--- zzzz-none-000/linux-3.10.107/net/ipv4/tcp_cubic.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/ipv4/tcp_cubic.c 2021-02-04 17:41:59.000000000 +0000 @@ -82,19 +82,18 @@ /* BIC TCP Parameters */ struct bictcp { u32 cnt; /* increase cwnd by 1 after ACKs */ - u32 last_max_cwnd; /* last maximum snd_cwnd */ + u32 last_max_cwnd; /* last maximum snd_cwnd */ u32 loss_cwnd; /* congestion window at last loss */ u32 last_cwnd; /* the last snd_cwnd */ u32 last_time; /* time when updated last_cwnd */ u32 bic_origin_point;/* origin point of bic function */ - u32 bic_K; /* time to origin point from the beginning of the current epoch */ + u32 bic_K; /* time to origin point + from the beginning of the current epoch */ u32 delay_min; /* min delay (msec << 3) */ u32 epoch_start; /* beginning of an epoch */ u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ -#define ACK_RATIO_SHIFT 4 -#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT) - u16 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ + u16 unused; u8 sample_cnt; /* number of samples to decide curr_rtt */ u8 found; /* the exit point is found? */ u32 round_start; /* beginning of each round */ @@ -113,7 +112,6 @@ ca->bic_K = 0; ca->delay_min = 0; ca->epoch_start = 0; - ca->delayed_ack = 2 << ACK_RATIO_SHIFT; ca->ack_cnt = 0; ca->tcp_cwnd = 0; ca->found = 0; @@ -153,6 +151,27 @@ tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } +static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) +{ + if (event == CA_EVENT_TX_START) { + struct bictcp *ca = inet_csk_ca(sk); + u32 now = tcp_time_stamp; + s32 delta; + + delta = now - tcp_sk(sk)->lsndtime; + + /* We were application limited (idle) for a while. + * Shift epoch_start to keep cwnd growth to cubic curve. + */ + if (ca->epoch_start && delta > 0) { + ca->epoch_start += delta; + if (after(ca->epoch_start, now)) + ca->epoch_start = now; + } + return; + } +} + /* calculate the cubic root of x using a table lookup followed by one * Newton-Raphson iteration. * Avg err ~= 0.195% @@ -204,23 +223,30 @@ /* * Compute congestion window to use. */ -static inline void bictcp_update(struct bictcp *ca, u32 cwnd) +static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) { u32 delta, bic_target, max_cnt; u64 offs, t; - ca->ack_cnt++; /* count the number of ACKs */ + ca->ack_cnt += acked; /* count the number of ACKed packets */ if (ca->last_cwnd == cwnd && (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32) return; + /* The CUBIC function can update ca->cnt at most once per jiffy. + * On all cwnd reduction events, ca->epoch_start is set to 0, + * which will force a recalculation of ca->cnt. + */ + if (ca->epoch_start && tcp_time_stamp == ca->last_time) + goto tcp_friendliness; + ca->last_cwnd = cwnd; ca->last_time = tcp_time_stamp; if (ca->epoch_start == 0) { - ca->epoch_start = tcp_time_stamp; /* record the beginning of an epoch */ - ca->ack_cnt = 1; /* start counting */ + ca->epoch_start = tcp_time_stamp; /* record beginning */ + ca->ack_cnt = acked; /* start counting */ ca->tcp_cwnd = cwnd; /* syn with cubic */ if (ca->last_max_cwnd <= cwnd) { @@ -263,9 +289,9 @@ /* c/rtt * (t-K)^3 */ delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ); - if (t < ca->bic_K) /* below origin*/ + if (t < ca->bic_K) /* below origin*/ bic_target = ca->bic_origin_point - delta; - else /* above origin*/ + else /* above origin*/ bic_target = ca->bic_origin_point + delta; /* cubic function - calc bictcp_cnt*/ @@ -282,16 +308,18 @@ if (ca->last_max_cwnd == 0 && ca->cnt > 20) ca->cnt = 20; /* increase cwnd 5% per RTT */ +tcp_friendliness: /* TCP Friendly */ if (tcp_friendliness) { u32 scale = beta_scale; + delta = (cwnd * scale) >> 3; while (ca->ack_cnt > delta) { /* update tcp cwnd */ ca->ack_cnt -= delta; ca->tcp_cwnd++; } - if (ca->tcp_cwnd > cwnd){ /* if bic is slower than