From 6ba8a3b19e764b6a65e4030ab0999be50c291e6c Mon Sep 17 00:00:00 2001 From: Nandita Dukkipati Date: Mon, 11 Mar 2013 10:00:43 +0000 Subject: tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati Acked-by: Neal Cardwell Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0d9bdacce99f..b794f89ac1f2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -98,7 +98,7 @@ int sysctl_tcp_frto_response __read_mostly; int sysctl_tcp_thin_dupack __read_mostly; int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; -int sysctl_tcp_early_retrans __read_mostly = 2; +int sysctl_tcp_early_retrans __read_mostly = 3; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ @@ -2150,15 +2150,16 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag) * 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 || (flag & FLAG_ECE) || !tp->srtt) + if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 || + (flag & FLAG_ECE) || !tp->srtt) return false; delay = max_t(unsigned long, (tp->srtt >> 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_RETRANS, delay, TCP_RTO_MAX); - tp->early_retrans_delayed = 1; + inet_csk_reset_xmit_timer(sk, ICSK_TIME_EARLY_RETRANS, delay, + TCP_RTO_MAX); return true; } @@ -2321,7 +2322,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) * 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) && + (tp->packets_out >= (tp->sacked_out + 1) && tp->packets_out < 4) && !tcp_may_send_now(sk)) return !tcp_pause_early_retransmit(sk, flag); @@ -3081,6 +3082,7 @@ static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) */ 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 @@ -3094,12 +3096,13 @@ void tcp_rearm_rto(struct sock *sk) } else { u32 rto = inet_csk(sk)->icsk_rto; /* Offset the time elapsed after installing regular RTO */ - if (tp->early_retrans_delayed) { + 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_CB(skb)->when + rto; s32 delta = (s32)(rto_time_stamp - tcp_time_stamp); /* delta may not be positive if the socket is locked - * when the delayed ER timer fires and is rescheduled. + * when the retrans timer fires and is rescheduled. */ if (delta > 0) rto = delta; @@ -3107,7 +3110,6 @@ void tcp_rearm_rto(struct sock *sk) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, TCP_RTO_MAX); } - tp->early_retrans_delayed = 0; } /* This function is called when the delayed ER timer fires. TCP enters @@ -3601,7 +3603,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, tp->snd_nxt)) goto invalid_ack; - if (tp->early_retrans_delayed) + 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)) @@ -3678,6 +3681,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (dst) dst_confirm(dst); } + + if (icsk->icsk_pending == ICSK_TIME_RETRANS) + tcp_schedule_loss_probe(sk); return 1; no_queue: -- cgit v1.2.3 From 9b717a8d245075ffb8e95a2dfb4ee97ce4747457 Mon Sep 17 00:00:00 2001 From: Nandita Dukkipati Date: Mon, 11 Mar 2013 10:00:44 +0000 Subject: tcp: TLP loss detection. This is the second of the TLP patch series; it augments the basic TLP algorithm with a loss detection scheme. This patch implements a mechanism for loss detection when a Tail loss probe retransmission plugs a hole thereby masking packet loss from the sender. The loss detection algorithm relies on counting TLP dupacks as outlined in Sec. 3 of: http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01 The basic idea is: Sender keeps track of TLP "episode" upon retransmission of a TLP packet. An episode ends when the sender receives an ACK above the SND.NXT (tracked by tlp_high_seq) at the time of the episode. We want to make sure that before the episode ends the sender receives a "TLP dupack", indicating that the TLP retransmission was unnecessary, so there was no loss/hole that needed plugging. If the sender gets no TLP dupack before the end of the episode, then it reduces ssthresh and the congestion window, because the TLP packet arriving at the receiver probably plugged a hole. Signed-off-by: Nandita Dukkipati Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b794f89ac1f2..836d74dd0187 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2682,6 +2682,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh) 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; @@ -3569,6 +3570,38 @@ static void tcp_send_challenge_ack(struct sock *sk) } } +/* This routine deals with acks during a TLP episode. + * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. + */ +static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + bool is_tlp_dupack = (ack == tp->tlp_high_seq) && + !