1// SPDX-License-Identifier: GPL-2.0-only
2
3/* WARNING: This implemenation is not necessarily the same
4 * as the tcp_cubic.c.  The purpose is mainly for testing
5 * the kernel BPF logic.
6 *
7 * Highlights:
8 * 1. CONFIG_HZ .kconfig map is used.
9 * 2. In bictcp_update(), calculation is changed to use usec
10 *    resolution (i.e. USEC_PER_JIFFY) instead of using jiffies.
11 *    Thus, usecs_to_jiffies() is not used in the bpf_cubic.c.
12 * 3. In bitctcp_update() [under tcp_friendliness], the original
13 *    "while (ca->ack_cnt > delta)" loop is changed to the equivalent
14 *    "ca->ack_cnt / delta" operation.
15 */
16
17#include <linux/bpf.h>
18#include <linux/stddef.h>
19#include <linux/tcp.h>
20#include "bpf_tcp_helpers.h"
21
22char _license[] SEC("license") = "GPL";
23
24#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
25
26#define BICTCP_BETA_SCALE    1024	/* Scale factor beta calculation
27					 * max_cwnd = snd_cwnd * beta
28					 */
29#define	BICTCP_HZ		10	/* BIC HZ 2^10 = 1024 */
30
31/* Two methods of hybrid slow start */
32#define HYSTART_ACK_TRAIN	0x1
33#define HYSTART_DELAY		0x2
34
35/* Number of delay samples for detecting the increase of delay */
36#define HYSTART_MIN_SAMPLES	8
37#define HYSTART_DELAY_MIN	(4000U)	/* 4ms */
38#define HYSTART_DELAY_MAX	(16000U)	/* 16 ms */
39#define HYSTART_DELAY_THRESH(x)	clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX)
40
41static int fast_convergence = 1;
42static const int beta = 717;	/* = 717/1024 (BICTCP_BETA_SCALE) */
43static int initial_ssthresh;
44static const int bic_scale = 41;
45static int tcp_friendliness = 1;
46
47static int hystart = 1;
48static int hystart_detect = HYSTART_ACK_TRAIN | HYSTART_DELAY;
49static int hystart_low_window = 16;
50static int hystart_ack_delta_us = 2000;
51
52static const __u32 cube_rtt_scale = (bic_scale * 10);	/* 1024*c/rtt */
53static const __u32 beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3
54				/ (BICTCP_BETA_SCALE - beta);
55/* calculate the "K" for (wmax-cwnd) = c/rtt * K^3
56 *  so K = cubic_root( (wmax-cwnd)*rtt/c )
57 * the unit of K is bictcp_HZ=2^10, not HZ
58 *
59 *  c = bic_scale >> 10
60 *  rtt = 100ms
61 *
62 * the following code has been designed and tested for
63 * cwnd < 1 million packets
64 * RTT < 100 seconds
65 * HZ < 1,000,00  (corresponding to 10 nano-second)
66 */
67
68/* 1/c * 2^2*bictcp_HZ * srtt, 2^40 */
69static const __u64 cube_factor = (__u64)(1ull << (10+3*BICTCP_HZ))
70				/ (bic_scale * 10);
71
72/* BIC TCP Parameters */
73struct bictcp {
74	__u32	cnt;		/* increase cwnd by 1 after ACKs */
75	__u32	last_max_cwnd;	/* last maximum snd_cwnd */
76	__u32	last_cwnd;	/* the last snd_cwnd */
77	__u32	last_time;	/* time when updated last_cwnd */
78	__u32	bic_origin_point;/* origin point of bic function */
79	__u32	bic_K;		/* time to origin point
80				   from the beginning of the current epoch */
81	__u32	delay_min;	/* min delay (usec) */
82	__u32	epoch_start;	/* beginning of an epoch */
83	__u32	ack_cnt;	/* number of acks */
84	__u32	tcp_cwnd;	/* estimated tcp cwnd */
85	__u16	unused;
