summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ice/ice_sriov.c
blob: 588ad8696756defb6154022fe4fc9b7c75eed366 (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
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2018, Intel Corporation. */

#include "ice.h"
#include "ice_vf_lib_private.h"
#include "ice_base.h"
#include "ice_lib.h"
#include "ice_fltr.h"
#include "ice_dcb_lib.h"
#include "ice_flow.h"
#include "ice_eswitch.h"
#include "ice_virtchnl_allowlist.h"
#include "ice_flex_pipe.h"
#include "ice_vf_vsi_vlan_ops.h"
#include "ice_vlan.h"

/**
 * ice_free_vf_entries - Free all VF entries from the hash table
 * @pf: pointer to the PF structure
 *
 * Iterate over the VF hash table, removing and releasing all VF entries.
 * Called during VF teardown or as cleanup during failed VF initialization.
 */
static void ice_free_vf_entries(struct ice_pf *pf)
{
	struct ice_vfs *vfs = &pf->vfs;
	struct hlist_node *tmp;
	struct ice_vf *vf;
	unsigned int bkt;

	/* Remove all VFs from the hash table and release their main
	 * reference. Once all references to the VF are dropped, ice_put_vf()
	 * will call ice_release_vf which will remove the VF memory.
	 */
	lockdep_assert_held(&vfs->table_lock);

	hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) {
		hash_del_rcu(&vf->entry);
		ice_put_vf(vf);
	}
}

/**
 * ice_free_vf_res - Free a VF's resources
 * @vf: pointer to the VF info
 */
static void ice_free_vf_res(struct ice_vf *vf)
{
	struct ice_pf *pf = vf->pf;
	int i, last_vector_idx;

	/* First, disable VF's configuration API to prevent OS from
	 * accessing the VF's VSI after it's freed or invalidated.
	 */
	clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
	ice_vf_fdir_exit(vf);
	/* free VF control VSI */
	if (vf->ctrl_vsi_idx != ICE_NO_VSI)
		ice_vf_ctrl_vsi_release(vf);

	/* free VSI and disconnect it from the parent uplink */
	if (vf->lan_vsi_idx != ICE_NO_VSI) {
		ice_vf_vsi_release(vf);
		vf->num_mac = 0;
	}

	last_vector_idx = vf->first_vector_idx + pf->vfs.num_msix_per - 1;

	/* clear VF MDD event information */
	memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events));
	memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events));

	/* Disable interrupts so that VF starts in a known state */
	for (i = vf->first_vector_idx; i <= last_vector_idx; i++) {
		wr32(&pf->hw, GLINT_DYN_CTL(i), GLINT_DYN_CTL_CLEARPBA_M);
		ice_flush(&pf->hw);
	}
	/* reset some of the state variables keeping track of the resources */
	clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states);
	clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states);
}

/**
 * ice_dis_vf_mappings
 * @vf: pointer to the VF structure
 */
static void ice_dis_vf_mappings(struct ice_vf *vf)
{
	struct ice_pf *pf = vf->pf;
	struct ice_vsi *vsi;
	struct device *dev;
	int first, last, v;
	struct ice_hw *hw;

	hw = &pf->hw;
	vsi = ice_get_vf_vsi(vf);
	if (WARN_ON(!vsi))
		return;

	dev = ice_pf_to_dev(pf);
	wr32(hw, VPINT_ALLOC(vf->vf_id), 0);
	wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0);

	first = vf->first_vector_idx;
	last = first + pf->vfs.num_msix_per - 1;
	for (v = first; v <= last; v++) {
		u32 reg;

		reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) &
			GLINT_VECT2FUNC_IS_PF_M) |
		       ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) &
			GLINT_VECT2FUNC_PF_NUM_M));
		wr32(hw, GLINT_VECT2FUNC(v), reg);
	}

	if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG)
		wr32(hw, VPLAN_TX_QBASE(vf->vf_id), 0);
	else
		dev_err(dev, "Scattered mode for VF Tx queues is not yet implemented\n");

	if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG)
		wr32(hw, VPLAN_RX_QBASE(vf->vf_id), 0);
	else
		dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n");
}

/**
 * ice_sriov_free_msix_res - Reset/free any used MSIX resources
 * @pf: pointer to the PF structure
 *
 * Since no MSIX entries are taken from the pf->irq_tracker then just clear
 * the pf->sriov_base_vector.
 *
 * Returns 0 on success, and -EINVAL on error.
 */
static int ice_sriov_free_msix_res(struct ice_pf *pf)
{
	struct ice_res_tracker *res;

	if (!pf)
		return -EINVAL;

	res = pf->irq_tracker;
	if (!res)
		return -EINVAL;

	/* give back irq_tracker resources used */
	WARN_ON(pf->sriov_base_vector < res->num_entries);

	pf->sriov_base_vector = 0;

	return 0;
}

/**
 * ice_free_vfs - Free all VFs
 * @pf: pointer to the PF structure
 */
void ice_free_vfs(struct ice_pf *pf)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_vfs *vfs = &pf->vfs;
	struct ice_hw *hw = &pf->hw;
	struct ice_vf *vf;
	unsigned int bkt;

	if (!ice_has_vfs(pf))
		return;

	while (test_and_set_bit(ICE_VF_DIS, pf->state))
		usleep_range(1000, 2000);

	/* Disable IOV before freeing resources. This lets any VF drivers
	 * running in the host get themselves cleaned up before we yank
	 * the carpet out from underneath their feet.
	 */
	if (!pci_vfs_assigned(pf->pdev))
		pci_disable_sriov(pf->pdev);
	else
		dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n");

	mutex_lock(&vfs->table_lock);

	ice_eswitch_release(pf);

	ice_for_each_vf(pf, bkt, vf) {
		mutex_lock(&vf->cfg_lock);

		ice_dis_vf_qs(vf);

		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
			/* disable VF qp mappings and set VF disable state */
			ice_dis_vf_mappings(vf);
			set_bit(ICE_VF_STATE_DIS, vf->vf_states);
			ice_free_vf_res(vf);
		}

		if (!pci_vfs_assigned(pf->pdev)) {
			u32 reg_idx, bit_idx;

			reg_idx = (hw->func_caps.vf_base_id + vf->vf_id) / 32;
			bit_idx = (hw->func_caps.vf_base_id + vf->vf_id) % 32;
			wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
		}

		/* clear malicious info since the VF is getting released */
		list_del(&vf->mbx_info.list_entry);

		mutex_unlock(&vf->cfg_lock);
	}

	if (ice_sriov_free_msix_res(pf))
		dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n");

	vfs->num_qps_per = 0;
	ice_free_vf_entries(pf);

	mutex_unlock(&vfs->table_lock);

	clear_bit(ICE_VF_DIS, pf->state);
	clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags);
}

