summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/hfi1/ud.c
blob: 4cb0fce5c096a6909fd05b2bb541c4bf37bf8157 (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
/*
 * Copyright(c) 2015 - 2018 Intel Corporation.
 *
 * This file is provided under a dual BSD/GPLv2 license.  When using or
 * redistributing this file, you may do so under either license.
 *
 * GPL LICENSE SUMMARY
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * BSD LICENSE
 *
 * 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.
 *  - Neither the name of Intel Corporation nor the names of its
 *    contributors may be used to endorse or promote products derived
 *    from this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS 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 COPYRIGHT
 * OWNER 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.
 *
 */

#include <linux/net.h>
#include <rdma/ib_smi.h>

#include "hfi.h"
#include "mad.h"
#include "verbs_txreq.h"
#include "trace_ibhdrs.h"
#include "qp.h"

/* We support only two types - 9B and 16B for now */
static const hfi1_make_req hfi1_make_ud_req_tbl[2] = {
	[HFI1_PKT_TYPE_9B] = &hfi1_make_ud_req_9B,
	[HFI1_PKT_TYPE_16B] = &hfi1_make_ud_req_16B
};

/**
 * ud_loopback - handle send on loopback QPs
 * @sqp: the sending QP
 * @swqe: the send work request
 *
 * This is called from hfi1_make_ud_req() to forward a WQE addressed
 * to the same HFI.
 * Note that the receive interrupt handler may be calling hfi1_ud_rcv()
 * while this is being called.
 */
static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
{
	struct hfi1_ibport *ibp = to_iport(sqp->ibqp.device, sqp->port_num);
	struct hfi1_pportdata *ppd;
	struct hfi1_qp_priv *priv = sqp->priv;
	struct rvt_qp *qp;
	struct rdma_ah_attr *ah_attr;
	unsigned long flags;
	struct rvt_sge_state ssge;
	struct rvt_sge *sge;
	struct ib_wc wc;
	u32 length;
	enum ib_qp_type sqptype, dqptype;

	rcu_read_lock();

	qp = rvt_lookup_qpn(ib_to_rvt(sqp->ibqp.device), &ibp->rvp,
			    swqe->ud_wr.remote_qpn);
	if (!qp) {
		ibp->rvp.n_pkt_drops++;
		rcu_read_unlock();
		return;
	}

	sqptype = sqp->ibqp.qp_type == IB_QPT_GSI ?
			IB_QPT_UD : sqp->ibqp.qp_type;
	dqptype = qp->ibqp.qp_type == IB_QPT_GSI ?
			IB_QPT_UD : qp->ibqp.qp_type;

	if (dqptype != sqptype ||
	    !(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK)) {
		ibp->rvp.n_pkt_drops++;
		goto drop;
	}

	ah_attr = &ibah_to_rvtah(swqe->ud_wr.ah)->attr;
	ppd = ppd_from_ibp(ibp);

	if (qp->ibqp.qp_num > 1) {
		u16 pkey;
		u32 slid;
		u8 sc5 = ibp->sl_to_sc[rdma_ah_get_sl(ah_attr)];

		pkey = hfi1_get_pkey(ibp, sqp->s_pkey_index);
		slid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
				   ((1 << ppd->lmc) - 1));
		if (unlikely(ingress_pkey_check(ppd, pkey, sc5,
						qp->s_pkey_index,
						slid, false))) {
			hfi1_bad_pkey(ibp, pkey,
				      rdma_ah_get_sl(ah_attr),
				      sqp->ibqp.qp_num, qp->ibqp.qp_num,
				      slid, rdma_ah_get_dlid(ah_attr));
			goto drop;
		}
	}

	/*
	 * Check that the qkey matches (except for QP0, see 9.6.1.4.1).
	 * Qkeys with the high order bit set mean use the
	 * qkey from the QP context instead of the WR (see 10.2.5).
	 */
	if (qp->ibqp.qp_num) {
		u32 qkey;

		qkey = (int)swqe->ud_wr.remote_qkey < 0 ?
			sqp->qkey : swqe->ud_wr.remote_qkey;
		if (unlikely(qkey != qp->qkey))
			goto drop; /* silently drop per IBTA spec */
	}

	/*
	 * A GRH is expected to precede the data even if not
	 * present on the wire.
	 */
	length = swqe->length;
	memset(&wc, 0, sizeof(wc));
	wc.byte_len = length + sizeof(struct ib_grh);

	if (swqe->wr.opcode == IB_WR_SEND_WITH_IMM) {
		wc.wc_flags = IB_WC_WITH_IMM;
		wc.ex.imm_data = swqe->wr.ex.imm_data;
	}

	spin_lock_irqsave(&qp->r_lock, flags);

