summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/bnxt_re/main.c
blob: 33a448036c2ebd99217a40b9bb9d6372a798af0d (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
/*
 * Broadcom NetXtreme-E RoCE driver.
 *
 * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
 * Broadcom refers to Broadcom Limited and/or its subsidiaries.
 *
 * 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
 * BSD license below:
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. 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.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS''
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
 * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS
 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
 * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
 * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
 * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
 * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * Description: Main component of the bnxt_re driver
 */

#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/ethtool.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/rculist.h>
#include <linux/spinlock.h>
#include <linux/pci.h>
#include <net/dcbnl.h>
#include <net/ipv6.h>
#include <net/addrconf.h>
#include <linux/if_ether.h>

#include <rdma/ib_verbs.h>
#include <rdma/ib_user_verbs.h>
#include <rdma/ib_umem.h>
#include <rdma/ib_addr.h>

#include "bnxt_ulp.h"
#include "roce_hsi.h"
#include "qplib_res.h"
#include "qplib_sp.h"
#include "qplib_fp.h"
#include "qplib_rcfw.h"
#include "bnxt_re.h"
#include "ib_verbs.h"
#include <rdma/bnxt_re-abi.h>
#include "bnxt.h"
#include "hw_counters.h"

static char version[] =
		BNXT_RE_DESC " v" ROCE_DRV_MODULE_VERSION "\n";

MODULE_AUTHOR("Eddie Wai <eddie.wai@broadcom.com>");
MODULE_DESCRIPTION(BNXT_RE_DESC " Driver");
MODULE_LICENSE("Dual BSD/GPL");

/* globals */
static struct list_head bnxt_re_dev_list = LIST_HEAD_INIT(bnxt_re_dev_list);
/* Mutex to protect the list of bnxt_re devices added */
static DEFINE_MUTEX(bnxt_re_dev_lock);
static struct workqueue_struct *bnxt_re_wq;
static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait);

/* SR-IOV helper functions */

static void bnxt_re_get_sriov_func_type(struct bnxt_re_dev *rdev)
{
	struct bnxt *bp;

	bp = netdev_priv(rdev->en_dev->net);
	if (BNXT_VF(bp))
		rdev->is_virtfn = 1;
}

/* Set the maximum number of each resource that the driver actually wants
 * to allocate. This may be up to the maximum number the firmware has
 * reserved for the function. The driver may choose to allocate fewer
 * resources than the firmware maximum.
 */
static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev)
{
	u32 vf_qps = 0, vf_srqs = 0, vf_cqs = 0, vf_mrws = 0, vf_gids = 0;
	u32 i;
	u32 vf_pct;
	u32 num_vfs;
	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;

	rdev->qplib_ctx.qpc_count = min_t(u32, BNXT_RE_MAX_QPC_COUNT,
					  dev_attr->max_qp);

	rdev->qplib_ctx.mrw_count = BNXT_RE_MAX_MRW_COUNT_256K;
	/* Use max_mr from fw since max_mrw does not get set */
	rdev->qplib_ctx.mrw_count = min_t(u32, rdev->qplib_ctx.mrw_count,
					  dev_attr->max_mr);
	rdev->qplib_ctx.srqc_count = min_t(u32, BNXT_RE_MAX_SRQC_COUNT,
					   dev_attr->max_srq);
	rdev->qplib_ctx.cq_count = min_t(u32, BNXT_RE_MAX_CQ_COUNT,
					 dev_attr->max_cq);

	for (i = 0; i < MAX_TQM_ALLOC_REQ; i++)
		rdev->qplib_ctx.tqm_count[i] =
		rdev->dev_attr.tqm_alloc_reqs[i];

	if (rdev->num_vfs) {
		/*
		 * Reserve a set of resources for the PF. Divide the remaining
		 * resources among the VFs
		 */
		vf_pct = 100 - BNXT_RE_PCT_RSVD_FOR_PF;
		num_vfs = 100 * rdev->num_vfs;
		vf_qps = (rdev->qplib_ctx.qpc_count * vf_pct) / num_vfs;
		vf_srqs = (rdev->qplib_ctx.srqc_count * vf_pct) / num_vfs;
		vf_cqs = (rdev->qplib_ctx.cq_count * vf_pct) / num_vfs;
		/*
		 * The driver allows many more MRs than other resources. If the
		 * firmware does also, then reserve a fixed amount for the PF
		 * and divide the rest among VFs. VFs may use many MRs for NFS
		 * mounts, ISER, NVME applications, etc. If the firmware
		 * severely restricts the number of MRs, then let PF have
		 * half and divide the rest among VFs, as for the other
		 * resource types.
		 */
		if (rdev->qplib_ctx.mrw_count < BNXT_RE_MAX_MRW_COUNT_64K)
			vf_mrws = rdev->qplib_ctx.mrw_count * vf_pct / num_vfs;
		else
			vf_mrws = (rdev->qplib_ctx.mrw_count -
				   BNXT_RE_RESVD_MR_FOR_PF) / rdev->num_vfs;
		vf_gids = BNXT_RE_MAX_GID_PER_VF;
	}
	rdev->qplib_ctx.vf_res.max_mrw_per_vf = vf_mrws;
	rdev->qplib_ctx.vf_res.max_gid_per_vf = vf_gids;
	rdev->qplib_ctx.vf_res.max_qp_per_vf = vf_qps;
	rdev->qplib_ctx.vf_res.max_srq_per_vf = vf_srqs;
	rdev->qplib_ctx.vf_res.max_cq_per_vf = vf_cqs;
}

/* for handling bnxt_en callbacks later */
static void bnxt_re_stop(void *p)
{
}

static void bnxt_re_start(void *p)
{
}

static void bnxt_re_sriov_config(void *p, int num_vfs)
{
	struct bnxt_re_dev *rdev = p;

	if (!rdev)
		return;

	rdev->num_vfs = num_vfs;
	bnxt_re_set_resource_limits(rdev);
	bnxt_qplib_set_func_resources(&rdev->qplib_res, &rdev->rcfw,
				      &rdev->qplib_ctx);
}

static void bnxt_re_shutdown(void *p)
{
	struct bnxt_re_dev *rdev = p;

	if (!rdev)
		return;

	bnxt_re_ib_unreg(rdev, false);
}

static struct bnxt_ulp_ops bnxt_re_ulp_ops = {
	.ulp_async_notifier = NULL,
	.ulp_stop = bnxt_re_stop,
	.ulp_start = bnxt_re_start,
	.ulp_sriov_config = bnxt_re_sriov_config,
	.ulp_shutdown = bnxt_re_shutdown
};

