[PATCH v7 2/4] tcp_vu: Build headers on the stack and write them into the iovec

Laurent Vivier

20 May 2026 20 May '26

5:18 p.m.

tcp_vu_prepare() currently assumes the first iovec element provided by the guest is large enough to hold all L2-L4 headers, and builds them in place via pointer casts into iov[0].iov_base. This assumption is enforced by an assert(). Since the headers in the buffer are uninitialized anyway, we can just as well build the Ethernet, IP, and TCP headers on the stack instead, and write them into the iovec with IOV_PUSH_HEADER(). This mirrors the approach already used in udp_vu_prepare(), and prepares for support of elements with multiple iovecs. Signed-off-by: Laurent Vivier Reviewed-by: Jon Maloy Reviewed-by: David Gibson --- tcp_vu.c | 64 +++++++++++++++++++++++++------------------------------- 1 file changed, 28 insertions(+), 36 deletions(-) diff --git a/tcp_vu.c b/tcp_vu.c index 65e7dfe63437..c13c45f71f3b 100644 --- a/tcp_vu.c +++ b/tcp_vu.c @@ -298,49 +298,41 @@ static void tcp_vu_prepare(const struct ctx *c, struct tcp_tap_conn *conn, bool v6 = !(inany_v4(&toside->eaddr) && inany_v4(&toside->oaddr)); size_t hdrlen = tcp_vu_hdrlen(v6); struct iov_tail payload = IOV_TAIL(iov, iov_cnt, hdrlen); - char *base = iov[0].iov_base; - struct ipv6hdr *ip6h = NULL; - struct iphdr *ip4h = NULL; - struct tcphdr *th; - struct ethhdr *eh; - - /* we guess the first iovec provided by the guest can embed - * all the headers needed by L2 frame, including any padding - */ - assert(iov[0].iov_len >= hdrlen); - - eh = vu_eth(base); - - memcpy(eh->h_dest, c->guest_mac, sizeof(eh->h_dest)); + struct tcphdr th = { + .doff = sizeof(th) / 4, + .ack = 1, + .psh = push, + }; + struct iov_tail l2frame; + struct ipv6hdr ip6h; + struct iphdr ip4h; + struct ethhdr eh; + + memcpy(eh.h_dest, c->guest_mac, sizeof(eh.h_dest)); /* initialize header */ - if (!v6) { - eh->h_proto = htons(ETH_P_IP); - - ip4h = vu_ip(base); - *ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); - th = vu_payloadv4(base); - } else { - eh->h_proto = htons(ETH_P_IPV6); - - ip6h = vu_ip(base); - *ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP); + if (!v6) + ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); + else + ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP); - th = vu_payloadv6(base); - } + tcp_fill_headers(c, conn, &eh, v6 ? NULL : &ip4h, v6 ? &ip6h : NULL, &th, + &payload, dlen, *csum_flags, conn->seq_to_tap); - memset(th, 0, sizeof(*th)); - th->doff = sizeof(*th) / 4; - th->ack = 1; - th->psh = push; + /* Preserve TCP_CSUM, overwrite IP4_CSUM as we set the checksum */ + if (!v6) + *csum_flags = (*csum_flags & TCP_CSUM) | ip4h.check; - tcp_fill_headers(c, conn, eh, ip4h, ip6h, th, &payload, dlen, - *csum_flags, conn->seq_to_tap); + /* write headers */ + l2frame = IOV_TAIL(iov, iov_cnt, VNET_HLEN); - /* Preserve TCP_CSUM, overwrite IP4_CSUM as we set the checksum */ - if (ip4h) - *csum_flags = (*csum_flags & TCP_CSUM) | ip4h->check; + IOV_PUSH_HEADER(&l2frame, eh); + if (!v6) + IOV_PUSH_HEADER(&l2frame, ip4h); + else + IOV_PUSH_HEADER(&l2frame, ip6h); + IOV_PUSH_HEADER(&l2frame, th); } /** -- 2.54.0

Show replies by date

Laurent Vivier

20 May 20 May

5:18 p.m.

New subject: [PATCH v7 3/4] tcp_vu: Support multibuffer frames in tcp_vu_sock_recv()