(flag & (FLAG_SND_UNA_ADVANCED | + FLAG_NOT_DUP | FLAG_DATA_SACKED)); + + /* Mark the end of TLP episode on receiving TLP dupack or when + * ack is after tlp_high_seq. + */ + if (is_tlp_dupack) { + tp->tlp_high_seq = 0; + return; + } + + if (after(ack, tp->tlp_high_seq)) { + tp->tlp_high_seq = 0; + /* Don't reduce cwnd if DSACK arrives for TLP retrans. */ + if (!(flag & FLAG_DSACKING_ACK)) { + tcp_init_cwnd_reduction(sk, true); + tcp_set_ca_state(sk, TCP_CA_CWR); + tcp_end_cwnd_reduction(sk); + tcp_set_ca_state(sk, TCP_CA_Open); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPLOSSPROBERECOVERY); + } + } +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@ -3676,6 +3709,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_cong_avoid(sk, ack, prior_in_flight); } + 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) @@ -3697,6 +3733,9 @@ no_queue: */ 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: -- cgit v1.2.3 From 1a2c6181c4a1922021b4d7df373bba612c3e5f04 Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Sun, 17 Mar 2013 08:23:34 +0000 Subject: tcp: Remove TCPCT TCPCT uses option-number 253, reserved for experimental use and should not be used in production environments. Further, TCPCT does not fully implement RFC 6013. As a nice side-effect, removing TCPCT increases TCP's performance for very short flows: Doing an apache-benchmark with -c 100 -n 100000, sending HTTP-requests for files of 1KB size. before this patch: average (among 7 runs) of 20845.5 Requests/Second after: average (among 7 runs) of 21403.6 Requests/Second Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 69 ++++++---------------------------------------------- 1 file changed, 7 insertions(+), 62 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 836d74dd0187..19f0149fb6a2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3760,8 +3760,8 @@ old_ack: * 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, - const u8 **hvpp, int estab, +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; @@ -3845,31 +3845,6 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o */ break; #endif - case TCPOPT_COOKIE: - /* This option is variable length. - */ - switch (opsize) { - case TCPOLEN_COOKIE_BASE: - /* not yet implemented */ - break; - case TCPOLEN_COOKIE_PAIR: - /* not yet implemented */ - break; - case TCPOLEN_COOKIE_MIN+0: - case TCPOLEN_COOKIE_MIN+2: - case TCPOLEN_COOKIE_MIN+4: - case TCPOLEN_COOKIE_MIN+6: - case TCPOLEN_COOKIE_MAX: - /* 16-bit multiple */ - opt_rx->cookie_plus = opsize; - *hvpp = ptr; - break; - default: - /* ignore option */ - break; - } - break; - case TCPOPT_EXP: /* Fast Open option shares code 254 using a * 16 bits magic number. It's valid only in @@ -3915,8 +3890,7 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr * 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, const u8 **hvpp) + 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. @@ -3930,7 +3904,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, return true; } - tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); + tcp_parse_options(skb, &tp->rx_opt, 1, NULL); if (tp->rx_opt.saw_tstamp) tp->rx_opt.rcv_tsecr -= tp->tsoffset; @@ -5311,12 +5285,10 @@ out: static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, int syn_inerr) { - const u8 *hash_location; struct tcp_sock *tp = tcp_sk(sk); /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(skb, th, tp, &hash_location) && - tp->rx_opt.saw_tstamp && + if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); @@ -5670,12 +5642,11 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, if (mss == tp->rx_opt.user_mss) { struct tcp_options_received opt; - const u8 *hash_location; /* 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, &hash_location, 0, NULL); + tcp_parse_options(synack, &opt, 0, NULL); mss = opt.mss_clamp; } @@ -5706,14 +5677,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len) { - const u8 *hash_location; struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct tcp_cookie_values *cvp = tp->cookie_values; struct tcp_fastopen_cookie foc = { .len = -1 }; int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc); + tcp_parse_options(skb, &tp->rx_opt, 