/**
 * ice_vf_vsi_setup - Set up a VF VSI
 * @vf: VF to setup VSI for
 *
 * Returns pointer to the successfully allocated VSI struct on success,
 * otherwise returns NULL on failure.
 */
static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf)
{
	struct ice_vsi_cfg_params params = {};
	struct ice_pf *pf = vf->pf;
	struct ice_vsi *vsi;

	params.type = ICE_VSI_VF;
	params.pi = ice_vf_get_port_info(vf);
	params.vf = vf;
	params.flags = ICE_VSI_FLAG_INIT;

	vsi = ice_vsi_setup(pf, &params);

	if (!vsi) {
		dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n");
		ice_vf_invalidate_vsi(vf);
		return NULL;
	}

	vf->lan_vsi_idx = vsi->idx;
	vf->lan_vsi_num = vsi->vsi_num;

	return vsi;
}

/**
 * ice_calc_vf_first_vector_idx - Calculate MSIX vector index in the PF space
 * @pf: pointer to PF structure
 * @vf: pointer to VF that the first MSIX vector index is being calculated for
 *
 * This returns the first MSIX vector index in PF space that is used by this VF.
 * This index is used when accessing PF relative registers such as
 * GLINT_VECT2FUNC and GLINT_DYN_CTL.
 * This will always be the OICR index in the AVF driver so any functionality
 * using vf->first_vector_idx for queue configuration will have to increment by
 * 1 to avoid meddling with the OICR index.
 */
static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf)
{
	return pf->sriov_base_vector + vf->vf_id * pf->vfs.num_msix_per;
}

/**
 * ice_ena_vf_msix_mappings - enable VF MSIX mappings in hardware
 * @vf: VF to enable MSIX mappings for
 *
 * Some of the registers need to be indexed/configured using hardware global
 * device values and other registers need 0-based values, which represent PF
 * based values.
 */
static void ice_ena_vf_msix_mappings(struct ice_vf *vf)
{
	int device_based_first_msix, device_based_last_msix;
	int pf_based_first_msix, pf_based_last_msix, v;
	struct ice_pf *pf = vf->pf;
	int device_based_vf_id;
	struct ice_hw *hw;
	u32 reg;

	hw = &pf->hw;
	pf_based_first_msix = vf->first_vector_idx;
	pf_based_last_msix = (pf_based_first_msix + pf->vfs.num_msix_per) - 1;

	device_based_first_msix = pf_based_first_msix +
		pf->hw.func_caps.common_cap.msix_vector_first_id;
	device_based_last_msix =
		(device_based_first_msix + pf->vfs.num_msix_per) - 1;
	device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id;

	reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) &
		VPINT_ALLOC_FIRST_M) |
	       ((device_based_last_msix << VPINT_ALLOC_LAST_S) &
		VPINT_ALLOC_LAST_M) | VPINT_ALLOC_VALID_M);
	wr32(hw, VPINT_ALLOC(vf->vf_id), reg);

	reg = (((device_based_first_msix << VPINT_ALLOC_PCI_FIRST_S)
		 & VPINT_ALLOC_PCI_FIRST_M) |
	       ((device_based_last_msix << VPINT_ALLOC_PCI_LAST_S) &
		VPINT_ALLOC_PCI_LAST_M) | VPINT_ALLOC_PCI_VALID_M);
	wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg);

	/* map the interrupts to its functions */
	for (v = pf_based_first_msix; v <= pf_based_last_msix; v++) {
		reg = (((device_based_vf_id << GLINT_VECT2FUNC_VF_NUM_S) &
			GLINT_VECT2FUNC_VF_NUM_M) |
		       ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) &
			GLINT_VECT2FUNC_PF_NUM_M));
		wr32(hw, GLINT_VECT2FUNC(v), reg);
	}

	/* Map mailbox interrupt to VF MSI-X vector 0 */
	wr32(hw, VPINT_MBX_CTL(device_based_vf_id), VPINT_MBX_CTL_CAUSE_ENA_M);
}

/**
 * ice_ena_vf_q_mappings - enable Rx/Tx queue mappings for a VF
 * @vf: VF to enable the mappings for
 * @max_txq: max Tx queues allowed on the VF's VSI
 * @max_rxq: max Rx queues allowed on the VF's VSI
 */
static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq)
{
	struct device *dev = ice_pf_to_dev(vf->pf);
	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
	struct ice_hw *hw = &vf->pf->hw;
	u32 reg;

	if (WARN_ON(!vsi))
		return;

	/* set regardless of mapping mode */
	wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), VPLAN_TXQ_MAPENA_TX_ENA_M);

	/* VF Tx queues allocation */
	if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) {
		/* set the VF PF Tx queue range
		 * VFNUMQ value should be set to (number of queues - 1). A value
		 * of 0 means 1 queue and a value of 255 means 256 queues
		 */
		reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) &
			VPLAN_TX_QBASE_VFFIRSTQ_M) |
		       (((max_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) &
			VPLAN_TX_QBASE_VFNUMQ_M));
		wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg);
	} else {
		dev_err(dev, "Scattered mode for VF Tx queues is not yet implemented\n");
	}

	/* set regardless of mapping mode */
	wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), VPLAN_RXQ_MAPENA_RX_ENA_M);

	/* VF Rx queues allocation */
	if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) {
		/* set the VF PF Rx queue range
		 * VFNUMQ value should be set to (number of queues - 1). A value
		 * of 0 means 1 queue and a value of 255 means 256 queues
		 */
		reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) &
			VPLAN_RX_QBASE_VFFIRSTQ_M) |
		       (((max_rxq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) &
			VPLAN_RX_QBASE_VFNUMQ_M));
		wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg);
	} else {
		dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n");
	}
}

/**
 * ice_ena_vf_mappings - enable VF MSIX and queue mapping
 * @vf: pointer to the VF structure
 */
static void ice_ena_vf_mappings(struct ice_vf *vf)
{
	struct ice_vsi *vsi = ice_get_vf_vsi(vf);

	if (WARN_ON(!vsi))
		return;

	ice_ena_vf_msix_mappings(vf);
	ice_ena_vf_q_mappings(vf, vsi->alloc_txq, vsi->alloc_rxq);
}

/**
 * ice_calc_vf_reg_idx - Calculate the VF's register index in the PF space
 * @vf: VF to calculate the register index for
 * @q_vector: a q_vector associated to the VF
 */
int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
{
	struct ice_pf *pf;

	if (!vf || !q_vector)
		return -EINVAL;

	pf = vf->pf;

	/* always add one to account for the OICR being the first MSIX */
	return pf->sriov_base_vector + pf->vfs.num_msix_per * vf->vf_id +
		q_vector->v_idx + 1;
}

/**
 * ice_get_max_valid_res_idx - Get the max valid resource index
 * @res: pointer to the resource to find the max valid index for
 *
 * Start from the end of the ice_res_tracker and return right when we find the
 * first res->list entry with the ICE_RES_VALID_BIT set. This function is only
 * valid for SR-IOV because it is the only consumer that manipulates the
 * res->end and this is always called when res->end is set to res->num_entries.
 */
static int ice_get_max_valid_res_idx(struct ice_res_tracker *res)
{
	int i;

	if (!res)
		return -EINVAL;

	for (i = res->num_entries - 1; i >= 0; i--)
		if (res->list[i] & ICE_RES_VALID_BIT)
			return i;

	return 0;
}

/**
 * ice_sriov_set_msix_res - Set any used MSIX resources
 * @pf: pointer to PF structure
 * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs
 *
 * This function allows SR-IOV resources to be taken from the end of the PF's
 * allowed HW MSIX vectors so that the irq_tracker will not be affected. We
 * just set the pf->sriov_base_vector and return success.
 *
 * If there are not enough resources available, return an error. This should
 * always be caught by ice_set_per_vf_res().
 *
 * Return 0 on success, and -EINVAL when there are not enough MSIX vectors
 * in the PF's space available for SR-IOV.
 */
static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed)
{
	u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
	int vectors_used = pf->irq_tracker->num_entries;
	int sriov_base_vector;

	sriov_base_vector = total_vectors - num_msix_needed;

