summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx5/core/lag.c
blob: 874c70e8cc5401d0bf8aa3c7cf22fdc2a1f88cad (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
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
/*
 * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/netdevice.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/vport.h>
#include "mlx5_core.h"
#include "eswitch.h"
#include "lag.h"
#include "lag_mp.h"

/* General purpose, use for short periods of time.
 * Beware of lock dependencies (preferably, no locks should be acquired
 * under it).
 */
static DEFINE_SPINLOCK(lag_lock);

static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1,
			       u8 remap_port2)
{
	u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {};
	void *lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx);

	MLX5_SET(create_lag_in, in, opcode, MLX5_CMD_OP_CREATE_LAG);

	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1);
	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2);

	return mlx5_cmd_exec_in(dev, create_lag, in);
}

static int mlx5_cmd_modify_lag(struct mlx5_core_dev *dev, u8 remap_port1,
			       u8 remap_port2)
{
	u32 in[MLX5_ST_SZ_DW(modify_lag_in)] = {};
	void *lag_ctx = MLX5_ADDR_OF(modify_lag_in, in, ctx);

	MLX5_SET(modify_lag_in, in, opcode, MLX5_CMD_OP_MODIFY_LAG);
	MLX5_SET(modify_lag_in, in, field_select, 0x1);

	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1);
	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2);

	return mlx5_cmd_exec_in(dev, modify_lag, in);
}

int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev)
{
	u32 in[MLX5_ST_SZ_DW(create_vport_lag_in)] = {};

	MLX5_SET(create_vport_lag_in, in, opcode, MLX5_CMD_OP_CREATE_VPORT_LAG);

	return mlx5_cmd_exec_in(dev, create_vport_lag, in);
}
EXPORT_SYMBOL(mlx5_cmd_create_vport_lag);

int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev)
{
	u32 in[MLX5_ST_SZ_DW(destroy_vport_lag_in)] = {};

	MLX5_SET(destroy_vport_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_VPORT_LAG);

	return mlx5_cmd_exec_in(dev, destroy_vport_lag, in);
}
EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag);

int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
				struct net_device *ndev)
{
	int i;

	for (i = 0; i < MLX5_MAX_PORTS; i++)
		if (ldev->pf[i].netdev == ndev)
			return i;

	return -1;
}

static bool __mlx5_lag_is_roce(struct mlx5_lag *ldev)
{
	return !!(ldev->flags & MLX5_LAG_FLAG_ROCE);
}

static bool __mlx5_lag_is_sriov(struct mlx5_lag *ldev)
{
	return !!(ldev->flags & MLX5_LAG_FLAG_SRIOV);
}

static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
					   u8 *port1, u8 *port2)
{
	*port1 = 1;
	*port2 = 2;
	if (!tracker->netdev_state[MLX5_LAG_P1].tx_enabled ||
	    !tracker->netdev_state[MLX5_LAG_P1].link_up) {
		*port1 = 2;
		return;
	}

	if (!tracker->netdev_state[MLX5_LAG_P2].tx_enabled ||
	    !tracker->netdev_state[MLX5_LAG_P2].link_up)
		*port2 = 1;
}

void mlx5_modify_lag(struct mlx5_lag *ldev,
		     struct lag_tracker *tracker)
{
	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
	u8 v2p_port1, v2p_port2;
	int err;

	mlx5_infer_tx_affinity_mapping(tracker, &v2p_port1,
				       &v2p_port2);

	if (v2p_port1 != ldev->v2p_map[MLX5_LAG_P1] ||
	    v2p_port2 != ldev->v2p_map[MLX5_LAG_P2]) {
		ldev->v2p_map[MLX5_LAG_P1] = v2p_port1;
		ldev->v2p_map[MLX5_LAG_P2] = v2p_port2;

		mlx5_core_info(dev0, "modify lag map port 1:%d port 2:%d",
			       ldev->v2p_map[MLX5_LAG_P1],
			       ldev->v2p_map[MLX5_LAG_P2]);

		err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2);
		if (err)
			mlx5_core_err(dev0,
				      "Failed to modify LAG (%d)\n",
				      err);
	}
}

static int mlx5_create_lag(struct mlx5_lag *ldev,
			   struct lag_tracker *tracker)
{
	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
	int err;

