From: David Gibson <david@gibson.dropbear.id.au>
To: Stefano Brivio <sbrivio@redhat.com>
Cc: passt-dev@passt.top, Jon Maloy <jmaloy@redhat.com>,
Paul Holzinger <pholzing@redhat.com>
Subject: Re: [PATCH 2/6] tcp: Factor sequence rewind for retransmissions into a new function
Date: Mon, 18 Aug 2025 12:46:47 +1000 [thread overview]
Message-ID: <aKKUFxoEV_oZrA7s@zatzit> (raw)
In-Reply-To: <20250815161042.3606244-3-sbrivio@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 3240 bytes --]
On Fri, Aug 15, 2025 at 06:10:38PM +0200, Stefano Brivio wrote:
> ...as I'm going to need a third occurrence of this in the next change.
>
> This introduces a small functional change in tcp_data_from_tap(): the
> sequence was previously rewound to the highest ACK number we found in
> the current packet batch, and not to the current value of
> seq_ack_from_tap.
>
> The two might differ in case tcp_sock_consume() failed, because in
> that case we're ignoring that ACK altogether. But if we're ignoring
> it, it looks more correct to me to start retransmitting from an
> earlier sequence anyway.
>
> Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
> ---
> tcp.c | 47 ++++++++++++++++++++++++++++++++---------------
> 1 file changed, 32 insertions(+), 15 deletions(-)
>
> diff --git a/tcp.c b/tcp.c
> index 7c1f237..1402ca2 100644
> --- a/tcp.c
> +++ b/tcp.c
> @@ -1097,6 +1097,26 @@ static void tcp_update_seqack_from_tap(const struct ctx *c,
> }
> }
>
> +/**
> + * tcp_rewind_seq() - Rewind sequence to tap and socket offset to current ACK
> + * @c: Execution context
> + * @conn: Connection pointer
> + *
> + * Return: 0 on success, -1 on failure, with connection reset
> + */
> +static int tcp_rewind_seq(const struct ctx *c, struct tcp_tap_conn *conn)
> +{
> + conn->seq_to_tap = conn->seq_ack_from_tap;
> + conn->events &= ~TAP_FIN_SENT;
> +
> + if (tcp_set_peek_offset(conn, 0)) {
> + tcp_rst(c, conn);
> + return -1;
> + }
> +
> + return 0;
> +}
> +
> /**
> * tcp_prepare_flags() - Prepare header for flags-only segment (no payload)
> * @c: Execution context
> @@ -1757,13 +1777,11 @@ static int tcp_data_from_tap(const struct ctx *c, struct tcp_tap_conn *conn,
> if (retr) {
> flow_trace(conn,
> "fast re-transmit, ACK: %u, previous sequence: %u",
> - max_ack_seq, conn->seq_to_tap);
> - conn->seq_to_tap = max_ack_seq;
> - conn->events &= ~TAP_FIN_SENT;
> - if (tcp_set_peek_offset(conn, 0)) {
> - tcp_rst(c, conn);
> + conn->seq_ack_from_tap, conn->seq_to_tap);
> +
> + if (tcp_rewind_seq(c, conn))
> return -1;
> - }
> +
> tcp_data_from_sock(c, conn);
> }
>
> @@ -2285,17 +2303,16 @@ void tcp_timer_handler(const struct ctx *c, union epoll_ref ref)
> tcp_rst(c, conn);
> } else {
> flow_dbg(conn, "ACK timeout, retry");
> - conn->retrans++;
> - conn->seq_to_tap = conn->seq_ack_from_tap;
> - conn->events &= ~TAP_FIN_SENT;
> +
> if (!conn->wnd_from_tap)
> conn->wnd_from_tap = 1; /* Zero-window probe */
> - if (tcp_set_peek_offset(conn, 0)) {
> - tcp_rst(c, conn);
> - } else {
> - tcp_data_from_sock(c, conn);
> - tcp_timer_ctl(c, conn);
> - }
> +
> + conn->retrans++;
> + if (tcp_rewind_seq(c, conn))
> + return;
> +
> + tcp_data_from_sock(c, conn);
> + tcp_timer_ctl(c, conn);
> }
> } else {
> struct itimerspec new = { { 0 }, { ACT_TIMEOUT, 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 --]
next prev parent reply other threads:[~2025-08-18 3:04 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-15 16:10 [PATCH 0/6] tcp: Fixes for issues uncovered by tests with 6.17-rc1 kernels Stefano Brivio
2025-08-15 16:10 ` [PATCH 1/6] tcp: FIN flags have to be retransmitted as well Stefano Brivio
2025-08-18 2:43 ` David Gibson
2025-08-15 16:10 ` [PATCH 2/6] tcp: Factor sequence rewind for retransmissions into a new function Stefano Brivio
2025-08-18 2:46 ` David Gibson [this message]
2025-08-15 16:10 ` [PATCH 3/6] tcp: Rewind sequence when guest shrinks window to zero Stefano Brivio
2025-08-18 2:49 ` David Gibson
2025-08-15 16:10 ` [PATCH 4/6] tcp: Fix closing logic for half-closed connections Stefano Brivio
2025-08-18 2:52 ` David Gibson
2025-08-15 16:10 ` [PATCH 5/6] tcp: Don't try to transmit right after the peer shrank the window to zero Stefano Brivio
2025-08-18 2:56 ` David Gibson
2025-08-18 17:06 ` Stefano Brivio
2025-08-19 0:55 ` David Gibson
2025-08-15 16:10 ` [PATCH 6/6] tcp: Fast re-transmit if half-closed, make TAP_FIN_RCVD path consistent Stefano Brivio
2025-08-18 3:04 ` David Gibson
2025-08-18 17:40 ` [PATCH 0/6] tcp: Fixes for issues uncovered by tests with 6.17-rc1 kernels Paul Holzinger
2025-08-18 21:58 ` Stefano Brivio
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=aKKUFxoEV_oZrA7s@zatzit \
--to=david@gibson.dropbear.id.au \
--cc=jmaloy@redhat.com \
--cc=passt-dev@passt.top \
--cc=pholzing@redhat.com \
--cc=sbrivio@redhat.com \
/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).