/* * 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, * Mark Evans, * Corey Minyard * Florian La Roche, * Charles Hedrick, * Linus Torvalds, * Alan Cox, * Matthew Dillon, * Arnt Gulbrandsen, * Jorge Cwik, */ /* * Changes: * Pedro Roque : Fast Retransmit/Recovery. * Two receive queues. * Retransmit queue handled by TCP. * Better retransmit timer handling. * New congestion avoidance. * Header prediction. * Variable renaming. * * Eric : Fast Retransmit. * Randy Scott : MSS option defines. * Eric Schenk : Fixes to slow start algorithm. * Eric Schenk : Yet another double ACK bug. * Eric Schenk : Delayed ACK bug fixes. * Eric Schenk : Floyd style fast retrans war avoidance. * David S. Miller : Don't allow zero congestion window. * Eric Schenk : Fix retransmitter so that it sends * next packet on ack of previous packet. * Andi Kleen : Moved open_request checking here * and process RSTs for open_requests. * Andi Kleen : Better prune_queue, and other fixes. * Andrey Savochkin: Fix RTT measurements in the presence of * timestamps. * Andrey Savochkin: Check sequence numbers correctly when * removing SACKs due to in sequence incoming * data segments. * Andi Kleen: Make sure we never ack data there is not * enough room for. Also make this condition * a fatal error if it might still happen. * Andi Kleen: Add tcp_measure_rcv_mss to make * connections with MSS #include #include #include #include #include #include #include #include #include #include #include int sysctl_tcp_timestamps __read_mostly = 1; int sysctl_tcp_window_scaling __read_mostly = 1; int sysctl_tcp_sack __read_mostly = 1; int sysctl_tcp_fack __read_mostly = 1; int sysctl_tcp_max_reordering __read_mostly = 300; int sysctl_tcp_dsack __read_mostly = 1; int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); /* rfc5961 challenge ack rate limiting */ int sysctl_tcp_challenge_ack_limit = 1000; int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; int sysctl_tcp_max_orphans __read_mostly = NR_FILE; int sysctl_tcp_frto __read_mostly = 2; int sysctl_tcp_min_rtt_wlen __read_mostly = 300; int sysctl_tcp_thin_dupack __read_mostly; int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; int sysctl_tcp_early_retrans __read_mostly = 3; int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; int sysctl_tcp_default_init_rwnd __read_mostly = TCP_INIT_CWND * 2; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ #define FLAG_DATA_ACKED 0x04 /* This ACK acknowledged new data. */ #define FLAG_RETRANS_DATA_ACKED 0x08 /* "" "" some of which was retransmitted. */ #define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */ #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ #define FLAG_LOST_RETRANS 0x80 /* This ACK marks some retransmission lost */ #define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/ #define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ #define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ #define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */ #define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) #define FLAG_CA_ALERT (FLAG_DATA_SACKED|FLAG_ECE) #define FLAG_FORWARD_PROGRESS (FLAG_ACKED|FLAG_DATA_SACKED) #define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH) #define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH)) #define REXMIT_NONE 0 /* no loss recovery to do */ #define REXMIT_LOST 1 /* retransmit packets marked lost */ #define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */ static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, unsigned int len) { static bool __once __read_mostly; if (!__once) { struct net_device *dev; __once = true; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); if (!dev || len >= dev->mtu) pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", dev ? dev->name : "Unknown driver"); rcu_read_unlock(); } } /* Adapt the MSS value used to make delayed ack decision to the * real world. */ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); const unsigned int lss = icsk->icsk_ack.last_seg_size; unsigned int len; icsk->icsk_ack.last_seg_size = 0; /* skb->len may jitter because of SACKs, even if peer * sends good full-sized frames. */ len = skb_shinfo(skb)->gso_size ? : skb->len; if (len >= icsk->icsk_ack.rcv_mss) { icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); /* Account for possibly-removed options */ if (unlikely(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE)) tcp_gro_dev_warn(sk, skb, len); } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. * * "len" is invariant segment length, including TCP header. */ len += skb->data - skb_transport_header(skb); if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) || /* If PSH is not set, packet should be * full sized, provided peer TCP is not badly broken. * This observation (if it is correct 8)) allows * to handle super-low mtu links fairly. */ (len >= TCP_MIN_MSS + sizeof(struct tcphdr) && !(tcp_flag_word(tcp_hdr(skb)) & TCP_REMNANT))) { /* Subtract also invariant (if peer is RFC compliant), * tcp header plus fixed timestamp option length. * Resulting "len" is MSS free of SACK jitter. */ len -= tcp_sk(sk)->tcp_header_len; icsk->icsk_ack.last_seg_size = len; if (len == lss) { icsk->icsk_ack.rcv_mss = len; return; } } if (icsk->icsk_ack.pending & ICSK_ACK_PUSHED) icsk->icsk_ack.pending |= ICSK_ACK_PUSHED2; icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; } } static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned int quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss); if (quickacks == 0) quickacks = 2; quickacks = min(quickacks, max_quickacks); if (quickacks > icsk->icsk_ack.quick) icsk->icsk_ack.quick = quickacks; } void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_incr_quickack(sk, max_quickacks); icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. */ static bool tcp_in_quickack_mode(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); const struct dst_entry *dst = __sk_dst_get(sk); return (dst && dst_metric(dst, RTAX_QUICKACK)) || (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong); } static void tcp_ecn_queue_cwr(struct tcp_sock *tp) { if (tp->ecn_flags & TCP_ECN_OK) tp->ecn_flags |= TCP_ECN_QUEUE_CWR; } static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb) { if (tcp_hdr(skb)->cwr) tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; } static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; } static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) { case INET_ECN_NOT_ECT: /* Funny extension: if ECT is not set on a segment, * and we already seen ECT on a previous segment, * it is probably a retransmit. */ if (tp->ecn_flags & TCP_ECN_SEEN) tcp_enter_quickack_mode(sk, 2); break; case INET_ECN_CE: if (tcp_ca_needs_ecn(sk)) tcp_ca_event(sk, CA_EVENT_ECN_IS_CE); if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) { /* Better not delay acks, sender can have a very low cwnd */ tcp_enter_quickack_mode(sk, 2); tp->ecn_flags |= TCP_ECN_DEMAND_CWR; } tp->ecn_flags |= TCP_ECN_SEEN; break; default: if (tcp_ca_needs_ecn(sk)) tcp_ca_event(sk, CA_EVENT_ECN_NO_CE); tp->ecn_flags |= TCP_ECN_SEEN; break; } } static void tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) { if (tcp_sk(sk)->ecn_flags & TCP_ECN_OK) __tcp_ecn_check_ce(sk, skb); } static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th) { if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || th->cwr)) tp->ecn_flags &= ~TCP_ECN_OK; } static void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th) { if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || !th->cwr)) tp->ecn_flags &= ~TCP_ECN_OK; } static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th) { if (th->ece && !th->syn && (tp->ecn_flags & TCP_ECN_OK)) return true; return false; } /* Buffer size and advertised window tuning. * * 1. Tuning sk->sk_sndbuf, when connection enters established state. */ static void tcp_sndbuf_expand(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; int sndmem, per_mss; u32 nr_segs; /* Worst case is non GSO/TSO : each frame consumes one skb * and skb->head is kmalloced using power of two area of memory */ per_mss = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) + MAX_TCP_HEADER + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); per_mss = roundup_pow_of_two(per_mss) + SKB_DATA_ALIGN(sizeof(struct sk_buff)); nr_segs = max_t(u32, TCP_INIT_CWND, tp->snd_cwnd); nr_segs = max_t(u32, nr_segs, tp->reordering + 1); /* Fast Recovery (RFC 5681 3.2) : * Cubic needs 1.7 factor, rounded to 2 to include * extra cushion (application might react slowly to POLLOUT) */ sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2; sndmem *= nr_segs * per_mss; if (sk->sk_sndbuf < sndmem) sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]); } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) * * All tcp_full_space() is split to two parts: "network" buffer, allocated * forward and advertised in receiver window (tp->rcv_wnd) and * "application buffer", required to isolate scheduling/application * latencies from network. * window_clamp is maximal advertised window. It can be less than * tcp_full_space(), in this case tcp_full_space() - window_clamp * is reserved for "application" buffer. The less window_clamp is * the smoother our behaviour from viewpoint of network, but the lower * throughput and the higher sensitivity of the connection to losses. 8) * * rcv_ssthresh is more strict window_clamp used at "slow start" * phase to predict further behaviour of this connection. * It is used for two goals: * - to enforce header prediction at sender, even when application * requires some significant "application buffer". It is check #1. * - to prevent pruning of receive queue because of misprediction * of receiver window. Check #2. * * The scheme does not work when sender sends good segments opening * window and then starts to feed us spaghetti. But it should work * in common situations. Otherwise, we have to rely on queue collapsing. */ /* Slow part of check#2. */ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); /* Optimize this! */ int truesize = tcp_win_from_space(skb->truesize) >> 1; int window = tcp_win_from_space(sysctl_tcp_rmem[2]) >> 1; while (tp->rcv_ssthresh <= window) { if (truesize <= skb->len) return 2 * inet_csk(sk)->icsk_ack.rcv_mss; truesize >>= 1; window >>= 1; } return 0; } static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); int room; room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh; /* Check #1 */ if (room > 0 && !tcp_under_memory_pressure(sk)) { int incr; /* Check #2. Increase window, if skb with such overhead * will fit to rcvbuf in future. */ if (tcp_win_from_space(skb->truesize) <= skb->len) incr = 2 * tp->advmss; else incr = __tcp_grow_window(sk, skb); if (incr) { incr = max_t(int, incr, 2 * skb->len); tp->rcv_ssthresh += min(room, incr); inet_csk(sk)->icsk_ack.quick |= 1; } } } /* 3. Tuning rcvbuf, when connection enters established state. */ static void tcp_fixup_rcvbuf(struct sock *sk) { u32 mss = tcp_sk(sk)->advmss; int rcvmem; rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER) * tcp_default_init_rwnd(mss); /* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency * Allow enough cushion so that sender is not limited by our window */ if (sysctl_tcp_moderate_rcvbuf) rcvmem <<= 2; if (sk->sk_rcvbuf < rcvmem) sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]); } /* 4. Try to fixup all. It is made immediately after connection enters * established state. */ void tcp_init_buffer_space(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); int maxwin; if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) tcp_fixup_rcvbuf(sk); if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) tcp_sndbuf_expand(sk); tp->rcvq_space.space = tp->rcv_wnd; tp->rcvq_space.time = tcp_time_stamp; tp->rcvq_space.seq = tp->copied_seq; maxwin = tcp_full_space(sk); if (tp->window_clamp >= maxwin) { tp->window_clamp = maxwin; if (sysctl_tcp_app_win && maxwin > 4 * tp->advmss) tp->window_clamp = max(maxwin - (maxwin >> sysctl_tcp_app_win), 4 * tp->advmss); } /* Force reservation of one segment. */ if (sysctl_tcp_app_win && tp->window_clamp > 2 * tp->advmss && tp->window_clamp + tp->advmss > maxwin) tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss); tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); tp->snd_cwnd_stamp = tcp_time_stamp; } /* 5. Recalculate window clamp after socket hit its memory bounds. */ static void tcp_clamp_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_ack.quick = 0; if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_under_memory_pressure(sk) && sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), sysctl_tcp_rmem[2]); } if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss); } /* Initialize RCV_MSS value. * RCV_MSS is an our guess about MSS used by the peer. * We haven't any direct information about the MSS. * It's better to underestimate the RCV_MSS rather than overestimate. * Overestimations make us ACKing less frequently than needed. * Underestimations are more easy to detect and fix by tcp_measure_rcv_mss(). */ void tcp_initialize_rcv_mss(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache); hint = min(hint, tp->rcv_wnd / 2); hint = min(hint, TCP_MSS_DEFAULT); hint = max(hint, TCP_MIN_MSS); inet_csk(sk)->icsk_ack.rcv_mss = hint; } EXPORT_SYMBOL(tcp_initialize_rcv_mss); /* Receiver "autotuning" code. * * The algorithm for RTT estimation w/o timestamps is based on * Dynamic Right-Sizing (DRS) by Wu Feng and Mike Fisk of LANL. * * * More detail on this code can be found at * , * though this reference is out of date. A new paper * is pending. */ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) { u32 new_sample = tp->rcv_rtt_est.rtt; long m = sample; if (m == 0) m = 1; if (new_sample != 0) { /* If we sample in larger samples in the non-timestamp * case, we could grossly overestimate the RTT especially * with chatty applications or bulk transfer apps which * are stalled on filesystem I/O. * * Also, since we are only going for a minimum in the * non-timestamp case, we do not smooth things out * else with timestamps disabled convergence takes too * long. */ if (!win_dep) { m -= (new_sample >> 3); new_sample += m; } else { m <<= 3; if (m < new_sample) new_sample = m; } } else { /* No previous measure. */ new_sample = m << 3; } if (tp->rcv_rtt_est.rtt != new_sample) tp->rcv_rtt_est.rtt = new_sample; } static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) { if (tp->rcv_rtt_est.time == 0) goto new_measure; if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rcv_rtt_est.time, 1); new_measure: tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd; tp->rcv_rtt_est.time = tcp_time_stamp; } static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); if (tp->rx_opt.rcv_tsecr && (TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rx_opt.rcv_tsecr, 0); } /* * This function should be called every time data is copied to user space. * It calculates the appropriate TCP receive buffer space. */ void tcp_rcv_space_adjust(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 copied; int time; time = tcp_time_stamp - tp->rcvq_space.time; if (time < (tp->rcv_rtt_est.rtt >> 3) || tp->rcv_rtt_est.rtt == 0) return; /* Number of bytes copied to user in last RTT */ copied = tp->copied_seq - tp->rcvq_space.seq; if (copied <= tp->rcvq_space.space) goto new_measure; /* A bit of theory : * copied = bytes received in previous RTT, our base window * To cope with packet losses, we need a 2x factor * To cope with slow start, and sender growing its cwin by 100 % * every RTT, we need a 4x factor, because the ACK we are sending * now is for the next RTT, not the current one : * */ if (sysctl_tcp_moderate_rcvbuf && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { int rcvmem, rcvbuf; u64 rcvwin; /* minimal window to cope with packet losses, assuming * steady state. Add some cushion because of small variations. */ rcvwin = ((u64)copied << 1) + 16 * tp->advmss; /* If rate increased by 25%, * assume slow start, rcvwin = 3 * copied * If rate increased by 50%, * assume sender can use 2x growth, rcvwin = 4 * copied */ if (copied >= tp->rcvq_space.space + (tp->rcvq_space.space >> 2)) { if (copied >= tp->rcvq_space.space + (tp->rcvq_space.space >> 1)) rcvwin <<= 1; else rcvwin += (rcvwin >> 1); } rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER); while (tcp_win_from_space(rcvmem) < tp->advmss) rcvmem += 128; do_div(rcvwin, tp->advmss); rcvbuf = min_t(u64, rcvwin * rcvmem, sysctl_tcp_rmem[2]); if (rcvbuf > sk->sk_rcvbuf) { sk->sk_rcvbuf = rcvbuf; /* Make the window clamp follow along. */ tp->window_clamp = tcp_win_from_space(rcvbuf); } } tp->rcvq_space.space = copied; new_measure: tp->rcvq_space.seq = tp->copied_seq; tp->rcvq_space.time = tcp_time_stamp; } /* There is something which you must keep in mind when you analyze the * behavior of the tp->ato delayed ack timeout interval. When a * connection starts up, we want to ack as quickly as possible. The * problem is that "good" TCP's do slow start at the beginning of data * transmission. The means that until we send the first few ACK's the * sender will sit on his end and only queue most of his data, because * he can only send snd_cwnd unacked packets at any given time. For * each ACK we send, he increments snd_cwnd and transmits more of his * queue. -DaveM */ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); u32 now; inet_csk_schedule_ack(sk); tcp_measure_rcv_mss(sk, skb); tcp_rcv_rtt_measure(tp); now = tcp_time_stamp; if (!icsk->icsk_ack.ato) { /* The _first_ data packet received, initialize * delayed ACK engine. */ tcp_incr_quickack(sk, TCP_MAX_QUICKACKS); icsk->icsk_ack.ato = TCP_ATO_MIN; } else { int m = now - icsk->icsk_ack.lrcvtime; if (m <= TCP_ATO_MIN / 2) { /* The fastest case is the first. */ icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + TCP_ATO_MIN / 2; } else if (m < icsk->icsk_ack.ato) { icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + m; if (icsk->icsk_ack.ato > icsk->icsk_rto) icsk->icsk_ack.ato = icsk->icsk_rto; } else if (m > icsk->icsk_rto) { /* Too long gap. Apparently sender failed to * restart window, so that we send ACKs quickly. */ tcp_incr_quickack(sk, TCP_MAX_QUICKACKS); sk_mem_reclaim(sk); } } icsk->icsk_ack.lrcvtime = now; tcp_ecn_check_ce(sk, skb); if (skb->len >= 128) tcp_grow_window(sk, skb); } /* Called to compute a smoothed rtt estimate. The data fed to this * routine either comes from timestamps, or from segments that were * known _not_ to have been retransmitted [see Karn/Partridge * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88 * piece by Van Jacobson. * NOTE: the next three routines used to be one big routine. * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) { struct tcp_sock *tp = tcp_sk(sk); long m = mrtt_us; /* RTT */ u32 srtt = tp->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev * are scaled versions of rtt and mean deviation. * This is designed to be as fast as possible * m stands for "measurement". * * On a 1990 paper the rto value is changed to: * RTO = rtt + 4 * mdev * * Funny. This algorithm seems to be very broken. * These formulae increase RTO, when it should be decreased, increase * too slowly, when it should be increased quickly, decrease too quickly * etc. I guess in BSD RTO takes ONE value, so that it is absolutely * does not matter how to _calculate_ it. Seems, it was trap * that VJ failed to avoid. 