Previously, tcp_vu_sock_recv() assumed a 1:1 mapping between virtqueue elements and iovecs (one iovec per element), enforced by an ASSERT. This prevented the use of virtqueue elements with multiple buffers (e.g. when mergeable rx buffers are not negotiated and headers are provided in a separate buffer). Introduce a struct vu_frame to track per-frame metadata: the range of elements and iovecs that make up each frame, and the frame's total size. This replaces the head[] array which only tracked element indices. A separate iov_msg[] array is built for recvmsg() by cloning the data portions (after stripping headers) using iov_tail helpers. Then a frame truncation after recvmsg() properly walks the frame and element arrays to adjust iovec counts and element counts. Signed-off-by: Laurent Vivier --- tcp_vu.c | 173 +++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 112 insertions(+), 61 deletions(-) diff --git a/tcp_vu.c b/tcp_vu.c index c13c45f71f3b..55242ec40410 100644 --- a/tcp_vu.c +++ b/tcp_vu.c @@ -35,9 +35,24 @@ #include "vu_common.h" #include -static struct iovec iov_vu[VIRTQUEUE_MAX_SIZE + DISCARD_IOV_NUM]; +static struct iovec iov_vu[VIRTQUEUE_MAX_SIZE]; static struct vu_virtq_element elem[VIRTQUEUE_MAX_SIZE]; -static int head[VIRTQUEUE_MAX_SIZE + 1]; + +/** + * struct vu_frame - Descriptor for a TCP frame mapped to virtqueue elements + * @idx_element: Index of first element in elem[] for this frame + * @num_element: Number of virtqueue elements used by this frame + * @idx_iovec: Index of first iovec in iov_vu[] for this frame + * @num_iovec: Number of iovecs covering this frame's buffers + * @size: Total frame size including all headers + */ +static struct vu_frame { + int idx_element; + int num_element; + int idx_iovec; + int num_iovec; + size_t size; +} frame[VIRTQUEUE_MAX_SIZE]; /** * tcp_vu_hdrlen() - Sum size of all headers, from TCP to virtio-net @@ -176,8 +191,8 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags) * @v6: Set for IPv6 connections * @already_sent: Number of bytes already sent * @fillsize: Maximum bytes to fill in guest-side receiving window - * @iov_cnt: number of iov (output) - * @head_cnt: Pointer to store the count of head iov entries (output) + * @elem_used: number of element (output) + * @frame_cnt: Pointer to store the number of frames (output) * * Return: number of bytes received from the socket, or a negative error code * on failure. @@ -185,57 +200,78 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags) static ssize_t tcp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, const struct tcp_tap_conn *conn, bool v6, uint32_t already_sent, size_t fillsize, - int *iov_cnt, int *head_cnt) + int *elem_used, int *frame_cnt) { + static struct iovec iov_msg[VIRTQUEUE_MAX_SIZE + DISCARD_IOV_NUM]; 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; + ssize_t ret, dlen; int elem_cnt; - ssize_t ret; - int i; - - *iov_cnt = 0; + int i, j; hdrlen = tcp_vu_hdrlen(v6); + *elem_used = 0; + iov_used = 0; elem_cnt = 0; - *head_cnt = 0; + *frame_cnt = 0; while (fillsize > 0 && elem_cnt < ARRAY_SIZE(elem) && - iov_used < VIRTQUEUE_MAX_SIZE) { - size_t frame_size, dlen, in_total; - struct iovec *iov; + iov_used < ARRAY_SIZE(iov_vu) && + *frame_cnt < ARRAY_SIZE(frame)) { + size_t frame_size, in_total; int cnt; cnt = vu_collect(vdev, vq, &elem[elem_cnt], ARRAY_SIZE(elem) - elem_cnt, - &iov_vu[DISCARD_IOV_NUM + iov_used], - VIRTQUEUE_MAX_SIZE - iov_used, &in_total, + &iov_vu[iov_used], + ARRAY_SIZE(iov_vu) - iov_used, &in_total, MIN(mss, fillsize) + hdrlen, &frame_size); if (cnt == 0) break; - assert((size_t)cnt == in_total); /* one iovec per element */ + + frame[*frame_cnt].idx_element = elem_cnt; + frame[*frame_cnt].num_element = cnt; + frame[*frame_cnt].idx_iovec = iov_used; + frame[*frame_cnt].num_iovec = in_total; + frame[*frame_cnt].size = frame_size; + (*frame_cnt)++; iov_used += in_total; - dlen = frame_size - hdrlen; + elem_cnt += cnt; - /* reserve space for headers in iov */ - iov = &elem[elem_cnt].in_sg[0]; - assert(iov->iov_len >= hdrlen); - iov->iov_base = (char *)iov->iov_base + hdrlen; - iov->iov_len -= hdrlen; - head[(*head_cnt)++] = elem_cnt; + fillsize -= frame_size - hdrlen; + } - fillsize -= dlen; - elem_cnt += cnt; + /* build an iov array without headers */ + for (i = 0, j = DISCARD_IOV_NUM; i < *frame_cnt && + j < ARRAY_SIZE(iov_msg); i++) { + struct iov_tail data; + ssize_t cnt; + + data = IOV_TAIL(&iov_vu[frame[i].idx_iovec], + frame[i].num_iovec, 0); + iov_drop_header(&data, hdrlen); + + cnt = iov_tail_clone(&iov_msg[j], ARRAY_SIZE(iov_msg) - j, + &data); + assert(cnt < ARRAY_SIZE(iov_msg) - j); + if (cnt < 0) + die("Missing entries in iov_msg"); + + j += cnt; } - if (tcp_prepare_iov(&mh_sock, iov_vu, already_sent, elem_cnt)) + if (tcp_prepare_iov(&mh_sock, iov_msg, already_sent, + j - DISCARD_IOV_NUM)) { /* Expect caller to do a TCP reset */ + vu_queue_rewind(vq, elem_cnt); return -1; + } do ret = recvmsg(s, &mh_sock, MSG_PEEK); @@ -249,32 +285,49 @@ static ssize_t tcp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, if (!peek_offset_cap) ret -= already_sent; - i = iov_skip_bytes(&iov_vu[DISCARD_IOV_NUM], iov_used, - MAX(hdrlen + ret, VNET_HLEN + ETH_ZLEN), - NULL); - if ((size_t)i < iov_used) - i++; + dlen = ret; - /* adjust head count */ - while (*head_cnt > 0 && head[*head_cnt - 1] >= i) - (*head_cnt)--; + /* truncate frame */ + for (i = 0; i < *frame_cnt; i++) { + struct vu_frame *f = &frame[i]; - /* mark end of array */ - head[*head_cnt] = i; - *iov_cnt = i; + if ((size_t)ret <= f->size - hdrlen) { + unsigned cnt; - /* release unused buffers */ - vu_queue_rewind(vq, elem_cnt - i); + cnt = iov_skip_bytes(&iov_vu[f->idx_iovec], f->num_iovec, + MAX(hdrlen + ret, VNET_HLEN + ETH_ZLEN), + NULL); + if (cnt < (unsigned)f->num_iovec) + cnt++; + + f->size = ret + hdrlen; + f->num_iovec = cnt; - /* restore space for headers in iov */ - for (i = 0; i < *head_cnt; i++) { - struct iovec *iov = &elem[head[i]].in_sg[0]; + for (j = 0; j < f->num_element; j++) { + struct vu_virtq_element *e; - iov->iov_base = (char *)iov->iov_base - hdrlen; - iov->iov_len += hdrlen; + e = &elem[f->idx_element + j]; + if (cnt <= e->in_num) { + e->in_num = cnt; + j++; + break; + } + cnt -= e->in_num; + } + f->num_element = j; + *elem_used += j; + i++; + break; + } + *elem_used += f->num_element; + ret -= f->size - hdrlen; } + *frame_cnt = i; - return ret; + /* release unused buffers */ + vu_queue_rewind(vq, elem_cnt - *elem_used); + + return dlen; } /** @@ -350,7 +403,7 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn) struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE]; uint32_t already_sent, check; ssize_t len, previous_dlen; - int i, iov_cnt, head_cnt; + int i, elem_cnt, frame_cnt; size_t hdrlen, fillsize; int v6 = CONN_V6(conn); @@ -388,7 +441,7 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn) * data from the socket */ len = tcp_vu_sock_recv(c, vq, conn, v6, already_sent, fillsize, - &iov_cnt, &head_cnt); + &elem_cnt, &frame_cnt); if (len < 0) { if (len != -EAGAIN && len != -EWOULDBLOCK) { tcp_rst(c, conn); @@ -402,6 +455,7 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn) } if (!len) { + vu_queue_rewind(vq, elem_cnt); if (already_sent) { conn_flag(c, conn, STALLED); } else if ((conn->events & (SOCK_FIN_RCVD | TAP_FIN_SENT)) == @@ -442,34 +496,31 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn) check = IP4_CSUM; if (*c->pcap) check |= TCP_CSUM; - for (i = 0, previous_dlen = -1; i < head_cnt; i++) { - struct iovec *iov = &elem[head[i]].in_sg[0]; - int buf_cnt = head[i + 1] - head[i]; - size_t frame_size = iov_size(iov, buf_cnt); - bool push = i == head_cnt - 1; + for (i = 0, previous_dlen = -1; i < frame_cnt; i++) { + struct iovec *iov = &iov_vu[frame[i].idx_iovec]; + int iov_cnt = frame[i].num_iovec; + bool push = i == frame_cnt - 1; ssize_t dlen; - assert(frame_size >= hdrlen); + assert(frame[i].size >= hdrlen); - dlen = frame_size - hdrlen; - if (dlen > len) - dlen = len; - len -= dlen; + dlen = frame[i].size - hdrlen; /* The IPv4 header checksum varies only with dlen */ if (previous_dlen != dlen) check |= IP4_CSUM; previous_dlen = dlen; - tcp_vu_prepare(c, conn, iov, buf_cnt, dlen, &check, push); + tcp_vu_prepare(c, conn, iov, iov_cnt, dlen, &check, push); - vu_pad(elem[head[i]].in_sg, buf_cnt, dlen + hdrlen); - vu_flush(vdev, vq, &elem[head[i]], buf_cnt, dlen + hdrlen); + vu_pad(iov, iov_cnt, dlen + hdrlen); if (*c->pcap) { - pcap_iov(iov, buf_cnt, VNET_HLEN, + pcap_iov(iov, iov_cnt, VNET_HLEN, dlen + hdrlen - VNET_HLEN); } + vu_flush(vdev, vq, &elem[frame[i].idx_element], + frame[i].num_element, dlen + hdrlen); conn->seq_to_tap += dlen; } -- 2.54.0

Laurent Vivier

5:18 p.m.