tcp */ + if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */ delta = ca->tcp_cwnd - cwnd; max_cnt = cwnd / delta; if (ca->cnt > max_cnt) @@ -299,28 +327,29 @@ } } - ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack; - if (ca->cnt == 0) /* cannot be zero */ - ca->cnt = 1; + /* The maximum rate of cwnd increase CUBIC allows is 1 packet per + * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT. + */ + ca->cnt = max(ca->cnt, 2U); } -static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) +static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - if (!tcp_is_cwnd_limited(sk, in_flight)) + if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { if (hystart && after(ack, ca->end_seq)) bictcp_hystart_reset(sk); - tcp_slow_start(tp); - } else { - bictcp_update(ca, tp->snd_cwnd); - tcp_cong_avoid_ai(tp, ca->cnt); + acked = tcp_slow_start(tp, acked); + if (!acked) + return; } - + bictcp_update(ca, tp->snd_cwnd, acked); + tcp_cong_avoid_ai(tp, ca->cnt, acked); } static u32 bictcp_recalc_ssthresh(struct sock *sk) @@ -362,16 +391,28 @@ struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - if (!(ca->found & hystart_detect)) { + if (ca->found & hystart_detect) + return; + + if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock(); /* first detection parameter - ack-train detection */ if ((s32)(now - ca->last_ack) <= hystart_ack_delta) { ca->last_ack = now; - if ((s32)(now - ca->round_start) > ca->delay_min >> 4) + if ((s32)(now - ca->round_start) > ca->delay_min >> 4) { ca->found |= HYSTART_ACK_TRAIN; + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPHYSTARTTRAINDETECT); + NET_ADD_STATS_BH(sock_net(sk), + LINUX_MIB_TCPHYSTARTTRAINCWND, + tp->snd_cwnd); + tp->snd_ssthresh = tp->snd_cwnd; + } } + } + if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { if (ca->curr_rtt == 0 || ca->curr_rtt > delay) @@ -380,15 +421,16 @@ ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + - HYSTART_DELAY_THRESH(ca->delay_min>>4)) + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { ca->found |= HYSTART_DELAY; + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPHYSTARTDELAYDETECT); + NET_ADD_STATS_BH(sock_net(sk), + LINUX_MIB_TCPHYSTARTDELAYCWND, + tp->snd_cwnd); + tp->snd_ssthresh = tp->snd_cwnd; + } } - /* - * Either one of two conditions are met, - * we exit from slow start immediately. - */ - if (ca->found & hystart_detect) - tp->snd_ssthresh = tp->snd_cwnd; } } @@ -397,20 +439,10 @@ */ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) { - const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); u32 delay; - if (icsk->icsk_ca_state == TCP_CA_Open) { - u32 ratio = ca->delayed_ack; - - ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT; - ratio += cnt; - - ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT); - } - /* Some calls are for duplicates without timetamps */ if (rtt_us < 0) return; @@ -428,7 +460,7 @@ ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ - if (hystart && tp->snd_cwnd <= tp->snd_ssthresh && + if (hystart && tcp_in_slow_start(tp) && tp->snd_cwnd >= hystart_low_window) hystart_update(sk, delay); } @@ -439,6 +471,7 @@ .cong_avoid = bictcp_cong_avoid, .set_state = bictcp_state, .undo_cwnd = bictcp_undo_cwnd, + .cwnd_event = bictcp_cwnd_event, .pkts_acked = bictcp_acked, .owner = THIS_MODULE, .name = "cubic", @@ -452,7 +485,8 @@ * based on SRTT of 100ms */ - beta_scale = 8*(BICTCP_BETA_SCALE+beta)/ 3 / (BICTCP_BETA_SCALE - beta); + beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3 + / (BICTCP_BETA_SCALE - beta); cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */ @@ -475,10 +509,6 @@ /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - /* hystart needs ms clock resolution */ - if (hystart && HZ < 1000) - cubictcp.flags |= TCP_CONG_RTT_STAMP; - return tcp_register_congestion_control(&cubictcp); }