summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
blob: 979af197f8a332d83ca17e88e73370aa1fb5691d (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
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019, Intel Corporation. */

#include "ice_dcb_lib.h"
#include "ice_dcb_nl.h"

/**
 * ice_vsi_cfg_netdev_tc - Setup the netdev TC configuration
 * @vsi: the VSI being configured
 * @ena_tc: TC map to be enabled
 */
void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc)
{
	struct net_device *netdev = vsi->netdev;
	struct ice_pf *pf = vsi->back;
	struct ice_dcbx_cfg *dcbcfg;
	u8 netdev_tc;
	int i;

	if (!netdev)
		return;

	if (!ena_tc) {
		netdev_reset_tc(netdev);
		return;
	}

	if (netdev_set_num_tc(netdev, vsi->tc_cfg.numtc))
		return;

	dcbcfg = &pf->hw.port_info->local_dcbx_cfg;

	ice_for_each_traffic_class(i)
		if (vsi->tc_cfg.ena_tc & BIT(i))
			netdev_set_tc_queue(netdev,
					    vsi->tc_cfg.tc_info[i].netdev_tc,
					    vsi->tc_cfg.tc_info[i].qcount_tx,
					    vsi->tc_cfg.tc_info[i].qoffset);

	for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
		u8 ets_tc = dcbcfg->etscfg.prio_table[i];

		/* Get the mapped netdev TC# for the UP */
		netdev_tc = vsi->tc_cfg.tc_info[ets_tc].netdev_tc;
		netdev_set_prio_tc_map(netdev, i, netdev_tc);
	}
}

/**
 * ice_dcb_get_ena_tc - return bitmap of enabled TCs
 * @dcbcfg: DCB config to evaluate for enabled TCs
 */
u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg)
{
	u8 i, num_tc, ena_tc = 1;

	num_tc = ice_dcb_get_num_tc(dcbcfg);

	for (i = 0; i < num_tc; i++)
		ena_tc |= BIT(i);

	return ena_tc;
}

/**
 * ice_is_pfc_causing_hung_q
 * @pf: pointer to PF structure
 * @txqueue: Tx queue which is supposedly hung queue
 *
 * find if PFC is causing the hung queue, if yes return true else false
 */
bool ice_is_pfc_causing_hung_q(struct ice_pf *pf, unsigned int txqueue)
{
	u8 num_tcs = 0, i, tc, up_mapped_tc, up_in_tc = 0;
	u64 ref_prio_xoff[ICE_MAX_UP];
	struct ice_vsi *vsi;
	u32 up2tc;

	vsi = ice_get_main_vsi(pf);
	if (!vsi)
		return false;

	ice_for_each_traffic_class(i)
		if (vsi->tc_cfg.ena_tc & BIT(i))
			num_tcs++;

	/* first find out the TC to which the hung queue belongs to */
	for (tc = 0; tc < num_tcs - 1; tc++)
		if (ice_find_q_in_range(vsi->tc_cfg.tc_info[tc].qoffset,
					vsi->tc_cfg.tc_info[tc + 1].qoffset,
					txqueue))
			break;

	/* Build a bit map of all UPs associated to the suspect hung queue TC,
	 * so that we check for its counter increment.
	 */
	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
	for (i = 0; i < ICE_MAX_UP; i++) {
		up_mapped_tc = (up2tc >> (i * 3)) & 0x7;
		if (up_mapped_tc == tc)
			up_in_tc |= BIT(i);
	}