	/* make sure we only grab irq_tracker entries from the list end and
	 * that we have enough available MSIX vectors
	 */
	if (sriov_base_vector < vectors_used)
		return -EINVAL;

	pf->sriov_base_vector = sriov_base_vector;

	return 0;
}

/**
 * ice_set_per_vf_res - check if vectors and queues are available
 * @pf: pointer to the PF structure
 * @num_vfs: the number of SR-IOV VFs being configured
 *
 * First, determine HW interrupts from common pool. If we allocate fewer VFs, we
 * get more vectors and can enable more queues per VF. Note that this does not
 * grab any vectors from the SW pool already allocated. Also note, that all
 * vector counts include one for each VF's miscellaneous interrupt vector
 * (i.e. OICR).
 *
 * Minimum VFs - 2 vectors, 1 queue pair
 * Small VFs - 5 vectors, 4 queue pairs
 * Medium VFs - 17 vectors, 16 queue pairs
 *
 * Second, determine number of queue pairs per VF by starting with a pre-defined
 * maximum each VF supports. If this is not possible, then we adjust based on
 * queue pairs available on the device.
 *
 * Lastly, set queue and MSI-X VF variables tracked by the PF so it can be used
 * by each VF during VF initialization and reset.
 */
static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
{
	int max_valid_res_idx = ice_get_max_valid_res_idx(pf->irq_tracker);
	u16 num_msix_per_vf, num_txq, num_rxq, avail_qs;
	int msix_avail_per_vf, msix_avail_for_sriov;
	struct device *dev = ice_pf_to_dev(pf);
	int err;

	lockdep_assert_held(&pf->vfs.table_lock);

	if (!num_vfs)
		return -EINVAL;

	if (max_valid_res_idx < 0)
		return -ENOSPC;

	/* determine MSI-X resources per VF */
	msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors -
		pf->irq_tracker->num_entries;
	msix_avail_per_vf = msix_avail_for_sriov / num_vfs;
	if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) {
		num_msix_per_vf = ICE_NUM_VF_MSIX_MED;
	} else if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_SMALL) {
		num_msix_per_vf = ICE_NUM_VF_MSIX_SMALL;
	} else if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MULTIQ_MIN) {
		num_msix_per_vf = ICE_NUM_VF_MSIX_MULTIQ_MIN;
	} else if (msix_avail_per_vf >= ICE_MIN_INTR_PER_VF) {
		num_msix_per_vf = ICE_MIN_INTR_PER_VF;
	} else {
		dev_err(dev, "Only %d MSI-X interrupts available for SR-IOV. Not enough to support minimum of %d MSI-X interrupts per VF for %d VFs\n",
			msix_avail_for_sriov, ICE_MIN_INTR_PER_VF,
			num_vfs);
		return -ENOSPC;
	}

	num_txq = min_t(u16, num_msix_per_vf - ICE_NONQ_VECS_VF,
			ICE_MAX_RSS_QS_PER_VF);
	avail_qs = ice_get_avail_txq_count(pf) / num_vfs;
	if (!avail_qs)
		num_txq = 0;
	else if (num_txq > avail_qs)
		num_txq = rounddown_pow_of_two(avail_qs);

	num_rxq = min_t(u16, num_msix_per_vf - ICE_NONQ_VECS_VF,
			ICE_MAX_RSS_QS_PER_VF);
	avail_qs = ice_get_avail_rxq_count(pf) / num_vfs;
	if (!avail_qs)
		num_rxq = 0;
	else if (num_rxq > avail_qs)
		num_rxq = rounddown_pow_of_two(avail_qs);

	if (num_txq < ICE_MIN_QS_PER_VF || num_rxq < ICE_MIN_QS_PER_VF) {
		dev_err(dev, "Not enough queues to support minimum of %d queue pairs per VF for %d VFs\n",
			ICE_MIN_QS_PER_VF, num_vfs);
		return -ENOSPC;
	}

	err = ice_sriov_set_msix_res(pf, num_msix_per_vf * num_vfs);
	if (err) {
		dev_err(dev, "Unable to set MSI-X resources for %d VFs, err %d\n",
			num_vfs, err);
		return err;
	}

	/* only allow equal Tx/Rx queue count (i.e. queue pairs) */
	pf->vfs.num_qps_per = min_t(int, num_txq, num_rxq);
	pf->vfs.num_msix_per = num_msix_per_vf;
	dev_info(dev, "Enabling %d VFs with %d vectors and %d queues per VF\n",
		 num_vfs, pf->vfs.num_msix_per, pf->vfs.num_qps_per);

	return 0;
}

/**
 * ice_init_vf_vsi_res - initialize/setup VF VSI resources
 * @vf: VF to initialize/setup the VSI for
 *
 * This function creates a VSI for the VF, adds a VLAN 0 filter, and sets up the
 * VF VSI's broadcast filter and is only used during initial VF creation.
 */
static int ice_init_vf_vsi_res(struct ice_vf *vf)
{
	struct ice_pf *pf = vf->pf;
	struct ice_vsi *vsi;
	int err;

	vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf);

	vsi = ice_vf_vsi_setup(vf);
	if (!vsi)
		return -ENOMEM;

	err = ice_vf_init_host_cfg(vf, vsi);
	if (err)
		goto release_vsi;

	return 0;

release_vsi:
	ice_vf_vsi_release(vf);
	return err;
}

/**
 * ice_start_vfs - start VFs so they are ready to be used by SR-IOV
 * @pf: PF the VFs are associated with
 */
static int ice_start_vfs(struct ice_pf *pf)
{
	struct ice_hw *hw = &pf->hw;
	unsigned int bkt, it_cnt;
	struct ice_vf *vf;
	int retval;

	lockdep_assert_held(&pf->vfs.table_lock);

	it_cnt = 0;
	ice_for_each_vf(pf, bkt, vf) {
		vf->vf_ops->clear_reset_trigger(vf);

		retval = ice_init_vf_vsi_res(vf);
		if (retval) {
			dev_err(ice_pf_to_dev(pf), "Failed to initialize VSI resources for VF %d, error %d\n",
				vf->vf_id, retval);
			goto teardown;
		}

		set_bit(ICE_VF_STATE_INIT, vf->vf_states);
		ice_ena_vf_mappings(vf);
		wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE);
		it_cnt++;
	}

	ice_flush(hw);
	return 0;

teardown:
	ice_for_each_vf(pf, bkt, vf) {
		if (it_cnt == 0)
			break;

		ice_dis_vf_mappings(vf);
		ice_vf_vsi_release(vf);
		it_cnt--;
	}

	return retval;
}

/**
 * ice_sriov_free_vf - Free VF memory after all references are dropped
 * @vf: pointer to VF to free
 *
 * Called by ice_put_vf through ice_release_vf once the last reference to a VF
 * structure has been dropped.
 */
static void ice_sriov_free_vf(struct ice_vf *vf)
{
	mutex_destroy(&vf->cfg_lock);

	kfree_rcu(vf, rcu);
}

/**
 * ice_sriov_clear_reset_state - clears VF Reset status register
 * @vf: the vf to configure
 */
static void ice_sriov_clear_reset_state(struct ice_vf *vf)
{
	struct ice_hw *hw = &vf->pf->hw;