0, &foc); if (tp->rx_opt.saw_tstamp) tp->rx_opt.rcv_tsecr -= tp->tsoffset; @@ -5810,30 +5779,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * is initialized. */ tp->copied_seq = tp->rcv_nxt; - if (cvp != NULL && - cvp->cookie_pair_size > 0 && - tp->rx_opt.cookie_plus > 0) { - int cookie_size = tp->rx_opt.cookie_plus - - TCPOLEN_COOKIE_BASE; - int cookie_pair_size = cookie_size - + cvp->cookie_desired; - - /* A cookie extension option was sent and returned. - * Note that each incoming SYNACK replaces the - * Responder cookie. The initial exchange is most - * fragile, as protection against spoofing relies - * entirely upon the sequence and timestamp (above). - * This replacement strategy allows the correct pair to - * pass through, while any others will be filtered via - * Responder verification later. - */ - if (sizeof(cvp->cookie_pair) >= cookie_pair_size) { - memcpy(&cvp->cookie_pair[cvp->cookie_desired], - hash_location, cookie_size); - cvp->cookie_pair_size = cookie_pair_size; - } - } - smp_mb(); tcp_finish_connect(sk, skb); -- cgit v1.2.3 From 9b44190dc114c1720b34975b5bfc65aece112ced Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 20 Mar 2013 13:32:58 +0000 Subject: tcp: refactor F-RTO The patch series refactor the F-RTO feature (RFC4138/5682). This is to simplify the loss recovery processing. Existing F-RTO was developed during the experimental stage (RFC4138) and has many experimental features. It takes a separate code path from the traditional timeout processing by overloading CA_Disorder instead of using CA_Loss state. This complicates CA_Disorder state handling because it's also used for handling dubious ACKs and undos. While the algorithm in the RFC does not change the congestion control, the implementation intercepts congestion control in various places (e.g., frto_cwnd in tcp_ack()). The new code implements newer F-RTO RFC5682 using CA_Loss processing path. F-RTO becomes a small extension in the timeout processing and interfaces with congestion control and Eifel undo modules. It lets congestion control (module) determines how many to send independently. F-RTO only chooses what to send in order to detect spurious retranmission. If timeout is found spurious it invokes existing Eifel undo algorithms like DSACK or TCP timestamp based detection. The first patch removes all F-RTO code except the sysctl_tcp_frto is left for the new implementation. Since CA_EVENT_FRTO is removed, TCP westwood now computes ssthresh on regular timeout CA_EVENT_LOSS event. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 375 +-------------------------------------------------- 1 file changed, 4 insertions(+), 371 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 19f0149fb6a2..231c79fe91f3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -93,7 +93,6 @@ 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_frto_response __read_mostly; int sysctl_tcp_thin_dupack __read_mostly; @@ -108,17 +107,14 @@ int sysctl_tcp_early_retrans __read_mostly = 3; #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ #define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/ -#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */ #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_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ #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 FLAG_ANY_PROGRESS (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED) #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)) @@ -1159,10 +1155,6 @@ static u8 tcp_sacktag_one(struct sock *sk, tcp_highest_sack_seq(tp))) state->reord = min(fack_count, state->reord); - - /* SACK enhanced F-RTO (RFC4138; Appendix B) */ - if (!after(end_seq, tp->frto_highmark)) - state->flag |= FLAG_ONLY_ORIG_SACKED; } if (sacked & TCPCB_LOST) { @@ -1555,7 +1547,6 @@ static int tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, u32 prior_snd_una) { - const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + TCP_SKB_CB(ack_skb)->sacked); @@ -1728,12 +1719,6 @@ walk: start_seq, end_seq, dup_sack); advance_sp: - /* SACK enhanced FRTO (RFC4138, Appendix B): Clearing correct - * due to in-order walk - */ - if (after(end_seq, tp->frto_highmark)) - state.flag &= ~FLAG_ONLY_ORIG_SACKED; - i++; } @@ -1750,8 +1735,7 @@ advance_sp: tcp_verify_left_out(tp); if ((state.reord < tp->fackets_out) && - ((icsk->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker) && - (!