From ac93bf86dc2cf0c5c8b32878084cdcbf6b49b7b1 Mon Sep 17 00:00:00 2001 From: Lukas Prause Date: Wed, 29 Oct 2025 12:03:06 +0100 Subject: [PATCH] Initial commit for TCP ROCCET source code. --- .gitignore | 1 + Makefile | 10 + README.md | 96 +++++++ roccet_kprobe.c | 66 +++++ tcp_roccet.c | 656 ++++++++++++++++++++++++++++++++++++++++++++ tcp_roccet.h | 52 ++++ tcp_roccet_struct.h | 52 ++++ 7 files changed, 933 insertions(+) create mode 100644 Makefile create mode 100644 README.md create mode 100644 roccet_kprobe.c create mode 100644 tcp_roccet.c create mode 100644 tcp_roccet.h create mode 100644 tcp_roccet_struct.h diff --git a/.gitignore b/.gitignore index 0c56f15..b4bcbc0 100644 --- a/.gitignore +++ b/.gitignore @@ -4,3 +4,4 @@ *.order *.symvers *.ko +.clang-format diff --git a/Makefile b/Makefile new file mode 100644 index 0000000..dd75988 --- /dev/null +++ b/Makefile @@ -0,0 +1,10 @@ +# Makefile for building both modules for the local machine + +obj-m += tcp_roccet.o +obj-m += roccet_kprobe.o + +all: + make -C /lib/modules/$(shell uname -r)/build M=$(PWD) modules + +clean: + make -C /lib/modules/$(shell uname -r)/build M=$(PWD) clean diff --git a/README.md b/README.md new file mode 100644 index 0000000..2668015 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +# TCP ROCCET :rocket: (RTT Oriented CUBIC Congestion control ExTension) + +TCP ROCCET is a new TCP congestion control +algorithm suited for current cellular 5G NR beyond networks. +It extends the kernel default congestion control CUBIC +and improves its performance, and additionally solves +unwanted side effects of CUBIC’s implementation. +ROCCET uses its own Slow Start, called LAUNCH, where loss +is not considered as a congestion event. +The congestion avoidance phase, called ORBITER, uses +CUBIC's window growth function and adds, based on RTT +and ACK rate, congestion events. + +NOTE: A paper for TCP ROCCET is currently under review. + +The oldest Linux kernel version we tested with ROCCET is 6.1. + +## Setup + +* Debian: `sudo apt install linux-headers-generic` +* Fedora: `sudo dnf install kernel-devel` +(`sudo reboot`) + +## Build +`make` + + +## Loading & Unloading the Module +**1.** Insert into Kernel: `sudo insmod tcp_roccet.ko` +In case you get the "Invalid module Format" error, it can help reinstalling the kernel-headers. + +**2.** Use the Algorithm: +* Either via globally loading it: `sudo sysctl net.ipv4.tcp_congestion_control=roccet` +* Or via using it in specific measurements: `sudo iperf3 -c -C roccet` + +**3.** Unload the Module: `sudo rmmod tcp_roccet` + + +## Debugging (Using kprobe) +In order to debug the `tcp_roccet` congestion control algorithm, there exists a Kprobe module (`roccet_kprobe.c`). Using this it is possible to inspect events generated by the algorithm. + +In order to use the Kprobe module the following steps are necessary: + +**1. Specify the event to inspect** +For this head into the `tcp_roccet.c` source code and find the function the Kprobe should attach to. + +For Example: +``` +__bpf_kfunc static void roccettcp_cong_avoid(struct sock *sk, u32 ack, u32 acked); +``` +Specify this function name in the field `symbol_name` of the `kprobe` struct in `roccet_kprobe.c` + +Obtain the arguments in the kprobe using the `regs` field. +(See the System V ABI for Linux under https://en.wikipedia.org/wiki/X86_calling_conventions#List_of_x86_calling_conventions) + +**2. Build Kprobe module** +Use the provided Makefile to build the `roccet_kprobe.c` module for the local machine. (`make`) + +For this the adequate linux-headers are