	/* Now that we figured out that hung queue is PFC enabled, still the
	 * Tx timeout can be legitimate. So to make sure Tx timeout is
	 * absolutely caused by PFC storm, check if the counters are
	 * incrementing.
	 */
	for (i = 0; i < ICE_MAX_UP; i++)
		if (up_in_tc & BIT(i))
			ref_prio_xoff[i] = pf->stats.priority_xoff_rx[i];

	ice_update_dcb_stats(pf);

	for (i = 0; i < ICE_MAX_UP; i++)
		if (up_in_tc & BIT(i))
			if (pf->stats.priority_xoff_rx[i] > ref_prio_xoff[i])
				return true;

	return false;
}

/**
 * ice_dcb_get_mode - gets the DCB mode
 * @port_info: pointer to port info structure
 * @host: if set it's HOST if not it's MANAGED
 */
static u8 ice_dcb_get_mode(struct ice_port_info *port_info, bool host)
{
	u8 mode;

	if (host)
		mode = DCB_CAP_DCBX_HOST;
	else
		mode = DCB_CAP_DCBX_LLD_MANAGED;

	if (port_info->local_dcbx_cfg.dcbx_mode & ICE_DCBX_MODE_CEE)
		return mode | DCB_CAP_DCBX_VER_CEE;
	else
		return mode | DCB_CAP_DCBX_VER_IEEE;
}

/**
 * ice_dcb_get_num_tc - Get the number of TCs from DCBX config
 * @dcbcfg: config to retrieve number of TCs from
 */
u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg)
{
	bool tc_unused = false;
	u8 num_tc = 0;
	u8 ret = 0;
	int i;

	/* Scan the ETS Config Priority Table to find traffic classes
	 * enabled and create a bitmask of enabled TCs
	 */
	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++)
		num_tc |= BIT(dcbcfg->etscfg.prio_table[i]);

	/* Scan bitmask for contiguous TCs starting with TC0 */
	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
		if (num_tc & BIT(i)) {
			if (!tc_unused) {
				ret++;
			} else {
				pr_err("Non-contiguous TCs - Disabling DCB\n");
				return 1;
			}
		} else {
			tc_unused = true;
		}
	}

	/* There is always at least 1 TC */
	if (!ret)
		ret = 1;

	return ret;
}

/**
 * ice_dcb_get_tc - Get the TC associated with the queue
 * @vsi: ptr to the VSI
 * @queue_index: queue number associated with VSI
 */
u8 ice_dcb_get_tc(struct ice_vsi *vsi, int queue_index)
{
	return vsi->tx_rings[queue_index]->dcb_tc;
}

/**
 * ice_vsi_cfg_dcb_rings - Update rings to reflect DCB TC
 * @vsi: VSI owner of rings being updated
 */
void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi)
{
	struct ice_ring *tx_ring, *rx_ring;
	u16 qoffset, qcount;
	int i, n;

	if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) {
		/* Reset the TC information */
		for (i = 0; i < vsi->num_txq; i++) {
			tx_ring = vsi->tx_rings[i];
			tx_ring->dcb_tc = 0;
		}
		for (i = 0; i < vsi->num_rxq; i++) {
			rx_ring = vsi->rx_rings[i];
			rx_ring->dcb_tc = 0;
		}
		return;
	}

	ice_for_each_traffic_class(n) {
		if (!(vsi->tc_cfg.ena_tc & BIT(n)))
			break;

		qoffset = vsi->tc_cfg.tc_info[n].qoffset;
		qcount = vsi->tc_cfg.tc_info[n].qcount_tx;
		for (i = qoffset; i < (qoffset + qcount); i++) {
			tx_ring = vsi->tx_rings[i];
			rx_ring = vsi->rx_rings[i];
			tx_ring->dcb_tc = n;
			rx_ring->dcb_tc = n;
		}
	}
}

/**
 * ice_dcb_bwchk - check if ETS bandwidth input parameters are correct
 * @pf: pointer to the PF struct
 * @dcbcfg: pointer to DCB config structure
 */
int ice_dcb_bwchk(struct ice_pf *pf, struct ice_dcbx_cfg *dcbcfg)
{
	struct ice_dcb_ets_cfg *etscfg = &dcbcfg->etscfg;
	u8 num_tc, total_bw = 0;
	int i;

	/* returns number of contigous TCs and 1 TC for non-contigous TCs,
	 * since at least 1 TC has to be configured
	 */
	num_tc = ice_dcb_get_num_tc(dcbcfg);

