tcp: remove icsk->icsk_retransmit_timer

Now sk->sk_timer is no longer used by TCP keepalive, we can use
its storage for TCP and MPTCP retransmit timers for better
cache locality.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251124175013.1473655-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: edumazet

Documentation/networking/net_cachelines/inet_connection_sock.rst

@@ -12,7 +12,6 @@ struct inet_sock                    icsk_inet              read_mostly         r
 struct request_sock_queue           icsk_accept_queue
 struct inet_bind_bucket             icsk_bind_hash         read_mostly                             tcp_set_state
 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

include/net/inet_connection_sock.h

@@ -56,7 +56,6 @@ 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
@@ -84,7 +83,6 @@ 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;
 	union {
 		struct timer_list icsk_keepalive_timer;
@@ -193,7 +191,7 @@ static inline void inet_csk_delack_init(struct sock *sk)
 
 static inline unsigned long tcp_timeout_expires(const struct sock *sk)
 {
-	return READ_ONCE(inet_csk(sk)->icsk_retransmit_timer.expires);
+	return READ_ONCE(sk->tcp_retransmit_timer.expires);
 }
 
 static inline unsigned long
@@ -209,7 +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);
@@ -241,7 +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);

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
@@ -482,8 +484,11 @@ struct sock {
 	};
 	struct sk_buff_head	sk_write_queue;
 	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;

net/ipv4/inet_connection_sock.c

@@ -737,7 +737,7 @@ void inet_csk_init_xmit_timers(struct sock *sk,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0);
+	timer_setup(&sk->tcp_retransmit_timer, retransmit_handler, 0);
 	timer_setup(&icsk->icsk_delack_timer, delack_handler, 0);
 	timer_setup(&icsk->icsk_keepalive_timer, keepalive_handler, 0);
 	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
@@ -750,7 +750,7 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
 	smp_store_release(&icsk->icsk_pending, 0);
 	smp_store_release(&icsk->icsk_ack.pending, 0);
 
-	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
+	sk_stop_timer(sk, &sk->tcp_retransmit_timer);
 	sk_stop_timer(sk, &icsk->icsk_delack_timer);
 	sk_stop_timer(sk, &icsk->icsk_keepalive_timer);
 }
@@ -765,7 +765,7 @@ void inet_csk_clear_xmit_timers_sync(struct sock *sk)
 	smp_store_release(&icsk->icsk_pending, 0);
 	smp_store_release(&icsk->icsk_ack.pending, 0);
 
-	sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer);
+	sk_stop_timer_sync(sk, &sk->tcp_retransmit_timer);
 	sk_stop_timer_sync(sk, &icsk->icsk_delack_timer);
 	sk_stop_timer_sync(sk, &icsk->icsk_keepalive_timer);
 }

net/ipv4/tcp_timer.c

@@ -698,7 +698,7 @@ void tcp_write_timer_handler(struct sock *sk)
 		return;
 
 	if (time_after(tcp_timeout_expires(sk), jiffies)) {
-		sk_reset_timer(sk, &icsk->icsk_retransmit_timer,
+		sk_reset_timer(sk, &sk->tcp_retransmit_timer,
 			       tcp_timeout_expires(sk));
 		return;
 	}
@@ -725,12 +725,10 @@ void tcp_write_timer_handler(struct sock *sk)
 
 static void tcp_write_timer(struct timer_list *t)
 {
-	struct inet_connection_sock *icsk =
-			timer_container_of(icsk, t, icsk_retransmit_timer);
-	struct sock *sk = &icsk->icsk_inet.sk;
+	struct sock *sk = timer_container_of(sk, t, tcp_retransmit_timer);
 
 	/* Avoid locking the socket when there is no pending event. */
-	if (!smp_load_acquire(&icsk->icsk_pending))
+	if (!smp_load_acquire(&inet_csk(sk)->icsk_pending))
 		goto out;
 
 	bh_lock_sock(sk);

net/mptcp/protocol.c

@@ -411,9 +411,7 @@ static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb)
 
 static void mptcp_stop_rtx_timer(struct sock *sk)
 {
-	struct inet_connection_sock *icsk = inet_csk(sk);
-
-	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
+	sk_stop_timer(sk, &sk->mptcp_retransmit_timer);
 	mptcp_sk(sk)->timer_ival = 0;
 }
 
@@ -954,20 +952,19 @@ static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list
 
 static bool mptcp_rtx_timer_pending(struct sock *sk)
 {
-	return timer_pending(&inet_csk(sk)->icsk_retransmit_timer);
+	return timer_pending(&sk->mptcp_retransmit_timer);
 }
 
 static void mptcp_reset_rtx_timer(struct sock *sk)
 {
-	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned long tout;
 
 	/* prevent rescheduling on close */
 	if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
 		return;
 
 	tout = mptcp_sk(sk)->timer_ival;
-	sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout);
+	sk_reset_timer(sk, &sk->mptcp_retransmit_timer, jiffies + tout);
 }
 
 bool mptcp_schedule_work(struct sock *sk)
@@ -2354,9 +2351,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 static void mptcp_retransmit_timer(struct timer_list *t)
 {
-	struct inet_connection_sock *icsk = timer_container_of(icsk, t,
-							       icsk_retransmit_timer);
-	struct sock *sk = &icsk->icsk_inet.sk;
+	struct sock *sk = timer_container_of(sk, t, mptcp_retransmit_timer);
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	bh_lock_sock(sk);
@@ -2975,7 +2970,7 @@ static void __mptcp_init_sock(struct sock *sk)
 	spin_lock_init(&msk->fallback_lock);
 
 	/* re-use the csk retrans timer for MPTCP-level retrans */
-	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
+	timer_setup(&sk->mptcp_retransmit_timer, mptcp_retransmit_timer, 0);
 	timer_setup(&msk->sk.mptcp_tout_timer, mptcp_tout_timer, 0);
 }
 

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

@@ -99,10 +99,10 @@ static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp,
 	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active = 1;
-		timer_expires = icsk->icsk_retransmit_timer.expires;
+		timer_expires = sp->tcp_retransmit_timer.expires;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
 		timer_active = 4;
-		timer_expires = icsk->icsk_retransmit_timer.expires;
+		timer_expires = sp->tcp_retransmit_timer.expires;
 	} else if (timer_pending(&icsk->icsk_keepalive_timer)) {
 		timer_active = 2;
 		timer_expires = icsk->icsk_keepalive_timer.expires;

tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c

@@ -99,10 +99,10 @@ static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_sock *tp,
 	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active = 1;
-		timer_expires = icsk->icsk_retransmit_timer.expires;
+		timer_expires = sp->tcp_retransmit_timer.expires;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
 		timer_active = 4;
-		timer_expires = icsk->icsk_retransmit_timer.expires;
+		timer_expires = sp->tcp_retransmit_timer.expires;
 	} else if (timer_pending(&icsk->icsk_keepalive_timer)) {
 		timer_active = 2;
 		timer_expires = icsk->icsk_keepalive_timer.expires;