required +* Debian: `sudo apt install linux-headers-generic` +* Fedora: `sudo dnf install kernel-devel` + +Required files for this are: +* `Makefile` +* `roccet_kprobe.c` +* `tcp_roccet.h` +* `tcp_roccet.c` (Optional; Need to remove corresponding entry in Makefile if missing) + +**3. Load Kprobe module** +To then load the Module use +`sudo insmod roccet_kprobe.ko` +If you are seeing the error "Unknown symbol in module" you need to first load the roccet algorithm. + +**4. See the trace output** +To see the trace output use +`sudo cat /sys/kernel/tracing/trace_pipe` + +**5. Unload Kprobe module** +To remove the module again use +`sudo rmmod roccet_kprobe` + +_See more info at_ https://docs.kernel.org/trace/kprobes.html and https://www.kernel.org/doc/Documentation/trace/kprobetrace.rst + +## Further Info +* On TCP-CC Ops: + * https://www.yonch.com/tech/linux-tcp-congestion-control-internals + * https://docs.ebpf.io/linux/program-type/BPF_PROG_TYPE_STRUCT_OPS/tcp_congestion_ops/ + +# Setup Development Environment +For specific Kernel: +1. Download linux source (the version you want to develop for) +2. Create Config via `make defconfig` +3. Compile kernel via `make` +4. Generate clangd Config via `python scripts/clang-tools/gen_compile_commands.py` +5. Copy `compile_commands.json` to development directory + diff --git a/roccet_kprobe.c b/roccet_kprobe.c new file mode 100644 index 0000000..0d10fb0 --- /dev/null +++ b/roccet_kprobe.c @@ -0,0 +1,66 @@ +#include "linux/kprobes.h" + +#include +#include + +/* Include the struct of the ROCCET congestion control algorithm. */ +#include "tcp_roccet.h" + +// Handler for the pre-call probe +static int handler_pre(struct kprobe *p, struct pt_regs *regs) +{ + /* System V ABI for x86_64 Linux: + * arg0: di, + * arg1: si, + * arg2: dx, + * ... + */ + + /* Get the first argument of the probed function */ + struct sock *sk = (struct sock *)regs->di; + struct roccettcp *ca = inet_csk_ca(sk); + + u32 ack = (u32)regs->si; + u32 acked = (u32)regs->dx; + + /* Use `trace_printk` to print debug information to the + * `/sys/kernel/tracing/trace buffer`. + * This buffer can be read using the debug trace interface of the kernel. + */ + trace_printk( + "roccettcp_cong_avoid: sk=%p ca=%p cnt=%u last_max_cwnd=%u, " + "last_congestion_event=%u\n", + sk, ca, ca->cnt, ca->last_max_cwnd, + ca->roccet_last_event_time_us); + trace_printk("ack: %u acked: %u\n", ack, acked); + + return 0; +} + +static struct kprobe kp = { + + /* Define which function to probe. */ + .symbol_name = "roccettcp_cong_avoid", + .pre_handler = handler_pre, /* Runs before the probed function. */ + .post_handler = NULL, /* Runs after the probed function. */ + +}; + +static int __init kprobe_init(void) +{ + return register_kprobe(&kp); +} +static void __exit kprobe_exit(void) +{ + unregister_kprobe(&kp); +} + +module_init(kprobe_init); +module_exit(kprobe_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Makes it possible to probe the ROCCET Congestion " + "Control Algrithm with kprobes. This enabled Debugging via a " + "loadable kernel module."); +MODULE_AUTHOR("Tim Füchsel"); +MODULE_VERSION("0.1"); diff --git a/tcp_roccet.c b/tcp_roccet.c new file mode 100644 index 0000000..e3d7966 --- /dev/null +++ b/tcp_roccet.c @@ -0,0 +1,656 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * TCP ROCCET: An RTT-Oriented CUBIC Congestion Control + * Extension for 5G and Beyond Networks + * + * TCP ROCCET is a new TCP congestion control + * algorithm suited for current cellular 5G NR beyond networks. + * It extends the kernel default