86	__u8	sample_cnt;	/* number of samples to decide curr_rtt */
87	__u8	found;		/* the exit point is found? */
88	__u32	round_start;	/* beginning of each round */
89	__u32	end_seq;	/* end_seq of the round */
90	__u32	last_ack;	/* last time when the ACK spacing is close */
91	__u32	curr_rtt;	/* the minimum rtt of current round */
92};
93
94static inline void bictcp_reset(struct bictcp *ca)
95{
96	ca->cnt = 0;
97	ca->last_max_cwnd = 0;
98	ca->last_cwnd = 0;
99	ca->last_time = 0;
100	ca->bic_origin_point = 0;
101	ca->bic_K = 0;
102	ca->delay_min = 0;
103	ca->epoch_start = 0;
104	ca->ack_cnt = 0;
105	ca->tcp_cwnd = 0;
106	ca->found = 0;
107}
108
109extern unsigned long CONFIG_HZ __kconfig;
110#define HZ CONFIG_HZ
111#define USEC_PER_MSEC	1000UL
112#define USEC_PER_SEC	1000000UL
113#define USEC_PER_JIFFY	(USEC_PER_SEC / HZ)
114
115static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor)
116{
117	return dividend / divisor;
118}
119
120#define div64_ul div64_u64
121
122#define BITS_PER_U64 (sizeof(__u64) * 8)
123static __always_inline int fls64(__u64 x)
124{
125	int num = BITS_PER_U64 - 1;
126
127	if (x == 0)
128		return 0;
129
130	if (!(x & (~0ull << (BITS_PER_U64-32)))) {
131		num -= 32;
132		x <<= 32;
133	}
134	if (!(x & (~0ull << (BITS_PER_U64-16)))) {
135		num -= 16;
136		x <<= 16;
137	}
138	if (!(x & (~0ull << (BITS_PER_U64-8)))) {
139		num -= 8;
140		x <<= 8;
141	}
142	if (!(x & (~0ull << (BITS_PER_U64-4)))) {
143		num -= 4;
144		x <<= 4;
145	}
146	if (!(x & (~0ull << (BITS_PER_U64-2)))) {
147		num -= 2;
148		x <<= 2;
149	}
150	if (!(x & (~0ull << (BITS_PER_U64-1))))
151		num -= 1;
152
153	return num + 1;
154}
155
156static __always_inline __u32 bictcp_clock_us(const struct sock *sk)
157{
158	return tcp_sk(sk)->tcp_mstamp;
159}
160
161static __always_inline void bictcp_hystart_reset(struct sock *sk)
162{
163	struct tcp_sock *tp = tcp_sk(sk);
164	struct bictcp *ca = inet_csk_ca(sk);
165
166	ca->round_start = ca->last_ack = bictcp_clock_us(sk);
167	ca->end_seq = tp->snd_nxt;
168	ca->curr_rtt = ~0U;
169	ca->sample_cnt = 0;
170}
171
172/* "struct_ops/" prefix is not a requirement
173 * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS
174 * as long as it is used in one of the func ptr
175 * under SEC(".struct_ops").
176 */
177SEC("struct_ops/bictcp_init")
178void BPF_PROG(bictcp_init, struct sock *sk)
179{
180	struct bictcp *ca = inet_csk_ca(sk);
181
182	bictcp_reset(ca);
183
184	if (hystart)
185		bictcp_hystart_reset(sk);
186
187	if (!hystart && initial_ssthresh)
188		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
189}
190
191/* No prefix in SEC will also work.
192 * The remaining tcp-cubic functions have an easier way.
193 */
194SEC("no-sec-prefix-bictcp_cwnd_event")
195void BPF_PROG(bictcp_cwnd_event, struct sock *sk, enum tcp_ca_event event)
196{
197	if (event == CA_EVENT_TX_START) {
198		struct bictcp *ca = inet_csk_ca(sk);
199		__u32 now = tcp_jiffies32;
200		__s32 delta;
201
202		delta = now - tcp_sk(sk)->lsndtime;
203
204		/* We were application limited (idle) for a while.
205		 * Shift epoch_start to keep cwnd growth to cubic curve.
