From: Jon Maloy <jmaloy@redhat.com>
To: Laurent Vivier <lvivier@redhat.com>, passt-dev@passt.top
Subject: Re: [PATCH v3 07/10] pcap: Pass explicit L2 length to pcap_iov()
Date: Mon, 11 May 2026 05:50:29 -0400 [thread overview]
Message-ID: <cad1d4e1-d699-4d80-b976-8da66719d3e4@redhat.com> (raw)
In-Reply-To: <20260416155721.3807225-8-lvivier@redhat.com>
On 2026-04-16 11:57, Laurent Vivier wrote:
> With vhost-user multibuffer frames, the iov can be larger than the
> actual L2 frame. The previous approach of computing L2 length as
> iov_size() - offset would overcount and write extra bytes into the
> pcap file.
>
> Pass the L2 frame length explicitly to pcap_frame() and pcap_iov(),
> and write exactly that many bytes instead of the full iov remainder.
>
> Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Jon Maloy <jmaloy@redhat.com>
See below.
> ---
> pcap.c | 28 +++++++++++++++++++---------
> pcap.h | 2 +-
> tap.c | 6 ++++--
> tcp_vu.c | 14 ++++++++------
[...]
> @@ -109,8 +115,11 @@ void pcap_multiple(const struct iovec *iov, size_t frame_parts, unsigned int n,
> if (clock_gettime(CLOCK_REALTIME, &now))
> err_perror("Failed to get CLOCK_REALTIME time");
>
> - for (i = 0; i < n; i++)
> - pcap_frame(iov + i * frame_parts, frame_parts, offset, &now);
> + for (i = 0; i < n; i++) {
> + pcap_frame(iov + i * frame_parts, frame_parts, offset,
> + iov_size(iov + i * frame_parts, frame_parts) - offset,
> + &now);
> + }
> }
>
> /**
> @@ -120,8 +129,9 @@ void pcap_multiple(const struct iovec *iov, size_t frame_parts, unsigned int n,
> * containing packet data to write, including L2 header
> * @iovcnt: Number of buffers (@iov entries)
> * @offset: Offset of the L2 frame within the full data length
> + * @l2len: Length of L2 frame data to capture
> */
> -void pcap_iov(const struct iovec *iov, size_t iovcnt, size_t offset)
> +void pcap_iov(const struct iovec *iov, size_t iovcnt, size_t offset, size_t l2len)
This line should be wrapped.
/jon
> {
> struct timespec now = { 0 };
>
> @@ -131,7 +141,7 @@ void pcap_iov(const struct iovec *iov, size_t iovcnt, size_t offset)
> if (clock_gettime(CLOCK_REALTIME, &now))
> err_perror("Failed to get CLOCK_REALTIME time");
>
> - pcap_frame(iov, iovcnt, offset, &now);
> + pcap_frame(iov, iovcnt, offset, l2len, &now);
> }
>
> /**
> diff --git a/pcap.h b/pcap.h
> index dface5df4ee6..c171257cbd73 100644
> --- a/pcap.h
> +++ b/pcap.h
> @@ -13,7 +13,7 @@ extern int pcap_fd;
> void pcap(const char *pkt, size_t l2len);
> void pcap_multiple(const struct iovec *iov, size_t frame_parts, unsigned int n,
> size_t offset);
> -void pcap_iov(const struct iovec *iov, size_t iovcnt, size_t offset);
> +void pcap_iov(const struct iovec *iov, size_t iovcnt, size_t offset, size_t l2len);
> void pcap_init(struct ctx *c);
>
> #endif /* PCAP_H */
> diff --git a/tap.c b/tap.c
> index 41a61a36c279..41ba2b8666a5 100644
> --- a/tap.c
> +++ b/tap.c
> @@ -500,7 +500,8 @@ static size_t tap_send_frames_passt(const struct ctx *c,
> /* Number of unsent or partially sent buffers for the frame */
> size_t rembufs = bufs_per_frame - (i % bufs_per_frame);
>
> - if (write_remainder(c->fd_tap, &iov[i], rembufs, buf_offset) < 0) {
> + if (write_remainder(c->fd_tap, &iov[i], rembufs, buf_offset,
> + SIZE_MAX) < 0) {
> err_perror("tap: partial frame send");
> return i;
> }
> @@ -1102,10 +1103,11 @@ void tap_handler(struct ctx *c, const struct timespec *now)
> void tap_add_packet(struct ctx *c, struct iov_tail *data,
> const struct timespec *now)
> {
> + size_t l2len = iov_tail_size(data);
> struct ethhdr eh_storage;
> const struct ethhdr *eh;