	/* no bandwidth checks required if there's only one TC, so assign
	 * all bandwidth to TC0 and return
	 */
	if (num_tc == 1) {
		etscfg->tcbwtable[0] = ICE_TC_MAX_BW;
		return 0;
	}

	for (i = 0; i < num_tc; i++)
		total_bw += etscfg->tcbwtable[i];

	if (!total_bw) {
		etscfg->tcbwtable[0] = ICE_TC_MAX_BW;
	} else if (total_bw != ICE_TC_MAX_BW) {
		dev_err(ice_pf_to_dev(pf), "Invalid config, total bandwidth must equal 100\n");
		return -EINVAL;
	}

	return 0;
}

/**
 * ice_pf_dcb_cfg - Apply new DCB configuration
 * @pf: pointer to the PF struct
 * @new_cfg: DCBX config to apply
 * @locked: is the RTNL held
 */
int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
{
	struct ice_aqc_port_ets_elem buf = { 0 };
	struct ice_dcbx_cfg *old_cfg, *curr_cfg;
	struct device *dev = ice_pf_to_dev(pf);
	int ret = ICE_DCB_NO_HW_CHG;
	struct ice_vsi *pf_vsi;

	curr_cfg = &pf->hw.port_info->local_dcbx_cfg;

	/* FW does not care if change happened */
	if (!pf->hw.port_info->is_sw_lldp)
		ret = ICE_DCB_HW_CHG_RST;

	/* Enable DCB tagging only when more than one TC */
	if (ice_dcb_get_num_tc(new_cfg) > 1) {
		dev_dbg(dev, "DCB tagging enabled (num TC > 1)\n");
		set_bit(ICE_FLAG_DCB_ENA, pf->flags);
	} else {
		dev_dbg(dev, "DCB tagging disabled (num TC = 1)\n");
		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
	}

	if (!memcmp(new_cfg, curr_cfg, sizeof(*new_cfg))) {
		dev_dbg(dev, "No change in DCB config required\n");
		return ret;
	}

	if (ice_dcb_bwchk(pf, new_cfg))
		return -EINVAL;

	/* Store old config in case FW config fails */
	old_cfg = kmemdup(curr_cfg, sizeof(*old_cfg), GFP_KERNEL);
	if (!old_cfg)
		return -ENOMEM;

	dev_info(dev, "Commit DCB Configuration to the hardware\n");
	pf_vsi = ice_get_main_vsi(pf);
	if (!pf_vsi) {
		dev_dbg(dev, "PF VSI doesn't exist\n");
		ret = -EINVAL;
		goto free_cfg;
	}

	/* avoid race conditions by holding the lock while disabling and
	 * re-enabling the VSI
	 */
	if (!locked)
		rtnl_lock();
	ice_dis_vsi(pf_vsi, true);

	memcpy(curr_cfg, new_cfg, sizeof(*curr_cfg));
	memcpy(&curr_cfg->etsrec, &curr_cfg->etscfg, sizeof(curr_cfg->etsrec));
	memcpy(&new_cfg->etsrec, &curr_cfg->etscfg, sizeof(curr_cfg->etsrec));

	/* Only send new config to HW if we are in SW LLDP mode. Otherwise,
	 * the new config came from the HW in the first place.
	 */
	if (pf->hw.port_info->is_sw_lldp) {
		ret = ice_set_dcb_cfg(pf->hw.port_info);
		if (ret) {
			dev_err(dev, "Set DCB Config failed\n");
			/* Restore previous settings to local config */
			memcpy(curr_cfg, old_cfg, sizeof(*curr_cfg));
			goto out;
		}
	}

	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
	if (ret) {
		dev_err(dev, "Query Port ETS failed\n");
		goto out;
	}

	ice_pf_dcb_recfg(pf);

out:
	ice_ena_vsi(pf_vsi, true);
	if (!locked)
		rtnl_unlock();
free_cfg:
	kfree(old_cfg);
	return ret;
}