206		 */
207		if (ca->epoch_start && delta > 0) {
208			ca->epoch_start += delta;
209			if (after(ca->epoch_start, now))
210				ca->epoch_start = now;
211		}
212		return;
213	}
214}
215
216/*
217 * cbrt(x) MSB values for x MSB values in [0..63].
218 * Precomputed then refined by hand - Willy Tarreau
219 *
220 * For x in [0..63],
221 *   v = cbrt(x << 18) - 1
222 *   cbrt(x) = (v[x] + 10) >> 6
223 */
224static const __u8 v[] = {
225	/* 0x00 */    0,   54,   54,   54,  118,  118,  118,  118,
226	/* 0x08 */  123,  129,  134,  138,  143,  147,  151,  156,
227	/* 0x10 */  157,  161,  164,  168,  170,  173,  176,  179,
228	/* 0x18 */  181,  185,  187,  190,  192,  194,  197,  199,
229	/* 0x20 */  200,  202,  204,  206,  209,  211,  213,  215,
230	/* 0x28 */  217,  219,  221,  222,  224,  225,  227,  229,
231	/* 0x30 */  231,  232,  234,  236,  237,  239,  240,  242,
232	/* 0x38 */  244,  245,  246,  248,  250,  251,  252,  254,
233};
234
235/* calculate the cubic root of x using a table lookup followed by one
236 * Newton-Raphson iteration.
237 * Avg err ~= 0.195%
238 */
239static __always_inline __u32 cubic_root(__u64 a)
240{
241	__u32 x, b, shift;
242
243	if (a < 64) {
244		/* a in [0..63] */
245		return ((__u32)v[(__u32)a] + 35) >> 6;
246	}
247
248	b = fls64(a);
249	b = ((b * 84) >> 8) - 1;
250	shift = (a >> (b * 3));
251
252	/* it is needed for verifier's bound check on v */
253	if (shift >= 64)
254		return 0;
255
256	x = ((__u32)(((__u32)v[shift] + 10) << b)) >> 6;
257
258	/*
259	 * Newton-Raphson iteration
260	 *                         2
261	 * x    = ( 2 * x  +  a / x  ) / 3
262	 *  k+1          k         k
263	 */
264	x = (2 * x + (__u32)div64_u64(a, (__u64)x * (__u64)(x - 1)));
265	x = ((x * 341) >> 10);
266	return x;
267}
268
269/*
270 * Compute congestion window to use.
271 */
272static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd,
273					  __u32 acked)
274{
275	__u32 delta, bic_target, max_cnt;
276	__u64 offs, t;
277
278	ca->ack_cnt += acked;	/* count the number of ACKed packets */
279
280	if (ca->last_cwnd == cwnd &&
281	    (__s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32)
282		return;
283
284	/* The CUBIC function can update ca->cnt at most once per jiffy.
285	 * On all cwnd reduction events, ca->epoch_start is set to 0,
286	 * which will force a recalculation of ca->cnt.
287	 */
288	if (ca->epoch_start && tcp_jiffies32 == ca->last_time)
289		goto tcp_friendliness;
290
291	ca->last_cwnd = cwnd;
292	ca->last_time = tcp_jiffies32;
293
294	if (ca->epoch_start == 0) {
295		ca->epoch_start = tcp_jiffies32;	/* record beginning */
296		ca->ack_cnt = acked;			/* start counting */
297		ca->tcp_cwnd = cwnd;			/* syn with cubic */
298
299		if (ca->last_max_cwnd <= cwnd) {
300			ca->bic_K = 0;
301			ca->bic_origin_point = cwnd;
302		} else {
303			/* Compute new K based on
304			 * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ)
305			 */
306			ca->bic_K = cubic_root(cube_factor
307					       * (ca->last_max_cwnd - cwnd));
308			ca->bic_origin_point = ca->last_max_cwnd;
309		}
310	}
311
312	/* cubic function - calc*/
313	/* calculate c * time^3 / rtt,
314	 *  while considering overflow in calculation of time^3
315	 * (so time^3 is done by using 64 bit)
316	 * and without the support of division of 64bit numbers
317	 * (so all divisions are done by using 32 bit)
318	 *  also NOTE the unit of those veriables
319	 *	  time  = (t - K) / 2^bictcp_HZ
320	 *	  c = bic_scale >> 10
321	 * rtt  = (srtt >> 3) / HZ
322	 * !!! The following code does not have overflow problems,
323	 * if the cwnd < 1 million packets !!!
