summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/mlx5/cq.c
blob: 9c0e67bd2ba7326cf711e3eba0cf2e6bbd630d3e (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
/*
 * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/kref.h>
#include <rdma/ib_umem.h>
#include <rdma/ib_user_verbs.h>
#include <rdma/ib_cache.h>
#include "mlx5_ib.h"
#include "user.h"

static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq)
{
	struct ib_cq *ibcq = &to_mibcq(cq)->ibcq;

	ibcq->comp_handler(ibcq, ibcq->cq_context);
}

static void mlx5_ib_cq_event(struct mlx5_core_cq *mcq, enum mlx5_event type)
{
	struct mlx5_ib_cq *cq = container_of(mcq, struct mlx5_ib_cq, mcq);
	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
	struct ib_cq *ibcq = &cq->ibcq;
	struct ib_event event;

	if (type != MLX5_EVENT_TYPE_CQ_ERROR) {
		mlx5_ib_warn(dev, "Unexpected event type %d on CQ %06x\n",
			     type, mcq->cqn);
		return;
	}

	if (ibcq->event_handler) {
		event.device     = &dev->ib_dev;
		event.event      = IB_EVENT_CQ_ERR;
		event.element.cq = ibcq;
		ibcq->event_handler(&event, ibcq->cq_context);
	}
}

static void *get_cqe_from_buf(struct mlx5_ib_cq_buf *buf, int n, int size)
{
	return mlx5_buf_offset(&buf->buf, n * size);
}

static void *get_cqe(struct mlx5_ib_cq *cq, int n)
{
	return get_cqe_from_buf(&cq->buf, n, cq->mcq.cqe_sz);
}

static u8 sw_ownership_bit(int n, int nent)
{
	return (n & nent) ? 1 : 0;
}

static void *get_sw_cqe(struct mlx5_ib_cq *cq, int n)
{
	void *cqe = get_cqe(cq, n & cq->ibcq.cqe);
	struct mlx5_cqe64 *cqe64;

	cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;

	if (likely((cqe64->op_own) >> 4 != MLX5_CQE_INVALID) &&
	    !((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & (cq->ibcq.cqe + 1)))) {
		return cqe;
	} else {
		return NULL;
	}
}

static void *next_cqe_sw(struct mlx5_ib_cq *cq)
{
	return get_sw_cqe(cq, cq->mcq.cons_index);
}

static enum ib_wc_opcode get_umr_comp(struct mlx5_ib_wq *wq, int idx)
{
	switch (wq->wr_data[idx]) {
	case MLX5_IB_WR_UMR:
		return 0;

	case IB_WR_LOCAL_INV:
		return IB_WC_LOCAL_INV;

	case IB_WR_REG_MR:
		return IB_WC_REG_MR;

	default:
		pr_warn("unknown completion status\n");
		return 0;
	}
}

static void handle_good_req(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
			    struct mlx5_ib_wq *wq, int idx)
{
	wc->wc_flags = 0;
	switch (be32_to_cpu(cqe->sop_drop_qpn) >> 24) {
	case MLX5_OPCODE_RDMA_WRITE_IMM:
		wc->wc_flags |= IB_WC_WITH_IMM;
	case MLX5_OPCODE_RDMA_WRITE:
		wc->opcode    = IB_WC_RDMA_WRITE;
		break;
	case MLX5_OPCODE_SEND_IMM:
		wc->wc_flags |= IB_WC_WITH_IMM;
	case MLX5_OPCODE_SEND:
	case MLX5_OPCODE_SEND_INVAL:
		wc->opcode    = IB_WC_SEND;
		break;
	case MLX5_OPCODE_RDMA_READ:
		wc->opcode    = IB_WC_RDMA_READ;
		wc->byte_len  = be32_to_cpu(cqe->byte_cnt);
		break;
	case MLX5_OPCODE_ATOMIC_CS:
		wc->opcode    = IB_WC_COMP_SWAP;
		wc->byte_len  = 8;
		break;
	case MLX5_OPCODE_ATOMIC_FA:
		wc->opcode    = IB_WC_FETCH_ADD;
		wc->byte_len  = 8;
		break;
	case MLX5_OPCODE_ATOMIC_MASKED_CS:
		wc->opcode    = IB_WC_MASKED_COMP_SWAP;
		wc->byte_len  = 8;
		break;
	case MLX5_OPCODE_ATOMIC_MASKED_FA:
		wc->opcode    = IB_WC_MASKED_FETCH_ADD;
		wc->byte_len  = 8;
		break;
	case MLX5_OPCODE_UMR:
		wc->opcode = get_umr_comp(wq, idx);
		break;
	}
}

enum {
	MLX5_GRH_IN_BUFFER = 1,
	MLX5_GRH_IN_CQE	   = 2,
};

static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
			     struct mlx5_ib_qp *qp)
{
	enum rdma_link_layer ll = rdma_port_get_link_layer(qp->ibqp.device, 1);
	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.device);
	struct mlx5_ib_srq *srq;
	struct mlx5_ib_wq *wq;
	u16 wqe_ctr;
	u8 g;

	if (qp->ibqp.srq || qp->ibqp.xrcd) {
		struct mlx5_core_srq *msrq = NULL;