/**
 * ice_cfg_etsrec_defaults - Set default ETS recommended DCB config
 * @pi: port information structure
 */
static void ice_cfg_etsrec_defaults(struct ice_port_info *pi)
{
	struct ice_dcbx_cfg *dcbcfg = &pi->local_dcbx_cfg;
	u8 i;

	/* Ensure ETS recommended DCB configuration is not already set */
	if (dcbcfg->etsrec.maxtcs)
		return;

	/* In CEE mode, set the default to 1 TC */
	dcbcfg->etsrec.maxtcs = 1;
	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
		dcbcfg->etsrec.tcbwtable[i] = i ? 0 : 100;
		dcbcfg->etsrec.tsatable[i] = i ? ICE_IEEE_TSA_STRICT :
						 ICE_IEEE_TSA_ETS;
	}
}

/**
 * ice_dcb_need_recfg - Check if DCB needs reconfig
 * @pf: board private structure
 * @old_cfg: current DCB config
 * @new_cfg: new DCB config
 */
static bool
ice_dcb_need_recfg(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,
		   struct ice_dcbx_cfg *new_cfg)
{
	struct device *dev = ice_pf_to_dev(pf);
	bool need_reconfig = false;

	/* Check if ETS configuration has changed */
	if (memcmp(&new_cfg->etscfg, &old_cfg->etscfg,
		   sizeof(new_cfg->etscfg))) {
		/* If Priority Table has changed reconfig is needed */
		if (memcmp(&new_cfg->etscfg.prio_table,
			   &old_cfg->etscfg.prio_table,
			   sizeof(new_cfg->etscfg.prio_table))) {
			need_reconfig = true;
			dev_dbg(dev, "ETS UP2TC changed.\n");
		}

		if (memcmp(&new_cfg->etscfg.tcbwtable,
			   &old_cfg->etscfg.tcbwtable,
			   sizeof(new_cfg->etscfg.tcbwtable)))
			dev_dbg(dev, "ETS TC BW Table changed.\n");

		if (memcmp(&new_cfg->etscfg.tsatable,
			   &old_cfg->etscfg.tsatable,
			   sizeof(new_cfg->etscfg.tsatable)))
			dev_dbg(dev, "ETS TSA Table changed.\n");
	}

	/* Check if PFC configuration has changed */
	if (memcmp(&new_cfg->pfc, &old_cfg->pfc, sizeof(new_cfg->pfc))) {
		need_reconfig = true;
		dev_dbg(dev, "PFC config change detected.\n");
	}

	/* Check if APP Table has changed */
	if (memcmp(&new_cfg->app, &old_cfg->app, sizeof(new_cfg->app))) {
		need_reconfig = true;
		dev_dbg(dev, "APP Table change detected.\n");
	}

	dev_dbg(dev, "dcb need_reconfig=%d\n", need_reconfig);
	return need_reconfig;
}

/**
 * ice_dcb_rebuild - rebuild DCB post reset
 * @pf: physical function instance
 */
void ice_dcb_rebuild(struct ice_pf *pf)
{
	struct ice_aqc_port_ets_elem buf = { 0 };
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_dcbx_cfg *err_cfg;
	enum ice_status ret;

	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
	if (ret) {
		dev_err(dev, "Query Port ETS failed\n");
		goto dcb_error;
	}

	/* If DCB was not enabled previously, we are done */
	if (!test_bit(ICE_FLAG_DCB_ENA, pf->flags))
		return;

	mutex_lock(&pf->tc_mutex);

	if (!pf->hw.port_info->is_sw_lldp)
		ice_cfg_etsrec_defaults(pf->hw.port_info);

	ret = ice_set_dcb_cfg(pf->hw.port_info);
	if (ret) {
		dev_err(dev, "Failed to set DCB config in rebuild\n");
		goto dcb_error;
	}

	if (!pf->hw.port_info->is_sw_lldp) {
		ret = ice_cfg_lldp_mib_change(&pf->hw, true);
		if (ret && !pf->hw.port_info->is_sw_lldp) {
			dev_err(dev, "Failed to register for MIB changes\n");
			goto dcb_error;
		}
	}