	/* Clear the reset status register so that VF immediately sees that
	 * the device is resetting, even if hardware hasn't yet gotten around
	 * to clearing VFGEN_RSTAT for us.
	 */
	wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_INPROGRESS);
}

/**
 * ice_sriov_clear_mbx_register - clears SRIOV VF's mailbox registers
 * @vf: the vf to configure
 */
static void ice_sriov_clear_mbx_register(struct ice_vf *vf)
{
	struct ice_pf *pf = vf->pf;

	wr32(&pf->hw, VF_MBX_ARQLEN(vf->vf_id), 0);
	wr32(&pf->hw, VF_MBX_ATQLEN(vf->vf_id), 0);
}

/**
 * ice_sriov_trigger_reset_register - trigger VF reset for SRIOV VF
 * @vf: pointer to VF structure
 * @is_vflr: true if reset occurred due to VFLR
 *
 * Trigger and cleanup after a VF reset for a SR-IOV VF.
 */
static void ice_sriov_trigger_reset_register(struct ice_vf *vf, bool is_vflr)
{
	struct ice_pf *pf = vf->pf;
	u32 reg, reg_idx, bit_idx;
	unsigned int vf_abs_id, i;
	struct device *dev;
	struct ice_hw *hw;

	dev = ice_pf_to_dev(pf);
	hw = &pf->hw;
	vf_abs_id = vf->vf_id + hw->func_caps.vf_base_id;

	/* In the case of a VFLR, HW has already reset the VF and we just need
	 * to clean up. Otherwise we must first trigger the reset using the
	 * VFRTRIG register.
	 */
	if (!is_vflr) {
		reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id));
		reg |= VPGEN_VFRTRIG_VFSWR_M;
		wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg);
	}

	/* clear the VFLR bit in GLGEN_VFLRSTAT */
	reg_idx = (vf_abs_id) / 32;
	bit_idx = (vf_abs_id) % 32;
	wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
	ice_flush(hw);

	wr32(hw, PF_PCI_CIAA,
	     VF_DEVICE_STATUS | (vf_abs_id << PF_PCI_CIAA_VF_NUM_S));
	for (i = 0; i < ICE_PCI_CIAD_WAIT_COUNT; i++) {
		reg = rd32(hw, PF_PCI_CIAD);
		/* no transactions pending so stop polling */
		if ((reg & VF_TRANS_PENDING_M) == 0)
			break;

		dev_err(dev, "VF %u PCI transactions stuck\n", vf->vf_id);
		udelay(ICE_PCI_CIAD_WAIT_DELAY_US);
	}
}

/**
 * ice_sriov_poll_reset_status - poll SRIOV VF reset status
 * @vf: pointer to VF structure
 *
 * Returns true when reset is successful, else returns false
 */
static bool ice_sriov_poll_reset_status(struct ice_vf *vf)
{
	struct ice_pf *pf = vf->pf;
	unsigned int i;
	u32 reg;

	for (i = 0; i < 10; i++) {
		/* VF reset requires driver to first reset the VF and then
		 * poll the status register to make sure that the reset
		 * completed successfully.
		 */
		reg = rd32(&pf->hw, VPGEN_VFRSTAT(vf->vf_id));
		if (reg & VPGEN_VFRSTAT_VFRD_M)
			return true;

		/* only sleep if the reset is not done */
		usleep_range(10, 20);
	}
	return false;
}

/**
 * ice_sriov_clear_reset_trigger - enable VF to access hardware
 * @vf: VF to enabled hardware access for
 */
static void ice_sriov_clear_reset_trigger(struct ice_vf *vf)
{
	struct ice_hw *hw = &vf->pf->hw;
	u32 reg;

	reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id));
	reg &= ~VPGEN_VFRTRIG_VFSWR_M;
	wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg);
	ice_flush(hw);
}

/**
 * ice_sriov_create_vsi - Create a new VSI for a VF
 * @vf: VF to create the VSI for
 *
 * This is called by ice_vf_recreate_vsi to create the new VSI after the old
 * VSI has been released.
 */
static int ice_sriov_create_vsi(struct ice_vf *vf)
{
	struct ice_vsi *vsi;

	vsi = ice_vf_vsi_setup(vf);
	if (!vsi)
		return -ENOMEM;

	return 0;
}

/**
 * ice_sriov_post_vsi_rebuild - tasks to do after the VF's VSI have been rebuilt
 * @vf: VF to perform tasks on
 */
static void ice_sriov_post_vsi_rebuild(struct ice_vf *vf)
{
	ice_ena_vf_mappings(vf);
	wr32(&vf->pf->hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE);
}

static const struct ice_vf_ops ice_sriov_vf_ops = {
	.reset_type = ICE_VF_RESET,
	.free = ice_sriov_free_vf,
	.clear_reset_state = ice_sriov_clear_reset_state,
	.clear_mbx_register = ice_sriov_clear_mbx_register,
	.trigger_reset_register = ice_sriov_trigger_reset_register,
	.poll_reset_status = ice_sriov_poll_reset_status,
	.clear_reset_trigger = ice_sriov_clear_reset_trigger,
	.irq_close = NULL,
	.create_vsi = ice_sriov_create_vsi,
	.post_vsi_rebuild = ice_sriov_post_vsi_rebuild,
};

/**
 * ice_create_vf_entries - Allocate and insert VF entries
 * @pf: pointer to the PF structure
 * @num_vfs: the number of VFs to allocate
 *
 * Allocate new VF entries and insert them into the hash table. Set some
 * basic default fields for initializing the new VFs.
 *
 * After this function exits, the hash table will have num_vfs entries
 * inserted.
 *
 * Returns 0 on success or an integer error code on failure.
 */
static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs)
{
	struct ice_vfs *vfs = &pf->vfs;
	struct ice_vf *vf;
	u16 vf_id;
	int err;

	lockdep_assert_held(&vfs->table_lock);

	for (vf_id = 0; vf_id < num_vfs; vf_id++) {
		vf = kzalloc(sizeof(*vf), GFP_KERNEL);
		if (!vf) {
			err = -ENOMEM;
			goto err_free_entries;
		}
		kref_init(&vf->refcnt);

		vf->pf = pf;
		vf->vf_id = vf_id;

		/* set sriov vf ops for VFs created during SRIOV flow */
		vf->vf_ops = &ice_sriov_vf_ops;

		ice_initialize_vf_entry(vf);

		vf->vf_sw_id = pf->first_sw;

		hash_add_rcu(vfs->table, &vf->entry, vf_id);
	}

	return 0;

err_free_entries:
	ice_free_vf_entries(pf);
	return err;
}

/**
 * ice_ena_vfs - enable VFs so they are ready to be used
 * @pf: pointer to the PF structure
 * @num_vfs: number of VFs to enable
 */
static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_hw *hw = &pf->hw;
	int ret;

