aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
blob: 79462c0368a0781ca7a38354726ed628097c0c89 (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
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
/*
 * 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 <generated/utsrelease.h>
#include <linux/mlx5/fs.h>
#include <net/switchdev.h>
#include <net/pkt_cls.h>
#include <net/netevent.h>
#include <net/arp.h>

#include "eswitch.h"
#include "en.h"
#include "en_rep.h"
#include "en_tc.h"
#include "fs_core.h"

static const char mlx5e_rep_driver_name[] = "mlx5e_rep";

static void mlx5e_rep_get_drvinfo(struct net_device *dev,
				  struct ethtool_drvinfo *drvinfo)
{
	strlcpy(drvinfo->driver, mlx5e_rep_driver_name,
		sizeof(drvinfo->driver));
	strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version));
}

static const struct counter_desc sw_rep_stats_desc[] = {
	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_packets) },
	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_bytes) },
	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_packets) },
	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) },
};

#define NUM_VPORT_REP_COUNTERS	ARRAY_SIZE(sw_rep_stats_desc)

static void mlx5e_rep_get_strings(struct net_device *dev,
				  u32 stringset, uint8_t *data)
{
	int i;

	switch (stringset) {
	case ETH_SS_STATS:
		for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++)
			strcpy(data + (i * ETH_GSTRING_LEN),
			       sw_rep_stats_desc[i].format);
		break;
	}
}

static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
{
	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;
	struct rtnl_link_stats64 *vport_stats;
	struct ifla_vf_stats vf_stats;
	int err;

	err = mlx5_eswitch_get_vport_stats(esw, rep->vport, &vf_stats);
	if (err) {
		pr_warn("vport %d error %d reading stats\n", rep->vport, err);
		return;
	}

	vport_stats = &priv->stats.vf_vport;
	/* flip tx/rx as we are reporting the counters for the switch vport */
	vport_stats->rx_packets = vf_stats.tx_packets;
	vport_stats->rx_bytes   = vf_stats.tx_bytes;
	vport_stats->tx_packets = vf_stats.rx_packets;
	vport_stats->tx_bytes   = vf_stats.rx_bytes;
}

static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
{
	struct mlx5e_sw_stats *s = &priv->stats.sw;
	struct mlx5e_rq_stats *rq_stats;
	struct mlx5e_sq_stats *sq_stats;
	int i, j;

	memset(s, 0, sizeof(*s));
	for (i = 0; i < priv->channels.num; i++) {
		struct mlx5e_channel *c = priv->channels.c[i];

		rq_stats = &c->rq.stats;

		s->rx_packets	+= rq_stats->packets;
		s->rx_bytes	+= rq_stats->bytes;

		for (j = 0; j < priv->channels.params.num_tc; j++) {
			sq_stats = &c->sq[j].stats;

			s->tx_packets		+= sq_stats->packets;
			s->tx_bytes		+= sq_stats->bytes;
		}
	}
}

static void mlx5e_rep_update_stats(struct mlx5e_priv *priv)
{
	mlx5e_rep_update_sw_counters(priv);
	mlx5e_rep_update_hw_counters(priv);
}

static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
					struct ethtool_stats *stats, u64 *data)
{
	struct mlx5e_priv *priv = netdev_priv(dev);
	int i;

	if (!data)
		return;

	mutex_lock(&priv->state_lock);
	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
		mlx5e_rep_update_sw_counters(priv);
	mutex_unlock(&priv->state_lock);

	for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++)
		data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.sw,
					       sw_rep_stats_desc, i);
}

static int mlx5e_rep_get_sset_count(struct net_device *dev, int sset)
{
	switch (sset) {
	case ETH_SS_STATS:
		return NUM_VPORT_REP_COUNTERS;
	default:
		return -EOPNOTSUPP;
	}
}

static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
	.get_link	   = ethtool_op_get_link,
	.get_strings       = mlx5e_rep_get_strings,
	.get_sset_count    = mlx5e_rep_get_sset_count,
	.get_ethtool_stats = mlx5e_rep_get_ethtool_stats,
};

int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
{
	struct mlx5e_priv *priv = netdev_priv(dev);
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;
	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;

	if (esw->mode == SRIOV_NONE)
		return -EOPNOTSUPP;