New subject: [PATCH v7 4/4] tcp_vu: Support multibuffer frames in tcp_vu_send_flag()

Build the Ethernet, IP, and TCP headers on the stack instead of directly in the buffer via pointer casts, then write them into the iovec with IOV_PUSH_HEADER(). This mirrors the approach already used in tcp_vu_prepare() and udp_vu_prepare(). Remove the vu_eth(), vu_ip(), vu_payloadv4() and vu_payloadv6() helpers from vu_common.h, as they are no longer used anywhere. Introduce tcp_vu_send_dup() to handle DUP_ACK duplication using vu_collect() and iov_memcpy() instead of a plain memcpy(), so that the duplicated frame is also properly scattered across multiple iovecs. Signed-off-by: Laurent Vivier Reviewed-by: Jon Maloy --- iov.c | 1 - tcp_vu.c | 156 ++++++++++++++++++++++++++++++---------------------- vu_common.h | 20 ------- 3 files changed, 91 insertions(+), 86 deletions(-) diff --git a/iov.c b/iov.c index 9248ba95a9f2..6fd684ad1a6b 100644 --- a/iov.c +++ b/iov.c @@ -208,7 +208,6 @@ void iov_memset(const struct iovec *iov, size_t iov_cnt, size_t offset, int c, * * Return: total number of bytes copied */ -/* cppcheck-suppress unusedFunction */ size_t iov_memcpy(struct iovec *dst_iov, size_t dst_iov_cnt, size_t dst_offset, const struct iovec *src_iov, size_t src_iov_cnt, size_t src_offset, size_t length) diff --git a/tcp_vu.c b/tcp_vu.c index 55242ec40410..30633760e4ec 100644 --- a/tcp_vu.c +++ b/tcp_vu.c @@ -74,6 +74,43 @@ static size_t tcp_vu_hdrlen(bool v6) return hdrlen; } +/** + * tcp_vu_send_dup() - Duplicate a frame into a new virtqueue element + * @c: Execution context + * @vq: Receive virtqueue + * @dest_elem: Destination virtqueue element to collect + * @dest_iov: Destination iovec array for collected buffers + * @max_dest_iov: Maximum number of entries in @dest_iov + * @src_iov: Source iovec array containing the frame to duplicate + * @src_cnt: Number of entries in @src_iov + * @vnlen: Total frame length including virtio-net header + * + * Return: number of virtqueue elements collected (0 if none available) + */ +static int tcp_vu_send_dup(const struct ctx *c, struct vu_virtq *vq, + struct vu_virtq_element *dest_elem, + struct iovec *dest_iov, size_t max_dest_iov, + const struct iovec *src_iov, size_t src_cnt, + size_t vnlen) +{ + const struct vu_dev *vdev = c->vdev; + size_t dest_cnt; + int elem_cnt; + + elem_cnt = vu_collect(vdev, vq, dest_elem, 1, dest_iov, max_dest_iov, + &dest_cnt, vnlen, NULL); + if (elem_cnt == 0) + return 0; + + iov_memcpy(dest_iov, dest_cnt, 0, src_iov, src_cnt, 0, + MAX(VNET_HLEN + ETH_ZLEN, vnlen)); + + if (*c->pcap) + pcap_iov(dest_iov, dest_cnt, VNET_HLEN, vnlen - VNET_HLEN); + + return elem_cnt; +} + /** * tcp_vu_send_flag() - Send segment with flags to vhost-user (no payload) * @c: Execution context @@ -88,97 +125,86 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags) { struct vu_dev *vdev = c->vdev; struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE]; + size_t optlen, hdrlen, iov_cnt, iov_used; struct vu_virtq_element flags_elem[2]; - size_t optlen, hdrlen, l2len; - struct ipv6hdr *ip6h = NULL; - struct iphdr *ip4h = NULL; - struct iovec flags_iov[2]; - struct tcp_syn_opts *opts; - struct iov_tail payload; - struct tcphdr *th; - struct ethhdr *eh; + struct iov_tail payload, l2frame; + int elem_cnt, dup_elem_cnt = 0; + struct iovec flags_iov[64]; + struct tcp_syn_opts opts; + struct tcphdr th = { 0 }; + struct ipv6hdr ip6h; + struct iphdr ip4h; + struct ethhdr eh; uint32_t seq; - int elem_cnt; int ret; hdrlen = tcp_vu_hdrlen(CONN_V6(conn)); elem_cnt = vu_collect(vdev, vq, &flags_elem[0], 1, - &flags_iov[0], 1, NULL, - hdrlen + sizeof(*opts), NULL); - if (elem_cnt != 1) + flags_iov, ARRAY_SIZE(flags_iov), &iov_cnt, + hdrlen + sizeof(opts), NULL); + if (elem_cnt == 0) return -EAGAIN; - assert(flags_elem[0].in_num == 1); - assert(flags_elem[0].in_sg[0].iov_len >= - MAX(hdrlen + sizeof(*opts), ETH_ZLEN + VNET_HLEN)); - - eh = vu_eth(flags_elem[0].in_sg[0].iov_base); - - memcpy(eh->h_dest, c->guest_mac, sizeof(eh->h_dest)); - memcpy(eh->h_source, c->our_tap_mac, sizeof(eh->h_source)); - - if (CONN_V4(conn)) { - eh->h_proto = htons(ETH_P_IP); - - ip4h = vu_ip(flags_elem[0].in_sg[0].iov_base); - *ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); - - th = vu_payloadv4(flags_elem[0].in_sg[0].iov_base); - } else { - eh->h_proto = htons(ETH_P_IPV6); - - ip6h = vu_ip(flags_elem[0].in_sg[0].iov_base); - *ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP); - th = vu_payloadv6(flags_elem[0].in_sg[0].iov_base); - } + memcpy(eh.h_dest, c->guest_mac, sizeof(eh.h_dest)); - memset(th, 0, sizeof(*th)); - th->doff = sizeof(*th) / 4; - th->ack = 1; + if (CONN_V4(conn)) + ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); + else + ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP); seq = conn->seq_to_tap; - opts = (struct tcp_syn_opts *)(th + 1); - ret = tcp_prepare_flags(c, conn, flags, th, opts, &optlen); + ret = tcp_prepare_flags(c, conn, flags, &th, &opts, &optlen); if (ret <= 0) { - vu_queue_rewind(vq, 1); + vu_queue_rewind(vq, elem_cnt); return ret; } - payload = IOV_TAIL(flags_elem[0].in_sg, 1, hdrlen); - if (flags & KEEPALIVE) seq--; - tcp_fill_headers(c, conn, eh, ip4h, ip6h, th, &payload, + iov_used = iov_skip_bytes(flags_iov, iov_cnt, + MAX(optlen + hdrlen, VNET_HLEN + ETH_ZLEN), + NULL); + if (iov_used < iov_cnt) + iov_used++; + iov_cnt = iov_used; + + payload = IOV_TAIL(flags_elem[0].in_sg, iov_cnt, hdrlen); + iov_from_buf(payload.iov, payload.cnt, payload.off, &opts, optlen); + tcp_fill_headers(c, conn, &eh, CONN_V4(conn) ? &ip4h : NULL, + CONN_V6(conn) ? &ip6h : NULL, &th, &payload, optlen, IP4_CSUM | (*c->pcap ? TCP_CSUM : 0), seq); - vu_pad(flags_elem[0].in_sg, 1, hdrlen + optlen); - vu_flush(vdev, vq, flags_elem, 1, hdrlen + optlen); + vu_pad(flags_elem[0].in_sg, iov_cnt, hdrlen + optlen); + + /* write headers */ + l2frame = IOV_TAIL(flags_elem[0].in_sg, iov_cnt, VNET_HLEN); + + IOV_PUSH_HEADER(&l2frame, eh); + if (CONN_V4(conn)) + IOV_PUSH_HEADER(&l2frame, ip4h); + else + IOV_PUSH_HEADER(&l2frame, ip6h); + IOV_PUSH_HEADER(&l2frame, th); - l2len = hdrlen + optlen - VNET_HLEN; if (*c->pcap) - pcap_iov(&flags_elem[0].in_sg[0], 1, VNET_HLEN, l2len); + pcap_iov(flags_elem[0].in_sg, iov_cnt, VNET_HLEN, + hdrlen + optlen - VNET_HLEN); if (flags & DUP_ACK) { - elem_cnt = vu_collect(vdev, vq, &flags_elem[1], 1, - &flags_iov[1], 1, NULL, - hdrlen + optlen, NULL); - if (elem_cnt == 1 && - flags_elem[1].in_sg[0].iov_len >= - flags_elem[0].in_sg[0].iov_len) { - memcpy(flags_elem[1].in_sg[0].iov_base, - flags_elem[0].in_sg[0].iov_base, - flags_elem[0].in_sg[0].iov_len); - - vu_flush(vdev, vq, &flags_elem[1], 1, hdrlen + optlen); - - if (*c->pcap) { - pcap_iov(&flags_elem[1].in_sg[0], 1, VNET_HLEN, - l2len); - } - } + dup_elem_cnt = tcp_vu_send_dup(c, vq, &flags_elem[elem_cnt], + &flags_iov[iov_cnt], + ARRAY_SIZE(flags_iov) - iov_cnt, + flags_elem[0].in_sg, iov_cnt, + hdrlen + optlen); } + vu_flush(vdev, vq, flags_elem, elem_cnt, hdrlen + optlen); + if (dup_elem_cnt) { + vu_flush(vdev, vq, &flags_elem[elem_cnt], dup_elem_cnt, + hdrlen + optlen); + } + vu_queue_notify(vdev, vq); return 0; diff --git a/vu_common.h b/vu_common.h index 51f70084a7cb..817384175a1d 100644 --- a/vu_common.h +++ b/vu_common.h @@ -15,26 +15,6 @@ #include "ip.h" #include "virtio.h" -static inline void *vu_eth(void *base) -{ - return ((char *)base + VNET_HLEN); -} - -static inline void *vu_ip(void *base) -{ - return (struct ethhdr *)vu_eth(base) + 1; -} - -static inline void *vu_payloadv4(void *base) -{ - return (struct iphdr *)vu_ip(base) + 1; -} - -static inline void *vu_payloadv6(void *base) -{ - return (struct ipv6hdr *)vu_ip(base) + 1; -} - 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_total, -- 2.54.0