		if (qp->ibqp.xrcd) {
			msrq = mlx5_core_get_srq(dev->mdev,
						 be32_to_cpu(cqe->srqn));
			srq = to_mibsrq(msrq);
		} else {
			srq = to_msrq(qp->ibqp.srq);
		}
		if (srq) {
			wqe_ctr = be16_to_cpu(cqe->wqe_counter);
			wc->wr_id = srq->wrid[wqe_ctr];
			mlx5_ib_free_srq_wqe(srq, wqe_ctr);
			if (msrq && atomic_dec_and_test(&msrq->refcount))
				complete(&msrq->free);
		}
	} else {
		wq	  = &qp->rq;
		wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
		++wq->tail;
	}
	wc->byte_len = be32_to_cpu(cqe->byte_cnt);

	switch (cqe->op_own >> 4) {
	case MLX5_CQE_RESP_WR_IMM:
		wc->opcode	= IB_WC_RECV_RDMA_WITH_IMM;
		wc->wc_flags	= IB_WC_WITH_IMM;
		wc->ex.imm_data = cqe->imm_inval_pkey;
		break;
	case MLX5_CQE_RESP_SEND:
		wc->opcode   = IB_WC_RECV;
		wc->wc_flags = IB_WC_IP_CSUM_OK;
		if (unlikely(!((cqe->hds_ip_ext & CQE_L3_OK) &&
			       (cqe->hds_ip_ext & CQE_L4_OK))))
			wc->wc_flags = 0;
		break;
	case MLX5_CQE_RESP_SEND_IMM:
		wc->opcode	= IB_WC_RECV;
		wc->wc_flags	= IB_WC_WITH_IMM;
		wc->ex.imm_data = cqe->imm_inval_pkey;
		break;
	case MLX5_CQE_RESP_SEND_INV:
		wc->opcode	= IB_WC_RECV;
		wc->wc_flags	= IB_WC_WITH_INVALIDATE;
		wc->ex.invalidate_rkey = be32_to_cpu(cqe->imm_inval_pkey);
		break;
	}
	wc->slid	   = be16_to_cpu(cqe->slid);
	wc->sl		   = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0xf;
	wc->src_qp	   = be32_to_cpu(cqe->flags_rqpn) & 0xffffff;
	wc->dlid_path_bits = cqe->ml_path;
	g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
	wc->wc_flags |= g ? IB_WC_GRH : 0;
	if (unlikely(is_qp1(qp->ibqp.qp_type))) {
		u16 pkey = be32_to_cpu(cqe->imm_inval_pkey) & 0xffff;

		ib_find_cached_pkey(&dev->ib_dev, qp->port, pkey,
				    &wc->pkey_index);
	} else {
		wc->pkey_index = 0;
	}

	if (ll != IB_LINK_LAYER_ETHERNET)
		return;

	switch (wc->sl & 0x3) {
	case MLX5_CQE_ROCE_L3_HEADER_TYPE_GRH:
		wc->network_hdr_type = RDMA_NETWORK_IB;
		break;
	case MLX5_CQE_ROCE_L3_HEADER_TYPE_IPV6:
		wc->network_hdr_type = RDMA_NETWORK_IPV6;
		break;
	case MLX5_CQE_ROCE_L3_HEADER_TYPE_IPV4:
		wc->network_hdr_type = RDMA_NETWORK_IPV4;
		break;
	}
	wc->wc_flags |= IB_WC_WITH_NETWORK_HDR_TYPE;
}

static void dump_cqe(struct mlx5_ib_dev *dev, struct mlx5_err_cqe *cqe)
{
	__be32 *p = (__be32 *)cqe;
	int i;

	mlx5_ib_warn(dev, "dump error cqe\n");
	for (i = 0; i < sizeof(*cqe) / 16; i++, p += 4)
		pr_info("%08x %08x %08x %08x\n", be32_to_cpu(p[0]),
			be32_to_cpu(p[1]), be32_to_cpu(p[2]),
			be32_to_cpu(p[3]));
}

static void mlx5_handle_error_cqe(struct mlx5_ib_dev *dev,
				  struct mlx5_err_cqe *cqe,
				  struct ib_wc *wc)
{
	int dump = 1;

	switch (cqe->syndrome) {
	case MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR:
		wc->status = IB_WC_LOC_LEN_ERR;
		break;
	case MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR:
		wc->status = IB_WC_LOC_QP_OP_ERR;
		break;
	case MLX5_CQE_SYNDROME_LOCAL_PROT_ERR:
		wc->status = IB_WC_LOC_PROT_ERR;
		break;
	case MLX5_CQE_SYNDROME_WR_FLUSH_ERR:
		dump = 0;
		wc->status = IB_WC_WR_FLUSH_ERR;
		break;
	case MLX5_CQE_SYNDROME_MW_BIND_ERR:
		wc->status = IB_WC_MW_BIND_ERR;
		break;
	case MLX5_CQE_SYNDROME_BAD_RESP_ERR:
		wc->status = IB_WC_BAD_RESP_ERR;
		break;
	case MLX5_CQE_SYNDROME_LOCAL_ACCESS_ERR:
		wc->status = IB_WC_LOC_ACCESS_ERR;
		break;
	case MLX5_CQE_SYNDROME_REMOTE_INVAL_REQ_ERR:
		wc->status = IB_WC_REM_INV_REQ_ERR;
		break;
	case MLX5_CQE_SYNDROME_REMOTE_ACCESS_ERR:
		wc->status = IB_WC_REM_ACCESS_ERR;
		break;
	case MLX5_CQE_SYNDROME_REMOTE_OP_ERR:
		wc->status = IB_WC_REM_OP_ERR;
		break;
	case MLX5_CQE_SYNDROME_TRANSPORT_RETRY_EXC_ERR:
		wc->status = IB_WC_RETRY_EXC_ERR;
		dump = 0;
		break;
	case MLX5_CQE_SYNDROME_RNR_RETRY_EXC_ERR:
		wc->status = IB_WC_RNR_RETRY_EXC_ERR;
		dump = 0;
		break;
	case MLX5_CQE_SYNDROME_REMOTE_ABORTED_ERR:
		wc->status = IB_WC_REM_ABORT_ERR;
		break;
	default:
		wc->status = IB_WC_GENERAL_ERR;
		break;
	}