	switch (attr->id) {
	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
		attr->u.ppid.id_len = ETH_ALEN;
		ether_addr_copy(attr->u.ppid.id, rep->hw_id);
		break;
	default:
		return -EOPNOTSUPP;
	}

	return 0;
}

int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv)
{
	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;
	struct mlx5e_channel *c;
	int n, tc, num_sqs = 0;
	int err = -ENOMEM;
	u16 *sqs;

	sqs = kcalloc(priv->channels.num * priv->channels.params.num_tc, sizeof(u16), GFP_KERNEL);
	if (!sqs)
		goto out;

	for (n = 0; n < priv->channels.num; n++) {
		c = priv->channels.c[n];
		for (tc = 0; tc < c->num_tc; tc++)
			sqs[num_sqs++] = c->sq[tc].sqn;
	}

	err = mlx5_eswitch_sqs2vport_start(esw, rep, sqs, num_sqs);
	kfree(sqs);

out:
	if (err)
		netdev_warn(priv->netdev, "Failed to add SQs FWD rules %d\n", err);
	return err;
}

void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv)
{
	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;

	mlx5_eswitch_sqs2vport_stop(esw, rep);
}

static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
{
#if IS_ENABLED(CONFIG_IPV6)
	unsigned long ipv6_interval = NEIGH_VAR(&ipv6_stub->nd_tbl->parms,
						DELAY_PROBE_TIME);
#else
	unsigned long ipv6_interval = ~0UL;
#endif
	unsigned long ipv4_interval = NEIGH_VAR(&arp_tbl.parms,
						DELAY_PROBE_TIME);
	struct net_device *netdev = rpriv->rep->netdev;
	struct mlx5e_priv *priv = netdev_priv(netdev);

	rpriv->neigh_update.min_interval = min_t(unsigned long, ipv6_interval, ipv4_interval);
	mlx5_fc_update_sampling_interval(priv->mdev, rpriv->neigh_update.min_interval);
}

void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv)
{
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;

	mlx5_fc_queue_stats_work(priv->mdev,
				 &neigh_update->neigh_stats_work,
				 neigh_update->min_interval);
}

static void mlx5e_rep_neigh_stats_work(struct work_struct *work)
{
	struct mlx5e_rep_priv *rpriv = container_of(work, struct mlx5e_rep_priv,
						    neigh_update.neigh_stats_work.work);
	struct net_device *netdev = rpriv->rep->netdev;
	struct mlx5e_priv *priv = netdev_priv(netdev);
	struct mlx5e_neigh_hash_entry *nhe;

	rtnl_lock();
	if (!list_empty(&rpriv->neigh_update.neigh_list))
		mlx5e_rep_queue_neigh_stats_work(priv);

	list_for_each_entry(nhe, &rpriv->neigh_update.neigh_list, neigh_list)
		mlx5e_tc_update_neigh_used_value(nhe);

	rtnl_unlock();
}

static void mlx5e_rep_neigh_entry_hold(struct mlx5e_neigh_hash_entry *nhe)
{
	refcount_inc(&nhe->refcnt);
}

static void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe)
{
	if (refcount_dec_and_test(&nhe->refcnt))
		kfree(nhe);
}

static void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
				   struct mlx5e_encap_entry *e,
				   bool neigh_connected,
				   unsigned char ha[ETH_ALEN])
{
	struct ethhdr *eth = (struct ethhdr *)e->encap_header;

	ASSERT_RTNL();

	if ((!neigh_connected && (e->flags & MLX5_ENCAP_ENTRY_VALID)) ||
	    !ether_addr_equal(e->h_dest, ha))
		mlx5e_tc_encap_flows_del(priv, e);

	if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
		ether_addr_copy(e->h_dest, ha);
		ether_addr_copy(eth->h_dest, ha);

		mlx5e_tc_encap_flows_add(priv, e);
	}
}

static void mlx5e_rep_neigh_update(struct work_struct *work)
{
	struct mlx5e_neigh_hash_entry *nhe =
		container_of(work, struct mlx5e_neigh_hash_entry, neigh_update_work);
	struct neighbour *n = nhe->n;
	struct mlx5e_encap_entry *e;
	unsigned char ha[ETH_ALEN];
	struct mlx5e_priv *priv;
	bool neigh_connected;
	bool encap_connected;
	u8 nud_state, dead;

	rtnl_lock();

