// SPDX-License-Identifier: GPL-2.0-only/* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> */ #include <linux/module.h>#include <linux/gfp.h>#include <net/tcp.h>#include <net/tcp_ecn.h>#include <net/rstreason.h> static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk){ const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); u32 elapsed, user_timeout; s32 remaining; user_timeout = READ_ONCE(icsk->icsk_user_timeout); if (!user_timeout) return icsk->icsk_rto; elapsed = tcp_time_stamp_ts(tp) - tp->retrans_stamp; if (tp->tcp_usec_ts) elapsed /= USEC_PER_MSEC; remaining = user_timeout - elapsed; if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));} u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when){ const struct inet_connection_sock *icsk = inet_csk(sk); u32 user_timeout; s32 remaining; s32 elapsed; user_timeout = READ_ONCE(icsk->icsk_user_timeout); if (!user_timeout || !icsk->icsk_probes_tstamp) return when; elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp; if (unlikely(elapsed < 0)) elapsed = 0; remaining = msecs_to_jiffies(user_timeout) - elapsed; remaining = max_t(int, remaining, TCP_TIMEOUT_MIN); return min_t(u32, remaining, when);} /** * tcp_write_err() - close socket and save error info * @sk: The socket the error has appeared on. * * Returns: Nothing (void) */ static void tcp_write_err(struct sock *sk){ tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);} /** * tcp_out_of_resources() - Close socket if out of resources * @sk: pointer to current socket * @do_reset: send a last packet with reset flag * * Do not allow orphaned sockets to eat all our resources. * This is direct violation of TCP specs, but it is required * to prevent DoS attacks. It is called when a retransmission timeout * or zero probe timeout occurs on orphaned socket. * * Also close if our net namespace is exiting; in that case there is no * hope of ever communicating again since all netns interfaces are already * down (or about to be down), and we need to release our dst references, * which have been moved to the netns loopback interface, so the namespace * can finish exiting. This condition is only possible if we are a kernel * socket, as those do not hold references to the namespace. * * Criteria is still not confirmed experimentally and may change. * We kill the socket, if: * 1. If number of orphaned sockets exceeds an administratively configured * limit. * 2. If we have strong memory pressure. * 3. If our net namespace is exiting. */static int tcp_out_of_resources(struct sock *sk, bool do_reset){ struct tcp_sock *tp = tcp_sk(sk); int shift = 0; /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*tcp_rto_max(sk) || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ if (READ_ONCE(sk->sk_err_soft)) shift++; if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ if ((s32)(tcp_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; } if (!check_net(sock_net(sk))) { /* Not possible to send reset; just close */ tcp_done(sk); return 1; } return 0;} /** * tcp_orphan_retries() - Returns maximal number of retries on an orphaned socket * @sk: Pointer to the current socket. * @alive: bool, socket alive state */static int tcp_orphan_retries(struct sock *sk, bool alive){ int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ /* We know from an ICMP that something is wrong. */ if (READ_ONCE(sk->sk_err_soft) && !alive) retries = 0; /* However, if socket sent something recently, select some safe * number of retries. 8 corresponds to >100 seconds with minimal * RTO of 200msec. */ if (retries == 0 && alive) retries = 8; return retries;} static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk){ const struct net *net = sock_net(sk); int mss; /* Black hole detection */ if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing)) return; if (!icsk->icsk_mtup.enabled) { icsk->icsk_mtup.enabled = 1; icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss); mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor)); mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss)); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);} static unsigned int tcp_model_timeout(struct sock *sk, unsigned int boundary, unsigned int rto_base){ unsigned int linear_backoff_thresh, timeout; linear_backoff_thresh = ilog2(tcp_rto_max(sk) / rto_base); if (boundary <= linear_backoff_thresh) timeout = ((2 << boundary) - 1) * rto_base; else timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * tcp_rto_max(sk); return