/* RoCE -> Net driver */

/* Driver registration routines used to let the networking driver (bnxt_en)
 * to know that the RoCE driver is now installed
 */
static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev, bool lock_wait)
{
	struct bnxt_en_dev *en_dev;
	int rc;

	if (!rdev)
		return -EINVAL;

	en_dev = rdev->en_dev;
	/* Acquire rtnl lock if it is not invokded from netdev event */
	if (lock_wait)
		rtnl_lock();

	rc = en_dev->en_ops->bnxt_unregister_device(rdev->en_dev,
						    BNXT_ROCE_ULP);
	if (lock_wait)
		rtnl_unlock();
	return rc;
}

static int bnxt_re_register_netdev(struct bnxt_re_dev *rdev)
{
	struct bnxt_en_dev *en_dev;
	int rc = 0;

	if (!rdev)
		return -EINVAL;

	en_dev = rdev->en_dev;

	rtnl_lock();
	rc = en_dev->en_ops->bnxt_register_device(en_dev, BNXT_ROCE_ULP,
						  &bnxt_re_ulp_ops, rdev);
	rtnl_unlock();
	return rc;
}

static int bnxt_re_free_msix(struct bnxt_re_dev *rdev, bool lock_wait)
{
	struct bnxt_en_dev *en_dev;
	int rc;

	if (!rdev)
		return -EINVAL;

	en_dev = rdev->en_dev;

	if (lock_wait)
		rtnl_lock();

	rc = en_dev->en_ops->bnxt_free_msix(rdev->en_dev, BNXT_ROCE_ULP);

	if (lock_wait)
		rtnl_unlock();
	return rc;
}

static int bnxt_re_request_msix(struct bnxt_re_dev *rdev)
{
	int rc = 0, num_msix_want = BNXT_RE_MAX_MSIX, num_msix_got;
	struct bnxt_en_dev *en_dev;

	if (!rdev)
		return -EINVAL;

	en_dev = rdev->en_dev;

	num_msix_want = min_t(u32, BNXT_RE_MAX_MSIX, num_online_cpus());

	rtnl_lock();
	num_msix_got = en_dev->en_ops->bnxt_request_msix(en_dev, BNXT_ROCE_ULP,
							 rdev->msix_entries,
							 num_msix_want);
	if (num_msix_got < BNXT_RE_MIN_MSIX) {
		rc = -EINVAL;
		goto done;
	}
	if (num_msix_got != num_msix_want) {
		dev_warn(rdev_to_dev(rdev),
			 "Requested %d MSI-X vectors, got %d\n",
			 num_msix_want, num_msix_got);
	}
	rdev->num_msix = num_msix_got;
done:
	rtnl_unlock();
	return rc;
}

static void bnxt_re_init_hwrm_hdr(struct bnxt_re_dev *rdev, struct input *hdr,
				  u16 opcd, u16 crid, u16 trid)
{
	hdr->req_type = cpu_to_le16(opcd);
	hdr->cmpl_ring = cpu_to_le16(crid);
	hdr->target_id = cpu_to_le16(trid);
}

static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg,
				int msg_len, void *resp, int resp_max_len,
				int timeout)
{
	fw_msg->msg = msg;
	fw_msg->msg_len = msg_len;
	fw_msg->resp = resp;
	fw_msg->resp_max_len = resp_max_len;
	fw_msg->timeout = timeout;
}

static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, u16 fw_ring_id,
				 bool lock_wait)
{
	struct bnxt_en_dev *en_dev = rdev->en_dev;
	struct hwrm_ring_free_input req = {0};
	struct hwrm_ring_free_output resp;
	struct bnxt_fw_msg fw_msg;
	bool do_unlock = false;
	int rc = -EINVAL;

	if (!en_dev)
		return rc;

	memset(&fw_msg, 0, sizeof(fw_msg));
	if (lock_wait) {
		rtnl_lock();
		do_unlock = true;
	}

	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_FREE, -1, -1);
	req.ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
	req.ring_id = cpu_to_le16(fw_ring_id);
	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
	if (rc)
		dev_err(rdev_to_dev(rdev),
			"Failed to free HW ring:%d :%#x", req.ring_id, rc);
	if (do_unlock)
		rtnl_unlock();
	return rc;
}

static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev, dma_addr_t *dma_arr,
				  int pages, int type, u32 ring_mask,
				  u32 map_index, u16 *fw_ring_id)
{
	struct bnxt_en_dev *en_dev = rdev->en_dev;
	struct hwrm_ring_alloc_input req = {0};
	struct hwrm_ring_alloc_output resp;
	struct bnxt_fw_msg fw_msg;
	int rc = -EINVAL;

	if (!en_dev)
		return rc;

	memset(&fw_msg, 0, sizeof(fw_msg));
	rtnl_lock();
	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_ALLOC, -1, -1);
	req.enables = 0;
	req.page_tbl_addr =  cpu_to_le64(dma_arr[0]);
	if (pages > 1) {
		/* Page size is in log2 units */
		req.page_size = BNXT_PAGE_SHIFT;
		req.page_tbl_depth = 1;
	}
	req.fbo = 0;
	/* Association of ring index with doorbell index and MSIX number */
	req.logical_id = cpu_to_le16(map_index);
	req.length = cpu_to_le32(ring_mask + 1);
	req.ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
	req.int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
	if (!rc)
		*fw_ring_id = le16_to_cpu(resp.ring_id);

	rtnl_unlock();
	return rc;
}

static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev,
				      u32 fw_stats_ctx_id, bool lock_wait)
{
	struct bnxt_en_dev *en_dev = rdev->en_dev;
	struct hwrm_stat_ctx_free_input req = {0};
	struct bnxt_fw_msg fw_msg;
	bool do_unlock = false;
	int rc = -EINVAL;

	if (!en_dev)
		return rc;

	memset(&fw_msg, 0, sizeof(fw_msg));
	if (lock_wait) {
		rtnl_lock();
		do_unlock = true;
	}

	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_FREE, -1, -1);
	req.stat_ctx_id = cpu_to_le32(fw_stats_ctx_id);
	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&req,
			    sizeof(req), DFLT_HWRM_CMD_TIMEOUT);
	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
	if (rc)
		dev_err(rdev_to_dev(rdev),
			"Failed to free HW stats context %#x", rc);

	if (do_unlock)
		rtnl_unlock();
	return rc;
}

static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev,
				       dma_addr_t dma_map,
				       u32 *fw_stats_ctx_id)
{
	struct hwrm_stat_ctx_alloc_output resp = {0};
	struct hwrm_stat_ctx_alloc_input req = {0};
	struct bnxt_en_dev *en_dev = rdev->en_dev;
	struct bnxt_fw_msg fw_msg;
	int rc = -EINVAL;

	*fw_stats_ctx_id = INVALID_STATS_CTX_ID;

	if (!en_dev)
		return rc;

	memset(&fw_msg, 0, sizeof(fw_msg));
	rtnl_lock();