	/* Disable global interrupt 0 so we don't try to handle the VFLR. */
	wr32(hw, GLINT_DYN_CTL(pf->oicr_idx),
	     ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
	set_bit(ICE_OICR_INTR_DIS, pf->state);
	ice_flush(hw);

	ret = pci_enable_sriov(pf->pdev, num_vfs);
	if (ret)
		goto err_unroll_intr;

	mutex_lock(&pf->vfs.table_lock);

	ret = ice_set_per_vf_res(pf, num_vfs);
	if (ret) {
		dev_err(dev, "Not enough resources for %d VFs, err %d. Try with fewer number of VFs\n",
			num_vfs, ret);
		goto err_unroll_sriov;
	}

	ret = ice_create_vf_entries(pf, num_vfs);
	if (ret) {
		dev_err(dev, "Failed to allocate VF entries for %d VFs\n",
			num_vfs);
		goto err_unroll_sriov;
	}

	ret = ice_start_vfs(pf);
	if (ret) {
		dev_err(dev, "Failed to start %d VFs, err %d\n", num_vfs, ret);
		ret = -EAGAIN;
		goto err_unroll_vf_entries;
	}

	clear_bit(ICE_VF_DIS, pf->state);

	ret = ice_eswitch_configure(pf);
	if (ret) {
		dev_err(dev, "Failed to configure eswitch, err %d\n", ret);
		goto err_unroll_sriov;
	}

	/* rearm global interrupts */
	if (test_and_clear_bit(ICE_OICR_INTR_DIS, pf->state))
		ice_irq_dynamic_ena(hw, NULL, NULL);

	mutex_unlock(&pf->vfs.table_lock);

	return 0;

err_unroll_vf_entries:
	ice_free_vf_entries(pf);
err_unroll_sriov:
	mutex_unlock(&pf->vfs.table_lock);
	pci_disable_sriov(pf->pdev);
err_unroll_intr:
	/* rearm interrupts here */
	ice_irq_dynamic_ena(hw, NULL, NULL);
	clear_bit(ICE_OICR_INTR_DIS, pf->state);
	return ret;
}

/**
 * ice_pci_sriov_ena - Enable or change number of VFs
 * @pf: pointer to the PF structure
 * @num_vfs: number of VFs to allocate
 *
 * Returns 0 on success and negative on failure
 */
static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs)
{
	int pre_existing_vfs = pci_num_vf(pf->pdev);
	struct device *dev = ice_pf_to_dev(pf);
	int err;

	if (pre_existing_vfs && pre_existing_vfs != num_vfs)
		ice_free_vfs(pf);
	else if (pre_existing_vfs && pre_existing_vfs == num_vfs)
		return 0;

	if (num_vfs > pf->vfs.num_supported) {
		dev_err(dev, "Can't enable %d VFs, max VFs supported is %d\n",
			num_vfs, pf->vfs.num_supported);
		return -EOPNOTSUPP;
	}

	dev_info(dev, "Enabling %d VFs\n", num_vfs);
	err = ice_ena_vfs(pf, num_vfs);
	if (err) {
		dev_err(dev, "Failed to enable SR-IOV: %d\n", err);
		return err;
	}

	set_bit(ICE_FLAG_SRIOV_ENA, pf->flags);
	return 0;
}

/**
 * ice_check_sriov_allowed - check if SR-IOV is allowed based on various checks
 * @pf: PF to enabled SR-IOV on
 */
static int ice_check_sriov_allowed(struct ice_pf *pf)
{
	struct device *dev = ice_pf_to_dev(pf);

	if (!test_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags)) {
		dev_err(dev, "This device is not capable of SR-IOV\n");
		return -EOPNOTSUPP;
	}

	if (ice_is_safe_mode(pf)) {
		dev_err(dev, "SR-IOV cannot be configured - Device is in Safe Mode\n");
		return -EOPNOTSUPP;
	}

	if (!ice_pf_state_is_nominal(pf)) {
		dev_err(dev, "Cannot enable SR-IOV, device not ready\n");
		return -EBUSY;
	}

	return 0;
}

/**
 * ice_sriov_configure - Enable or change number of VFs via sysfs
 * @pdev: pointer to a pci_dev structure
 * @num_vfs: number of VFs to allocate or 0 to free VFs
 *
 * This function is called when the user updates the number of VFs in sysfs. On
 * success return whatever num_vfs was set to by the caller. Return negative on
 * failure.
 */
int ice_sriov_configure(struct pci_dev *pdev, int num_vfs)
{
	struct ice_pf *pf = pci_get_drvdata(pdev);
	struct device *dev = ice_pf_to_dev(pf);
	int err;

	err = ice_check_sriov_allowed(pf);
	if (err)
		return err;

	if (!num_vfs) {
		if (!pci_vfs_assigned(pdev)) {
			ice_free_vfs(pf);
			if (pf->lag)
				ice_enable_lag(pf->lag);
			return 0;
		}

		dev_err(dev, "can't free VFs because some are assigned to VMs.\n");
		return -EBUSY;
	}

	err = ice_pci_sriov_ena(pf, num_vfs);
	if (err)
		return err;

	if (pf->lag)
		ice_disable_lag(pf->lag);
	return num_vfs;
}

/**
 * ice_process_vflr_event - Free VF resources via IRQ calls
 * @pf: pointer to the PF structure
 *
 * called from the VFLR IRQ handler to
 * free up VF resources and state variables
 */
void ice_process_vflr_event(struct ice_pf *pf)
{
	struct ice_hw *hw = &pf->hw;
	struct ice_vf *vf;
	unsigned int bkt;
	u32 reg;

	if (!test_and_clear_bit(ICE_VFLR_EVENT_PENDING, pf->state) ||
	    !ice_has_vfs(pf))
		return;

	mutex_lock(&pf->vfs.table_lock);
	ice_for_each_vf(pf, bkt, vf) {
		u32 reg_idx, bit_idx;

		reg_idx = (hw->func_caps.vf_base_id + vf->vf_id) / 32;
		bit_idx = (hw->func_caps.vf_base_id + vf->vf_id) % 32;
		/* read GLGEN_VFLRSTAT register to find out the flr VFs */
		reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx));
		if (reg & BIT(bit_idx))
			/* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */
			ice_reset_vf(vf, ICE_VF_RESET_VFLR | ICE_VF_RESET_LOCK);
	}
	mutex_unlock(&pf->vfs.table_lock);
}