David Gibson

22 May 22 May

3:16 a.m.

New subject: [PATCH v7 3/4] tcp_vu: Support multibuffer frames in tcp_vu_sock_recv()

On Wed, May 20, 2026 at 05:18:26PM +0200, Laurent Vivier wrote:

...

Previously, tcp_vu_sock_recv() assumed a 1:1 mapping between virtqueue elements and iovecs (one iovec per element), enforced by an ASSERT. This prevented the use of virtqueue elements with multiple buffers (e.g. when mergeable rx buffers are not negotiated and headers are provided in a separate buffer).

Introduce a struct vu_frame to track per-frame metadata: the range of elements and iovecs that make up each frame, and the frame's total size. This replaces the head[] array which only tracked element indices.

A separate iov_msg[] array is built for recvmsg() by cloning the data portions (after stripping headers) using iov_tail helpers.

Then a frame truncation after recvmsg() properly walks the frame and element arrays to adjust iovec counts and element counts.

Signed-off-by: Laurent Vivier

Reviewed-by: David Gibson

...

--- tcp_vu.c | 173 +++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 112 insertions(+), 61 deletions(-)

diff --git a/tcp_vu.c b/tcp_vu.c index c13c45f71f3b..55242ec40410 100644 --- a/tcp_vu.c +++ b/tcp_vu.c @@ -35,9 +35,24 @@ #include "vu_common.h" #include

-static struct iovec iov_vu[VIRTQUEUE_MAX_SIZE + DISCARD_IOV_NUM]; +static struct iovec iov_vu[VIRTQUEUE_MAX_SIZE]; static struct vu_virtq_element elem[VIRTQUEUE_MAX_SIZE]; -static int head[VIRTQUEUE_MAX_SIZE + 1]; + +/** + * struct vu_frame - Descriptor for a TCP frame mapped to virtqueue elements + * @idx_element: Index of first element in elem[] for this frame + * @num_element: Number of virtqueue elements used by this frame + * @idx_iovec: Index of first iovec in iov_vu[] for this frame + * @num_iovec: Number of iovecs covering this frame's buffers + * @size: Total frame size including all headers + */ +static struct vu_frame { + int idx_element; + int num_element; + int idx_iovec; + int num_iovec; + size_t size; +} frame[VIRTQUEUE_MAX_SIZE];

/** * tcp_vu_hdrlen() - Sum size of all headers, from TCP to virtio-net @@ -176,8 +191,8 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags) * @v6: Set for IPv6 connections * @already_sent: Number of bytes already sent * @fillsize: Maximum bytes to fill in guest-side receiving window - * @iov_cnt: number of iov (output) - * @head_cnt: Pointer to store the count of head iov entries (output) + * @elem_used: number of element (output) + * @frame_cnt: Pointer to store the number of frames (output) * * Return: number of bytes received from the socket, or a negative error code * on failure. @@ -185,57 +200,78 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags) static ssize_t tcp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, const struct tcp_tap_conn *conn, bool v6, uint32_t already_sent, size_t fillsize, - int *iov_cnt, int *head_cnt) + int *elem_used, int *frame_cnt) { + static struct iovec iov_msg[VIRTQUEUE_MAX_SIZE + DISCARD_IOV_NUM]; 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; + ssize_t ret, dlen; int elem_cnt; - ssize_t ret; - int i; - - *iov_cnt = 0; + int i, j;

hdrlen = tcp_vu_hdrlen(v6);

