summaryrefslogtreecommitdiffstats
path: root/net/sched/sch_etf.c
blob: 2278f3d420cd2938d570d783a3da5ee3fa18911a (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
// SPDX-License-Identifier: GPL-2.0

/* net/sched/sch_etf.c  Earliest TxTime First queueing discipline.
 *
 * Authors:	Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
 *		Vinicius Costa Gomes <vinicius.gomes@intel.com>
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
#include <linux/rbtree.h>
#include <linux/skbuff.h>
#include <linux/posix-timers.h>
#include <net/netlink.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/sock.h>

#define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON)
#define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON)

struct etf_sched_data {
	bool offload;
	bool deadline_mode;
	int clockid;
	int queue;
	s32 delta; /* in ns */
	ktime_t last; /* The txtime of the last skb sent to the netdevice. */
	struct rb_root head;
	struct qdisc_watchdog watchdog;
	ktime_t (*get_time)(void);
};

static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = {
	[TCA_ETF_PARMS]	= { .len = sizeof(struct tc_etf_qopt) },
};

static inline int validate_input_params(struct tc_etf_qopt *qopt,
					struct netlink_ext_ack *extack)
{
	/* Check if params comply to the following rules:
	 *	* Clockid and delta must be valid.
	 *
	 *	* Dynamic clockids are not supported.
	 *
	 *	* Delta must be a positive integer.
	 *
	 * Also note that for the HW offload case, we must
	 * expect that system clocks have been synchronized to PHC.
	 */
	if (qopt->clockid < 0) {
		NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported");
		return -ENOTSUPP;
	}

	if (qopt->clockid != CLOCK_TAI) {
		NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used");
		return -EINVAL;
	}

	if (qopt->delta < 0) {
		NL_SET_ERR_MSG(extack, "Delta must be positive");
		return -EINVAL;
	}

	return 0;
}

static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
{
	struct etf_sched_data *q = qdisc_priv(sch);
	ktime_t txtime = nskb->tstamp;
	struct sock *sk = nskb->sk;
	ktime_t now;

	if (!sk || !sk_fullsock(sk))
		return false;

	if (!sock_flag(sk, SOCK_TXTIME))
		return false;

	/* We don't perform crosstimestamping.
	 * Drop if packet's clockid differs from qdisc's.
	 */
	if (sk->sk_clockid != q->clockid)
		return false;

	if (sk->sk_txtime_deadline_mode != q->deadline_mode)
		return false;

	now = q->get_time();
	if (ktime_before(txtime, now) || ktime_before(txtime, q->last))
		return false;

	return true;
}

static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch)
{
	struct etf_sched_data *q = qdisc_priv(sch);
	struct rb_node *p;

	p = rb_first(&q->head);
	if (!p)
		return NULL;

	return rb_to_skb(p);
}

static void reset_watchdog(struct Qdisc *sch)
{
	struct etf_sched_data *q = qdisc_priv(sch);
	struct sk_buff *skb = etf_peek_timesortedlist(sch);
	ktime_t next;

	if (!skb)
		return;

	next = ktime_sub_ns(skb->tstamp, q->delta);
	qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
}

static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
{
	struct sock_exterr_skb *serr;
	struct sk_buff *clone;
	ktime_t txtime = skb->tstamp;
	struct sock *sk = skb->sk;

	if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors))
		return;

	clone = skb_clone(skb, GFP_ATOMIC);
	if (!clone)
		return;

	serr = SKB_EXT_ERR(clone);
	serr->ee.ee_errno = err;
	serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME;
	serr->ee.ee_type = 0;
	serr->ee.ee_code = code;
	serr->ee.ee_pad = 0;
	serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
	serr->ee.ee_info = txtime; /* low part of tstamp */

	if (sock_queue_err_skb(sk, clone))
		kfree_skb(clone);
}

static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
				      struct sk_buff **to_free)
{
	struct etf_sched_data *q = qdisc_priv(sch);
	struct rb_node **p = &q->head.rb_node, *parent = NULL;
	ktime_t txtime = nskb->tstamp;

	if (!is_packet_valid(sch, nskb)) {
		report_sock_error(nskb, EINVAL,
				  SO_EE_CODE_TXTIME_INVALID_PARAM);
		return qdisc_drop(nskb, sch, to_free);
	}

	while (*p) {
		struct sk_buff *skb;

		parent = *p;
		skb = rb_to_skb(parent);
		if (ktime_after(txtime, skb->tstamp))
			p = &parent->rb_right;
		else
			p = &parent->rb_left;
	}
	rb_link_node(&nskb->rbnode, parent, p);
	rb_insert_color(&nskb->rbnode, &q->head);

	qdisc_qstats_backlog_inc(sch, nskb);
	sch->q.qlen++;