congestion control CUBIC + * and improves its performance, and additionally solves an + * unwanted side effects of CUBIC’s implementation. + * ROCCET uses its own Slow Start, called LAUNCH, where loss + * is not considered as a congestion event. + * The congestion avoidance phase, called ORBITER, uses + * CUBIC's window growth function and adds, based on RTT + * and ACK rate, congestion events. + * + * NOTE: A paper for TCP ROCCET is currently under review. + * A draft of this paper can be found here: + * + * + * Further information about CUBIC: + * TCP CUBIC: Binary Increase Congestion control for TCP v2.3 + * Home page: + * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC + * This is from the implementation of CUBIC TCP in + * Sangtae Ha, Injong Rhee and Lisong Xu, + * "CUBIC: A New TCP-Friendly High-Speed TCP Variant" + * in ACM SIGOPS Operating System Review, July 2008. + * Available from: + * http://netsrv.csc.ncsu.edu/export/cubic_a_new_tcp_2008.pdf + * + * CUBIC integrates a new slow start algorithm, called HyStart. + * The details of HyStart are presented in + * Sangtae Ha and Injong Rhee, + * "Taming the Elephants: New TCP Slow Start", NCSU TechReport 2008. + * Available from: + * http://netsrv.csc.ncsu.edu/export/hystart_techreport_2008.pdf + * + * All testing results are available from: + * http://netsrv.csc.ncsu.edu/wiki/index.php/TCP_Testing + * + * Unless CUBIC is enabled and congestion window is large + * this behaves the same as the original Reno. + */ + +#include "tcp_roccet.h" +#include "linux/printk.h" +#include +#include +#include +#include +#include +#include + +/* Scale factor beta calculation (max_cwnd = snd_cwnd * beta) */ +#define BICTCP_BETA_SCALE 1024 + +#define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */ + +/* Alpha value for the sRrTT multiplied by 100. + * Here 20 represents a value of 0.2 + */ +#define ROCCET_ALPHA_TIMES_100 20 + +/* The amount of seconds ROCCET stores a minRTT. + * Enable "calculate_min_rtt" first. + */ +#define ROCCET_RTT_LOOKBACK_S 10 + +/* Parameters that are specific to the ROCCET-Algorithm */ +static int sr_rtt_upper_bound __read_mostly = 100; +static int ack_rate_diff_ss __read_mostly = 10; +static int ack_rate_diff_ca __read_mostly = 200; +static int calculate_min_rtt __read_mostly = 0; +static int ignore_loss __read_mostly = 0; +static int roccet_minRTT_interpolation_factor __read_mostly = 70; + +module_param(sr_rtt_upper_bound, int, 0644); +MODULE_PARM_DESC(sr_rtt_upper_bound, "ROCCET's upper bound for srRTT."); +module_param(ack_rate_diff_ss, int, 0644); +MODULE_PARM_DESC(ack_rate_diff_ss, + "ROCCET's threshold to exit slow start if ACK-rate defer by " + "given amount of segments."); +module_param(ack_rate_diff_ca, int, 0644); +MODULE_PARM_DESC(ack_rate_diff_ca, + "ROCCET's threshold for ack-rate and cum_cwnd, in percantage " + "of the current cwnd."); +module_param(calculate_min_rtt, int, 0644); +MODULE_PARM_DESC(calculate_min_rtt, + "Calculate min RTT if no lower RTT occurs after 10 sec."); +module_param(ignore_loss, int, 0644); +MODULE_PARM_DESC(ignore_loss, "Ignore loss as a congestion event."); +module_param(roccet_minRTT_interpolation_factor, int, 0644); +MODULE_PARM_DESC( + roccet_minRTT_interpolation_factor, + "ROCCET factor for interpolating the current RTT with the last minRTT " + "(minRTT = (factor * currRTT + (100-factor) * minRTT) / 100)"); + +static int fast_convergence __read_mostly = 1; +static int beta __read_mostly = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */ +static int initial_ssthresh __read_mostly; +static