	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1);
	req.update_period_ms = cpu_to_le32(1000);
	req.stats_dma_addr = cpu_to_le64(dma_map);
	req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE;
	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
	if (!rc)
		*fw_stats_ctx_id = le32_to_cpu(resp.stat_ctx_id);

	rtnl_unlock();
	return rc;
}

/* Device */

static bool is_bnxt_re_dev(struct net_device *netdev)
{
	struct ethtool_drvinfo drvinfo;

	if (netdev->ethtool_ops && netdev->ethtool_ops->get_drvinfo) {
		memset(&drvinfo, 0, sizeof(drvinfo));
		netdev->ethtool_ops->get_drvinfo(netdev, &drvinfo);

		if (strcmp(drvinfo.driver, "bnxt_en"))
			return false;
		return true;
	}
	return false;
}

static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev)
{
	struct bnxt_re_dev *rdev;

	rcu_read_lock();
	list_for_each_entry_rcu(rdev, &bnxt_re_dev_list, list) {
		if (rdev->netdev == netdev) {
			rcu_read_unlock();
			return rdev;
		}
	}
	rcu_read_unlock();
	return NULL;
}

static void bnxt_re_dev_unprobe(struct net_device *netdev,
				struct bnxt_en_dev *en_dev)
{
	dev_put(netdev);
	module_put(en_dev->pdev->driver->driver.owner);
}

static struct bnxt_en_dev *bnxt_re_dev_probe(struct net_device *netdev)
{
	struct bnxt *bp = netdev_priv(netdev);
	struct bnxt_en_dev *en_dev;
	struct pci_dev *pdev;

	/* Call bnxt_en's RoCE probe via indirect API */
	if (!bp->ulp_probe)
		return ERR_PTR(-EINVAL);

	en_dev = bp->ulp_probe(netdev);
	if (IS_ERR(en_dev))
		return en_dev;

	pdev = en_dev->pdev;
	if (!pdev)
		return ERR_PTR(-EINVAL);

	if (!(en_dev->flags & BNXT_EN_FLAG_ROCE_CAP)) {
		dev_info(&pdev->dev,
			"%s: probe error: RoCE is not supported on this device",
			ROCE_DRV_MODULE_NAME);
		return ERR_PTR(-ENODEV);
	}

	/* Bump net device reference count */
	if (!try_module_get(pdev->driver->driver.owner))
		return ERR_PTR(-ENODEV);

	dev_hold(netdev);

	return en_dev;
}

static void bnxt_re_unregister_ib(struct bnxt_re_dev *rdev)
{
	ib_unregister_device(&rdev->ibdev);
}

static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
{
	struct ib_device *ibdev = &rdev->ibdev;

	/* ib device init */
	ibdev->owner = THIS_MODULE;
	ibdev->node_type = RDMA_NODE_IB_CA;
	strlcpy(ibdev->name, "bnxt_re%d", IB_DEVICE_NAME_MAX);
	strlcpy(ibdev->node_desc, BNXT_RE_DESC " HCA",
		strlen(BNXT_RE_DESC) + 5);
	ibdev->phys_port_cnt = 1;

	bnxt_qplib_get_guid(rdev->netdev->dev_addr, (u8 *)&ibdev->node_guid);

	ibdev->num_comp_vectors	= 1;
	ibdev->dev.parent = &rdev->en_dev->pdev->dev;
	ibdev->local_dma_lkey = BNXT_QPLIB_RSVD_LKEY;

	/* User space */
	ibdev->uverbs_abi_ver = BNXT_RE_ABI_VERSION;
	ibdev->uverbs_cmd_mask =
			(1ull << IB_USER_VERBS_CMD_GET_CONTEXT)		|
			(1ull << IB_USER_VERBS_CMD_QUERY_DEVICE)	|
			(1ull << IB_USER_VERBS_CMD_QUERY_PORT)		|
			(1ull << IB_USER_VERBS_CMD_ALLOC_PD)		|
			(1ull << IB_USER_VERBS_CMD_DEALLOC_PD)		|
			(1ull << IB_USER_VERBS_CMD_REG_MR)		|
			(1ull << IB_USER_VERBS_CMD_REREG_MR)		|
			(1ull << IB_USER_VERBS_CMD_DEREG_MR)		|
			(1ull << IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) |
			(1ull << IB_USER_VERBS_CMD_CREATE_CQ)		|
			(1ull << IB_USER_VERBS_CMD_RESIZE_CQ)		|
			(1ull << IB_USER_VERBS_CMD_DESTROY_CQ)		|
			(1ull << IB_USER_VERBS_CMD_CREATE_QP)		|
			(1ull << IB_USER_VERBS_CMD_MODIFY_QP)		|
			(1ull << IB_USER_VERBS_CMD_QUERY_QP)		|
			(1ull << IB_USER_VERBS_CMD_DESTROY_QP)		|
			(1ull << IB_USER_VERBS_CMD_CREATE_SRQ)		|
			(1ull << IB_USER_VERBS_CMD_MODIFY_SRQ)		|
			(1ull << IB_USER_VERBS_CMD_QUERY_SRQ)		|
			(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ)		|
			(1ull << IB_USER_VERBS_CMD_CREATE_AH)		|
			(1ull << IB_USER_VERBS_CMD_MODIFY_AH)		|
			(1ull << IB_USER_VERBS_CMD_QUERY_AH)		|
			(1ull << IB_USER_VERBS_CMD_DESTROY_AH);
	/* POLL_CQ and REQ_NOTIFY_CQ is directly handled in libbnxt_re */

	/* Kernel verbs */
	ibdev->query_device		= bnxt_re_query_device;
	ibdev->modify_device		= bnxt_re_modify_device;

	ibdev->query_port		= bnxt_re_query_port;
	ibdev->get_port_immutable	= bnxt_re_get_port_immutable;
	ibdev->get_dev_fw_str           = bnxt_re_query_fw_str;
	ibdev->query_pkey		= bnxt_re_query_pkey;
	ibdev->query_gid		= bnxt_re_query_gid;
	ibdev->get_netdev		= bnxt_re_get_netdev;
	ibdev->add_gid			= bnxt_re_add_gid;
	ibdev->del_gid			= bnxt_re_del_gid;
	ibdev->get_link_layer		= bnxt_re_get_link_layer;

	ibdev->alloc_pd			= bnxt_re_alloc_pd;
	ibdev->dealloc_pd		= bnxt_re_dealloc_pd;

	ibdev->create_ah		= bnxt_re_create_ah;
	ibdev->modify_ah		= bnxt_re_modify_ah;
	ibdev->query_ah			= bnxt_re_query_ah;
	ibdev->destroy_ah		= bnxt_re_destroy_ah;

	ibdev->create_srq		= bnxt_re_create_srq;
	ibdev->modify_srq		= bnxt_re_modify_srq;
	ibdev->query_srq		= bnxt_re_query_srq;
	ibdev->destroy_srq		= bnxt_re_destroy_srq;
	ibdev->post_srq_recv		= bnxt_re_post_srq_recv;