324	 */
325
326	t = (__s32)(tcp_jiffies32 - ca->epoch_start) * USEC_PER_JIFFY;
327	t += ca->delay_min;
328	/* change the unit from usec to bictcp_HZ */
329	t <<= BICTCP_HZ;
330	t /= USEC_PER_SEC;
331
332	if (t < ca->bic_K)		/* t - K */
333		offs = ca->bic_K - t;
334	else
335		offs = t - ca->bic_K;
336
337	/* c/rtt * (t-K)^3 */
338	delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ);
339	if (t < ca->bic_K)                            /* below origin*/
340		bic_target = ca->bic_origin_point - delta;
341	else                                          /* above origin*/
342		bic_target = ca->bic_origin_point + delta;
343
344	/* cubic function - calc bictcp_cnt*/
345	if (bic_target > cwnd) {
346		ca->cnt = cwnd / (bic_target - cwnd);
347	} else {
348		ca->cnt = 100 * cwnd;              /* very small increment*/
349	}
350
351	/*
352	 * The initial growth of cubic function may be too conservative
353	 * when the available bandwidth is still unknown.
354	 */
355	if (ca->last_max_cwnd == 0 && ca->cnt > 20)
356		ca->cnt = 20;	/* increase cwnd 5% per RTT */
357
358tcp_friendliness:
359	/* TCP Friendly */
360	if (tcp_friendliness) {
361		__u32 scale = beta_scale;
362		__u32 n;
363
364		/* update tcp cwnd */
365		delta = (cwnd * scale) >> 3;
366		if (ca->ack_cnt > delta && delta) {
367			n = ca->ack_cnt / delta;
368			ca->ack_cnt -= n * delta;
369			ca->tcp_cwnd += n;
370		}
371
372		if (ca->tcp_cwnd > cwnd) {	/* if bic is slower than tcp */
373			delta = ca->tcp_cwnd - cwnd;
374			max_cnt = cwnd / delta;
375			if (ca->cnt > max_cnt)
376				ca->cnt = max_cnt;
377		}
378	}
379
380	/* The maximum rate of cwnd increase CUBIC allows is 1 packet per
381	 * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT.
382	 */
383	ca->cnt = max(ca->cnt, 2U);
384}
385
386/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */
387void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
388{
389	struct tcp_sock *tp = tcp_sk(sk);
390	struct bictcp *ca = inet_csk_ca(sk);
391
392	if (!tcp_is_cwnd_limited(sk))
393		return;
394
395	if (tcp_in_slow_start(tp)) {
396		if (hystart && after(ack, ca->end_seq))
397			bictcp_hystart_reset(sk);
398		acked = tcp_slow_start(tp, acked);
399		if (!acked)
400			return;
401	}
402	bictcp_update(ca, tp->snd_cwnd, acked);
403	tcp_cong_avoid_ai(tp, ca->cnt, acked);
404}
405
406__u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
407{
408	const struct tcp_sock *tp = tcp_sk(sk);
409	struct bictcp *ca = inet_csk_ca(sk);
410
411	ca->epoch_start = 0;	/* end of epoch */
412
413	/* Wmax and fast convergence */
414	if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence)
415		ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta))
416			/ (2 * BICTCP_BETA_SCALE);
417	else
418		ca->last_max_cwnd = tp->snd_cwnd;
419
420	return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
421}
422
423void BPF_STRUCT_OPS(bictcp_state, struct sock *sk, __u8 new_state)
424{
425	if (new_state == TCP_CA_Loss) {
426		bictcp_reset(inet_csk_ca(sk));
427		bictcp_hystart_reset(sk);
428	}
429}
430
431#define GSO_MAX_SIZE		65536
432
433/* Account for TSO/GRO delays.