	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1],
				       &ldev->v2p_map[MLX5_LAG_P2]);

	mlx5_core_info(dev0, "lag map port 1:%d port 2:%d",
		       ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2]);

	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[MLX5_LAG_P1],
				  ldev->v2p_map[MLX5_LAG_P2]);
	if (err)
		mlx5_core_err(dev0,
			      "Failed to create LAG (%d)\n",
			      err);
	return err;
}

int mlx5_activate_lag(struct mlx5_lag *ldev,
		      struct lag_tracker *tracker,
		      u8 flags)
{
	bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE);
	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
	int err;

	err = mlx5_create_lag(ldev, tracker);
	if (err) {
		if (roce_lag) {
			mlx5_core_err(dev0,
				      "Failed to activate RoCE LAG\n");
		} else {
			mlx5_core_err(dev0,
				      "Failed to activate VF LAG\n"
				      "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n");
		}
		return err;
	}

	ldev->flags |= flags;
	return 0;
}

static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
{
	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
	u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {};
	bool roce_lag = __mlx5_lag_is_roce(ldev);
	int err;

	ldev->flags &= ~MLX5_LAG_MODE_FLAGS;

	MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG);
	err = mlx5_cmd_exec_in(dev0, destroy_lag, in);
	if (err) {
		if (roce_lag) {
			mlx5_core_err(dev0,
				      "Failed to deactivate RoCE LAG; driver restart required\n");
		} else {
			mlx5_core_err(dev0,
				      "Failed to deactivate VF LAG; driver restart required\n"
				      "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n");
		}
	}

	return err;
}

static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
{
	if (!ldev->pf[MLX5_LAG_P1].dev || !ldev->pf[MLX5_LAG_P2].dev)
		return false;

#ifdef CONFIG_MLX5_ESWITCH
	return mlx5_esw_lag_prereq(ldev->pf[MLX5_LAG_P1].dev,
				   ldev->pf[MLX5_LAG_P2].dev);
#else
	return (!mlx5_sriov_is_enabled(ldev->pf[MLX5_LAG_P1].dev) &&
		!mlx5_sriov_is_enabled(ldev->pf[MLX5_LAG_P2].dev));
#endif
}

static void mlx5_lag_add_ib_devices(struct mlx5_lag *ldev)
{
	int i;

	for (i = 0; i < MLX5_MAX_PORTS; i++)
		if (ldev->pf[i].dev)
			mlx5_add_dev_by_protocol(ldev->pf[i].dev,
						 MLX5_INTERFACE_PROTOCOL_IB);
}

static void mlx5_lag_remove_ib_devices(struct mlx5_lag *ldev)
{
	int i;

	for (i = 0; i < MLX5_MAX_PORTS; i++)
		if (ldev->pf[i].dev)
			mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
						    MLX5_INTERFACE_PROTOCOL_IB);
}

static void mlx5_do_bond(struct mlx5_lag *ldev)
{
	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
	struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev;
	struct lag_tracker tracker;
	bool do_bond, roce_lag;
	int err;

	if (!dev0 || !dev1)
		return;

	spin_lock(&lag_lock);
	tracker = ldev->tracker;
	spin_unlock(&lag_lock);

	do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);

	if (do_bond && !__mlx5_lag_is_active(ldev)) {
		roce_lag = !mlx5_sriov_is_enabled(dev0) &&
			   !mlx5_sriov_is_enabled(dev1);

#ifdef CONFIG_MLX5_ESWITCH
		roce_lag &= dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
			    dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE;
#endif

		if (roce_lag)
			mlx5_lag_remove_ib_devices(ldev);

		err = mlx5_activate_lag(ldev, &tracker,
					roce_lag ? MLX5_LAG_FLAG_ROCE :
					MLX5_LAG_FLAG_SRIOV);
		if (err) {
			if (roce_lag)
				mlx5_lag_add_ib_devices(ldev);

			return;
		}

		if (roce_lag) {
			mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
			mlx5_nic_vport_enable_roce(dev1);
		}
	} else if (do_bond && __mlx5_lag_is_active(ldev)) {
		mlx5_modify_lag(ldev, &tracker);
	} else if (!do_bond && __mlx5_lag_is_active(ldev)) {
		roce_lag = __mlx5_lag_is_roce(ldev);

		if (roce_lag) {
			mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
			mlx5_nic_vport_disable_roce(dev1);
		}

		err = mlx5_deactivate_lag(ldev);
		if (err)
			return;