+ *elem_used = 0; + iov_used = 0; elem_cnt = 0; - *head_cnt = 0; + *frame_cnt = 0; while (fillsize > 0 && elem_cnt < ARRAY_SIZE(elem) && - iov_used < VIRTQUEUE_MAX_SIZE) { - size_t frame_size, dlen, in_total; - struct iovec *iov; + iov_used < ARRAY_SIZE(iov_vu) && + *frame_cnt < ARRAY_SIZE(frame)) { + size_t frame_size, in_total; int cnt;

cnt = vu_collect(vdev, vq, &elem[elem_cnt], ARRAY_SIZE(elem) - elem_cnt, - &iov_vu[DISCARD_IOV_NUM + iov_used], - VIRTQUEUE_MAX_SIZE - iov_used, &in_total, + &iov_vu[iov_used], + ARRAY_SIZE(iov_vu) - iov_used, &in_total, MIN(mss, fillsize) + hdrlen, &frame_size); if (cnt == 0) break; - assert((size_t)cnt == in_total); /* one iovec per element */ + + frame[*frame_cnt].idx_element = elem_cnt; + frame[*frame_cnt].num_element = cnt; + frame[*frame_cnt].idx_iovec = iov_used; + frame[*frame_cnt].num_iovec = in_total; + frame[*frame_cnt].size = frame_size; + (*frame_cnt)++;

iov_used += in_total; - dlen = frame_size - hdrlen; + elem_cnt += cnt;

- /* reserve space for headers in iov */ - iov = &elem[elem_cnt].in_sg[0]; - assert(iov->iov_len >= hdrlen); - iov->iov_base = (char *)iov->iov_base + hdrlen; - iov->iov_len -= hdrlen; - head[(*head_cnt)++] = elem_cnt; + fillsize -= frame_size - hdrlen; + }

- fillsize -= dlen; - elem_cnt += cnt; + /* build an iov array without headers */ + for (i = 0, j = DISCARD_IOV_NUM; i < *frame_cnt && + j < ARRAY_SIZE(iov_msg); i++) { + struct iov_tail data; + ssize_t cnt; + + data = IOV_TAIL(&iov_vu[frame[i].idx_iovec], + frame[i].num_iovec, 0); + iov_drop_header(&data, hdrlen); + + cnt = iov_tail_clone(&iov_msg[j], ARRAY_SIZE(iov_msg) - j, + &data); + assert(cnt < ARRAY_SIZE(iov_msg) - j); + if (cnt < 0) + die("Missing entries in iov_msg"); + + j += cnt; }

- if (tcp_prepare_iov(&mh_sock, iov_vu, already_sent, elem_cnt)) + if (tcp_prepare_iov(&mh_sock, iov_msg, already_sent, + j - DISCARD_IOV_NUM)) { /* Expect caller to do a TCP reset */ + vu_queue_rewind(vq, elem_cnt); return -1; + }

do ret = recvmsg(s, &mh_sock, MSG_PEEK); @@ -249,32 +285,49 @@ static ssize_t tcp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, if (!peek_offset_cap) ret -= already_sent;

- i = iov_skip_bytes(&iov_vu[DISCARD_IOV_NUM], iov_used, - MAX(hdrlen + ret, VNET_HLEN + ETH_ZLEN), - NULL); - if ((size_t)i < iov_used) - i++; + dlen = ret;

- /* adjust head count */ - while (*head_cnt > 0 && head[*head_cnt - 1] >= i) - (*head_cnt)--; + /* truncate frame */ + for (i = 0; i < *frame_cnt; i++) { + struct vu_frame *f = &frame[i];

- /* mark end of array */ - head[*head_cnt] = i; - *iov_cnt = i; + if ((size_t)ret <= f->size - hdrlen) { + unsigned cnt;

- /* release unused buffers */ - vu_queue_rewind(vq, elem_cnt - i); + cnt = iov_skip_bytes(&iov_vu[f->idx_iovec], f->num_iovec, + MAX(hdrlen + ret, VNET_HLEN + ETH_ZLEN), + NULL); + if (cnt < (unsigned)f->num_iovec) + cnt++; + + f->size = ret + hdrlen; + f->num_iovec = cnt;

- /* restore space for headers in iov */ - for (i = 0; i < *head_cnt; i++) { - struct iovec *iov = &elem[head[i]].in_sg[0]; + for (j = 0; j < f->num_element; j++) { + struct vu_virtq_element *e;

- iov->iov_base = (char *)iov->iov_base - hdrlen; - iov->iov_len += hdrlen; + e = &elem[f->idx_element + j]; + if (cnt <= e->in_num) { + e->in_num = cnt; + j++; + break; + } + cnt -= e->in_num; + } + f->num_element = j; + *elem_used += j; + i++; + break; + } + *elem_used += f->num_element; + ret -= f->size - hdrlen; } + *frame_cnt = i;

- return ret; + /* release unused buffers */ + vu_queue_rewind(vq, elem_cnt - *elem_used); + + return dlen; }

/** @@ -350,7 +403,7 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn) struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE]; uint32_t already_sent, check; ssize_t len, previous_dlen; - int i, iov_cnt, head_cnt; + int i, elem_cnt, frame_cnt; size_t hdrlen, fillsize; int v6 = CONN_V6(conn);

@@ -388,7 +441,7 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn) * data from the socket */ len = tcp_vu_sock_recv(c, vq, conn, v6, already_sent, fillsize, - &iov_cnt, &head_cnt); + &elem_cnt, &frame_cnt); if (len < 0) { if (len != -EAGAIN && len != -EWOULDBLOCK) { tcp_rst(c, conn); @@ -402,6 +455,7 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn) }

if (!len) { + vu_queue_rewind(vq, elem_cnt); if (already_sent) { conn_flag(c, conn, STALLED); } else if ((conn->events & (SOCK_FIN_RCVD | TAP_FIN_SENT)) == @@ -442,34 +496,31 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn) check = IP4_CSUM; if (*c->pcap) check |= TCP_CSUM; - for (i = 0, previous_dlen = -1; i < head_cnt; i++) { - struct iovec *iov = &elem[head[i]].in_sg[0]; - int buf_cnt = head[i + 1] - head[i]; - size_t frame_size = iov_size(iov, buf_cnt); - bool push = i == head_cnt - 1; + for (i = 0, previous_dlen = -1; i < frame_cnt; i++) { + struct iovec *iov = &iov_vu[frame[i].idx_iovec]; + int iov_cnt = frame[i].num_iovec; + bool push = i == frame_cnt - 1; ssize_t dlen;

- assert(frame_size >= hdrlen); + assert(frame[i].size >= hdrlen);

- dlen = frame_size - hdrlen; - if (dlen > len) - dlen = len; - len -= dlen; + dlen = frame[i].size - hdrlen;

/* The IPv4 header checksum varies only with dlen */ if (previous_dlen != dlen) check |= IP4_CSUM; previous_dlen = dlen;

- tcp_vu_prepare(c, conn, iov, buf_cnt, dlen, &check, push); + tcp_vu_prepare(c, conn, iov, iov_cnt, dlen, &check, push);

- vu_pad(elem[head[i]].in_sg, buf_cnt, dlen + hdrlen); - vu_flush(vdev, vq, &elem[head[i]], buf_cnt, dlen + hdrlen); + vu_pad(iov, iov_cnt, dlen + hdrlen);

if (*c->pcap) { - pcap_iov(iov, buf_cnt, VNET_HLEN, + pcap_iov(iov, iov_cnt, VNET_HLEN, dlen + hdrlen - VNET_HLEN); } + vu_flush(vdev, vq, &elem[frame[i].idx_element], + frame[i].num_element, dlen + hdrlen);

conn->seq_to_tap += dlen; } -- 2.54.0

-- 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

David Gibson

3:24 a.m.

