summaryrefslogtreecommitdiff
path: root/net/sched/sch_fq_pie.c
blob: d6aba6edd16e5eab120a57c316fcb06a5d5f3442 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
// SPDX-License-Identifier: GPL-2.0-only
/* Flow Queue PIE discipline
 *
 * Copyright (C) 2019 Mohit P. Tahiliani <tahiliani@nitk.edu.in>
 * Copyright (C) 2019 Sachin D. Patil <sdp.sachin@gmail.com>
 * Copyright (C) 2019 V. Saicharan <vsaicharan1998@gmail.com>
 * Copyright (C) 2019 Mohit Bhasi <mohitbhasi1998@gmail.com>
 * Copyright (C) 2019 Leslie Monis <lesliemonis@gmail.com>
 * Copyright (C) 2019 Gautam Ramakrishnan <gautamramk@gmail.com>
 */

#include <linux/jhash.h>
#include <linux/sizes.h>
#include <linux/vmalloc.h>
#include <net/pkt_cls.h>
#include <net/pie.h>

/* Flow Queue PIE
 *
 * Principles:
 *   - Packets are classified on flows.
 *   - This is a Stochastic model (as we use a hash, several flows might
 *                                 be hashed to the same slot)
 *   - Each flow has a PIE managed queue.
 *   - Flows are linked onto two (Round Robin) lists,
 *     so that new flows have priority on old ones.
 *   - For a given flow, packets are not reordered.
 *   - Drops during enqueue only.
 *   - ECN capability is off by default.
 *   - ECN threshold (if ECN is enabled) is at 10% by default.
 *   - Uses timestamps to calculate queue delay by default.
 */

/**
 * struct fq_pie_flow - contains data for each flow
 * @vars:	pie vars associated with the flow
 * @deficit:	number of remaining byte credits
 * @backlog:	size of data in the flow
 * @qlen:	number of packets in the flow
 * @flowchain:	flowchain for the flow
 * @head:	first packet in the flow
 * @tail:	last packet in the flow
 */
struct fq_pie_flow {
	struct pie_vars vars;
	s32 deficit;
	u32 backlog;
	u32 qlen;
	struct list_head flowchain;
	struct sk_buff *head;
	struct sk_buff *tail;
};

struct fq_pie_sched_data {
	struct tcf_proto __rcu *filter_list; /* optional external classifier */
	struct tcf_block *block;
	struct fq_pie_flow *flows;
	struct Qdisc *sch;
	struct list_head old_flows;
	struct list_head new_flows;
	struct pie_params p_params;
	u32 ecn_prob;
	u32 flows_cnt;
	u32 quantum;
	u32 memory_limit;
	u32 new_flow_count;
	u32 memory_usage;
	u32 overmemory;
	struct pie_stats stats;
	struct timer_list adapt_timer;
};

static unsigned int fq_pie_hash(const struct fq_pie_sched_data *q,
				struct sk_buff *skb)
{
	return reciprocal_scale(skb_get_hash(skb), q->flows_cnt);
}

static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch,
				    int *qerr)
{
	struct fq_pie_sched_data *q = qdisc_priv(sch);
	struct tcf_proto *filter;
	struct tcf_result res;
	int result;

	if (TC_H_MAJ(skb->priority) == sch->handle &&
	    TC_H_MIN(skb->priority) > 0 &&
	    TC_H_MIN(skb->priority) <= q->flows_cnt)
		return TC_H_MIN(skb->priority);

	filter = rcu_dereference_bh(q->filter_list);
	if (!filter)
		return fq_pie_hash(q, skb) + 1;

	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
	result = tcf_classify(skb, NULL, filter, &res, false);
	if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
		switch (result) {
		case TC_ACT_STOLEN:
		case TC_ACT_QUEUED:
		case TC_ACT_TRAP:
			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
			fallthrough;
		case TC_ACT_SHOT:
			return 0;
		}
#endif
		if (TC_H_MIN(res.classid) <= q->flows_cnt)
			return TC_H_MIN(res.classid);
	}
	return 0;
}