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark))) + ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state.reord, 0); out: @@ -1825,197 +1809,6 @@ static inline void tcp_reset_reno_sack(struct tcp_sock *tp) tp->sacked_out = 0; } -static int tcp_is_sackfrto(const struct tcp_sock *tp) -{ - return (sysctl_tcp_frto == 0x2) && !tcp_is_reno(tp); -} - -/* F-RTO can only be used if TCP has never retransmitted anything other than - * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here) - */ -bool tcp_use_frto(struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - const struct inet_connection_sock *icsk = inet_csk(sk); - struct sk_buff *skb; - - if (!sysctl_tcp_frto) - return false; - - /* MTU probe and F-RTO won't really play nicely along currently */ - if (icsk->icsk_mtup.probe_size) - return false; - - if (tcp_is_sackfrto(tp)) - return true; - - /* Avoid expensive walking of rexmit queue if possible */ - if (tp->retrans_out > 1) - return false; - - skb = tcp_write_queue_head(sk); - if (tcp_skb_is_last(sk, skb)) - return true; - skb = tcp_write_queue_next(sk, skb); /* Skips head */ - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) - return false; - /* Short-circuit when first non-SACKed skb has been checked */ - if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) - break; - } - return true; -} - -/* RTO occurred, but do not yet enter Loss state. Instead, defer RTO - * recovery a bit and use heuristics in tcp_process_frto() to detect if - * the RTO was spurious. Only clear SACKED_RETRANS of the head here to - * keep retrans_out counting accurate (with SACK F-RTO, other than head - * may still have that bit set); TCPCB_LOST and remaining SACKED_RETRANS - * bits are handled if the Loss state is really to be entered (in - * tcp_enter_frto_loss). - * - * Do like tcp_enter_loss() would; when RTO expires the second time it - * does: - * "Reduce ssthresh if it has not yet been made inside this window." - */ -void tcp_enter_frto(struct sock *sk) -{ - const struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - - if ((!tp->frto_counter && icsk->icsk_ca_state <= TCP_CA_Disorder) || - tp->snd_una == tp->high_seq || - ((icsk->icsk_ca_state == TCP_CA_Loss || tp->frto_counter) && - !icsk->icsk_retransmits)) { - tp->prior_ssthresh = tcp_current_ssthresh(sk); - /* Our state is too optimistic in ssthresh() call because cwnd - * is not reduced until tcp_enter_frto_loss() when previous F-RTO - * recovery has not yet completed. Pattern would be this: RTO, - * Cumulative ACK, RTO (2xRTO for the same segment does not end - * up here twice). - * RFC4138 should be more specific on what to do, even though - * RTO is quite unlikely to occur after the first Cumulative ACK - * due to back-off and complexity of triggering events ... - */ - if (tp->frto_counter) { - u32 stored_cwnd; - stored_cwnd = tp->snd_cwnd; - tp->snd_cwnd = 2; - tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); - tp->snd_cwnd = stored_cwnd; - } else { - tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); - } - /* ... in theory, cong.control module could do "any tricks" in - * ssthresh(), which means that ca_state, lost bits and lost_out - * counter would have to be faked before the call occurs. We - * consider that too expensive, unlikely and hacky, so modules - * using these in ssthresh() must deal these incompatibility - * issues if they receives CA_EVENT_FRTO and frto_counter != 0 - */ - tcp_ca_event(sk, CA_EVENT_FRTO); - } - - tp->undo_marker = tp->snd_una; - tp->undo_retrans = 0; - - skb = tcp_write_queue_head(sk); - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) - tp->undo_marker = 0; - 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_verify_left_out(tp); - - /* Too bad if TCP was application limited */ - tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp) + 1); - - /* Earlier loss recovery underway (see RFC4138; Appendix B). - * The last condition is necessary at least in tp->frto_counter case. - */ - if (tcp_is_sackfrto(tp) && (tp->frto_counter || - ((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) && - after(tp->high_seq, tp->snd_una)) { - tp->frto_highmark = tp->high_seq; - } else { - tp->frto_highmark = tp->snd_nxt; - } - tcp_set_ca_state(sk, TCP_CA_Disorder); - tp->high_seq = tp->snd_nxt; - tp->frto_counter = 1; -} - -/* Enter Loss state after F-RTO was applied. Dupack arrived after RTO, - * which indicates that we should follow the traditional RTO recovery, - * i.e. mark everything lost and do go-back-N retransmission. - */ -static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) -{ - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - - tp->lost_out = 0; - tp->retrans_out = 0; - if (tcp_is_reno(tp)) - tcp_reset_reno_sack(tp); - - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - - TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; - /* - * Count the retransmission made on RTO correctly (only when - * waiting for the first ACK and did not get it)... - */ - if ((tp->frto_counter == 1) && !(flag & FLAG_DATA_ACKED)) { - /* For some reason this R-bit might get cleared? */ - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) - tp->retrans_out += tcp_skb_pcount(skb); - /* ...enter this if branch just for the first segment */ - flag |= FLAG_DATA_ACKED; - } else { - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) - tp->undo_marker = 0; - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - } - - /* Marking forward transmissions that were made after RTO lost - * can cause unnecessary retransmissions in some scenarios, - * SACK blocks will mitigate that in some but not in all cases. - * We used to not mark them but it was causing break-ups with - * receivers that do only in-order receival. - * - * TODO: we could detect presence of such receiver and select - * different behavior per flow. - */ - if (!(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); - - tp->snd_cwnd = tcp_packets_in_flight(tp) + allowed_segments; - tp->snd_cwnd_cnt = 0; - tp->snd_cwnd_stamp = tcp_time_stamp; - tp->frto_counter = 0; - - tp->reordering = min_t(unsigned int, tp->reordering, - sysctl_tcp_reordering); - tcp_set_ca_state(sk, TCP_CA_Loss); - tp->high_seq = tp->snd_nxt; - TCP_ECN_queue_cwr(tp); - - tcp_clear_all_retrans_hints(tp); -} - static void tcp_clear_retrans_partial(struct tcp_sock *tp) { tp->retrans_out = 0; @@ -2090,8 +1883,6 @@ void tcp_enter_loss(struct sock *sk, int how) tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; TCP_ECN_queue_cwr(tp); - /* Abort F-RTO algorithm if one is in progress */ - tp->frto_counter = 0; } /* If ACK arrived pointing to a remembered SACK, it means that our @@ -2275,10 +2066,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) struct tcp_sock *tp = tcp_sk(sk); __u32 packets_out; - /* Do not perform any recovery during F-RTO algorithm */ - if (tp->frto_counter) - return false; - /* Trick#1: The loss is proven. */ if (tp->lost_out) return true; @@ -2760,7 +2547,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked) tcp_verify_left_out(tp); - if (!tp->frto_counter && !tcp_any_retrans_done(sk)) + if (!tcp_any_retrans_done(sk)) tp->retrans_stamp = 0; if (flag & FLAG_ECE) @@ -3198,8 +2985,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, flag |= FLAG_RETRANS_DATA_ACKED; ca_seq_rtt = -1; seq_rtt = -1; - if ((flag & FLAG_DATA_ACKED) || (acked_pcount > 1)) - flag |= FLAG_NONHEAD_RETRANS_ACKED; } else { ca_seq_rtt = now - scb->when; last_ackt = skb->tstamp; @@ -3408,150 +3193,6 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } -/* A very conservative spurious RTO response algorithm: reduce cwnd and - * continue in congestion avoidance. - */ -static void tcp_conservative_spur_to_response(struct tcp_sock *tp) -{ - tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); - tp->snd_cwnd_cnt = 0; - TCP_ECN_queue_cwr(tp); - tcp_moderate_cwnd(tp); -} - -/* A conservative spurious RTO response algorithm: reduce cwnd using - * PRR and continue in congestion avoidance. - */ -static void tcp_cwr_spur_to_response(struct sock *sk) -{ - tcp_enter_cwr(sk, 0); -} - -static void tcp_undo_spur_to_response(struct sock *sk, int flag) -{ - if (flag & FLAG_ECE) - tcp_cwr_spur_to_response(sk); - else - tcp_undo_cwr(sk, true); -} - -/* F-RTO spurious RTO detection algorithm (RFC4138) - * - * F-RTO affects during two new ACKs following RTO (well, almost, see inline - * comments). State (ACK number) is kept in frto_counter. When ACK advances - * window (but not to or beyond highest sequence sent before RTO): - * On First ACK, send two new segments out. - * On Second ACK, RTO was likely spurious. Do