New subject: [PATCH v7 4/4] tcp_vu: Support multibuffer frames in tcp_vu_send_flag()

On Wed, May 20, 2026 at 05:18:27PM +0200, Laurent Vivier wrote:

...

Build the Ethernet, IP, and TCP headers on the stack instead of directly in the buffer via pointer casts, then write them into the iovec with IOV_PUSH_HEADER(). This mirrors the approach already used in tcp_vu_prepare() and udp_vu_prepare().

Remove the vu_eth(), vu_ip(), vu_payloadv4() and vu_payloadv6() helpers from vu_common.h, as they are no longer used anywhere.

Introduce tcp_vu_send_dup() to handle DUP_ACK duplication using vu_collect() and iov_memcpy() instead of a plain memcpy(), so that the duplicated frame is also properly scattered across multiple iovecs.

Signed-off-by: Laurent Vivier Reviewed-by: Jon Maloy

One query below. But at worst it can be addressed as a follow up, so Reviewed-by: David Gibson

...

--- iov.c | 1 - tcp_vu.c | 156 ++++++++++++++++++++++++++++++---------------------- vu_common.h | 20 ------- 3 files changed, 91 insertions(+), 86 deletions(-)

diff --git a/iov.c b/iov.c index 9248ba95a9f2..6fd684ad1a6b 100644 --- a/iov.c +++ b/iov.c @@ -208,7 +208,6 @@ void iov_memset(const struct iovec *iov, size_t iov_cnt, size_t offset, int c, * * Return: total number of bytes copied */ -/* cppcheck-suppress unusedFunction */ size_t iov_memcpy(struct iovec *dst_iov, size_t dst_iov_cnt, size_t dst_offset, const struct iovec *src_iov, size_t src_iov_cnt, size_t src_offset, size_t length) diff --git a/tcp_vu.c b/tcp_vu.c index 55242ec40410..30633760e4ec 100644 --- a/tcp_vu.c +++ b/tcp_vu.c @@ -74,6 +74,43 @@ static size_t tcp_vu_hdrlen(bool v6) return hdrlen; }

+/** + * tcp_vu_send_dup() - Duplicate a frame into a new virtqueue element + * @c: Execution context + * @vq: Receive virtqueue + * @dest_elem: Destination virtqueue element to collect + * @dest_iov: Destination iovec array for collected buffers + * @max_dest_iov: Maximum number of entries in @dest_iov + * @src_iov: Source iovec array containing the frame to duplicate + * @src_cnt: Number of entries in @src_iov + * @vnlen: Total frame length including virtio-net header + * + * Return: number of virtqueue elements collected (0 if none available) + */ +static int tcp_vu_send_dup(const struct ctx *c, struct vu_virtq *vq, + struct vu_virtq_element *dest_elem, + struct iovec *dest_iov, size_t max_dest_iov, + const struct iovec *src_iov, size_t src_cnt, + size_t vnlen) +{ + const struct vu_dev *vdev = c->vdev; + size_t dest_cnt; + int elem_cnt; + + elem_cnt = vu_collect(vdev, vq, dest_elem, 1, dest_iov, max_dest_iov, + &dest_cnt, vnlen, NULL);

This (and the one in tcp_vu_send_flag()) still allows a maximum of 1 element, although it now allows multiple iovs. That differs from the main data path, as of the previous patch.. Is that intentional, or just a gap?

...

+ if (elem_cnt == 0) + return 0; + + iov_memcpy(dest_iov, dest_cnt, 0, src_iov, src_cnt, 0, + MAX(VNET_HLEN + ETH_ZLEN, vnlen)); + + if (*c->pcap) + pcap_iov(dest_iov, dest_cnt, VNET_HLEN, vnlen - VNET_HLEN); + + return elem_cnt; +} + /** * tcp_vu_send_flag() - Send segment with flags to vhost-user (no payload) * @c: Execution context @@ -88,97 +125,86 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags) { struct vu_dev *vdev = c->vdev; struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE]; + size_t optlen, hdrlen, iov_cnt, iov_used; struct vu_virtq_element flags_elem[2]; - size_t optlen, hdrlen, l2len; - struct ipv6hdr *ip6h = NULL; - struct iphdr *ip4h = NULL; - struct iovec flags_iov[2]; - struct tcp_syn_opts *opts; - struct iov_tail payload; - struct tcphdr *th; - struct ethhdr *eh; + struct iov_tail payload, l2frame; + int elem_cnt, dup_elem_cnt = 0; + struct iovec flags_iov[64]; + struct tcp_syn_opts opts; + struct tcphdr th = { 0 }; + struct ipv6hdr ip6h; + struct iphdr ip4h; + struct ethhdr eh; uint32_t seq; - int elem_cnt; int ret;

hdrlen = tcp_vu_hdrlen(CONN_V6(conn));

elem_cnt = vu_collect(vdev, vq, &flags_elem[0], 1, - &flags_iov[0], 1, NULL, - hdrlen + sizeof(*opts), NULL); - if (elem_cnt != 1) + flags_iov, ARRAY_SIZE(flags_iov), &iov_cnt, + hdrlen + sizeof(opts), NULL); + if (elem_cnt == 0) return -EAGAIN;

- assert(flags_elem[0].in_num == 1); - assert(flags_elem[0].in_sg[0].iov_len >= - MAX(hdrlen + sizeof(*opts), ETH_ZLEN + VNET_HLEN)); - - eh = vu_eth(flags_elem[0].in_sg[0].iov_base); - - memcpy(eh->h_dest, c->guest_mac, sizeof(eh->h_dest)); - memcpy(eh->h_source, c->our_tap_mac, sizeof(eh->h_source)); - - if (CONN_V4(conn)) { - eh->h_proto = htons(ETH_P_IP); - - ip4h = vu_ip(flags_elem[0].in_sg[0].iov_base); - *ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); - - th = vu_payloadv4(flags_elem[0].in_sg[0].iov_base); - } else { - eh->h_proto = htons(ETH_P_IPV6); - - ip6h = vu_ip(flags_elem[0].in_sg[0].iov_base); - *ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP); - th = vu_payloadv6(flags_elem[0].in_sg[0].iov_base); - } + memcpy(eh.h_dest, c->guest_mac, sizeof(eh.h_dest));

- memset(th, 0, sizeof(*th)); - th->doff = sizeof(*th) / 4; - th->ack = 1; + if (CONN_V4(conn)) + ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); + else + ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP);

seq = conn->seq_to_tap; - opts = (struct tcp_syn_opts *)(th + 1); - ret = tcp_prepare_flags(c, conn, flags, th, opts, &optlen); + ret = tcp_prepare_flags(c, conn, flags, &th, &opts, &optlen); if (ret <= 0) { - vu_queue_rewind(vq, 1); + vu_queue_rewind(vq, elem_cnt); return ret; }

- payload = IOV_TAIL(flags_elem[0].in_sg, 1, hdrlen); - if (flags & KEEPALIVE) seq--;

- tcp_fill_headers(c, conn, eh, ip4h, ip6h, th, &payload, + iov_used = iov_skip_bytes(flags_iov, iov_cnt, + MAX(optlen + hdrlen, VNET_HLEN + ETH_ZLEN), + NULL); + if (iov_used < iov_cnt) + iov_used++; + iov_cnt = iov_used; + + payload = IOV_TAIL(flags_elem[0].in_sg, iov_cnt, hdrlen); + iov_from_buf(payload.iov, payload.cnt, payload.off, &opts, optlen); + tcp_fill_headers(c, conn, &eh, CONN_V4(conn) ? &ip4h : NULL, + CONN_V6(conn) ? &ip6h : NULL, &th, &payload, optlen, IP4_CSUM | (*c->pcap ? TCP_CSUM : 0), seq);