434 * Otherwise short RTT flows could get too small ssthresh, since during
435 * slow start we begin with small TSO packets and ca->delay_min would
436 * not account for long aggregation delay when TSO packets get bigger.
437 * Ideally even with a very small RTT we would like to have at least one
438 * TSO packet being sent and received by GRO, and another one in qdisc layer.
439 * We apply another 100% factor because @rate is doubled at this point.
440 * We cap the cushion to 1ms.
441 */
442static __always_inline __u32 hystart_ack_delay(struct sock *sk)
443{
444	unsigned long rate;
445
446	rate = sk->sk_pacing_rate;
447	if (!rate)
448		return 0;
449	return min((__u64)USEC_PER_MSEC,
450		   div64_ul((__u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate));
451}
452
453static __always_inline void hystart_update(struct sock *sk, __u32 delay)
454{
455	struct tcp_sock *tp = tcp_sk(sk);
456	struct bictcp *ca = inet_csk_ca(sk);
457	__u32 threshold;
458
459	if (hystart_detect & HYSTART_ACK_TRAIN) {
460		__u32 now = bictcp_clock_us(sk);
461
462		/* first detection parameter - ack-train detection */
463		if ((__s32)(now - ca->last_ack) <= hystart_ack_delta_us) {
464			ca->last_ack = now;
465
466			threshold = ca->delay_min + hystart_ack_delay(sk);
467
468			/* Hystart ack train triggers if we get ack past
469			 * ca->delay_min/2.
470			 * Pacing might have delayed packets up to RTT/2
471			 * during slow start.
472			 */
473			if (sk->sk_pacing_status == SK_PACING_NONE)
474				threshold >>= 1;
475
476			if ((__s32)(now - ca->round_start) > threshold) {
477				ca->found = 1;
478				tp->snd_ssthresh = tp->snd_cwnd;
479			}
480		}
481	}
482
483	if (hystart_detect & HYSTART_DELAY) {
484		/* obtain the minimum delay of more than sampling packets */
485		if (ca->curr_rtt > delay)
486			ca->curr_rtt = delay;
487		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
488			ca->sample_cnt++;
489		} else {
490			if (ca->curr_rtt > ca->delay_min +
491			    HYSTART_DELAY_THRESH(ca->delay_min >> 3)) {
492				ca->found = 1;
493				tp->snd_ssthresh = tp->snd_cwnd;
494			}
495		}
496	}
497}
498
499void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
500		    const struct ack_sample *sample)
501{
502	const struct tcp_sock *tp = tcp_sk(sk);
503	struct bictcp *ca = inet_csk_ca(sk);
504	__u32 delay;
505
506	/* Some calls are for duplicates without timetamps */
507	if (sample->rtt_us < 0)
508		return;
509
510	/* Discard delay samples right after fast recovery */
511	if (ca->epoch_start && (__s32)(tcp_jiffies32 - ca->epoch_start) < HZ)
512		return;
513
514	delay = sample->rtt_us;
515	if (delay == 0)
516		delay = 1;
517
518	/* first time call or link delay decreases */
519	if (ca->delay_min == 0 || ca->delay_min > delay)
520		ca->delay_min = delay;
521
522	/* hystart triggers when cwnd is larger than some threshold */
523	if (!ca->found && tcp_in_slow_start(tp) && hystart &&
524	    tp->snd_cwnd >= hystart_low_window)
525		hystart_update(sk, delay);
526}
527
528__u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk)
529{
530	const struct tcp_sock *tp = tcp_sk(sk);
531
532	return max(tp->snd_cwnd, tp->prior_cwnd);
533}
534
535SEC(".struct_ops")
536struct tcp_congestion_ops cubic = {
537	.init		= (void *)bictcp_init,
538	.ssthresh	= (void *)bictcp_recalc_ssthresh,
539	.cong_avoid	= (void *)bictcp_cong_avoid,
540	.set_state	= (void *)bictcp_state,
541	.undo_cwnd	= (void *)tcp_reno_undo_cwnd,
542	.cwnd_event	= (void *)bictcp_cwnd_event,
543	.pkts_acked     = (void *)bictcp_acked,
544	.name		= "bpf_cubic",
545};
546