TCP重传导致连接Reset

void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_SOFT); tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED_SOFT); tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick; }

/* * Using different timers for retransmit, delayed acks and probes * We may wish use just one timer maintaining a list of expire jiffies * to optimize. */ void inet_csk_init_xmit_timers(struct sock *sk, void (*retransmit_handler)(struct timer_list *t), void (*delack_handler)(struct timer_list *t), void (*keepalive_handler)(struct timer_list *t)) { struct inet_connection_sock *icsk = inet_csk(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); icsk->icsk_pending = icsk->icsk_ack.pending = 0; }

static void tcp_write_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_retransmit_timer); struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_write_timer_handler(sk); } else { /* delegate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); sock_put(sk); }

void tcp_retransmit_timer(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); if (tp->fastopen_rsk) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); tcp_fastopen_synack_timer(sk); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). */ return; } if (!tp->packets_out || WARN_ON_ONCE(tcp_rtx_queue_empty(sk))) return; tp->tlp_high_seq = 0; if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { /* Receiver dastardly shrinks window. Our retransmits * become zero probes, but we should not timeout this * connection. If the socket is an orphan, time it out, * we cannot allow such beasts to hang infinitely. */ struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", &inet->inet_daddr, ntohs(inet->inet_dport), inet->inet_num, tp->snd_una, tp->snd_nxt); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", &sk->sk_v6_daddr, ntohs(inet->inet_dport), inet->inet_num, tp->snd_una, tp->snd_nxt); } #endif if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) { tcp_write_err(sk); goto out; } tcp_enter_loss(sk); tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1); __sk_dst_reset(sk); goto out_reset_timer; } __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); if (tcp_write_timeout(sk)) goto out; if (icsk->icsk_retransmits == 0) { int mib_idx = 0; if (icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL; else mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL; } else if (icsk->icsk_ca_state == TCP_CA_Loss) { mib_idx = LINUX_MIB_TCPLOSSFAILURES; } else if ((icsk->icsk_ca_state == TCP_CA_Disorder) || tp->sacked_out) { if (tcp_is_sack(tp)) mib_idx = LINUX_MIB_TCPSACKFAILURES; else mib_idx = LINUX_MIB_TCPRENOFAILURES; } if (mib_idx) __NET_INC_STATS(sock_net(sk), mib_idx); } tcp_enter_loss(sk); if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, * do not backoff. */ if (!icsk->icsk_retransmits) icsk->icsk_retransmits = 1; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL), TCP_RTO_MAX); goto out; } /* Increase the timeout each time we retransmit. Note that * we do not increase the rtt estimate. rto is initialized * from rtt, but increases here. Jacobson (SIGCOMM 88) suggests * that doubling rto each time is the least we can get away with. * In KA9Q, Karn uses this for the first few times, and then * goes to quadratic. netBSD doubles, but only goes up to *64, * and clamps at 1 to 64 sec afterwards. Note that 120 sec is * defined in the protocol as the maximum possible RTT. I guess * we'll have to use something other than TCP to talk to the * University of Mars. * * PAWS allows us longer timeouts and large windows, so once * implemented ftp to mars will work nicely. We will have to fix * the 120 second clamps though! */ icsk->icsk_backoff++; icsk->icsk_retransmits++; out_reset_timer: /* If stream is thin, use linear timeouts. Since 'icsk_backoff' is * used to reset timer, set to 0. Recalculate 'icsk_rto' as this * might be increased if the stream oscillates between thin and thick, * thus the old value might already be too high compared to the value * set by 'tcp_set_rto' in tcp_input.c which resets the rto without * backoff. Limit to TCP_THIN_LINEAR_RETRIES before initiating * exponential backoff behaviour to avoid continue hammering * linear-timeout retransmissions into a black hole */ if (sk->sk_state == TCP_ESTABLISHED && (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) && tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; icsk->icsk_rto = clamp(__tcp_set_rto(tp), tcp_rto_min(sk), TCP_RTO_MAX); } else { /* Use normal (exponential) backoff */ icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX); if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0)) __sk_dst_reset(sk); out:; }

/** * 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 || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ if (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, GFP_ATOMIC); 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; }

/* We get here when a process closes a file descriptor (either due to * an explicit close() or as a byproduct of exit()'ing) and there * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ void tcp_send_active_reset(struct sock *sk, gfp_t priority) { struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); /* NOTE: No TCP options attached and we never retransmit this. */ skb = alloc_skb(MAX_TCP_HEADER, priority); if (!skb) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ trace_tcp_send_reset(sk, NULL); }