	wc->vendor_err = cqe->vendor_err_synd;
	if (dump)
		dump_cqe(dev, cqe);
}

static int is_atomic_response(struct mlx5_ib_qp *qp, uint16_t idx)
{
	/* TBD: waiting decision
	*/
	return 0;
}

static void *mlx5_get_atomic_laddr(struct mlx5_ib_qp *qp, uint16_t idx)
{
	struct mlx5_wqe_data_seg *dpseg;
	void *addr;

	dpseg = mlx5_get_send_wqe(qp, idx) + sizeof(struct mlx5_wqe_ctrl_seg) +
		sizeof(struct mlx5_wqe_raddr_seg) +
		sizeof(struct mlx5_wqe_atomic_seg);
	addr = (void *)(unsigned long)be64_to_cpu(dpseg->addr);
	return addr;
}

static void handle_atomic(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64,
			  uint16_t idx)
{
	void *addr;
	int byte_count;
	int i;

	if (!is_atomic_response(qp, idx))
		return;

	byte_count = be32_to_cpu(cqe64->byte_cnt);
	addr = mlx5_get_atomic_laddr(qp, idx);

	if (byte_count == 4) {
		*(uint32_t *)addr = be32_to_cpu(*((__be32 *)addr));
	} else {
		for (i = 0; i < byte_count; i += 8) {
			*(uint64_t *)addr = be64_to_cpu(*((__be64 *)addr));
			addr += 8;
		}
	}

	return;
}

static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64,
			   u16 tail, u16 head)
{
	u16 idx;

	do {
		idx = tail & (qp->sq.wqe_cnt - 1);
		handle_atomic(qp, cqe64, idx);
		if (idx == head)
			break;

		tail = qp->sq.w_list[idx].next;
	} while (1);
	tail = qp->sq.w_list[idx].next;
	qp->sq.last_poll = tail;
}

static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
{
	mlx5_buf_free(dev->mdev, &buf->buf);
}

static void get_sig_err_item(struct mlx5_sig_err_cqe *cqe,
			     struct ib_sig_err *item)
{
	u16 syndrome = be16_to_cpu(cqe->syndrome);

#define GUARD_ERR   (1 << 13)
#define APPTAG_ERR  (1 << 12)
#define REFTAG_ERR  (1 << 11)

	if (syndrome & GUARD_ERR) {
		item->err_type = IB_SIG_BAD_GUARD;
		item->expected = be32_to_cpu(cqe->expected_trans_sig) >> 16;
		item->actual = be32_to_cpu(cqe->actual_trans_sig) >> 16;
	} else
	if (syndrome & REFTAG_ERR) {
		item->err_type = IB_SIG_BAD_REFTAG;
		item->expected = be32_to_cpu(cqe->expected_reftag);
		item->actual = be32_to_cpu(cqe->actual_reftag);
	} else
	if (syndrome & APPTAG_ERR) {
		item->err_type = IB_SIG_BAD_APPTAG;
		item->expected = be32_to_cpu(cqe->expected_trans_sig) & 0xffff;
		item->actual = be32_to_cpu(cqe->actual_trans_sig) & 0xffff;
	} else {
		pr_err("Got signature completion error with bad syndrome %04x\n",
		       syndrome);
	}

	item->sig_err_offset = be64_to_cpu(cqe->err_offset);
	item->key = be32_to_cpu(cqe->mkey);
}

static int mlx5_poll_one(struct mlx5_ib_cq *cq,
			 struct mlx5_ib_qp **cur_qp,
			 struct ib_wc *wc)
{
	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
	struct mlx5_err_cqe *err_cqe;
	struct mlx5_cqe64 *cqe64;
	struct mlx5_core_qp *mqp;
	struct mlx5_ib_wq *wq;
	struct mlx5_sig_err_cqe *sig_err_cqe;
	struct mlx5_core_mkey *mmkey;
	struct mlx5_ib_mr *mr;
	uint8_t opcode;
	uint32_t qpn;
	u16 wqe_ctr;
	void *cqe;
	int idx;

repoll:
	cqe = next_cqe_sw(cq);
	if (!cqe)
		return -EAGAIN;

	cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;

	++cq->mcq.cons_index;

	/* Make sure we read CQ entry contents after we've checked the
	 * ownership bit.
	 */
	rmb();

	opcode = cqe64->op_own >> 4;
	if (unlikely(opcode == MLX5_CQE_RESIZE_CQ)) {
		if (likely(cq->resize_buf)) {
			free_cq_buf(dev, &cq->buf);
			cq->buf = *cq->resize_buf;
			kfree(cq->resize_buf);
			cq->resize_buf = NULL;
			goto repoll;
		} else {
			mlx5_ib_warn(dev, "unexpected resize cqe\n");
		}
	}

	qpn = ntohl(cqe64->sop_drop_qpn) & 0xffffff;
	if (!*cur_qp || (qpn != (*cur_qp)->ibqp.qp_num)) {
		/* We do not have to take the QP table lock here,
		 * because CQs will be locked while QPs are removed
		 * from the table.
		 */
		mqp = __mlx5_qp_lookup(dev->mdev, qpn);
		if (unlikely(!mqp)) {
			mlx5_ib_warn(dev, "CQE@CQ %06x for unknown QPN %6x\n",
				     cq->mcq.cqn, qpn);
			return -EINVAL;
		}

