public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
From: Eric Dumazet <edumazet@google.com>
To: "David S . Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	 Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>,
	Neal Cardwell <ncardwell@google.com>,
	 Kuniyuki Iwashima <kuniyu@google.com>,
	netdev@vger.kernel.org, eric.dumazet@gmail.com,
	 Eric Dumazet <edumazet@google.com>
Subject: [PATCH net-next 2/3] tcp: move tcp_rack_update_reo_wnd() to tcp_input.c
Date: Tue, 27 Jan 2026 03:21:46 +0000	[thread overview]
Message-ID: <20260127032147.3498272-3-edumazet@google.com> (raw)
In-Reply-To: <20260127032147.3498272-1-edumazet@google.com>

tcp_rack_update_reo_wnd() is called only once from tcp_ack()

Move it to tcp_input.c so that it can be inlined by the compiler
to save space and cpu cycles.

$ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
add/remove: 0/2 grow/shrink: 1/0 up/down: 110/-153 (-43)
Function                                     old     new   delta
tcp_ack                                     5631    5741    +110
__pfx_tcp_rack_update_reo_wnd                 16       -     -16
tcp_rack_update_reo_wnd                      137       -    -137
Total: Before=22572723, After=22572680, chg -0.00%

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 include/net/tcp.h       |  1 -
 net/ipv4/tcp_input.c    | 43 +++++++++++++++++++++++++++++++++++++++++
 net/ipv4/tcp_recovery.c | 43 -----------------------------------------
 3 files changed, 43 insertions(+), 44 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index efff433de9a4..a4d9f263ea68 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2517,7 +2517,6 @@ extern bool tcp_rack_mark_lost(struct sock *sk);
 extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
 			     u64 xmit_time);
 extern void tcp_rack_reo_timeout(struct sock *sk);
-extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs);
 
 /* tcp_plb.c */
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f2fafba95705..d504a9a9b6ec 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4149,6 +4149,49 @@ static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered,
 	return delivered;
 }
 
+/* Updates the RACK's reo_wnd based on DSACK and no. of recoveries.
+ *
+ * If a DSACK is received that seems like it may have been due to reordering
+ * triggering fast recovery, increment reo_wnd by min_rtt/4 (upper bounded
+ * by srtt), since there is possibility that spurious retransmission was
+ * due to reordering delay longer than reo_wnd.
+ *
+ * Persist the current reo_wnd value for TCP_RACK_RECOVERY_THRESH (16)
+ * no. of successful recoveries (accounts for full DSACK-based loss
+ * recovery undo). After that, reset it to default (min_rtt/4).
+ *
+ * At max, reo_wnd is incremented only once per rtt. So that the new
+ * DSACK on which we are reacting, is due to the spurious retx (approx)
+ * after the reo_wnd has been updated last time.
+ *
+ * reo_wnd is tracked in terms of steps (of min_rtt/4), rather than
+ * absolute value to account for change in rtt.
+ */
+static void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+	     TCP_RACK_STATIC_REO_WND) ||
+	    !rs->prior_delivered)
+		return;
+
+	/* Disregard DSACK if a rtt has not passed since we adjusted reo_wnd */
+	if (before(rs->prior_delivered, tp->rack.last_delivered))
+		tp->rack.dsack_seen = 0;
+
+	/* Adjust the reo_wnd if update is pending */
+	if (tp->rack.dsack_seen) {
+		tp->rack.reo_wnd_steps = min_t(u32, 0xFF,
+					       tp->rack.reo_wnd_steps + 1);
+		tp->rack.dsack_seen = 0;
+		tp->rack.last_delivered = tp->delivered;
+		tp->rack.reo_wnd_persist = TCP_RACK_RECOVERY_THRESH;
+	} else if (!tp->rack.reo_wnd_persist) {
+		tp->rack.reo_wnd_steps = 1;
+	}
+}
+
 /* This routine deals with incoming acks, but not outgoing ones. */
 static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 {
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index c52fd3254b6e..40732b84771e 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -166,49 +166,6 @@ void tcp_rack_reo_timeout(struct sock *sk)
 		tcp_rearm_rto(sk);
 }
 
-/* Updates the RACK's reo_wnd based on DSACK and no. of recoveries.
- *
- * If a DSACK is received that seems like it may have been due to reordering
- * triggering fast recovery, increment reo_wnd by min_rtt/4 (upper bounded
- * by srtt), since there is possibility that spurious retransmission was
- * due to reordering delay longer than reo_wnd.
- *
- * Persist the current reo_wnd value for TCP_RACK_RECOVERY_THRESH (16)
- * no. of successful recoveries (accounts for full DSACK-based loss
- * recovery undo). After that, reset it to default (min_rtt/4).
- *
- * At max, reo_wnd is incremented only once per rtt. So that the new
- * DSACK on which we are reacting, is due to the spurious retx (approx)
- * after the reo_wnd has been updated last time.
- *
- * reo_wnd is tracked in terms of steps (of min_rtt/4), rather than
- * absolute value to account for change in rtt.
- */
-void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
-	     TCP_RACK_STATIC_REO_WND) ||
-	    !rs->prior_delivered)
-		return;
-
-	/* Disregard DSACK if a rtt has not passed since we adjusted reo_wnd */
-	if (before(rs->prior_delivered, tp->rack.last_delivered))
-		tp->rack.dsack_seen = 0;
-
-	/* Adjust the reo_wnd if update is pending */
-	if (tp->rack.dsack_seen) {
-		tp->rack.reo_wnd_steps = min_t(u32, 0xFF,
-					       tp->rack.reo_wnd_steps + 1);
-		tp->rack.dsack_seen = 0;
-		tp->rack.last_delivered = tp->delivered;
-		tp->rack.reo_wnd_persist = TCP_RACK_RECOVERY_THRESH;
-	} else if (!tp->rack.reo_wnd_persist) {
-		tp->rack.reo_wnd_steps = 1;
-	}
-}
-
 /* RFC6582 NewReno recovery for non-SACK connection. It simply retransmits
  * the next unacked packet upon receiving
  * a) three or more DUPACKs to start the fast recovery
-- 
2.53.0.rc1.217.geba53bf80e-goog


  parent reply	other threads:[~2026-01-27  3:21 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-27  3:21 [PATCH net-next 0/3] tcp: make tcp_ack() faster Eric Dumazet
2026-01-27  3:21 ` [PATCH net-next 1/3] tcp: mark tcp_process_tlp_ack() as unlikely Eric Dumazet
2026-01-27  3:27   ` Kuniyuki Iwashima
2026-01-27  3:21 ` Eric Dumazet [this message]
2026-01-27  3:28   ` [PATCH net-next 2/3] tcp: move tcp_rack_update_reo_wnd() to tcp_input.c Kuniyuki Iwashima
2026-01-27  3:21 ` [PATCH net-next 3/3] tcp: move tcp_rack_advance() " Eric Dumazet
2026-01-27  3:29   ` Kuniyuki Iwashima
2026-01-29  3:50 ` [PATCH net-next 0/3] tcp: make tcp_ack() faster patchwork-bot+netdevbpf

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=20260127032147.3498272-3-edumazet@google.com \
    --to=edumazet@google.com \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=horms@kernel.org \
    --cc=kuba@kernel.org \
    --cc=kuniyu@google.com \
    --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