	/* Now we may need to re-arm the qdisc watchdog for the next packet. */
	reset_watchdog(sch);

	return NET_XMIT_SUCCESS;
}

static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
				 bool drop)
{
	struct etf_sched_data *q = qdisc_priv(sch);

	rb_erase(&skb->rbnode, &q->head);

	/* The rbnode field in the skb re-uses these fields, now that
	 * we are done with the rbnode, reset them.
	 */
	skb->next = NULL;
	skb->prev = NULL;
	skb->dev = qdisc_dev(sch);

	qdisc_qstats_backlog_dec(sch, skb);

	if (drop) {
		struct sk_buff *to_free = NULL;

		report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);

		qdisc_drop(skb, sch, &to_free);
		kfree_skb_list(to_free);
		qdisc_qstats_overlimit(sch);
	} else {
		qdisc_bstats_update(sch, skb);

		q->last = skb->tstamp;
	}

	sch->q.qlen--;
}

static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
{
	struct etf_sched_data *q = qdisc_priv(sch);
	struct sk_buff *skb;
	ktime_t now, next;

	skb = etf_peek_timesortedlist(sch);
	if (!skb)
		return NULL;

	now = q->get_time();

	/* Drop if packet has expired while in queue. */
	if (ktime_before(skb->tstamp, now)) {
		timesortedlist_erase(sch, skb, true);
		skb = NULL;
		goto out;
	}

	/* When in deadline mode, dequeue as soon as possible and change the
	 * txtime from deadline to (now + delta).
	 */
	if (q->deadline_mode) {
		timesortedlist_erase(sch, skb, false);
		skb->tstamp = now;
		goto out;
	}

	next = ktime_sub_ns(skb->tstamp, q->delta);

	/* Dequeue only if now is within the [txtime - delta, txtime] range. */
	if (ktime_after(now, next))
		timesortedlist_erase(sch, skb, false);
	else
		skb = NULL;

out:
	/* Now we may need to re-arm the qdisc watchdog for the next packet. */
	reset_watchdog(sch);

	return skb;
}

static void etf_disable_offload(struct net_device *dev,
				struct etf_sched_data *q)
{
	struct tc_etf_qopt_offload etf = { };
	const struct net_device_ops *ops;
	int err;

	if (!q->offload)
		return;

	ops = dev->netdev_ops;
	if (!ops->ndo_setup_tc)
		return;

	etf.queue = q->queue;
	etf.enable = 0;

	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
	if (err < 0)
		pr_warn("Couldn't disable ETF offload for queue %d\n",
			etf.queue);
}

static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q,
			      struct netlink_ext_ack *extack)
{
	const struct net_device_ops *ops = dev->netdev_ops;
	struct tc_etf_qopt_offload etf = { };
	int err;

	if (q->offload)
		return 0;

	if (!ops->ndo_setup_tc) {
		NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload");
		return -EOPNOTSUPP;
	}

	etf.queue = q->queue;
	etf.enable = 1;

	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
	if (err < 0) {
		NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload");
		return err;
	}

	return 0;
}

static int etf_init(struct Qdisc *sch, struct nlattr *opt,
		    struct netlink_ext_ack *extack)
{
	struct etf_sched_data *q = qdisc_priv(sch);
	struct net_device *dev = qdisc_dev(sch);
	struct nlattr *tb[TCA_ETF_MAX + 1];
	struct tc_etf_qopt *qopt;
	int err;

	if (!opt) {
		NL_SET_ERR_MSG(extack,
			       "Missing ETF qdisc options which are mandatory");
		return -EINVAL;
	}

	err = nla_parse_nested(tb, TCA_ETF_MAX, opt, etf_policy, extack);
	if (err < 0)
		return err;

	if (!tb[TCA_ETF_PARMS]) {
		NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters");
		return -EINVAL;
	}

	qopt = nla_data(tb[TCA_ETF_PARMS]);

	pr_debug("delta %d clockid %d offload %s deadline %s\n",
		 qopt->delta, qopt->clockid,
		 OFFLOAD_IS_ON(qopt) ? "on" : "off",
		 DEADLINE_MODE_IS_ON(qopt) ? "on" : "off");

	err = validate_input_params(qopt, extack);
	if (err < 0)
		return err;