jiffies_to_msecs(timeout);}/** * retransmits_timed_out() - returns true if this connection has timed out * @sk: The current socket * @boundary: max number of retransmissions * @timeout: A custom timeout value. * If set to 0 the default timeout is calculated and used. * Using TCP_RTO_MIN and the number of unsuccessful retransmits. * * The default "timeout" value this function can calculate and use * is equivalent to the timeout of a TCP Connection * after "boundary" unsuccessful, exponentially backed-off * retransmissions with an initial RTO of TCP_RTO_MIN. */static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout){ struct tcp_sock *tp = tcp_sk(sk); unsigned int start_ts, delta; if (!inet_csk(sk)->icsk_retransmits) return false; start_ts = tp->retrans_stamp; if (likely(timeout == 0)) { unsigned int rto_base = TCP_RTO_MIN; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) rto_base = tcp_timeout_init(sk); timeout = tcp_model_timeout(sk, boundary, rto_base); } if (tp->tcp_usec_ts) { /* delta maybe off up to a jiffy due to timer granularity. */ delta = tp->tcp_mstamp - start_ts + jiffies_to_usecs(1); return (s32)(delta - timeout * USEC_PER_MSEC) >= 0; } return (s32)(tcp_time_stamp_ts(tp) - start_ts - timeout) >= 0;} /* A write timeout has occurred. Process the after effects. */static int tcp_write_timeout(struct sock *sk){ struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); bool expired = false, do_reset; int retry_until, max_retransmits; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) __dst_negative_advice(sk); /* Paired with WRITE_ONCE() in tcp_sock_set_syncnt() */ retry_until = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); max_retransmits = retry_until; if (sk->sk_state == TCP_SYN_SENT) max_retransmits += READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts); expired = icsk->icsk_retransmits >= max_retransmits; } else { if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); __dst_negative_advice(sk); } retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = icsk->icsk_rto < tcp_rto_max(sk); retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || !retransmits_timed_out(sk, retry_until, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; } } if (!expired) expired = retransmits_timed_out(sk, retry_until, READ_ONCE(icsk->icsk_user_timeout)); tcp_fastopen_active_detect_blackhole(sk, expired); mptcp_active_detect_blackhole(sk, expired); if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB, icsk->icsk_retransmits, icsk->icsk_rto, (int)expired); if (expired) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; } if (__sk_rethink_txhash_reset_dst(sk)) { WRITE_ONCE(tp->timeout_rehash, tp->timeout_rehash + 1); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH); } return 0;} /* Called with BH disabled */void tcp_delack_timer_handler(struct sock *sk){ struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return; /* Handling the sack compression case */ if (tp->compressed_ack) { tcp_mstamp_refresh(tp); tcp_sack_compress_send_ack(sk); return; } if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) return; if (time_after(icsk_delack_timeout(icsk), jiffies)) { sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk_delack_timeout(icsk)); return; } icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min3((u32)icsk->icsk_ack.ato << 1, icsk->icsk_rto, (u32)TCP_DELACK_MAX); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } tcp_mstamp_refresh(tp); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); }} /** * tcp_delack_timer() - The TCP delayed ACK timeout handler * @t: Pointer to the timer. (gets casted to struct sock *) * * This function gets (indirectly) called when the kernel timer for a TCP packet * of this socket expires. Calls tcp_delack_timer_handler() to do the actual work. * * Returns: Nothing (void) */static void tcp_delack_timer(struct timer_list *t){ struct inet_connection_sock *icsk = timer_container_of(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); } else { __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk);out: sock_put(sk);} static void tcp_probe_timer(struct sock *sk){ struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; if (tp->packets_out || !skb) { WRITE_ONCE(icsk->icsk_probes_out, 0); icsk->icsk_probes_tstamp = 0; return; } /* RFC 1122 4.2.2.17 requires the sender to stay open indefinitely as * long as the receiver continues to respond probes. We support this by * default and reset icsk_probes_out with incoming ACKs. But if the * socket is orphaned or the user specifies TCP_USER_TIMEOUT, we * kill the socket when the retry count and the time exceeds the * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ if (!icsk->icsk_probes_tstamp) { icsk->icsk_probes_tstamp = tcp_jiffies32; } else { u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); if (user_timeout && (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >= msecs_to_jiffies(user_timeout)) goto abort; } max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { unsigned int rto_max = tcp_rto_max(sk); const bool alive = inet_csk_rto_backoff(icsk, rto_max) < rto_max; max_probes = tcp_orphan_retries(sk, alive); if (!alive && icsk->icsk_backoff >= max_probes) goto abort; if (tcp_out_of_resources(sk, true)) return; } if (icsk->icsk_probes_out >= max_probes) {abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ tcp_send_probe0(sk); }} static void tcp_update_rto_stats(struct sock *sk){ struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); if (!icsk->icsk_retransmits) { tp->total_rto_recoveries++; tp->rto_stamp = tcp_time_stamp_ms(tp); } WRITE_ONCE(icsk->icsk_retransmits, icsk->icsk_retransmits + 1); tp->total_rto++;} /* * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req){ struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int max_retries; tcp_syn_ack_timeout(req); /* Add one more retry for fastopen. * Paired with WRITE_ONCE() in tcp_sock_set_syncnt() */ max_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; } /* Lower cwnd after certain SYNACK timeout like tcp_init_transfer() */ if (icsk->icsk_retransmits == 1) tcp_enter_loss(sk); /* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error * returned from rtx_syn_ack() to make it more persistent like * regular retransmit because if the child socket has been accepted * it's not good to give up too easily. */ tcp_rtx_synack(sk, req); if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok) tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_SEND; req->num_timeout++; tcp_update_rto_stats(sk); if (!tp->retrans_stamp) tp->retrans_stamp = tcp_time_stamp_ts(tp); tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, req->timeout << req->num_timeout, false);} static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct sk_buff *skb, u32 rtx_delta){ const struct inet_connection_sock *icsk = inet_csk(sk);Lines 1–500 of 907. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> */ #include <linux/module.h> #include <linux/gfp.h> #include <net/tcp.h> #include <net/tcp_ecn.h> #include <net/rstreason.h> static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); u32 elapsed, user_timeout; s32 remaining; user_timeout = READ_ONCE(icsk->icsk_user_timeout); if (!user_timeout) return icsk->icsk_rto; elapsed = tcp_time_stamp_ts(tp) - tp->retrans_stamp; if (tp->tcp_usec_ts) elapsed /= USEC_PER_MSEC; remaining = user_timeout - elapsed; if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining)); } u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { const struct inet_connection_sock *icsk = inet_csk(sk); u32 user_timeout; s32 remaining; s32 elapsed; user_timeout = READ_ONCE(icsk->icsk_user_timeout); if (!user_timeout || !icsk->icsk_probes_tstamp) return when; elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp; if (unlikely(elapsed < 0)) elapsed = 0; remaining = msecs_to_jiffies(user_timeout) - elapsed; remaining = max_t(int, remaining, TCP_TIMEOUT_MIN); return min_t(u32, remaining, when); } /** * tcp_write_err() - close socket and save error info * @sk: The socket the error has appeared on. * * Returns: Nothing (void) */ static void tcp_write_err(struct sock *sk) { tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); } /** * tcp_out_of_resources() - Close socket if out of resources * @sk: pointer to current socket * @do_reset: send a last packet with reset flag * * Do not allow orphaned sockets to eat all our resources. * This is direct violation of TCP specs, but it is required * to prevent DoS attacks. It is called when a retransmission timeout * or zero probe timeout occurs on orphaned socket. * * Also close if our net namespace is exiting; in that case there is no * hope of ever communicating again since all netns interfaces are already * down (or about to be down), and we need to release our dst references, * which have been moved to the netns loopback interface, so the namespace * can finish exiting. This