	ibdev->create_qp		= bnxt_re_create_qp;
	ibdev->modify_qp		= bnxt_re_modify_qp;
	ibdev->query_qp			= bnxt_re_query_qp;
	ibdev->destroy_qp		= bnxt_re_destroy_qp;

	ibdev->post_send		= bnxt_re_post_send;
	ibdev->post_recv		= bnxt_re_post_recv;

	ibdev->create_cq		= bnxt_re_create_cq;
	ibdev->destroy_cq		= bnxt_re_destroy_cq;
	ibdev->poll_cq			= bnxt_re_poll_cq;
	ibdev->req_notify_cq		= bnxt_re_req_notify_cq;

	ibdev->get_dma_mr		= bnxt_re_get_dma_mr;
	ibdev->dereg_mr			= bnxt_re_dereg_mr;
	ibdev->alloc_mr			= bnxt_re_alloc_mr;
	ibdev->map_mr_sg		= bnxt_re_map_mr_sg;

	ibdev->reg_user_mr		= bnxt_re_reg_user_mr;
	ibdev->alloc_ucontext		= bnxt_re_alloc_ucontext;
	ibdev->dealloc_ucontext		= bnxt_re_dealloc_ucontext;
	ibdev->mmap			= bnxt_re_mmap;
	ibdev->get_hw_stats             = bnxt_re_ib_get_hw_stats;
	ibdev->alloc_hw_stats           = bnxt_re_ib_alloc_hw_stats;

	return ib_register_device(ibdev, NULL);
}

static ssize_t show_rev(struct device *device, struct device_attribute *attr,
			char *buf)
{
	struct bnxt_re_dev *rdev = to_bnxt_re_dev(device, ibdev.dev);

	return scnprintf(buf, PAGE_SIZE, "0x%x\n", rdev->en_dev->pdev->vendor);
}

static ssize_t show_hca(struct device *device, struct device_attribute *attr,
			char *buf)
{
	struct bnxt_re_dev *rdev = to_bnxt_re_dev(device, ibdev.dev);

	return scnprintf(buf, PAGE_SIZE, "%s\n", rdev->ibdev.node_desc);
}

static DEVICE_ATTR(hw_rev, 0444, show_rev, NULL);
static DEVICE_ATTR(hca_type, 0444, show_hca, NULL);

static struct device_attribute *bnxt_re_attributes[] = {
	&dev_attr_hw_rev,
	&dev_attr_hca_type
};

static void bnxt_re_dev_remove(struct bnxt_re_dev *rdev)
{
	dev_put(rdev->netdev);
	rdev->netdev = NULL;

	mutex_lock(&bnxt_re_dev_lock);
	list_del_rcu(&rdev->list);
	mutex_unlock(&bnxt_re_dev_lock);

	synchronize_rcu();

	ib_dealloc_device(&rdev->ibdev);
	/* rdev is gone */
}

static struct bnxt_re_dev *bnxt_re_dev_add(struct net_device *netdev,
					   struct bnxt_en_dev *en_dev)
{
	struct bnxt_re_dev *rdev;

	/* Allocate bnxt_re_dev instance here */
	rdev = (struct bnxt_re_dev *)ib_alloc_device(sizeof(*rdev));
	if (!rdev) {
		dev_err(NULL, "%s: bnxt_re_dev allocation failure!",
			ROCE_DRV_MODULE_NAME);
		return NULL;
	}
	/* Default values */
	rdev->netdev = netdev;
	dev_hold(rdev->netdev);
	rdev->en_dev = en_dev;
	rdev->id = rdev->en_dev->pdev->devfn;
	INIT_LIST_HEAD(&rdev->qp_list);
	mutex_init(&rdev->qp_lock);
	atomic_set(&rdev->qp_count, 0);
	atomic_set(&rdev->cq_count, 0);
	atomic_set(&rdev->srq_count, 0);
	atomic_set(&rdev->mr_count, 0);
	atomic_set(&rdev->mw_count, 0);
	rdev->cosq[0] = 0xFFFF;
	rdev->cosq[1] = 0xFFFF;

	mutex_lock(&bnxt_re_dev_lock);
	list_add_tail_rcu(&rdev->list, &bnxt_re_dev_list);
	mutex_unlock(&bnxt_re_dev_lock);
	return rdev;
}

static int bnxt_re_handle_unaffi_async_event(struct creq_func_event
					     *unaffi_async)
{
	switch (unaffi_async->event) {
	case CREQ_FUNC_EVENT_EVENT_TX_WQE_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_TX_DATA_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_RX_WQE_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_RX_DATA_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_CQ_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_TQM_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_CFCQ_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_CFCS_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_CFCC_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_CFCM_ERROR:
		break;
	case CREQ_FUNC_EVENT_EVENT_TIM_ERROR:
		break;
	default:
		return -EINVAL;
	}
	return 0;
}

static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event,
					 struct bnxt_re_qp *qp)
{
	struct ib_event event;

	memset(&event, 0, sizeof(event));
	if (qp->qplib_qp.srq) {
		event.device = &qp->rdev->ibdev;
		event.element.qp = &qp->ib_qp;
		event.event = IB_EVENT_QP_LAST_WQE_REACHED;
	}

	if (event.device && qp->ib_qp.event_handler)
		qp->ib_qp.event_handler(&event, qp->ib_qp.qp_context);

	return 0;
}

static int bnxt_re_handle_affi_async_event(struct creq_qp_event *affi_async,
					   void *obj)
{
	int rc = 0;
	u8 event;

	if (!obj)
		return rc; /* QP was already dead, still return success */

	event = affi_async->event;
	if (event == CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION) {
		struct bnxt_qplib_qp *lib_qp = obj;
		struct bnxt_re_qp *qp = container_of(lib_qp, struct bnxt_re_qp,
						     qplib_qp);
		rc = bnxt_re_handle_qp_async_event(affi_async, qp);
	}
	return rc;
}

static int bnxt_re_aeq_handler(struct bnxt_qplib_rcfw *rcfw,
			       void *aeqe, void *obj)
{
	struct creq_qp_event *affi_async;
	struct creq_func_event *unaffi_async;
	u8 type;
	int rc;

	type = ((struct creq_base *)aeqe)->type;
	if (type == CREQ_BASE_TYPE_FUNC_EVENT) {
		unaffi_async = aeqe;
		rc = bnxt_re_handle_unaffi_async_event(unaffi_async);
	} else {
		affi_async = aeqe;
		rc = bnxt_re_handle_affi_async_event(affi_async, obj);
	}

	return rc;
}

static int bnxt_re_srqn_handler(struct bnxt_qplib_nq *nq,
				struct bnxt_qplib_srq *handle, u8 event)
{
	struct bnxt_re_srq *srq = container_of(handle, struct bnxt_re_srq,
					       qplib_srq);
	struct ib_event ib_event;
	int rc = 0;

