From e45a4957d4acf1d659838bff0c1405aac801249e Mon Sep 17 00:00:00 2001 From: CN_SZTL Date: Wed, 26 Feb 2020 19:27:42 +0800 Subject: [PATCH] kernel/4.19: fix bbr patch --- ...-based-on-ack-aggregation-estimation.patch | 344 ++++++++++++++++++ 1 file changed, 344 insertions(+) create mode 100644 target/linux/generic/pending-4.19/607-tcp_bbr-adapt-cwnd-based-on-ack-aggregation-estimation.patch diff --git a/target/linux/generic/pending-4.19/607-tcp_bbr-adapt-cwnd-based-on-ack-aggregation-estimation.patch b/target/linux/generic/pending-4.19/607-tcp_bbr-adapt-cwnd-based-on-ack-aggregation-estimation.patch new file mode 100644 index 0000000000..5dcd680780 --- /dev/null +++ b/target/linux/generic/pending-4.19/607-tcp_bbr-adapt-cwnd-based-on-ack-aggregation-estimation.patch @@ -0,0 +1,344 @@ +From 232aa8ec3ed979d4716891540c03a806ecab0c37 Mon Sep 17 00:00:00 2001 +From: Priyaranjan Jha +Date: Wed, 23 Jan 2019 12:04:53 -0800 +Subject: tcp_bbr: refactor bbr_target_cwnd() for general inflight provisioning + +Because bbr_target_cwnd() is really a general-purpose BBR helper for +computing some volume of inflight data as a function of the estimated +BDP, refactor it into following helper functions: +- bbr_bdp() +- bbr_quantization_budget() +- bbr_inflight() + +Signed-off-by: Priyaranjan Jha +Signed-off-by: Neal Cardwell +Signed-off-by: Yuchung Cheng +Signed-off-by: David S. Miller +--- +diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h +--- a/include/net/inet_connection_sock.h ++++ b/include/net/inet_connection_sock.h +@@ -138,4 +138,4 @@ + +- u64 icsk_ca_priv[88 / sizeof(u64)]; +-#define ICSK_CA_PRIV_SIZE (11 * sizeof(u64)) ++ u64 icsk_ca_priv[104 / sizeof(u64)]; ++#define ICSK_CA_PRIV_SIZE (13 * sizeof(u64)) + }; + +diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c +--- a/net/ipv4/tcp_bbr.c ++++ b/net/ipv4/tcp_bbr.c +@@ -117,2 +117,10 @@ + u32 full_bw; /* recent bw, to estimate if pipe is full */ ++ ++ /* For tracking ACK aggregation: */ ++ u64 ack_epoch_mstamp; /* start of ACK sampling epoch */ ++ u16 extra_acked[2]; /* max excess data ACKed in epoch */ ++ u32 ack_epoch_acked:20, /* packets (S)ACKed in sampling epoch */ ++ extra_acked_win_rtts:5, /* age of extra_acked, in round trips */ ++ extra_acked_win_idx:1, /* current index in extra_acked array */ ++ unused_c:6; + }; +@@ -176,2 +184,11 @@ + ++/* Gain factor for adding extra_acked to target cwnd: */ ++static const int bbr_extra_acked_gain = BBR_UNIT; ++/* Window length of extra_acked window. */ ++static const u32 bbr_extra_acked_win_rtts = 5; ++/* Max allowed val for ack_epoch_acked, after which sampling epoch is reset */ ++static const u32 bbr_ack_epoch_acked_reset_thresh = 1U << 20; ++/* Time period for clamping cwnd increment due to ack aggregation */ ++static const u32 bbr_extra_acked_max_us = 100 * 1000; ++ + static void bbr_check_probe_rtt_done(struct sock *sk); +@@ -202,2 +219,12 @@ + ++/* Return maximum extra acked in past k-2k round trips, ++ * where k = bbr_extra_acked_win_rtts. ++ */ ++static u16 bbr_extra_acked(const struct sock *sk) ++{ ++ struct bbr *bbr = inet_csk_ca(sk); ++ ++ return max(bbr->extra_acked[0], bbr->extra_acked[1]); ++} ++ + /* Return rate in bytes