	/*
	 * Get the next work request entry to find where to put the data.
	 */
	if (qp->r_flags & RVT_R_REUSE_SGE) {
		qp->r_flags &= ~RVT_R_REUSE_SGE;
	} else {
		int ret;

		ret = rvt_get_rwqe(qp, false);
		if (ret < 0) {
			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
			goto bail_unlock;
		}
		if (!ret) {
			if (qp->ibqp.qp_num == 0)
				ibp->rvp.n_vl15_dropped++;
			goto bail_unlock;
		}
	}
	/* Silently drop packets which are too big. */
	if (unlikely(wc.byte_len > qp->r_len)) {
		qp->r_flags |= RVT_R_REUSE_SGE;
		ibp->rvp.n_pkt_drops++;
		goto bail_unlock;
	}

	if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
		struct ib_grh grh;
		struct ib_global_route grd = *(rdma_ah_read_grh(ah_attr));

		/*
		 * For loopback packets with extended LIDs, the
		 * sgid_index in the GRH is 0 and the dgid is
		 * OPA GID of the sender. While creating a response
		 * to the loopback packet, IB core creates the new
		 * sgid_index from the DGID and that will be the
		 * OPA_GID_INDEX. The new dgid is from the sgid
		 * index and that will be in the IB GID format.
		 *
		 * We now have a case where the sent packet had a
		 * different sgid_index and dgid compared to the
		 * one that was received in response.
		 *
		 * Fix this inconsistency.
		 */
		if (priv->hdr_type == HFI1_PKT_TYPE_16B) {
			if (grd.sgid_index == 0)
				grd.sgid_index = OPA_GID_INDEX;

			if (ib_is_opa_gid(&grd.dgid))
				grd.dgid.global.interface_id =
				cpu_to_be64(ppd->guids[HFI1_PORT_GUID_INDEX]);
		}

		hfi1_make_grh(ibp, &grh, &grd, 0, 0);
		rvt_copy_sge(qp, &qp->r_sge, &grh,
			     sizeof(grh), true, false);
		wc.wc_flags |= IB_WC_GRH;
	} else {
		rvt_skip_sge(&qp->r_sge, sizeof(struct ib_grh), true);
	}
	ssge.sg_list = swqe->sg_list + 1;
	ssge.sge = *swqe->sg_list;
	ssge.num_sge = swqe->wr.num_sge;
	sge = &ssge.sge;
	while (length) {
		u32 len = rvt_get_sge_length(sge, length);

		WARN_ON_ONCE(len == 0);
		rvt_copy_sge(qp, &qp->r_sge, sge->vaddr, len, true, false);
		rvt_update_sge(&ssge, len, false);
		length -= len;
	}
	rvt_put_ss(&qp->r_sge);
	if (!test_and_clear_bit(RVT_R_WRID_VALID, &qp->r_aflags))
		goto bail_unlock;
	wc.wr_id = qp->r_wr_id;
	wc.status = IB_WC_SUCCESS;
	wc.opcode = IB_WC_RECV;
	wc.qp = &qp->ibqp;
	wc.src_qp = sqp->ibqp.qp_num;
	if (qp->ibqp.qp_type == IB_QPT_GSI || qp->ibqp.qp_type == IB_QPT_SMI) {
		if (sqp->ibqp.qp_type == IB_QPT_GSI ||
		    sqp->ibqp.qp_type == IB_QPT_SMI)
			wc.pkey_index = swqe->ud_wr.pkey_index;
		else
			wc.pkey_index = sqp->s_pkey_index;
	} else {
		wc.pkey_index = 0;
	}
	wc.slid = (ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
				   ((1 << ppd->lmc) - 1))) & U16_MAX;
	/* Check for loopback when the port lid is not set */
	if (wc.slid == 0 && sqp->ibqp.qp_type == IB_QPT_GSI)
		wc.slid = be16_to_cpu(IB_LID_PERMISSIVE);
	wc.sl = rdma_ah_get_sl(ah_attr);
	wc.dlid_path_bits = rdma_ah_get_dlid(ah_attr) & ((1 << ppd->lmc) - 1);
	wc.port_num = qp->port_num;
	/* Signal completion event if the solicited bit is set. */
	rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
		     swqe->wr.send_flags & IB_SEND_SOLICITED);
	ibp->rvp.n_loop_pkts++;
bail_unlock:
	spin_unlock_irqrestore(&qp->r_lock, flags);
drop:
	rcu_read_unlock();
}

