tcp: introduce icsk->icsk_keepalive_timer

sk->sk_timer has been used for TCP keepalives.

Keepalive timers are not in fast path, we want to use sk->sk_timer
storage for retransmit timers, for better cache locality.

Create icsk->icsk_keepalive_timer and change keepalive
code to no longer use sk->sk_timer.

Added space is reclaimed in the following patch.

This includes changes to MPTCP, which was also using sk_timer.

Alias icsk->mptcp_tout_timer and icsk->icsk_keepalive_timer
for inet_sk_diag_fill() sake.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251124175013.1473655-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: edumazet

Documentation/networking/net_cachelines/inet_connection_sock.rst

@@ -14,6 +14,7 @@ struct inet_bind_bucket             icsk_bind_hash         read_mostly
 struct inet_bind2_bucket            icsk_bind2_hash        read_mostly                             tcp_set_state,inet_put_port
 struct timer_list                   icsk_retransmit_timer  read_write                              inet_csk_reset_xmit_timer,tcp_connect
 struct timer_list                   icsk_delack_timer      read_mostly                             inet_csk_reset_xmit_timer,tcp_connect
+struct timer_list                   icsk_keepalive_timer
 u32                                 icsk_rto               read_write                              tcp_cwnd_validate,tcp_schedule_loss_probe,tcp_connect_init,tcp_connect,tcp_write_xmit,tcp_push_one
 u32                                 icsk_rto_min
 u32                                 icsk_rto_max           read_mostly                             tcp_reset_xmit_timer

include/net/inet_connection_sock.h

@@ -57,6 +57,9 @@ struct inet_connection_sock_af_ops {
  * @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 +84,12 @@ 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_retransmit_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;

net/ipv4/inet_connection_sock.c

@@ -739,7 +739,7 @@ void inet_csk_init_xmit_timers(struct sock *sk,
 
 	timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0);
 	timer_setup(&icsk->icsk_delack_timer, delack_handler, 0);
-	timer_setup(&sk->sk_timer, keepalive_handler, 0);
+	timer_setup(&icsk->icsk_keepalive_timer, keepalive_handler, 0);
 	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
 }
 
@@ -752,7 +752,7 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
 
 	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
 	sk_stop_timer(sk, &icsk->icsk_delack_timer);
-	sk_stop_timer(sk, &sk->sk_timer);
+	sk_stop_timer(sk, &icsk->icsk_keepalive_timer);
 }
 
 void inet_csk_clear_xmit_timers_sync(struct sock *sk)
@@ -767,7 +767,7 @@ void inet_csk_clear_xmit_timers_sync(struct sock *sk)
 
 	sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer);
 	sk_stop_timer_sync(sk, &icsk->icsk_delack_timer);
-	sk_stop_timer_sync(sk, &sk->sk_timer);
+	sk_stop_timer_sync(sk, &icsk->icsk_keepalive_timer);
 }
 
 struct dst_entry *inet_csk_route_req(const struct sock *sk,

net/ipv4/inet_diag.c

@@ -293,11 +293,11 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		r->idiag_retrans = READ_ONCE(icsk->icsk_probes_out);
 		r->idiag_expires =
 			jiffies_delta_to_msecs(tcp_timeout_expires(sk) - jiffies);
-	} else if (timer_pending(&sk->sk_timer)) {
+	} else if (timer_pending(&icsk->icsk_keepalive_timer)) {
 		r->idiag_timer = 2;
 		r->idiag_retrans = READ_ONCE(icsk->icsk_probes_out);
 		r->idiag_expires =
-			jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies);
+			jiffies_delta_to_msecs(icsk->icsk_keepalive_timer.expires - jiffies);
 	}
 
 	if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {

net/ipv4/tcp_ipv4.c

@@ -2873,9 +2873,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 	} else if (icsk_pending == ICSK_TIME_PROBE0) {
 		timer_active	= 4;
 		timer_expires	= tcp_timeout_expires(sk);
-	} else if (timer_pending(&sk->sk_timer)) {
+	} else if (timer_pending(&icsk->icsk_keepalive_timer)) {
 		timer_active	= 2;
-		timer_expires	= sk->sk_timer.expires;
+		timer_expires	= icsk->icsk_keepalive_timer.expires;
 	} else {
 		timer_active	= 0;
 		timer_expires = jiffies;