8) */ if (srtt != 0) { m -= (srtt >> 3); /* m is now error in rtt est */ srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ m -= (tp->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain * for mdev in this case (alpha*beta). * Like Eifel it also prevents growth of rto, * but also it limits too fast rto decreases, * happening in pure Eifel. */ if (m > 0) m >>= 3; } else { m -= (tp->mdev_us >> 2); /* similar update on mdev */ } tp->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ if (tp->mdev_us > tp->mdev_max_us) { tp->mdev_max_us = tp->mdev_us; if (tp->mdev_max_us > tp->rttvar_us) tp->rttvar_us = tp->mdev_max_us; } if (after(tp->snd_una, tp->rtt_seq)) { if (tp->mdev_max_us < tp->rttvar_us) tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2; tp->rtt_seq = tp->snd_nxt; tp->mdev_max_us = tcp_rto_min_us(sk); } } else { /* no previous measure. */ srtt = m << 3; /* take the measured time to be rtt */ tp->mdev_us = m << 1; /* make sure rto = 3*rtt */ tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk)); tp->mdev_max_us = tp->rttvar_us; tp->rtt_seq = tp->snd_nxt; } tp->srtt_us = max(1U, srtt); } /* Set the sk_pacing_rate to allow proper sizing of TSO packets. * Note: TCP stack does not yet implement pacing. * FQ packet scheduler can be used to implement cheap but effective * TCP pacing, to smooth the burst on large writes when packets * in flight is significantly lower than cwnd (or rwin) */ int sysctl_tcp_pacing_ss_ratio __read_mostly = 200; int sysctl_tcp_pacing_ca_ratio __read_mostly = 120; static void tcp_update_pacing_rate(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u64 rate; /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ rate = (u64)tp->mss_cache * ((USEC_PER_SEC / 100) << 3); /* current rate is (cwnd * mss) / srtt * In Slow Start [1], set sk_pacing_rate to 200 % the current rate. * In Congestion Avoidance phase, set it to 120 % the current rate. * * [1] : Normal Slow Start condition is (tp->snd_cwnd < tp->snd_ssthresh) * If snd_cwnd >= (tp->snd_ssthresh / 2), we are approaching * end of slow start and should slow down. */ if (tp->snd_cwnd < tp->snd_ssthresh / 2) rate *= sysctl_tcp_pacing_ss_ratio; else rate *= sysctl_tcp_pacing_ca_ratio; rate *= max(tp->snd_cwnd, tp->packets_out); if (likely(tp->srtt_us)) do_div(rate, tp->srtt_us); /* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate * without any lock. We want to make sure compiler wont store * intermediate values in this location. */ ACCESS_ONCE(sk->sk_pacing_rate) = min_t(u64, rate, sk->sk_max_pacing_rate); } /* Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ static void tcp_set_rto(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); /* Old crap is replaced with new one. 8) * * More seriously: * 1. If rtt variance happened to be less 50msec, it is hallucination. * It cannot be less due to utterly erratic ACK generation made * at least by solaris and freebsd. "Erratic ACKs" has _nothing_ * to do with delayed acks, because at cwnd>2 true delack timeout * is invisible. Actually, Linux-2.4 also generates erratic * ACKs in some circumstances. */ inet_csk(sk)->icsk_rto = __tcp_set_rto(tp); /* 2. Fixups made earlier cannot be right. * If we do not estimate RTO correctly without them, * all the algo is pure shit and should be replaced * with correct one. It is exactly, which we pretend to do. */ /* NOTE: clamping at TCP_RTO_MIN is not required, current algo * guarantees that rto is higher. */ tcp_bound_rto(sk); } __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst) { __u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0); if (!cwnd) cwnd = TCP_INIT_CWND; return min_t(__u32, cwnd, tp->snd_cwnd_clamp); } /* * Packet counting of FACK is based on in-order assumptions, therefore TCP * disables it when reordering is detected */ void tcp_disable_fack(struct tcp_sock *tp) { /* RFC3517 uses different metric in lost marker => reset on change */ if (tcp_is_fack(tp)) tp->lost_skb_hint = NULL; tp->rx_opt.sack_ok &= ~TCP_FACK_ENABLED; } /* Take a notice that peer is sending D-SACKs */ static void tcp_dsack_seen(struct tcp_sock *tp) { tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; } static void tcp_update_reordering(struct sock *sk, const int metric, const int ts) { struct tcp_sock *tp = tcp_sk(sk); if (metric > tp->reordering) { int mib_idx; tp->reordering = min(sysctl_tcp_max_reordering, metric); /* This exciting event is worth to be remembered. 8) */ if (ts) mib_idx = LINUX_MIB_TCPTSREORDER; else if (tcp_is_reno(tp)) mib_idx = LINUX_MIB_TCPRENOREORDER; else if (tcp_is_fack(tp)) mib_idx = LINUX_MIB_TCPFACKREORDER; else mib_idx = LINUX_MIB_TCPSACKREORDER; NET_INC_STATS(sock_net(sk), mib_idx); #if FASTRETRANS_DEBUG > 1 pr_debug("Disorder%d %d %u f%u s%u rr%d\n", tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, tp->reordering, tp->fackets_out, tp->sacked_out, tp->undo_marker ? tp->undo_retrans : 0); #endif tcp_disable_fack(tp); } if (metric > 0) tcp_disable_early_retrans(tp); tp->rack.reord = 1; } /* This must be called before lost_out is incremented */ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) { if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) || (tp->retransmit_skb_hint && before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->retransmit_skb_hint)->seq))) tp->retransmit_skb_hint = skb; if (!tp->lost_out || after(TCP_SKB_CB(skb)->end_seq, tp->retransmit_high)) tp->retransmit_high = TCP_SKB_CB(skb)->end_seq; } /* Sum the number of packets on the wire we have marked as lost. * There are two cases we care about here: * a) Packet hasn't been marked lost (nor retransmitted), * and this is the first loss. * b) Packet has been marked both lost and retransmitted, * and this means we think it was lost again. */ static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb) { __u8 sacked = TCP_SKB_CB(skb)->sacked; if (!(sacked & TCPCB_LOST) || ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS))) tp->lost += tcp_skb_pcount(skb); } static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb) { if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { tcp_verify_retransmit_hint(tp, skb); tp->lost_out += tcp_skb_pcount(skb); tcp_sum_lost(tp, skb); TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; } } void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) { tcp_verify_retransmit_hint(tp, skb); tcp_sum_lost(tp, skb); if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { tp->lost_out += tcp_skb_pcount(skb); TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; } } /* This procedure tags the retransmission queue when SACKs arrive. * * We have three tag bits: SACKED(S), RETRANS(R) and LOST(L). * Packets in queue with these bits set are counted in variables * sacked_out, retrans_out and lost_out, correspondingly. * * Valid combinations are: * Tag InFlight Description * 0 1 - orig segment is in flight. * S 0 - nothing flies, orig reached receiver. * L 0 - nothing flies, orig lost by net. * R 2 - both orig and retransmit are in flight. * L|R 1 - orig is lost, retransmit is in flight. * S|R 1 - orig reached receiver, retrans is still in flight. * (L|S|R is logically valid, it could occur when L|R is sacked, * but it is equivalent to plain S and code short-curcuits it to S. * L|S is logically invalid, it would mean -1 packet in flight 8)) * * These 6 states form finite state machine, controlled by the following events: * 1. New ACK (+SACK) arrives. (tcp_sacktag_write_queue()) * 2. Retransmission. (tcp_retransmit_skb(), tcp_xmit_retransmit_queue()) * 3. Loss detection event of two flavors: * A. Scoreboard estimator decided the packet is lost. * A'. Reno "three dupacks" marks head of queue lost. * A''. Its FACK modification, head until snd.fack is lost. * B. SACK arrives sacking SND.NXT at the moment, when the * segment was retransmitted. * 4. D-SACK added new rule: D-SACK changes any tag to S. * * It is pleasant to note, that state diagram turns out to be commutative, * so that we are allowed not to be bothered by order of our actions, * when multiple events arrive simultaneously. (see the function below). * * Reordering detection. * -------------------- * Reordering metric is maximal distance, which a packet can be displaced * in packet stream. With SACKs we can estimate it: * * 1. SACK fills old hole and the corresponding segment was not * ever retransmitted -> reordering. Alas, we cannot use it * when segment was retransmitted. * 2. The last flaw is solved with D-SACK. D-SACK arrives * for retransmitted and already SACKed segment -> reordering.. * Both of these heuristics are not used in Loss state, when we cannot * account for retransmits accurately. * * SACK block validation. * ---------------------- * * SACK block range validation checks that the received SACK block fits to * the expected sequence limits, i.e., it is between SND.UNA and SND.NXT. * Note that SND.UNA is not included to the range though being valid because * it means that the receiver is rather inconsistent with itself reporting * SACK reneging when it should advance SND.UNA. Such SACK block this is * perfectly valid, however, in light of RFC2018 which explicitly states * that "SACK block MUST reflect the newest segment. Even if the newest * segment is going to be discarded ...", not that it looks very clever * in case of head skb. Due to potentional receiver driven attacks, we * choose to avoid immediate execution of a walk in write queue due to * reneging and defer head skb's loss recovery to standard loss recovery * procedure that will eventually trigger (nothing forbids us doing this). * * Implements also blockage to start_seq wrap-around. Problem lies in the * fact that though start_seq (s) is before end_seq (i.e., not reversed), * there's no guarantee that it will be before snd_nxt (n). The problem * happens when start_seq resides between end_seq wrap (e_w) and snd_nxt * wrap (s_w): * * <- outs wnd -> <- wrapzone -> * u e n u_w e_w s n_w * | | | | | | | * |<------------+------+----- TCP seqno space --------------+---------->| * ...-- <2^31 ->| |<--------... * ...---- >2^31 ------>| |<--------... * * Current code wouldn't be vulnerable but it's better still to discard such * crazy SACK blocks. Doing this check for start_seq alone closes somewhat * similar case (end_seq after snd_nxt wrap) as earlier reversed check in * snd_nxt wrap -> snd_una region will then become "well defined", i.e., * equal to the ideal case (infinite seqno space without wrap caused issues). * * With D-SACK the lower bound is extended to cover sequence space below * SND.UNA down to undo_marker, which is the last point of interest. Yet * again, D-SACK block must not to go across snd_una (for the same reason as * for the normal SACK blocks, explained above). But there all simplicity * ends, TCP might receive valid D-SACKs below that. As long as they reside * fully below undo_marker they do not affect behavior in anyway and can * therefore be safely ignored. In rare cases (which are more or less * theoretical ones), the D-SACK will nicely cross that boundary due to skb * fragmentation and packet reordering past skb's retransmission. To consider * them correctly, the acceptable range must be extended even more though * the exact amount is rather hard to quantify. However, tp->max_window can * be used as an exaggerated estimate. */ static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack, u32 start_seq, u32 end_seq) { /* Too far in future, or reversed (interpretation is ambiguous) */ if (after(end_seq, tp->snd_nxt) || !before(start_seq, end_seq)) return false; /* Nasty start_seq wrap-around check (see comments above) */ if (!before(start_seq, tp->snd_nxt)) return false; /* In outstanding window? ...This is valid exit for D-SACKs too. * start_seq == snd_una is non-sensical (see comments above) */ if (after(start_seq, tp->snd_una)) return true; if (!is_dsack || !tp->undo_marker) return false; /* ...Then it's D-SACK, and must reside below snd_una completely */ if (after(end_seq, tp->snd_una)) return false; if (!before(start_seq, tp->undo_marker)) return true; /* Too old */ if (!after(end_seq, tp->undo_marker)) return false; /* Undo_marker boundary crossing (overestimates a lot). Known already: * start_seq < undo_marker and end_seq >= undo_marker. */ return !before(start_seq, end_seq - tp->max_window); } static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, struct tcp_sack_block_wire *sp, int num_sacks, u32 prior_snd_una) { struct tcp_sock *tp = tcp_sk(sk); u32 start_seq_0 = get_unaligned_be32(&sp[0].start_seq); u32 end_seq_0 = get_unaligned_be32(&sp[0].end_seq); bool dup_sack = false; if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) { dup_sack = true; tcp_dsack_seen(tp); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECV); } else if (num_sacks > 1) { u32 end_seq_1 = get_unaligned_be32(&sp[1].end_seq); u32 start_seq_1 = get_unaligned_be32(&sp[1].start_seq); if (!after(end_seq_0, end_seq_1) && !before(start_seq_0, start_seq_1)) { dup_sack = true; tcp_dsack_seen(tp); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKOFORECV); } } /* D-SACK for already forgotten data... Do dumb counting. */ if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 && !after(end_seq_0, prior_snd_una) && after(end_seq_0, tp->undo_marker)) tp->undo_retrans--; return dup_sack; } struct tcp_sacktag_state { int reord; int fack_count; /* Timestamps for earliest and latest never-retransmitted segment * that was SACKed. RTO needs the earliest RTT to stay conservative, * but congestion control should still get an accurate delay signal. */ struct skb_mstamp first_sackt; struct skb_mstamp last_sackt; struct rate_sample *rate; int flag; }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, * the incoming SACK may not exactly match but we can find smaller MSS * aligned portion of it that matches. Therefore we might need to fragment * which may fail and creates some hassle (caller must handle error case * returns). * * FIXME: this could be merged to shift decision code */ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, u32 start_seq, u32 end_seq) { int err; bool in_sack; unsigned int pkt_len; unsigned int mss; in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) && !before(end_seq, TCP_SKB_CB(skb)->end_seq); if (tcp_skb_pcount(skb) > 1 && !in_sack && after(TCP_SKB_CB(skb)->end_seq, start_seq)) { mss = tcp_skb_mss(skb); in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq); if (!in_sack) { pkt_len = start_seq - TCP_SKB_CB(skb)->seq; if (pkt_len < mss) pkt_len = mss; } else { pkt_len = end_seq - TCP_SKB_CB(skb)->seq; if (pkt_len < mss) return -EINVAL; } /* Round if necessary so that SACKs cover only full MSSes * and/or the remaining small portion (if present) */ if (pkt_len > mss) { unsigned int new_len = (pkt_len / mss) * mss; if (!in_sack && new_len < pkt_len) new_len += mss; pkt_len = new_len; } if (pkt_len >= skb->len && !in_sack) return 0; err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); if (err < 0) return err; } return in_sack; } /* Mark the given newly-SACKed range as such, adjusting counters and hints. */ static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, int dup_sack, int pcount, const struct skb_mstamp *xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { if (tp->undo_marker && tp->undo_retrans > 0 && after(end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) state->reord = min(fack_count, state->reord); } /* Nothing to do; acked frame is about to be dropped (was ACKed). */ if (!after(end_seq, tp->snd_una)) return sacked; if (!(sacked & TCPCB_SACKED_ACKED)) { tcp_rack_advance(tp, xmit_time, sacked); if (sacked & TCPCB_SACKED_RETRANS) { /* If the segment is not tagged as lost, * we do not clear RETRANS, believing * that retransmission is still in flight. */ if (sacked & TCPCB_LOST) { sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS); tp->lost_out -= pcount; tp->retrans_out -= pcount; } } else { if (!(sacked & TCPCB_RETRANS)) { /* New sack for not retransmitted frame, * which was in hole. It is reordering. */ if (before(start_seq, tcp_highest_sack_seq(tp))) state->reord = min(fack_count, state->reord); if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; if (state->first_sackt.v64 == 0) state->first_sackt = *xmit_time; state->last_sackt = *xmit_time; } if (sacked & TCPCB_LOST) { sacked &= ~TCPCB_LOST; tp->lost_out -= pcount; } } sacked |= TCPCB_SACKED_ACKED; state->flag |= FLAG_DATA_SACKED; tp->sacked_out += pcount; tp->delivered += pcount; /* Out-of-order packets delivered */ fack_count += pcount; /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ if (!tcp_is_fack(tp) && tp->lost_skb_hint && before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) tp->lost_cnt_hint += pcount; if (fack_count > tp->fackets_out) tp->fackets_out = fack_count; } /* D-SACK. We can detect redundant retransmission in S|R and plain R * frames and clear it. undo_retrans is decreased above, L|R frames * are accounted above as well. */ if (dup_sack && (sacked & TCPCB_SACKED_RETRANS)) { sacked &= ~TCPCB_SACKED_RETRANS; tp->retrans_out -= pcount; } return sacked; } /* Shift newly-SACKed bytes from this skb to the immediately previous * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. */ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state, unsigned int pcount, int shifted, int mss, bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev = tcp_write_queue_prev(sk, skb); u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */ u32 end_seq = start_seq + shifted; /* end of newly-SACKed */ BUG_ON(!pcount); /* Adjust counters and hints for the newly sacked sequence * range but discard the return value since prev is already * marked. We must tag the range first because the seq * advancement below implicitly advances * tcp_highest_sack_seq() when skb is highest_sack. */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, &skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; TCP_SKB_CB(prev)->end_seq += shifted; TCP_SKB_CB(skb)->seq += shifted; tcp_skb_pcount_add(prev, pcount); WARN_ON_ONCE(tcp_skb_pcount(skb) < pcount); tcp_skb_pcount_add(skb, -pcount); /* When we're adding to gso_segs == 1, gso_size will be zero, * in theory this shouldn't be necessary but as long as DSACK * code can come after this skb later on it's better to keep * setting gso_size to something. */ if (!TCP_SKB_CB(prev)->tcp_gso_size) TCP_SKB_CB(prev)->tcp_gso_size = mss; /* CHECKME: To clear or not to clear? Mimics normal skb currently */ if (tcp_skb_pcount(skb) <= 1) TCP_SKB_CB(skb)->tcp_gso_size = 0; /* Difference in this won't matter, both ACKed by the same cumul. ACK */ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); if (skb->len > 0) { BUG_ON(!tcp_skb_pcount(skb)); NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKSHIFTED); return false; } /* Whole SKB was eaten :-) */ if (skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = prev; if (skb == tp->lost_skb_hint) { tp->lost_skb_hint = prev; tp->lost_cnt_hint -= tcp_skb_pcount(prev); } TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(prev)->eor = TCP_SKB_CB(skb)->eor; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) TCP_SKB_CB(prev)->end_seq++; if (skb == tcp_highest_sack(sk)) tcp_advance_highest_sack(sk, skb); tcp_skb_collapse_tstamp(prev, skb); if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp.v64)) TCP_SKB_CB(prev)->tx.delivered_mstamp.v64 = 0; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED); return true; } /* I wish gso_size would have a bit more sane initialization than * something-or-zero which complicates things */ static int tcp_skb_seglen(const struct sk_buff *skb) { return tcp_skb_pcount(skb) == 1 ? skb->len : tcp_skb_mss(skb); } /* Shifting pages past head area doesn't work */ static int skb_can_shift(const struct sk_buff *skb) { return !skb_headlen(skb) && skb_is_nonlinear(skb); } int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen) { /* TCP min gso_size is 8 bytes (TCP_MIN_GSO_SIZE) * Since TCP_SKB_CB(skb)->tcp_gso_segs is 16 bits, we need * to make sure not storing more than 65535 * 8 bytes per skb, * even if current MSS is bigger. */ if (unlikely(to->len + shiftlen >= 65535 * TCP_MIN_GSO_SIZE)) return 0; if (unlikely(tcp_skb_pcount(to) + pcount > 65535)) return 0; return skb_shift(to, from, shiftlen); } /* Try collapsing SACK blocks spanning across multiple skbs to a single * skb. */ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state, u32 start_seq, u32 end_seq, bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev; int mss; int next_pcount; int pcount = 0; int len; int in_sack; if (!sk_can_gso(sk)) goto fallback; /* Normally R but no L won't result in plain S */ if (!dup_sack && (TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS) goto fallback; if (!skb_can_shift(skb)) goto fallback; /* This frame is about to be dropped (was ACKed). */ if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) goto fallback; /* Can only happen with delayed DSACK + discard craziness */ if (unlikely(skb == tcp_write_queue_head(sk))) goto fallback; prev = tcp_write_queue_prev(sk, skb); if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback; if (!tcp_skb_can_collapse_to(prev)) goto fallback; in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) && !before(end_seq, TCP_SKB_CB(skb)->end_seq); if (in_sack) { len = skb->len; pcount = tcp_skb_pcount(skb); mss = tcp_skb_seglen(skb); /* TODO: Fix DSACKs to not fragment already SACKed and we can * drop this restriction as unnecessary */ if (mss != tcp_skb_seglen(prev)) goto fallback; } else { if (!after(TCP_SKB_CB(skb)->end_seq, start_seq)) goto noop; /* CHECKME: This is non-MSS split case only?, this will * cause skipped skbs due to advancing loop btw, original * has that feature too */ if (tcp_skb_pcount(skb) <= 1) goto noop; in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq); if (!in_sack) { /* TODO: head