static void hfi1_make_bth_deth(struct rvt_qp *qp, struct rvt_swqe *wqe,
			       struct ib_other_headers *ohdr,
			       u16 *pkey, u32 extra_bytes, bool bypass)
{
	u32 bth0;
	struct hfi1_ibport *ibp;

	ibp = to_iport(qp->ibqp.device, qp->port_num);
	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM) {
		ohdr->u.ud.imm_data = wqe->wr.ex.imm_data;
		bth0 = IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE << 24;
	} else {
		bth0 = IB_OPCODE_UD_SEND_ONLY << 24;
	}

	if (wqe->wr.send_flags & IB_SEND_SOLICITED)
		bth0 |= IB_BTH_SOLICITED;
	bth0 |= extra_bytes << 20;
	if (qp->ibqp.qp_type == IB_QPT_GSI || qp->ibqp.qp_type == IB_QPT_SMI)
		*pkey = hfi1_get_pkey(ibp, wqe->ud_wr.pkey_index);
	else
		*pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
	if (!bypass)
		bth0 |= *pkey;
	ohdr->bth[0] = cpu_to_be32(bth0);
	ohdr->bth[1] = cpu_to_be32(wqe->ud_wr.remote_qpn);
	ohdr->bth[2] = cpu_to_be32(mask_psn(wqe->psn));
	/*
	 * Qkeys with the high order bit set mean use the
	 * qkey from the QP context instead of the WR (see 10.2.5).
	 */
	ohdr->u.ud.deth[0] = cpu_to_be32((int)wqe->ud_wr.remote_qkey < 0 ?
					 qp->qkey : wqe->ud_wr.remote_qkey);
	ohdr->u.ud.deth[1] = cpu_to_be32(qp->ibqp.qp_num);
}

void hfi1_make_ud_req_9B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
			 struct rvt_swqe *wqe)
{
	u32 nwords, extra_bytes;
	u16 len, slid, dlid, pkey;
	u16 lrh0 = 0;
	u8 sc5;
	struct hfi1_qp_priv *priv = qp->priv;
	struct ib_other_headers *ohdr;
	struct rdma_ah_attr *ah_attr;
	struct hfi1_pportdata *ppd;
	struct hfi1_ibport *ibp;
	struct ib_grh *grh;

	ibp = to_iport(qp->ibqp.device, qp->port_num);
	ppd = ppd_from_ibp(ibp);
	ah_attr = &ibah_to_rvtah(wqe->ud_wr.ah)->attr;

	extra_bytes = -wqe->length & 3;
	nwords = ((wqe->length + extra_bytes) >> 2) + SIZE_OF_CRC;
	/* header size in dwords LRH+BTH+DETH = (8+12+8)/4. */
	ps->s_txreq->hdr_dwords = 7;
	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM)
		ps->s_txreq->hdr_dwords++;

	if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
		grh = &ps->s_txreq->phdr.hdr.ibh.u.l.grh;
		ps->s_txreq->hdr_dwords +=
			hfi1_make_grh(ibp, grh, rdma_ah_read_grh(ah_attr),
				      ps->s_txreq->hdr_dwords - LRH_9B_DWORDS,
				      nwords);
		lrh0 = HFI1_LRH_GRH;
		ohdr = &ps->s_txreq->phdr.hdr.ibh.u.l.oth;
	} else {
		lrh0 = HFI1_LRH_BTH;
		ohdr = &ps->s_txreq->phdr.hdr.ibh.u.oth;
	}

	sc5 = ibp->sl_to_sc[rdma_ah_get_sl(ah_attr)];
	lrh0 |= (rdma_ah_get_sl(ah_attr) & 0xf) << 4;
	if (qp->ibqp.qp_type == IB_QPT_SMI) {
		lrh0 |= 0xF000; /* Set VL (see ch. 13.5.3.1) */
		priv->s_sc = 0xf;
	} else {
		lrh0 |= (sc5 & 0xf) << 12;
		priv->s_sc = sc5;
	}

	dlid = opa_get_lid(rdma_ah_get_dlid(ah_attr), 9B);
	if (dlid == be16_to_cpu(IB_LID_PERMISSIVE)) {
		slid = be16_to_cpu(IB_LID_PERMISSIVE);
	} else {
		u16 lid = (u16)ppd->lid;

		if (lid) {
			lid |= rdma_ah_get_path_bits(ah_attr) &
				((1 << ppd->lmc) - 1);
			slid = lid;
		} else {
			slid = be16_to_cpu(IB_LID_PERMISSIVE);
		}
	}
	hfi1_make_bth_deth(qp, wqe, ohdr, &pkey, extra_bytes, false);
	len = ps->s_txreq->hdr_dwords + nwords;