/* add skb to flow queue (tail add) */
static inline void flow_queue_add(struct fq_pie_flow *flow,
				  struct sk_buff *skb)
{
	if (!flow->head)
		flow->head = skb;
	else
		flow->tail->next = skb;
	flow->tail = skb;
	skb->next = NULL;
}

static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
				struct sk_buff **to_free)
{
	struct fq_pie_sched_data *q = qdisc_priv(sch);
	struct fq_pie_flow *sel_flow;
	int ret;
	u8 memory_limited = false;
	u8 enqueue = false;
	u32 pkt_len;
	u32 idx;

	/* Classifies packet into corresponding flow */
	idx = fq_pie_classify(skb, sch, &ret);
	if (idx == 0) {
		if (ret & __NET_XMIT_BYPASS)
			qdisc_qstats_drop(sch);
		__qdisc_drop(skb, to_free);
		return ret;
	}
	idx--;

	sel_flow = &q->flows[idx];
	/* Checks whether adding a new packet would exceed memory limit */
	get_pie_cb(skb)->mem_usage = skb->truesize;
	memory_limited = q->memory_usage > q->memory_limit + skb->truesize;

	/* Checks if the qdisc is full */
	if (unlikely(qdisc_qlen(sch) >= sch->limit)) {
		q->stats.overlimit++;
		goto out;
	} else if (unlikely(memory_limited)) {
		q->overmemory++;
	}

	if (!pie_drop_early(sch, &q->p_params, &sel_flow->vars,
			    sel_flow->backlog, skb->len)) {
		enqueue = true;
	} else if (q->p_params.ecn &&
		   sel_flow->vars.prob <= (MAX_PROB / 100) * q->ecn_prob &&
		   INET_ECN_set_ce(skb)) {
		/* If packet is ecn capable, mark it if drop probability
		 * is lower than the parameter ecn_prob, else drop it.
		 */
		q->stats.ecn_mark++;
		enqueue = true;
	}
	if (enqueue) {
		/* Set enqueue time only when dq_rate_estimator is disabled. */
		if (!q->p_params.dq_rate_estimator)
			pie_set_enqueue_time(skb);

		pkt_len = qdisc_pkt_len(skb);
		q->stats.packets_in++;
		q->memory_usage += skb->truesize;
		sch->qstats.backlog += pkt_len;
		sch->q.qlen++;
		flow_queue_add(sel_flow, skb);
		if (list_empty(&sel_flow->flowchain)) {
			list_add_tail(&sel_flow->flowchain, &q->new_flows);
			q->new_flow_count++;
			sel_flow->deficit = q->quantum;
			sel_flow->qlen = 0;
			sel_flow->backlog = 0;
		}
		sel_flow->qlen++;
		sel_flow->backlog += pkt_len;
		return NET_XMIT_SUCCESS;
	}
out:
	q->stats.dropped++;
	sel_flow->vars.accu_prob = 0;
	__qdisc_drop(skb, to_free);
	qdisc_qstats_drop(sch);
	return NET_XMIT_CN;
}

static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = {
	[TCA_FQ_PIE_LIMIT]		= {.type = NLA_U32},
	[TCA_FQ_PIE_FLOWS]		= {.type = NLA_U32},
	[TCA_FQ_PIE_TARGET]		= {.type = NLA_U32},
	[TCA_FQ_PIE_TUPDATE]		= {.type = NLA_U32},
	[TCA_FQ_PIE_ALPHA]		= {.type = NLA_U32},
	[TCA_FQ_PIE_BETA]		= {.type = NLA_U32},
	[TCA_FQ_PIE_QUANTUM]		= {.type = NLA_U32},
	[TCA_FQ_PIE_MEMORY_LIMIT]	= {.type = NLA_U32},
	[TCA_FQ_PIE_ECN_PROB]		= {.type = NLA_U32},
	[TCA_FQ_PIE_ECN]		= {.type = NLA_U32},
	[TCA_FQ_PIE_BYTEMODE]		= {.type = NLA_U32},
	[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]	= {.type = NLA_U32},
};