		*cur_qp = to_mibqp(mqp);
	}

	wc->qp  = &(*cur_qp)->ibqp;
	switch (opcode) {
	case MLX5_CQE_REQ:
		wq = &(*cur_qp)->sq;
		wqe_ctr = be16_to_cpu(cqe64->wqe_counter);
		idx = wqe_ctr & (wq->wqe_cnt - 1);
		handle_good_req(wc, cqe64, wq, idx);
		handle_atomics(*cur_qp, cqe64, wq->last_poll, idx);
		wc->wr_id = wq->wrid[idx];
		wq->tail = wq->wqe_head[idx] + 1;
		wc->status = IB_WC_SUCCESS;
		break;
	case MLX5_CQE_RESP_WR_IMM:
	case MLX5_CQE_RESP_SEND:
	case MLX5_CQE_RESP_SEND_IMM:
	case MLX5_CQE_RESP_SEND_INV:
		handle_responder(wc, cqe64, *cur_qp);
		wc->status = IB_WC_SUCCESS;
		break;
	case MLX5_CQE_RESIZE_CQ:
		break;
	case MLX5_CQE_REQ_ERR:
	case MLX5_CQE_RESP_ERR:
		err_cqe = (struct mlx5_err_cqe *)cqe64;
		mlx5_handle_error_cqe(dev, err_cqe, wc);
		mlx5_ib_dbg(dev, "%s error cqe on cqn 0x%x:\n",
			    opcode == MLX5_CQE_REQ_ERR ?
			    "Requestor" : "Responder", cq->mcq.cqn);
		mlx5_ib_dbg(dev, "syndrome 0x%x, vendor syndrome 0x%x\n",
			    err_cqe->syndrome, err_cqe->vendor_err_synd);
		if (opcode == MLX5_CQE_REQ_ERR) {
			wq = &(*cur_qp)->sq;
			wqe_ctr = be16_to_cpu(cqe64->wqe_counter);
			idx = wqe_ctr & (wq->wqe_cnt - 1);
			wc->wr_id = wq->wrid[idx];
			wq->tail = wq->wqe_head[idx] + 1;
		} else {
			struct mlx5_ib_srq *srq;

			if ((*cur_qp)->ibqp.srq) {
				srq = to_msrq((*cur_qp)->ibqp.srq);
				wqe_ctr = be16_to_cpu(cqe64->wqe_counter);
				wc->wr_id = srq->wrid[wqe_ctr];
				mlx5_ib_free_srq_wqe(srq, wqe_ctr);
			} else {
				wq = &(*cur_qp)->rq;
				wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
				++wq->tail;
			}
		}
		break;
	case MLX5_CQE_SIG_ERR:
		sig_err_cqe = (struct mlx5_sig_err_cqe *)cqe64;

		read_lock(&dev->mdev->priv.mkey_table.lock);
		mmkey = __mlx5_mr_lookup(dev->mdev,
					 mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
		if (unlikely(!mmkey)) {
			read_unlock(&dev->mdev->priv.mkey_table.lock);
			mlx5_ib_warn(dev, "CQE@CQ %06x for unknown MR %6x\n",
				     cq->mcq.cqn, be32_to_cpu(sig_err_cqe->mkey));
			return -EINVAL;
		}

		mr = to_mibmr(mmkey);
		get_sig_err_item(sig_err_cqe, &mr->sig->err_item);
		mr->sig->sig_err_exists = true;
		mr->sig->sigerr_count++;

		mlx5_ib_warn(dev, "CQN: 0x%x Got SIGERR on key: 0x%x err_type %x err_offset %llx expected %x actual %x\n",
			     cq->mcq.cqn, mr->sig->err_item.key,
			     mr->sig->err_item.err_type,
			     mr->sig->err_item.sig_err_offset,
			     mr->sig->err_item.expected,
			     mr->sig->err_item.actual);

		read_unlock(&dev->mdev->priv.mkey_table.lock);
		goto repoll;
	}

	return 0;
}

static int poll_soft_wc(struct mlx5_ib_cq *cq, int num_entries,
			struct ib_wc *wc)
{
	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
	struct mlx5_ib_wc *soft_wc, *next;
	int npolled = 0;

	list_for_each_entry_safe(soft_wc, next, &cq->wc_list, list) {
		if (npolled >= num_entries)
			break;

		mlx5_ib_dbg(dev, "polled software generated completion on CQ 0x%x\n",
			    cq->mcq.cqn);

		wc[npolled++] = soft_wc->wc;
		list_del(&soft_wc->list);
		kfree(soft_wc);
	}

	return npolled;
}

int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
{
	struct mlx5_ib_cq *cq = to_mcq(ibcq);
	struct mlx5_ib_qp *cur_qp = NULL;
	unsigned long flags;
	int soft_polled = 0;
	int npolled;
	int err = 0;

	spin_lock_irqsave(&cq->lock, flags);

	if (unlikely(!list_empty(&cq->wc_list)))
		soft_polled = poll_soft_wc(cq, num_entries, wc);

	for (npolled = 0; npolled < num_entries - soft_polled; npolled++) {
		err = mlx5_poll_one(cq, &cur_qp, wc + soft_polled + npolled);
		if (err)
			break;
	}