per second, optionally with a gain. +@@ -206,2 +233,6 @@ + */ ++static bool tcp_needs_internal_pacing(const struct sock *sk) ++{ ++ return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; ++} + static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) +@@ -307,2 +338,4 @@ + bbr->idle_restart = 1; ++ bbr->ack_epoch_mstamp = tp->tcp_mstamp; ++ bbr->ack_epoch_acked = 0; + /* Avoid pointless buffer overflows: pace at est. bw if we don't +@@ -317,6 +350,5 @@ + +-/* Find target cwnd. Right-size the cwnd based on min RTT and the +- * estimated bottleneck bandwidth: ++/* Calculate bdp based on min RTT and the estimated bottleneck bandwidth: + * +- * cwnd = bw * min_rtt * gain = BDP * gain ++ * bdp = bw * min_rtt * gain + * +@@ -326,17 +358,7 @@ + * noise may cause BBR to under-estimate the rate. +- * +- * To achieve full performance in high-speed paths, we budget enough cwnd to +- * fit full-sized skbs in-flight on both end hosts to fully utilize the path: +- * - one skb in sending host Qdisc, +- * - one skb in sending host TSO/GSO engine +- * - one skb being received by receiver host LRO/GRO/delayed-ACK engine +- * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because +- * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets, +- * which allows 2 outstanding 2-packet sequences, to try to keep pipe +- * full even with ACK-every-other-packet delayed ACKs. + */ +-static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) ++static u32 bbr_bdp(struct sock *sk, u32 bw, int gain) + { + struct bbr *bbr = inet_csk_ca(sk); +- u32 cwnd; ++ u32 bdp; + u64 w; +@@ -355,3 +377,20 @@ + /* Apply a gain to the given value, then remove the BW_SCALE shift. */ +- cwnd = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; ++ bdp = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; ++ ++ return bdp; ++} ++ ++/* To achieve full performance in high-speed paths, we budget enough cwnd to ++ * fit full-sized skbs in-flight on both end hosts to fully utilize the path: ++ * - one skb in sending host Qdisc, ++ * - one skb in sending host TSO/GSO engine ++ * - one skb being received by receiver host LRO/GRO/delayed-ACK engine ++ * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because ++ * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets, ++ * which allows 2 outstanding 2-packet sequences, to try to keep pipe ++ * full even with ACK-every-other-packet delayed ACKs. ++ */ ++static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd) ++{ ++ struct bbr *bbr = inet_csk_ca(sk); + +@@ -364,3 +403,3 @@ + /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ +- if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT) ++ if (bbr->mode == BBR_PROBE_BW && bbr->cycle_idx == 0) + cwnd += 2; +@@ -370,2 +409,29 @@ + ++/* Find inflight based on min RTT and the estimated bottleneck bandwidth. */ ++static u32 bbr_inflight(struct sock *sk, u32 bw, int gain) ++{ ++ u32 inflight; ++ ++ inflight = bbr_bdp(sk, bw, gain); ++ inflight = bbr_quantization_budget(sk, inflight); ++ ++ return inflight; ++} ++ ++/* Find the cwnd increment based on estimate of ack aggregation */ ++static u32 bbr_ack_aggregation_cwnd(struct sock *sk) ++{ ++ u32 max_aggr_cwnd, aggr_cwnd = 0; ++ ++ if (bbr_extra_acked_gain && bbr_full_bw_reached(sk)) { ++ max_aggr_cwnd = ((u64)bbr_bw(sk) * bbr_extra_acked_max_us) ++ / BW_UNIT; ++ aggr_cwnd = (bbr_extra_acked_gain * bbr_extra_acked(sk)) ++ >> BBR_SCALE; ++ aggr_cwnd = min(aggr_cwnd, max_aggr_cwnd); ++ } ++ ++ return aggr_cwnd; ++} ++ + /* An optimization in BBR to reduce losses: On the first round of recovery, we +@@ -430,4 +496,11 @@ + ++ target_cwnd = bbr_bdp(sk, bw, gain); ++ ++ /* Increment the cwnd to account for excess ACKed data that seems ++ * due to aggregation (of data and/or ACKs) visible in the ACK stream. ++ */ ++ target_cwnd += bbr_ack_aggregation_cwnd(sk); ++ target_cwnd = bbr_quantization_budget(sk, target_cwnd); ++ + /* If we're below target cwnd, slow start cwnd toward target cwnd. */ +- target_cwnd = bbr_target_cwnd(sk, bw, gain); + if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ +@@ -472,3 +545,3 @@ + (rs->losses || /* perhaps pacing_gain*BDP won't fit */ +- inflight >= bbr_target_cwnd(sk, bw, bbr->pacing_gain)); ++ inflight >= bbr_inflight(sk, bw, bbr->pacing_gain)); + +@@ -479,3 +552,3 @@ + return is_full_length || +- inflight <= bbr_target_cwnd(sk, bw, BBR_UNIT); ++ inflight <= bbr_inflight(sk, bw, BBR_UNIT); + } +@@ -489,4 +562,2 @@ + bbr->cycle_mstamp = tp->delivered_mstamp; +- bbr->pacing_gain = bbr->lt_use_bw ? BBR_UNIT : +- bbr_pacing_gain[bbr->cycle_idx]; + } +@@ -508,4 +579,2 @@ + bbr->mode = BBR_STARTUP; +- bbr->pacing_gain = bbr_high_gain; +- bbr->cwnd_gain = bbr_high_gain; + } +@@ -517,4 +586,2 @@ + bbr->mode = BBR_PROBE_BW; +- bbr->pacing_gain = BBR_UNIT; +- bbr->cwnd_gain = bbr_cwnd_gain; + bbr->cycle_idx = CYCLE_LEN - 1 - prandom_u32_max(bbr_cycle_rand); +@@ -701,2 +768,63 @@ + ++/* Estimates the windowed max degree of ack aggregation. ++ * This is used to provision extra in-flight data to keep sending during ++ * inter-ACK silences. ++ * ++ * Degree of ack aggregation is estimated as extra data acked beyond expected. ++ * ++ * max_extra_acked = "maximum recent excess data ACKed beyond max_bw * interval" ++ * cwnd += max_extra_acked ++ * ++ * Max extra_acked is clamped by cwnd and bw * bbr_extra_acked_max_us (100 ms). ++ * Max filter is an approximate sliding window of 5-10 (packet timed) round ++ * trips. ++ */ ++static void bbr_update_ack_aggregation(struct sock *sk, ++ const struct rate_sample *rs) ++{ ++ u32 epoch_us, expected_acked, extra_acked; ++ struct bbr *bbr = inet_csk_ca(sk); ++ struct tcp_sock *tp = tcp_sk(sk); ++ ++ if (!bbr_extra_acked_gain || rs->acked_sacked <= 0 || ++ rs->delivered < 0 || rs->interval_us <= 0) ++ return; ++ ++ if (bbr->round_start) { ++ bbr->extra_acked_win_rtts = min(0x1F, ++ bbr->extra_acked_win_rtts + 1); ++ if (bbr->extra_acked_win_rtts >= bbr_extra_acked_win_rtts) { ++ bbr->extra_acked_win_rtts = 0; ++ bbr->extra_acked_win_idx = bbr->extra_acked_win_idx ? ++ 0 : 1; ++ bbr->extra_acked[bbr->extra_acked_win_idx] = 0; ++ } ++ } ++ ++ /* Compute how many packets we expected to be delivered over epoch. */ ++ epoch_us = tcp_stamp_us_delta(tp->delivered_mstamp, ++ bbr->ack_epoch_mstamp); ++ expected_acked = ((u64)bbr_bw(sk) * epoch_us) / BW_UNIT; ++ ++ /* Reset the aggregation epoch if ACK