int bic_scale __read_mostly = 41; +static int tcp_friendliness __read_mostly = 1; + +static u32 cube_rtt_scale __read_mostly; +static u32 beta_scale __read_mostly; +static u64 cube_factor __read_mostly; + +/* Note parameters that are used for precomputing scale factors are read-only */ +module_param(fast_convergence, int, 0644); +MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence"); +module_param(beta, int, 0644); +MODULE_PARM_DESC(beta, "beta for multiplicative increase"); +module_param(initial_ssthresh, int, 0644); +MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold"); +module_param(bic_scale, int, 0444); +MODULE_PARM_DESC( + bic_scale, + "scale (scaled by 1024) value for bic function (bic_scale/1024)"); +module_param(tcp_friendliness, int, 0644); +MODULE_PARM_DESC(tcp_friendliness, "turn on/off tcp friendliness"); + +static inline void roccettcp_reset(struct roccettcp *ca) +{ + memset(ca, 0, offsetof(struct roccettcp, curr_rtt)); + ca->bw_limit.sum_cwnd = 1; + ca->bw_limit.sum_acked = 1; + ca->bw_limit.next_check = 0; + ca->curr_min_rtt_timed.rtt = ~0U; + ca->curr_min_rtt_timed.time = ~0U; + ca->last_rtt = 0; +} + +static inline void update_min_rtt(struct sock *sk) +{ + struct roccettcp *ca = inet_csk_ca(sk); + u32 now = jiffies_to_usecs(tcp_jiffies32); + + if (now - ca->curr_min_rtt_timed.time > + ROCCET_RTT_LOOKBACK_S * USEC_PER_SEC && + calculate_min_rtt) { + u32 new_min_rtt = max(ca->curr_rtt, 1); + u32 old_min_rtt = ca->curr_min_rtt_timed.rtt; + + u32 interpolated_min_rtt = + (new_min_rtt * roccet_minRTT_interpolation_factor + + old_min_rtt * + (100 - roccet_minRTT_interpolation_factor)) / + 100; + + ca->curr_min_rtt_timed.rtt = interpolated_min_rtt; + ca->curr_min_rtt_timed.time = now; + } + + /* Check if new lower min RTT was found. If so, set it directly */ + if (ca->curr_rtt < ca->curr_min_rtt_timed.rtt) { + ca->curr_min_rtt_timed.rtt = max(ca->curr_rtt, 1); + ca->curr_min_rtt_timed.time = now; + } +} + +/* Return difference between last and current ack rate. + */ +static inline int get_ack_rate_diff(struct roccettcp *ca) +{ + return ca->ack_rate.last_rate - ca->ack_rate.curr_rate; +} + +/* Update ack rate sampled by 100ms. + */ +static inline void update_ack_rate(struct sock *sk) +{ + struct roccettcp *ca = inet_csk_ca(sk); + u32 now = jiffies_to_usecs(tcp_jiffies32); + u32 interval = USEC_PER_MSEC * 100; + + if ((u32)(now - ca->ack_rate.last_rate_time) >= interval) { + ca->ack_rate.last_rate_time = now; + ca->ack_rate.last_rate = ca->ack_rate.curr_rate; + ca->ack_rate.curr_rate = ca->ack_rate.cnt; + ca->ack_rate.cnt = 0; + } else { + ca->ack_rate.cnt += 1; + } +} + +/* Compute srRTT. + */ +static inline void update_srrtt(struct sock *sk) +{ + struct roccettcp *ca = inet_csk_ca(sk); + + if (ca->curr_min_rtt_timed.rtt == 0) + return; + + /* Calculate the new rRTT (Scaled by 100). + * 100 * ((sRTT - sRTT_min) / sRTT_min) + */ + u32 rRTT = (100 * (ca->curr_rtt - ca->curr_min_rtt_timed.rtt)) / + ca->curr_min_rtt_timed.rtt; + + // (1 - alpha) * srRTT + alpha * rRTT + ca->curr_srRTT = ((100 - ROCCET_ALPHA_TIMES_100) * ca->curr_srRTT + + ROCCET_ALPHA_TIMES_100 * rRTT) / + 100; +} + +__bpf_kfunc static void roccettcp_init(struct sock *sk) +{ + struct roccettcp *ca = inet_csk_ca(sk); + + roccettcp_reset(ca); + + if (initial_ssthresh) + tcp_sk(sk)->snd_ssthresh = initial_ssthresh; + + /* Initial roccet paramters */ + ca->roccet_last_event_time_us = 0; + ca->curr_min_rtt = ~0U; + ca->ack_rate.last_rate = 0; + ca->ack_rate.last_rate_time = 0; + ca->ack_rate.curr_rate = 0; + ca->ack_rate.cnt = 