	/* If these parameters are changed after we release the lock,
	 * we'll receive another event letting us know about it.
	 * We use this lock to avoid inconsistency between the neigh validity
	 * and it's hw address.
	 */
	read_lock_bh(&n->lock);
	memcpy(ha, n->ha, ETH_ALEN);
	nud_state = n->nud_state;
	dead = n->dead;
	read_unlock_bh(&n->lock);

	neigh_connected = (nud_state & NUD_VALID) && !dead;

	list_for_each_entry(e, &nhe->encap_list, encap_list) {
		encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID);
		priv = netdev_priv(e->out_dev);

		if (encap_connected != neigh_connected ||
		    !ether_addr_equal(e->h_dest, ha))
			mlx5e_rep_update_flows(priv, e, neigh_connected, ha);
	}
	mlx5e_rep_neigh_entry_release(nhe);
	rtnl_unlock();
	neigh_release(n);
}

static struct mlx5e_neigh_hash_entry *
mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
			     struct mlx5e_neigh *m_neigh);

static int mlx5e_rep_netevent_event(struct notifier_block *nb,
				    unsigned long event, void *ptr)
{
	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
						    neigh_update.netevent_nb);
	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
	struct net_device *netdev = rpriv->rep->netdev;
	struct mlx5e_priv *priv = netdev_priv(netdev);
	struct mlx5e_neigh_hash_entry *nhe = NULL;
	struct mlx5e_neigh m_neigh = {};
	struct neigh_parms *p;
	struct neighbour *n;
	bool found = false;

	switch (event) {
	case NETEVENT_NEIGH_UPDATE:
		n = ptr;
#if IS_ENABLED(CONFIG_IPV6)
		if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl)
#else
		if (n->tbl != &arp_tbl)
#endif
			return NOTIFY_DONE;

		m_neigh.dev = n->dev;
		m_neigh.family = n->ops->family;
		memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len);

		/* We are in atomic context and can't take RTNL mutex, so use
		 * spin_lock_bh to lookup the neigh table. bh is used since
		 * netevent can be called from a softirq context.
		 */
		spin_lock_bh(&neigh_update->encap_lock);
		nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh);
		if (!nhe) {
			spin_unlock_bh(&neigh_update->encap_lock);
			return NOTIFY_DONE;
		}

		/* This assignment is valid as long as the the neigh reference
		 * is taken
		 */
		nhe->n = n;

		/* Take a reference to ensure the neighbour and mlx5 encap
		 * entry won't be destructed until we drop the reference in
		 * delayed work.
		 */
		neigh_hold(n);
		mlx5e_rep_neigh_entry_hold(nhe);

		if (!queue_work(priv->wq, &nhe->neigh_update_work)) {
			mlx5e_rep_neigh_entry_release(nhe);
			neigh_release(n);
		}
		spin_unlock_bh(&neigh_update->encap_lock);
		break;

	case NETEVENT_DELAY_PROBE_TIME_UPDATE:
		p = ptr;

		/* We check the device is present since we don't care about
		 * changes in the default table, we only care about changes
		 * done per device delay prob time parameter.
		 */
#if IS_ENABLED(CONFIG_IPV6)
		if (!p->dev || (p->tbl != ipv6_stub->nd_tbl && p->tbl != &arp_tbl))
#else
		if (!p->dev || p->tbl != &arp_tbl)
#endif
			return NOTIFY_DONE;

		/* We are in atomic context and can't take RTNL mutex,
		 * so use spin_lock_bh to walk the neigh list and look for
		 * the relevant device. bh is used since netevent can be
		 * called from a softirq context.
		 */
		spin_lock_bh(&neigh_update->encap_lock);
		list_for_each_entry(nhe, &neigh_update->neigh_list, neigh_list) {
			if (p->dev == nhe->m_neigh.dev) {
				found = true;
				break;
			}
		}
		spin_unlock_bh(&neigh_update->encap_lock);
		if (!found)
			return NOTIFY_DONE;

		neigh_update->min_interval = min_t(unsigned long,
						   NEIGH_VAR(p, DELAY_PROBE_TIME),
						   neigh_update->min_interval);
		mlx5_fc_update_sampling_interval(priv->mdev,
						 neigh_update->min_interval);
		break;
	}
	return NOTIFY_DONE;
}

static const struct rhashtable_params mlx5e_neigh_ht_params = {
	.head_offset = offsetof(struct mlx5e_neigh_hash_entry, rhash_node),
	.key_offset = offsetof(struct mlx5e_neigh_hash_entry, m_neigh),
	.key_len = sizeof(struct mlx5e_neigh),
	.automatic_shrinking = true,
};

static int mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv)
{
	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
	int err;

	err = rhashtable_init(&neigh_update->neigh_ht, &mlx5e_neigh_ht_params);
	if (err)
		return err;