condition is only possible if we are a kernel * socket, as those do not hold references to the namespace. * * Criteria is still not confirmed experimentally and may change. * We kill the socket, if: * 1. If number of orphaned sockets exceeds an administratively configured * limit. * 2. If we have strong memory pressure. * 3. If our net namespace is exiting. */ static int tcp_out_of_resources(struct sock *sk, bool do_reset) { struct tcp_sock *tp = tcp_sk(sk); int shift = 0; /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*tcp_rto_max(sk) || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ if (READ_ONCE(sk->sk_err_soft)) shift++; if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ if ((s32)(tcp_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; } if (!check_net(sock_net(sk))) { /* Not possible to send reset; just close */ tcp_done(sk); return 1; } return 0; } /** * tcp_orphan_retries() - Returns maximal number of retries on an orphaned socket * @sk: Pointer to the current socket. * @alive: bool, socket alive state */ static int tcp_orphan_retries(struct sock *sk, bool alive) { int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ /* We know from an ICMP that something is wrong. */ if (READ_ONCE(sk->sk_err_soft) && !alive) retries = 0; /* However, if socket sent something recently, select some safe * number of retries. 8 corresponds to >100 seconds with minimal * RTO of 200msec. */ if (retries == 0 && alive) retries = 8; return retries; } static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) { const struct net *net = sock_net(sk); int mss; /* Black hole detection */ if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing)) return; if (!icsk->icsk_mtup.enabled) { icsk->icsk_mtup.enabled = 1; icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss); mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor)); mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss)); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } static unsigned int tcp_model_timeout(struct sock *sk, unsigned int boundary, unsigned int rto_base) { unsigned int linear_backoff_thresh, timeout; linear_backoff_thresh = ilog2(tcp_rto_max(sk) / rto_base); if (boundary <= linear_backoff_thresh) timeout = ((2 << boundary) - 1) * rto_base; else timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * tcp_rto_max(sk); return jiffies_to_msecs(timeout); } /** * retransmits_timed_out() - returns true if this connection has timed out * @sk: The current socket * @boundary: max number of retransmissions * @timeout: A custom timeout value. * If set to 0 the default timeout is calculated and used. * Using TCP_RTO_MIN and the number of unsuccessful retransmits. * * The default "timeout" value this function can calculate and use * is equivalent to the timeout of a TCP Connection * after "boundary" unsuccessful, exponentially backed-off * retransmissions with an initial RTO of TCP_RTO_MIN. */ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { struct tcp_sock *tp = tcp_sk(sk); unsigned int start_ts, delta; if (!inet_csk(sk)->icsk_retransmits) return false; start_ts = tp->retrans_stamp; if (likely(timeout == 0)) { unsigned int rto_base = TCP_RTO_MIN; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) rto_base = tcp_timeout_init(sk); timeout = tcp_model_timeout(sk, boundary, rto_base); } if (tp->tcp_usec_ts) { /* delta maybe off up to a jiffy due to timer granularity. */ delta = tp->tcp_mstamp - start_ts + jiffies_to_usecs(1); return (s32)(delta - timeout * USEC_PER_MSEC) >= 0; } return (s32)(tcp_time_stamp_ts(tp) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); bool expired = false, do_reset; int retry_until, max_retransmits; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) __dst_negative_advice(sk); /* Paired with WRITE_ONCE() in tcp_sock_set_syncnt() */ retry_until = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); max_retransmits = retry_until; if (sk->sk_state == TCP_SYN_SENT) max_retransmits += READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts); expired = icsk->icsk_retransmits >= max_retransmits; } else { if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); __dst_negative_advice(sk); } retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = icsk->icsk_rto < tcp_rto_max(sk); retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || !retransmits_timed_out(sk, retry_until, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; } } if (!expired) expired = retransmits_timed_out(sk, retry_until, READ_ONCE(icsk->icsk_user_timeout)); tcp_fastopen_active_detect_blackhole(sk, expired); mptcp_active_detect_blackhole(sk, expired); if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB, icsk->icsk_retransmits, icsk->icsk_rto, (int)expired); if (expired) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; } if (__sk_rethink_txhash_reset_dst(sk)) { WRITE_ONCE(tp->timeout_rehash, tp->timeout_rehash + 1); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH); } return 0; } /* Called with BH disabled */ void tcp_delack_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return; /* Handling the sack compression case */ if (tp->compressed_ack) { tcp_mstamp_refresh(tp); tcp_sack_compress_send_ack(sk); return; } if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) return; if (time_after(icsk_delack_timeout(icsk), jiffies)) { sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk_delack_timeout(icsk)); return; } icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min3((u32)icsk->icsk_ack.ato << 1, icsk->icsk_rto, (u32)TCP_DELACK_MAX); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } tcp_mstamp_refresh(tp); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } } /** * tcp_delack_timer() - The TCP delayed ACK timeout handler * @t: Pointer to the timer. (gets casted to struct sock *) * * This function gets (indirectly) called when the kernel timer for a TCP packet * of this socket expires. Calls tcp_delack_timer_handler() to do the actual work. * * Returns: Nothing (void) */ static void tcp_delack_timer(struct timer_list *t) { struct inet_connection_sock *icsk = timer_container_of(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); } else { __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); out: sock_put(sk); } static void tcp_probe_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; if (tp->packets_out || !skb) { WRITE_ONCE(icsk->icsk_probes_out, 0); icsk->icsk_probes_tstamp = 0; return; } /* RFC 1122 4.2.2.17 requires the sender to stay open indefinitely as * long as the receiver continues to respond probes. We support this by * default and reset icsk_probes_out with incoming ACKs. But if the * socket is orphaned or the user specifies TCP_USER_TIMEOUT, we * kill the socket when the retry count and the time exceeds the * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ if (!icsk->icsk_probes_tstamp) { icsk->icsk_probes_tstamp = tcp_jiffies32; } else { u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); if (user_timeout && (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >= msecs_to_jiffies(user_timeout)) goto abort; } max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { unsigned int rto_max = tcp_rto_max(sk); const bool alive = inet_csk_rto_backoff(icsk, rto_max) < rto_max; max_probes = tcp_orphan_retries(sk, alive); if (!alive && icsk->icsk_backoff >= max_probes) goto abort; if (tcp_out_of_resources(sk, true)) return; } if (icsk->icsk_probes_out >= max_probes) { abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ tcp_send_probe0(sk); } } static void tcp_update_rto_stats(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); if (!icsk->icsk_retransmits) { tp->total_rto_recoveries++; tp->rto_stamp = tcp_time_stamp_ms(tp); } WRITE_ONCE(icsk->icsk_retransmits, icsk->icsk_retransmits + 1); tp->total_rto++; } /* * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int max_retries; tcp_syn_ack_timeout(req); /* Add one more retry for fastopen. * Paired with WRITE_ONCE() in tcp_sock_set_syncnt() */ max_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; } /* Lower cwnd after certain SYNACK timeout like tcp_init_transfer() */ if (icsk->icsk_retransmits == 1) tcp_enter_loss(sk); /* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error * returned from rtx_syn_ack() to make it more persistent like * regular retransmit because if the child socket has been accepted * it's not good to give up too easily. */ tcp_rtx_synack(sk, req); if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok) tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_SEND; req->num_timeout++; tcp_update_rto_stats(sk); if (!tp->retrans_stamp) tp->retrans_stamp = tcp_time_stamp_ts(tp); tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, req->timeout << req->num_timeout, false); } static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct sk_buff *skb, u32 rtx_delta) { const struct inet_connection_sock *icsk = inet_csk(sk);