	if (!srq) {
		dev_err(NULL, "%s: SRQ is NULL, SRQN not handled",
			ROCE_DRV_MODULE_NAME);
		rc = -EINVAL;
		goto done;
	}
	ib_event.device = &srq->rdev->ibdev;
	ib_event.element.srq = &srq->ib_srq;
	if (event == NQ_SRQ_EVENT_EVENT_SRQ_THRESHOLD_EVENT)
		ib_event.event = IB_EVENT_SRQ_LIMIT_REACHED;
	else
		ib_event.event = IB_EVENT_SRQ_ERR;

	if (srq->ib_srq.event_handler) {
		/* Lock event_handler? */
		(*srq->ib_srq.event_handler)(&ib_event,
					     srq->ib_srq.srq_context);
	}
done:
	return rc;
}

static int bnxt_re_cqn_handler(struct bnxt_qplib_nq *nq,
			       struct bnxt_qplib_cq *handle)
{
	struct bnxt_re_cq *cq = container_of(handle, struct bnxt_re_cq,
					     qplib_cq);

	if (!cq) {
		dev_err(NULL, "%s: CQ is NULL, CQN not handled",
			ROCE_DRV_MODULE_NAME);
		return -EINVAL;
	}
	if (cq->ib_cq.comp_handler) {
		/* Lock comp_handler? */
		(*cq->ib_cq.comp_handler)(&cq->ib_cq, cq->ib_cq.cq_context);
	}

	return 0;
}

static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev)
{
	int i;

	if (rdev->nq[0].hwq.max_elements) {
		for (i = 1; i < rdev->num_msix; i++)
			bnxt_qplib_disable_nq(&rdev->nq[i - 1]);
	}

	if (rdev->qplib_res.rcfw)
		bnxt_qplib_cleanup_res(&rdev->qplib_res);
}

static int bnxt_re_init_res(struct bnxt_re_dev *rdev)
{
	int rc = 0, i;

	bnxt_qplib_init_res(&rdev->qplib_res);

	for (i = 1; i < rdev->num_msix ; i++) {
		rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq[i - 1],
					  i - 1, rdev->msix_entries[i].vector,
					  rdev->msix_entries[i].db_offset,
					  &bnxt_re_cqn_handler,
					  &bnxt_re_srqn_handler);

		if (rc) {
			dev_err(rdev_to_dev(rdev),
				"Failed to enable NQ with rc = 0x%x", rc);
			goto fail;
		}
	}
	return 0;
fail:
	return rc;
}

static void bnxt_re_free_nq_res(struct bnxt_re_dev *rdev, bool lock_wait)
{
	int i;

	for (i = 0; i < rdev->num_msix - 1; i++) {
		bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id, lock_wait);
		bnxt_qplib_free_nq(&rdev->nq[i]);
	}
}

static void bnxt_re_free_res(struct bnxt_re_dev *rdev, bool lock_wait)
{
	bnxt_re_free_nq_res(rdev, lock_wait);

	if (rdev->qplib_res.dpi_tbl.max) {
		bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
				       &rdev->qplib_res.dpi_tbl,
				       &rdev->dpi_privileged);
	}
	if (rdev->qplib_res.rcfw) {
		bnxt_qplib_free_res(&rdev->qplib_res);
		rdev->qplib_res.rcfw = NULL;
	}
}

static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
{
	int rc = 0, i;

	/* Configure and allocate resources for qplib */
	rdev->qplib_res.rcfw = &rdev->rcfw;
	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr,
				     rdev->is_virtfn);
	if (rc)
		goto fail;

	rc = bnxt_qplib_alloc_res(&rdev->qplib_res, rdev->en_dev->pdev,
				  rdev->netdev, &rdev->dev_attr);
	if (rc)
		goto fail;

	rc = bnxt_qplib_alloc_dpi(&rdev->qplib_res.dpi_tbl,
				  &rdev->dpi_privileged,
				  rdev);
	if (rc)
		goto dealloc_res;

	for (i = 0; i < rdev->num_msix - 1; i++) {
		rdev->nq[i].hwq.max_elements = BNXT_RE_MAX_CQ_COUNT +
			BNXT_RE_MAX_SRQC_COUNT + 2;
		rc = bnxt_qplib_alloc_nq(rdev->en_dev->pdev, &rdev->nq[i]);
		if (rc) {
			dev_err(rdev_to_dev(rdev), "Alloc Failed NQ%d rc:%#x",
				i, rc);
			goto dealloc_dpi;
		}
		rc = bnxt_re_net_ring_alloc
			(rdev, rdev->nq[i].hwq.pbl[PBL_LVL_0].pg_map_arr,
			 rdev->nq[i].hwq.pbl[rdev->nq[i].hwq.level].pg_count,
			 HWRM_RING_ALLOC_CMPL,
			 BNXT_QPLIB_NQE_MAX_CNT - 1,
			 rdev->msix_entries[i + 1].ring_idx,
			 &rdev->nq[i].ring_id);
		if (rc) {
			dev_err(rdev_to_dev(rdev),
				"Failed to allocate NQ fw id with rc = 0x%x",
				rc);
			goto free_nq;
		}
	}
	return 0;
free_nq:
	for (i = 0; i < rdev->num_msix - 1; i++)
		bnxt_qplib_free_nq(&rdev->nq[i]);
dealloc_dpi:
	bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
			       &rdev->qplib_res.dpi_tbl,
			       &rdev->dpi_privileged);
dealloc_res:
	bnxt_qplib_free_res(&rdev->qplib_res);

fail:
	rdev->qplib_res.rcfw = NULL;
	return rc;
}

static void bnxt_re_dispatch_event(struct ib_device *ibdev, struct ib_qp *qp,
				   u8 port_num, enum ib_event_type event)
{
	struct ib_event ib_event;

	ib_event.device = ibdev;
	if (qp)
		ib_event.element.qp = qp;
	else
		ib_event.element.port_num = port_num;
	ib_event.event = event;
	ib_dispatch_event(&ib_event);
}

#define HWRM_QUEUE_PRI2COS_QCFG_INPUT_FLAGS_IVLAN      0x02
static int bnxt_re_query_hwrm_pri2cos(struct bnxt_re_dev *rdev, u8 dir,
				      u64 *cid_map)
{
	struct hwrm_queue_pri2cos_qcfg_input req = {0};
	struct bnxt *bp = netdev_priv(rdev->netdev);
	struct hwrm_queue_pri2cos_qcfg_output resp;
	struct bnxt_en_dev *en_dev = rdev->en_dev;
	struct bnxt_fw_msg fw_msg;
	u32 flags = 0;
	u8 *qcfgmap, *tmp_map;
	int rc = 0, i;

	if (!cid_map)
		return -EINVAL;

	memset(&fw_msg, 0, sizeof(fw_msg));
	bnxt_re_init_hwrm_hdr(rdev, (void *)&req,
			      HWRM_QUEUE_PRI2COS_QCFG, -1, -1);
	flags |= (dir & 0x01);
	flags |= HWRM_QUEUE_PRI2COS_QCFG_INPUT_FLAGS_IVLAN;
	req.flags = cpu_to_le32(flags);
	req.port_id = bp->pf.port_id;

