From 3a6e8fd0bf4042c572dc52e634878b9aca02970d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Nov 2025 17:50:10 +0000 Subject: tcp: rename icsk_timeout() to tcp_timeout_expires() In preparation of sk->tcp_timeout_timer introduction, rename icsk_timeout() helper and change its argument to plain 'const struct sock *sk'. Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20251124175013.1473655-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index fd40af2221b9..765c2149d678 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -184,10 +184,9 @@ 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(inet_csk(sk)->icsk_retransmit_timer.expires); } static inline unsigned long -- cgit v1.2.3 From 27e8257a86516682e2ec5d7543a8909c37ae8b00 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Nov 2025 17:50:11 +0000 Subject: net: move sk_dst_pending_confirm and sk_pacing_status to sock_read_tx group These two fields are mostly read in TCP tx path, move them in an more appropriate group for better cache locality. Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20251124175013.1473655-3-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 4 ++-- net/core/sock.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 38d48cfe0741..a89aa97151f5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -481,8 +481,6 @@ 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; @@ -493,6 +491,8 @@ 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; diff --git a/net/core/sock.c b/net/core/sock.c index b26a6cdc9bcd..45c98bf524b2 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -4519,14 +4519,14 @@ static int __init sock_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_send_head); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_pending); - CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_dst_pending_confirm); - CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_status); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_frag); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_timer); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_zckey); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tskey); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_dst_pending_confirm); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_pacing_status); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_max_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_sndtimeo); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_priority); -- cgit v1.2.3 From 08dfe370239e53494453cee1e2ded2cdaa1efd12 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Nov 2025 17:50:12 +0000 Subject: 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 Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20251124175013.1473655-4-edumazet@google.com Signed-off-by: Jakub Kicinski --- .../networking/net_cachelines/inet_connection_sock.rst | 1 + include/net/inet_connection_sock.h | 11 +++++++++-- net/ipv4/inet_connection_sock.c | 6 +++--- net/ipv4/inet_diag.c | 4 ++-- net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv4/tcp_timer.c | 9 +++++---- net/ipv6/tcp_ipv6.c | 4 ++-- net/mptcp/protocol.c | 10 ++++++---- net/mptcp/protocol.h | 2 +- tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c | 4 ++-- tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c | 4 ++-- 11 files changed, 35 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/Documentation/networking/net_cachelines/inet_connection_sock.rst b/Documentation/networking/net_cachelines/inet_connection_sock.rst index 8fae85ebb773..4f65de2def8c 100644 --- a/Documentation/networking/net_cachelines/inet_connection_sock.rst +++ b/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 diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 765c2149d678..e0d90b996348 100644 --- a/include/net/inet_connection_sock.h +++ b/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; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b4eae731c9ba..4fc09f9bf25d 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/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, diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 9f63c09439a0..3f5b1418a610 100644 --- a/net/ipv4/inet_diag.c +++ b/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) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7b8af2c8d03a..f8a9596e8f4d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/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; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index afbd901e610e..d2678dfd8118 100644 --- a/net/ipv4/tcp_timer.c +++ b/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; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 33c76c3a6da7..280fe5978559 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/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; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 4288b6a53b6e..89a5f63921e6 100644 --- a/net/mptcp/protocol.c +++ b/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); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 313da78e2b75..9c0d17876b22 100644 --- a/net/mptcp/protocol.h +++ b/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; } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c index 164640db3a29..685811326a04 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c +++ b/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(); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c index 591c703f5032..0f4a92712751 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c @@ -103,9 +103,9 @@ static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_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(); -- cgit v1.2.3 From 9a5e5334adc039fa652aa071ea95b18db0bc1f43 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Nov 2025 17:50:13 +0000 Subject: 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 Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20251124175013.1473655-5-edumazet@google.com Signed-off-by: Jakub Kicinski --- .../networking/net_cachelines/inet_connection_sock.rst | 1 - include/net/inet_connection_sock.h | 8 +++----- include/net/sock.h | 9 +++++++-- net/ipv4/inet_connection_sock.c | 6 +++--- net/ipv4/tcp_timer.c | 8 +++----- net/mptcp/protocol.c | 15 +++++---------- tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c | 4 ++-- tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c | 4 ++-- 8 files changed, 25 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/Documentation/networking/net_cachelines/inet_connection_sock.rst b/Documentation/networking/net_cachelines/inet_connection_sock.rst index 4f65de2def8c..cc2000f55c29 100644 --- a/Documentation/networking/net_cachelines/inet_connection_sock.rst +++ b/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 diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index e0d90b996348..ecb362025c4e 100644 --- a/include/net/inet_connection_sock.h +++ b/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); diff --git a/include/net/sock.h b/include/net/sock.h index a89aa97151f5..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 @@ -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; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4fc09f9bf25d..97d57c52b9ad 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/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); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d2678dfd8118..160080c9021d 100644 --- a/net/ipv4/tcp_timer.c +++ b/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); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 89a5f63921e6..bb7d634cf312 100644 --- a/net/mptcp/protocol.c +++ b/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; } @@ -954,12 +952,11 @@ 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 */ @@ -967,7 +964,7 @@ static void mptcp_reset_rtx_timer(struct sock *sk) 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 @@ out_err: 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); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c index 685811326a04..b1e509b231cd 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c +++ b/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; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c index 0f4a92712751..dbc7166aee91 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c +++ b/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; -- cgit v1.2.3