spurious response (response - * algorithm is not part of the F-RTO detection algorithm - * given in RFC4138 but can be selected separately). - * Otherwise (basically on duplicate ACK), RTO was (likely) caused by a loss - * and TCP falls back to conventional RTO recovery. F-RTO allows overriding - * of Nagle, this is done using frto_counter states 2 and 3, when a new data - * segment of any size sent during F-RTO, state 2 is upgraded to 3. - * - * Rationale: if the RTO was spurious, new ACKs should arrive from the - * original window even after we transmit two new data segments. - * - * SACK version: - * on first step, wait until first cumulative ACK arrives, then move to - * the second step. In second step, the next ACK decides. - * - * F-RTO is implemented (mainly) in four functions: - * - tcp_use_frto() is used to determine if TCP is can use F-RTO - * - tcp_enter_frto() prepares TCP state on RTO if F-RTO is used, it is - * called when tcp_use_frto() showed green light - * - tcp_process_frto() handles incoming ACKs during F-RTO algorithm - * - tcp_enter_frto_loss() is called if there is not enough evidence - * to prove that the RTO is indeed spurious. It transfers the control - * from F-RTO to the conventional RTO recovery - */ -static bool tcp_process_frto(struct sock *sk, int flag) -{ - struct tcp_sock *tp = tcp_sk(sk); - - tcp_verify_left_out(tp); - - /* Duplicate the behavior from Loss state (fastretrans_alert) */ - if (flag & FLAG_DATA_ACKED) - inet_csk(sk)->icsk_retransmits = 0; - - if ((flag & FLAG_NONHEAD_RETRANS_ACKED) || - ((tp->frto_counter >= 2) && (flag & FLAG_RETRANS_DATA_ACKED))) - tp->undo_marker = 0; - - if (!before(tp->snd_una, tp->frto_highmark)) { - tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag); - return true; - } - - if (!tcp_is_sackfrto(tp)) { - /* RFC4138 shortcoming in step 2; should also have case c): - * ACK isn't duplicate nor advances window, e.g., opposite dir - * data, winupdate - */ - if (!(flag & FLAG_ANY_PROGRESS) && (flag & FLAG_NOT_DUP)) - return true; - - if (!(flag & FLAG_DATA_ACKED)) { - tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 0 : 3), - flag); - return true; - } - } else { - if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) { - if (!tcp_packets_in_flight(tp)) { - tcp_enter_frto_loss(sk, 2, flag); - return true; - } - - /* Prevent sending of new data. */ - tp->snd_cwnd = min(tp->snd_cwnd, - tcp_packets_in_flight(tp)); - return true; - } - - if ((tp->frto_counter >= 2) && - (!(flag & FLAG_FORWARD_PROGRESS) || - ((flag & FLAG_DATA_SACKED) && - !(flag & FLAG_ONLY_ORIG_SACKED)))) { - /* RFC4138 shortcoming (see comment above) */ - if (!(flag & FLAG_FORWARD_PROGRESS) && - (flag & FLAG_NOT_DUP)) - return true; - - tcp_enter_frto_loss(sk, 3, flag); - return true; - } - } - - if (tp->frto_counter == 1) { - /* tcp_may_send_now needs to see updated state */ - tp->snd_cwnd = tcp_packets_in_flight(tp) + 2; - tp->frto_counter = 2; - - if (!tcp_may_send_now(sk)) - tcp_enter_frto_loss(sk, 2, flag); - - return true; - } else { - switch (sysctl_tcp_frto_response) { - case 2: - tcp_undo_spur_to_response(sk, flag); - break; - case 1: - tcp_conservative_spur_to_response(tp); - break; - default: - tcp_cwr_spur_to_response(sk); - break; - } - tp->frto_counter = 0; - tp->undo_marker = 0; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); - } - return false; -} - /* RFC 5961 7 [ACK Throttling] */ static void tcp_send_challenge_ack(struct sock *sk) { @@ -3616,7 +3257,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int prior_packets; int prior_sacked = tp->sacked_out; int pkts_acked = 0; - bool frto_cwnd = false; /* If the ack is older than previous acks * then we can probably ignore it. @@ -3690,22 +3330,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) pkts_acked = prior_packets - tp->packets_out; - if (tp->frto_counter) - frto_cwnd = tcp_process_frto(sk, flag); - /* Guarantee sacktag reordering detection against wrap-arounds */ - if (before(tp->frto_highmark, tp->snd_una)) - tp->frto_highmark = 0; - if (tcp_ack_is_dubious(sk, flag)) { /* Advance CWND, if state allows this. */ - if ((flag & FLAG_DATA_ACKED) && !frto_cwnd && - tcp_may_raise_cwnd(sk, flag)) + if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, is_dupack, flag); } else { - if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) + if (flag & FLAG_DATA_ACKED) tcp_cong_avoid(sk, ack, prior_in_flight); } -- cgit v1.2.3 From ab42d9ee3d215ab74a49818ffc53771a88ce7ddf Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 20 Mar 2013 13:32:59 +0000 Subject: tcp: refactor CA_Loss state processing Consolidate all of TCP CA_Loss state processing in tcp_fastretrans_alert() into a new function called tcp_process_loss(). This is to prepare the new F-RTO implementation in the next patch. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 42 ++++++++++++++++++++++++++---------------- 1 file changed, 26 insertions(+), 16 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 231c79fe91f3..8d821e45b917 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2664,6 +2664,30 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) 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) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + if (!before(tp->snd_una, tp->high_seq)) { + icsk->icsk_retransmits = 0; + tcp_try_undo_recovery(sk); + return; + } + + if (flag & FLAG_DATA_ACKED) + icsk->icsk_retransmits = 0; + if (tcp_is_reno(tp) && flag & FLAG_SND_UNA_ADVANCED) + tcp_reset_reno_sack(tp); + if (tcp_try_undo_loss(sk)) + return; + tcp_moderate_cwnd(tp); + tcp_xmit_retransmit_queue(sk); +} + /* 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 @@ -2710,12 +2734,6 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, tp->retrans_stamp = 0; } else if (!before(tp->snd_una, tp->high_seq)) { switch (icsk->icsk_ca_state) { - case TCP_CA_Loss: - icsk->icsk_retransmits = 0; - if (tcp_try_undo_recovery(sk)) - return; - break; - case TCP_CA_CWR: /* CWR is to be held something *above* high_seq * is ACKed for CWR bit to reach receiver. */ @@ -2746,18 +2764,10 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked; break; case TCP_CA_Loss: - if (flag & FLAG_DATA_ACKED) - icsk->icsk_retransmits = 0; - if (tcp_is_reno(tp) && flag & FLAG_SND_UNA_ADVANCED) - tcp_reset_reno_sack(tp); - if (!tcp_try_undo_loss(sk)) { - tcp_moderate_cwnd(tp); - tcp_xmit_retransmit_queue(sk); - return; - } + tcp_process_loss(sk, flag); if (icsk->icsk_ca_state != TCP_CA_Open) return; - /* Loss is undone; fall through to processing in Open state. */ + /* Fall through to processing in Open state. */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) -- cgit v1.2.3 From e33099f96d99c391b3325caa9c44258de04aae86 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 20 Mar 2013 13:33:00 +0000 Subject: tcp: implement RFC5682 F-RTO This patch implements F-RTO (foward RTO recovery): When the first retransmission after timeout is acknowledged, F-RTO sends new data instead of old data. If the next ACK acknowledges some never-retransmitted data, then the timeout was spurious and the congestion state is reverted. Otherwise if the next ACK selectively acknowledges the new data, then the timeout was genuine and the loss recovery continues. This idea applies to recurring timeouts as well. While F-RTO sends different data during timeout recovery, it does not (and should not) change the congestion control. The implementaion follows the three steps of SACK enhanced algorithm (section 3) in RFC5682. Step 1 is in tcp_enter_loss(). Step 2 and 3 are in tcp_process_loss(). The basic version is not supported because SACK enhanced version also works for non-SACK connections. The new implementation is functionally in parity with the old F-RTO implementation except the one case where it increases undo events: In addition to the RFC algorithm, a spurious timeout may be detected without sending data in step 2, as long as the SACK confirms not all the original data are dropped. When this happens, the sender will undo the cwnd and perhaps enter fast recovery instead. This additional check increases the F-RTO undo events by 5x compared to the prior implementation on Google Web servers, since the sender often does not have new data to send for HTTP. Note F-RTO may detect spurious timeout before Eifel with timestamps does so. Signed-off-by: Yuchung Cheng Acked-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 73 ++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 60 insertions(+), 13 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8d821e45b917..b2b36196b342 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -107,6 +107,7 @@ int sysctl_tcp_early_retrans __read_mostly = 