	dev_info(dev, "DCB restored after reset\n");
	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
	if (ret) {
		dev_err(dev, "Query Port ETS failed\n");
		goto dcb_error;
	}

	mutex_unlock(&pf->tc_mutex);

	return;

dcb_error:
	dev_err(dev, "Disabling DCB until new settings occur\n");
	err_cfg = kzalloc(sizeof(*err_cfg), GFP_KERNEL);
	if (!err_cfg) {
		mutex_unlock(&pf->tc_mutex);
		return;
	}

	err_cfg->etscfg.willing = true;
	err_cfg->etscfg.tcbwtable[0] = ICE_TC_MAX_BW;
	err_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
	memcpy(&err_cfg->etsrec, &err_cfg->etscfg, sizeof(err_cfg->etsrec));
	/* Coverity warns the return code of ice_pf_dcb_cfg() is not checked
	 * here as is done for other calls to that function. That check is
	 * not necessary since this is in this function's error cleanup path.
	 * Suppress the Coverity warning with the following comment...
	 */
	/* coverity[check_return] */
	ice_pf_dcb_cfg(pf, err_cfg, false);
	kfree(err_cfg);

	mutex_unlock(&pf->tc_mutex);
}

/**
 * ice_dcb_init_cfg - set the initial DCB config in SW
 * @pf: PF to apply config to
 * @locked: Is the RTNL held
 */
static int ice_dcb_init_cfg(struct ice_pf *pf, bool locked)
{
	struct ice_dcbx_cfg *newcfg;
	struct ice_port_info *pi;
	int ret = 0;

	pi = pf->hw.port_info;
	newcfg = kmemdup(&pi->local_dcbx_cfg, sizeof(*newcfg), GFP_KERNEL);
	if (!newcfg)
		return -ENOMEM;

	memset(&pi->local_dcbx_cfg, 0, sizeof(*newcfg));

	dev_info(ice_pf_to_dev(pf), "Configuring initial DCB values\n");
	if (ice_pf_dcb_cfg(pf, newcfg, locked))
		ret = -EINVAL;

	kfree(newcfg);

	return ret;
}

/**
 * ice_dcb_sw_dflt_cfg - Apply a default DCB config
 * @pf: PF to apply config to
 * @ets_willing: configure ETS willing
 * @locked: was this function called with RTNL held
 */
static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked)
{
	struct ice_aqc_port_ets_elem buf = { 0 };
	struct ice_dcbx_cfg *dcbcfg;
	struct ice_port_info *pi;
	struct ice_hw *hw;
	int ret;

	hw = &pf->hw;
	pi = hw->port_info;
	dcbcfg = kzalloc(sizeof(*dcbcfg), GFP_KERNEL);
	if (!dcbcfg)
		return -ENOMEM;

	memset(&pi->local_dcbx_cfg, 0, sizeof(*dcbcfg));

	dcbcfg->etscfg.willing = ets_willing ? 1 : 0;
	dcbcfg->etscfg.maxtcs = hw->func_caps.common_cap.maxtc;
	dcbcfg->etscfg.tcbwtable[0] = 100;
	dcbcfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;

	memcpy(&dcbcfg->etsrec, &dcbcfg->etscfg,
	       sizeof(dcbcfg->etsrec));
	dcbcfg->etsrec.willing = 0;

	dcbcfg->pfc.willing = 1;
	dcbcfg->pfc.pfccap = hw->func_caps.common_cap.maxtc;

	dcbcfg->numapps = 1;
	dcbcfg->app[0].selector = ICE_APP_SEL_ETHTYPE;
	dcbcfg->app[0].priority = 3;
	dcbcfg->app[0].prot_id = ICE_APP_PROT_ID_FCOE;

	ret = ice_pf_dcb_cfg(pf, dcbcfg, locked);
	kfree(dcbcfg);
	if (ret)
		return ret;

	return ice_query_port_ets(pi, &buf, sizeof(buf), NULL);
}

/**
 * ice_dcb_tc_contig - Check that TCs are contiguous
 * @prio_table: pointer to priority table
 *
 * Check if TCs begin with TC0 and are contiguous
 */
static bool ice_dcb_tc_contig(u8 *prio_table)
{
	bool found_empty = false;
	u8 used_tc = 0;
	int i;