rate is below expected rate or ++ * significantly large no. of ack received since epoch (potentially ++ * quite old epoch). ++ */ ++ if (bbr->ack_epoch_acked <= expected_acked || ++ (bbr->ack_epoch_acked + rs->acked_sacked >= ++ bbr_ack_epoch_acked_reset_thresh)) { ++ bbr->ack_epoch_acked = 0; ++ bbr->ack_epoch_mstamp = tp->delivered_mstamp; ++ expected_acked = 0; ++ } ++ ++ /* Compute excess data delivered, beyond what was expected. */ ++ bbr->ack_epoch_acked = min_t(u32, 0xFFFFF, ++ bbr->ack_epoch_acked + rs->acked_sacked); ++ extra_acked = bbr->ack_epoch_acked - expected_acked; ++ extra_acked = min(extra_acked, tp->snd_cwnd); ++ if (extra_acked > bbr->extra_acked[bbr->extra_acked_win_idx]) ++ bbr->extra_acked[bbr->extra_acked_win_idx] = extra_acked; ++} ++ + /* Estimate when the pipe is full, using the change in delivery rate: BBR +@@ -735,6 +863,4 @@ + bbr->mode = BBR_DRAIN; /* drain queue we created */ +- bbr->pacing_gain = bbr_drain_gain; /* pace slow to drain */ +- bbr->cwnd_gain = bbr_high_gain; /* maintain cwnd */ + tcp_sk(sk)->snd_ssthresh = +- bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT); ++ bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT); + } /* fall through to check if in-flight is already small: */ +@@ -742,3 +868,3 @@ + tcp_packets_in_flight(tcp_sk(sk)) <= +- bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT)) ++ bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT)) + bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ +@@ -798,4 +924,2 @@ + bbr->mode = BBR_PROBE_RTT; /* dip, drain queue */ +- bbr->pacing_gain = BBR_UNIT; +- bbr->cwnd_gain = BBR_UNIT; + bbr_save_cwnd(sk); /* note cwnd so we can restore it */ +@@ -827,2 +951,31 @@ + ++static void bbr_update_gains(struct sock *sk) ++{ ++ struct bbr *bbr = inet_csk_ca(sk); ++ ++ switch (bbr->mode) { ++ case BBR_STARTUP: ++ bbr->pacing_gain = bbr_high_gain; ++ bbr->cwnd_gain = bbr_high_gain; ++ break; ++ case BBR_DRAIN: ++ bbr->pacing_gain = bbr_drain_gain; /* slow, to drain */ ++ bbr->cwnd_gain = bbr_high_gain; /* keep cwnd */ ++ break; ++ case BBR_PROBE_BW: ++ bbr->pacing_gain = (bbr->lt_use_bw ? ++ BBR_UNIT : ++ bbr_pacing_gain[bbr->cycle_idx]); ++ bbr->cwnd_gain = bbr_cwnd_gain; ++ break; ++ case BBR_PROBE_RTT: ++ bbr->pacing_gain = BBR_UNIT; ++ bbr->cwnd_gain = BBR_UNIT; ++ break; ++ default: ++ WARN_ONCE(1, "BBR bad mode: %u\n", bbr->mode); ++ break; ++ } ++} ++ + static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) +@@ -830,2 +983,3 @@ + bbr_update_bw(sk, rs); ++ bbr_update_ack_aggregation(sk, rs); + bbr_update_cycle_phase(sk, rs); +@@ -834,2 +988,3 @@ + bbr_update_min_rtt(sk, rs); ++ bbr_update_gains(sk); + } +@@ -880,2 +1035,9 @@ + ++ bbr->ack_epoch_mstamp = tp->tcp_mstamp; ++ bbr->ack_epoch_acked = 0; ++ bbr->extra_acked_win_rtts = 0; ++ bbr->extra_acked_win_idx = 0; ++ bbr->extra_acked[0] = 0; ++ bbr->extra_acked[1] = 0; ++ + cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); + +diff --git a/include/net/tcp.h b/include/net/tcp.h +--- a/include/net/tcp.h ++++ b/include/net/tcp.h +@@ -1000,2 +1000,3 @@ + bool is_retrans; /* is sample from retransmission? */ ++ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ + }; +