merge to next could be attempted here * if (!after(TCP_SKB_CB(skb)->end_seq, end_seq)), * though it might not be worth of the additional hassle * * ...we can probably just fallback to what was done * previously. We could try merging non-SACKed ones * as well but it probably isn't going to buy off * because later SACKs might again split them, and * it would make skb timestamp tracking considerably * harder problem. */ goto fallback; } len = end_seq - TCP_SKB_CB(skb)->seq; BUG_ON(len < 0); BUG_ON(len > skb->len); /* MSS boundaries should be honoured or else pcount will * severely break even though it makes things bit trickier. * Optimize common case to avoid most of the divides */ mss = tcp_skb_mss(skb); /* TODO: Fix DSACKs to not fragment already SACKed and we can * drop this restriction as unnecessary */ if (mss != tcp_skb_seglen(prev)) goto fallback; if (len == mss) { pcount = 1; } else if (len < mss) { goto noop; } else { pcount = len / mss; len = pcount * mss; } } /* tcp_sacktag_one() won't SACK-tag ranges below snd_una */ if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una)) goto fallback; if (!tcp_skb_shift(prev, skb, pcount, len)) goto fallback; if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) goto out; /* Hole filled allows collapsing with the next as well, this is very * useful when hole on every nth skb pattern happens */ if (prev == tcp_write_queue_tail(sk)) goto out; skb = tcp_write_queue_next(sk, prev); if (!skb_can_shift(skb) || (skb == tcp_send_head(sk)) || ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) || (mss != tcp_skb_seglen(skb))) goto out; len = skb->len; next_pcount = tcp_skb_pcount(skb); if (tcp_skb_shift(prev, skb, next_pcount, len)) { pcount += next_pcount; tcp_shifted_skb(sk, skb, state, next_pcount, len, mss, 0); } out: state->fack_count += pcount; return prev; noop: return skb; fallback: NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKSHIFTFALLBACK); return NULL; } static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, struct tcp_sack_block *next_dup, struct tcp_sacktag_state *state, u32 start_seq, u32 end_seq, bool dup_sack_in) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *tmp; tcp_for_write_queue_from(skb, sk) { int in_sack = 0; bool dup_sack = dup_sack_in; if (skb == tcp_send_head(sk)) break; /* queue is in-order => we can short-circuit the walk early */ if (!before(TCP_SKB_CB(skb)->seq, end_seq)) break; if (next_dup && before(TCP_SKB_CB(skb)->seq, next_dup->end_seq)) { in_sack = tcp_match_skb_to_sack(sk, skb, next_dup->start_seq, next_dup->end_seq); if (in_sack > 0) dup_sack = true; } /* skb reference here is a bit tricky to get right, since * shifting can eat and free both this skb and the next, * so not even _safe variant of the loop is enough. */ if (in_sack <= 0) { tmp = tcp_shift_skb_data(sk, skb, state, start_seq, end_seq, dup_sack); if (tmp) { if (tmp != skb) { skb = tmp; continue; } in_sack = 0; } else { in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq); } } if (unlikely(in_sack < 0)) break; if (in_sack) { TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), &skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) tcp_advance_highest_sack(sk, skb); } state->fack_count += tcp_skb_pcount(skb); } return skb; } /* Avoid all extra work that is being done by sacktag while walking in * a normal way */ static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, struct tcp_sacktag_state *state, u32 skip_to_seq) { tcp_for_write_queue_from(skb, sk) { if (skb == tcp_send_head(sk)) break; if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq)) break; state->fack_count += tcp_skb_pcount(skb); } return skb; } static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, struct sock *sk, struct tcp_sack_block *next_dup, struct tcp_sacktag_state *state, u32 skip_to_seq) { if (!next_dup) return skb; if (before(next_dup->start_seq, skip_to_seq)) { skb = tcp_sacktag_skip(skb, sk, state, next_dup->start_seq); skb = tcp_sacktag_walk(skb, sk, NULL, state, next_dup->start_seq, next_dup->end_seq, 1); } return skb; } static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_block *cache) { return cache < tp->recv_sack_cache + ARRAY_SIZE(tp->recv_sack_cache); } static int tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, u32 prior_snd_una, struct tcp_sacktag_state *state) { struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + TCP_SKB_CB(ack_skb)->sacked); struct tcp_sack_block_wire *sp_wire = (struct tcp_sack_block_wire *)(ptr+2); struct tcp_sack_block sp[TCP_NUM_SACKS]; struct tcp_sack_block *cache; struct sk_buff *skb; int num_sacks = min(TCP_NUM_SACKS, (ptr[1] - TCPOLEN_SACK_BASE) >> 3); int used_sacks; bool found_dup_sack = false; int i, j; int first_sack_index; state->flag = 0; state->reord = tp->packets_out; if (!tp->sacked_out) { if (WARN_ON(tp->fackets_out)) tp->fackets_out = 0; tcp_highest_sack_reset(sk); } found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire, num_sacks, prior_snd_una); if (found_dup_sack) { state->flag |= FLAG_DSACKING_ACK; tp->delivered++; /* A spurious retransmission is delivered */ } /* Eliminate too old ACKs, but take into * account more or less fresh ones, they can * contain valid SACK info. */ if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window)) return 0; if (!tp->packets_out) goto out; used_sacks = 0; first_sack_index = 0; for (i = 0; i < num_sacks; i++) { bool dup_sack = !i && found_dup_sack; sp[used_sacks].start_seq = get_unaligned_be32(&sp_wire[i].start_seq); sp[used_sacks].end_seq = get_unaligned_be32(&sp_wire[i].end_seq); if (!tcp_is_sackblock_valid(tp, dup_sack, sp[used_sacks].start_seq, sp[used_sacks].end_seq)) { int mib_idx; if (dup_sack) { if (!tp->undo_marker) mib_idx = LINUX_MIB_TCPDSACKIGNOREDNOUNDO; else mib_idx = LINUX_MIB_TCPDSACKIGNOREDOLD; } else { /* Don't count olds caused by ACK reordering */ if ((TCP_SKB_CB(ack_skb)->ack_seq != tp->snd_una) && !after(sp[used_sacks].end_seq, tp->snd_una)) continue; mib_idx = LINUX_MIB_TCPSACKDISCARD; } NET_INC_STATS(sock_net(sk), mib_idx); if (i == 0) first_sack_index = -1; continue; } /* Ignore very old stuff early */ if (!after(sp[used_sacks].end_seq, prior_snd_una)) { if (i == 0) first_sack_index = -1; continue; } used_sacks++; } /* order SACK blocks to allow in order walk of the retrans queue */ for (i = used_sacks - 1; i > 0; i--) { for (j = 0; j < i; j++) { if (after(sp[j].start_seq, sp[j + 1].start_seq)) { swap(sp[j], sp[j + 1]); /* Track where the first SACK block goes to */ if (j == first_sack_index) first_sack_index = j + 1; } } } skb = tcp_write_queue_head(sk); state->fack_count = 0; i = 0; if (!tp->sacked_out) { /* It's already past, so skip checking against it */ cache = tp->recv_sack_cache + ARRAY_SIZE(tp->recv_sack_cache); } else { cache = tp->recv_sack_cache; /* Skip empty blocks in at head of the cache */ while (tcp_sack_cache_ok(tp, cache) && !cache->start_seq && !cache->end_seq) cache++; } while (i < used_sacks) { u32 start_seq = sp[i].start_seq; u32 end_seq = sp[i].end_seq; bool dup_sack = (found_dup_sack && (i == first_sack_index)); struct tcp_sack_block *next_dup = NULL; if (found_dup_sack && ((i + 1) == first_sack_index)) next_dup = &sp[i + 1]; /* Skip too early cached blocks */ while (tcp_sack_cache_ok(tp, cache) && !before(start_seq, cache->end_seq)) cache++; /* Can skip some work by looking recv_sack_cache? */ if (tcp_sack_cache_ok(tp, cache) && !dup_sack && after(end_seq, cache->start_seq)) { /* Head todo? */ if (before(start_seq, cache->start_seq)) { skb = tcp_sacktag_skip(skb, sk, state, start_seq); skb = tcp_sacktag_walk(skb, sk, next_dup, state, start_seq, cache->start_seq, dup_sack); } /* Rest of the block already fully processed? */ if (!after(end_seq, cache->end_seq)) goto advance_sp; skb = tcp_maybe_skipping_dsack(skb, sk, next_dup, state, cache->end_seq); /* ...tail remains todo... */ if (tcp_highest_sack_seq(tp) == cache->end_seq) { /* ...but better entrypoint exists! */ skb = tcp_highest_sack(sk); if (!skb) break; state->fack_count = tp->fackets_out; cache++; goto walk; } skb = tcp_sacktag_skip(skb, sk, state, cache->end_seq); /* Check overlap against next cached too (past this one already) */ cache++; continue; } if (!before(start_seq, tcp_highest_sack_seq(tp))) { skb = tcp_highest_sack(sk); if (!skb) break; state->fack_count = tp->fackets_out; } skb = tcp_sacktag_skip(skb, sk, state, start_seq); walk: skb = tcp_sacktag_walk(skb, sk, next_dup, state, start_seq, end_seq, dup_sack); advance_sp: i++; } /* Clear the head of the cache sack blocks so we can skip it next time */ for (i = 0; i < ARRAY_SIZE(tp->recv_sack_cache) - used_sacks; i++) { tp->recv_sack_cache[i].start_seq = 0; tp->recv_sack_cache[i].end_seq = 0; } for (j = 0; j < used_sacks; j++) tp->recv_sack_cache[i++] = sp[j]; if ((state->reord < tp->fackets_out) && ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state->reord, 0); tcp_verify_left_out(tp); out: #if FASTRETRANS_DEBUG > 0 WARN_ON((int)tp->sacked_out < 0); WARN_ON((int)tp->lost_out < 0); WARN_ON((int)tp->retrans_out < 0); WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif return state->flag; } /* Limits sacked_out so that sum with lost_out isn't ever larger than * packets_out. Returns false if sacked_out adjustement wasn't necessary. */ static bool tcp_limit_reno_sacked(struct tcp_sock *tp) { u32 holes; holes = max(tp->lost_out, 1U); holes = min(holes, tp->packets_out); if ((tp->sacked_out + holes) > tp->packets_out) { tp->sacked_out = tp->packets_out - holes; return true; } return false; } /* If we receive more dupacks than we expected counting segments * in assumption of absent reordering, interpret this as reordering. * The only another reason could be bug in receiver TCP. */ static void tcp_check_reno_reordering(struct sock *sk, const int addend) { struct tcp_sock *tp = tcp_sk(sk); if (tcp_limit_reno_sacked(tp)) tcp_update_reordering(sk, tp->packets_out + addend, 0); } /* Emulate SACKs for SACKless connection: account for a new dupack. */ static void tcp_add_reno_sack(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 prior_sacked = tp->sacked_out; tp->sacked_out++; tcp_check_reno_reordering(sk, 0); if (tp->sacked_out > prior_sacked) tp->delivered++; /* Some out-of-order packet is delivered */ tcp_verify_left_out(tp); } /* Account for ACK, ACKing some data in Reno Recovery phase. */ static void tcp_remove_reno_sacks(struct sock *sk, int acked) { struct tcp_sock *tp = tcp_sk(sk); if (acked > 0) { /* One ACK acked hole. The rest eat duplicate ACKs. */ tp->delivered += max_t(int, acked - tp->sacked_out, 1); if (acked - 1 >= tp->sacked_out) tp->sacked_out = 0; else tp->sacked_out -= acked - 1; } tcp_check_reno_reordering(sk, acked); tcp_verify_left_out(tp); } static inline void tcp_reset_reno_sack(struct tcp_sock *tp) { tp->sacked_out = 0; } void tcp_clear_retrans(struct tcp_sock *tp) { tp->retrans_out = 0; tp->lost_out = 0; tp->undo_marker = 0; tp->undo_retrans = -1; tp->fackets_out = 0; tp->sacked_out = 0; } static inline void tcp_init_undo(struct tcp_sock *tp) { tp->undo_marker = tp->snd_una; /* Retransmission still in flight may cause DSACKs later. */ tp->undo_retrans = tp->retrans_out ? : -1; } /* Enter Loss state. If we detect SACK reneging, forget all SACK information * and reset tags completely, otherwise preserve SACKs. If receiver * dropped its ofo queue, we will know this due to reneging detection. */ void tcp_enter_loss(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sk_buff *skb; bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; bool is_reneg; /* is receiver reneging on SACKs? */ bool mark_lost; /* Reduce ssthresh if it has not yet been made inside this window. */ if (icsk->icsk_ca_state <= TCP_CA_Disorder || !after(tp->high_seq, tp->snd_una) || (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) { tp->prior_ssthresh = tcp_current_ssthresh(sk); tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); tcp_ca_event(sk, CA_EVENT_LOSS); tcp_init_undo(tp); } tp->snd_cwnd = 1; tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; tp->retrans_out = 0; tp->lost_out = 0; if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); skb = tcp_write_queue_head(sk); is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED); if (is_reneg) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); tp->sacked_out = 0; tp->fackets_out = 0; /* Mark SACK reneging until we recover from this loss event. */ tp->is_sack_reneg = 1; } tcp_clear_all_retrans_hints(tp); tcp_for_write_queue(skb, sk) { if (skb == tcp_send_head(sk)) break; mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || is_reneg); if (mark_lost) tcp_sum_lost(tp, skb); TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; if (mark_lost) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; tp->lost_out += tcp_skb_pcount(skb); tp->retransmit_high = TCP_SKB_CB(skb)->end_seq; } } tcp_verify_left_out(tp); /* Timeout in disordered state after receiving substantial DUPACKs * suggests that the degree of reordering is over-estimated. */ if (icsk->icsk_ca_state <= TCP_CA_Disorder && tp->sacked_out >= net->ipv4.sysctl_tcp_reordering) tp->reordering = min_t(unsigned int, tp->reordering, net->ipv4.sysctl_tcp_reordering); tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; tcp_ecn_queue_cwr(tp); /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous * loss recovery is underway except recurring timeout(s) on * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing */ tp->frto = sysctl_tcp_frto && (new_recovery || icsk->icsk_retransmits) && !inet_csk(sk)->icsk_mtup.probe_size; } /* If ACK arrived pointing to a remembered SACK, it means that our * remembered SACKs do not reflect real state of receiver i.e. * receiver _host_ is heavily congested (or buggy). * * To avoid big spurious retransmission bursts due to transient SACK * scoreboard oddities that look like reneging, we give the receiver a * little time (max(RTT/2, 10ms)) to send us some more ACKs that will * restore sanity to the SACK scoreboard. If the apparent reneging * persists until this RTO then we'll clear the SACK scoreboard. */ static bool tcp_check_sack_reneging(struct sock *sk, int flag) { if (flag & FLAG_SACK_RENEGING) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX); return true; } return false; } static inline int tcp_fackets_out(const struct tcp_sock *tp) { return tcp_is_reno(tp) ? tp->sacked_out + 1 : tp->fackets_out; } /* Heurestics to calculate number of duplicate ACKs. There's no dupACKs * counter when SACK is enabled (without SACK, sacked_out is used for * that purpose). * * Instead, with FACK TCP uses fackets_out that includes both SACKed * segments up to the highest received SACK block so far and holes in * between them. * * With reordering, holes may still be in flight, so RFC3517 recovery * uses pure sacked_out (total number of SACKed segments) even though * it violates the RFC that uses duplicate ACKs, often these are equal * but when e.g. out-of-window ACKs or packet duplication occurs, * they differ. Since neither occurs due to loss, TCP should really * ignore them. */ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) { return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1; } static bool tcp_pause_early_retransmit(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay; /* Delay early retransmit and entering fast recovery for * max(RTT/4, 2msec) unless ack has ECE mark, no RTT samples * available, or RTO is scheduled to fire first. */ if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 || (flag & FLAG_ECE) || !tp->srtt_us) return false; delay = max(usecs_to_jiffies(tp->srtt_us >> 5), msecs_to_jiffies(2)); if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay))) return false; inet_csk_reset_xmit_timer(sk, ICSK_TIME_EARLY_RETRANS, delay, TCP_RTO_MAX); return true; } /* Linux NewReno/SACK/FACK/ECN state machine. * -------------------------------------- * * "Open" Normal state, no dubious events, fast path. * "Disorder" In all the respects it is "Open", * but requires a bit more attention. It is entered when * we see some SACKs or dupacks. It is split of "Open" * mainly to move some processing from fast path to slow one. * "CWR" CWND was reduced due to some Congestion Notification event. * It can be ECN, ICMP source quench, local device congestion. * "Recovery" CWND was reduced, we are fast-retransmitting. * "Loss" CWND was reduced due to RTO timeout or SACK reneging. * * tcp_fastretrans_alert() is entered: * - each incoming ACK, if state is not "Open" * - when arrived ACK is unusual, namely: * * SACK * * Duplicate ACK. * * ECN ECE. * * Counting packets in flight is pretty simple. * * in_flight = packets_out - left_out + retrans_out * * packets_out is SND.NXT-SND.UNA counted in packets. * * retrans_out is number of retransmitted segments. * * left_out is number of segments left network, but not ACKed yet. * * left_out = sacked_out + lost_out * * sacked_out: Packets, which arrived to receiver out of order * and hence not ACKed. With SACKs this number is simply * amount of SACKed data. Even without SACKs * it is easy to give pretty reliable estimate of this number, * counting duplicate ACKs. * * lost_out: Packets lost by network. TCP has no explicit * "loss notification" feedback from network (for now). * It means that this number can be only _guessed_. * Actually, it is the heuristics to predict lossage that * distinguishes different algorithms. * * F.e. after RTO, when all the queue is considered as lost, * lost_out = packets_out and in_flight = retrans_out. * * Essentially, we have now two algorithms counting * lost packets. * * FACK: It is the simplest heuristics. As soon as we decided * that something is lost, we decide that _all_ not SACKed * packets until the most forward SACK are lost. I.e. * lost_out = fackets_out - sacked_out and left_out = fackets_out. * It is absolutely correct estimate, if network does not reorder * packets. And it loses any connection to reality when reordering * takes place. We use FACK by default until reordering * is suspected on the path to this destination. * * NewReno: when Recovery is entered, we assume that one segment * is lost (classic Reno). While we are in Recovery and * a partial ACK arrives, we assume that one more packet * is lost (NewReno). This heuristics are the same in NewReno * and SACK. * * Imagine, that's all! Forget about all this shamanism about CWND inflation * deflation etc. CWND is real congestion window, never inflated, changes * only according to classic VJ rules. * * Really tricky (and requiring careful tuning) part of algorithm * is hidden in functions tcp_time_to_recover() and tcp_xmit_retransmit_queue(). * The first determines the moment _when_ we should reduce CWND and, * hence, slow down forward transmission. In fact, it determines the moment * when we decide that hole is caused by loss, rather than by a reorder. * * tcp_xmit_retransmit_queue() decides, _what_ we should retransmit to fill * holes, caused by lost packets. * * And the most logically complicated part of algorithm is undo * heuristics. We detect false retransmits due to both too early * fast retransmit (reordering) and underestimated RTO, analyzing * timestamps and D-SACKs. When we detect that some segments were * retransmitted by mistake and CWND reduction was wrong, we undo * window reduction and abort recovery phase. This logic is hidden * inside several functions named tcp_try_undo_. */ /* This function decides, when we should leave Disordered state * and enter Recovery phase, reducing congestion window. * * Main question: may we further continue forward transmission * with the same cwnd? */ static bool tcp_time_to_recover(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); __u32 packets_out; int tcp_reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering; /* Trick#1: The loss is proven. */ if (tp->lost_out) return true; /* Not-A-Trick#2 : Classic rule... */ if (tcp_dupack_heuristics(tp) > tp->reordering) return true; /* Trick#4: It is still not OK... But will it be useful to delay * recovery more? */ packets_out = tp->packets_out; if (packets_out <= tp->reordering && tp->sacked_out >= max_t(__u32, packets_out/2, tcp_reordering) && !tcp_may_send_now(sk)) { /* We have nothing to send. This connection is limited * either by receiver window or by application. */ return true; } /* If a thin stream is detected, retransmit after first * received dupack. Employ only if SACK is supported in order * to avoid possible corner-case series of spurious retransmissions * Use only if there are no unsent data. */ if ((tp->thin_dupack || sysctl_tcp_thin_dupack) && tcp_stream_is_thin(tp) && tcp_dupack_heuristics(tp) > 1 && tcp_is_sack(tp) && !tcp_send_head(sk)) return true; /* Trick#6: TCP early retransmit, per RFC5827. To avoid spurious * retransmissions due to small network reorderings, we implement * Mitigation A.3 in the RFC and delay the retransmission for a short * interval if appropriate. */ if (tp->do_early_retrans && !tp->retrans_out && tp->sacked_out && (tp->packets_out >= (tp->sacked_out + 1) && tp->packets_out < 4) && !tcp_may_send_now(sk)) return !tcp_pause_early_retransmit(sk, flag); return false; } /* Detect loss in event "A" above by marking head of queue up as lost. * For FACK or non-SACK(Reno) senders, the first "packets" number of segments * are considered lost. For RFC3517 SACK, a segment is considered lost if it * has at least tp->reordering SACKed seqments above it; "packets" refers to * the maximum SACKed segments to pass before reaching this limit. */ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int cnt, oldcnt, lost; unsigned int mss; /* Use SACK to deduce losses of new sequences sent during recovery */ const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; WARN_ON(packets > tp->packets_out); if (tp->lost_skb_hint) { skb = tp->lost_skb_hint; cnt = tp->lost_cnt_hint; /* Head already handled? */ if (mark_head && skb != tcp_write_queue_head(sk)) return; } else { skb = tcp_write_queue_head(sk); cnt = 0; } tcp_for_write_queue_from(skb, sk) { if (skb == tcp_send_head(sk)) break; /* TODO: do this better */ /* this is not the most efficient way to do this... */ tp->lost_skb_hint = skb; tp->lost_cnt_hint = cnt; if (after(TCP_SKB_CB(skb)->end_seq, loss_high)) break; oldcnt = cnt; if (tcp_is_fack(tp) || tcp_is_reno(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) cnt += tcp_skb_pcount(skb); if (cnt > packets) { if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || (oldcnt >= packets)) break; mss = tcp_skb_mss(skb); /* If needed, chop off the prefix to mark as lost. */ lost = (packets - oldcnt) * mss; if (lost < skb->len && tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } tcp_skb_mark_lost(tp, skb); if (mark_head) break; } tcp_verify_left_out(tp); } /* Account newly detected lost packet(s) */ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) { struct tcp_sock *tp = tcp_sk(sk); if (tcp_is_reno(tp)) { tcp_mark_head_lost(sk, 1, 1); } else if (tcp_is_fack(tp)) { int lost = tp->fackets_out - tp->reordering; if (lost <= 0) lost = 1; tcp_mark_head_lost(sk, lost, 0); } else { int sacked_upto = tp->sacked_out - tp->reordering; if (sacked_upto >= 0) tcp_mark_head_lost(sk, sacked_upto, 0); else if (fast_rexmit) tcp_mark_head_lost(sk, 1, 1); } } static bool tcp_tsopt_ecr_before(const struct tcp_sock *tp, u32 when) { return tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && before(tp->rx_opt.rcv_tsecr, when); } /* skb is spurious retransmitted if the returned timestamp echo * reply is prior to the skb transmission time */ static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp, const struct sk_buff *skb) { return (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) && tcp_tsopt_ecr_before(tp, tcp_skb_timestamp(skb)); } /* Nothing was retransmitted or returned timestamp is less * than timestamp of the first retransmission. */ static inline bool tcp_packet_delayed(const struct tcp_sock *tp) { return !tp->retrans_stamp || tcp_tsopt_ecr_before(tp, tp->retrans_stamp); } /* Undo procedures. */ /* We can clear retrans_stamp when there are no retransmissions in the * window. It would seem that it is trivially available for us in * tp->retrans_out, however, that kind of assumptions doesn't consider * what will happen if errors occur when sending retransmission for the * second time. ...It could the that such segment has only * TCPCB_EVER_RETRANS set at the present time. It seems that checking * the head skb is enough except for some reneging corner cases that * are not worth the effort. * * Main reason for all this complexity is the fact that connection dying * time now depends on the validity of the retrans_stamp, in particular, * that successive retransmissions of a segment must not advance * retrans_stamp under any conditions. */ static bool tcp_any_retrans_done(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; if (tp->retrans_out) return true; skb = tcp_write_queue_head(sk); if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) return true; return false; } #if FASTRETRANS_DEBUG > 1 static void DBGUNDO(struct sock *sk, const char *msg) { struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { pr_debug("Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n", msg, &inet->inet_daddr, ntohs(inet->inet_dport), tp->snd_cwnd, tcp_left_out(tp), tp->snd_ssthresh, tp->prior_ssthresh, tp->packets_out); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n", msg, &sk->sk_v6_daddr, ntohs(inet->inet_dport), tp->snd_cwnd, tcp_left_out(tp), tp->snd_ssthresh, tp->prior_ssthresh, tp->packets_out); } #endif } #else #define DBGUNDO(x...) do { } while (0) #endif static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) { struct tcp_sock *tp = tcp_sk(sk); if (unmark_loss) { struct sk_buff *skb; tcp_for_write_queue(skb, sk) { if (skb == tcp_send_head(sk)) break; TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; } tp->lost_out = 0; tcp_clear_all_retrans_hints(tp); } if (tp->prior_ssthresh) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->undo_cwnd) tp->snd_cwnd = icsk->icsk_ca_ops->undo_cwnd(sk); else tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1); if (tp->prior_ssthresh > tp->snd_ssthresh) { tp->snd_ssthresh = tp->prior_ssthresh; tcp_ecn_withdraw_cwr(tp); } } tp->snd_cwnd_stamp = tcp_time_stamp; tp->undo_marker = 0; } static inline bool tcp_may_undo(const struct tcp_sock *tp) { return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp)); } /* People celebrate: "We love our President!" */ static bool tcp_try_undo_recovery(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (tcp_may_undo(tp)) { int mib_idx; /* Happy end! We did not retransmit anything * or our original transmission succeeded. */ DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans"); tcp_undo_cwnd_reduction(sk, false); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) mib_idx = LINUX_MIB_TCPLOSSUNDO; else mib_idx = LINUX_MIB_TCPFULLUNDO; NET_INC_STATS(sock_net(sk), mib_idx); } if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { /* Hold old state until something *above* high_seq * is ACKed. For Reno it is MUST to prevent false * fast retransmits (RFC2582). SACK TCP is safe. */ if (!tcp_any_retrans_done(sk)) tp->retrans_stamp = 0; return true; } tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; return false; } /* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */ static bool tcp_try_undo_dsack(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (tp->undo_marker && !tp->undo_retrans) { DBGUNDO(sk, "D-SACK"); tcp_undo_cwnd_reduction(sk, false); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKUNDO); return true; } return false; } /* Undo during loss recovery after partial ACK or using F-RTO. */ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) { struct tcp_sock *tp = tcp_sk(sk); if (frto_undo || tcp_may_undo(tp)) { tcp_undo_cwnd_reduction(sk, true); DBGUNDO(sk, "partial loss"); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSUNDO); if (frto_undo) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); inet_csk(sk)->icsk_retransmits = 0; if (frto_undo || tcp_is_sack(tp)) { tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; } return true; } return false; } /* The cwnd reduction in CWR and Recovery uses the PRR algorithm in RFC 6937. * It computes the number of packets to send (sndcnt) based on packets newly * delivered: * 1) If the packets in flight is larger than ssthresh, PRR spreads the * cwnd reductions across a full RTT. * 2) Otherwise PRR uses packet conservation to send as much as delivered. * But when the retransmits are acked without further losses, PRR * slow starts cwnd up to ssthresh to speed up the recovery. */ static void tcp_init_cwnd_reduction(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); tp->high_seq = tp->snd_nxt; tp->tlp_high_seq = 0; tp->snd_cwnd_cnt = 0; tp->prior_cwnd = tp->snd_cwnd; tp->prr_delivered = 0; tp->prr_out = 0; tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk); tcp_ecn_queue_cwr(tp); } static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag) { struct tcp_sock *tp = tcp_sk(sk); int sndcnt = 0; int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp); if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd)) return; tp->prr_delivered += newly_acked_sacked; if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + tp->prior_cwnd - 1; sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; } else if ((flag & FLAG_RETRANS_DATA_ACKED) && !(flag & FLAG_LOST_RETRANS)) { sndcnt = min_t(int, delta, max_t(int, tp->prr_delivered - tp->prr_out, newly_acked_sacked) + 1); } else { sndcnt = min(delta, newly_acked_sacked); } /* Force a fast retransmit upon entering fast recovery */ sndcnt = max(sndcnt, (tp->prr_out ? 0 : 1)); tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; } static inline void tcp_end_cwnd_reduction(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (inet_csk(sk)->icsk_ca_ops->cong_control) return; /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH && (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) { tp->snd_cwnd = tp->snd_ssthresh; tp->snd_cwnd_stamp = tcp_time_stamp; } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } /* Enter CWR state. Disable cwnd undo since congestion is proven with ECN */ void tcp_enter_cwr(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); tp->prior_ssthresh = 0; if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { tp->undo_marker = 0; tcp_init_cwnd_reduction(sk); tcp_set_ca_state(sk, TCP_CA_CWR); } } EXPORT_SYMBOL(tcp_enter_cwr); static void tcp_try_keep_open(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); int state = TCP_CA_Open; if (tcp_left_out(tp) || tcp_any_retrans_done(sk)) state = TCP_CA_Disorder; if (inet_csk(sk)->icsk_ca_state != state) { tcp_set_ca_state(sk, state); tp->high_seq = tp->snd_nxt; } } static void tcp_try_to_open(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); tcp_verify_left_out(tp); if (!tcp_any_retrans_done(sk)) tp->retrans_stamp = 0; if (flag & FLAG_ECE) tcp_enter_cwr(sk); if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); } } static void tcp_mtup_probe_failed(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1; icsk->icsk_mtup.probe_size = 0; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPFAIL); } static void tcp_mtup_probe_success(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); /* FIXME: breaks with very large cwnd */ tp->prior_ssthresh = tcp_current_ssthresh(sk); tp->snd_cwnd = tp->snd_cwnd * tcp_mss_to_mtu(sk, tp->mss_cache) / icsk->icsk_mtup.probe_size; tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; tp->snd_ssthresh = tcp_current_ssthresh(sk); icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; icsk->icsk_mtup.probe_size = 0; tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); } /* Do a simple retransmit without using the backoff mechanisms in * tcp_timer. This is used for path mtu discovery. * The socket is already locked here. */ void tcp_simple_retransmit(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int mss = tcp_current_mss(sk); u32 prior_lost = tp->lost_out; tcp_for_write_queue(skb, sk) { if (skb == tcp_send_head(sk)) break; if (tcp_skb_seglen(skb) > mss && !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; tp->retrans_out -= tcp_skb_pcount(skb); } tcp_skb_mark_lost_uncond_verify(tp, skb); } } tcp_clear_retrans_hints_partial(tp); if (prior_lost == tp->lost_out) return; if (tcp_is_reno(tp)) tcp_limit_reno_sacked(tp); tcp_verify_left_out(tp); /* Don't muck with the congestion window here. * Reason is that we do not increase amount of _data_ * in network, but units changed and effective * cwnd/ssthresh really reduced now. */ if (icsk->icsk_ca_state != TCP_CA_Loss) { tp->high_seq = tp->snd_nxt; tp->snd_ssthresh = tcp_current_ssthresh(sk); tp->prior_ssthresh = 0; tp->undo_marker = 0; tcp_set_ca_state(sk, TCP_CA_Loss); } tcp_xmit_retransmit_queue(sk); } EXPORT_SYMBOL(tcp_simple_retransmit); static void tcp_enter_recovery(struct sock *sk, bool ece_ack) { struct tcp_sock *tp = tcp_sk(sk); int mib_idx; if (tcp_is_reno(tp)) mib_idx = LINUX_MIB_TCPRENORECOVERY; else mib_idx = LINUX_MIB_TCPSACKRECOVERY; NET_INC_STATS(sock_net(sk), mib_idx); tp->prior_ssthresh = 0; tcp_init_undo(tp); if (!tcp_in_cwnd_reduction(sk)) { if (!ece_ack) tp->prior_ssthresh = tcp_current_ssthresh(sk); tcp_init_cwnd_reduction(sk); } tcp_set_ca_state(sk, TCP_CA_Recovery); } /* Process an ACK in CA_Loss state. Move to CA_Open if lost data are * recovered or spurious. Otherwise retransmits more on partial ACKs. */ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, int *rexmit) { struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); if ((flag & FLAG_SND_UNA_ADVANCED) && tcp_try_undo_loss(sk, false)) return; if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ /* Step 3.b. A timeout is spurious if not all data are * lost, i.e., never-retransmitted data are (s)acked. */ if ((flag & FLAG_ORIG_SACK_ACKED) && tcp_try_undo_loss(sk, true)) return; if (after(tp->snd_nxt, tp->high_seq)) { if (flag & FLAG_DATA_SACKED || is_dupack) tp->frto = 0; /* Step 3.a. loss was real */ } else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) { tp->high_seq = tp->snd_nxt; /* Step 2.b. Try send new data (but deferred until cwnd * is updated in tcp_ack()). Otherwise fall back to * the conventional recovery. */ if (tcp_send_head(sk) && after(tcp_wnd_end(tp), tp->snd_nxt)) { *rexmit = REXMIT_NEW; return; } tp->frto = 0; } } if (recovered) { /* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */ tcp_try_undo_recovery(sk); return; } if (tcp_is_reno(tp)) { /* A Reno DUPACK means new data in F-RTO step 2.b above are * delivered. Lower inflight to clock out (re)tranmissions. */ if (after(tp->snd_nxt, tp->high_seq) && is_dupack) tcp_add_reno_sack(sk); else if (flag & FLAG_SND_UNA_ADVANCED) tcp_reset_reno_sack(tp); } *rexmit = REXMIT_LOST; } /* Undo during fast recovery after partial ACK. */ static bool tcp_try_undo_partial(struct sock *sk, const int acked) { struct tcp_sock *tp = tcp_sk(sk); if (tp->undo_marker && tcp_packet_delayed(tp)) { /* Plain luck! Hole if filled with delayed * packet, rather than with a retransmit. */ tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1); /* We are getting evidence that the reordering degree is higher * than we realized. If there are no retransmits out then we * can undo. Otherwise we clock out new packets but do not * mark more packets lost or retransmit more. */ if (tp->retrans_out) return true; if (!tcp_any_retrans_done(sk)) tp->retrans_stamp = 0; DBGUNDO(sk, "partial recovery"); tcp_undo_cwnd_reduction(sk, true); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); tcp_try_keep_open(sk); return true; } return false; } /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and * packets lost by network. * * Besides that it updates the congestion state when packet loss or ECN * is detected. But it does not reduce the cwnd, it is done by the * congestion control later. * * It does _not_ decide what to send, it is made in function * tcp_xmit_retransmit_queue(). */ static void tcp_fastretrans_alert(struct sock *sk, const int acked, bool is_dupack, int *ack_flag, int *rexmit) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int fast_rexmit = 0, flag = *ack_flag; bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); if (!tp->packets_out && tp->sacked_out) tp->sacked_out = 0; if (!tp->sacked_out && tp->fackets_out) tp->fackets_out = 0; /* Now state machine starts. * A. ECE, hence prohibit cwnd undoing, the reduction is required. */ if (flag & FLAG_ECE) tp->prior_ssthresh = 0; /* B. In all the states check for reneging SACKs. */ if (tcp_check_sack_reneging(sk, flag)) return; /* C. Check consistency of the current state. */ tcp_verify_left_out(tp); /* D. Check state exit conditions. State can be terminated * when high_seq is ACKed. */ if (icsk->icsk_ca_state == TCP_CA_Open) { WARN_ON(tp->retrans_out != 0); tp->retrans_stamp = 0; } else if (!before(tp->snd_una, tp->high_seq)) { switch (icsk->icsk_ca_state) { case TCP_CA_CWR: /* CWR is to be held something *above* high_seq * is ACKed for CWR bit to reach receiver. */ if (tp->snd_una != tp->high_seq) { tcp_end_cwnd_reduction(sk); tcp_set_ca_state(sk, TCP_CA_Open); } break; case TCP_CA_Recovery: if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); if (tcp_try_undo_recovery(sk)) return; tcp_end_cwnd_reduction(sk); break; } } /* Use RACK to detect loss */ if (sysctl_tcp_recovery & TCP_RACK_LOST_RETRANS && tcp_rack_mark_lost(sk)) { flag |= FLAG_LOST_RETRANS; *ack_flag |= FLAG_LOST_RETRANS; } /* E. Process state. */ switch (icsk->icsk_ca_state) { case TCP_CA_Recovery: if (!(flag & FLAG_SND_UNA_ADVANCED)) { if (tcp_is_reno(tp) && is_dupack) tcp_add_reno_sack(sk); } else { if (tcp_try_undo_partial(sk, acked)) return; /* Partial ACK arrived. Force fast retransmit. */ do_lost = tcp_is_reno(tp) || tcp_fackets_out(tp) > tp->reordering; } if (tcp_try_undo_dsack(sk)) { tcp_try_keep_open(sk); return; } break; case TCP_CA_Loss: tcp_process_loss(sk, flag, is_dupack, rexmit); if (icsk->icsk_ca_state != TCP_CA_Open && !(flag & FLAG_LOST_RETRANS)) return; /* Change state if cwnd is undone or retransmits are lost */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) tcp_reset_reno_sack(tp); if (is_dupack) tcp_add_reno_sack(sk); } if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); if (!tcp_time_to_recover(sk, flag)) { tcp_try_to_open(sk, flag); return; } /* MTU probe failure: don't reduce cwnd */ if (icsk->icsk_ca_state < TCP_CA_CWR && icsk->icsk_mtup.probe_size && tp->snd_una == tp->mtu_probe.probe_seq_start) { tcp_mtup_probe_failed(sk); /* Restores the reduction we did in tcp_mtup_probe() */ tp->snd_cwnd++; tcp_simple_retransmit(sk); return; } /* Otherwise enter Recovery state */ tcp_enter_recovery(sk, (flag & FLAG_ECE)); fast_rexmit = 1; } if (do_lost) tcp_update_scoreboard(sk, fast_rexmit); *rexmit = REXMIT_LOST; } static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) { struct tcp_sock *tp = tcp_sk(sk); u32 wlen = sysctl_tcp_min_rtt_wlen * HZ; minmax_running_min(&tp->rtt_min, wlen, tcp_time_stamp, rtt_us ? : jiffies_to_usecs(1)); } static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, long seq_rtt_us, long sack_rtt_us, long ca_rtt_us) { const struct tcp_sock *tp = tcp_sk(sk); /* Prefer RTT measured from ACK's timing to TS-ECR. This is because * broken middle-boxes or peers may corrupt TS-ECR fields. But * Karn's algorithm forbids taking RTT if some retransmitted data * is acked (RFC6298). */ if (seq_rtt_us < 0) seq_rtt_us = sack_rtt_us; /* RTTM Rule: A TSecr value received in a segment is used to * update the averaged RTT measurement only if the segment * acknowledges some new data, i.e., only if it advances the * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) seq_rtt_us = ca_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr); if (seq_rtt_us < 0) return false; /* ca_rtt_us >= 0 is counting on the invariant that ca_rtt_us is * always taken together with ACK, SACK, or TS-opts. Any negative * values will be skipped with the seq_rtt_us < 0 check above. */ tcp_update_rtt_min(sk, ca_rtt_us); tcp_rtt_estimator(sk, seq_rtt_us); tcp_set_rto(sk); /* RFC6298: only reset backoff on valid RTT measurement. */ inet_csk(sk)->icsk_backoff = 0; return true; } /* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) { long rtt_us = -1L; if (req && !req->num_retrans && tcp_rsk(req)->snt_synack.v64) { struct skb_mstamp now; skb_mstamp_get(&now); rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack); } tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us); } static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { const struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_ca_ops->cong_avoid(sk, ack, acked); tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp; } /* Restart timer after forward progress on connection. * RFC2988 recommends to restart timer to now+rto. */ void tcp_rearm_rto(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); /* If the retrans timer is currently being used by Fast Open * for SYN-ACK retrans purpose, stay put. */ if (tp->fastopen_rsk) return; if (!tp->packets_out) { inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); } else { u32 rto = inet_csk(sk)->icsk_rto; /* Offset the time elapsed after installing regular RTO */ if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { struct sk_buff *skb = tcp_write_queue_head(sk); const u32 rto_time_stamp = tcp_skb_timestamp(skb) + rto; s32 delta = (s32)(rto_time_stamp - tcp_time_stamp); /* delta may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ rto = max(delta, 1); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, TCP_RTO_MAX); } } /* This function is called when the delayed ER timer fires. TCP enters * fast recovery and performs fast-retransmit. */ void tcp_resume_early_retransmit(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); tcp_rearm_rto(sk); /* Stop if ER is disabled after the delayed ER timer is scheduled */ if (!tp->do_early_retrans) return; tcp_enter_recovery(sk, false); tcp_update_scoreboard(sk, 1); tcp_xmit_retransmit_queue(sk); } /* If we get here, the whole TSO packet has not been acked. */ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); u32 packets_acked; BUG_ON(!