>
> - pcap_iov(data->iov, data->cnt, data->off);
> + pcap_iov(data->iov, data->cnt, data->off, l2len);
>
> eh = IOV_PEEK_HEADER(data, eh_storage);
> if (!eh)
> diff --git a/tcp_vu.c b/tcp_vu.c
> index 0cd01190d612..7b7ea9c789b1 100644
> --- a/tcp_vu.c
> +++ b/tcp_vu.c
> @@ -128,7 +128,8 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
> return ret;
> }
>
> - iov_truncate(&flags_iov[0], 1, hdrlen + optlen);
> + l2len = hdrlen + optlen - VNET_HLEN;
> + iov_truncate(&flags_iov[0], 1, l2len + VNET_HLEN);
> payload = IOV_TAIL(flags_elem[0].in_sg, 1, hdrlen);
>
> if (flags & KEEPALIVE)
> @@ -137,13 +138,12 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
> tcp_fill_headers(c, conn, eh, ip4h, ip6h, th, &payload,
> NULL, seq, !*c->pcap);
>
> - l2len = optlen + hdrlen - VNET_HLEN;
> vu_pad(&flags_elem[0].in_sg[0], l2len);
>
> vu_flush(vdev, vq, flags_elem, 1);
>
> if (*c->pcap)
> - pcap_iov(&flags_elem[0].in_sg[0], 1, VNET_HLEN);
> + pcap_iov(&flags_elem[0].in_sg[0], 1, VNET_HLEN, l2len);
>
> if (flags & DUP_ACK) {
> elem_cnt = vu_collect(vdev, vq, &flags_elem[1], 1,
> @@ -158,8 +158,10 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
>
> vu_flush(vdev, vq, &flags_elem[1], 1);
>
> - if (*c->pcap)
> - pcap_iov(&flags_elem[1].in_sg[0], 1, VNET_HLEN);
> + if (*c->pcap) {
> + pcap_iov(&flags_elem[1].in_sg[0], 1, VNET_HLEN,
> + l2len);
> + }
> }
> }
> vu_queue_notify(vdev, vq);
> @@ -464,7 +466,7 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
> vu_flush(vdev, vq, &elem[head[i]], buf_cnt);
>
> if (*c->pcap)
> - pcap_iov(iov, buf_cnt, VNET_HLEN);
> + pcap_iov(iov, buf_cnt, VNET_HLEN, l2len);
>
> conn->seq_to_tap += dlen;
> }
> diff --git a/udp_vu.c b/udp_vu.c
> index 1a73d997f683..76242d423778 100644
> --- a/udp_vu.c
> +++ b/udp_vu.c
> @@ -182,6 +182,7 @@ void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx)
> static struct iovec iov_vu[VIRTQUEUE_MAX_SIZE];
> struct vu_dev *vdev = c->vdev;
> struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
> + size_t hdrlen = udp_vu_hdrlen(v6);
> int i;
>
> assert(!c->no_udp);
> @@ -227,7 +228,8 @@ void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx)
> udp_vu_prepare(c, iov_vu, toside, dlen);
> if (*c->pcap) {
> udp_vu_csum(toside, iov_vu, iov_cnt, dlen);
> - pcap_iov(iov_vu, iov_cnt, VNET_HLEN);
> + pcap_iov(iov_vu, iov_cnt, VNET_HLEN,
> + hdrlen + dlen - VNET_HLEN);
> }
> vu_flush(vdev, vq, elem, elem_used);
> vu_queue_notify(vdev, vq);
> diff --git a/util.c b/util.c
> index 73c9d51d7b4a..141aad275869 100644
> --- a/util.c
> +++ b/util.c
> @@ -722,31 +722,54 @@ int do_clone(int (*fn)(void *), char *stack_area, size_t stack_size, int flags,
> * @iov: IO vector
> * @iovcnt: Number of entries in @iov
> * @skip: Number of bytes of the vector to skip writing
> + * @length: Number of bytes of the vector to write
> *
> * Return: 0 on success, -1 on error (with errno set)
> *
> * #syscalls writev
> */
> -int write_remainder(int fd, const struct iovec *iov, size_t iovcnt, size_t skip)
> +int write_remainder(int fd, const struct iovec *iov, size_t iovcnt,
> + size_t skip, size_t length)
> {
> size_t i = 0, offset;
>
> - while ((i += iov_skip_bytes(iov + i, iovcnt - i, skip, &offset)) < iovcnt) {
> + while (length &&
> + (i += iov_skip_bytes(iov + i, iovcnt - i, skip, &offset)) < iovcnt) {
> ssize_t rc;
> + size_t end;
>
> if (offset) {
> + size_t len = MIN(length, iov[i].iov_len - offset);
> +
> /* Write the remainder of the partially written buffer */
> if (write_all_buf(fd, (char *)iov[i].iov_base + offset,
> - iov[i].iov_len - offset) < 0)
> + len) < 0)
