From: Stefano Brivio <sbrivio@redhat.com>
To: passt-dev@passt.top
Cc: Jon Maloy <jmaloy@redhat.com>, Paul Holzinger <pholzing@redhat.com>
Subject: [PATCH 3/6] tcp: Rewind sequence when guest shrinks window to zero
Date: Fri, 15 Aug 2025 18:10:39 +0200 [thread overview]
Message-ID: <20250815161042.3606244-4-sbrivio@redhat.com> (raw)
In-Reply-To: <20250815161042.3606244-1-sbrivio@redhat.com>
A window shrunk to zero means by definition that anything else that
might be in flight is now out of window. Restart from the currently
acknowledged sequence.
Suggested-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
tcp.c | 25 ++++++++++++++++---------
1 file changed, 16 insertions(+), 9 deletions(-)
diff --git a/tcp.c b/tcp.c
index 1402ca2..dda0a2e 100644
--- a/tcp.c
+++ b/tcp.c
@@ -1257,19 +1257,25 @@ static void tcp_get_tap_ws(struct tcp_tap_conn *conn,
/**
* tcp_tap_window_update() - Process an updated window from tap side
+ * @c: Execution context
* @conn: Connection pointer
* @wnd: Window value, host order, unscaled
*/
-static void tcp_tap_window_update(struct tcp_tap_conn *conn, unsigned wnd)
+static void tcp_tap_window_update(const struct ctx *c,
+ struct tcp_tap_conn *conn, unsigned wnd)
{
wnd = MIN(MAX_WINDOW, wnd << conn->ws_from_tap);
/* Work-around for bug introduced in peer kernel code, commit
- * e2142825c120 ("net: tcp: send zero-window ACK when no memory").
- * We don't update if window shrank to zero.
+ * e2142825c120 ("net: tcp: send zero-window ACK when no memory"): don't
+ * update the window if it shrank to zero, so that we'll eventually
+ * retry to send data, but rewind the sequence as that obviously implies
+ * that no data beyond the updated window will ever be acknowledged.
*/
- if (!wnd && SEQ_LT(conn->seq_ack_from_tap, conn->seq_to_tap))
+ if (!wnd && SEQ_LT(conn->seq_ack_from_tap, conn->seq_to_tap)) {
+ tcp_rewind_seq(c, conn);
return;
+ }
conn->wnd_from_tap = MIN(wnd >> conn->ws_from_tap, USHRT_MAX);
@@ -1694,7 +1700,8 @@ static int tcp_data_from_tap(const struct ctx *c, struct tcp_tap_conn *conn,
tcp_timer_ctl(c, conn);
if (p->count == 1) {
- tcp_tap_window_update(conn, ntohs(th->window));
+ tcp_tap_window_update(c, conn,
+ ntohs(th->window));
return 1;
}
@@ -1772,7 +1779,7 @@ static int tcp_data_from_tap(const struct ctx *c, struct tcp_tap_conn *conn,
if (ack && !tcp_sock_consume(conn, max_ack_seq))
tcp_update_seqack_from_tap(c, conn, max_ack_seq);
- tcp_tap_window_update(conn, max_ack_seq_wnd);
+ tcp_tap_window_update(c, conn, max_ack_seq_wnd);
if (retr) {
flow_trace(conn,
@@ -1861,7 +1868,7 @@ static void tcp_conn_from_sock_finish(const struct ctx *c,
const struct tcphdr *th,
const char *opts, size_t optlen)
{
- tcp_tap_window_update(conn, ntohs(th->window));
+ tcp_tap_window_update(c, conn, ntohs(th->window));
tcp_get_tap_ws(conn, opts, optlen);
/* First value is not scaled */
@@ -2059,7 +2066,7 @@ int tcp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af,
if (!th->ack)
goto reset;
- tcp_tap_window_update(conn, ntohs(th->window));
+ tcp_tap_window_update(c, conn, ntohs(th->window));
tcp_data_from_sock(c, conn);
@@ -2071,7 +2078,7 @@ int tcp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af,
if (conn->events & TAP_FIN_RCVD) {
tcp_sock_consume(conn, ntohl(th->ack_seq));
tcp_update_seqack_from_tap(c, conn, ntohl(th->ack_seq));
- tcp_tap_window_update(conn, ntohs(th->window));
+ tcp_tap_window_update(c, conn, ntohs(th->window));
tcp_data_from_sock(c, conn);
if (conn->events & SOCK_FIN_RCVD &&
--
@@ -1257,19 +1257,25 @@ static void tcp_get_tap_ws(struct tcp_tap_conn *conn,
/**
* tcp_tap_window_update() - Process an updated window from tap side
+ * @c: Execution context
* @conn: Connection pointer
* @wnd: Window value, host order, unscaled
*/
-static void tcp_tap_window_update(struct tcp_tap_conn *conn, unsigned wnd)
+static void tcp_tap_window_update(const struct ctx *c,
+ struct tcp_tap_conn *conn, unsigned wnd)
{
wnd = MIN(MAX_WINDOW, wnd << conn->ws_from_tap);
/* Work-around for bug introduced in peer kernel code, commit
- * e2142825c120 ("net: tcp: send zero-window ACK when no memory").