	INIT_LIST_HEAD(&neigh_update->neigh_list);
	spin_lock_init(&neigh_update->encap_lock);
	INIT_DELAYED_WORK(&neigh_update->neigh_stats_work,
			  mlx5e_rep_neigh_stats_work);
	mlx5e_rep_neigh_update_init_interval(rpriv);

	rpriv->neigh_update.netevent_nb.notifier_call = mlx5e_rep_netevent_event;
	err = register_netevent_notifier(&rpriv->neigh_update.netevent_nb);
	if (err)
		goto out_err;
	return 0;

out_err:
	rhashtable_destroy(&neigh_update->neigh_ht);
	return err;
}

static void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv)
{
	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
	struct mlx5e_priv *priv = netdev_priv(rpriv->rep->netdev);

	unregister_netevent_notifier(&neigh_update->netevent_nb);

	flush_workqueue(priv->wq); /* flush neigh update works */

	cancel_delayed_work_sync(&rpriv->neigh_update.neigh_stats_work);

	rhashtable_destroy(&neigh_update->neigh_ht);
}

static int mlx5e_rep_neigh_entry_insert(struct mlx5e_priv *priv,
					struct mlx5e_neigh_hash_entry *nhe)
{
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	int err;

	err = rhashtable_insert_fast(&rpriv->neigh_update.neigh_ht,
				     &nhe->rhash_node,
				     mlx5e_neigh_ht_params);
	if (err)
		return err;

	list_add(&nhe->neigh_list, &rpriv->neigh_update.neigh_list);

	return err;
}

static void mlx5e_rep_neigh_entry_remove(struct mlx5e_priv *priv,
					 struct mlx5e_neigh_hash_entry *nhe)
{
	struct mlx5e_rep_priv *rpriv = priv->ppriv;

	spin_lock_bh(&rpriv->neigh_update.encap_lock);

	list_del(&nhe->neigh_list);

	rhashtable_remove_fast(&rpriv->neigh_update.neigh_ht,
			       &nhe->rhash_node,
			       mlx5e_neigh_ht_params);
	spin_unlock_bh(&rpriv->neigh_update.encap_lock);
}

/* This function must only be called under RTNL lock or under the
 * representor's encap_lock in case RTNL mutex can't be held.
 */
static struct mlx5e_neigh_hash_entry *
mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
			     struct mlx5e_neigh *m_neigh)
{
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;

	return rhashtable_lookup_fast(&neigh_update->neigh_ht, m_neigh,
				      mlx5e_neigh_ht_params);
}

static int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,
					struct mlx5e_encap_entry *e,
					struct mlx5e_neigh_hash_entry **nhe)
{
	int err;

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

	memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh));
	INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update);
	INIT_LIST_HEAD(&(*nhe)->encap_list);
	refcount_set(&(*nhe)->refcnt, 1);

	err = mlx5e_rep_neigh_entry_insert(priv, *nhe);
	if (err)
		goto out_free;
	return 0;

out_free:
	kfree(*nhe);
	return err;
}

static void mlx5e_rep_neigh_entry_destroy(struct mlx5e_priv *priv,
					  struct mlx5e_neigh_hash_entry *nhe)
{
	/* The neigh hash entry must be removed from the hash table regardless
	 * of the reference count value, so it won't be found by the next
	 * neigh notification call. The neigh hash entry reference count is
	 * incremented only during creation and neigh notification calls and
	 * protects from freeing the nhe struct.
	 */
	mlx5e_rep_neigh_entry_remove(priv, nhe);
	mlx5e_rep_neigh_entry_release(nhe);
}

int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
				 struct mlx5e_encap_entry *e)
{
	struct mlx5e_neigh_hash_entry *nhe;
	int err;

	nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh);
	if (!nhe) {
		err = mlx5e_rep_neigh_entry_create(priv, e, &nhe);
		if (err)
			return err;
	}
	list_add(&e->encap_list, &nhe->encap_list);
	return 0;
}

