summaryrefslogtreecommitdiffstats
path: root/net/bridge/br_mrp.c
blob: 528d767eb026fc85c33b24243bd41cb226176d96 (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
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
// SPDX-License-Identifier: GPL-2.0-or-later

#include <linux/mrp_bridge.h>
#include "br_private_mrp.h"

static const u8 mrp_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x1 };

static struct net_bridge_port *br_mrp_get_port(struct net_bridge *br,
					       u32 ifindex)
{
	struct net_bridge_port *res = NULL;
	struct net_bridge_port *port;

	list_for_each_entry(port, &br->port_list, list) {
		if (port->dev->ifindex == ifindex) {
			res = port;
			break;
		}
	}

	return res;
}

static struct br_mrp *br_mrp_find_id(struct net_bridge *br, u32 ring_id)
{
	struct br_mrp *res = NULL;
	struct br_mrp *mrp;

	list_for_each_entry_rcu(mrp, &br->mrp_list, list,
				lockdep_rtnl_is_held()) {
		if (mrp->ring_id == ring_id) {
			res = mrp;
			break;
		}
	}

	return res;
}

static bool br_mrp_unique_ifindex(struct net_bridge *br, u32 ifindex)
{
	struct br_mrp *mrp;

	list_for_each_entry_rcu(mrp, &br->mrp_list, list,
				lockdep_rtnl_is_held()) {
		struct net_bridge_port *p;

		p = rtnl_dereference(mrp->p_port);
		if (p && p->dev->ifindex == ifindex)
			return false;

		p = rtnl_dereference(mrp->s_port);
		if (p && p->dev->ifindex == ifindex)
			return false;
	}

	return true;
}

static struct br_mrp *br_mrp_find_port(struct net_bridge *br,
				       struct net_bridge_port *p)
{
	struct br_mrp *res = NULL;
	struct br_mrp *mrp;

	list_for_each_entry_rcu(mrp, &br->mrp_list, list,
				lockdep_rtnl_is_held()) {
		if (rcu_access_pointer(mrp->p_port) == p ||
		    rcu_access_pointer(mrp->s_port) == p) {
			res = mrp;
			break;
		}
	}

	return res;
}

static int br_mrp_next_seq(struct br_mrp *mrp)
{
	mrp->seq_id++;
	return mrp->seq_id;
}

static struct sk_buff *br_mrp_skb_alloc(struct net_bridge_port *p,
					const u8 *src, const u8 *dst)
{
	struct ethhdr *eth_hdr;
	struct sk_buff *skb;
	u16 *version;

	skb = dev_alloc_skb(MRP_MAX_FRAME_LENGTH);
	if (!skb)
		return NULL;

	skb->dev = p->dev;
	skb->protocol = htons(ETH_P_MRP);
	skb->priority = MRP_FRAME_PRIO;
	skb_reserve(skb, sizeof(*eth_hdr));

	eth_hdr = skb_push(skb, sizeof(*eth_hdr));
	ether_addr_copy(eth_hdr->h_dest, dst);
	ether_addr_copy(eth_hdr->h_source, src);
	eth_hdr->h_proto = htons(ETH_P_MRP);

	version = skb_put(skb, sizeof(*version));
	*version = cpu_to_be16(MRP_VERSION);

	return skb;
}

static void br_mrp_skb_tlv(struct sk_buff *skb,
			   enum br_mrp_tlv_header_type type,
			   u8 length)
{
	struct br_mrp_tlv_hdr *hdr;

	hdr = skb_put(skb, sizeof(*hdr));
	hdr->type = type;
	hdr->length = length;
}

static void br_mrp_skb_common(struct sk_buff *skb, struct br_mrp *mrp)
{
	struct br_mrp_common_hdr *hdr;

	br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_COMMON, sizeof(*hdr));

	hdr = skb_put(skb, sizeof(*hdr));
	hdr->seq_id = cpu_to_be16(br_mrp_next_seq(mrp));
	memset(hdr->domain, 0xff, MRP_DOMAIN_UUID_LENGTH);
}

static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp,
					     struct net_bridge_port *p,
					     enum br_mrp_port_role_type port_role)
{
	struct br_mrp_ring_test_hdr *hdr = NULL;
	struct sk_buff *skb = NULL;

	if (!p)
		return NULL;

	skb = br_mrp_skb_alloc(p, p->dev->dev_addr, mrp_test_dmac);
	if (!skb)
		return NULL;

	br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_RING_TEST, sizeof(*hdr));
	hdr = skb_put(skb, sizeof(*hdr));