	if (npolled)
		mlx5_cq_set_ci(&cq->mcq);

	spin_unlock_irqrestore(&cq->lock, flags);

	if (err == 0 || err == -EAGAIN)
		return soft_polled + npolled;
	else
		return err;
}

int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
{
	struct mlx5_core_dev *mdev = to_mdev(ibcq->device)->mdev;
	struct mlx5_ib_cq *cq = to_mcq(ibcq);
	void __iomem *uar_page = mdev->priv.uuari.uars[0].map;
	unsigned long irq_flags;
	int ret = 0;

	spin_lock_irqsave(&cq->lock, irq_flags);
	if (cq->notify_flags != IB_CQ_NEXT_COMP)
		cq->notify_flags = flags & IB_CQ_SOLICITED_MASK;

	if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && !list_empty(&cq->wc_list))
		ret = 1;
	spin_unlock_irqrestore(&cq->lock, irq_flags);

	mlx5_cq_arm(&cq->mcq,
		    (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ?
		    MLX5_CQ_DB_REQ_NOT_SOL : MLX5_CQ_DB_REQ_NOT,
		    uar_page,
		    MLX5_GET_DOORBELL_LOCK(&mdev->priv.cq_uar_lock),
		    to_mcq(ibcq)->mcq.cons_index);

	return ret;
}

static int alloc_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf,
			int nent, int cqe_size)
{
	int err;

	err = mlx5_buf_alloc(dev->mdev, nent * cqe_size, &buf->buf);
	if (err)
		return err;

	buf->cqe_size = cqe_size;
	buf->nent = nent;

	return 0;
}

static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
			  struct ib_ucontext *context, struct mlx5_ib_cq *cq,
			  int entries, struct mlx5_create_cq_mbox_in **cqb,
			  int *cqe_size, int *index, int *inlen)
{
	struct mlx5_ib_create_cq ucmd;
	size_t ucmdlen;
	int page_shift;
	int npages;
	int ncont;
	int err;

	ucmdlen =
		(udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
		 sizeof(ucmd)) ? (sizeof(ucmd) -
				  sizeof(ucmd.reserved)) : sizeof(ucmd);

	if (ib_copy_from_udata(&ucmd, udata, ucmdlen))
		return -EFAULT;

	if (ucmdlen == sizeof(ucmd) &&
	    ucmd.reserved != 0)
		return -EINVAL;

	if (ucmd.cqe_size != 64 && ucmd.cqe_size != 128)
		return -EINVAL;

	*cqe_size = ucmd.cqe_size;

	cq->buf.umem = ib_umem_get(context, ucmd.buf_addr,
				   entries * ucmd.cqe_size,
				   IB_ACCESS_LOCAL_WRITE, 1);
	if (IS_ERR(cq->buf.umem)) {
		err = PTR_ERR(cq->buf.umem);
		return err;
	}

	err = mlx5_ib_db_map_user(to_mucontext(context), ucmd.db_addr,
				  &cq->db);
	if (err)
		goto err_umem;

	mlx5_ib_cont_pages(cq->buf.umem, ucmd.buf_addr, &npages, &page_shift,
			   &ncont, NULL);
	mlx5_ib_dbg(dev, "addr 0x%llx, size %u, npages %d, page_shift %d, ncont %d\n",
		    ucmd.buf_addr, entries * ucmd.cqe_size, npages, page_shift, ncont);

	*inlen = sizeof(**cqb) + sizeof(*(*cqb)->pas) * ncont;
	*cqb = mlx5_vzalloc(*inlen);
	if (!*cqb) {
		err = -ENOMEM;
		goto err_db;
	}
	mlx5_ib_populate_pas(dev, cq->buf.umem, page_shift, (*cqb)->pas, 0);
	(*cqb)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;

	*index = to_mucontext(context)->uuari.uars[0].index;

	return 0;

err_db:
	mlx5_ib_db_unmap_user(to_mucontext(context), &cq->db);

err_umem:
	ib_umem_release(cq->buf.umem);
	return err;
}

static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_ucontext *context)
{
	mlx5_ib_db_unmap_user(to_mucontext(context), &cq->db);
	ib_umem_release(cq->buf.umem);
}

static void init_cq_buf(struct mlx5_ib_cq *cq, struct mlx5_ib_cq_buf *buf)
{
	int i;
	void *cqe;
	struct mlx5_cqe64 *cqe64;

	for (i = 0; i < buf->nent; i++) {
		cqe = get_cqe_from_buf(buf, i, buf->cqe_size);
		cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64;
		cqe64->op_own = MLX5_CQE_INVALID << 4;
	}
}

static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
			    int entries, int cqe_size,
			    struct mlx5_create_cq_mbox_in **cqb,
			    int *index, int *inlen)
{
	int err;

	err = mlx5_db_alloc(dev->mdev, &cq->db);
	if (err)
		return err;

	cq->mcq.set_ci_db  = cq->db.db;
	cq->mcq.arm_db     = cq->db.db + 1;
	cq->mcq.cqe_sz = cqe_size;

	err = alloc_cq_buf(dev, &cq->buf, entries, cqe_size);
	if (err)
		goto err_db;

	init_cq_buf(cq, &cq->buf);

	*inlen = sizeof(**cqb) + sizeof(*(*cqb)->pas) * cq->buf.buf.npages;
	*cqb = mlx5_vzalloc(*inlen);
	if (!*cqb) {
		err = -ENOMEM;
		goto err_buf;
	}
	mlx5_fill_page_array(&cq->buf.buf, (*cqb)->pas);