static inline struct sk_buff *dequeue_head(struct fq_pie_flow *flow)
{
	struct sk_buff *skb = flow->head;

	flow->head = skb->next;
	skb->next = NULL;
	return skb;
}

static struct sk_buff *fq_pie_qdisc_dequeue(struct Qdisc *sch)
{
	struct fq_pie_sched_data *q = qdisc_priv(sch);
	struct sk_buff *skb = NULL;
	struct fq_pie_flow *flow;
	struct list_head *head;
	u32 pkt_len;

begin:
	head = &q->new_flows;
	if (list_empty(head)) {
		head = &q->old_flows;
		if (list_empty(head))
			return NULL;
	}

	flow = list_first_entry(head, struct fq_pie_flow, flowchain);
	/* Flow has exhausted all its credits */
	if (flow->deficit <= 0) {
		flow->deficit += q->quantum;
		list_move_tail(&flow->flowchain, &q->old_flows);
		goto begin;
	}

	if (flow->head) {
		skb = dequeue_head(flow);
		pkt_len = qdisc_pkt_len(skb);
		sch->qstats.backlog -= pkt_len;
		sch->q.qlen--;
		qdisc_bstats_update(sch, skb);
	}

	if (!skb) {
		/* force a pass through old_flows to prevent starvation */
		if (head == &q->new_flows && !list_empty(&q->old_flows))
			list_move_tail(&flow->flowchain, &q->old_flows);
		else
			list_del_init(&flow->flowchain);
		goto begin;
	}

	flow->qlen--;
	flow->deficit -= pkt_len;
	flow->backlog -= pkt_len;
	q->memory_usage -= get_pie_cb(skb)->mem_usage;
	pie_process_dequeue(skb, &q->p_params, &flow->vars, flow->backlog);
	return skb;
}

static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
			 struct netlink_ext_ack *extack)
{
	struct fq_pie_sched_data *q = qdisc_priv(sch);
	struct nlattr *tb[TCA_FQ_PIE_MAX + 1];
	unsigned int len_dropped = 0;
	unsigned int num_dropped = 0;
	int err;

	if (!opt)
		return -EINVAL;

	err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack);
	if (err < 0)
		return err;

	sch_tree_lock(sch);
	if (tb[TCA_FQ_PIE_LIMIT]) {
		u32 limit = nla_get_u32(tb[TCA_FQ_PIE_LIMIT]);

		q->p_params.limit = limit;
		sch->limit = limit;
	}
	if (tb[TCA_FQ_PIE_FLOWS]) {
		if (q->flows) {
			NL_SET_ERR_MSG_MOD(extack,
					   "Number of flows cannot be changed");
			goto flow_error;
		}
		q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]);
		if (!q->flows_cnt || q->flows_cnt > 65536) {
			NL_SET_ERR_MSG_MOD(extack,
					   "Number of flows must range in [1..65536]");
			goto flow_error;
		}
	}

	/* convert from microseconds to pschedtime */
	if (tb[TCA_FQ_PIE_TARGET]) {
		/* target is in us */
		u32 target = nla_get_u32(tb[TCA_FQ_PIE_TARGET]);

		/* convert to pschedtime */
		q->p_params.target =
			PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC);
	}

	/* tupdate is in jiffies */
	if (tb[TCA_FQ_PIE_TUPDATE])
		q->p_params.tupdate =
			usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE]));

	if (tb[TCA_FQ_PIE_ALPHA])
		q->p_params.alpha = nla_get_u32(tb[TCA_FQ_PIE_ALPHA]);

	if (tb[TCA_FQ_PIE_BETA])
		q->p_params.beta = nla_get_u32(tb[TCA_FQ_PIE_BETA]);

	if (tb[TCA_FQ_PIE_QUANTUM])
		q->quantum = nla_get_u32(tb[TCA_FQ_PIE_QUANTUM]);

	if (tb[TCA_FQ_PIE_MEMORY_LIMIT])
		q->memory_limit = nla_get_u32(tb[TCA_FQ_PIE_MEMORY_LIMIT]);