> return -1;
> +
> + length -= len;
> i++;
> +
> + if (!length || i >= iovcnt)
> + break;
> + }
> +
> + end = iov_skip_bytes(iov + i, iovcnt - i, length, NULL);
> +
> + /* Write a trailing partial buffer */
> + if (!end) {
> + size_t len = MIN(length, iov[i].iov_len);
> +
> + if (write_all_buf(fd, iov[i].iov_base, len) < 0)
> + return -1;
> + break;
> }
>
> /* Write as much of the remaining whole buffers as we can */
> - rc = writev(fd, &iov[i], iovcnt - i);
> + rc = writev(fd, &iov[i], end);
> if (rc < 0)
> return -1;
>
> + length -= rc;
> skip = rc;
> }
> return 0;
> diff --git a/util.h b/util.h
> index 92aeabc86b52..888093277896 100644
> --- a/util.h
> +++ b/util.h
> @@ -235,7 +235,8 @@ int fls(unsigned long x);
> int ilog2(unsigned long x);
> int write_file(const char *path, const char *buf);
> intmax_t read_file_integer(const char *path, intmax_t fallback);
> -int write_remainder(int fd, const struct iovec *iov, size_t iovcnt, size_t skip);
> +int write_remainder(int fd, const struct iovec *iov, size_t iovcnt,
> + size_t skip, size_t length);
> int read_remainder(int fd, const struct iovec *iov, size_t cnt, size_t skip);
> void close_open_files(int argc, char **argv);
> bool snprintf_check(char *str, size_t size, const char *format, ...);
> diff --git a/vu_common.c b/vu_common.c
> index 57949ca32309..f254cb67ec78 100644
> --- a/vu_common.c
> +++ b/vu_common.c
> @@ -268,7 +268,7 @@ int vu_send_single(const struct ctx *c, const void *buf, size_t size)
> iov_from_buf(in_sg, in_total, VNET_HLEN, buf, total);
>
> if (*c->pcap)
> - pcap_iov(in_sg, in_total, VNET_HLEN);
> + pcap_iov(in_sg, in_total, VNET_HLEN, size);
>
> vu_flush(vdev, vq, elem, elem_cnt);
> vu_queue_notify(vdev, vq);
next prev parent reply other threads:[~2026-05-11 9:50 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-16 15:57 [PATCH v3 00/10] vhost-user: Preparatory series for multiple iovec entries per virtqueue element Laurent Vivier
2026-04-16 15:57 ` [PATCH v3 01/10] iov: Introduce iov_memset() Laurent Vivier
2026-04-16 15:57 ` [PATCH v3 02/10] iov: Add iov_memcpy() to copy data between iovec arrays Laurent Vivier
2026-05-11 9:07 ` Jon Maloy
2026-04-16 15:57 ` [PATCH v3 03/10] vu_common: Move vnethdr setup into vu_flush() Laurent Vivier
2026-04-16 15:57 ` [PATCH v3 04/10] udp_vu: Move virtqueue management from udp_vu_sock_recv() to its caller Laurent Vivier
2026-05-11 9:30 ` Jon Maloy
2026-05-11 10:44 ` David Gibson
2026-04-16 15:57 ` [PATCH v3 05/10] udp_vu: Pass iov explicitly to helpers instead of using file-scoped array Laurent Vivier
2026-05-11 9:37 ` Jon Maloy
2026-04-16 15:57 ` [PATCH v3 06/10] checksum: Pass explicit L4 length to checksum functions Laurent Vivier
2026-05-11 1:33 ` David Gibson
2026-04-16 15:57 ` [PATCH v3 07/10] pcap: Pass explicit L2 length to pcap_iov() Laurent Vivier
2026-05-11 1:42 ` David Gibson
2026-05-11 9:50 ` Jon Maloy [this message]
2026-04-16 15:57 ` [PATCH v3 08/10] vu_common: Pass explicit frame length to vu_flush() Laurent Vivier
2026-04-16 15:57 ` [PATCH v3 09/10] tcp: Pass explicit data length to tcp_fill_headers() Laurent Vivier
2026-04-16 15:57 ` [PATCH v3 10/10] vhost-user: Centralise Ethernet frame padding in vu_collect() and vu_pad() Laurent Vivier
2026-05-11 2:01 ` David Gibson
2026-05-11 9:53 ` [PATCH v3 00/10] vhost-user: Preparatory series for multiple iovec entries per virtqueue element Jon Maloy
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=cad1d4e1-d699-4d80-b976-8da66719d3e4@redhat.com \
--to=jmaloy@redhat.com \
--cc=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).