	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);

	if (OFFLOAD_IS_ON(qopt)) {
		err = etf_enable_offload(dev, q, extack);
		if (err < 0)
			return err;
	}

	/* Everything went OK, save the parameters used. */
	q->delta = qopt->delta;
	q->clockid = qopt->clockid;
	q->offload = OFFLOAD_IS_ON(qopt);
	q->deadline_mode = DEADLINE_MODE_IS_ON(qopt);

	switch (q->clockid) {
	case CLOCK_REALTIME:
		q->get_time = ktime_get_real;
		break;
	case CLOCK_MONOTONIC:
		q->get_time = ktime_get;
		break;
	case CLOCK_BOOTTIME:
		q->get_time = ktime_get_boottime;
		break;
	case CLOCK_TAI:
		q->get_time = ktime_get_clocktai;
		break;
	default:
		NL_SET_ERR_MSG(extack, "Clockid is not supported");
		return -ENOTSUPP;
	}

	qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid);

	return 0;
}

static void timesortedlist_clear(struct Qdisc *sch)
{
	struct etf_sched_data *q = qdisc_priv(sch);
	struct rb_node *p = rb_first(&q->head);

	while (p) {
		struct sk_buff *skb = rb_to_skb(p);

		p = rb_next(p);

		rb_erase(&skb->rbnode, &q->head);
		rtnl_kfree_skbs(skb, skb);
		sch->q.qlen--;
	}
}

static void etf_reset(struct Qdisc *sch)
{
	struct etf_sched_data *q = qdisc_priv(sch);

	/* Only cancel watchdog if it's been initialized. */
	if (q->watchdog.qdisc == sch)
		qdisc_watchdog_cancel(&q->watchdog);

	/* No matter which mode we are on, it's safe to clear both lists. */
	timesortedlist_clear(sch);
	__qdisc_reset_queue(&sch->q);

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

	q->last = 0;
}

static void etf_destroy(struct Qdisc *sch)
{
	struct etf_sched_data *q = qdisc_priv(sch);
	struct net_device *dev = qdisc_dev(sch);

	/* Only cancel watchdog if it's been initialized. */
	if (q->watchdog.qdisc == sch)
		qdisc_watchdog_cancel(&q->watchdog);

	etf_disable_offload(dev, q);
}

static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
{
	struct etf_sched_data *q = qdisc_priv(sch);
	struct tc_etf_qopt opt = { };
	struct nlattr *nest;

	nest = nla_nest_start(skb, TCA_OPTIONS);
	if (!nest)
		goto nla_put_failure;

	opt.delta = q->delta;
	opt.clockid = q->clockid;
	if (q->offload)
		opt.flags |= TC_ETF_OFFLOAD_ON;

	if (q->deadline_mode)
		opt.flags |= TC_ETF_DEADLINE_MODE_ON;

	if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt))
		goto nla_put_failure;

	return nla_nest_end(skb, nest);

nla_put_failure:
	nla_nest_cancel(skb, nest);
	return -1;
}

static struct Qdisc_ops etf_qdisc_ops __read_mostly = {
	.id		=	"etf",
	.priv_size	=	sizeof(struct etf_sched_data),
	.enqueue	=	etf_enqueue_timesortedlist,
	.dequeue	=	etf_dequeue_timesortedlist,
	.peek		=	etf_peek_timesortedlist,
	.init		=	etf_init,
	.reset		=	etf_reset,
	.destroy	=	etf_destroy,
	.dump		=	etf_dump,
	.owner		=	THIS_MODULE,
};

static int __init etf_module_init(void)
{
	return register_qdisc(&etf_qdisc_ops);
}

static void __exit etf_module_exit(void)
{
	unregister_qdisc(&etf_qdisc_ops);
}
module_init(etf_module_init)
module_exit(etf_module_exit)
MODULE_LICENSE("GPL");