void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
				  struct mlx5e_encap_entry *e)
{
	struct mlx5e_neigh_hash_entry *nhe;

	list_del(&e->encap_list);
	nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh);

	if (list_empty(&nhe->encap_list))
		mlx5e_rep_neigh_entry_destroy(priv, nhe);
}

static int mlx5e_rep_open(struct net_device *dev)
{
	struct mlx5e_priv *priv = netdev_priv(dev);
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;
	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
	int err;

	err = mlx5e_open(dev);
	if (err)
		return err;

	err = mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP);
	if (!err)
		netif_carrier_on(dev);

	return 0;
}

static int mlx5e_rep_close(struct net_device *dev)
{
	struct mlx5e_priv *priv = netdev_priv(dev);
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;
	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;

	(void)mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);

	return mlx5e_close(dev);
}

static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
					char *buf, size_t len)
{
	struct mlx5e_priv *priv = netdev_priv(dev);
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;
	int ret;

	ret = snprintf(buf, len, "%d", rep->vport - 1);
	if (ret >= len)
		return -EOPNOTSUPP;

	return 0;
}

static int mlx5e_rep_ndo_setup_tc(struct net_device *dev, u32 handle,
				  __be16 proto, struct tc_to_netdev *tc)
{
	struct mlx5e_priv *priv = netdev_priv(dev);

	if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS))
		return -EOPNOTSUPP;

	if (tc->egress_dev) {
		struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
		struct net_device *uplink_dev = mlx5_eswitch_get_uplink_netdev(esw);

		return uplink_dev->netdev_ops->ndo_setup_tc(uplink_dev, handle,
							    proto, tc);
	}

	switch (tc->type) {
	case TC_SETUP_CLSFLOWER:
		switch (tc->cls_flower->command) {
		case TC_CLSFLOWER_REPLACE:
			return mlx5e_configure_flower(priv, proto, tc->cls_flower);
		case TC_CLSFLOWER_DESTROY:
			return mlx5e_delete_flower(priv, tc->cls_flower);
		case TC_CLSFLOWER_STATS:
			return mlx5e_stats_flower(priv, tc->cls_flower);
		}
	default:
		return -EOPNOTSUPP;
	}
}

bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
{
	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep;

	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
		return false;

	rep = rpriv->rep;
	if (esw->mode == SRIOV_OFFLOADS &&
	    rep && rep->vport == FDB_UPLINK_VPORT)
		return true;

	return false;
}

static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
{
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;

	if (rep && rep->vport != FDB_UPLINK_VPORT)
		return true;

	return false;
}

bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id)
{
	struct mlx5e_priv *priv = netdev_priv(dev);

	switch (attr_id) {
	case IFLA_OFFLOAD_XSTATS_CPU_HIT:
		if (mlx5e_is_vf_vport_rep(priv) || mlx5e_is_uplink_rep(priv))
			return true;
	}

	return false;
}

static int
mlx5e_get_sw_stats64(const struct net_device *dev,
		     struct rtnl_link_stats64 *stats)
{
	struct mlx5e_priv *priv = netdev_priv(dev);
	struct mlx5e_sw_stats *sstats = &priv->stats.sw;

	stats->rx_packets = sstats->rx_packets;
	stats->rx_bytes   = sstats->rx_bytes;
	stats->tx_packets = sstats->tx_packets;
	stats->tx_bytes   = sstats->tx_bytes;

	stats->tx_dropped = sstats->tx_queue_dropped;

	return 0;
}

int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
			    void *sp)
{
	switch (attr_id) {
	case IFLA_OFFLOAD_XSTATS_CPU_HIT:
		return mlx5e_get_sw_stats64(dev, sp);
	}

	return -EINVAL;
}

static void
mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
	struct mlx5e_priv *priv = netdev_priv(dev);

	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
}

static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
	.switchdev_port_attr_get	= mlx5e_attr_get,
};

static const struct net_device_ops mlx5e_netdev_ops_rep = {
	.ndo_open                = mlx5e_rep_open,
	.ndo_stop                = mlx5e_rep_close,
	.ndo_start_xmit          = mlx5e_xmit,
	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
	.ndo_setup_tc            = mlx5e_rep_ndo_setup_tc,
	.ndo_get_stats64         = mlx5e_rep_get_stats,
	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
};

static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
				   struct mlx5e_params *params)
{
	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;

	params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
	params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;