0; +} + +__bpf_kfunc static void roccettcp_cwnd_event(struct sock *sk, + enum tcp_ca_event event) +{ + if (event == CA_EVENT_TX_START) { + struct roccettcp *ca = inet_csk_ca(sk); + u32 now = tcp_jiffies32; + 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% + */ +static u32 cubic_root(u64 a) +{ + u32 x, b, shift; + /* cbrt(x) MSB values for x MSB values in [0..63]. + * Precomputed then refined by hand - Willy Tarreau + * + * For x in [0..63], + * v = cbrt(x << 18) - 1 + * cbrt(x) = (v[x] + 10) >> 6 + */ + static const u8 v[] = { + /* 0x00 */ 0, 54, 54, 54, 118, 118, 118, 118, + /* 0x08 */ 123, 129, 134, 138, 143, 147, 151, 156, + /* 0x10 */ 157, 161, 164, 168, 170, 173, 176, 179, + /* 0x18 */ 181, 185, 187, 190, 192, 194, 197, 199, + /* 0x20 */ 200, 202, 204, 206, 209, 211, 213, 215, + /* 0x28 */ 217, 219, 221, 222, 224, 225, 227, 229, + /* 0x30 */ 231, 232, 234, 236, 237, 239, 240, 242, + /* 0x38 */ 244, 245, 246, 248, 250, 251, 252, 254, + }; + + b = fls64(a); + if (b < 7) { + /* a in [0..63] */ + return ((u32)v[(u32)a] + 35) >> 6; + } + + b = ((b * 84) >> 8) - 1; + shift = (a >> (b * 3)); + + x = ((u32)(((u32)v[shift] + 10) << b)) >> 6; + + /* Newton-Raphson iteration + * 2 + * x = ( 2 * x + a / x ) / 3 + * k+1 k k + */ + x = (2 * x + (u32)div64_u64(a, (u64)x * (u64)(x - 1))); + x = ((x * 341) >> 10); + return x; +} + +/* Compute congestion window to use. + */ +static inline void bictcp_update(struct roccettcp *ca, u32 cwnd, u32 acked) +{ + u32 delta, bic_target, max_cnt; + u64 offs, t; + + ca->ack_cnt += acked; /* count the number of ACKed packets */ + + if (ca->last_cwnd == cwnd && + (s32)(tcp_jiffies32 - 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_jiffies32 == ca->last_time) + goto tcp_friendliness; + + ca->last_cwnd = cwnd; + ca->last_time = tcp_jiffies32; + + if (ca->epoch_start == 0) { + ca->epoch_start = tcp_jiffies32; /* record beginning */ + ca->ack_cnt = acked; /* start counting */ + ca->tcp_cwnd = cwnd; /* syn with cubic */ + + if (ca->last_max_cwnd <= cwnd) { + ca->bic_K = 0; + ca->bic_origin_point = cwnd; + } else { + /* Compute new K based on + * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ) + */ + ca->bic_K = cubic_root(cube_factor * + (ca->last_max_cwnd - cwnd)); + ca->bic_origin_point = ca->last_max_cwnd; + } + } + + /* cubic function - calc */ + /* calculate c * time^3 / rtt, + * while considering overflow in calculation of time^3 + * (so time^3 is done by using 64 bit) + * and without the support of division of 64bit numbers + * (so all divisions are done by using 32 bit) + * also NOTE the unit of those veriables + * time = (t - K) / 2^bictcp_HZ + * c = bic_scale >> 10 + * rtt = (srtt >> 3) / HZ + * !!! The following code does not have overflow problems, + * if the cwnd < 1 million packets !!! + */ + + t = (s32)(tcp_jiffies32 - ca->epoch_start); + t += usecs_to_jiffies(ca->delay_min); + + /* change the unit from HZ to bictcp_HZ */ + t <<= BICTCP_HZ; + do_div(t, HZ); + + if (t < ca->bic_K) /* t - K */ + offs = ca->bic_K - t; + else + offs = t - ca->bic_K; + + /* c/rtt * (t-K)^3 */ + delta = (cube_rtt_scale * offs * offs * offs) >> (10 + 3 * BICTCP_HZ); + if (t < ca->bic_K) /* below origin*/ + bic_target = ca->bic_origin_point - delta; + else /* above origin*/ + bic_target = ca->bic_origin_point + delta; + + /* cubic function - calc bictcp_cnt*/ + if (bic_target > cwnd) { + ca->cnt = cwnd / (bic_target - cwnd); + } else { + ca->cnt = 100 * cwnd; /* very small increment*/ + } + + /* The initial growth of cubic function may be too conservative + * when the available bandwidth