	/* Setup the packet */
	ps->s_txreq->phdr.hdr.hdr_type = HFI1_PKT_TYPE_9B;
	hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
			 lrh0, len, dlid, slid);
}

void hfi1_make_ud_req_16B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
			  struct rvt_swqe *wqe)
{
	struct hfi1_qp_priv *priv = qp->priv;
	struct ib_other_headers *ohdr;
	struct rdma_ah_attr *ah_attr;
	struct hfi1_pportdata *ppd;
	struct hfi1_ibport *ibp;
	u32 dlid, slid, nwords, extra_bytes;
	u32 dest_qp = wqe->ud_wr.remote_qpn;
	u32 src_qp = qp->ibqp.qp_num;
	u16 len, pkey;
	u8 l4, sc5;
	bool is_mgmt = false;

	ibp = to_iport(qp->ibqp.device, qp->port_num);
	ppd = ppd_from_ibp(ibp);
	ah_attr = &ibah_to_rvtah(wqe->ud_wr.ah)->attr;

	/*
	 * Build 16B Management Packet if either the destination
	 * or source queue pair number is 0 or 1.
	 */
	if (dest_qp == 0 || src_qp == 0 || dest_qp == 1 || src_qp == 1) {
		/* header size in dwords 16B LRH+L4_FM = (16+8)/4. */
		ps->s_txreq->hdr_dwords = 6;
		is_mgmt = true;
	} else {
		/* header size in dwords 16B LRH+BTH+DETH = (16+12+8)/4. */
		ps->s_txreq->hdr_dwords = 9;
		if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM)
			ps->s_txreq->hdr_dwords++;
	}

	/* SW provides space for CRC and LT for bypass packets. */
	extra_bytes = hfi1_get_16b_padding((ps->s_txreq->hdr_dwords << 2),
					   wqe->length);
	nwords = ((wqe->length + extra_bytes + SIZE_OF_LT) >> 2) + SIZE_OF_CRC;

	if ((rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) &&
	    hfi1_check_mcast(rdma_ah_get_dlid(ah_attr))) {
		struct ib_grh *grh;
		struct ib_global_route *grd = rdma_ah_retrieve_grh(ah_attr);
		/*
		 * Ensure OPA GIDs are transformed to IB gids
		 * before creating the GRH.
		 */
		if (grd->sgid_index == OPA_GID_INDEX) {
			dd_dev_warn(ppd->dd, "Bad sgid_index. sgid_index: %d\n",
				    grd->sgid_index);
			grd->sgid_index = 0;
		}
		grh = &ps->s_txreq->phdr.hdr.opah.u.l.grh;
		ps->s_txreq->hdr_dwords += hfi1_make_grh(
			ibp, grh, grd,
			ps->s_txreq->hdr_dwords - LRH_16B_DWORDS,
			nwords);
		ohdr = &ps->s_txreq->phdr.hdr.opah.u.l.oth;
		l4 = OPA_16B_L4_IB_GLOBAL;
	} else {
		ohdr = &ps->s_txreq->phdr.hdr.opah.u.oth;
		l4 = OPA_16B_L4_IB_LOCAL;
	}

	sc5 = ibp->sl_to_sc[rdma_ah_get_sl(ah_attr)];
	if (qp->ibqp.qp_type == IB_QPT_SMI)
		priv->s_sc = 0xf;
	else
		priv->s_sc = sc5;

	dlid = opa_get_lid(rdma_ah_get_dlid(ah_attr), 16B);
	if (!ppd->lid)
		slid = be32_to_cpu(OPA_LID_PERMISSIVE);
	else
		slid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
			   ((1 << ppd->lmc) - 1));

	if (is_mgmt) {
		l4 = OPA_16B_L4_FM;
		pkey = hfi1_get_pkey(ibp, wqe->ud_wr.pkey_index);
		hfi1_16B_set_qpn(&ps->s_txreq->phdr.hdr.opah.u.mgmt,
				 dest_qp, src_qp);
	} else {
		hfi1_make_bth_deth(qp, wqe, ohdr, &pkey, extra_bytes, true);
	}
	/* Convert dwords to flits */
	len = (ps->s_txreq->hdr_dwords + nwords) >> 1;