/**
 * ice_get_vf_from_pfq - get the VF who owns the PF space queue passed in
 * @pf: PF used to index all VFs
 * @pfq: queue index relative to the PF's function space
 *
 * If no VF is found who owns the pfq then return NULL, otherwise return a
 * pointer to the VF who owns the pfq
 *
 * If this function returns non-NULL, it acquires a reference count of the VF
 * structure. The caller is responsible for calling ice_put_vf() to drop this
 * reference.
 */
static struct ice_vf *ice_get_vf_from_pfq(struct ice_pf *pf, u16 pfq)
{
	struct ice_vf *vf;
	unsigned int bkt;

	rcu_read_lock();
	ice_for_each_vf_rcu(pf, bkt, vf) {
		struct ice_vsi *vsi;
		u16 rxq_idx;

		vsi = ice_get_vf_vsi(vf);
		if (!vsi)
			continue;

		ice_for_each_rxq(vsi, rxq_idx)
			if (vsi->rxq_map[rxq_idx] == pfq) {
				struct ice_vf *found;

				if (kref_get_unless_zero(&vf->refcnt))
					found = vf;
				else
					found = NULL;
				rcu_read_unlock();
				return found;
			}
	}
	rcu_read_unlock();

	return NULL;
}

/**
 * ice_globalq_to_pfq - convert from global queue index to PF space queue index
 * @pf: PF used for conversion
 * @globalq: global queue index used to convert to PF space queue index
 */
static u32 ice_globalq_to_pfq(struct ice_pf *pf, u32 globalq)
{
	return globalq - pf->hw.func_caps.common_cap.rxq_first_id;
}

/**
 * ice_vf_lan_overflow_event - handle LAN overflow event for a VF
 * @pf: PF that the LAN overflow event happened on
 * @event: structure holding the event information for the LAN overflow event
 *
 * Determine if the LAN overflow event was caused by a VF queue. If it was not
 * caused by a VF, do nothing. If a VF caused this LAN overflow event trigger a
 * reset on the offending VF.
 */
void
ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event)
{
	u32 gldcb_rtctq, queue;
	struct ice_vf *vf;

	gldcb_rtctq = le32_to_cpu(event->desc.params.lan_overflow.prtdcb_ruptq);
	dev_dbg(ice_pf_to_dev(pf), "GLDCB_RTCTQ: 0x%08x\n", gldcb_rtctq);

	/* event returns device global Rx queue number */
	queue = (gldcb_rtctq & GLDCB_RTCTQ_RXQNUM_M) >>
		GLDCB_RTCTQ_RXQNUM_S;

	vf = ice_get_vf_from_pfq(pf, ice_globalq_to_pfq(pf, queue));
	if (!vf)
		return;

	ice_reset_vf(vf, ICE_VF_RESET_NOTIFY | ICE_VF_RESET_LOCK);
	ice_put_vf(vf);
}

/**
 * ice_set_vf_spoofchk
 * @netdev: network interface device structure
 * @vf_id: VF identifier
 * @ena: flag to enable or disable feature
 *
 * Enable or disable VF spoof checking
 */
int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_pf *pf = np->vsi->back;
	struct ice_vsi *vf_vsi;
	struct device *dev;
	struct ice_vf *vf;
	int ret;

	dev = ice_pf_to_dev(pf);

	vf = ice_get_vf_by_id(pf, vf_id);
	if (!vf)
		return -EINVAL;

	ret = ice_check_vf_ready_for_reset(vf);
	if (ret)
		goto out_put_vf;

	vf_vsi = ice_get_vf_vsi(vf);
	if (!vf_vsi) {
		netdev_err(netdev, "VSI %d for VF %d is null\n",
			   vf->lan_vsi_idx, vf->vf_id);
		ret = -EINVAL;
		goto out_put_vf;
	}

	if (vf_vsi->type != ICE_VSI_VF) {
		netdev_err(netdev, "Type %d of VSI %d for VF %d is no ICE_VSI_VF\n",
			   vf_vsi->type, vf_vsi->vsi_num, vf->vf_id);
		ret = -ENODEV;
		goto out_put_vf;
	}

	if (ena == vf->spoofchk) {
		dev_dbg(dev, "VF spoofchk already %s\n", ena ? "ON" : "OFF");
		ret = 0;
		goto out_put_vf;
	}

	ret = ice_vsi_apply_spoofchk(vf_vsi, ena);
	if (ret)
		dev_err(dev, "Failed to set spoofchk %s for VF %d VSI %d\n error %d\n",
			ena ? "ON" : "OFF", vf->vf_id, vf_vsi->vsi_num, ret);
	else
		vf->spoofchk = ena;

out_put_vf:
	ice_put_vf(vf);
	return ret;
}

/**
 * ice_get_vf_cfg
 * @netdev: network interface device structure
 * @vf_id: VF identifier
 * @ivi: VF configuration structure
 *
 * return VF configuration
 */
int
ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi)
{
	struct ice_pf *pf = ice_netdev_to_pf(netdev);
	struct ice_vf *vf;
	int ret;

	vf = ice_get_vf_by_id(pf, vf_id);
	if (!vf)
		return -EINVAL;

	ret = ice_check_vf_ready_for_cfg(vf);
	if (ret)
		goto out_put_vf;

	ivi->vf = vf_id;
	ether_addr_copy(ivi->mac, vf->hw_lan_addr);

	/* VF configuration for VLAN and applicable QoS */
	ivi->vlan = ice_vf_get_port_vlan_id(vf);
	ivi->qos = ice_vf_get_port_vlan_prio(vf);
	if (ice_vf_is_port_vlan_ena(vf))
		ivi->vlan_proto = cpu_to_be16(ice_vf_get_port_vlan_tpid(vf));

	ivi->trusted = vf->trusted;
	ivi->spoofchk = vf->spoofchk;
	if (!vf->link_forced)
		ivi->linkstate = IFLA_VF_LINK_STATE_AUTO;
	else if (vf->link_up)
		ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE;
	else
		ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE;
	ivi->max_tx_rate = vf->max_tx_rate;
	ivi->min_tx_rate = vf->min_tx_rate;

out_put_vf:
	ice_put_vf(vf);
	return ret;
}

/**
 * ice_set_vf_mac
 * @netdev: network interface device structure
 * @vf_id: VF identifier
 * @mac: MAC address
 *
 * program VF MAC address
 */
int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
{
	struct ice_pf *pf = ice_netdev_to_pf(netdev);
	struct ice_vf *vf;
	int ret;

	if (is_multicast_ether_addr(mac)) {
		netdev_err(netdev, "%pM not a valid unicast address\n", mac);
		return -EINVAL;
	}

	vf = ice_get_vf_by_id(pf, vf_id);
	if (!vf)
		return -EINVAL;

	/* nothing left to do, unicast MAC already set */
	if (ether_addr_equal(vf->dev_lan_addr, mac) &&
	    ether_addr_equal(vf->hw_lan_addr, mac)) {
		ret = 0;
		goto out_put_vf;
	}

	ret = ice_check_vf_ready_for_reset(vf);
	if (ret)
		goto out_put_vf;

	mutex_lock(&vf->cfg_lock);

	/* VF is notified of its new MAC via the PF's response to the
	 * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset
	 */
	ether_addr_copy(vf->dev_lan_addr, mac);
	ether_addr_copy(vf->hw_lan_addr, mac);
	if (is_zero_ether_addr(mac)) {
		/* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */
		vf->pf_set_mac = false;
		netdev_info(netdev, "Removing MAC on VF %d. VF driver will be reinitialized\n",
			    vf->vf_id);
	} else {
		/* PF will add MAC rule for the VF */
		vf->pf_set_mac = true;
		netdev_info(netdev, "Setting MAC %pM on VF %d. VF driver will be reinitialized\n",
			    mac, vf_id);
	}

	ice_reset_vf(vf, ICE_VF_RESET_NOTIFY);
	mutex_unlock(&vf->cfg_lock);

out_put_vf:
	ice_put_vf(vf);
	return ret;
}

/**
 * ice_set_vf_trust
 * @netdev: network interface device structure
 * @vf_id: VF identifier
 * @trusted: Boolean value to enable/disable trusted VF
 *
 * Enable or disable a given VF as trusted
 */
int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted)
{
	struct ice_pf *pf = ice_netdev_to_pf(netdev);
	struct ice_vf *vf;
	int ret;

	vf = ice_get_vf_by_id(pf, vf_id);
	if (!vf)
		return -EINVAL;

	if (ice_is_eswitch_mode_switchdev(pf)) {
		dev_info(ice_pf_to_dev(pf), "Trusted VF is forbidden in switchdev mode\n");
		return -EOPNOTSUPP;
	}

	ret = ice_check_vf_ready_for_reset(vf);
	if (ret)
		goto out_put_vf;