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)); packets_acked = tcp_skb_pcount(skb); if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) return 0; packets_acked -= tcp_skb_pcount(skb); if (packets_acked) { BUG_ON(tcp_skb_pcount(skb) == 0); BUG_ON(!before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq)); } return packets_acked; } static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, u32 prior_snd_una) { const struct skb_shared_info *shinfo; /* Avoid cache line misses to get skb_shinfo() and shinfo->tx_flags */ if (likely(!TCP_SKB_CB(skb)->txstamp_ack)) return; shinfo = skb_shinfo(skb); if (!before(shinfo->tskey, prior_snd_una) && before(shinfo->tskey, tcp_sk(sk)->snd_una)) __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); } /* Remove acknowledged frames from the retransmission queue. If our packet * is before the ack sequence we can discard it as it's confirmed to have * arrived at the other end. */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, u32 prior_snd_una, int *acked, struct tcp_sacktag_state *sack, struct skb_mstamp *now) { const struct inet_connection_sock *icsk = inet_csk(sk); struct skb_mstamp first_ackt, last_ackt; struct tcp_sock *tp = tcp_sk(sk); u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; bool fully_acked = true; long sack_rtt_us = -1L; long seq_rtt_us = -1L; long ca_rtt_us = -1L; struct sk_buff *skb; u32 pkts_acked = 0; u32 last_in_flight = 0; bool rtt_update; int flag = 0; first_ackt.v64 = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); u8 sacked = scb->sacked; u32 acked_pcount; tcp_ack_tstamp(sk, skb, prior_snd_una); /* Determine how many packets and what bytes were acked, tso and else */ if (after(scb->end_seq, tp->snd_una)) { if (tcp_skb_pcount(skb) == 1 || !after(tp->snd_una, scb->seq)) break; acked_pcount = tcp_tso_acked(sk, skb); if (!acked_pcount) break; fully_acked = false; } else { /* Speedup tcp_unlink_write_queue() and next loop */ prefetchw(skb->next); acked_pcount = tcp_skb_pcount(skb); } if (unlikely(sacked & TCPCB_RETRANS)) { if (sacked & TCPCB_SACKED_RETRANS) tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; } else if (!(sacked & TCPCB_SACKED_ACKED)) { last_ackt = skb->skb_mstamp; WARN_ON_ONCE(last_ackt.v64 == 0); if (!first_ackt.v64) first_ackt = last_ackt; last_in_flight = TCP_SKB_CB(skb)->tx.in_flight; reord = min(pkts_acked, reord); if (!after(scb->end_seq, tp->high_seq)) flag |= FLAG_ORIG_SACK_ACKED; } if (sacked & TCPCB_SACKED_ACKED) { tp->sacked_out -= acked_pcount; } else if (tcp_is_sack(tp)) { tp->delivered += acked_pcount; if (!tcp_skb_spurious_retrans(tp, skb)) tcp_rack_advance(tp, &skb->skb_mstamp, sacked); } if (sacked & TCPCB_LOST) tp->lost_out -= acked_pcount; tp->packets_out -= acked_pcount; pkts_acked += acked_pcount; tcp_rate_skb_delivered(sk, skb, sack->rate); /* Initial outgoing SYN's get put onto the write_queue * just like anything else we transmit. It is not * true data, and if we misinform our callers that * this ACK acks real data, we will erroneously exit * connection startup slow start one packet too * quickly. This is severely frowned upon behavior. */ if (likely(!(scb->tcp_flags & TCPHDR_SYN))) { flag |= FLAG_DATA_ACKED; } else { flag |= FLAG_SYN_ACKED; tp->retrans_stamp = 0; } if (!fully_acked) break; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); if (unlikely(skb == tp->retransmit_skb_hint)) tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; } if (likely(between(tp->snd_up, prior_snd_una, tp->snd_una))) tp->snd_up = tp->snd_una; if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) { seq_rtt_us = skb_mstamp_us_delta(now, &first_ackt); ca_rtt_us = skb_mstamp_us_delta(now, &last_ackt); } if (sack->first_sackt.v64) { sack_rtt_us = skb_mstamp_us_delta(now, &sack->first_sackt); ca_rtt_us = skb_mstamp_us_delta(now, &sack->last_sackt); } sack->rate->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet, or -1 */ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, ca_rtt_us); if (flag & FLAG_ACKED) { tcp_rearm_rto(sk); if (unlikely(icsk->icsk_mtup.probe_size && !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) { tcp_mtup_probe_success(sk); } if (tcp_is_reno(tp)) { tcp_remove_reno_sacks(sk, pkts_acked); /* If any of the cumulatively ACKed segments was * retransmitted, non-SACK case cannot confirm that * progress was due to original transmission due to * lack of TCPCB_SACKED_ACKED bits even if some of * the packets may have been never retransmitted. */ if (flag & FLAG_RETRANS_DATA_ACKED) flag &= ~FLAG_ORIG_SACK_ACKED; } else { int delta; /* Non-retransmitted hole got filled? That's reordering */ if (reord < prior_fackets && reord <= tp->fackets_out) tcp_update_reordering(sk, tp->fackets_out - reord, 0); delta = tcp_is_fack(tp) ? pkts_acked : prior_sacked - tp->sacked_out; tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta); } tp->fackets_out -= min(pkts_acked, tp->fackets_out); } else if (skb && rtt_update && sack_rtt_us >= 0 && sack_rtt_us > skb_mstamp_us_delta(now, &skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. */ tcp_rearm_rto(sk); } if (icsk->icsk_ca_ops->pkts_acked) { struct ack_sample sample = { .pkts_acked = pkts_acked, .rtt_us = ca_rtt_us, .in_flight = last_in_flight }; icsk->icsk_ca_ops->pkts_acked(sk, &sample); } #if FASTRETRANS_DEBUG > 0 WARN_ON((int)tp->sacked_out < 0); WARN_ON((int)tp->lost_out < 0); WARN_ON((int)tp->retrans_out < 0); if (!tp->packets_out && tcp_is_sack(tp)) { icsk = inet_csk(sk); if (tp->lost_out) { pr_debug("Leak l=%u %d\n", tp->lost_out, icsk->icsk_ca_state); tp->lost_out = 0; } if (tp->sacked_out) { pr_debug("Leak s=%u %d\n", tp->sacked_out, icsk->icsk_ca_state); tp->sacked_out = 0; } if (tp->retrans_out) { pr_debug("Leak r=%u %d\n", tp->retrans_out, icsk->icsk_ca_state); tp->retrans_out = 0; } } #endif *acked = pkts_acked; return flag; } static void tcp_ack_probe(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); /* Was it a usable window open? */ if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq, tcp_wnd_end(tp))) { icsk->icsk_backoff = 0; inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0); /* Socket must be waked up by subsequent tcp_data_snd_check(). * This function is not for random using! */ } else { unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX); inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, TCP_RTO_MAX); } } static inline bool tcp_ack_is_dubious(const struct sock *sk, const int flag) { return !(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open; } /* Decide wheather to run the increase function of congestion control. */ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) { /* If reordering is high then always grow cwnd whenever data is * delivered regardless of its ordering. Otherwise stay conservative * and only grow cwnd on in-order delivery (RFC5681). A stretched ACK w/ * new SACK or ECE mark may first advance cwnd here and later reduce * cwnd in tcp_fastretrans_alert() based on more states. */ if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering) return flag & FLAG_FORWARD_PROGRESS; return flag & FLAG_DATA_ACKED; } /* The "ultimate" congestion control function that aims to replace the rigid * cwnd increase and decrease control (tcp_cong_avoid,tcp_*cwnd_reduction). * It's called toward the end of processing an ACK with precise rate * information. All transmission or retransmission are delayed afterwards. */ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked, int flag, const struct rate_sample *rs) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->cong_control) { icsk->icsk_ca_ops->cong_control(sk, rs); return; } if (tcp_in_cwnd_reduction(sk)) { /* Reduce cwnd if state mandates */ tcp_cwnd_reduction(sk, acked_sacked, flag); } else if (tcp_may_raise_cwnd(sk, flag)) { /* Advance cwnd if state allows */ tcp_cong_avoid(sk, ack, acked_sacked); } tcp_update_pacing_rate(sk); } /* Check that window update is acceptable. * The function assumes that snd_una<=ack<=snd_next. */ static inline bool tcp_may_update_window(const struct tcp_sock *tp, const u32 ack, const u32 ack_seq, const u32 nwin) { return after(ack, tp->snd_una) || after(ack_seq, tp->snd_wl1) || (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd); } /* If we update tp->snd_una, also update tp->bytes_acked */ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) { u32 delta = ack - tp->snd_una; sock_owned_by_me((struct sock *)tp); u64_stats_update_begin_raw(&tp->syncp); tp->bytes_acked += delta; u64_stats_update_end_raw(&tp->syncp); tp->snd_una = ack; } /* If we update tp->rcv_nxt, also update tp->bytes_received */ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) { u32 delta = seq - tp->rcv_nxt; sock_owned_by_me((struct sock *)tp); u64_stats_update_begin_raw(&tp->syncp); tp->bytes_received += delta; u64_stats_update_end_raw(&tp->syncp); tp->rcv_nxt = seq; } /* Update our send window. * * Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2 * and in FreeBSD. NetBSD's one is even worse.) is wrong. */ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 ack, u32 ack_seq) { struct tcp_sock *tp = tcp_sk(sk); int flag = 0; u32 nwin = ntohs(tcp_hdr(skb)->window); if (likely(!tcp_hdr(skb)->syn)) nwin <<= tp->rx_opt.snd_wscale; if (tcp_may_update_window(tp, ack, ack_seq, nwin)) { flag |= FLAG_WIN_UPDATE; tcp_update_wl(tp, ack_seq); if (tp->snd_wnd != nwin) { tp->snd_wnd = nwin; /* Note, it is the only place, where * fast path is recovered for sending TCP. */ tp->pred_flags = 0; tcp_fast_path_check(sk); if (tcp_send_head(sk)) tcp_slow_start_after_idle_check(sk); if (nwin > tp->max_window) { tp->max_window = nwin; tcp_sync_mss(sk, inet_csk(sk)->icsk_pmtu_cookie); } } } tcp_snd_una_update(tp, ack); return flag; } static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, u32 *last_oow_ack_time) { if (*last_oow_ack_time) { s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { NET_INC_STATS(net, mib_idx); return true; /* rate-limited: don't send yet! */ } } *last_oow_ack_time = tcp_time_stamp; return false; /* not rate-limited: go ahead, send dupack now! */ } /* Return true if we're currently rate-limiting out-of-window ACKs and * thus shouldn't send a dupack right now. We rate-limit dupacks in * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS * attacks that send repeated SYNs or ACKs for the same connection. To * do this, we do not send a duplicate SYNACK or ACK if the remote * endpoint is sending out-of-window SYNs or pure ACKs at a high rate. */ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, int mib_idx, u32 *last_oow_ack_time) { /* Data packets without SYNs are not likely part of an ACK loop. */ if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && !tcp_hdr(skb)->syn) return false; return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time); } /* RFC 5961 7 [ACK Throttling] */ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) { /* unprotected vars, we dont care of overwrites */ static u32 challenge_timestamp; static unsigned int challenge_count; struct tcp_sock *tp = tcp_sk(sk); u32 count, now; /* First check our per-socket dupack rate limit. */ if (__tcp_oow_rate_limited(sock_net(sk), LINUX_MIB_TCPACKSKIPPEDCHALLENGE, &tp->last_oow_ack_time)) return; /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1; challenge_timestamp = now; WRITE_ONCE(challenge_count, half + prandom_u32_max(sysctl_tcp_challenge_ack_limit)); } count = READ_ONCE(challenge_count); if (count > 0) { WRITE_ONCE(challenge_count, count - 1); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } } static void tcp_store_ts_recent(struct tcp_sock *tp) { tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; tp->rx_opt.ts_recent_stamp = get_seconds(); } static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) { if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { /* PAWS bug workaround wrt. ACK frames, the PAWS discard * extra check below makes sure this can only happen * for pure ACK frames. -DaveM * * Not only, also it occurs for expired timestamps. */ if (tcp_paws_check(&tp->rx_opt, 0)) tcp_store_ts_recent(tp); } } /* This routine deals with acks during a TLP episode and ends an episode by * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack */ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) { struct tcp_sock *tp = tcp_sk(sk); if (before(ack, tp->tlp_high_seq)) return; if (!tp->tlp_retrans) { /* TLP of new data has been acknowledged */ tp->tlp_high_seq = 0; } else if (flag & FLAG_DSACKING_ACK) { /* This DSACK means original and TLP probe arrived; no loss */ tp->tlp_high_seq = 0; } else if (after(ack, tp->tlp_high_seq)) { /* ACK advances: there was a loss, so reduce cwnd. Reset * tlp_high_seq in tcp_init_cwnd_reduction() */ tcp_init_cwnd_reduction(sk); tcp_set_ca_state(sk, TCP_CA_CWR); tcp_end_cwnd_reduction(sk); tcp_try_keep_open(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBERECOVERY); } else if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP | FLAG_DATA_SACKED))) { /* Pure dupack: original and TLP probe arrived; no loss */ tp->tlp_high_seq = 0; } } static inline void tcp_in_ack_event(struct sock *sk, u32 flags) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->in_ack_event) icsk->icsk_ca_ops->in_ack_event(sk, flags); } /* Congestion control has updated the cwnd already. So if we're in * loss recovery then now we do any new sends (for FRTO) or * retransmits (for CA_Loss or CA_recovery) that make sense. */ static void tcp_xmit_recovery(struct sock *sk, int rexmit) { struct tcp_sock *tp = tcp_sk(sk); if (rexmit == REXMIT_NONE) return; if (unlikely(rexmit == 2)) { __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); if (after(tp->snd_nxt, tp->high_seq)) return; tp->frto = 0; } tcp_xmit_retransmit_queue(sk); } /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_sacktag_state sack_state; struct rate_sample rs = { .prior_delivered = 0 }; u32 prior_snd_una = tp->snd_una; bool is_sack_reneg = tp->is_sack_reneg; u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; u32 prior_fackets; int prior_packets = tp->packets_out; u32 delivered = tp->delivered; u32 lost = tp->lost; int acked = 0; /* Number of packets newly acked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ struct skb_mstamp now; sack_state.first_sackt.v64 = 0; sack_state.rate = &rs; /* We very likely will need to access write queue head. */ prefetchw(sk->sk_write_queue.next); /* If the ack is older than previous acks * then we can probably ignore it. */ if (before(ack, prior_snd_una)) { /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ if (before(ack, prior_snd_una - tp->max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) tcp_send_challenge_ack(sk, skb); return -1; } goto old_ack; } /* If the ack includes data we haven't sent yet, discard * this segment (RFC793 Section 3.9). */ if (after(ack, tp->snd_nxt)) goto invalid_ack; skb_mstamp_get(&now); if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; icsk->icsk_retransmits = 0; } prior_fackets = tp->fackets_out; rs.prior_in_flight = tcp_packets_in_flight(tp); /* ts_recent update must be made after we are sure that the packet * is in window. */ if (flag & FLAG_UPDATE_TS_RECENT) tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) { /* Window is constant, pure forward advance. * No more checks are required. * Note, we use the fact that SND.UNA>=SND.WL2. */ tcp_update_wl(tp, ack_seq); tcp_snd_una_update(tp, ack); flag |= FLAG_WIN_UPDATE; tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS); } else { u32 ack_ev_flags = CA_ACK_SLOWPATH; if (ack_seq != TCP_SKB_CB(skb)->end_seq) flag |= FLAG_DATA; else NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPUREACKS); flag |= tcp_ack_update_window(sk, skb, ack, ack_seq); if (TCP_SKB_CB(skb)->sacked) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, &sack_state); if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) { flag |= FLAG_ECE; ack_ev_flags |= CA_ACK_ECE; } if (flag & FLAG_WIN_UPDATE) ack_ev_flags |= CA_ACK_WIN_UPDATE; tcp_in_ack_event(sk, ack_ev_flags); } /* We passed data and got it acked, remove any soft error * log. Something worked... */ sk->sk_err_soft = 0; icsk->icsk_probes_out = 0; tp->rcv_tstamp = tcp_time_stamp; if (!prior_packets) goto no_queue; /* See if we can take anything off of the retransmit queue. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked, &sack_state, &now); if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit); } if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) { struct dst_entry *dst = __sk_dst_get(sk); if (dst) dst_confirm(dst); } if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ lost = tp->lost - lost; /* freshly marked lost */ tcp_rate_gen(sk, delivered, lost, is_sack_reneg, &now, &rs); tcp_cong_control(sk, ack, delivered, flag, &rs); tcp_xmit_recovery(sk, rexmit); return 1; no_queue: /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit); /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. */ if (tcp_send_head(sk)) tcp_ack_probe(sk); if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); return 1; invalid_ack: SOCK_DEBUG(sk, "Ack %u after %u:%u\n", ack, tp->snd_una, tp->snd_nxt); return -1; old_ack: /* If data was SACKed, tag it and see if we should send more data. * If data was DSACKed, see if we can undo a cwnd reduction. */ if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, &sack_state); tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit); tcp_xmit_recovery(sk, rexmit); } SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt); return 0; } static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, bool syn, struct tcp_fastopen_cookie *foc, bool exp_opt) { /* Valid only in SYN or SYN-ACK with an even length. */ if (!foc || !syn || len < 0 || (len & 1)) return; if (len >= TCP_FASTOPEN_COOKIE_MIN && len <= TCP_FASTOPEN_COOKIE_MAX) memcpy(foc->val, cookie, len); else if (len != 0) len = -1; foc->len = len; foc->exp = exp_opt; } /* Look for tcp options. Normally only called on SYN and SYNACK packets. * But, this can also be called on packets in the established flow when * the fast version below fails. */ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc) { const unsigned char *ptr; const struct tcphdr *th = tcp_hdr(skb); int length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); opt_rx->saw_tstamp = 0; while (length > 0) { int opcode = *ptr++; int opsize; switch (opcode) { case TCPOPT_EOL: return; case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ length--; continue; default: opsize = *ptr++; if (opsize < 2) /* "silly options" */ return; if (opsize > length) return; /* don't parse partial options */ switch (opcode) { case TCPOPT_MSS: if (opsize == TCPOLEN_MSS && th->syn && !estab) { u16 in_mss = get_unaligned_be16(ptr); if (in_mss) { if (opt_rx->user_mss && opt_rx->user_mss < in_mss) in_mss = opt_rx->user_mss; opt_rx->mss_clamp = in_mss; } } break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && !estab && sysctl_tcp_window_scaling) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > 14) { net_info_ratelimited("%s: Illegal window scaling value %d >14 received\n", __func__, snd_wscale); snd_wscale = 14; } opt_rx->snd_wscale = snd_wscale; } break; case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || (!estab && sysctl_tcp_timestamps))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); } break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && !estab && sysctl_tcp_sack) { opt_rx->sack_ok = TCP_SACK_SEEN; tcp_sack_reset(opt_rx); } break; case TCPOPT_SACK: if ((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) && !