	hdr->prio = cpu_to_be16(MRP_DEFAULT_PRIO);
	ether_addr_copy(hdr->sa, p->br->dev->dev_addr);
	hdr->port_role = cpu_to_be16(port_role);
	hdr->state = cpu_to_be16(mrp->ring_state);
	hdr->transitions = cpu_to_be16(mrp->ring_transitions);
	hdr->timestamp = cpu_to_be32(jiffies_to_msecs(jiffies));

	br_mrp_skb_common(skb, mrp);
	br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0);

	return skb;
}

static void br_mrp_test_work_expired(struct work_struct *work)
{
	struct delayed_work *del_work = to_delayed_work(work);
	struct br_mrp *mrp = container_of(del_work, struct br_mrp, test_work);
	struct net_bridge_port *p;
	bool notify_open = false;
	struct sk_buff *skb;

	if (time_before_eq(mrp->test_end, jiffies))
		return;

	if (mrp->test_count_miss < mrp->test_max_miss) {
		mrp->test_count_miss++;
	} else {
		/* Notify that the ring is open only if the ring state is
		 * closed, otherwise it would continue to notify at every
		 * interval.
		 */
		if (mrp->ring_state == BR_MRP_RING_STATE_CLOSED)
			notify_open = true;
	}

	rcu_read_lock();

	p = rcu_dereference(mrp->p_port);
	if (p) {
		skb = br_mrp_alloc_test_skb(mrp, p, BR_MRP_PORT_ROLE_PRIMARY);
		if (!skb)
			goto out;

		skb_reset_network_header(skb);
		dev_queue_xmit(skb);

		if (notify_open && !mrp->ring_role_offloaded)
			br_mrp_port_open(p->dev, true);
	}

	p = rcu_dereference(mrp->s_port);
	if (p) {
		skb = br_mrp_alloc_test_skb(mrp, p, BR_MRP_PORT_ROLE_SECONDARY);
		if (!skb)
			goto out;

		skb_reset_network_header(skb);
		dev_queue_xmit(skb);

		if (notify_open && !mrp->ring_role_offloaded)
			br_mrp_port_open(p->dev, true);
	}

out:
	rcu_read_unlock();

	queue_delayed_work(system_wq, &mrp->test_work,
			   usecs_to_jiffies(mrp->test_interval));
}

/* Deletes the MRP instance.
 * note: called under rtnl_lock
 */
static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp)
{
	struct net_bridge_port *p;
	u8 state;

	/* Stop sending MRP_Test frames */
	cancel_delayed_work_sync(&mrp->test_work);
	br_mrp_switchdev_send_ring_test(br, mrp, 0, 0, 0);

	br_mrp_switchdev_del(br, mrp);

	/* Reset the ports */
	p = rtnl_dereference(mrp->p_port);
	if (p) {
		spin_lock_bh(&br->lock);
		state = netif_running(br->dev) ?
				BR_STATE_FORWARDING : BR_STATE_DISABLED;
		p->state = state;
		p->flags &= ~BR_MRP_AWARE;
		spin_unlock_bh(&br->lock);
		br_mrp_port_switchdev_set_state(p, state);
		rcu_assign_pointer(mrp->p_port, NULL);
	}

	p = rtnl_dereference(mrp->s_port);
	if (p) {
		spin_lock_bh(&br->lock);
		state = netif_running(br->dev) ?
				BR_STATE_FORWARDING : BR_STATE_DISABLED;
		p->state = state;
		p->flags &= ~BR_MRP_AWARE;
		spin_unlock_bh(&br->lock);
		br_mrp_port_switchdev_set_state(p, state);
		rcu_assign_pointer(mrp->s_port, NULL);
	}

	list_del_rcu(&mrp->list);
	kfree_rcu(mrp, rcu);
}

/* Adds a new MRP instance.
 * note: called under rtnl_lock
 */
int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance)
{
	struct net_bridge_port *p;
	struct br_mrp *mrp;
	int err;

	/* If the ring exists, it is not possible to create another one with the
	 * same ring_id
	 */
	mrp = br_mrp_find_id(br, instance->ring_id);
	if (mrp)
		return -EINVAL;

	if (!br_mrp_get_port(br, instance->p_ifindex) ||
	    !br_mrp_get_port(br, instance->s_ifindex))
		return -EINVAL;