	(*cqb)->ctx.log_pg_sz = cq->buf.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT;
	*index = dev->mdev->priv.uuari.uars[0].index;

	return 0;

err_buf:
	free_cq_buf(dev, &cq->buf);

err_db:
	mlx5_db_free(dev->mdev, &cq->db);
	return err;
}

static void destroy_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq)
{
	free_cq_buf(dev, &cq->buf);
	mlx5_db_free(dev->mdev, &cq->db);
}

static void notify_soft_wc_handler(struct work_struct *work)
{
	struct mlx5_ib_cq *cq = container_of(work, struct mlx5_ib_cq,
					     notify_work);

	cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
}

struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
				const struct ib_cq_init_attr *attr,
				struct ib_ucontext *context,
				struct ib_udata *udata)
{
	int entries = attr->cqe;
	int vector = attr->comp_vector;
	struct mlx5_create_cq_mbox_in *cqb = NULL;
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct mlx5_ib_cq *cq;
	int uninitialized_var(index);
	int uninitialized_var(inlen);
	int cqe_size;
	unsigned int irqn;
	int eqn;
	int err;

	if (entries < 0 ||
	    (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))))
		return ERR_PTR(-EINVAL);

	if (check_cq_create_flags(attr->flags))
		return ERR_PTR(-EOPNOTSUPP);

	entries = roundup_pow_of_two(entries + 1);
	if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)))
		return ERR_PTR(-EINVAL);

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

	cq->ibcq.cqe = entries - 1;
	mutex_init(&cq->resize_mutex);
	spin_lock_init(&cq->lock);
	cq->resize_buf = NULL;
	cq->resize_umem = NULL;
	cq->create_flags = attr->flags;

	if (context) {
		err = create_cq_user(dev, udata, context, cq, entries,
				     &cqb, &cqe_size, &index, &inlen);
		if (err)
			goto err_create;
	} else {
		/* for now choose 64 bytes till we have a proper interface */
		cqe_size = 64;
		err = create_cq_kernel(dev, cq, entries, cqe_size, &cqb,
				       &index, &inlen);
		if (err)
			goto err_create;

		INIT_WORK(&cq->notify_work, notify_soft_wc_handler);
	}

	cq->cqe_size = cqe_size;
	cqb->ctx.cqe_sz_flags = cqe_sz_to_mlx_sz(cqe_size) << 5;

	if (cq->create_flags & IB_CQ_FLAGS_IGNORE_OVERRUN)
		cqb->ctx.cqe_sz_flags |= (1 << 1);

	cqb->ctx.log_sz_usr_page = cpu_to_be32((ilog2(entries) << 24) | index);
	err = mlx5_vector2eqn(dev->mdev, vector, &eqn, &irqn);
	if (err)
		goto err_cqb;

	cqb->ctx.c_eqn = cpu_to_be16(eqn);
	cqb->ctx.db_record_addr = cpu_to_be64(cq->db.dma);

	err = mlx5_core_create_cq(dev->mdev, &cq->mcq, cqb, inlen);
	if (err)
		goto err_cqb;

	mlx5_ib_dbg(dev, "cqn 0x%x\n", cq->mcq.cqn);
	cq->mcq.irqn = irqn;
	if (context)
		cq->mcq.tasklet_ctx.comp = mlx5_ib_cq_comp;
	else
		cq->mcq.comp  = mlx5_ib_cq_comp;
	cq->mcq.event = mlx5_ib_cq_event;

	INIT_LIST_HEAD(&cq->wc_list);

	if (context)
		if (ib_copy_to_udata(udata, &cq->mcq.cqn, sizeof(__u32))) {
			err = -EFAULT;
			goto err_cmd;
		}


	kvfree(cqb);
	return &cq->ibcq;

err_cmd:
	mlx5_core_destroy_cq(dev->mdev, &cq->mcq);

err_cqb:
	kvfree(cqb);
	if (context)
		destroy_cq_user(cq, context);
	else
		destroy_cq_kernel(dev, cq);

err_create:
	kfree(cq);

	return ERR_PTR(err);
}


int mlx5_ib_destroy_cq(struct ib_cq *cq)
{
	struct mlx5_ib_dev *dev = to_mdev(cq->device);
	struct mlx5_ib_cq *mcq = to_mcq(cq);
	struct ib_ucontext *context = NULL;

	if (cq->uobject)
		context = cq->uobject->context;

	mlx5_core_destroy_cq(dev->mdev, &mcq->mcq);
	if (context)
		destroy_cq_user(mcq, context);
	else
		destroy_cq_kernel(dev, mcq);

	kfree(mcq);

	return 0;
}

static int is_equal_rsn(struct mlx5_cqe64 *cqe64, u32 rsn)
{
	return rsn == (ntohl(cqe64->sop_drop_qpn) & 0xffffff);
}

void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 rsn, struct mlx5_ib_srq *srq)
{
	struct mlx5_cqe64 *cqe64, *dest64;
	void *cqe, *dest;
	u32 prod_index;
	int nfreed = 0;
	u8 owner_bit;

	if (!cq)
		return;

	/* First we need to find the current producer index, so we
	 * know where to start cleaning from.  It doesn't matter if HW
	 * adds new entries after this loop -- the QP we're worried
	 * about is already in RESET, so the new entries won't come
	 * from our QP and therefore don't need to be checked.
	 */
	for (prod_index = cq->mcq.cons_index; get_sw_cqe(cq, prod_index); prod_index++)
		if (prod_index == cq->mcq.cons_index + cq->ibcq.cqe)
			break;