		if (roce_lag)
			mlx5_lag_add_ib_devices(ldev);
	}
}

static void mlx5_queue_bond_work(struct mlx5_lag *ldev, unsigned long delay)
{
	queue_delayed_work(ldev->wq, &ldev->bond_work, delay);
}

static void mlx5_do_bond_work(struct work_struct *work)
{
	struct delayed_work *delayed_work = to_delayed_work(work);
	struct mlx5_lag *ldev = container_of(delayed_work, struct mlx5_lag,
					     bond_work);
	int status;

	status = mlx5_dev_list_trylock();
	if (!status) {
		/* 1 sec delay. */
		mlx5_queue_bond_work(ldev, HZ);
		return;
	}

	mlx5_do_bond(ldev);
	mlx5_dev_list_unlock();
}

static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
					 struct lag_tracker *tracker,
					 struct net_device *ndev,
					 struct netdev_notifier_changeupper_info *info)
{
	struct net_device *upper = info->upper_dev, *ndev_tmp;
	struct netdev_lag_upper_info *lag_upper_info = NULL;
	bool is_bonded;
	int bond_status = 0;
	int num_slaves = 0;
	int idx;

	if (!netif_is_lag_master(upper))
		return 0;

	if (info->linking)
		lag_upper_info = info->upper_info;

	/* The event may still be of interest if the slave does not belong to
	 * us, but is enslaved to a master which has one or more of our netdevs
	 * as slaves (e.g., if a new slave is added to a master that bonds two
	 * of our netdevs, we should unbond).
	 */
	rcu_read_lock();
	for_each_netdev_in_bond_rcu(upper, ndev_tmp) {
		idx = mlx5_lag_dev_get_netdev_idx(ldev, ndev_tmp);
		if (idx > -1)
			bond_status |= (1 << idx);

		num_slaves++;
	}
	rcu_read_unlock();

	/* None of this lagdev's netdevs are slaves of this master. */
	if (!(bond_status & 0x3))
		return 0;

	if (lag_upper_info)
		tracker->tx_type = lag_upper_info->tx_type;

	/* Determine bonding status:
	 * A device is considered bonded if both its physical ports are slaves
	 * of the same lag master, and only them.
	 * Lag mode must be activebackup or hash.
	 */
	is_bonded = (num_slaves == MLX5_MAX_PORTS) &&
		    (bond_status == 0x3) &&
		    ((tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) ||
		     (tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH));

	if (tracker->is_bonded != is_bonded) {
		tracker->is_bonded = is_bonded;
		return 1;
	}

	return 0;
}

static int mlx5_handle_changelowerstate_event(struct mlx5_lag *ldev,
					      struct lag_tracker *tracker,
					      struct net_device *ndev,
					      struct netdev_notifier_changelowerstate_info *info)
{
	struct netdev_lag_lower_state_info *lag_lower_info;
	int idx;

	if (!netif_is_lag_port(ndev))
		return 0;

	idx = mlx5_lag_dev_get_netdev_idx(ldev, ndev);
	if (idx == -1)
		return 0;

	/* This information is used to determine virtual to physical
	 * port mapping.
	 */
	lag_lower_info = info->lower_state_info;
	if (!lag_lower_info)
		return 0;

	tracker->netdev_state[idx] = *lag_lower_info;

	return 1;
}

static int mlx5_lag_netdev_event(struct notifier_block *this,
				 unsigned long event, void *ptr)
{
	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
	struct lag_tracker tracker;
	struct mlx5_lag *ldev;
	int changed = 0;

	if ((event != NETDEV_CHANGEUPPER) && (event != NETDEV_CHANGELOWERSTATE))
		return NOTIFY_DONE;

	ldev    = container_of(this, struct mlx5_lag, nb);
	tracker = ldev->tracker;

	switch (event) {
	case NETDEV_CHANGEUPPER:
		changed = mlx5_handle_changeupper_event(ldev, &tracker, ndev,
							ptr);
		break;
	case NETDEV_CHANGELOWERSTATE:
		changed = mlx5_handle_changelowerstate_event(ldev, &tracker,
							     ndev, ptr);
		break;
	}

	spin_lock(&lag_lock);
	ldev->tracker = tracker;
	spin_unlock(&lag_lock);

	if (changed)
		mlx5_queue_bond_work(ldev, 0);

	return NOTIFY_DONE;
}

static struct mlx5_lag *mlx5_lag_dev_alloc(void)
{
	struct mlx5_lag *ldev;

	ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
	if (!ldev)
		return NULL;

	ldev->wq = create_singlethread_workqueue("mlx5_lag");
	if (!ldev->wq) {
		kfree(ldev);
		return NULL;
	}

	INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work);

	return ldev;
}

static void mlx5_lag_dev_free(struct mlx5_lag *ldev)
{
	destroy_workqueue(ldev->wq);
	kfree(ldev);
}

static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
				struct mlx5_core_dev *dev,
				struct net_device *netdev)
{
	unsigned int fn = PCI_FUNC(dev->pdev->devfn);

	if (fn >= MLX5_MAX_PORTS)
		return;

	spin_lock(&lag_lock);
	ldev->pf[fn].dev    = dev;
	ldev->pf[fn].netdev = netdev;
	ldev->tracker.netdev_state[fn].link_up = 0;
	ldev->tracker.netdev_state[fn].tx_enabled = 0;

	dev->priv.lag = ldev;

	spin_unlock(&lag_lock);
}

static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
				   struct mlx5_core_dev *dev)
{
	int i;

	for (i = 0; i < MLX5_MAX_PORTS; i++)
		if (ldev->pf[i].dev == dev)
			break;

	if (i == MLX5_MAX_PORTS)
		return;

	spin_lock(&lag_lock);
	memset(&ldev->pf[i], 0, sizeof(*ldev->pf));

	dev->priv.lag = NULL;
	spin_unlock(&lag_lock);
}

/* Must be called with intf_mutex held */
void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
{
	struct mlx5_lag *ldev = NULL;
	struct mlx5_core_dev *tmp_dev;
	int err;

	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
	    !MLX5_CAP_GEN(dev, lag_master) ||
	    (MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS))
		return;

	tmp_dev = mlx5_get_next_phys_dev(dev);
	if (tmp_dev)
		ldev = tmp_dev->priv.lag;

	if (!ldev) {
		ldev = mlx5_lag_dev_alloc();
		if (!ldev) {
			mlx5_core_err(dev, "Failed to alloc lag dev\n");
			return;
		}
	}

	mlx5_lag_dev_add_pf(ldev, dev, netdev);

	if (!ldev->nb.notifier_call) {
		ldev->nb.notifier_call = mlx5_lag_netdev_event;
		if (register_netdevice_notifier_net(&init_net, &ldev->nb)) {
			ldev->nb.notifier_call = NULL;
			mlx5_core_err(dev, "Failed to register LAG netdev notifier\n");
		}
	}

	err = mlx5_lag_mp_init(ldev);
	if (err)
		mlx5_core_err(dev, "Failed to init multipath lag err=%d\n",
			      err);
}

/* Must be called with intf_mutex held */
void mlx5_lag_remove(struct mlx5_core_dev *dev)
{
	struct mlx5_lag *ldev;
	int i;

	ldev = mlx5_lag_dev_get(dev);
	if (!ldev)
		return;

	if (__mlx5_lag_is_active(ldev))
		mlx5_deactivate_lag(ldev);

	mlx5_lag_dev_remove_pf(ldev, dev);

	for (i = 0; i < MLX5_MAX_PORTS; i++)
		if (ldev->pf[i].dev)
			break;

	if (i == MLX5_MAX_PORTS) {
		if (ldev->nb.notifier_call) {
			unregister_netdevice_notifier_net(&init_net, &ldev->nb);
			ldev->nb.notifier_call = NULL;
		}
		mlx5_lag_mp_cleanup(ldev);
		cancel_delayed_work_sync(&ldev->bond_work);
		mlx5_lag_dev_free(ldev);
	}
}

bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
{
	struct mlx5_lag *ldev;
	bool res;

	spin_lock(&lag_lock);
	ldev = mlx5_lag_dev_get(dev);
	res  = ldev && __mlx5_lag_is_roce(ldev);
	spin_unlock(&lag_lock);

	return res;
}
EXPORT_SYMBOL(mlx5_lag_is_roce);

bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
{
	struct mlx5_lag *ldev;
	bool res;

	spin_lock(&lag_lock);
	ldev = mlx5_lag_dev_get(dev);
	res  = ldev && __mlx5_lag_is_active(ldev);
	spin_unlock(&lag_lock);