	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
	if (rc)
		return rc;

	if (resp.queue_cfg_info) {
		dev_warn(rdev_to_dev(rdev),
			 "Asymmetric cos queue configuration detected");
		dev_warn(rdev_to_dev(rdev),
			 " on device, QoS may not be fully functional\n");
	}
	qcfgmap = &resp.pri0_cos_queue_id;
	tmp_map = (u8 *)cid_map;
	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
		tmp_map[i] = qcfgmap[i];

	return rc;
}

static bool bnxt_re_is_qp1_or_shadow_qp(struct bnxt_re_dev *rdev,
					struct bnxt_re_qp *qp)
{
	return (qp->ib_qp.qp_type == IB_QPT_GSI) || (qp == rdev->qp1_sqp);
}

static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev)
{
	int mask = IB_QP_STATE;
	struct ib_qp_attr qp_attr;
	struct bnxt_re_qp *qp;

	qp_attr.qp_state = IB_QPS_ERR;
	mutex_lock(&rdev->qp_lock);
	list_for_each_entry(qp, &rdev->qp_list, list) {
		/* Modify the state of all QPs except QP1/Shadow QP */
		if (!bnxt_re_is_qp1_or_shadow_qp(rdev, qp)) {
			if (qp->qplib_qp.state !=
			    CMDQ_MODIFY_QP_NEW_STATE_RESET &&
			    qp->qplib_qp.state !=
			    CMDQ_MODIFY_QP_NEW_STATE_ERR) {
				bnxt_re_dispatch_event(&rdev->ibdev, &qp->ib_qp,
						       1, IB_EVENT_QP_FATAL);
				bnxt_re_modify_qp(&qp->ib_qp, &qp_attr, mask,
						  NULL);
			}
		}
	}
	mutex_unlock(&rdev->qp_lock);
}

static int bnxt_re_update_gid(struct bnxt_re_dev *rdev)
{
	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
	struct bnxt_qplib_gid gid;
	u16 gid_idx, index;
	int rc = 0;

	if (!test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
		return 0;

	if (!sgid_tbl) {
		dev_err(rdev_to_dev(rdev), "QPLIB: SGID table not allocated");
		return -EINVAL;
	}

	for (index = 0; index < sgid_tbl->active; index++) {
		gid_idx = sgid_tbl->hw_id[index];

		if (!memcmp(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero,
			    sizeof(bnxt_qplib_gid_zero)))
			continue;
		/* need to modify the VLAN enable setting of non VLAN GID only
		 * as setting is done for VLAN GID while adding GID
		 */
		if (sgid_tbl->vlan[index])
			continue;

		memcpy(&gid, &sgid_tbl->tbl[index], sizeof(gid));

		rc = bnxt_qplib_update_sgid(sgid_tbl, &gid, gid_idx,
					    rdev->qplib_res.netdev->dev_addr);
	}

	return rc;
}

static u32 bnxt_re_get_priority_mask(struct bnxt_re_dev *rdev)
{
	u32 prio_map = 0, tmp_map = 0;
	struct net_device *netdev;
	struct dcb_app app;

	netdev = rdev->netdev;

	memset(&app, 0, sizeof(app));
	app.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE;
	app.protocol = ETH_P_IBOE;
	tmp_map = dcb_ieee_getapp_mask(netdev, &app);
	prio_map = tmp_map;

	app.selector = IEEE_8021QAZ_APP_SEL_DGRAM;
	app.protocol = ROCE_V2_UDP_DPORT;
	tmp_map = dcb_ieee_getapp_mask(netdev, &app);
	prio_map |= tmp_map;

	return prio_map;
}

static void bnxt_re_parse_cid_map(u8 prio_map, u8 *cid_map, u16 *cosq)
{
	u16 prio;
	u8 id;

	for (prio = 0, id = 0; prio < 8; prio++) {
		if (prio_map & (1 << prio)) {
			cosq[id] = cid_map[prio];
			id++;
			if (id == 2) /* Max 2 tcs supported */
				break;
		}
	}
}

static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev)
{
	u8 prio_map = 0;
	u64 cid_map;
	int rc;

	/* Get priority for roce */
	prio_map = bnxt_re_get_priority_mask(rdev);

	if (prio_map == rdev->cur_prio_map)
		return 0;
	rdev->cur_prio_map = prio_map;
	/* Get cosq id for this priority */
	rc = bnxt_re_query_hwrm_pri2cos(rdev, 0, &cid_map);
	if (rc) {
		dev_warn(rdev_to_dev(rdev), "no cos for p_mask %x\n", prio_map);
		return rc;
	}
	/* Parse CoS IDs for app priority */
	bnxt_re_parse_cid_map(prio_map, (u8 *)&cid_map, rdev->cosq);

	/* Config BONO. */
	rc = bnxt_qplib_map_tc2cos(&rdev->qplib_res, rdev->cosq);
	if (rc) {
		dev_warn(rdev_to_dev(rdev), "no tc for cos{%x, %x}\n",
			 rdev->cosq[0], rdev->cosq[1]);
		return rc;
	}

	/* Actual priorities are not programmed as they are already
	 * done by L2 driver; just enable or disable priority vlan tagging
	 */
	if ((prio_map == 0 && rdev->qplib_res.prio) ||
	    (prio_map != 0 && !rdev->qplib_res.prio)) {
		rdev->qplib_res.prio = prio_map ? true : false;

		bnxt_re_update_gid(rdev);
	}

	return 0;
}

static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait)
{
	int i, rc;

	if (test_and_clear_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags)) {
		for (i = 0; i < ARRAY_SIZE(bnxt_re_attributes); i++)
			device_remove_file(&rdev->ibdev.dev,
					   bnxt_re_attributes[i]);
		/* Cleanup ib dev */
		bnxt_re_unregister_ib(rdev);
	}
	if (test_and_clear_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags))
		cancel_delayed_work(&rdev->worker);

	bnxt_re_cleanup_res(rdev);
	bnxt_re_free_res(rdev, lock_wait);

	if (test_and_clear_bit(BNXT_RE_FLAG_RCFW_CHANNEL_EN, &rdev->flags)) {
		rc = bnxt_qplib_deinit_rcfw(&rdev->rcfw);
		if (rc)
			dev_warn(rdev_to_dev(rdev),
				 "Failed to deinitialize RCFW: %#x", rc);
		bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id,
					   lock_wait);
		bnxt_qplib_free_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx);
		bnxt_qplib_disable_rcfw_channel(&rdev->rcfw);
		bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id, lock_wait);
		bnxt_qplib_free_rcfw_channel(&rdev->rcfw);
	}
	if (test_and_clear_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags)) {
		rc = bnxt_re_free_msix(rdev, lock_wait);
		if (rc)
			dev_warn(rdev_to_dev(rdev),
				 "Failed to free MSI-X vectors: %#x", rc);
	}
	if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags)) {
		rc = bnxt_re_unregister_netdev(rdev, lock_wait);
		if (rc)
			dev_warn(rdev_to_dev(rdev),
				 "Failed to unregister with netdev: %#x", rc);
	}
}

