21 ` Laurent Vivier [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260313072136.4075535-4-lvivier@redhat.com \
--to=lvivier@redhat.com \
--cc=passt-dev@passt.top \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://passt.top/passt
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for IMAP folder(s).