- vu_pad(flags_elem[0].in_sg, 1, hdrlen + optlen); - vu_flush(vdev, vq, flags_elem, 1, hdrlen + optlen); + vu_pad(flags_elem[0].in_sg, iov_cnt, hdrlen + optlen); + + /* write headers */ + l2frame = IOV_TAIL(flags_elem[0].in_sg, iov_cnt, VNET_HLEN); + + IOV_PUSH_HEADER(&l2frame, eh); + if (CONN_V4(conn)) + IOV_PUSH_HEADER(&l2frame, ip4h); + else + IOV_PUSH_HEADER(&l2frame, ip6h); + IOV_PUSH_HEADER(&l2frame, th);

- l2len = hdrlen + optlen - VNET_HLEN; if (*c->pcap) - pcap_iov(&flags_elem[0].in_sg[0], 1, VNET_HLEN, l2len); + pcap_iov(flags_elem[0].in_sg, iov_cnt, VNET_HLEN, + hdrlen + optlen - VNET_HLEN);

if (flags & DUP_ACK) { - elem_cnt = vu_collect(vdev, vq, &flags_elem[1], 1, - &flags_iov[1], 1, NULL, - hdrlen + optlen, NULL); - if (elem_cnt == 1 && - flags_elem[1].in_sg[0].iov_len >= - flags_elem[0].in_sg[0].iov_len) { - memcpy(flags_elem[1].in_sg[0].iov_base, - flags_elem[0].in_sg[0].iov_base, - flags_elem[0].in_sg[0].iov_len); - - vu_flush(vdev, vq, &flags_elem[1], 1, hdrlen + optlen); - - if (*c->pcap) { - pcap_iov(&flags_elem[1].in_sg[0], 1, VNET_HLEN, - l2len); - } - } + dup_elem_cnt = tcp_vu_send_dup(c, vq, &flags_elem[elem_cnt], + &flags_iov[iov_cnt], + ARRAY_SIZE(flags_iov) - iov_cnt, + flags_elem[0].in_sg, iov_cnt, + hdrlen + optlen); } + vu_flush(vdev, vq, flags_elem, elem_cnt, hdrlen + optlen); + if (dup_elem_cnt) { + vu_flush(vdev, vq, &flags_elem[elem_cnt], dup_elem_cnt, + hdrlen + optlen); + } + vu_queue_notify(vdev, vq);

return 0; diff --git a/vu_common.h b/vu_common.h index 51f70084a7cb..817384175a1d 100644 --- a/vu_common.h +++ b/vu_common.h @@ -15,26 +15,6 @@ #include "ip.h" #include "virtio.h"

-static inline void *vu_eth(void *base) -{ - return ((char *)base + VNET_HLEN); -} - -static inline void *vu_ip(void *base) -{ - return (struct ethhdr *)vu_eth(base) + 1; -} - -static inline void *vu_payloadv4(void *base) -{ - return (struct iphdr *)vu_ip(base) + 1; -} - -static inline void *vu_payloadv6(void *base) -{ - return (struct ipv6hdr *)vu_ip(base) + 1; -} - 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_total, -- 2.54.0

-- 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

Laurent Vivier

11:41 a.m.

New subject: [PATCH v7 4/4] tcp_vu: Support multibuffer frames in tcp_vu_send_flag()

On 5/22/26 03:24, David Gibson wrote:

...

On Wed, May 20, 2026 at 05:18:27PM +0200, Laurent Vivier wrote:

...
Build the Ethernet, IP, and TCP headers on the stack instead of directly in the buffer via pointer casts, then write them into the iovec with IOV_PUSH_HEADER(). This mirrors the approach already used in tcp_vu_prepare() and udp_vu_prepare().

Remove the vu_eth(), vu_ip(), vu_payloadv4() and vu_payloadv6() helpers from vu_common.h, as they are no longer used anywhere.

Introduce tcp_vu_send_dup() to handle DUP_ACK duplication using vu_collect() and iov_memcpy() instead of a plain memcpy(), so that the duplicated frame is also properly scattered across multiple iovecs.

Signed-off-by: Laurent Vivier Reviewed-by: Jon Maloy

One query below. But at worst it can be addressed as a follow up, so

Reviewed-by: David Gibson

...
--- iov.c | 1 - tcp_vu.c | 156 ++++++++++++++++++++++++++++++---------------------- vu_common.h | 20 ------- 3 files changed, 91 insertions(+), 86 deletions(-)

diff --git a/iov.c b/iov.c index 9248ba95a9f2..6fd684ad1a6b 100644 --- a/iov.c +++ b/iov.c @@ -208,7 +208,6 @@ void iov_memset(const struct iovec *iov, size_t iov_cnt, size_t offset, int c, * * Return: total number of bytes copied */ -/* cppcheck-suppress unusedFunction */ size_t iov_memcpy(struct iovec *dst_iov, size_t dst_iov_cnt, size_t dst_offset, const struct iovec *src_iov, size_t src_iov_cnt, size_t src_offset, size_t length) diff --git a/tcp_vu.c b/tcp_vu.c index 55242ec40410..30633760e4ec 100644 --- a/tcp_vu.c +++ b/tcp_vu.c @@ -74,6 +74,43 @@ static size_t tcp_vu_hdrlen(bool v6) return hdrlen; }

+/** + * tcp_vu_send_dup() - Duplicate a frame into a new virtqueue element + * @c: Execution context + * @vq: Receive virtqueue + * @dest_elem: Destination virtqueue element to collect + * @dest_iov: Destination iovec array for collected buffers + * @max_dest_iov: Maximum number of entries in @dest_iov + * @src_iov: Source iovec array containing the frame to duplicate + * @src_cnt: Number of entries in @src_iov + * @vnlen: Total frame length including virtio-net header + * + * Return: number of virtqueue elements collected (0 if none available) + */ +static int tcp_vu_send_dup(const struct ctx *c, struct vu_virtq *vq, + struct vu_virtq_element *dest_elem, + struct iovec *dest_iov, size_t max_dest_iov, + const struct iovec *src_iov, size_t src_cnt, + size_t vnlen) +{ + const struct vu_dev *vdev = c->vdev; + size_t dest_cnt; + int elem_cnt; + + elem_cnt = vu_collect(vdev, vq, dest_elem, 1, dest_iov, max_dest_iov, + &dest_cnt, vnlen, NULL);

This (and the one in tcp_vu_send_flag()) still allows a maximum of 1 element, although it now allows multiple iovs. That differs from the main data path, as of the previous patch.. Is that intentional, or just a gap?

It's intentionnal, 1 element will always have enough space to send flags. Thanks, Laurent

...

