public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
From: Stefano Brivio <sbrivio@redhat.com>
To: passt-dev@passt.top
Cc: Jon Maloy <jmaloy@redhat.com>, Paul Holzinger <pholzing@redhat.com>
Subject: [PATCH 2/6] tcp: Factor sequence rewind for retransmissions into a new function
Date: Fri, 15 Aug 2025 18:10:38 +0200	[thread overview]
Message-ID: <20250815161042.3606244-3-sbrivio@redhat.com> (raw)
In-Reply-To: <20250815161042.3606244-1-sbrivio@redhat.com>

...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>
---
 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 } };
-- 
@@ -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 } };
-- 
2.43.0


  parent reply	other threads:[~2025-08-15 16:10 UTC|newest]

Thread overview: 7+ 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
2025-08-15 16:10 ` Stefano Brivio [this message]
2025-08-15 16:10 ` [PATCH 3/6] tcp: Rewind sequence when guest shrinks window to zero Stefano Brivio
2025-08-15 16:10 ` [PATCH 4/6] tcp: Fix closing logic for half-closed connections Stefano Brivio
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
2025-08-15 16:10 ` [PATCH 6/6] tcp: Fast re-transmit if half-closed, make TAP_FIN_RCVD path consistent 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=20250815161042.3606244-3-sbrivio@redhat.com \
    --to=sbrivio@redhat.com \
    --cc=jmaloy@redhat.com \
    --cc=passt-dev@passt.top \
    --cc=pholzing@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).