	/* Check if already trusted */
	if (trusted == vf->trusted) {
		ret = 0;
		goto out_put_vf;
	}

	mutex_lock(&vf->cfg_lock);

	vf->trusted = trusted;
	ice_reset_vf(vf, ICE_VF_RESET_NOTIFY);
	dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n",
		 vf_id, trusted ? "" : "un");

	mutex_unlock(&vf->cfg_lock);

out_put_vf:
	ice_put_vf(vf);
	return ret;
}

/**
 * ice_set_vf_link_state
 * @netdev: network interface device structure
 * @vf_id: VF identifier
 * @link_state: required link state
 *
 * Set VF's link state, irrespective of physical link state status
 */
int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state)
{
	struct ice_pf *pf = ice_netdev_to_pf(netdev);
	struct ice_vf *vf;
	int ret;

	vf = ice_get_vf_by_id(pf, vf_id);
	if (!vf)
		return -EINVAL;

	ret = ice_check_vf_ready_for_cfg(vf);
	if (ret)
		goto out_put_vf;

	switch (link_state) {
	case IFLA_VF_LINK_STATE_AUTO:
		vf->link_forced = false;
		break;
	case IFLA_VF_LINK_STATE_ENABLE:
		vf->link_forced = true;
		vf->link_up = true;
		break;
	case IFLA_VF_LINK_STATE_DISABLE:
		vf->link_forced = true;
		vf->link_up = false;
		break;
	default:
		ret = -EINVAL;
		goto out_put_vf;
	}

	ice_vc_notify_vf_link_state(vf);

out_put_vf:
	ice_put_vf(vf);
	return ret;
}

/**
 * ice_calc_all_vfs_min_tx_rate - calculate cumulative min Tx rate on all VFs
 * @pf: PF associated with VFs
 */
static int ice_calc_all_vfs_min_tx_rate(struct ice_pf *pf)
{
	struct ice_vf *vf;
	unsigned int bkt;
	int rate = 0;

	rcu_read_lock();
	ice_for_each_vf_rcu(pf, bkt, vf)
		rate += vf->min_tx_rate;
	rcu_read_unlock();

	return rate;
}

/**
 * ice_min_tx_rate_oversubscribed - check if min Tx rate causes oversubscription
 * @vf: VF trying to configure min_tx_rate
 * @min_tx_rate: min Tx rate in Mbps
 *
 * Check if the min_tx_rate being passed in will cause oversubscription of total
 * min_tx_rate based on the current link speed and all other VFs configured
 * min_tx_rate
 *
 * Return true if the passed min_tx_rate would cause oversubscription, else
 * return false
 */
static bool
ice_min_tx_rate_oversubscribed(struct ice_vf *vf, int min_tx_rate)
{
	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
	int all_vfs_min_tx_rate;
	int link_speed_mbps;

	if (WARN_ON(!vsi))
		return false;

	link_speed_mbps = ice_get_link_speed_mbps(vsi);
	all_vfs_min_tx_rate = ice_calc_all_vfs_min_tx_rate(vf->pf);

	/* this VF's previous rate is being overwritten */
	all_vfs_min_tx_rate -= vf->min_tx_rate;

	if (all_vfs_min_tx_rate + min_tx_rate > link_speed_mbps) {
		dev_err(ice_pf_to_dev(vf->pf), "min_tx_rate of %d Mbps on VF %u would cause oversubscription of %d Mbps based on the current link speed %d Mbps\n",
			min_tx_rate, vf->vf_id,
			all_vfs_min_tx_rate + min_tx_rate - link_speed_mbps,
			link_speed_mbps);
		return true;
	}

	return false;
}

/**
 * ice_set_vf_bw - set min/max VF bandwidth
 * @netdev: network interface device structure
 * @vf_id: VF identifier
 * @min_tx_rate: Minimum Tx rate in Mbps
 * @max_tx_rate: Maximum Tx rate in Mbps
 */
int
ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
	      int max_tx_rate)
{
	struct ice_pf *pf = ice_netdev_to_pf(netdev);
	struct ice_vsi *vsi;
	struct device *dev;
	struct ice_vf *vf;
	int ret;

	dev = ice_pf_to_dev(pf);

	vf = ice_get_vf_by_id(pf, vf_id);
	if (!vf)
		return -EINVAL;

	ret = ice_check_vf_ready_for_cfg(vf);
	if (ret)
		goto out_put_vf;

	vsi = ice_get_vf_vsi(vf);
	if (!vsi) {
		ret = -EINVAL;
		goto out_put_vf;
	}

	if (min_tx_rate && ice_is_dcb_active(pf)) {
		dev_err(dev, "DCB on PF is currently enabled. VF min Tx rate limiting not allowed on this PF.\n");
		ret = -EOPNOTSUPP;
		goto out_put_vf;
	}

	if (ice_min_tx_rate_oversubscribed(vf, min_tx_rate)) {
		ret = -EINVAL;
		goto out_put_vf;
	}

	if (vf->min_tx_rate != (unsigned int)min_tx_rate) {
		ret = ice_set_min_bw_limit(vsi, (u64)min_tx_rate * 1000);
		if (ret) {
			dev_err(dev, "Unable to set min-tx-rate for VF %d\n",
				vf->vf_id);
			goto out_put_vf;
		}

		vf->min_tx_rate = min_tx_rate;
	}

	if (vf->max_tx_rate != (unsigned int)max_tx_rate) {
		ret = ice_set_max_bw_limit(vsi, (u64)max_tx_rate * 1000);
		if (ret) {
			dev_err(dev, "Unable to set max-tx-rate for VF %d\n",
				vf->vf_id);
			goto out_put_vf;
		}

		vf->max_tx_rate = max_tx_rate;
	}

out_put_vf:
	ice_put_vf(vf);
	return ret;
}

/**
 * ice_get_vf_stats - populate some stats for the VF
 * @netdev: the netdev of the PF
 * @vf_id: the host OS identifier (0-255)
 * @vf_stats: pointer to the OS memory to be initialized
 */
int ice_get_vf_stats(struct net_device *netdev, int vf_id,
		     struct ifla_vf_stats *vf_stats)
{
	struct ice_pf *pf = ice_netdev_to_pf(netdev);
	struct ice_eth_stats *stats;
	struct ice_vsi *vsi;
	struct ice_vf *vf;
	int ret;

	vf = ice_get_vf_by_id(pf, vf_id);
	if (!vf)
		return -EINVAL;

