tcp: add a fast path in tcp_delack_timer()

delack timer is not stopped from inet_csk_clear_xmit_timer()
because we do not define INET_CSK_CLEAR_TIMERS.

This is a conscious choice : inet_csk_clear_xmit_timer()
is often called from another cpu. Calling del_timer()
would cause false sharing and lock contention.

This means that very often, tcp_delack_timer() is called
at the timer expiration, while there is no ACK to transmit.

This can be detected very early, avoiding the socket spinlock.

Notes:
- test about tp->compressed_ack is racy,
  but in the unlikely case there is a race, the dedicated
  compressed_ack_timer hrtimer would close it.

- Even if the fast path is not taken, reading
  icsk->icsk_ack.pending and tp->compressed_ack
  before acquiring the socket spinlock reduces
  acquisition time and chances of contention.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20241002173042.917928-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 18 insertions, 6 deletions

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 914d19772704..3c82fad904d4 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -202,7 +202,7 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
 		sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
 #endif
 	} else if (what == ICSK_TIME_DACK) {
-		icsk->icsk_ack.pending = 0;
+		smp_store_release(&icsk->icsk_ack.pending, 0);
 		icsk->icsk_ack.retry = 0;
 #ifdef INET_CSK_CLEAR_TIMERS
 		sk_stop_timer(sk, &icsk->icsk_delack_timer);
@@ -233,7 +233,8 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
 		icsk->icsk_timeout = jiffies + when;
 		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
 	} else if (what == ICSK_TIME_DACK) {
-		icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
+		smp_store_release(&icsk->icsk_ack.pending,
+				  icsk->icsk_ack.pending | ICSK_ACK_TIMER);
 		icsk->icsk_ack.timeout = jiffies + when;
 		sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
 	} else {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8c53385cc808..12e975ed4910 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -776,7 +776,7 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	smp_store_release(&icsk->icsk_pending, 0);
-	icsk->icsk_ack.pending = 0;
+	smp_store_release(&icsk->icsk_ack.pending, 0);
 
 	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
 	sk_stop_timer(sk, &icsk->icsk_delack_timer);
@@ -792,7 +792,7 @@ void inet_csk_clear_xmit_timers_sync(struct sock *sk)
 	sock_not_owned_by_me(sk);
 
 	smp_store_release(&icsk->icsk_pending, 0);
-	icsk->icsk_ack.pending = 0;
+	smp_store_release(&icsk->icsk_ack.pending, 0);
 
 	sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer);
 	sk_stop_timer_sync(sk, &icsk->icsk_delack_timer);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4d0407301603..08772395690d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4224,7 +4224,8 @@ void tcp_send_delayed_ack(struct sock *sk)
 		if (!time_before(timeout, icsk->icsk_ack.timeout))
 			timeout = icsk->icsk_ack.timeout;
 	}
-	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
+	smp_store_release(&icsk->icsk_ack.pending,
+			  icsk->icsk_ack.pending | ICSK_ACK_SCHED | ICSK_ACK_TIMER);
 	icsk->icsk_ack.timeout = timeout;
 	sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
 }
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b7266b9101ce..c3a7442332d4 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -361,6 +361,14 @@ static void tcp_delack_timer(struct timer_list *t)
 			from_timer(icsk, t, icsk_delack_timer);
 	struct sock *sk = &icsk->icsk_inet.sk;
 
+	/* Avoid taking socket spinlock if there is no ACK to send.
+	 * The compressed_ack check is racy, but a separate hrtimer
+	 * will take care of it eventually.
+	 */
+	if (!(smp_load_acquire(&icsk->icsk_ack.pending) & ICSK_ACK_TIMER) &&
+	    !READ_ONCE(tcp_sk(sk)->compressed_ack))
+		goto out;
+
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk)) {
 		tcp_delack_timer_handler(sk);
@@ -371,6 +379,7 @@ static void tcp_delack_timer(struct timer_list *t)
 			sock_hold(sk);
 	}
 	bh_unlock_sock(sk);
+out:
 	sock_put(sk);
 }
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c2317919fc14..e85862352084 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3504,7 +3504,8 @@ static void schedule_3rdack_retransmission(struct sock *ssk)
 	timeout += jiffies;
 
 	WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER);
-	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
+	smp_store_release(&icsk->icsk_ack.pending,
+			  icsk->icsk_ack.pending | ICSK_ACK_SCHED | ICSK_ACK_TIMER);
 	icsk->icsk_ack.timeout = timeout;
 	sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout);
 }