...
+ if (elem_cnt == 0) + return 0; + + iov_memcpy(dest_iov, dest_cnt, 0, src_iov, src_cnt, 0, + MAX(VNET_HLEN + ETH_ZLEN, vnlen)); + + if (*c->pcap) + pcap_iov(dest_iov, dest_cnt, VNET_HLEN, vnlen - VNET_HLEN); + + return elem_cnt; +} + /** * tcp_vu_send_flag() - Send segment with flags to vhost-user (no payload) * @c: Execution context @@ -88,97 +125,86 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags) { struct vu_dev *vdev = c->vdev; struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE]; + size_t optlen, hdrlen, iov_cnt, iov_used; struct vu_virtq_element flags_elem[2]; - size_t optlen, hdrlen, l2len; - struct ipv6hdr *ip6h = NULL; - struct iphdr *ip4h = NULL; - struct iovec flags_iov[2]; - struct tcp_syn_opts *opts; - struct iov_tail payload; - struct tcphdr *th; - struct ethhdr *eh; + struct iov_tail payload, l2frame; + int elem_cnt, dup_elem_cnt = 0; + struct iovec flags_iov[64]; + struct tcp_syn_opts opts; + struct tcphdr th = { 0 }; + struct ipv6hdr ip6h; + struct iphdr ip4h; + struct ethhdr eh; uint32_t seq; - int elem_cnt; int ret;

hdrlen = tcp_vu_hdrlen(CONN_V6(conn));

elem_cnt = vu_collect(vdev, vq, &flags_elem[0], 1, - &flags_iov[0], 1, NULL, - hdrlen + sizeof(*opts), NULL); - if (elem_cnt != 1) + flags_iov, ARRAY_SIZE(flags_iov), &iov_cnt, + hdrlen + sizeof(opts), NULL); + if (elem_cnt == 0) return -EAGAIN;

- assert(flags_elem[0].in_num == 1); - assert(flags_elem[0].in_sg[0].iov_len >= - MAX(hdrlen + sizeof(*opts), ETH_ZLEN + VNET_HLEN)); - - eh = vu_eth(flags_elem[0].in_sg[0].iov_base); - - memcpy(eh->h_dest, c->guest_mac, sizeof(eh->h_dest)); - memcpy(eh->h_source, c->our_tap_mac, sizeof(eh->h_source)); - - if (CONN_V4(conn)) { - eh->h_proto = htons(ETH_P_IP); - - ip4h = vu_ip(flags_elem[0].in_sg[0].iov_base); - *ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); - - th = vu_payloadv4(flags_elem[0].in_sg[0].iov_base); - } else { - eh->h_proto = htons(ETH_P_IPV6); - - ip6h = vu_ip(flags_elem[0].in_sg[0].iov_base); - *ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP); - th = vu_payloadv6(flags_elem[0].in_sg[0].iov_base); - } + memcpy(eh.h_dest, c->guest_mac, sizeof(eh.h_dest));

- memset(th, 0, sizeof(*th)); - th->doff = sizeof(*th) / 4; - th->ack = 1; + if (CONN_V4(conn)) + ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); + else + ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP);

seq = conn->seq_to_tap; - opts = (struct tcp_syn_opts *)(th + 1); - ret = tcp_prepare_flags(c, conn, flags, th, opts, &optlen); + ret = tcp_prepare_flags(c, conn, flags, &th, &opts, &optlen); if (ret <= 0) { - vu_queue_rewind(vq, 1); + vu_queue_rewind(vq, elem_cnt); return ret; }

- payload = IOV_TAIL(flags_elem[0].in_sg, 1, hdrlen); - if (flags & KEEPALIVE) seq--;

- tcp_fill_headers(c, conn, eh, ip4h, ip6h, th, &payload, + iov_used = iov_skip_bytes(flags_iov, iov_cnt, + MAX(optlen + hdrlen, VNET_HLEN + ETH_ZLEN), + NULL); + if (iov_used < iov_cnt) + iov_used++; + iov_cnt = iov_used; + + payload = IOV_TAIL(flags_elem[0].in_sg, iov_cnt, hdrlen); + iov_from_buf(payload.iov, payload.cnt, payload.off, &opts, optlen); + tcp_fill_headers(c, conn, &eh, CONN_V4(conn) ? &ip4h : NULL, + CONN_V6(conn) ? &ip6h : NULL, &th, &payload, optlen, IP4_CSUM | (*c->pcap ? TCP_CSUM : 0), seq);

- vu_pad(flags_elem[0].in_sg, 1, hdrlen + optlen); - vu_flush(vdev, vq, flags_elem, 1, hdrlen + optlen); + vu_pad(flags_elem[0].in_sg, iov_cnt, hdrlen + optlen); + + /* write headers */ + l2frame = IOV_TAIL(flags_elem[0].in_sg, iov_cnt, VNET_HLEN); + + IOV_PUSH_HEADER(&l2frame, eh); + if (CONN_V4(conn)) + IOV_PUSH_HEADER(&l2frame, ip4h); + else + IOV_PUSH_HEADER(&l2frame, ip6h); + IOV_PUSH_HEADER(&l2frame, th);

- l2len = hdrlen + optlen - VNET_HLEN; if (*c->pcap) - pcap_iov(&flags_elem[0].in_sg[0], 1, VNET_HLEN, l2len); + pcap_iov(flags_elem[0].in_sg, iov_cnt, VNET_HLEN, + hdrlen + optlen - VNET_HLEN);

if (flags & DUP_ACK) { - elem_cnt = vu_collect(vdev, vq, &flags_elem[1], 1, - &flags_iov[1], 1, NULL, - hdrlen + optlen, NULL); - if (elem_cnt == 1 && - flags_elem[1].in_sg[0].iov_len >= - flags_elem[0].in_sg[0].iov_len) { - memcpy(flags_elem[1].in_sg[0].iov_base, - flags_elem[0].in_sg[0].iov_base, - flags_elem[0].in_sg[0].iov_len); - - vu_flush(vdev, vq, &flags_elem[1], 1, hdrlen + optlen); - - if (*c->pcap) { - pcap_iov(&flags_elem[1].in_sg[0], 1, VNET_HLEN, - l2len); - } - } + dup_elem_cnt = tcp_vu_send_dup(c, vq, &flags_elem[elem_cnt], + &flags_iov[iov_cnt], + ARRAY_SIZE(flags_iov) - iov_cnt, + flags_elem[0].in_sg, iov_cnt, + hdrlen + optlen); } + vu_flush(vdev, vq, flags_elem, elem_cnt, hdrlen + optlen); + if (dup_elem_cnt) { + vu_flush(vdev, vq, &flags_elem[elem_cnt], dup_elem_cnt, + hdrlen + optlen); + } + vu_queue_notify(vdev, vq);

return 0; diff --git a/vu_common.h b/vu_common.h index 51f70084a7cb..817384175a1d 100644 --- a/vu_common.h +++ b/vu_common.h @@ -15,26 +15,6 @@ #include "ip.h" #include "virtio.h"

-static inline void *vu_eth(void *base) -{ - return ((char *)base + VNET_HLEN); -} - -static inline void *vu_ip(void *base) -{ - return (struct ethhdr *)vu_eth(base) + 1; -} - -static inline void *vu_payloadv4(void *base) -{ - return (struct iphdr *)vu_ip(base) + 1; -} - -static inline void *vu_payloadv6(void *base) -{ - return (struct ipv6hdr *)vu_ip(base) + 1; -} - 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_total, -- 2.54.0

Age (days ago)

Last active (days ago)

List overview

Download

5 comments

2 participants

participants (2)

David Gibson
Laurent Vivier