	ret = ice_check_vf_ready_for_cfg(vf);
	if (ret)
		goto out_put_vf;

	vsi = ice_get_vf_vsi(vf);
	if (!vsi) {
		ret = -EINVAL;
		goto out_put_vf;
	}

	ice_update_eth_stats(vsi);
	stats = &vsi->eth_stats;

	memset(vf_stats, 0, sizeof(*vf_stats));

	vf_stats->rx_packets = stats->rx_unicast + stats->rx_broadcast +
		stats->rx_multicast;
	vf_stats->tx_packets = stats->tx_unicast + stats->tx_broadcast +
		stats->tx_multicast;
	vf_stats->rx_bytes   = stats->rx_bytes;
	vf_stats->tx_bytes   = stats->tx_bytes;
	vf_stats->broadcast  = stats->rx_broadcast;
	vf_stats->multicast  = stats->rx_multicast;
	vf_stats->rx_dropped = stats->rx_discards;
	vf_stats->tx_dropped = stats->tx_discards;

out_put_vf:
	ice_put_vf(vf);
	return ret;
}

/**
 * ice_is_supported_port_vlan_proto - make sure the vlan_proto is supported
 * @hw: hardware structure used to check the VLAN mode
 * @vlan_proto: VLAN TPID being checked
 *
 * If the device is configured in Double VLAN Mode (DVM), then both ETH_P_8021Q
 * and ETH_P_8021AD are supported. If the device is configured in Single VLAN
 * Mode (SVM), then only ETH_P_8021Q is supported.
 */
static bool
ice_is_supported_port_vlan_proto(struct ice_hw *hw, u16 vlan_proto)
{
	bool is_supported = false;

	switch (vlan_proto) {
	case ETH_P_8021Q:
		is_supported = true;
		break;
	case ETH_P_8021AD:
		if (ice_is_dvm_ena(hw))
			is_supported = true;
		break;
	}

	return is_supported;
}

/**
 * ice_set_vf_port_vlan
 * @netdev: network interface device structure
 * @vf_id: VF identifier
 * @vlan_id: VLAN ID being set
 * @qos: priority setting
 * @vlan_proto: VLAN protocol
 *
 * program VF Port VLAN ID and/or QoS
 */
int
ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
		     __be16 vlan_proto)
{
	struct ice_pf *pf = ice_netdev_to_pf(netdev);
	u16 local_vlan_proto = ntohs(vlan_proto);
	struct device *dev;
	struct ice_vf *vf;
	int ret;

	dev = ice_pf_to_dev(pf);

	if (vlan_id >= VLAN_N_VID || qos > 7) {
		dev_err(dev, "Invalid Port VLAN parameters for VF %d, ID %d, QoS %d\n",
			vf_id, vlan_id, qos);
		return -EINVAL;
	}

	if (!ice_is_supported_port_vlan_proto(&pf->hw, local_vlan_proto)) {
		dev_err(dev, "VF VLAN protocol 0x%04x is not supported\n",
			local_vlan_proto);
		return -EPROTONOSUPPORT;
	}

	vf = ice_get_vf_by_id(pf, vf_id);
	if (!vf)
		return -EINVAL;

	ret = ice_check_vf_ready_for_reset(vf);
	if (ret)
		goto out_put_vf;

	if (ice_vf_get_port_vlan_prio(vf) == qos &&
	    ice_vf_get_port_vlan_tpid(vf) == local_vlan_proto &&
	    ice_vf_get_port_vlan_id(vf) == vlan_id) {
		/* duplicate request, so just return success */
		dev_dbg(dev, "Duplicate port VLAN %u, QoS %u, TPID 0x%04x request\n",
			vlan_id, qos, local_vlan_proto);
		ret = 0;
		goto out_put_vf;
	}

	mutex_lock(&vf->cfg_lock);

	vf->port_vlan_info = ICE_VLAN(local_vlan_proto, vlan_id, qos);
	if (ice_vf_is_port_vlan_ena(vf))
		dev_info(dev, "Setting VLAN %u, QoS %u, TPID 0x%04x on VF %d\n",
			 vlan_id, qos, local_vlan_proto, vf_id);
	else
		dev_info(dev, "Clearing port VLAN on VF %d\n", vf_id);

	ice_reset_vf(vf, ICE_VF_RESET_NOTIFY);
	mutex_unlock(&vf->cfg_lock);

out_put_vf:
	ice_put_vf(vf);
	return ret;
}

/**
 * ice_print_vf_rx_mdd_event - print VF Rx malicious driver detect event
 * @vf: pointer to the VF structure
 */
void ice_print_vf_rx_mdd_event(struct ice_vf *vf)
{
	struct ice_pf *pf = vf->pf;
	struct device *dev;

	dev = ice_pf_to_dev(pf);

	dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n",
		 vf->mdd_rx_events.count, pf->hw.pf_id, vf->vf_id,
		 vf->dev_lan_addr,
		 test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)
			  ? "on" : "off");
}

/**
 * ice_print_vfs_mdd_events - print VFs malicious driver detect event
 * @pf: pointer to the PF structure
 *
 * Called from ice_handle_mdd_event to rate limit and print VFs MDD events.
 */
void ice_print_vfs_mdd_events(struct ice_pf *pf)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_hw *hw = &pf->hw;
	struct ice_vf *vf;
	unsigned int bkt;

	/* check that there are pending MDD events to print */
	if (!test_and_clear_bit(ICE_MDD_VF_PRINT_PENDING, pf->state))
		return;

	/* VF MDD event logs are rate limited to one second intervals */
	if (time_is_after_jiffies(pf->vfs.last_printed_mdd_jiffies + HZ * 1))
		return;

	pf->vfs.last_printed_mdd_jiffies = jiffies;

	mutex_lock(&pf->vfs.table_lock);
	ice_for_each_vf(pf, bkt, vf) {
		/* only print Rx MDD event message if there are new events */
		if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) {
			vf->mdd_rx_events.last_printed =
							vf->mdd_rx_events.count;
			ice_print_vf_rx_mdd_event(vf);
		}

		/* only print Tx MDD event message if there are new events */
		if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) {
			vf->mdd_tx_events.last_printed =
							vf->mdd_tx_events.count;

			dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n",
				 vf->mdd_tx_events.count, hw->pf_id, vf->vf_id,
				 vf->dev_lan_addr);
		}
	}
	mutex_unlock(&pf->vfs.table_lock);
}

/**
 * ice_restore_all_vfs_msi_state - restore VF MSI state after PF FLR
 * @pdev: pointer to a pci_dev structure
 *
 * Called when recovering from a PF FLR to restore interrupt capability to
 * the VFs.
 */
void ice_restore_all_vfs_msi_state(struct pci_dev *pdev)
{
	u16 vf_id;
	int pos;

	if (!pci_num_vf(pdev))
		return;

	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
	if (pos) {
		struct pci_dev *vfdev;

		pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID,
				     &vf_id);
		vfdev = pci_get_device(pdev->vendor, vf_id, NULL);
		while (vfdev) {
			if (vfdev->is_virtfn && vfdev->physfn == pdev)
				pci_restore_msi_state(vfdev);
			vfdev = pci_get_device(pdev->vendor, vf_id,
					       vfdev);
		}
	}
}