((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK) && opt_rx->sack_ok) { TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *)th; } break; #ifdef CONFIG_TCP_MD5SIG case TCPOPT_MD5SIG: /* * The MD5 Hash has already been * checked (see tcp_v{4,6}_do_rcv()). */ break; #endif case TCPOPT_FASTOPEN: tcp_parse_fastopen_option( opsize - TCPOLEN_FASTOPEN_BASE, ptr, th->syn, foc, false); break; case TCPOPT_EXP: /* Fast Open option shares code 254 using a * 16 bits magic number. */ if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE && get_unaligned_be16(ptr) == TCPOPT_FASTOPEN_MAGIC) tcp_parse_fastopen_option(opsize - TCPOLEN_EXP_FASTOPEN_BASE, ptr + 2, th->syn, foc, true); break; } ptr += opsize-2; length -= opsize; } } } EXPORT_SYMBOL(tcp_parse_options); static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr *th) { const __be32 *ptr = (const __be32 *)(th + 1); if (*ptr == htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) { tp->rx_opt.saw_tstamp = 1; ++ptr; tp->rx_opt.rcv_tsval = ntohl(*ptr); ++ptr; if (*ptr) tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset; else tp->rx_opt.rcv_tsecr = 0; return true; } return false; } /* Fast parse options. This hopes to only see timestamps. * If it is wrong it falls back on tcp_parse_options(). */ static bool tcp_fast_parse_options(const struct sk_buff *skb, const struct tcphdr *th, struct tcp_sock *tp) { /* In the spirit of fast parsing, compare doff directly to constant * values. Because equality is used, short doff can be ignored here. */ if (th->doff == (sizeof(*th) / 4)) { tp->rx_opt.saw_tstamp = 0; return false; } else if (tp->rx_opt.tstamp_ok && th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) { if (tcp_parse_aligned_timestamp(tp, th)) return true; } tcp_parse_options(skb, &tp->rx_opt, 1, NULL); if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; return true; } #ifdef CONFIG_TCP_MD5SIG /* * Parse MD5 Signature option */ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) { int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); /* If not enough data remaining, we can short cut */ while (length >= TCPOLEN_MD5SIG) { int opcode = *ptr++; int opsize; switch (opcode) { case TCPOPT_EOL: return NULL; case TCPOPT_NOP: length--; continue; default: opsize = *ptr++; if (opsize < 2 || opsize > length) return NULL; if (opcode == TCPOPT_MD5SIG) return opsize == TCPOLEN_MD5SIG ? ptr : NULL; } ptr += opsize - 2; length -= opsize; } return NULL; } EXPORT_SYMBOL(tcp_parse_md5sig_option); #endif /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM * * It is not fatal. If this ACK does _not_ change critical state (seqs, window) * it can pass through stack. So, the following predicate verifies that * this segment is not used for anything but congestion avoidance or * fast retransmit. Moreover, we even are able to eliminate most of such * second order effects, if we apply some small "replay" window (~RTO) * to timestamp space. * * All these measures still do not guarantee that we reject wrapped ACKs * on networks with high bandwidth, when sequence space is recycled fastly, * but it guarantees that such events will be very rare and do not affect * connection seriously. This doesn't look nice, but alas, PAWS is really * buggy extension. * * [ Later note. Even worse! It is buggy for segments _with_ data. RFC * states that events when retransmit arrives after original data are rare. * It is a blatant lie. VJ forgot about fast retransmit! 8)8) It is * the biggest problem on large power networks even with minor reordering. * OK, let's give it small replay window. If peer clock is even 1hz, it is safe * up to bandwidth of 18Gigabit/sec. 8) ] */ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); const struct tcphdr *th = tcp_hdr(skb); u32 seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; return (/* 1. Pure ACK with correct sequence number. */ (th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) && /* 2. ... and duplicate ACK. */ ack == tp->snd_una && /* 3. ... and does not update window. */ !tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) && /* 4. ... and sits in replay window. */ (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ); } static inline bool tcp_paws_discard(const struct sock *sk, const struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); return !tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW) && !tcp_disordered_ack(sk, skb); } /* Check segment sequence number for validity. * * Segment controls are considered valid, if the segment * fits to the window after truncation to the window. Acceptability * of data (and SYN, FIN, of course) is checked separately. * See tcp_data_queue(), for example. * * Also, controls (RST is main one) are accepted using RCV.WUP instead * of RCV.NXT. Peer still did not advance his SND.UNA when we * delayed ACK, so that hisSND.UNA<=ourRCV.WUP. * (borrowed from freebsd) */ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) { return !before(end_seq, tp->rcv_wup) && !after(seq, tp->rcv_nxt + tcp_receive_window(tp)); } /* When we get a reset we do this. */ void tcp_reset(struct sock *sk) { /* We want the right error as BSD sees it (and indeed as we do). */ switch (sk->sk_state) { case TCP_SYN_SENT: sk->sk_err = ECONNREFUSED; break; case TCP_CLOSE_WAIT: sk->sk_err = EPIPE; break; case TCP_CLOSE: return; default: sk->sk_err = ECONNRESET; } /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_error_report(sk); tcp_done(sk); } /* * Process the FIN bit. This now behaves as it is supposed to work * and the FIN takes effect when it is validly part of sequence * space. Not before when we get holes. * * If we are ESTABLISHED, a received fin moves us to CLOSE-WAIT * (and thence onto LAST-ACK and finally, CLOSE, we never enter * TIME-WAIT) * * If we are in FINWAIT-1, a received FIN indicates simultaneous * close and we go into CLOSING (and later onto TIME-WAIT) * * If we are in FINWAIT-2, a received FIN moves us to TIME-WAIT. */ void tcp_fin(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); inet_csk_schedule_ack(sk); sk->sk_shutdown |= RCV_SHUTDOWN; sock_set_flag(sk, SOCK_DONE); switch (sk->sk_state) { case TCP_SYN_RECV: case TCP_ESTABLISHED: /* Move to CLOSE_WAIT */ tcp_set_state(sk, TCP_CLOSE_WAIT); inet_csk(sk)->icsk_ack.pingpong = 1; break; case TCP_CLOSE_WAIT: case TCP_CLOSING: /* Received a retransmission of the FIN, do * nothing. */ break; case TCP_LAST_ACK: /* RFC793: Remain in the LAST-ACK state. */ break; case TCP_FIN_WAIT1: /* This case occurs when a simultaneous close * happens, we must ack the received FIN and * enter the CLOSING state. */ tcp_send_ack(sk); tcp_set_state(sk, TCP_CLOSING); break; case TCP_FIN_WAIT2: /* Received a FIN -- send ACK and enter TIME_WAIT. */ tcp_send_ack(sk); tcp_time_wait(sk, TCP_TIME_WAIT, 0); break; default: /* Only TCP_LISTEN and TCP_CLOSE are left, in these * cases we should never reach this piece of code. */ pr_err("%s: Impossible, sk->sk_state=%d\n", __func__, sk->sk_state); break; } /* It _is_ possible, that we have something out-of-order _after_ FIN. * Probably, we should reset in this case. For now drop them. */ skb_rbtree_purge(&tp->out_of_order_queue); if (tcp_is_sack(tp)) tcp_sack_reset(&tp->rx_opt); sk_mem_reclaim(sk); if (!sock_flag(sk, SOCK_DEAD)) { sk->sk_state_change(sk); /* Do not send POLL_HUP for half duplex close. */ if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE) sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); else sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); } } static inline bool tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, u32 end_seq) { if (!after(seq, sp->end_seq) && !after(sp->start_seq, end_seq)) { if (before(seq, sp->start_seq)) sp->start_seq = seq; if (after(end_seq, sp->end_seq)) sp->end_seq = end_seq; return true; } return false; } static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); if (tcp_is_sack(tp) && sysctl_tcp_dsack) { int mib_idx; if (before(seq, tp->rcv_nxt)) mib_idx = LINUX_MIB_TCPDSACKOLDSENT; else mib_idx = LINUX_MIB_TCPDSACKOFOSENT; NET_INC_STATS(sock_net(sk), mib_idx); tp->rx_opt.dsack = 1; tp->duplicate_sack[0].start_seq = seq; tp->duplicate_sack[0].end_seq = end_seq; } } static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); if (!tp->rx_opt.dsack) tcp_dsack_set(sk, seq, end_seq); else tcp_sack_extend(tp->duplicate_sack, seq, end_seq); } static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); if (tcp_is_sack(tp) && sysctl_tcp_dsack) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) end_seq = tp->rcv_nxt; tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, end_seq); } } tcp_send_ack(sk); } /* These routines update the SACK block as out-of-order packets arrive or * in-order packets close up the sequence space. */ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp) { int this_sack; struct tcp_sack_block *sp = &tp->selective_acks[0]; struct tcp_sack_block *swalk = sp + 1; /* See if the recent change to the first SACK eats into * or hits the sequence space of other SACK blocks, if so coalesce. */ for (this_sack = 1; this_sack < tp->rx_opt.num_sacks;) { if (tcp_sack_extend(sp, swalk->start_seq, swalk->end_seq)) { int i; /* Zap SWALK, by moving every further SACK up by one slot. * Decrease num_sacks. */ tp->rx_opt.num_sacks--; for (i = this_sack; i < tp->rx_opt.num_sacks; i++) sp[i] = sp[i + 1]; continue; } this_sack++, swalk++; } } static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_sack_block *sp = &tp->selective_acks[0]; int cur_sacks = tp->rx_opt.num_sacks; int this_sack; if (!cur_sacks) goto new_sack; for (this_sack = 0; this_sack < cur_sacks; this_sack++, sp++) { if (tcp_sack_extend(sp, seq, end_seq)) { /* Rotate this_sack to the first one. */ for (; this_sack > 0; this_sack--, sp--) swap(*sp, *(sp - 1)); if (cur_sacks > 1) tcp_sack_maybe_coalesce(tp); return; } } /* Could not find an adjacent existing SACK, build a new one, * put it at the front, and shift everyone else down. We * always know there is at least one SACK present already here. * * If the sack array is full, forget about the last one. */ if (this_sack >= TCP_NUM_SACKS) { this_sack--; tp->rx_opt.num_sacks--; sp--; } for (; this_sack > 0; this_sack--, sp--) *sp = *(sp - 1); new_sack: /* Build the new head SACK, and we're done. */ sp->start_seq = seq; sp->end_seq = end_seq; tp->rx_opt.num_sacks++; } /* RCV.NXT advances, some SACKs should be eaten. */ static void tcp_sack_remove(struct tcp_sock *tp) { struct tcp_sack_block *sp = &tp->selective_acks[0]; int num_sacks = tp->rx_opt.num_sacks; int this_sack; /* Empty ofo queue, hence, all the SACKs are eaten. Clear. */ if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tp->rx_opt.num_sacks = 0; return; } for (this_sack = 0; this_sack < num_sacks;) { /* Check if the start of the sack is covered by RCV.NXT. */ if (!before(tp->rcv_nxt, sp->start_seq)) { int i; /* RCV.NXT must cover all the block! */ WARN_ON(before(tp->rcv_nxt, sp->end_seq)); /* Zap this SACK, by moving forward any other SACKS. */ for (i = this_sack+1; i < num_sacks; i++) tp->selective_acks[i-1] = tp->selective_acks[i]; num_sacks--; continue; } this_sack++; sp++; } tp->rx_opt.num_sacks = num_sacks; } /** * tcp_try_coalesce - try to merge skb to prior one * @sk: socket * @to: prior buffer * @from: buffer to add in queue * @fragstolen: pointer to boolean * * Before queueing skb @from after @to, try to merge them * to reduce overall memory use and queue lengths, if cost is small. * Packets in ofo or receive queues can stay a long time. * Better try to coalesce them right now to avoid future collapses. * Returns true if caller should free @from instead of queueing it */ static bool tcp_try_coalesce(struct sock *sk, struct sk_buff *to, struct sk_buff *from, bool *fragstolen) { int delta; *fragstolen = false; /* Its possible this segment overlaps with prior segment in queue */ if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq) return false; if (!skb_try_coalesce(to, from, fragstolen, &delta)) return false; atomic_add(delta, &sk->sk_rmem_alloc); sk_mem_charge(sk, delta); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE); TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq; TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq; TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags; return true; } static bool tcp_ooo_try_coalesce(struct sock *sk, struct sk_buff *to, struct sk_buff *from, bool *fragstolen) { bool res = tcp_try_coalesce(sk, to, from, fragstolen); /* In case tcp_drop() is called later, update to->gso_segs */ if (res) { u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) + max_t(u16, 1, skb_shinfo(from)->gso_segs); skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF); } return res; } static void tcp_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); __kfree_skb(skb); } /* This one checks to see if we can put data from the * out_of_order queue into the receive_queue. */ static void tcp_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); __u32 dsack_high = tp->rcv_nxt; bool fin, fragstolen, eaten; struct sk_buff *skb, *tail; struct rb_node *p; p = rb_first(&tp->out_of_order_queue); while (p) { skb = rb_to_skb(p); if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; if (before(TCP_SKB_CB(skb)->seq, dsack_high)) { __u32 dsack = dsack_high; if (before(TCP_SKB_CB(skb)->end_seq, dsack_high)) dsack_high = TCP_SKB_CB(skb)->end_seq; tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack); } p = rb_next(p); rb_erase(&skb->rbnode, &tp->out_of_order_queue); if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) { SOCK_DEBUG(sk, "ofo packet was already received\n"); tcp_drop(sk, skb); continue; } SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n", tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); tail = skb_peek_tail(&sk->sk_receive_queue); eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) __skb_queue_tail(&sk->sk_receive_queue, skb); else kfree_skb_partial(skb, fragstolen); if (unlikely(fin)) { tcp_fin(sk); /* tcp_fin() purges tp->out_of_order_queue, * so we must end this loop right now. */ break; } } } static bool tcp_prune_ofo_queue(struct sock *sk); static int tcp_prune_queue(struct sock *sk); static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, unsigned int size) { if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, size)) { if (tcp_prune_queue(sk) < 0) return -1; while (!sk_rmem_schedule(sk, skb, size)) { if (!tcp_prune_ofo_queue(sk)) return -1; } } return 0; } static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node **p, *parent; struct sk_buff *skb1; u32 seq, end_seq; bool fragstolen; tcp_ecn_check_ce(sk, skb); if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); tcp_drop(sk, skb); return; } /* Disable header prediction. */ tp->pred_flags = 0; inet_csk_schedule_ack(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); seq = TCP_SKB_CB(skb)->seq; end_seq = TCP_SKB_CB(skb)->end_seq; SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", tp->rcv_nxt, seq, end_seq); p = &tp->out_of_order_queue.rb_node; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { /* Initial out of order segment, build 1 SACK. */ if (tcp_is_sack(tp)) { tp->rx_opt.num_sacks = 1; tp->selective_acks[0].start_seq = seq; tp->selective_acks[0].end_seq = end_seq; } rb_link_node(&skb->rbnode, NULL, p); rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); tp->ooo_last_skb = skb; goto end; } /* In the typical case, we are adding an skb to the end of the list. * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { coalesce_done: /* For non sack flows, do not grow window to force DUPACK * and trigger fast retransmit. */ if (tcp_is_sack(tp)) tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); skb = NULL; goto add_sack; } /* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */ if (!before(seq, TCP_SKB_CB(tp->ooo_last_skb)->end_seq)) { parent = &tp->ooo_last_skb->rbnode; p = &parent->rb_right; goto insert; } /* Find place to insert this segment. Handle overlaps on the way. */ parent = NULL; while (*p) { parent = *p; skb1 = rb_to_skb(parent); if (before(seq, TCP_SKB_CB(skb1)->seq)) { p = &parent->rb_left; continue; } if (before(seq, TCP_SKB_CB(skb1)->end_seq)) { if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { /* All the bits are present. Drop. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); tcp_drop(sk, skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); goto add_sack; } if (after(seq, TCP_SKB_CB(skb1)->seq)) { /* Partial overlap. */ tcp_dsack_set(sk, seq, TCP_SKB_CB(skb1)->end_seq); } else { /* skb's seq == skb1's seq and skb covers skb1. * Replace skb1 with skb. */ rb_replace_node(&skb1->rbnode, &skb->rbnode, &tp->out_of_order_queue); tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); tcp_drop(sk, skb1); goto merge_right; } } else if (tcp_ooo_try_coalesce(sk, skb1, skb, &fragstolen)) { goto coalesce_done; } p = &parent->rb_right; } insert: /* Insert segment into RB tree. */ rb_link_node(&skb->rbnode, parent, p); rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); merge_right: /* Remove other segments covered by skb. */ while ((skb1 = skb_rb_next(skb)) != NULL) { if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) break; if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, end_seq); break; } rb_erase(&skb1->rbnode, &tp->out_of_order_queue); tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); tcp_drop(sk, skb1); } /* If there is no skb after us, we are the last_skb ! */ if (!skb1) tp->ooo_last_skb = skb; add_sack: if (tcp_is_sack(tp)) tcp_sack_new_ofo_skb(sk, seq, end_seq); end: if (skb) { /* For non sack flows, do not grow window to force DUPACK * and trigger fast retransmit. */ if (tcp_is_sack(tp)) tcp_grow_window(sk, skb); skb_set_owner_r(skb, sk); } } static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen, bool *fragstolen) { int eaten; struct sk_buff *tail = skb_peek_tail(&sk->sk_receive_queue); __skb_pull(skb, hdrlen); eaten = (tail && tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0; tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { __skb_queue_tail(&sk->sk_receive_queue, skb); skb_set_owner_r(skb, sk); } return eaten; } int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_buff *skb; int err = -ENOMEM; int data_len = 0; bool fragstolen; if (size == 0) return 0; if (size > PAGE_SIZE) { int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS); data_len = npages << PAGE_SHIFT; size = data_len + (size & ~PAGE_MASK); } skb = alloc_skb_with_frags(size - data_len, data_len, PAGE_ALLOC_COSTLY_ORDER, &err, sk->sk_allocation); if (!skb) goto err; skb_put(skb, size - data_len); skb->data_len = data_len; skb->len = size; if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) goto err_free; err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); if (err) goto err_free; TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size; TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1; if (tcp_queue_rcv(sk, skb, 0, &fragstolen)) { WARN_ON_ONCE(fragstolen); /* should not happen */ __kfree_skb(skb); } return size; err_free: kfree_skb(skb); err: return err; } static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); bool fragstolen = false; int eaten = -1; if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { __kfree_skb(skb); return; } skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); tcp_ecn_accept_cwr(tp, skb); tp->rx_opt.dsack = 0; /* Queue data for delivery to the user. * Packets in sequence go to the receive queue. * Out of sequence packets to the out_of_order_queue. */ if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) { if (tcp_receive_window(tp) == 0) goto out_of_window; /* Ok. In sequence. In window. */ if (tp->ucopy.task == current && tp->copied_seq == tp->rcv_nxt && tp->ucopy.len && sock_owned_by_user(sk) && !tp->urg_data) { int chunk = min_t(unsigned int, skb->len, tp->ucopy.len); __set_current_state(TASK_RUNNING); if (!skb_copy_datagram_msg(skb, 0, tp->ucopy.msg, chunk)) { tp->ucopy.len -= chunk; tp->copied_seq += chunk; eaten = (chunk == skb->len); tcp_rcv_space_adjust(sk); } } if (eaten <= 0) { queue_and_out: if (eaten < 0) { if (skb_queue_len(&sk->sk_receive_queue) == 0) sk_forced_mem_schedule(sk, skb->truesize); else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) goto drop; } eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); } tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); if (skb->len) tcp_event_data_recv(sk, skb); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) tcp_fin(sk); if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tcp_ofo_queue(sk); /* RFC2581. 