net/ipv4/tcp_timer.c

@@ -755,12 +755,12 @@ void tcp_syn_ack_timeout(const struct request_sock *req)
 
 void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len)
 {
-	sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
+	sk_reset_timer(sk, &inet_csk(sk)->icsk_keepalive_timer, jiffies + len);
 }
 
 static void tcp_delete_keepalive_timer(struct sock *sk)
 {
-	sk_stop_timer(sk, &sk->sk_timer);
+	sk_stop_timer(sk, &inet_csk(sk)->icsk_keepalive_timer);
 }
 
 void tcp_set_keepalive(struct sock *sk, int val)
@@ -777,8 +777,9 @@ EXPORT_IPV6_MOD_GPL(tcp_set_keepalive);
 
 static void tcp_keepalive_timer(struct timer_list *t)
 {
-	struct sock *sk = timer_container_of(sk, t, sk_timer);
-	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk =
+		timer_container_of(icsk, t, icsk_keepalive_timer);
+	struct sock *sk = &icsk->icsk_inet.sk;
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 elapsed;
 

net/ipv6/tcp_ipv6.c

@@ -2167,9 +2167,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	} else if (icsk_pending == ICSK_TIME_PROBE0) {
 		timer_active	= 4;
 		timer_expires	= tcp_timeout_expires(sp);
-	} else if (timer_pending(&sp->sk_timer)) {
+	} else if (timer_pending(&icsk->icsk_keepalive_timer)) {
 		timer_active	= 2;
-		timer_expires	= sp->sk_timer.expires;
+		timer_expires	= icsk->icsk_keepalive_timer.expires;
 	} else {
 		timer_active	= 0;
 		timer_expires = jiffies;

net/mptcp/protocol.c

@@ -2374,7 +2374,9 @@ static void mptcp_retransmit_timer(struct timer_list *t)
 
 static void mptcp_tout_timer(struct timer_list *t)
 {
-	struct sock *sk = timer_container_of(sk, t, sk_timer);
+	struct inet_connection_sock *icsk =
+		timer_container_of(icsk, t, mptcp_tout_timer);
+	struct sock *sk = &icsk->icsk_inet.sk;
 
 	mptcp_schedule_work(sk);
 	sock_put(sk);
@@ -2828,7 +2830,7 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout)
 	 */
 	timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout;
 
-	sk_reset_timer(sk, &sk->sk_timer, timeout);
+	sk_reset_timer(sk, &inet_csk(sk)->mptcp_tout_timer, timeout);
 }
 
 static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
@@ -2974,7 +2976,7 @@ static void __mptcp_init_sock(struct sock *sk)
 
 	/* re-use the csk retrans timer for MPTCP-level retrans */
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
-	timer_setup(&sk->sk_timer, mptcp_tout_timer, 0);
+	timer_setup(&msk->sk.mptcp_tout_timer, mptcp_tout_timer, 0);
 }
 
 static void mptcp_ca_reset(struct sock *sk)
@@ -3176,7 +3178,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	might_sleep();
 
 	mptcp_stop_rtx_timer(sk);
-	sk_stop_timer(sk, &sk->sk_timer);
+	sk_stop_timer(sk, &inet_csk(sk)->mptcp_tout_timer);
 	msk->pm.status = 0;
 	mptcp_release_sched(msk);
 

net/mptcp/protocol.h

@@ -892,7 +892,7 @@ static inline void mptcp_stop_tout_timer(struct sock *sk)
 	if (!inet_csk(sk)->icsk_mtup.probe_timestamp)
 		return;
 
-	sk_stop_timer(sk, &sk->sk_timer);
+	sk_stop_timer(sk, &inet_csk(sk)->mptcp_tout_timer);
 	inet_csk(sk)->icsk_mtup.probe_timestamp = 0;
 }
 

tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c

@@ -103,9 +103,9 @@ static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp,
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
 		timer_active = 4;
 		timer_expires = icsk->icsk_retransmit_timer.expires;
-	} else if (timer_pending(&sp->sk_timer)) {
+	} else if (timer_pending(&icsk->icsk_keepalive_timer)) {
 		timer_active = 2;
-		timer_expires = sp->sk_timer.expires;
+		timer_expires = icsk->icsk_keepalive_timer.expires;
 	} else {
 		timer_active = 0;
 		timer_expires = bpf_jiffies64();