	/* Now sweep backwards through the CQ, removing CQ entries
	 * that match our QP by copying older entries on top of them.
	 */
	while ((int) --prod_index - (int) cq->mcq.cons_index >= 0) {
		cqe = get_cqe(cq, prod_index & cq->ibcq.cqe);
		cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
		if (is_equal_rsn(cqe64, rsn)) {
			if (srq && (ntohl(cqe64->srqn) & 0xffffff))
				mlx5_ib_free_srq_wqe(srq, be16_to_cpu(cqe64->wqe_counter));
			++nfreed;
		} else if (nfreed) {
			dest = get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe);
			dest64 = (cq->mcq.cqe_sz == 64) ? dest : dest + 64;
			owner_bit = dest64->op_own & MLX5_CQE_OWNER_MASK;
			memcpy(dest, cqe, cq->mcq.cqe_sz);
			dest64->op_own = owner_bit |
				(dest64->op_own & ~MLX5_CQE_OWNER_MASK);
		}
	}

	if (nfreed) {
		cq->mcq.cons_index += nfreed;
		/* Make sure update of buffer contents is done before
		 * updating consumer index.
		 */
		wmb();
		mlx5_cq_set_ci(&cq->mcq);
	}
}

void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq)
{
	if (!cq)
		return;

	spin_lock_irq(&cq->lock);
	__mlx5_ib_cq_clean(cq, qpn, srq);
	spin_unlock_irq(&cq->lock);
}

int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
{
	struct mlx5_modify_cq_mbox_in *in;
	struct mlx5_ib_dev *dev = to_mdev(cq->device);
	struct mlx5_ib_cq *mcq = to_mcq(cq);
	int err;
	u32 fsel;

	if (!MLX5_CAP_GEN(dev->mdev, cq_moderation))
		return -ENOSYS;

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

	in->cqn = cpu_to_be32(mcq->mcq.cqn);
	fsel = (MLX5_CQ_MODIFY_PERIOD | MLX5_CQ_MODIFY_COUNT);
	in->ctx.cq_period = cpu_to_be16(cq_period);
	in->ctx.cq_max_count = cpu_to_be16(cq_count);
	in->field_select = cpu_to_be32(fsel);
	err = mlx5_core_modify_cq(dev->mdev, &mcq->mcq, in, sizeof(*in));
	kfree(in);

	if (err)
		mlx5_ib_warn(dev, "modify cq 0x%x failed\n", mcq->mcq.cqn);

	return err;
}

static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
		       int entries, struct ib_udata *udata, int *npas,
		       int *page_shift, int *cqe_size)
{
	struct mlx5_ib_resize_cq ucmd;
	struct ib_umem *umem;
	int err;
	int npages;
	struct ib_ucontext *context = cq->buf.umem->context;

	err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
	if (err)
		return err;

	if (ucmd.reserved0 || ucmd.reserved1)
		return -EINVAL;

	umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size,
			   IB_ACCESS_LOCAL_WRITE, 1);
	if (IS_ERR(umem)) {
		err = PTR_ERR(umem);
		return err;
	}

	mlx5_ib_cont_pages(umem, ucmd.buf_addr, &npages, page_shift,
			   npas, NULL);

	cq->resize_umem = umem;
	*cqe_size = ucmd.cqe_size;

	return 0;
}

static void un_resize_user(struct mlx5_ib_cq *cq)
{
	ib_umem_release(cq->resize_umem);
}

static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
			 int entries, int cqe_size)
{
	int err;

	cq->resize_buf = kzalloc(sizeof(*cq->resize_buf), GFP_KERNEL);
	if (!cq->resize_buf)
		return -ENOMEM;

	err = alloc_cq_buf(dev, cq->resize_buf, entries, cqe_size);
	if (err)
		goto ex;

	init_cq_buf(cq, cq->resize_buf);

	return 0;

ex:
	kfree(cq->resize_buf);
	return err;
}

static void un_resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq)
{
	free_cq_buf(dev, cq->resize_buf);
	cq->resize_buf = NULL;
}

static int copy_resize_cqes(struct mlx5_ib_cq *cq)
{
	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
	struct mlx5_cqe64 *scqe64;
	struct mlx5_cqe64 *dcqe64;
	void *start_cqe;
	void *scqe;
	void *dcqe;
	int ssize;
	int dsize;
	int i;
	u8 sw_own;

	ssize = cq->buf.cqe_size;
	dsize = cq->resize_buf->cqe_size;
	if (ssize != dsize) {
		mlx5_ib_warn(dev, "resize from different cqe size is not supported\n");
		return -EINVAL;
	}

	i = cq->mcq.cons_index;
	scqe = get_sw_cqe(cq, i);
	scqe64 = ssize == 64 ? scqe : scqe + 64;
	start_cqe = scqe;
	if (!scqe) {
		mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
		return -EINVAL;
	}

	while ((scqe64->op_own >> 4) != MLX5_CQE_RESIZE_CQ) {
		dcqe = get_cqe_from_buf(cq->resize_buf,
					(i + 1) & (cq->resize_buf->nent),
					dsize);
		dcqe64 = dsize == 64 ? dcqe : dcqe + 64;
		sw_own = sw_ownership_bit(i + 1, cq->resize_buf->nent);
		memcpy(dcqe, scqe, dsize);
		dcqe64->op_own = (dcqe64->op_own & ~MLX5_CQE_OWNER_MASK) | sw_own;