	if (tb[TCA_FQ_PIE_ECN_PROB])
		q->ecn_prob = nla_get_u32(tb[TCA_FQ_PIE_ECN_PROB]);

	if (tb[TCA_FQ_PIE_ECN])
		q->p_params.ecn = nla_get_u32(tb[TCA_FQ_PIE_ECN]);

	if (tb[TCA_FQ_PIE_BYTEMODE])
		q->p_params.bytemode = nla_get_u32(tb[TCA_FQ_PIE_BYTEMODE]);

	if (tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR])
		q->p_params.dq_rate_estimator =
			nla_get_u32(tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]);

	/* Drop excess packets if new limit is lower */
	while (sch->q.qlen > sch->limit) {
		struct sk_buff *skb = fq_pie_qdisc_dequeue(sch);

		len_dropped += qdisc_pkt_len(skb);
		num_dropped += 1;
		rtnl_kfree_skbs(skb, skb);
	}
	qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped);

	sch_tree_unlock(sch);
	return 0;

flow_error:
	sch_tree_unlock(sch);
	return -EINVAL;
}

static void fq_pie_timer(struct timer_list *t)
{
	struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer);
	struct Qdisc *sch = q->sch;
	spinlock_t *root_lock; /* to lock qdisc for probability calculations */
	u32 idx;

	root_lock = qdisc_lock(qdisc_root_sleeping(sch));
	spin_lock(root_lock);

	for (idx = 0; idx < q->flows_cnt; idx++)
		pie_calculate_probability(&q->p_params, &q->flows[idx].vars,
					  q->flows[idx].backlog);

	/* reset the timer to fire after 'tupdate' jiffies. */
	if (q->p_params.tupdate)
		mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate);

	spin_unlock(root_lock);
}

static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt,
		       struct netlink_ext_ack *extack)
{
	struct fq_pie_sched_data *q = qdisc_priv(sch);
	int err;
	u32 idx;

	pie_params_init(&q->p_params);
	sch->limit = 10 * 1024;
	q->p_params.limit = sch->limit;
	q->quantum = psched_mtu(qdisc_dev(sch));
	q->sch = sch;
	q->ecn_prob = 10;
	q->flows_cnt = 1024;
	q->memory_limit = SZ_32M;

	INIT_LIST_HEAD(&q->new_flows);
	INIT_LIST_HEAD(&q->old_flows);
	timer_setup(&q->adapt_timer, fq_pie_timer, 0);

	if (opt) {
		err = fq_pie_change(sch, opt, extack);

		if (err)
			return err;
	}

	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
	if (err)
		goto init_failure;

	q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_pie_flow),
			    GFP_KERNEL);
	if (!q->flows) {
		err = -ENOMEM;
		goto init_failure;
	}
	for (idx = 0; idx < q->flows_cnt; idx++) {
		struct fq_pie_flow *flow = q->flows + idx;

		INIT_LIST_HEAD(&flow->flowchain);
		pie_vars_init(&flow->vars);
	}

	mod_timer(&q->adapt_timer, jiffies + HZ / 2);

	return 0;

init_failure:
	q->flows_cnt = 0;

	return err;
}

static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb)
{
	struct fq_pie_sched_data *q = qdisc_priv(sch);
	struct nlattr *opts;

	opts = nla_nest_start(skb, TCA_OPTIONS);
	if (!opts)
		return -EMSGSIZE;

