diff options
author | Martin KaFai Lau <kafai@fb.com> | 2020-01-08 16:35:17 -0800 |
---|---|---|
committer | Alexei Starovoitov <ast@kernel.org> | 2020-01-09 08:46:18 -0800 |
commit | 09903869f69f37fd7a465183545b5739c6274654 (patch) | |
tree | c07bf1d77af64ba689ace342512ccbbc0c2d6a00 /tools/testing/selftests/bpf/progs | |
parent | bpf: libbpf: Add STRUCT_OPS support (diff) | |
download | linux-dev-09903869f69f37fd7a465183545b5739c6274654.tar.xz linux-dev-09903869f69f37fd7a465183545b5739c6274654.zip |
bpf: Add bpf_dctcp example
This patch adds a bpf_dctcp example. It currently does not do
no-ECN fallback but the same could be done through the cgrp2-bpf.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200109003517.3856825-1-kafai@fb.com
Diffstat (limited to 'tools/testing/selftests/bpf/progs')
-rw-r--r-- | tools/testing/selftests/bpf/progs/bpf_dctcp.c | 210 |
1 files changed, 210 insertions, 0 deletions
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c new file mode 100644 index 000000000000..5f9b613663e5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +/* WARNING: This implemenation is not necessarily the same + * as the tcp_dctcp.c. The purpose is mainly for testing + * the kernel BPF logic. + */ + +#include <linux/bpf.h> +#include <linux/types.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +#define DCTCP_MAX_ALPHA 1024U + +struct dctcp { + __u32 old_delivered; + __u32 old_delivered_ce; + __u32 prior_rcv_nxt; + __u32 dctcp_alpha; + __u32 next_seq; + __u32 ce_state; + __u32 loss_cwnd; +}; + +static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */ +static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA; + +static __always_inline void dctcp_reset(const struct tcp_sock *tp, + struct dctcp *ca) +{ + ca->next_seq = tp->snd_nxt; + + ca->old_delivered = tp->delivered; + ca->old_delivered_ce = tp->delivered_ce; +} + +BPF_TCP_OPS_1(dctcp_init, void, struct sock *, sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct dctcp *ca = inet_csk_ca(sk); + + ca->prior_rcv_nxt = tp->rcv_nxt; + ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); + ca->loss_cwnd = 0; + ca->ce_state = 0; + + dctcp_reset(tp, ca); +} + +BPF_TCP_OPS_1(dctcp_ssthresh, __u32, struct sock *, sk) +{ + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + ca->loss_cwnd = tp->snd_cwnd; + return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U); +} + +BPF_TCP_OPS_2(dctcp_update_alpha, void, + struct sock *, sk, __u32, flags) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct dctcp *ca = inet_csk_ca(sk); + + /* Expired RTT */ + if (!before(tp->snd_una, ca->next_seq)) { + __u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce; + __u32 alpha = ca->dctcp_alpha; + + /* alpha = (1 - g) * alpha + g * F */ + + alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); + if (delivered_ce) { + __u32 delivered = tp->delivered - ca->old_delivered; + + /* If dctcp_shift_g == 1, a 32bit value would overflow + * after 8 M packets. + */ + delivered_ce <<= (10 - dctcp_shift_g); + delivered_ce /= max(1U, delivered); + + alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA); + } + ca->dctcp_alpha = alpha; + dctcp_reset(tp, ca); + } +} + +static __always_inline void dctcp_react_to_loss(struct sock *sk) +{ + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + ca->loss_cwnd = tp->snd_cwnd; + tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); +} + +BPF_TCP_OPS_2(dctcp_state, void, struct sock *, sk, __u8, new_state) +{ + if (new_state == TCP_CA_Recovery && + new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state)) + dctcp_react_to_loss(sk); + /* We handle RTO in dctcp_cwnd_event to ensure that we perform only + * one loss-adjustment per RTT. + */ +} + +static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (ce_state == 1) + tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + else + tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; +} + +/* Minimal DCTP CE state machine: + * + * S: 0 <- last pkt was non-CE + * 1 <- last pkt was CE + */ +static __always_inline +void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt, + __u32 *prior_rcv_nxt, __u32 *ce_state) +{ + __u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0; + + if (*ce_state != new_ce_state) { + /* CE state has changed, force an immediate ACK to + * reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { + dctcp_ece_ack_cwr(sk, *ce_state); + bpf_tcp_send_ack(sk, *prior_rcv_nxt); + } + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + } + *prior_rcv_nxt = tcp_sk(sk)->rcv_nxt; + *ce_state = new_ce_state; + dctcp_ece_ack_cwr(sk, new_ce_state); +} + +BPF_TCP_OPS_2(dctcp_cwnd_event, void, + struct sock *, sk, enum tcp_ca_event, ev) +{ + struct dctcp *ca = inet_csk_ca(sk); + + switch (ev) { + case CA_EVENT_ECN_IS_CE: + case CA_EVENT_ECN_NO_CE: + dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); + break; + case CA_EVENT_LOSS: + dctcp_react_to_loss(sk); + break; + default: + /* Don't care for the rest. */ + break; + } +} + +BPF_TCP_OPS_1(dctcp_cwnd_undo, __u32, struct sock *, sk) +{ + const struct dctcp *ca = inet_csk_ca(sk); + + return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); +} + +BPF_TCP_OPS_3(tcp_reno_cong_avoid, void, + struct sock *, sk, __u32, ack, __u32, acked) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!tcp_is_cwnd_limited(sk)) + return; + + /* In "safe" area, increase. */ + if (tcp_in_slow_start(tp)) { + acked = tcp_slow_start(tp, acked); + if (!acked) + return; + } + /* In dangerous area, increase slowly. */ + tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked); +} + +SEC(".struct_ops") +struct tcp_congestion_ops dctcp_nouse = { + .init = (void *)dctcp_init, + .set_state = (void *)dctcp_state, + .flags = TCP_CONG_NEEDS_ECN, + .name = "bpf_dctcp_nouse", +}; + +SEC(".struct_ops") +struct tcp_congestion_ops dctcp = { + .init = (void *)dctcp_init, + .in_ack_event = (void *)dctcp_update_alpha, + .cwnd_event = (void *)dctcp_cwnd_event, + .ssthresh = (void *)dctcp_ssthresh, + .cong_avoid = (void *)tcp_reno_cong_avoid, + .undo_cwnd = (void *)dctcp_cwnd_undo, + .set_state = (void *)dctcp_state, + .flags = TCP_CONG_NEEDS_ECN, + .name = "bpf_dctcp", +}; |