	/* Create a bitmap of used TCs */
	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++)
		used_tc |= BIT(prio_table[i]);

	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++) {
		if (used_tc & BIT(i)) {
			if (found_empty)
				return false;
		} else {
			found_empty = true;
		}
	}

	return true;
}

/**
 * ice_dcb_noncontig_cfg - Configure DCB for non-contiguous TCs
 * @pf: pointer to the PF struct
 *
 * If non-contiguous TCs, then configure SW DCB with TC0 and ETS non-willing
 */
static int ice_dcb_noncontig_cfg(struct ice_pf *pf)
{
	struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->local_dcbx_cfg;
	struct device *dev = ice_pf_to_dev(pf);
	int ret;

	/* Configure SW DCB default with ETS non-willing */
	ret = ice_dcb_sw_dflt_cfg(pf, false, true);
	if (ret) {
		dev_err(dev, "Failed to set local DCB config %d\n", ret);
		return ret;
	}

	/* Reconfigure with ETS willing so that FW will send LLDP MIB event */
	dcbcfg->etscfg.willing = 1;
	ret = ice_set_dcb_cfg(pf->hw.port_info);
	if (ret)
		dev_err(dev, "Failed to set DCB to unwilling\n");

	return ret;
}

/**
 * ice_pf_dcb_recfg - Reconfigure all VEBs and VSIs
 * @pf: pointer to the PF struct
 *
 * Assumed caller has already disabled all VSIs before
 * calling this function. Reconfiguring DCB based on
 * local_dcbx_cfg.
 */
void ice_pf_dcb_recfg(struct ice_pf *pf)
{
	struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->local_dcbx_cfg;
	u8 tc_map = 0;
	int v, ret;

	/* Update each VSI */
	ice_for_each_vsi(pf, v) {
		struct ice_vsi *vsi = pf->vsi[v];

		if (!vsi)
			continue;

		if (vsi->type == ICE_VSI_PF) {
			tc_map = ice_dcb_get_ena_tc(dcbcfg);

			/* If DCBX request non-contiguous TC, then configure
			 * default TC
			 */
			if (!ice_dcb_tc_contig(dcbcfg->etscfg.prio_table)) {
				tc_map = ICE_DFLT_TRAFFIC_CLASS;
				ice_dcb_noncontig_cfg(pf);
			}
		} else {
			tc_map = ICE_DFLT_TRAFFIC_CLASS;
		}

		ret = ice_vsi_cfg_tc(vsi, tc_map);
		if (ret) {
			dev_err(ice_pf_to_dev(pf), "Failed to config TC for VSI index: %d\n",
				vsi->idx);
			continue;
		}

		ice_vsi_map_rings_to_vectors(vsi);
		if (vsi->type == ICE_VSI_PF)
			ice_dcbnl_set_all(vsi);
	}
}

/**
 * ice_init_pf_dcb - initialize DCB for a PF
 * @pf: PF to initialize DCB for
 * @locked: Was function called with RTNL held
 */
int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_port_info *port_info;
	struct ice_hw *hw = &pf->hw;
	int err;

	port_info = hw->port_info;

	err = ice_init_dcb(hw, false);
	if (err && !port_info->is_sw_lldp) {
		dev_err(dev, "Error initializing DCB %d\n", err);
		goto dcb_init_err;
	}

	dev_info(dev, "DCB is enabled in the hardware, max number of TCs supported on this port are %d\n",
		 pf->hw.func_caps.common_cap.maxtc);
	if (err) {
		struct ice_vsi *pf_vsi;