	/* convert target from pschedtime to us */
	if (nla_put_u32(skb, TCA_FQ_PIE_LIMIT, sch->limit) ||
	    nla_put_u32(skb, TCA_FQ_PIE_FLOWS, q->flows_cnt) ||
	    nla_put_u32(skb, TCA_FQ_PIE_TARGET,
			((u32)PSCHED_TICKS2NS(q->p_params.target)) /
			NSEC_PER_USEC) ||
	    nla_put_u32(skb, TCA_FQ_PIE_TUPDATE,
			jiffies_to_usecs(q->p_params.tupdate)) ||
	    nla_put_u32(skb, TCA_FQ_PIE_ALPHA, q->p_params.alpha) ||
	    nla_put_u32(skb, TCA_FQ_PIE_BETA, q->p_params.beta) ||
	    nla_put_u32(skb, TCA_FQ_PIE_QUANTUM, q->quantum) ||
	    nla_put_u32(skb, TCA_FQ_PIE_MEMORY_LIMIT, q->memory_limit) ||
	    nla_put_u32(skb, TCA_FQ_PIE_ECN_PROB, q->ecn_prob) ||
	    nla_put_u32(skb, TCA_FQ_PIE_ECN, q->p_params.ecn) ||
	    nla_put_u32(skb, TCA_FQ_PIE_BYTEMODE, q->p_params.bytemode) ||
	    nla_put_u32(skb, TCA_FQ_PIE_DQ_RATE_ESTIMATOR,
			q->p_params.dq_rate_estimator))
		goto nla_put_failure;

	return nla_nest_end(skb, opts);

nla_put_failure:
	nla_nest_cancel(skb, opts);
	return -EMSGSIZE;
}

static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
{
	struct fq_pie_sched_data *q = qdisc_priv(sch);
	struct tc_fq_pie_xstats st = {
		.packets_in	= q->stats.packets_in,
		.overlimit	= q->stats.overlimit,
		.overmemory	= q->overmemory,
		.dropped	= q->stats.dropped,
		.ecn_mark	= q->stats.ecn_mark,
		.new_flow_count = q->new_flow_count,
		.memory_usage   = q->memory_usage,
	};
	struct list_head *pos;

	sch_tree_lock(sch);
	list_for_each(pos, &q->new_flows)
		st.new_flows_len++;

	list_for_each(pos, &q->old_flows)
		st.old_flows_len++;
	sch_tree_unlock(sch);

	return gnet_stats_copy_app(d, &st, sizeof(st));
}

static void fq_pie_reset(struct Qdisc *sch)
{
	struct fq_pie_sched_data *q = qdisc_priv(sch);
	u32 idx;

	INIT_LIST_HEAD(&q->new_flows);
	INIT_LIST_HEAD(&q->old_flows);
	for (idx = 0; idx < q->flows_cnt; idx++) {
		struct fq_pie_flow *flow = q->flows + idx;

		/* Removes all packets from flow */
		rtnl_kfree_skbs(flow->head, flow->tail);
		flow->head = NULL;

		INIT_LIST_HEAD(&flow->flowchain);
		pie_vars_init(&flow->vars);
	}

	sch->q.qlen = 0;
	sch->qstats.backlog = 0;
}

static void fq_pie_destroy(struct Qdisc *sch)
{
	struct fq_pie_sched_data *q = qdisc_priv(sch);

	tcf_block_put(q->block);
	q->p_params.tupdate = 0;
	del_timer_sync(&q->adapt_timer);
	kvfree(q->flows);
}

static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = {
	.id		= "fq_pie",
	.priv_size	= sizeof(struct fq_pie_sched_data),
	.enqueue	= fq_pie_qdisc_enqueue,
	.dequeue	= fq_pie_qdisc_dequeue,
	.peek		= qdisc_peek_dequeued,
	.init		= fq_pie_init,
	.destroy	= fq_pie_destroy,
	.reset		= fq_pie_reset,
	.change		= fq_pie_change,
	.dump		= fq_pie_dump,
	.dump_stats	= fq_pie_dump_stats,
	.owner		= THIS_MODULE,
};

static int __init fq_pie_module_init(void)
{
	return register_qdisc(&fq_pie_qdisc_ops);
}

static void __exit fq_pie_module_exit(void)
{
	unregister_qdisc(&fq_pie_qdisc_ops);
}

module_init(fq_pie_module_init);
module_exit(fq_pie_module_exit);

MODULE_DESCRIPTION("Flow Queue Proportional Integral controller Enhanced (FQ-PIE)");
MODULE_AUTHOR("Mohit P. Tahiliani");
MODULE_LICENSE("GPL");