4.2. SHOULD send immediate ACK, when * gap in queue is filled. */ if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) inet_csk(sk)->icsk_ack.pingpong = 0; } if (tp->rx_opt.num_sacks) tcp_sack_remove(tp); tcp_fast_path_check(sk); if (eaten > 0) kfree_skb_partial(skb, fragstolen); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return; } if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { /* A retransmit, 2nd most common case. Force an immediate ack. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); out_of_window: tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); inet_csk_schedule_ack(sk); drop: tcp_drop(sk, skb); return; } /* Out of window. F.e. zero window probe. */ if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp))) goto out_of_window; if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { /* Partial packet, seq < rcv_next < end_seq */ SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n", tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, tp->rcv_nxt); /* If window is closed, drop tail of packet. But after * remembering D-SACK for its head made in previous line. */ if (!tcp_receive_window(tp)) goto out_of_window; goto queue_and_out; } tcp_data_queue_ofo(sk, skb); } static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *list) { if (list) return !skb_queue_is_last(list, skb) ? skb->next : NULL; return skb_rb_next(skb); } static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, struct sk_buff_head *list, struct rb_root *root) { struct sk_buff *next = tcp_skb_next(skb, list); if (list) __skb_unlink(skb, list); else rb_erase(&skb->rbnode, root); __kfree_skb(skb); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOLLAPSED); return next; } /* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */ static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct sk_buff *skb1; while (*p) { parent = *p; skb1 = rb_to_skb(parent); if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq)) p = &parent->rb_left; else p = &parent->rb_right; } rb_link_node(&skb->rbnode, parent, p); rb_insert_color(&skb->rbnode, root); } /* Collapse contiguous sequence of skbs head..tail with * sequence numbers start..end. * * If tail is NULL, this means until the end of the queue. * * Segments with FIN/SYN are not collapsed (only because this * simplifies code) */ static void tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, struct sk_buff *head, struct sk_buff *tail, u32 start, u32 end) { struct sk_buff *skb = head, *n; struct sk_buff_head tmp; bool end_of_skbs; /* First, check that queue is collapsible and find * the point where collapsing can be useful. */ restart: for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) { n = tcp_skb_next(skb, list); /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { skb = tcp_collapse_one(sk, skb, list, root); if (!skb) break; goto restart; } /* The first skb to collapse is: * - not SYN/FIN and * - bloated or contains data before "start" or * overlaps to the next one. */ if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) && (tcp_win_from_space(skb->truesize) > skb->len || before(TCP_SKB_CB(skb)->seq, start))) { end_of_skbs = false; break; } if (n && n != tail && TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { end_of_skbs = false; break; } /* Decided to skip this, advance start seq. */ start = TCP_SKB_CB(skb)->end_seq; } if (end_of_skbs || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) return; __skb_queue_head_init(&tmp); while (before(start, end)) { int copy = min_t(int, SKB_MAX_ORDER(0, 0), end - start); struct sk_buff *nskb; nskb = alloc_skb(copy, GFP_ATOMIC); if (!nskb) break; memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start; if (list) __skb_queue_before(list, skb, nskb); else __skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */ skb_set_owner_r(nskb, sk); /* Copy data, releasing collapsed skbs. */ while (copy > 0) { int offset = start - TCP_SKB_CB(skb)->seq; int size = TCP_SKB_CB(skb)->end_seq - start; BUG_ON(offset < 0); if (size > 0) { size = min(copy, size); if (skb_copy_bits(skb, offset, skb_put(nskb, size), size)) BUG(); TCP_SKB_CB(nskb)->end_seq += size; copy -= size; start += size; } if (!before(start, TCP_SKB_CB(skb)->end_seq)) { skb = tcp_collapse_one(sk, skb, list, root); if (!skb || skb == tail || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) goto end; } } } end: skb_queue_walk_safe(&tmp, skb, n) tcp_rbtree_insert(root, skb); } /* Collapse ofo queue. Algorithm: select contiguous sequence of skbs * and tcp_collapse() them until all the queue is collapsed. */ static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 range_truesize, sum_tiny = 0; struct sk_buff *skb, *head; u32 start, end; skb = skb_rb_first(&tp->out_of_order_queue); new_range: if (!skb) { tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue); return; } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; range_truesize = skb->truesize; for (head = skb;;) { skb = skb_rb_next(skb); /* Range is terminated when we see a gap or when * we are at the queue end. */ if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { /* Do not attempt collapsing tiny skbs */ if (range_truesize != head->truesize || end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { tcp_collapse(sk, NULL, &tp->out_of_order_queue, head, skb, start, end); } else { sum_tiny += range_truesize; if (sum_tiny > sk->sk_rcvbuf >> 3) return; } goto new_range; } range_truesize += skb->truesize; if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; if (after(TCP_SKB_CB(skb)->end_seq, end)) end = TCP_SKB_CB(skb)->end_seq; } } /* * Clean the out-of-order queue to make room. * We drop high sequences packets to : * 1) Let a chance for holes to be filled. * 2) not add too big latencies if thousands of packets sit there. * (But if application shrinks SO_RCVBUF, we could still end up * freeing whole queue here) * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks. * * Return true if queue has shrunk. */ static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node *node, *prev; int goal; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); goal = sk->sk_rcvbuf >> 3; node = &tp->ooo_last_skb->rbnode; do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); goal -= rb_to_skb(node)->truesize; tcp_drop(sk, rb_to_skb(node)); if (!prev || goal <= 0) { sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) break; goal = sk->sk_rcvbuf >> 3; } node = prev; } while (node); tp->ooo_last_skb = rb_to_skb(prev); /* Reset SACK state. A conforming SACK implementation will * do the same at a timeout based retransmit. When a connection * is in a sad state like this, we care only about integrity * of the connection not performance. */ if (tp->rx_opt.sack_ok) tcp_sack_reset(&tp->rx_opt); return true; } /* Reduce allocated memory if we can, trying to get * the socket within its memory limits again. * * Return less than zero if we should start dropping frames * until the socket owning process reads some of the data * to stabilize the situation. */ static int tcp_prune_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); SOCK_DEBUG(sk, "prune_queue: c=%x\n", tp->copied_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED); if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) tcp_clamp_window(sk); else if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) return 0; tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) tcp_collapse(sk, &sk->sk_receive_queue, NULL, skb_peek(&sk->sk_receive_queue), NULL, tp->copied_seq, tp->rcv_nxt); sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) return 0; /* Collapsing did not help, destructive actions follow. * This must not ever occur. */ tcp_prune_ofo_queue(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) return 0; /* If we are really being abused, tell the caller to silently * drop receive data on the floor. It will get retransmitted * and hopefully then we'll have sufficient space. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_RCVPRUNED); /* Massive buffer overcommit. */ tp->pred_flags = 0; return -1; } static bool tcp_should_expand_sndbuf(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); /* If the user specified a specific send buffer setting, do * not modify it. */ if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) return false; /* If we are under global TCP memory pressure, do not expand. */ if (tcp_under_memory_pressure(sk)) return false; /* If we are under soft global TCP memory pressure, do not expand. */ if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0)) return false; /* If we filled the congestion window, do not expand. */ if (tcp_packets_in_flight(tp) >= tp->snd_cwnd) return false; return true; } /* When incoming ACK allowed to free some skb from write_queue, * we remember this event in flag SOCK_QUEUE_SHRUNK and wake up socket * on the exit from tcp input handler. * * PROBLEM: sndbuf expansion does not work well with largesend. */ static void tcp_new_space(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (tcp_should_expand_sndbuf(sk)) { tcp_sndbuf_expand(sk); tp->snd_cwnd_stamp = tcp_time_stamp; } sk->sk_write_space(sk); } static void tcp_check_space(struct sock *sk) { if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) { sock_reset_flag(sk, SOCK_QUEUE_SHRUNK); /* pairs with tcp_poll() */ smp_mb(); if (sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) tcp_new_space(sk); } } static inline void tcp_data_snd_check(struct sock *sk) { tcp_push_pending_frames(sk); tcp_check_space(sk); } /* * Check if sending an ack is needed. */ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) { struct tcp_sock *tp = tcp_sk(sk); /* More than one full frame received... */ if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss && /* ... and right edge of window advances far enough. * (tcp_recvmsg() will send ACK otherwise). Or... */ __tcp_select_window(sk) >= tp->rcv_wnd) || /* We ACK each frame or... */ tcp_in_quickack_mode(sk) || /* We have out of order data. */ (ofo_possible && !RB_EMPTY_ROOT(&tp->out_of_order_queue))) { /* Then ack it now */ tcp_send_ack(sk); } else { /* Else, send delayed ack. */ tcp_send_delayed_ack(sk); } } static inline void tcp_ack_snd_check(struct sock *sk) { if (!inet_csk_ack_scheduled(sk)) { /* We sent a data segment already. */ return; } __tcp_ack_snd_check(sk, 1); } /* * This routine is only called when we have urgent data * signaled. Its the 'slow' part of tcp_urg. It could be * moved inline now as tcp_urg is only called from one * place. We handle URGent data wrong. We have to - as * BSD still doesn't use the correction from RFC961. * For 1003.1g we should support a new option TCP_STDURG to permit * either form (or just set the sysctl tcp_stdurg). */ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) { struct tcp_sock *tp = tcp_sk(sk); u32 ptr = ntohs(th->urg_ptr); if (ptr && !sysctl_tcp_stdurg) ptr--; ptr += ntohl(th->seq); /* Ignore urgent data that we've already seen and read. */ if (after(tp->copied_seq, ptr)) return; /* Do not replay urg ptr. * * NOTE: interesting situation not covered by specs. * Misbehaving sender may send urg ptr, pointing to segment, * which we already have in ofo queue. We are not able to fetch * such data and will stay in TCP_URG_NOTYET until will be eaten * by recvmsg(). Seems, we are not obliged to handle such wicked * situations. But it is worth to think about possibility of some * DoSes using some hypothetical application level deadlock. */ if (before(ptr, tp->rcv_nxt)) return; /* Do we already have a newer (or duplicate) urgent pointer? */ if (tp->urg_data && !after(ptr, tp->urg_seq)) return; /* Tell the world about our new urgent pointer. */ sk_send_sigurg(sk); /* We may be adding urgent data when the last byte read was * urgent. To do this requires some care. We cannot just ignore * tp->copied_seq since we would read the last urgent byte again * as data, nor can we alter copied_seq until this data arrives * or we break the semantics of SIOCATMARK (and thus sockatmark()) * * NOTE. Double Dutch. Rendering to plain English: author of comment * above did something sort of send("A", MSG_OOB); send("B", MSG_OOB); * and expect that both A and B disappear from stream. This is _wrong_. * Though this happens in BSD with high probability, this is occasional. * Any application relying on this is buggy. Note also, that fix "works" * only in this artificial test. Insert some normal data between A and B and we will * decline of BSD again. Verdict: it is better to remove to trap * buggy users. */ if (tp->urg_seq == tp->copied_seq && tp->urg_data && !sock_flag(sk, SOCK_URGINLINE) && tp->copied_seq != tp->rcv_nxt) { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); tp->copied_seq++; if (skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)) { __skb_unlink(skb, &sk->sk_receive_queue); __kfree_skb(skb); } } tp->urg_data = TCP_URG_NOTYET; tp->urg_seq = ptr; /* Disable header prediction. */ tp->pred_flags = 0; } /* This is the 'fast' part of urgent handling. */ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th) { struct tcp_sock *tp = tcp_sk(sk); /* Check if we get a new urgent pointer - normally not. */ if (th->urg) tcp_check_urg(sk, th); /* Do we wait for any urgent data? - normally not... */ if (tp->urg_data == TCP_URG_NOTYET) { u32 ptr = tp->urg_seq - ntohl(th->seq) + (th->doff * 4) - th->syn; /* Is the urgent pointer pointing into this packet? */ if (ptr < skb->len) { u8 tmp; if (skb_copy_bits(skb, ptr, &tmp, 1)) BUG(); tp->urg_data = TCP_URG_VALID | tmp; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); } } } static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen) { struct tcp_sock *tp = tcp_sk(sk); int chunk = skb->len - hlen; int err; if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_msg(skb, hlen, tp->ucopy.msg, chunk); else err = skb_copy_and_csum_datagram_msg(skb, hlen, tp->ucopy.msg); if (!err) { tp->ucopy.len -= chunk; tp->copied_seq += chunk; tcp_rcv_space_adjust(sk); } return err; } /* Does PAWS and seqno based validation of an incoming segment, flags will * play significant role here. */ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, int syn_inerr) { struct tcp_sock *tp = tcp_sk(sk); bool rst_seq_match = false; /* RFC1323: H1. Apply PAWS check first. */ if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); if (!tcp_oow_rate_limited(sock_net(sk), skb, LINUX_MIB_TCPACKSKIPPEDPAWS, &tp->last_oow_ack_time)) tcp_send_dupack(sk, skb); goto discard; } /* Reset is accepted even if it did not pass PAWS. */ } /* Step 1: check sequence number */ if (!tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq)) { /* RFC793, page 37: "In all states except SYN-SENT, all reset * (RST) segments are validated by checking their SEQ-fields." * And page 69: "If an incoming segment is not acceptable, * an acknowledgment should be sent in reply (unless the RST * bit is set, if so drop the segment and return)". */ if (!th->rst) { if (th->syn) goto syn_challenge; if (!tcp_oow_rate_limited(sock_net(sk), skb, LINUX_MIB_TCPACKSKIPPEDSEQ, &tp->last_oow_ack_time)) tcp_send_dupack(sk, skb); } goto discard; } /* Step 2: check RST bit */ if (th->rst) { /* RFC 5961 3.2 (extend to match against SACK too if available): * If seq num matches RCV.NXT or the right-most SACK block, * then * RESET the connection * else * Send a challenge ACK */ if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) { rst_seq_match = true; } else if (tcp_is_sack(tp) && tp->rx_opt.num_sacks > 0) { struct tcp_sack_block *sp = &tp->selective_acks[0]; int max_sack = sp[0].end_seq; int this_sack; for (this_sack = 1; this_sack < tp->rx_opt.num_sacks; ++this_sack) { max_sack = after(sp[this_sack].end_seq, max_sack) ? sp[this_sack].end_seq : max_sack; } if (TCP_SKB_CB(skb)->seq == max_sack) rst_seq_match = true; } if (rst_seq_match) tcp_reset(sk); else tcp_send_challenge_ack(sk, skb); goto discard; } /* step 3: check security and precedence [ignored] */ /* step 4: Check for a SYN * RFC 5961 4.2 : Send a challenge ack */ if (th->syn) { syn_challenge: if (syn_inerr) TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE); tcp_send_challenge_ack(sk, skb); goto discard; } return true; discard: tcp_drop(sk, skb); return false; } /* * TCP receive function for the ESTABLISHED state. * * It is split into a fast path and a slow path. The fast path is * disabled when: * - A zero window was announced from us - zero window probing * is only handled properly in the slow path. * - Out of order segments arrived. * - Urgent data is expected. * - There is no buffer space left * - Unexpected TCP flags/window values/header lengths are received * (detected by checking the TCP header against pred_flags) * - Data is sent in both directions. Fast path only supports pure senders * or pure receivers (this means either the sequence number or the ack * value must stay constant) * - Unexpected TCP option. * * When these conditions are not satisfied it drops into a standard * receive procedure patterned after RFC793 to handle all cases. * The first three cases are guaranteed by proper pred_flags setting, * the rest is checked inline. Fast processing is turned on in * tcp_data_queue when everything is OK. */ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); if (unlikely(!sk->sk_rx_dst)) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. * The code loosely follows the one in the famous * "30 instruction TCP receive" Van Jacobson mail. * * Van's trick is to deposit buffers into socket queue * on a device interrupt, to call tcp_recv function * on the receive process context and checksum and copy * the buffer to user space. smart... * * Our current scheme is not silly either but we take the * extra cost of the net_bh soft interrupt processing... * We do checksum and copy also but from device to kernel. */ tp->rx_opt.saw_tstamp = 0; /* pred_flags is 0xS?10 << 16 + snd_wnd * if header_prediction is to be made * 'S' will always be tp->tcp_header_len >> 2 * '?' will be 0 for the fast path, otherwise pred_flags is 0 to * turn it off (when there are holes in the receive * space for instance) * PSH flag is ignored. */ if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags && TCP_SKB_CB(skb)->seq == tp->rcv_nxt && !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) { int tcp_header_len = tp->tcp_header_len; /* Timestamp header prediction: tcp_header_len * is automatically equal to th->doff*4 due to pred_flags * match. */ /* Check timestamp */ if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) { /* No? Slow path! */ if (!tcp_parse_aligned_timestamp(tp, th)) goto slow_path; /* If PAWS failed, check it more carefully in slow path */ if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) < 0) goto slow_path; /* DO NOT update ts_recent here, if checksum fails * and timestamp was corrupted part, it will result * in a hung connection since we will drop all * future packets due to the PAWS test. */ } if (len <= tcp_header_len) { /* Bulk data transfer: sender */ if (len == tcp_header_len) { /* Predicted packet is in window by definition. * seq == rcv_nxt and rcv_wup <= rcv_nxt. * Hence, check seq<=rcv_wup reduces to: */ if (tcp_header_len == (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) && tp->rcv_nxt == tp->rcv_wup) tcp_store_ts_recent(tp); /* We know that such packets are checksummed * on entry. */ tcp_ack(sk, skb, 0); __kfree_skb(skb); tcp_data_snd_check(sk); return; } else { /* Header too small */ TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; } } else { int eaten = 0; bool fragstolen = false; if (tp->ucopy.task == current && tp->copied_seq == tp->rcv_nxt && len - tcp_header_len <= tp->ucopy.len && sock_owned_by_user(sk)) { __set_current_state(TASK_RUNNING); if (!tcp_copy_to_iovec(sk, skb, tcp_header_len)) { /* Predicted packet is in window by definition. * seq == rcv_nxt and rcv_wup <= rcv_nxt. * Hence, check seq<=rcv_wup reduces to: */ if (tcp_header_len == (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) && tp->rcv_nxt == tp->rcv_wup) tcp_store_ts_recent(tp); tcp_rcv_rtt_measure_ts(sk, skb); __skb_pull(skb, tcp_header_len); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER); eaten = 1; } } if (!eaten) { if (tcp_checksum_complete(skb)) goto csum_error; if ((int)skb->truesize > sk->sk_forward_alloc) goto step5; /* Predicted packet is in window by definition. * seq == rcv_nxt and rcv_wup <= rcv_nxt. * Hence, check seq<=rcv_wup reduces to: */ if (tcp_header_len == (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) && tp->rcv_nxt == tp->rcv_wup) tcp_store_ts_recent(tp); tcp_rcv_rtt_measure_ts(sk, skb); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ eaten = tcp_queue_rcv(sk, skb, tcp_header_len, &fragstolen); } tcp_event_data_recv(sk, skb); if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) { /* Well, only one small jumplet in fast path... */ tcp_ack(sk, skb, FLAG_DATA); tcp_data_snd_check(sk); if (!inet_csk_ack_scheduled(sk)) goto no_ack; } else { tcp_update_wl(tp, TCP_SKB_CB(skb)->seq); } __tcp_ack_snd_check(sk, 0); no_ack: if (eaten) kfree_skb_partial(skb, fragstolen); sk->sk_data_ready(sk); return; } } slow_path: if (len < (th->doff << 2) || tcp_checksum_complete(skb)) goto csum_error; if (!th->ack && !th->rst && !th->syn) goto discard; /* * Standard slow path. */ if (!tcp_validate_incoming(sk, skb, th, 1)) return; step5: if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0) goto discard; tcp_rcv_rtt_measure_ts(sk, skb); /* Process urgent data. */ tcp_urg(sk, skb, th); /* step 7: process the segment text */ tcp_data_queue(sk, skb); tcp_data_snd_check(sk); tcp_ack_snd_check(sk); return; csum_error: TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); discard: tcp_drop(sk, skb); } EXPORT_SYMBOL(tcp_rcv_established); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); tcp_set_state(sk, TCP_ESTABLISHED); icsk->icsk_ack.lrcvtime = tcp_time_stamp; if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); } /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); tcp_init_metrics(sk); tcp_init_congestion_control(sk); /* Prevent spurious tcp_cwnd_restart() on first data * packet. */ tp->lsndtime = tcp_time_stamp; tcp_init_buffer_space(sk); if (sock_flag(sk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); if (!tp->rx_opt.snd_wscale) __tcp_fast_path_on(tp, tp->snd_wnd); else tp->pred_flags = 0; } static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, struct tcp_fastopen_cookie *cookie) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL; u16 mss = tp->rx_opt.mss_clamp, try_exp = 0; bool syn_drop = false; if (mss == tp->rx_opt.user_mss) { struct tcp_options_received opt; /* Get original SYNACK MSS value if user MSS sets mss_clamp */ tcp_clear_options(&opt); opt.user_mss = opt.mss_clamp = 0; tcp_parse_options(synack, &opt, 0, NULL); mss = opt.mss_clamp; } if (!tp->syn_fastopen) { /* Ignore an unsolicited cookie */ cookie->len = -1; } else if (tp->total_retrans) { /* SYN timed out and the SYN-ACK neither has a cookie nor * acknowledges data. Presumably the remote received only * the retransmitted (regular) SYNs: either the original * SYN-data or the corresponding SYN-ACK was dropped. */ syn_drop = (cookie->len < 0 && data); } else if (cookie->len < 0 && !tp->syn_data) { /* We requested a cookie but didn't get it. If we did not use * the (old) exp opt format then try so next time (try_exp=1). * Otherwise we go back to use the RFC7413 opt (try_exp=2). */ try_exp = tp->syn_fastopen_exp ? 