	return res;
}
EXPORT_SYMBOL(mlx5_lag_is_active);

bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
{
	struct mlx5_lag *ldev;
	bool res;

	spin_lock(&lag_lock);
	ldev = mlx5_lag_dev_get(dev);
	res  = ldev && __mlx5_lag_is_sriov(ldev);
	spin_unlock(&lag_lock);

	return res;
}
EXPORT_SYMBOL(mlx5_lag_is_sriov);

void mlx5_lag_update(struct mlx5_core_dev *dev)
{
	struct mlx5_lag *ldev;

	mlx5_dev_list_lock();
	ldev = mlx5_lag_dev_get(dev);
	if (!ldev)
		goto unlock;

	mlx5_do_bond(ldev);

unlock:
	mlx5_dev_list_unlock();
}

struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
{
	struct net_device *ndev = NULL;
	struct mlx5_lag *ldev;

	spin_lock(&lag_lock);
	ldev = mlx5_lag_dev_get(dev);

	if (!(ldev && __mlx5_lag_is_roce(ldev)))
		goto unlock;

	if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
		ndev = ldev->tracker.netdev_state[MLX5_LAG_P1].tx_enabled ?
		       ldev->pf[MLX5_LAG_P1].netdev :
		       ldev->pf[MLX5_LAG_P2].netdev;
	} else {
		ndev = ldev->pf[MLX5_LAG_P1].netdev;
	}
	if (ndev)
		dev_hold(ndev);

unlock:
	spin_unlock(&lag_lock);

	return ndev;
}
EXPORT_SYMBOL(mlx5_lag_get_roce_netdev);

u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
			   struct net_device *slave)
{
	struct mlx5_lag *ldev;
	u8 port = 0;

	spin_lock(&lag_lock);
	ldev = mlx5_lag_dev_get(dev);
	if (!(ldev && __mlx5_lag_is_roce(ldev)))
		goto unlock;

	if (ldev->pf[MLX5_LAG_P1].netdev == slave)
		port = MLX5_LAG_P1;
	else
		port = MLX5_LAG_P2;

	port = ldev->v2p_map[port];

unlock:
	spin_unlock(&lag_lock);
	return port;
}
EXPORT_SYMBOL(mlx5_lag_get_slave_port);

bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
{
	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev,
						 priv);
	struct mlx5_lag *ldev;

	if (intf->protocol != MLX5_INTERFACE_PROTOCOL_IB)
		return true;

	ldev = mlx5_lag_dev_get(dev);
	if (!ldev || !__mlx5_lag_is_roce(ldev) ||
	    ldev->pf[MLX5_LAG_P1].dev == dev)
		return true;

	/* If bonded, we do not add an IB device for PF1. */
	return false;
}

int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
				 u64 *values,
				 int num_counters,
				 size_t *offsets)
{
	int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
	struct mlx5_core_dev *mdev[MLX5_MAX_PORTS];
	struct mlx5_lag *ldev;
	int num_ports;
	int ret, i, j;
	void *out;

	out = kvzalloc(outlen, GFP_KERNEL);
	if (!out)
		return -ENOMEM;

	memset(values, 0, sizeof(*values) * num_counters);

	spin_lock(&lag_lock);
	ldev = mlx5_lag_dev_get(dev);
	if (ldev && __mlx5_lag_is_roce(ldev)) {
		num_ports = MLX5_MAX_PORTS;
		mdev[MLX5_LAG_P1] = ldev->pf[MLX5_LAG_P1].dev;
		mdev[MLX5_LAG_P2] = ldev->pf[MLX5_LAG_P2].dev;
	} else {
		num_ports = 1;
		mdev[MLX5_LAG_P1] = dev;
	}
	spin_unlock(&lag_lock);

	for (i = 0; i < num_ports; ++i) {
		u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = {};

		MLX5_SET(query_cong_statistics_in, in, opcode,
			 MLX5_CMD_OP_QUERY_CONG_STATISTICS);
		ret = mlx5_cmd_exec_inout(mdev[i], query_cong_statistics, in,
					  out);
		if (ret)
			goto free;

		for (j = 0; j < num_counters; ++j)
			values[j] += be64_to_cpup((__be64 *)(out + offsets[j]));
	}

free:
	kvfree(out);
	return ret;
}
EXPORT_SYMBOL(mlx5_lag_query_cong_counters);