		++i;
		scqe = get_sw_cqe(cq, i);
		scqe64 = ssize == 64 ? scqe : scqe + 64;
		if (!scqe) {
			mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
			return -EINVAL;
		}

		if (scqe == start_cqe) {
			pr_warn("resize CQ failed to get resize CQE, CQN 0x%x\n",
				cq->mcq.cqn);
			return -ENOMEM;
		}
	}
	++cq->mcq.cons_index;
	return 0;
}

int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
{
	struct mlx5_ib_dev *dev = to_mdev(ibcq->device);
	struct mlx5_ib_cq *cq = to_mcq(ibcq);
	struct mlx5_modify_cq_mbox_in *in;
	int err;
	int npas;
	int page_shift;
	int inlen;
	int uninitialized_var(cqe_size);
	unsigned long flags;

	if (!MLX5_CAP_GEN(dev->mdev, cq_resize)) {
		pr_info("Firmware does not support resize CQ\n");
		return -ENOSYS;
	}

	if (entries < 1 ||
	    entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) {
		mlx5_ib_warn(dev, "wrong entries number %d, max %d\n",
			     entries,
			     1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz));
		return -EINVAL;
	}

	entries = roundup_pow_of_two(entries + 1);
	if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
		return -EINVAL;

	if (entries == ibcq->cqe + 1)
		return 0;

	mutex_lock(&cq->resize_mutex);
	if (udata) {
		err = resize_user(dev, cq, entries, udata, &npas, &page_shift,
				  &cqe_size);
	} else {
		cqe_size = 64;
		err = resize_kernel(dev, cq, entries, cqe_size);
		if (!err) {
			npas = cq->resize_buf->buf.npages;
			page_shift = cq->resize_buf->buf.page_shift;
		}
	}

	if (err)
		goto ex;

	inlen = sizeof(*in) + npas * sizeof(in->pas[0]);
	in = mlx5_vzalloc(inlen);
	if (!in) {
		err = -ENOMEM;
		goto ex_resize;
	}

	if (udata)
		mlx5_ib_populate_pas(dev, cq->resize_umem, page_shift,
				     in->pas, 0);
	else
		mlx5_fill_page_array(&cq->resize_buf->buf, in->pas);

	in->field_select = cpu_to_be32(MLX5_MODIFY_CQ_MASK_LOG_SIZE  |
				       MLX5_MODIFY_CQ_MASK_PG_OFFSET |
				       MLX5_MODIFY_CQ_MASK_PG_SIZE);
	in->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
	in->ctx.cqe_sz_flags = cqe_sz_to_mlx_sz(cqe_size) << 5;
	in->ctx.page_offset = 0;
	in->ctx.log_sz_usr_page = cpu_to_be32(ilog2(entries) << 24);
	in->hdr.opmod = cpu_to_be16(MLX5_CQ_OPMOD_RESIZE);
	in->cqn = cpu_to_be32(cq->mcq.cqn);

	err = mlx5_core_modify_cq(dev->mdev, &cq->mcq, in, inlen);
	if (err)
		goto ex_alloc;

	if (udata) {
		cq->ibcq.cqe = entries - 1;
		ib_umem_release(cq->buf.umem);
		cq->buf.umem = cq->resize_umem;
		cq->resize_umem = NULL;
	} else {
		struct mlx5_ib_cq_buf tbuf;
		int resized = 0;

		spin_lock_irqsave(&cq->lock, flags);
		if (cq->resize_buf) {
			err = copy_resize_cqes(cq);
			if (!err) {
				tbuf = cq->buf;
				cq->buf = *cq->resize_buf;
				kfree(cq->resize_buf);
				cq->resize_buf = NULL;
				resized = 1;
			}
		}
		cq->ibcq.cqe = entries - 1;
		spin_unlock_irqrestore(&cq->lock, flags);
		if (resized)
			free_cq_buf(dev, &tbuf);
	}
	mutex_unlock(&cq->resize_mutex);

	kvfree(in);
	return 0;

ex_alloc:
	kvfree(in);

ex_resize:
	if (udata)
		un_resize_user(cq);
	else
		un_resize_kernel(dev, cq);
ex:
	mutex_unlock(&cq->resize_mutex);
	return err;
}

int mlx5_ib_get_cqe_size(struct mlx5_ib_dev *dev, struct ib_cq *ibcq)
{
	struct mlx5_ib_cq *cq;

	if (!ibcq)
		return 128;

	cq = to_mcq(ibcq);
	return cq->cqe_size;
}

/* Called from atomic context */
int mlx5_ib_generate_wc(struct ib_cq *ibcq, struct ib_wc *wc)
{
	struct mlx5_ib_wc *soft_wc;
	struct mlx5_ib_cq *cq = to_mcq(ibcq);
	unsigned long flags;

	soft_wc = kmalloc(sizeof(*soft_wc), GFP_ATOMIC);
	if (!soft_wc)
		return -ENOMEM;

	soft_wc->wc = *wc;
	spin_lock_irqsave(&cq->lock, flags);
	list_add_tail(&soft_wc->list, &cq->wc_list);
	if (cq->notify_flags == IB_CQ_NEXT_COMP ||
	    wc->status != IB_WC_SUCCESS) {
		cq->notify_flags = 0;
		schedule_work(&cq->notify_work);
	}
	spin_unlock_irqrestore(&cq->lock, flags);

	return 0;
}