3; #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ #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 */ @@ -1155,6 +1156,8 @@ static u8 tcp_sacktag_one(struct sock *sk, 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 (sacked & TCPCB_LOST) { @@ -1835,10 +1838,13 @@ void tcp_enter_loss(struct sock *sk, int how) const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; + bool new_recovery = false; /* Reduce ssthresh if it has not yet been made inside this window. */ - if (icsk->icsk_ca_state <= TCP_CA_Disorder || tp->snd_una == tp->high_seq || + 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)) { + new_recovery = true; tp->prior_ssthresh = tcp_current_ssthresh(sk); tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); tcp_ca_event(sk, CA_EVENT_LOSS); @@ -1883,6 +1889,14 @@ void tcp_enter_loss(struct sock *sk, int how) 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 @@ -2426,12 +2440,12 @@ static int tcp_try_undo_partial(struct sock *sk, int acked) return failed; } -/* Undo during loss recovery after partial ACK. */ -static bool tcp_try_undo_loss(struct sock *sk) +/* 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 (tcp_may_undo(tp)) { + if (frto_undo || tcp_may_undo(tp)) { struct sk_buff *skb; tcp_for_write_queue(skb, sk) { if (skb == tcp_send_head(sk)) @@ -2445,9 +2459,12 @@ static bool tcp_try_undo_loss(struct sock *sk) tp->lost_out = 0; tcp_undo_cwr(sk, true); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO); + if (frto_undo) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPSPURIOUSRTOS); inet_csk(sk)->icsk_retransmits = 0; tp->undo_marker = 0; - if (tcp_is_sack(tp)) + if (frto_undo || tcp_is_sack(tp)) tcp_set_ca_state(sk, TCP_CA_Open); return true; } @@ -2667,24 +2684,52 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) /* 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) +static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + bool recovered = !before(tp->snd_una, tp->high_seq); - if (!before(tp->snd_una, tp->high_seq)) { + if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ + if (flag & FLAG_ORIG_SACK_ACKED) { + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + tcp_try_undo_loss(sk, true); + return; + } + if (after(tp->snd_nxt, tp->high_seq) && + (flag & FLAG_DATA_SACKED || is_dupack)) { + tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ + } else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) { + tp->high_seq = tp->snd_nxt; + __tcp_push_pending_frames(sk, tcp_current_mss(sk), + TCP_NAGLE_OFF); + if (after(tp->snd_nxt, tp->high_seq)) + return; /* Step 2.b */ + tp->frto = 0; + } + } + + if (recovered) { + /* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */ icsk->icsk_retransmits = 0; tcp_try_undo_recovery(sk); return; } - if (flag & FLAG_DATA_ACKED) icsk->icsk_retransmits = 0; - if (tcp_is_reno(tp) && flag & FLAG_SND_UNA_ADVANCED) - tcp_reset_reno_sack(tp); - if (tcp_try_undo_loss(sk)) + 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); + } + if (tcp_try_undo_loss(sk, false)) return; - tcp_moderate_cwnd(tp); tcp_xmit_retransmit_queue(sk); } @@ -2764,7 +2809,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked; break; case TCP_CA_Loss: - tcp_process_loss(sk, flag); + tcp_process_loss(sk, flag, is_dupack); if (icsk->icsk_ca_state != TCP_CA_Open) return; /* Fall through to processing in Open state. */ @@ -3003,6 +3048,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, } if (!(sacked & TCPCB_SACKED_ACKED)) reord = min(pkts_acked, reord); + if (!after(scb->end_seq, tp->high_seq)) + flag |= FLAG_ORIG_SACK_ACKED; } if (sacked & TCPCB_SACKED_ACKED) -- cgit v1.2.3 From 6a5dc9e598fe90160fee7de098fa319665f5253e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 29 Apr 2013 08:39:56 +0000 Subject: net: Add MIB counters for checksum errors Add MIB counters for checksum errors in IP layer, and TCP/UDP/ICMP layers, to help diagnose problems. $ nstat -a | grep Csum IcmpInCsumErrors 72 0.0 TcpInCsumErrors 382 0.0 UdpInCsumErrors 463221 0.0 Icmp6InCsumErrors 75 0.0 Udp6InCsumErrors 173442 0.0 IpExtInCsumErrors 10884 0.0 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index aafd052865ba..08bbe6096528 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5273,6 +5273,7 @@ step5: return 0; csum_error: + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS); discard: -- cgit v1.2.3