- * We don't update if window shrank to zero.
+ * e2142825c120 ("net: tcp: send zero-window ACK when no memory"): don't
+ * update the window if it shrank to zero, so that we'll eventually
+ * retry to send data, but rewind the sequence as that obviously implies
+ * that no data beyond the updated window will ever be acknowledged.
*/
- if (!wnd && SEQ_LT(conn->seq_ack_from_tap, conn->seq_to_tap))
+ if (!wnd && SEQ_LT(conn->seq_ack_from_tap, conn->seq_to_tap)) {
+ tcp_rewind_seq(c, conn);
return;
+ }
conn->wnd_from_tap = MIN(wnd >> conn->ws_from_tap, USHRT_MAX);
@@ -1694,7 +1700,8 @@ static int tcp_data_from_tap(const struct ctx *c, struct tcp_tap_conn *conn,
tcp_timer_ctl(c, conn);
if (p->count == 1) {
- tcp_tap_window_update(conn, ntohs(th->window));
+ tcp_tap_window_update(c, conn,
+ ntohs(th->window));
return 1;
}
@@ -1772,7 +1779,7 @@ static int tcp_data_from_tap(const struct ctx *c, struct tcp_tap_conn *conn,
if (ack && !tcp_sock_consume(conn, max_ack_seq))
tcp_update_seqack_from_tap(c, conn, max_ack_seq);
- tcp_tap_window_update(conn, max_ack_seq_wnd);
+ tcp_tap_window_update(c, conn, max_ack_seq_wnd);
if (retr) {
flow_trace(conn,
@@ -1861,7 +1868,7 @@ static void tcp_conn_from_sock_finish(const struct ctx *c,
const struct tcphdr *th,
const char *opts, size_t optlen)
{
- tcp_tap_window_update(conn, ntohs(th->window));
+ tcp_tap_window_update(c, conn, ntohs(th->window));
tcp_get_tap_ws(conn, opts, optlen);
/* First value is not scaled */
@@ -2059,7 +2066,7 @@ int tcp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af,
if (!th->ack)
goto reset;
- tcp_tap_window_update(conn, ntohs(th->window));
+ tcp_tap_window_update(c, conn, ntohs(th->window));
tcp_data_from_sock(c, conn);
@@ -2071,7 +2078,7 @@ int tcp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af,
if (conn->events & TAP_FIN_RCVD) {
tcp_sock_consume(conn, ntohl(th->ack_seq));
tcp_update_seqack_from_tap(c, conn, ntohl(th->ack_seq));
- tcp_tap_window_update(conn, ntohs(th->window));
+ tcp_tap_window_update(c, conn, ntohs(th->window));
tcp_data_from_sock(c, conn);
if (conn->events & SOCK_FIN_RCVD &&
--
2.43.0
next prev 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 ` [PATCH 2/6] tcp: Factor sequence rewind for retransmissions into a new function Stefano Brivio
2025-08-15 16:10 ` Stefano Brivio [this message]
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=20250815161042.3606244-4-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).