	/* Setup the packet */
	ps->s_txreq->phdr.hdr.hdr_type = HFI1_PKT_TYPE_16B;
	hfi1_make_16b_hdr(&ps->s_txreq->phdr.hdr.opah,
			  slid, dlid, len, pkey, 0, 0, l4, priv->s_sc);
}

/**
 * hfi1_make_ud_req - construct a UD request packet
 * @qp: the QP
 *
 * Assume s_lock is held.
 *
 * Return 1 if constructed; otherwise, return 0.
 */
int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
{
	struct hfi1_qp_priv *priv = qp->priv;
	struct rdma_ah_attr *ah_attr;
	struct hfi1_pportdata *ppd;
	struct hfi1_ibport *ibp;
	struct rvt_swqe *wqe;
	int next_cur;
	u32 lid;

	ps->s_txreq = get_txreq(ps->dev, qp);
	if (!ps->s_txreq)
		goto bail_no_tx;

	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_NEXT_SEND_OK)) {
		if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND))
			goto bail;
		/* We are in the error state, flush the work request. */
		if (qp->s_last == READ_ONCE(qp->s_head))
			goto bail;
		/* If DMAs are in progress, we can't flush immediately. */
		if (iowait_sdma_pending(&priv->s_iowait)) {
			qp->s_flags |= RVT_S_WAIT_DMA;
			goto bail;
		}
		wqe = rvt_get_swqe_ptr(qp, qp->s_last);
		rvt_send_complete(qp, wqe, IB_WC_WR_FLUSH_ERR);
		goto done_free_tx;
	}

	/* see post_one_send() */
	if (qp->s_cur == READ_ONCE(qp->s_head))
		goto bail;

	wqe = rvt_get_swqe_ptr(qp, qp->s_cur);
	next_cur = qp->s_cur + 1;
	if (next_cur >= qp->s_size)
		next_cur = 0;

	/* Construct the header. */
	ibp = to_iport(qp->ibqp.device, qp->port_num);
	ppd = ppd_from_ibp(ibp);
	ah_attr = &ibah_to_rvtah(wqe->ud_wr.ah)->attr;
	priv->hdr_type = hfi1_get_hdr_type(ppd->lid, ah_attr);
	if ((!hfi1_check_mcast(rdma_ah_get_dlid(ah_attr))) ||
	    (rdma_ah_get_dlid(ah_attr) == be32_to_cpu(OPA_LID_PERMISSIVE))) {
		lid = rdma_ah_get_dlid(ah_attr) & ~((1 << ppd->lmc) - 1);
		if (unlikely(!loopback &&
			     ((lid == ppd->lid) ||
			      ((lid == be32_to_cpu(OPA_LID_PERMISSIVE)) &&
			       (qp->ibqp.qp_type == IB_QPT_GSI))))) {
			unsigned long tflags = ps->flags;
			/*
			 * If DMAs are in progress, we can't generate
			 * a completion for the loopback packet since
			 * it would be out of order.
			 * Instead of waiting, we could queue a
			 * zero length descriptor so we get a callback.
			 */
			if (iowait_sdma_pending(&priv->s_iowait)) {
				qp->s_flags |= RVT_S_WAIT_DMA;
				goto bail;
			}
			qp->s_cur = next_cur;
			spin_unlock_irqrestore(&qp->s_lock, tflags);
			ud_loopback(qp, wqe);
			spin_lock_irqsave(&qp->s_lock, tflags);
			ps->flags = tflags;
			rvt_send_complete(qp, wqe, IB_WC_SUCCESS);
			goto done_free_tx;
		}
	}

	qp->s_cur = next_cur;
	ps->s_txreq->s_cur_size = wqe->length;
	ps->s_txreq->ss = &qp->s_sge;
	qp->s_srate = rdma_ah_get_static_rate(ah_attr);
	qp->srate_mbps = ib_rate_to_mbps(qp->s_srate);
	qp->s_wqe = wqe;
	qp->s_sge.sge = wqe->sg_list[0];
	qp->s_sge.sg_list = wqe->sg_list + 1;
	qp->s_sge.num_sge = wqe->wr.num_sge;
	qp->s_sge.total_len = wqe->length;