/* worker thread for polling periodic events. Now used for QoS programming*/
static void bnxt_re_worker(struct work_struct *work)
{
	struct bnxt_re_dev *rdev = container_of(work, struct bnxt_re_dev,
						worker.work);

	bnxt_re_setup_qos(rdev);
	schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000));
}

static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev)
{
	int i, j, rc;

	/* Registered a new RoCE device instance to netdev */
	rc = bnxt_re_register_netdev(rdev);
	if (rc) {
		pr_err("Failed to register with netedev: %#x\n", rc);
		return -EINVAL;
	}
	set_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);

	/* Check whether VF or PF */
	bnxt_re_get_sriov_func_type(rdev);

	rc = bnxt_re_request_msix(rdev);
	if (rc) {
		pr_err("Failed to get MSI-X vectors: %#x\n", rc);
		rc = -EINVAL;
		goto fail;
	}
	set_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags);

	/* Establish RCFW Communication Channel to initialize the context
	 * memory for the function and all child VFs
	 */
	rc = bnxt_qplib_alloc_rcfw_channel(rdev->en_dev->pdev, &rdev->rcfw,
					   BNXT_RE_MAX_QPC_COUNT);
	if (rc) {
		pr_err("Failed to allocate RCFW Channel: %#x\n", rc);
		goto fail;
	}
	rc = bnxt_re_net_ring_alloc
			(rdev, rdev->rcfw.creq.pbl[PBL_LVL_0].pg_map_arr,
			 rdev->rcfw.creq.pbl[rdev->rcfw.creq.level].pg_count,
			 HWRM_RING_ALLOC_CMPL, BNXT_QPLIB_CREQE_MAX_CNT - 1,
			 rdev->msix_entries[BNXT_RE_AEQ_IDX].ring_idx,
			 &rdev->rcfw.creq_ring_id);
	if (rc) {
		pr_err("Failed to allocate CREQ: %#x\n", rc);
		goto free_rcfw;
	}
	rc = bnxt_qplib_enable_rcfw_channel
				(rdev->en_dev->pdev, &rdev->rcfw,
				 rdev->msix_entries[BNXT_RE_AEQ_IDX].vector,
				 rdev->msix_entries[BNXT_RE_AEQ_IDX].db_offset,
				 rdev->is_virtfn, &bnxt_re_aeq_handler);
	if (rc) {
		pr_err("Failed to enable RCFW channel: %#x\n", rc);
		goto free_ring;
	}

	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr,
				     rdev->is_virtfn);
	if (rc)
		goto disable_rcfw;
	if (!rdev->is_virtfn)
		bnxt_re_set_resource_limits(rdev);

	rc = bnxt_qplib_alloc_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx, 0);
	if (rc) {
		pr_err("Failed to allocate QPLIB context: %#x\n", rc);
		goto disable_rcfw;
	}
	rc = bnxt_re_net_stats_ctx_alloc(rdev,
					 rdev->qplib_ctx.stats.dma_map,
					 &rdev->qplib_ctx.stats.fw_id);
	if (rc) {
		pr_err("Failed to allocate stats context: %#x\n", rc);
		goto free_ctx;
	}

	rc = bnxt_qplib_init_rcfw(&rdev->rcfw, &rdev->qplib_ctx,
				  rdev->is_virtfn);
	if (rc) {
		pr_err("Failed to initialize RCFW: %#x\n", rc);
		goto free_sctx;
	}
	set_bit(BNXT_RE_FLAG_RCFW_CHANNEL_EN, &rdev->flags);

	/* Resources based on the 'new' device caps */
	rc = bnxt_re_alloc_res(rdev);
	if (rc) {
		pr_err("Failed to allocate resources: %#x\n", rc);
		goto fail;
	}
	rc = bnxt_re_init_res(rdev);
	if (rc) {
		pr_err("Failed to initialize resources: %#x\n", rc);
		goto fail;
	}

	if (!rdev->is_virtfn) {
		rc = bnxt_re_setup_qos(rdev);
		if (rc)
			pr_info("RoCE priority not yet configured\n");

		INIT_DELAYED_WORK(&rdev->worker, bnxt_re_worker);
		set_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags);
		schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000));
	}

	/* Register ib dev */
	rc = bnxt_re_register_ib(rdev);
	if (rc) {
		pr_err("Failed to register with IB: %#x\n", rc);
		goto fail;
	}
	dev_info(rdev_to_dev(rdev), "Device registered successfully");
	for (i = 0; i < ARRAY_SIZE(bnxt_re_attributes); i++) {
		rc = device_create_file(&rdev->ibdev.dev,
					bnxt_re_attributes[i]);
		if (rc) {
			dev_err(rdev_to_dev(rdev),
				"Failed to create IB sysfs: %#x", rc);
			/* Must clean up all created device files */
			for (j = 0; j < i; j++)
				device_remove_file(&rdev->ibdev.dev,
						   bnxt_re_attributes[j]);
			bnxt_re_unregister_ib(rdev);
			goto fail;
		}
	}
	set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags);
	ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
			 &rdev->active_width);
	set_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS, &rdev->flags);
	bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_PORT_ACTIVE);
	bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_GID_CHANGE);

	return 0;
free_sctx:
	bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id, true);
free_ctx:
	bnxt_qplib_free_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx);
disable_rcfw:
	bnxt_qplib_disable_rcfw_channel(&rdev->rcfw);
free_ring:
	bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id, true);
free_rcfw:
	bnxt_qplib_free_rcfw_channel(&rdev->rcfw);
fail:
	bnxt_re_ib_unreg(rdev, true);
	return rc;
}

static void bnxt_re_dev_unreg(struct bnxt_re_dev *rdev)
{
	struct bnxt_en_dev *en_dev = rdev->en_dev;
	struct net_device *netdev = rdev->netdev;

	bnxt_re_dev_remove(rdev);

	if (netdev)
		bnxt_re_dev_unprobe(netdev, en_dev);
}

static int bnxt_re_dev_reg(struct bnxt_re_dev **rdev, struct net_device *netdev)
{
	struct bnxt_en_dev *en_dev;
	int rc = 0;

	if (!is_bnxt_re_dev(netdev))
		return -ENODEV;

	en_dev = bnxt_re_dev_probe(netdev);
	if (IS_ERR(en_dev)) {
		if (en_dev != ERR_PTR(-ENODEV))
			pr_err("%s: Failed to probe\n", ROCE_DRV_MODULE_NAME);
		rc = PTR_ERR(en_dev);
		goto exit;
	}
	*rdev = bnxt_re_dev_add(netdev, en_dev);
	if (!*rdev) {
		rc = -ENOMEM;
		bnxt_re_dev_unprobe(netdev, en_dev);
		goto exit;
	}
exit:
	return rc;
}

static void bnxt_re_remove_one(struct bnxt_re_dev *rdev)
{
	pci_dev_put(rdev->en_dev->pdev);
}