2 : 1; } tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp); if (data) { /* Retransmit unacked data in SYN */ tcp_for_write_queue_from(data, sk) { if (data == tcp_send_head(sk) || __tcp_retransmit_skb(sk, data, 1)) break; } tcp_rearm_rto(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; } tp->syn_data_acked = tp->syn_data; if (tp->syn_data_acked) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); tcp_fastopen_add_skb(sk, synack); return false; } static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_cookie foc = { .len = -1 }; int saved_clamp = tp->rx_opt.mss_clamp; bool fastopen_fail; tcp_parse_options(skb, &tp->rx_opt, 0, &foc); if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; if (th->ack) { /* rfc793: * "If the state is SYN-SENT then * first check the ACK bit * If the ACK bit is set * If SEG.ACK =< ISS, or SEG.ACK > SND.NXT, send * a reset (unless the RST bit is set, if so drop * the segment and return)" */ if (!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_una) || after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) goto reset_and_undo; if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, tcp_time_stamp)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); goto reset_and_undo; } /* Now ACK is acceptable. * * "If the RST bit is set * If the ACK was acceptable then signal the user "error: * connection reset", drop the segment, enter CLOSED state, * delete TCB, and return." */ if (th->rst) { tcp_reset(sk); goto discard; } /* rfc793: * "fifth, if neither of the SYN or RST bits is set then * drop the segment and return." * * See note below! * --ANK(990513) */ if (!th->syn) goto discard_and_undo; /* rfc793: * "If the SYN bit is on ... * are acceptable then ... * (our SYN has been ACKed), change the connection * state to ESTABLISHED..." */ tcp_ecn_rcv_synack(tp, th); tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); tcp_ack(sk, skb, FLAG_SLOWPATH); /* Ok.. it's good. Set up sequence numbers and * move to established. */ tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is * never scaled. */ tp->snd_wnd = ntohs(th->window); if (!tp->rx_opt.wscale_ok) { tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0; tp->window_clamp = min(tp->window_clamp, 65535U); } if (tp->rx_opt.saw_tstamp) { tp->rx_opt.tstamp_ok = 1; tp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; tcp_store_ts_recent(tp); } else { tp->tcp_header_len = sizeof(struct tcphdr); } if (tcp_is_sack(tp) && sysctl_tcp_fack) tcp_enable_fack(tp); tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ tp->copied_seq = tp->rcv_nxt; smp_mb(); tcp_finish_connect(sk, skb); fastopen_fail = (tp->syn_fastopen || tp->syn_data) && tcp_rcv_fastopen_synack(sk, skb, &foc); if (!sock_flag(sk, SOCK_DEAD)) { sk->sk_state_change(sk); sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); } if (fastopen_fail) return -1; if (sk->sk_write_pending || icsk->icsk_accept_queue.rskq_defer_accept || icsk->icsk_ack.pingpong) { /* Save one ACK. Data will be ready after * several ticks, if write_pending is set. * * It may be deleted, but with this feature tcpdumps * look so _wonderfully_ clever, that I was not able * to stand against the temptation 8) --ANK */ inet_csk_schedule_ack(sk); tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, TCP_DELACK_MAX, TCP_RTO_MAX); discard: tcp_drop(sk, skb); return 0; } else { tcp_send_ack(sk); } return -1; } /* No ACK in the segment */ if (th->rst) { /* rfc793: * "If the RST bit is set * * Otherwise (no ACK) drop the segment and return." */ goto discard_and_undo; } /* PAWS check. */ if (tp->rx_opt.ts_recent_stamp && tp->rx_opt.saw_tstamp && tcp_paws_reject(&tp->rx_opt, 0)) goto discard_and_undo; if (th->syn) { /* We see SYN without ACK. It is attempt of * simultaneous connect with crossed SYNs. * Particularly, it can be connect to self. */ tcp_set_state(sk, TCP_SYN_RECV); if (tp->rx_opt.saw_tstamp) { tp->rx_opt.tstamp_ok = 1; tcp_store_ts_recent(tp); tp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { tp->tcp_header_len = sizeof(struct tcphdr); } tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; tp->copied_seq = tp->rcv_nxt; tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is * never scaled. */ tp->snd_wnd = ntohs(th->window); tp->snd_wl1 = TCP_SKB_CB(skb)->seq; tp->max_window = tp->snd_wnd; tcp_ecn_rcv_syn(tp, th); tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); tcp_send_synack(sk); #if 0 /* Note, we could accept data and URG from this segment. * There are no obstacles to make this (except that we must * either change tcp_recvmsg() to prevent it from returning data * before 3WHS completes per RFC793, or employ TCP Fast Open). * * However, if we ignore data in ACKless segments sometimes, * we have no reasons to accept it sometimes. * Also, seems the code doing it in step6 of tcp_rcv_state_process * is not flawless. So, discard packet for sanity. * Uncomment this return to process the data. */ return -1; #else goto discard; #endif } /* "fifth, if neither of the SYN or RST bits is set then * drop the segment and return." */ discard_and_undo: tcp_clear_options(&tp->rx_opt); tp->rx_opt.mss_clamp = saved_clamp; goto discard; reset_and_undo: tcp_clear_options(&tp->rx_opt); tp->rx_opt.mss_clamp = saved_clamp; return 1; } /* * This function implements the receiving procedure of RFC 793 for * all states except ESTABLISHED and TIME_WAIT. * It's called from both tcp_v4_rcv and tcp_v6_rcv and should be * address independent. */ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); const struct tcphdr *th = tcp_hdr(skb); struct request_sock *req; int queued = 0; bool acceptable; switch (sk->sk_state) { case TCP_CLOSE: goto discard; case TCP_LISTEN: if (th->ack) return 1; if (th->rst) goto discard; if (th->syn) { if (th->fin) goto discard; /* It is possible that we process SYN packets from backlog, * so we need to make sure to disable BH and RCU right there. */ rcu_read_lock(); local_bh_disable(); acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0; local_bh_enable(); rcu_read_unlock(); if (!acceptable) return 1; consume_skb(skb); return 0; } goto discard; case TCP_SYN_SENT: tp->rx_opt.saw_tstamp = 0; queued = tcp_rcv_synsent_state_process(sk, skb, th); if (queued >= 0) return queued; /* Do step6 onward by hand. */ tcp_urg(sk, skb, th); __kfree_skb(skb); tcp_data_snd_check(sk); return 0; } tp->rx_opt.saw_tstamp = 0; req = tp->fastopen_rsk; if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); if (!tcp_check_req(sk, skb, req, true)) goto discard; } if (!th->ack && !th->rst && !th->syn) goto discard; if (!tcp_validate_incoming(sk, skb, th, 0)) return 0; /* step 5: check the ACK field */ acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT | FLAG_NO_CHALLENGE_ACK) > 0; if (!acceptable) { if (sk->sk_state == TCP_SYN_RECV) return 1; /* send one RST */ tcp_send_challenge_ack(sk, skb); goto discard; } switch (sk->sk_state) { case TCP_SYN_RECV: if (!tp->srtt_us) tcp_synack_rtt_meas(sk, req); /* Once we leave TCP_SYN_RECV, we no longer need req * so release it. */ if (req) { inet_csk(sk)->icsk_retransmits = 0; reqsk_fastopen_remove(sk, req, false); } else { /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); tcp_init_congestion_control(sk); tcp_mtup_init(sk); tp->copied_seq = tp->rcv_nxt; tcp_init_buffer_space(sk); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); sk->sk_state_change(sk); /* Note, that this wakeup is only for marginal crossed SYN case. * Passively open sockets are not waked up, because * sk->sk_sleep == NULL and sk->sk_socket == NULL. */ if (sk->sk_socket) sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); tp->snd_una = TCP_SKB_CB(skb)->ack_seq; tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; if (req) { /* Re-arm the timer because data may have been sent out. * This is similar to the regular data transmission case * when new data has just been ack'ed. * * (TFO) - we could try to be more aggressive and * retransmitting any data sooner based on when they * are sent out. */ tcp_rearm_rto(sk); } else tcp_init_metrics(sk); if (!inet_csk(sk)->icsk_ca_ops->cong_control) tcp_update_pacing_rate(sk); /* Prevent spurious tcp_cwnd_restart() on first data packet */ tp->lsndtime = tcp_time_stamp; tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); break; case TCP_FIN_WAIT1: { struct dst_entry *dst; int tmo; /* If we enter the TCP_FIN_WAIT1 state and we are a * Fast Open socket and this is the first acceptable * ACK we have received, this would have acknowledged * our SYNACK so stop the SYNACK timer. */ if (req) { /* We no longer need the request sock. */ reqsk_fastopen_remove(sk, req, false); tcp_rearm_rto(sk); } if (tp->snd_una != tp->write_seq) break; tcp_set_state(sk, TCP_FIN_WAIT2); sk->sk_shutdown |= SEND_SHUTDOWN; dst = __sk_dst_get(sk); if (dst) dst_confirm(dst); if (!sock_flag(sk, SOCK_DEAD)) { /* Wake up lingering close() */ sk->sk_state_change(sk); break; } if (tp->linger2 < 0 || (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) { tcp_done(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); return 1; } tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) { inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); } else if (th->fin || sock_owned_by_user(sk)) { /* Bad case. We could lose such FIN otherwise. * It is not a big problem, but it looks confusing * and not so rare event. We still can lose it now, * if it spins in bh_lock_sock(), but it is really * marginal case. */ inet_csk_reset_keepalive_timer(sk, tmo); } else { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto discard; } break; } case TCP_CLOSING: if (tp->snd_una == tp->write_seq) { tcp_time_wait(sk, TCP_TIME_WAIT, 0); goto discard; } break; case TCP_LAST_ACK: if (tp->snd_una == tp->write_seq) { tcp_update_metrics(sk); tcp_done(sk); goto discard; } break; } /* step 6: check the URG bit */ tcp_urg(sk, skb, th); /* step 7: process the segment text */ switch (sk->sk_state) { case TCP_CLOSE_WAIT: case TCP_CLOSING: case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: /* RFC 793 says to queue data in these states, * RFC 1122 says we MUST send a reset. * BSD 4.4 also does reset. */ if (sk->sk_shutdown & RCV_SHUTDOWN) { if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); tcp_reset(sk); return 1; } } /* Fall through */ case TCP_ESTABLISHED: tcp_data_queue(sk, skb); queued = 1; break; } /* tcp_data could move socket to TIME-WAIT */ if (sk->sk_state != TCP_CLOSE) { tcp_data_snd_check(sk); tcp_ack_snd_check(sk); } if (!queued) { discard: tcp_drop(sk, skb); } return 0; } EXPORT_SYMBOL(tcp_rcv_state_process); static inline void pr_drop_req(struct request_sock *req, __u16 port, int family) { struct inet_request_sock *ireq = inet_rsk(req); if (family == AF_INET) net_dbg_ratelimited("drop open request from %pI4/%u\n", &ireq->ir_rmt_addr, port); #if IS_ENABLED(CONFIG_IPV6) else if (family == AF_INET6) net_dbg_ratelimited("drop open request from %pI6/%u\n", &ireq->ir_v6_rmt_addr, port); #endif } /* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set * * If we receive a SYN packet with these bits set, it means a * network is playing bad games with TOS bits. In order to * avoid possible false congestion notifications, we disable * TCP ECN negotiation. * * Exception: tcp_ca wants ECN. This is required for DCTCP * congestion control: Linux DCTCP asserts ECT on all packets, * including SYN, which is most optimal solution; however, * others, such as FreeBSD do not. */ static void tcp_ecn_create_request(struct request_sock *req, const struct sk_buff *skb, const struct sock *listen_sk, const struct dst_entry *dst) { const struct tcphdr *th = tcp_hdr(skb); const struct net *net = sock_net(listen_sk); bool th_ecn = th->ece && th->cwr; bool ect, ecn_ok; u32 ecn_ok_dst; if (!th_ecn) return; ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield); ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK); ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst; if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || (ecn_ok_dst & DST_FEATURE_ECN_CA)) inet_rsk(req)->ecn_ok = 1; } static void tcp_openreq_init(struct request_sock *req, const struct tcp_options_received *rx_opt, struct sk_buff *skb, const struct sock *sk) { struct inet_request_sock *ireq = inet_rsk(req); req->rsk_rcv_wnd = 0; /* So that tcp_send_synack() knows! */ req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; skb_mstamp_get(&tcp_rsk(req)->snt_synack); tcp_rsk(req)->last_oow_ack_time = 0; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; ireq->tstamp_ok = rx_opt->tstamp_ok; ireq->sack_ok = rx_opt->sack_ok; ireq->snd_wscale = rx_opt->snd_wscale; ireq->wscale_ok = rx_opt->wscale_ok; ireq->acked = 0; ireq->ecn_ok = 0; ireq->ir_rmt_port = tcp_hdr(skb)->source; ireq->ir_num = ntohs(tcp_hdr(skb)->dest); ireq->ir_mark = inet_request_mark(sk, skb); } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener) { struct request_sock *req = reqsk_alloc(ops, sk_listener, attach_listener); if (req) { struct inet_request_sock *ireq = inet_rsk(req); kmemcheck_annotate_bitfield(ireq, flags); ireq->ireq_opt = NULL; #if IS_ENABLED(CONFIG_IPV6) ireq->pktopts = NULL; #endif atomic64_set(&ireq->ir_cookie, 0); ireq->ireq_state = TCP_NEW_SYN_RECV; write_pnet(&ireq->ireq_net, sock_net(sk_listener)); ireq->ireq_family = sk_listener->sk_family; } return req; } EXPORT_SYMBOL(inet_reqsk_alloc); /* * Return true if a syncookie should be sent */ static bool tcp_syn_flood_action(const struct sock *sk, const struct sk_buff *skb, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; bool want_cookie = false; struct net *net = sock_net(sk); #ifdef CONFIG_SYN_COOKIES if (net->ipv4.sysctl_tcp_syncookies) { msg = "Sending cookies"; want_cookie = true; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); } else #endif __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); if (!queue->synflood_warned && net->ipv4.sysctl_tcp_syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, ntohs(tcp_hdr(skb)->dest), msg); return want_cookie; } static void tcp_reqsk_record_syn(const struct sock *sk, struct request_sock *req, const struct sk_buff *skb) { if (tcp_sk(sk)->save_syn) { u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb); u32 *copy; copy = kmalloc(len + sizeof(u32), GFP_ATOMIC); if (copy) { copy[0] = len; memcpy(©[1], skb_network_header(skb), len); req->saved_syn = copy; } } } int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { struct tcp_fastopen_cookie foc = { .len = -1 }; __u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sock *fastopen_sk = NULL; struct dst_entry *dst = NULL; struct request_sock *req; bool want_cookie = false; struct flowi fl; /* TW buckets are converted to open requests without * limitations, they conserve resources and peer is * evidently real one. */ if ((net->ipv4.sysctl_tcp_syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name); if (!want_cookie) goto drop; } if (sk_acceptq_is_full(sk)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; } req = inet_reqsk_alloc(rsk_ops, sk, !want_cookie); if (!req) goto drop; tcp_rsk(req)->af_specific = af_ops; tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = af_ops->mss_clamp; tmp_opt.user_mss = tp->rx_opt.user_mss; tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc); if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb, sk); inet_rsk(req)->no_srccheck = inet_sk(sk)->transparent; /* Note: tcp_v6_init_req() might override ir_iif for link locals */ inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); af_ops->init_req(req, sk, skb); if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; if (!want_cookie && !isn) { /* VJ's idea. We save last timestamp seen * from the destination in peer table, when entering * state TIME-WAIT, and check against it before * accepting new connection request. * * If "isn" is not zero, this request hit alive * timewait bucket, so that all the necessary checks * are made in the function processing timewait state. */ if (tcp_death_row.sysctl_tw_recycle) { bool strict; dst = af_ops->route_req(sk, &fl, req, &strict); if (dst && strict && !tcp_peer_is_proven(req, dst, true, tmp_opt.saw_tstamp)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); goto drop_and_release; } } /* Kill the following clause, if you dislike this way. */ else if (!net->ipv4.sysctl_tcp_syncookies && (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < (sysctl_max_syn_backlog >> 2)) && !tcp_peer_is_proven(req, dst, false, tmp_opt.saw_tstamp)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. * It means that we continue to communicate * to destinations, already remembered * to the moment of synflood. */ pr_drop_req(req, ntohs(tcp_hdr(skb)->source), rsk_ops->family); goto drop_and_release; } isn = af_ops->init_seq(skb); } if (!dst) { dst = af_ops->route_req(sk, &fl, req, NULL); if (!dst) goto drop_and_free; } tcp_ecn_create_request(req, skb, sk, dst); if (want_cookie) { isn = cookie_init_sequence(af_ops, sk, skb, &req->mss); req->cookie_ts = tmp_opt.tstamp_ok; if (!tmp_opt.tstamp_ok) inet_rsk(req)->ecn_ok = 0; } tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->txhash = net_tx_rndhash(); tcp_openreq_init_rwin(req, sk, dst); if (!want_cookie) { tcp_reqsk_record_syn(sk, req, skb); fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); } if (fastopen_sk) { af_ops->send_synack(fastopen_sk, dst, &fl, req, &foc, TCP_SYNACK_FASTOPEN); /* Add the child socket directly into the accept queue */ if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { reqsk_fastopen_remove(fastopen_sk, req, false); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); reqsk_put(req); goto drop; } sk->sk_data_ready(sk); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); } else { tcp_rsk(req)->tfo_listener = false; if (!want_cookie) inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : TCP_SYNACK_COOKIE); if (want_cookie) { reqsk_free(req); return 0; } } reqsk_put(req); return 0; drop_and_release: dst_release(dst); drop_and_free: reqsk_free(req); drop: tcp_listendrop(sk); return 0; } EXPORT_SYMBOL(tcp_conn_request);