	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);

	params->tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
	params->num_tc                = 1;
	params->lro_wqe_sz            = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
}

static void mlx5e_build_rep_netdev(struct net_device *netdev)
{
	netdev->netdev_ops = &mlx5e_netdev_ops_rep;

	netdev->watchdog_timeo    = 15 * HZ;

	netdev->ethtool_ops	  = &mlx5e_rep_ethtool_ops;

#ifdef CONFIG_NET_SWITCHDEV
	netdev->switchdev_ops = &mlx5e_rep_switchdev_ops;
#endif

	netdev->features	 |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL;
	netdev->hw_features      |= NETIF_F_HW_TC;

	eth_hw_addr_random(netdev);
}

static void mlx5e_init_rep(struct mlx5_core_dev *mdev,
			   struct net_device *netdev,
			   const struct mlx5e_profile *profile,
			   void *ppriv)
{
	struct mlx5e_priv *priv = netdev_priv(netdev);

	priv->mdev                         = mdev;
	priv->netdev                       = netdev;
	priv->profile                      = profile;
	priv->ppriv                        = ppriv;

	mutex_init(&priv->state_lock);

	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);

	priv->channels.params.num_channels = profile->max_nch(mdev);
	mlx5e_build_rep_params(mdev, &priv->channels.params);
	mlx5e_build_rep_netdev(netdev);
}

static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
{
	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;
	struct mlx5_flow_handle *flow_rule;
	int err;

	mlx5e_init_l2_addr(priv);

	err = mlx5e_create_direct_rqts(priv);
	if (err)
		return err;

	err = mlx5e_create_direct_tirs(priv);
	if (err)
		goto err_destroy_direct_rqts;

	flow_rule = mlx5_eswitch_create_vport_rx_rule(esw,
						      rep->vport,
						      priv->direct_tir[0].tirn);
	if (IS_ERR(flow_rule)) {
		err = PTR_ERR(flow_rule);
		goto err_destroy_direct_tirs;
	}
	rep->vport_rx_rule = flow_rule;

	err = mlx5e_tc_init(priv);
	if (err)
		goto err_del_flow_rule;

	return 0;

err_del_flow_rule:
	mlx5_del_flow_rules(rep->vport_rx_rule);
err_destroy_direct_tirs:
	mlx5e_destroy_direct_tirs(priv);
err_destroy_direct_rqts:
	mlx5e_destroy_direct_rqts(priv);
	return err;
}

static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
{
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	struct mlx5_eswitch_rep *rep = rpriv->rep;

	mlx5e_tc_cleanup(priv);
	mlx5_del_flow_rules(rep->vport_rx_rule);
	mlx5e_destroy_direct_tirs(priv);
	mlx5e_destroy_direct_rqts(priv);
}

static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
{
	int err;

	err = mlx5e_create_tises(priv);
	if (err) {
		mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err);
		return err;
	}
	return 0;
}

static int mlx5e_get_rep_max_num_channels(struct mlx5_core_dev *mdev)
{
#define	MLX5E_PORT_REPRESENTOR_NCH 1
	return MLX5E_PORT_REPRESENTOR_NCH;
}

static struct mlx5e_profile mlx5e_rep_profile = {
	.init			= mlx5e_init_rep,
	.init_rx		= mlx5e_init_rep_rx,
	.cleanup_rx		= mlx5e_cleanup_rep_rx,
	.init_tx		= mlx5e_init_rep_tx,
	.cleanup_tx		= mlx5e_cleanup_nic_tx,
	.update_stats           = mlx5e_rep_update_stats,
	.max_nch		= mlx5e_get_rep_max_num_channels,
	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
	.rx_handlers.handle_rx_cqe_mpwqe = NULL /* Not supported */,
	.max_tc			= 1,
};

/* e-Switch vport representors */

static int
mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
{
	struct mlx5e_priv *priv = netdev_priv(rep->netdev);
	struct mlx5e_rep_priv *rpriv = priv->ppriv;

	int err;

	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
		err = mlx5e_add_sqs_fwd_rules(priv);
		if (err)
			return err;
	}

	err = mlx5e_rep_neigh_init(rpriv);
	if (err)
		goto err_remove_sqs;

	return 0;

err_remove_sqs:
	mlx5e_remove_sqs_fwd_rules(priv);
	return err;
}

static void
mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
{
	struct mlx5e_priv *priv = netdev_priv(rep->netdev);
	struct mlx5e_rep_priv *rpriv = priv->ppriv;