/* Handle all deferred netevents tasks */
static void bnxt_re_task(struct work_struct *work)
{
	struct bnxt_re_work *re_work;
	struct bnxt_re_dev *rdev;
	int rc = 0;

	re_work = container_of(work, struct bnxt_re_work, work);
	rdev = re_work->rdev;

	if (re_work->event != NETDEV_REGISTER &&
	    !test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
		return;

	switch (re_work->event) {
	case NETDEV_REGISTER:
		rc = bnxt_re_ib_reg(rdev);
		if (rc)
			dev_err(rdev_to_dev(rdev),
				"Failed to register with IB: %#x", rc);
		break;
	case NETDEV_UP:
		bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1,
				       IB_EVENT_PORT_ACTIVE);
		break;
	case NETDEV_DOWN:
		bnxt_re_dev_stop(rdev);
		break;
	case NETDEV_CHANGE:
		if (!netif_carrier_ok(rdev->netdev))
			bnxt_re_dev_stop(rdev);
		else if (netif_carrier_ok(rdev->netdev))
			bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1,
					       IB_EVENT_PORT_ACTIVE);
		ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
				 &rdev->active_width);
		break;
	default:
		break;
	}
	smp_mb__before_atomic();
	atomic_dec(&rdev->sched_count);
	kfree(re_work);
}

static void bnxt_re_init_one(struct bnxt_re_dev *rdev)
{
	pci_dev_get(rdev->en_dev->pdev);
}

/*
 * "Notifier chain callback can be invoked for the same chain from
 * different CPUs at the same time".
 *
 * For cases when the netdev is already present, our call to the
 * register_netdevice_notifier() will actually get the rtnl_lock()
 * before sending NETDEV_REGISTER and (if up) NETDEV_UP
 * events.
 *
 * But for cases when the netdev is not already present, the notifier
 * chain is subjected to be invoked from different CPUs simultaneously.
 *
 * This is protected by the netdev_mutex.
 */
static int bnxt_re_netdev_event(struct notifier_block *notifier,
				unsigned long event, void *ptr)
{
	struct net_device *real_dev, *netdev = netdev_notifier_info_to_dev(ptr);
	struct bnxt_re_work *re_work;
	struct bnxt_re_dev *rdev;
	int rc = 0;
	bool sch_work = false;

	real_dev = rdma_vlan_dev_real_dev(netdev);
	if (!real_dev)
		real_dev = netdev;

	rdev = bnxt_re_from_netdev(real_dev);
	if (!rdev && event != NETDEV_REGISTER)
		goto exit;
	if (real_dev != netdev)
		goto exit;

	switch (event) {
	case NETDEV_REGISTER:
		if (rdev)
			break;
		rc = bnxt_re_dev_reg(&rdev, real_dev);
		if (rc == -ENODEV)
			break;
		if (rc) {
			pr_err("Failed to register with the device %s: %#x\n",
			       real_dev->name, rc);
			break;
		}
		bnxt_re_init_one(rdev);
		sch_work = true;
		break;

	case NETDEV_UNREGISTER:
		/* netdev notifier will call NETDEV_UNREGISTER again later since
		 * we are still holding the reference to the netdev
		 */
		if (atomic_read(&rdev->sched_count) > 0)
			goto exit;
		bnxt_re_ib_unreg(rdev, false);
		bnxt_re_remove_one(rdev);
		bnxt_re_dev_unreg(rdev);
		break;

	default:
		sch_work = true;
		break;
	}
	if (sch_work) {
		/* Allocate for the deferred task */
		re_work = kzalloc(sizeof(*re_work), GFP_ATOMIC);
		if (re_work) {
			re_work->rdev = rdev;
			re_work->event = event;
			re_work->vlan_dev = (real_dev == netdev ?
					     NULL : netdev);
			INIT_WORK(&re_work->work, bnxt_re_task);
			atomic_inc(&rdev->sched_count);
			queue_work(bnxt_re_wq, &re_work->work);
		}
	}

exit:
	return NOTIFY_DONE;
}

static struct notifier_block bnxt_re_netdev_notifier = {
	.notifier_call = bnxt_re_netdev_event
};

static int __init bnxt_re_mod_init(void)
{
	int rc = 0;

	pr_info("%s: %s", ROCE_DRV_MODULE_NAME, version);

	bnxt_re_wq = create_singlethread_workqueue("bnxt_re");
	if (!bnxt_re_wq)
		return -ENOMEM;

	INIT_LIST_HEAD(&bnxt_re_dev_list);

	rc = register_netdevice_notifier(&bnxt_re_netdev_notifier);
	if (rc) {
		pr_err("%s: Cannot register to netdevice_notifier",
		       ROCE_DRV_MODULE_NAME);
		goto err_netdev;
	}
	return 0;

err_netdev:
	destroy_workqueue(bnxt_re_wq);

	return rc;
}

static void __exit bnxt_re_mod_exit(void)
{
	struct bnxt_re_dev *rdev, *next;
	LIST_HEAD(to_be_deleted);

	mutex_lock(&bnxt_re_dev_lock);
	/* Free all adapter allocated resources */
	if (!list_empty(&bnxt_re_dev_list))
		list_splice_init(&bnxt_re_dev_list, &to_be_deleted);
	mutex_unlock(&bnxt_re_dev_lock);
       /*
	* Cleanup the devices in reverse order so that the VF device
	* cleanup is done before PF cleanup
	*/
	list_for_each_entry_safe_reverse(rdev, next, &to_be_deleted, list) {
		dev_info(rdev_to_dev(rdev), "Unregistering Device");
		/*
		 * Flush out any scheduled tasks before destroying the
		 * resources
		 */
		flush_workqueue(bnxt_re_wq);
		bnxt_re_dev_stop(rdev);
		bnxt_re_ib_unreg(rdev, true);
		bnxt_re_remove_one(rdev);
		bnxt_re_dev_unreg(rdev);
	}
	unregister_netdevice_notifier(&bnxt_re_netdev_notifier);
	if (bnxt_re_wq)
		destroy_workqueue(bnxt_re_wq);
}

module_init(bnxt_re_mod_init);
module_exit(bnxt_re_mod_exit);