		/* FW LLDP is disabled, activate SW DCBX/LLDP mode */
		dev_info(dev, "FW LLDP is disabled, DCBx/LLDP in SW mode.\n");
		clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags);
		err = ice_dcb_sw_dflt_cfg(pf, true, locked);
		if (err) {
			dev_err(dev, "Failed to set local DCB config %d\n",
				err);
			err = -EIO;
			goto dcb_init_err;
		}

		/* If the FW DCBX engine is not running then Rx LLDP packets
		 * need to be redirected up the stack.
		 */
		pf_vsi = ice_get_main_vsi(pf);
		if (!pf_vsi) {
			dev_err(dev, "Failed to set local DCB config\n");
			err = -EIO;
			goto dcb_init_err;
		}

		ice_cfg_sw_lldp(pf_vsi, false, true);

		pf->dcbx_cap = ice_dcb_get_mode(port_info, true);
		return 0;
	}

	set_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags);

	/* DCBX/LLDP enabled in FW, set DCBNL mode advertisement */
	pf->dcbx_cap = ice_dcb_get_mode(port_info, false);

	err = ice_dcb_init_cfg(pf, locked);
	if (err)
		goto dcb_init_err;

	return err;

dcb_init_err:
	dev_err(dev, "DCB init failed\n");
	return err;
}

/**
 * ice_update_dcb_stats - Update DCB stats counters
 * @pf: PF whose stats needs to be updated
 */
void ice_update_dcb_stats(struct ice_pf *pf)
{
	struct ice_hw_port_stats *prev_ps, *cur_ps;
	struct ice_hw *hw = &pf->hw;
	u8 port;
	int i;

	port = hw->port_info->lport;
	prev_ps = &pf->stats_prev;
	cur_ps = &pf->stats;

	for (i = 0; i < 8; i++) {
		ice_stat_update32(hw, GLPRT_PXOFFRXC(port, i),
				  pf->stat_prev_loaded,
				  &prev_ps->priority_xoff_rx[i],
				  &cur_ps->priority_xoff_rx[i]);
		ice_stat_update32(hw, GLPRT_PXONRXC(port, i),
				  pf->stat_prev_loaded,
				  &prev_ps->priority_xon_rx[i],
				  &cur_ps->priority_xon_rx[i]);
		ice_stat_update32(hw, GLPRT_PXONTXC(port, i),
				  pf->stat_prev_loaded,
				  &prev_ps->priority_xon_tx[i],
				  &cur_ps->priority_xon_tx[i]);
		ice_stat_update32(hw, GLPRT_PXOFFTXC(port, i),
				  pf->stat_prev_loaded,
				  &prev_ps->priority_xoff_tx[i],
				  &cur_ps->priority_xoff_tx[i]);
		ice_stat_update32(hw, GLPRT_RXON2OFFCNT(port, i),
				  pf->stat_prev_loaded,
				  &prev_ps->priority_xon_2_xoff[i],
				  &cur_ps->priority_xon_2_xoff[i]);
	}
}

/**
 * ice_tx_prepare_vlan_flags_dcb - prepare VLAN tagging for DCB
 * @tx_ring: ring to send buffer on
 * @first: pointer to struct ice_tx_buf
 *
 * This should not be called if the outer VLAN is software offloaded as the VLAN
 * tag will already be configured with the correct ID and priority bits
 */
void
ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,
			      struct ice_tx_buf *first)
{
	struct sk_buff *skb = first->skb;

	if (!test_bit(ICE_FLAG_DCB_ENA, tx_ring->vsi->back->flags))
		return;

	/* Insert 802.1p priority into VLAN header */
	if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN) ||
	    skb->priority != TC_PRIO_CONTROL) {
		first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M;
		/* Mask the lower 3 bits to set the 802.1p priority */
		first->tx_flags |= (skb->priority & 0x7) <<
				   ICE_TX_FLAGS_VLAN_PR_S;
		/* if this is not already set it means a VLAN 0 + priority needs
		 * to be offloaded
		 */
		first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
	}
}