	/* It is not possible to have the same port part of multiple rings */
	if (!br_mrp_unique_ifindex(br, instance->p_ifindex) ||
	    !br_mrp_unique_ifindex(br, instance->s_ifindex))
		return -EINVAL;

	mrp = kzalloc(sizeof(*mrp), GFP_KERNEL);
	if (!mrp)
		return -ENOMEM;

	mrp->ring_id = instance->ring_id;

	p = br_mrp_get_port(br, instance->p_ifindex);
	spin_lock_bh(&br->lock);
	p->state = BR_STATE_FORWARDING;
	p->flags |= BR_MRP_AWARE;
	spin_unlock_bh(&br->lock);
	rcu_assign_pointer(mrp->p_port, p);

	p = br_mrp_get_port(br, instance->s_ifindex);
	spin_lock_bh(&br->lock);
	p->state = BR_STATE_FORWARDING;
	p->flags |= BR_MRP_AWARE;
	spin_unlock_bh(&br->lock);
	rcu_assign_pointer(mrp->s_port, p);

	INIT_DELAYED_WORK(&mrp->test_work, br_mrp_test_work_expired);
	list_add_tail_rcu(&mrp->list, &br->mrp_list);

	err = br_mrp_switchdev_add(br, mrp);
	if (err)
		goto delete_mrp;

	return 0;

delete_mrp:
	br_mrp_del_impl(br, mrp);

	return err;
}

/* Deletes the MRP instance from which the port is part of
 * note: called under rtnl_lock
 */
void br_mrp_port_del(struct net_bridge *br, struct net_bridge_port *p)
{
	struct br_mrp *mrp = br_mrp_find_port(br, p);

	/* If the port is not part of a MRP instance just bail out */
	if (!mrp)
		return;

	br_mrp_del_impl(br, mrp);
}

/* Deletes existing MRP instance based on ring_id
 * note: called under rtnl_lock
 */
int br_mrp_del(struct net_bridge *br, struct br_mrp_instance *instance)
{
	struct br_mrp *mrp = br_mrp_find_id(br, instance->ring_id);

	if (!mrp)
		return -EINVAL;

	br_mrp_del_impl(br, mrp);

	return 0;
}

/* Set port state, port state can be forwarding, blocked or disabled
 * note: already called with rtnl_lock
 */
int br_mrp_set_port_state(struct net_bridge_port *p,
			  enum br_mrp_port_state_type state)
{
	if (!p || !(p->flags & BR_MRP_AWARE))
		return -EINVAL;

	spin_lock_bh(&p->br->lock);

	if (state == BR_MRP_PORT_STATE_FORWARDING)
		p->state = BR_STATE_FORWARDING;
	else
		p->state = BR_STATE_BLOCKING;

	spin_unlock_bh(&p->br->lock);

	br_mrp_port_switchdev_set_state(p, state);

	return 0;
}

/* Set port role, port role can be primary or secondary
 * note: already called with rtnl_lock
 */
int br_mrp_set_port_role(struct net_bridge_port *p,
			 struct br_mrp_port_role *role)
{
	struct br_mrp *mrp;

	if (!p || !(p->flags & BR_MRP_AWARE))
		return -EINVAL;

	mrp = br_mrp_find_id(p->br, role->ring_id);

	if (!mrp)
		return -EINVAL;

	if (role->role == BR_MRP_PORT_ROLE_PRIMARY)
		rcu_assign_pointer(mrp->p_port, p);
	else
		rcu_assign_pointer(mrp->s_port, p);

	br_mrp_port_switchdev_set_role(p, role->role);

	return 0;
}

/* Set ring state, ring state can be only Open or Closed
 * note: already called with rtnl_lock
 */
int br_mrp_set_ring_state(struct net_bridge *br,
			  struct br_mrp_ring_state *state)
{
	struct br_mrp *mrp = br_mrp_find_id(br, state->ring_id);

	if (!mrp)
		return -EINVAL;

	if (mrp->ring_state == BR_MRP_RING_STATE_CLOSED &&
	    state->ring_state != BR_MRP_RING_STATE_CLOSED)
		mrp->ring_transitions++;

	mrp->ring_state = state->ring_state;

	br_mrp_switchdev_set_ring_state(br, mrp, state->ring_state);

	return 0;
}

/* Set ring role, ring role can be only MRM(Media Redundancy Manager) or
 * MRC(Media Redundancy Client).
 * note: already called with rtnl_lock
 */
int br_mrp_set_ring_role(struct net_bridge *br,
			 struct br_mrp_ring_role *role)
{
	struct br_mrp *mrp = br_mrp_find_id(br, role->ring_id);
	int err;

	if (!mrp)
		return -EINVAL;

	mrp->ring_role = role->ring_role;

	/* If there is an error just bailed out */
	err = br_mrp_switchdev_set_ring_role(br, mrp, role->ring_role);
	if (err && err != -EOPNOTSUPP)
		return err;

