Merge branch 'tcp-provide-better-locality-for-retransmit-timer'

Eric Dumazet says:

====================
tcp: provide better locality for retransmit timer

TCP stack uses three timers per flow, currently spread this way:

- sk->sk_timer : keepalive timer
- icsk->icsk_retransmit_timer : retransmit timer
- icsk->icsk_delack_timer : delayed ack timer

This series moves the retransmit timer to sk->sk_timer location,
to increase data locality in TX paths.

keepalive timers are not often used, this change should be neutral for them.

After the series we have following fields:

- sk->tcp_retransmit_timer : retransmit timer, in sock_write_tx group
- icsk->icsk_delack_timer : delayed ack timer
- icsk->icsk_keepalive_timer : keepalive timer

Moving icsk_delack_timer in a beter location would also be welcomed.
====================

Link: https://patch.msgid.link/20251124175013.1473655-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 21 insertions, 12 deletions

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index fd40af2221b9..ecb362025c4e 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -56,7 +56,9 @@ struct inet_connection_sock_af_ops {
  * @icsk_accept_queue:	   FIFO of established children
  * @icsk_bind_hash:	   Bind node
  * @icsk_bind2_hash:	   Bind node in the bhash2 table
- * @icsk_retransmit_timer: Resend (no ack)
+ * @icsk_delack_timer:     Delayed ACK timer
+ * @icsk_keepalive_timer:  Keepalive timer
+ * @mptcp_tout_timer: mptcp timer
  * @icsk_rto:		   Retransmit timeout
  * @icsk_pmtu_cookie	   Last pmtu seen by socket
  * @icsk_ca_ops		   Pluggable congestion control hook
@@ -81,8 +83,11 @@ struct inet_connection_sock {
 	struct request_sock_queue icsk_accept_queue;
 	struct inet_bind_bucket	  *icsk_bind_hash;
 	struct inet_bind2_bucket  *icsk_bind2_hash;
- 	struct timer_list	  icsk_retransmit_timer;
- 	struct timer_list	  icsk_delack_timer;
+	struct timer_list	  icsk_delack_timer;
+	union {
+		struct timer_list icsk_keepalive_timer;
+		struct timer_list mptcp_tout_timer;
+	};
 	__u32			  icsk_rto;
 	__u32                     icsk_rto_min;
 	u32			  icsk_rto_max;
@@ -184,10 +189,9 @@ static inline void inet_csk_delack_init(struct sock *sk)
 	memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
 }
 
-static inline unsigned long
-icsk_timeout(const struct inet_connection_sock *icsk)
+static inline unsigned long tcp_timeout_expires(const struct sock *sk)
 {
-	return READ_ONCE(icsk->icsk_retransmit_timer.expires);
+	return READ_ONCE(sk->tcp_retransmit_timer.expires);
 }
 
 static inline unsigned long
@@ -203,7 +207,7 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
 	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
 		smp_store_release(&icsk->icsk_pending, 0);
 #ifdef INET_CSK_CLEAR_TIMERS
-		sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
+		sk_stop_timer(sk, &sk->tcp_retransmit_timer);
 #endif
 	} else if (what == ICSK_TIME_DACK) {
 		smp_store_release(&icsk->icsk_ack.pending, 0);
@@ -235,7 +239,7 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
 	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
 	    what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) {
 		smp_store_release(&icsk->icsk_pending, what);
-		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, when);
+		sk_reset_timer(sk, &sk->tcp_retransmit_timer, when);
 	} else if (what == ICSK_TIME_DACK) {
 		smp_store_release(&icsk->icsk_ack.pending,
 				  icsk->icsk_ack.pending | ICSK_ACK_TIMER);
diff --git a/include/net/sock.h b/include/net/sock.h
index 38d48cfe0741..02253c6a578b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -305,6 +305,8 @@ struct sk_filter;
   *	@sk_txrehash: enable TX hash rethink
   *	@sk_filter: socket filtering instructions
   *	@sk_timer: sock cleanup timer
+  *	@tcp_retransmit_timer: tcp retransmit timer
+  *	@mptcp_retransmit_timer: mptcp retransmit timer
   *	@sk_stamp: time stamp of last packet received
   *	@sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
   *	@sk_tsflags: SO_TIMESTAMPING flags
@@ -481,11 +483,12 @@ struct sock {
 		struct rb_root	tcp_rtx_queue;
 	};
 	struct sk_buff_head	sk_write_queue;
-	u32			sk_dst_pending_confirm;
-	u32			sk_pacing_status; /* see enum sk_pacing */
 	struct page_frag	sk_frag;
-	struct timer_list	sk_timer;
-
+	union {
+		struct timer_list	sk_timer;
+		struct timer_list	tcp_retransmit_timer;
+		struct timer_list	mptcp_retransmit_timer;
+	};
 	unsigned long		sk_pacing_rate; /* bytes per second */
 	atomic_t		sk_zckey;
 	atomic_t		sk_tskey;
@@ -493,6 +496,8 @@ struct sock {
 	__cacheline_group_end(sock_write_tx);
 
 	__cacheline_group_begin(sock_read_tx);
+	u32			sk_dst_pending_confirm;
+	u32			sk_pacing_status; /* see enum sk_pacing */
 	unsigned long		sk_max_pacing_rate;
 	long			sk_sndtimeo;
 	u32			sk_priority;