/**
 * ice_dcb_process_lldp_set_mib_change - Process MIB change
 * @pf: ptr to ice_pf
 * @event: pointer to the admin queue receive event
 */
void
ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
				    struct ice_rq_event_info *event)
{
	struct ice_aqc_port_ets_elem buf = { 0 };
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_aqc_lldp_get_mib *mib;
	struct ice_dcbx_cfg tmp_dcbx_cfg;
	bool need_reconfig = false;
	struct ice_port_info *pi;
	struct ice_vsi *pf_vsi;
	u8 mib_type;
	int ret;

	/* Not DCB capable or capability disabled */
	if (!(test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)))
		return;

	if (pf->dcbx_cap & DCB_CAP_DCBX_HOST) {
		dev_dbg(dev, "MIB Change Event in HOST mode\n");
		return;
	}

	pi = pf->hw.port_info;
	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
	/* Ignore if event is not for Nearest Bridge */
	mib_type = ((mib->type >> ICE_AQ_LLDP_BRID_TYPE_S) &
		    ICE_AQ_LLDP_BRID_TYPE_M);
	dev_dbg(dev, "LLDP event MIB bridge type 0x%x\n", mib_type);
	if (mib_type != ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID)
		return;

	/* Check MIB Type and return if event for Remote MIB update */
	mib_type = mib->type & ICE_AQ_LLDP_MIB_TYPE_M;
	dev_dbg(dev, "LLDP event mib type %s\n", mib_type ? "remote" : "local");
	if (mib_type == ICE_AQ_LLDP_MIB_REMOTE) {
		/* Update the remote cached instance and return */
		ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
					 ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID,
					 &pi->remote_dcbx_cfg);
		if (ret) {
			dev_err(dev, "Failed to get remote DCB config\n");
			return;
		}
	}

	mutex_lock(&pf->tc_mutex);

	/* store the old configuration */
	tmp_dcbx_cfg = pf->hw.port_info->local_dcbx_cfg;

	/* Reset the old DCBX configuration data */
	memset(&pi->local_dcbx_cfg, 0, sizeof(pi->local_dcbx_cfg));

	/* Get updated DCBX data from firmware */
	ret = ice_get_dcb_cfg(pf->hw.port_info);
	if (ret) {
		dev_err(dev, "Failed to get DCB config\n");
		goto out;
	}

	/* No change detected in DCBX configs */
	if (!memcmp(&tmp_dcbx_cfg, &pi->local_dcbx_cfg, sizeof(tmp_dcbx_cfg))) {
		dev_dbg(dev, "No change detected in DCBX configuration.\n");
		goto out;
	}

	pf->dcbx_cap = ice_dcb_get_mode(pi, false);

	need_reconfig = ice_dcb_need_recfg(pf, &tmp_dcbx_cfg,
					   &pi->local_dcbx_cfg);
	ice_dcbnl_flush_apps(pf, &tmp_dcbx_cfg, &pi->local_dcbx_cfg);
	if (!need_reconfig)
		goto out;

	/* Enable DCB tagging only when more than one TC */
	if (ice_dcb_get_num_tc(&pi->local_dcbx_cfg) > 1) {
		dev_dbg(dev, "DCB tagging enabled (num TC > 1)\n");
		set_bit(ICE_FLAG_DCB_ENA, pf->flags);
	} else {
		dev_dbg(dev, "DCB tagging disabled (num TC = 1)\n");
		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
	}

	pf_vsi = ice_get_main_vsi(pf);
	if (!pf_vsi) {
		dev_dbg(dev, "PF VSI doesn't exist\n");
		goto out;
	}

	rtnl_lock();
	ice_dis_vsi(pf_vsi, true);

	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
	if (ret) {
		dev_err(dev, "Query Port ETS failed\n");
		goto unlock_rtnl;
	}

	/* changes in configuration update VSI */
	ice_pf_dcb_recfg(pf);

	ice_ena_vsi(pf_vsi, true);
unlock_rtnl:
	rtnl_unlock();
out:
	mutex_unlock(&pf->tc_mutex);
}