is still unknown. + */ + 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 */ + delta = ca->tcp_cwnd - cwnd; + max_cnt = cwnd / delta; + if (ca->cnt > max_cnt) + ca->cnt = max_cnt; + } + } + + /* 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); +} + +__bpf_kfunc static void roccettcp_cong_avoid(struct sock *sk, u32 ack, + u32 acked) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct roccettcp *ca = inet_csk_ca(sk); + + u32 now = jiffies_to_usecs(tcp_jiffies32); + u32 bw_limit_detect = 0; + u32 roccet_xj; + u32 jitter; + if (ca->last_rtt > ca->curr_rtt) { + jitter = ca->last_rtt - ca->curr_rtt; + } else { + jitter = ca->curr_rtt - ca->last_rtt; + } + + /* Update roccet paramters */ + update_ack_rate(sk); + update_min_rtt(sk); + update_srrtt(sk); + + /* ROCCET drain. + * Do not increase the cwnd for 100ms after a roccet congestion event + */ + if (now - ca->roccet_last_event_time_us <= 100 * USEC_PER_MSEC) + return; + + /* Lift off: Detect an exit point for tcp slow start + * in networks with large buffers of multiple BDP + * Like in cellular networks (5G, ...). + */ + if (tcp_in_slow_start(tp) && ca->curr_srRTT > sr_rtt_upper_bound && + get_ack_rate_diff(ca) >= ack_rate_diff_ss) { + ca->epoch_start = 0; + + /* Handle inital slow start. Here we observe the most problems */ + if (tp->snd_ssthresh == TCP_INFINITE_SSTHRESH) { + tcp_sk(sk)->snd_ssthresh = tcp_snd_cwnd(tp) / 2; + tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) / 2); + } else { + tcp_sk(sk)->snd_ssthresh = + tcp_snd_cwnd(tp) - (tcp_snd_cwnd(tp) / 3); + tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) - + (tcp_snd_cwnd(tp) / 3)); + } + ca->roccet_last_event_time_us = now; + return; + } + + if (tcp_in_slow_start(tp)) { + acked = tcp_slow_start(tp, acked); + if (!acked) + return; + } + + if (ca->bw_limit.next_check == 0) + ca->bw_limit.next_check = now + 5 * ca->curr_rtt; + + ca->bw_limit.sum_cwnd += tcp_snd_cwnd(tp); + ca->bw_limit.sum_acked += acked; + + if (ca->bw_limit.next_check < now) { + /* We send more data as we got acked in the last 5 RTTs */ + if ((ca->bw_limit.sum_cwnd * 100) / ca->bw_limit.sum_acked >= + ack_rate_diff_ca) + bw_limit_detect = 1; + + /* reset struct and set next end of period */ + ca->bw_limit.sum_cwnd = 1; + + /* set to 1 to avoid division by zero */ + ca->bw_limit.sum_acked = 1; + ca->bw_limit.next_check = now + 5 * ca->curr_rtt; + } + + /* Respects the jitter of the connection and add it on top of the upper bound + * for the srRTT + */ + roccet_xj = ((jitter * 100) / ca->curr_min_rtt_timed.rtt) + + sr_rtt_upper_bound; + if (roccet_xj < sr_rtt_upper_bound) + roccet_xj = sr_rtt_upper_bound; + + if (ca->curr_srRTT > roccet_xj && bw_limit_detect) { + ca->epoch_start = 0; + ca->roccet_last_event_time_us = now; + ca->cnt = 100 * tcp_snd_cwnd(tp); + + /* Set Wmax if cwnd is larger than the old Wmax */ + if (tcp_snd_cwnd(tp) > ca->last_max_cwnd) + ca->last_max_cwnd = tcp_snd_cwnd(tp); + + tcp_snd_cwnd_set(tp, min(tp->snd_cwnd_clamp, + max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U))); + tp->snd_ssthresh = tcp_snd_cwnd(tp); + return; + } + + /* Terminates this function if cwnd is not fully utilized. + * In mobile networks like 5G, this termination causes the cwnd to be frozen at + * an excessively high value. This is because slow start or HyStart massively + * exceed the available bandwidth and leave the cwnd at an excessively high + * value. The cwnd cannot therefore be fully utilized because it is limited by + * the connection capacity. + */ + if (!tcp_is_cwnd_limited(sk)) + return; + + bictcp_update(ca, tcp_snd_cwnd(tp), acked); + tcp_cong_avoid_ai(tp, max(1, ca->cnt), acked); +} + +__bpf_kfunc static u32 roccettcp_recalc_ssthresh(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct roccettcp *ca = inet_csk_ca(sk); + + if (ignore_loss) + return tcp_snd_cwnd(tp); + + /* Don't exit slow start if loss occurs. */ + if (tcp_in_slow_start(tp)) + return tcp_snd_cwnd(tp); + + ca->epoch_start = 0; /* end of epoch */ + + /* Wmax and fast convergence */ + if (tcp_snd_cwnd(tp) < ca->last_max_cwnd && fast_convergence) + ca->last_max_cwnd = + (tcp_snd_cwnd(tp) * (BICTCP_BETA_SCALE + beta)) / + (2 * BICTCP_BETA_SCALE); + else + ca->last_max_cwnd = tcp_snd_cwnd(tp); + + return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U); +} + +__bpf_kfunc static void roccettcp_state(struct sock *sk, u8 new_state) +{ + struct roccettcp *ca = inet_csk_ca(sk); + if (new_state == TCP_CA_Loss) + roccettcp_reset(ca); +} + +__bpf_kfunc static void roccettcp_acked(struct sock *sk, + const struct ack_sample *sample) +{ + struct roccettcp *ca = inet_csk_ca(sk); + + /* Some calls are for duplicates without timestamps */ + if (sample->rtt_us < 0) + return; + + /* Discard delay samples right after fast recovery */ + if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ) + return; + + u32 delay = sample->rtt_us; + if (delay == 0) + delay = 1; + + /* first time call or link delay decreases */ + if (ca->delay_min == 0 || ca->delay_min > delay) + ca->delay_min = delay; + + /* Get valid sample for roccet */ + if (sample->rtt_us > 0) { + ca->last_rtt = ca->curr_rtt; + ca->curr_rtt = sample->rtt_us; + } +} + +static struct tcp_congestion_ops roccet_tcp __read_mostly = { + .init = roccettcp_init, + .ssthresh = roccettcp_recalc_ssthresh, + .cong_avoid = roccettcp_cong_avoid, + .set_state = roccettcp_state, + .undo_cwnd = tcp_reno_undo_cwnd, + .cwnd_event = roccettcp_cwnd_event, + .pkts_acked = roccettcp_acked, + .owner = THIS_MODULE, + .name = "roccet", +}; + +BTF_KFUNCS_START(tcp_roccet_check_kfunc_ids) +BTF_ID_FLAGS(func, roccettcp_init) +BTF_ID_FLAGS(func, roccettcp_recalc_ssthresh) +BTF_ID_FLAGS(func, roccettcp_cong_avoid) +BTF_ID_FLAGS(func, roccettcp_state) +BTF_ID_FLAGS(func, roccettcp_cwnd_event) +BTF_ID_FLAGS(func, roccettcp_acked) +BTF_KFUNCS_END(tcp_roccet_check_kfunc_ids) + +static const struct btf_kfunc_id_set tcp_roccet_kfunc_set = { + .owner = THIS_MODULE, + .set = &tcp_roccet_check_kfunc_ids, +}; + +static int __init roccettcp_register(void) +{ + int ret; + + BUILD_BUG_ON(sizeof(struct roccettcp) > ICSK_CA_PRIV_SIZE); + + /* Precompute a bunch of the scaling factors that are used per-packet + * based on SRTT of 100ms + */ + + beta_scale = + 8 * (BICTCP_BETA_SCALE + beta) / 3 / (BICTCP_BETA_SCALE - beta); + + cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */ + + /* calculate the "K" for (wmax-cwnd) = c/rtt * K^3 + * so K = cubic_root( (wmax-cwnd)*rtt/c ) + * the unit of K is bictcp_HZ=2^10, not HZ + * + * c = bic_scale >> 10 + * rtt = 100ms + * + * the following code has been designed and tested for + * cwnd < 1 million packets + * RTT < 100 seconds + * HZ < 1,000,00 (corresponding to 10 nano-second) + */ + + /* 1/c * 2^2*bictcp_HZ * srtt */ + cube_factor = 1ull << (10 + 3 * BICTCP_HZ); /* 2^40 */ + + /* divide by bic_scale and by constant Srtt (100ms) */ + do_div(cube_factor, bic_scale * 10); + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &tcp_roccet_kfunc_set); + if (ret < 0) + return ret; + return tcp_register_congestion_control(&roccet_tcp); +} + +static void __exit roccettcp_unregister(void) +{ + tcp_unregister_congestion_control(&roccet_tcp); +} + +module_init(roccettcp_register); +module_exit(roccettcp_unregister); + +MODULE_AUTHOR("Lukas Prause, Tim Füchsel"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("ROCCET TCP"); +MODULE_VERSION("1.0"); diff --git a/tcp_roccet.h b/tcp_roccet.h new file mode 100644 index 0000000..dc1e03b --- /dev/null +++ b/tcp_roccet.h @@ -0,0 +1,52 @@ +/* + * TCP ROCCET congestion control interface + */ +#ifndef __TCP_ROCCET_H +#define __TCP_ROCCET_H 1 + +#include + +struct AckRate { + u16 last_rate; /* Last ACK-rate */ + u32 last_rate_time; /* Timestamp of the last ACK-rate */ + u16 curr_rate; /* Current ACK-rate */ + u16 cnt; /* Used for counting acks */ +}; + +struct BandwidthLimitDetect { + u32 sum_cwnd; /* sum of cwnd during time interval */ + u32 sum_acked; /* sum of received acks during time interval */ + u32 next_check; /* end/upper bound of time interval */ +}; + +struct TimedRTT { + u32 time; /* Time of recoding */ + u32 rtt; /* Measured RTT */ +}; + +/* Based on the BICTCP struct with additions specific for the ROCCET-Algorithm */ +struct roccettcp { + u32 cnt; /* increase cwnd by 1 after ACKs */ + u32 last_max_cwnd; /* last maximum snd_cwnd */ + 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 delay_min; /* min delay (usec) */ + u32 epoch_start; /* beginning of an epoch */ + u32 ack_cnt; /* number of acks */ + u32 tcp_cwnd; /* estimated tcp cwnd */ + u32 curr_rtt; /* the minimum rtt of current round */ + + u32 roccet_last_event_time_us; /* The last time ROCCETv2 was triggered */ + u32 curr_min_rtt; /* The current observed minRTT */ + struct TimedRTT curr_min_rtt_timed; /* The current observed minRTT with + the timestamp when it was observed */ + u32 curr_srRTT; /* The srRTT calculated based on the latest ACK */ + struct AckRate ack_rate; /* The last and the current ACK rate */ + struct BandwidthLimitDetect bw_limit; + u32 last_rtt; /* Used for jitter calculation */ +}; + +#endif /* __TCP_ROCCET_H */ \ No newline at end of file diff --git a/tcp_roccet_struct.h b/tcp_roccet_struct.h new file mode 100644 index 0000000..b860f57 --- /dev/null +++ b/tcp_roccet_struct.h @@ -0,0 +1,52 @@ +// Include Guard +#ifndef TCP_ROCCET_STRUCT +#define TCP_ROCCET_STRUCT + +#include + +struct AckRate { + u16 last_rate; + u32 last_rate_time; + u16 curr_rate; + u16 cnt; +}; + +struct BandwidthLimitDetect { + u32 sum_cwnd; /* sum of cwnd during time interval */ + u32 sum_acked; /* sum of received acks during time interval */ + u32 next_check; /* end/upper bound of time interval */ +}; + +struct TimedRTT { + u32 time; + u32 rtt; +}; + +/* BIC TCP Parameters */ +struct bictcp { + u32 cnt; /* increase cwnd by 1 after ACKs */ + u32 last_max_cwnd; /* last maximum snd_cwnd */ + 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 delay_min; /* min delay (usec) */ + u32 epoch_start; /* beginning of an epoch */ + u32 ack_cnt; /* number of acks */ + u32 tcp_cwnd; /* estimated tcp cwnd */ + + u32 curr_rtt; /* the minimum rtt of current round */ + + // ROCCETv2 specific + u32 roccet_last_event_time_us; /* The last time ROCCETv2 was triggered */ + u32 curr_min_rtt; /* The current observed minRTT */ + struct TimedRTT curr_min_rtt_timed; /* The current observed minRTT with the + timestamp when it was observed */ + u32 curr_srRTT; /* The srRTT calculated based on the latest ACK */ + struct AckRate ack_rate; /* The last and the current ACK rate */ + struct BandwidthLimitDetect bw_limit; + u32 last_rtt; /* Used for jitter calculation */ +}; + +#endif /* TCP_ROCCET_STRUCT */ \ No newline at end of file