	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
		mlx5e_remove_sqs_fwd_rules(priv);

	/* clean (and re-init) existing uplink offloaded TC rules */
	mlx5e_tc_cleanup(priv);
	mlx5e_tc_init(priv);

	mlx5e_rep_neigh_cleanup(rpriv);
}

static int
mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
{
	struct mlx5e_rep_priv *rpriv;
	struct net_device *netdev;
	int err;

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

	netdev = mlx5e_create_netdev(esw->dev, &mlx5e_rep_profile, rpriv);
	if (!netdev) {
		pr_warn("Failed to create representor netdev for vport %d\n",
			rep->vport);
		kfree(rpriv);
		return -EINVAL;
	}

	rep->netdev = netdev;
	rpriv->rep = rep;

	err = mlx5e_attach_netdev(netdev_priv(netdev));
	if (err) {
		pr_warn("Failed to attach representor netdev for vport %d\n",
			rep->vport);
		goto err_destroy_netdev;
	}

	err = mlx5e_rep_neigh_init(rpriv);
	if (err) {
		pr_warn("Failed to initialized neighbours handling for vport %d\n",
			rep->vport);
		goto err_detach_netdev;
	}

	err = register_netdev(netdev);
	if (err) {
		pr_warn("Failed to register representor netdev for vport %d\n",
			rep->vport);
		goto err_neigh_cleanup;
	}

	return 0;

err_neigh_cleanup:
	mlx5e_rep_neigh_cleanup(rpriv);

err_detach_netdev:
	mlx5e_detach_netdev(netdev_priv(netdev));

err_destroy_netdev:
	mlx5e_destroy_netdev(netdev_priv(netdev));
	kfree(rpriv);
	return err;

}

static void
mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
{
	struct net_device *netdev = rep->netdev;
	struct mlx5e_priv *priv = netdev_priv(netdev);
	struct mlx5e_rep_priv *rpriv = priv->ppriv;
	void *ppriv = priv->ppriv;

	unregister_netdev(rep->netdev);

	mlx5e_rep_neigh_cleanup(rpriv);
	mlx5e_detach_netdev(priv);
	mlx5e_destroy_netdev(priv);
	kfree(ppriv); /* mlx5e_rep_priv */
}

static void mlx5e_rep_register_vf_vports(struct mlx5e_priv *priv)
{
	struct mlx5_core_dev *mdev = priv->mdev;
	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
	int vport;
	u8 mac[ETH_ALEN];

	mlx5_query_nic_vport_mac_address(mdev, 0, mac);

	for (vport = 1; vport < total_vfs; vport++) {
		struct mlx5_eswitch_rep rep;

		rep.load = mlx5e_vport_rep_load;
		rep.unload = mlx5e_vport_rep_unload;
		rep.vport = vport;
		ether_addr_copy(rep.hw_id, mac);
		mlx5_eswitch_register_vport_rep(esw, vport, &rep);
	}
}

static void mlx5e_rep_unregister_vf_vports(struct mlx5e_priv *priv)
{
	struct mlx5_core_dev *mdev = priv->mdev;
	struct mlx5_eswitch *esw = mdev->priv.eswitch;
	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
	int vport;

	for (vport = 1; vport < total_vfs; vport++)
		mlx5_eswitch_unregister_vport_rep(esw, vport);
}

void mlx5e_register_vport_reps(struct mlx5e_priv *priv)
{
	struct mlx5_core_dev *mdev = priv->mdev;
	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
	struct mlx5_eswitch_rep rep;

	mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
	rep.load = mlx5e_nic_rep_load;
	rep.unload = mlx5e_nic_rep_unload;
	rep.vport = FDB_UPLINK_VPORT;
	rep.netdev = priv->netdev;
	mlx5_eswitch_register_vport_rep(esw, 0, &rep); /* UPLINK PF vport*/

	mlx5e_rep_register_vf_vports(priv); /* VFs vports */
}

void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv)
{
	struct mlx5_core_dev *mdev = priv->mdev;
	struct mlx5_eswitch *esw   = mdev->priv.eswitch;

	mlx5e_rep_unregister_vf_vports(priv); /* VFs vports */
	mlx5_eswitch_unregister_vport_rep(esw, 0); /* UPLINK PF*/
}