	/* Now detect if the HW actually applied the role or not. If the HW
	 * applied the role it means that the SW will not to do those operations
	 * anymore. For example if the role ir MRM then the HW will notify the
	 * SW when ring is open, but if the is not pushed to the HW the SW will
	 * need to detect when the ring is open
	 */
	mrp->ring_role_offloaded = err == -EOPNOTSUPP ? 0 : 1;

	return 0;
}

/* Start to generate MRP test frames, the frames are generated by HW and if it
 * fails, they are generated by the SW.
 * note: already called with rtnl_lock
 */
int br_mrp_start_test(struct net_bridge *br,
		      struct br_mrp_start_test *test)
{
	struct br_mrp *mrp = br_mrp_find_id(br, test->ring_id);

	if (!mrp)
		return -EINVAL;

	/* Try to push it to the HW and if it fails then continue to generate in
	 * SW and if that also fails then return error
	 */
	if (!br_mrp_switchdev_send_ring_test(br, mrp, test->interval,
					     test->max_miss, test->period))
		return 0;

	mrp->test_interval = test->interval;
	mrp->test_end = jiffies + usecs_to_jiffies(test->period);
	mrp->test_max_miss = test->max_miss;
	mrp->test_count_miss = 0;
	queue_delayed_work(system_wq, &mrp->test_work,
			   usecs_to_jiffies(test->interval));

	return 0;
}

/* Process only MRP Test frame. All the other MRP frames are processed by
 * userspace application
 * note: already called with rcu_read_lock
 */
static void br_mrp_mrm_process(struct br_mrp *mrp, struct net_bridge_port *port,
			       struct sk_buff *skb)
{
	const struct br_mrp_tlv_hdr *hdr;
	struct br_mrp_tlv_hdr _hdr;

	/* Each MRP header starts with a version field which is 16 bits.
	 * Therefore skip the version and get directly the TLV header.
	 */
	hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr);
	if (!hdr)
		return;

	if (hdr->type != BR_MRP_TLV_HEADER_RING_TEST)
		return;

	mrp->test_count_miss = 0;

	/* Notify the userspace that the ring is closed only when the ring is
	 * not closed
	 */
	if (mrp->ring_state != BR_MRP_RING_STATE_CLOSED)
		br_mrp_port_open(port->dev, false);
}

/* This will just forward the frame to the other mrp ring port(MRC role) or will
 * not do anything.
 * note: already called with rcu_read_lock
 */
static int br_mrp_rcv(struct net_bridge_port *p,
		      struct sk_buff *skb, struct net_device *dev)
{
	struct net_device *s_dev, *p_dev, *d_dev;
	struct net_bridge_port *p_port, *s_port;
	struct net_bridge *br;
	struct sk_buff *nskb;
	struct br_mrp *mrp;

	/* If port is disabled don't accept any frames */
	if (p->state == BR_STATE_DISABLED)
		return 0;

	br = p->br;
	mrp =  br_mrp_find_port(br, p);
	if (unlikely(!mrp))
		return 0;

	p_port = rcu_dereference(mrp->p_port);
	if (!p_port)
		return 0;

	s_port = rcu_dereference(mrp->s_port);
	if (!s_port)
		return 0;

	/* If the role is MRM then don't forward the frames */
	if (mrp->ring_role == BR_MRP_RING_ROLE_MRM) {
		br_mrp_mrm_process(mrp, p, skb);
		return 1;
	}

	/* Clone the frame and forward it on the other MRP port */
	nskb = skb_clone(skb, GFP_ATOMIC);
	if (!nskb)
		return 0;

	p_dev = p_port->dev;
	s_dev = s_port->dev;

	if (p_dev == dev)
		d_dev = s_dev;
	else
		d_dev = p_dev;

	nskb->dev = d_dev;
	skb_push(nskb, ETH_HLEN);
	dev_queue_xmit(nskb);

	return 1;
}

/* Check if the frame was received on a port that is part of MRP ring
 * and if the frame has MRP eth. In that case process the frame otherwise do
 * normal forwarding.
 * note: already called with rcu_read_lock
 */
int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
{
	/* If there is no MRP instance do normal forwarding */
	if (likely(!(p->flags & BR_MRP_AWARE)))
		goto out;

	if (unlikely(skb->protocol == htons(ETH_P_MRP)))
		return br_mrp_rcv(p, skb, p->dev);

out:
	return 0;
}

bool br_mrp_enabled(struct net_bridge *br)
{
	return !list_empty(&br->mrp_list);
}