mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Petr Tesarik <ptesarik@suse.com>
To: Paolo Abeni <pabeni@redhat.com>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Neal Cardwell <ncardwell@google.com>,
	Kuniyuki Iwashima <kuniyu@google.com>,
	netdev@vger.kernel.org (open list:NETWORKING [TCP])
Cc: David Ahern <dsahern@kernel.org>,
	Jakub Kicinski <kuba@kernel.org>,
	linux-kernel@vger.kernel.org (open list),
	Petr Tesarik <ptesarik@suse.com>
Subject: [PATCH net v2 2/2] tcp_metrics: use ssthresh value from dst if there is no metrics
Date: Fri, 20 Jun 2025 14:56:44 +0200	[thread overview]
Message-ID: <20250620125644.1045603-3-ptesarik@suse.com> (raw)
In-Reply-To: <20250620125644.1045603-1-ptesarik@suse.com>

If there is no cached TCP metrics entry for a connection, initialize
tp->snd_ssthresh from the corresponding dst entry. Of course, this value
may have to be clamped to tp->snd_cwnd_clamp, but let's not copy and paste
the existing code. Instead, move the check to the common path.

When ssthresh value is zero, the connection should enter initial slow
start, indicated by setting tp->snd_ssthresh to infinity (ignoring the
value of tp->snd_cwnd_clamp). Move this check against zero to the common
path, too.

Fixes: 51c5d0c4b169 ("tcp: Maintain dynamic metrics in local cache.")
Signed-off-by: Petr Tesarik <ptesarik@suse.com>
---
 net/ipv4/tcp_metrics.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index dd8f3457bd72..6f7172ea8bc8 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -473,12 +473,13 @@ void tcp_init_metrics(struct sock *sk)
 	/* ssthresh may have been reduced unnecessarily during.
 	 * 3WHS. Restore it back to its initial default.
 	 */
-	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+	tp->snd_ssthresh = 0;
 	if (!dst)
 		goto reset;
 
 	if (dst_metric_locked(dst, RTAX_CWND))
 		tp->snd_cwnd_clamp = dst_metric(dst, RTAX_CWND);
+	tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH);
 
 	rcu_read_lock();
 	tm = tcp_get_metrics(sk, dst, false);
@@ -487,13 +488,8 @@ void tcp_init_metrics(struct sock *sk)
 		goto reset;
 	}
 
-	val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ?
-	      0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
-	if (val) {
-		tp->snd_ssthresh = val;
-		if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
-			tp->snd_ssthresh = tp->snd_cwnd_clamp;
-	}
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save))
+		tp->snd_ssthresh = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 	val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
 	if (val && tp->reordering != val)
 		tp->reordering = val;
@@ -537,6 +533,11 @@ void tcp_init_metrics(struct sock *sk)
 
 		inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
 	}
+
+	if (!tp->snd_ssthresh)
+		tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+	else if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
+		tp->snd_ssthresh = tp->snd_cwnd_clamp;
 }
 
 bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)
-- 
2.49.0


  parent reply	other threads:[~2025-06-20 12:57 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-20 12:56 [PATCH net v2 0/2] tcp_metrics: fix hanlding of route options Petr Tesarik
2025-06-20 12:56 ` [PATCH net v2 1/2] tcp_metrics: set congestion window clamp from the dst entry Petr Tesarik
2025-06-20 12:56 ` Petr Tesarik [this message]
2025-06-20 13:24 ` [PATCH net v2 0/2] tcp_metrics: fix hanlding of route options Eric Dumazet
2025-06-23  7:36   ` Petr Tesarik
2025-06-23 11:44     ` Eric Dumazet

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=20250620125644.1045603-3-ptesarik@suse.com \
    --to=ptesarik@suse.com \
    --cc=davem@davemloft.net \
    --cc=dsahern@kernel.org \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=kuniyu@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@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.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®