	/* Make the appropriate header */
	hfi1_make_ud_req_tbl[priv->hdr_type](qp, ps, qp->s_wqe);
	priv->s_sde = qp_to_sdma_engine(qp, priv->s_sc);
	ps->s_txreq->sde = priv->s_sde;
	priv->s_sendcontext = qp_to_send_context(qp, priv->s_sc);
	ps->s_txreq->psc = priv->s_sendcontext;
	/* disarm any ahg */
	priv->s_ahg->ahgcount = 0;
	priv->s_ahg->ahgidx = 0;
	priv->s_ahg->tx_flags = 0;

	return 1;

done_free_tx:
	hfi1_put_txreq(ps->s_txreq);
	ps->s_txreq = NULL;
	return 1;

bail:
	hfi1_put_txreq(ps->s_txreq);

bail_no_tx:
	ps->s_txreq = NULL;
	qp->s_flags &= ~RVT_S_BUSY;
	return 0;
}

/*
 * Hardware can't check this so we do it here.
 *
 * This is a slightly different algorithm than the standard pkey check.  It
 * special cases the management keys and allows for 0x7fff and 0xffff to be in
 * the table at the same time.
 *
 * @returns the index found or -1 if not found
 */
int hfi1_lookup_pkey_idx(struct hfi1_ibport *ibp, u16 pkey)
{
	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
	unsigned i;

	if (pkey == FULL_MGMT_P_KEY || pkey == LIM_MGMT_P_KEY) {
		unsigned lim_idx = -1;

		for (i = 0; i < ARRAY_SIZE(ppd->pkeys); ++i) {
			/* here we look for an exact match */
			if (ppd->pkeys[i] == pkey)
				return i;
			if (ppd->pkeys[i] == LIM_MGMT_P_KEY)
				lim_idx = i;
		}

		/* did not find 0xffff return 0x7fff idx if found */
		if (pkey == FULL_MGMT_P_KEY)
			return lim_idx;

		/* no match...  */
		return -1;
	}

	pkey &= 0x7fff; /* remove limited/full membership bit */

	for (i = 0; i < ARRAY_SIZE(ppd->pkeys); ++i)
		if ((ppd->pkeys[i] & 0x7fff) == pkey)
			return i;

	/*
	 * Should not get here, this means hardware failed to validate pkeys.
	 */
	return -1;
}

void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
		    u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
		    u8 sc5, const struct ib_grh *old_grh)
{
	u64 pbc, pbc_flags = 0;
	u32 bth0, plen, vl, hwords = 7;
	u16 len;
	u8 l4;
	struct hfi1_opa_header hdr;
	struct ib_other_headers *ohdr;
	struct pio_buf *pbuf;
	struct send_context *ctxt = qp_to_send_context(qp, sc5);
	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
	u32 nwords;

	hdr.hdr_type = HFI1_PKT_TYPE_16B;
	/* Populate length */
	nwords = ((hfi1_get_16b_padding(hwords << 2, 0) +
		   SIZE_OF_LT) >> 2) + SIZE_OF_CRC;
	if (old_grh) {
		struct ib_grh *grh = &hdr.opah.u.l.grh;

		grh->version_tclass_flow = old_grh->version_tclass_flow;
		grh->paylen = cpu_to_be16(
			(hwords - LRH_16B_DWORDS + nwords) << 2);
		grh->hop_limit = 0xff;
		grh->sgid = old_grh->dgid;
		grh->dgid = old_grh->sgid;
		ohdr = &hdr.opah.u.l.oth;
		l4 = OPA_16B_L4_IB_GLOBAL;
		hwords += sizeof(struct ib_grh) / sizeof(u32);
	} else {
		ohdr = &hdr.opah.u.oth;
		l4 = OPA_16B_L4_IB_LOCAL;
	}

	/* BIT 16 to 19 is TVER. Bit 20 to 22 is pad cnt */
	bth0 = (IB_OPCODE_CNP << 24) | (1 << 16) |
	       (hfi1_get_16b_padding(hwords << 2, 0) << 20);
	ohdr->bth[0] = cpu_to_be32(bth0);

	ohdr->bth[1] = cpu_to_be32(remote_qpn);
	ohdr->bth[2] = 0; /* PSN 0 */

	/* Convert dwords to flits */
	len = (hwords + nwords) >> 1;
	hfi1_make_16b_hdr(&hdr.opah, slid, dlid, len, pkey, 1, 0, l4, sc5);

	plen = 2 /* PBC */ + hwords + nwords;
	pbc_flags |= PBC_PACKET_BYPASS | PBC_INSERT_BYPASS_ICRC;
	vl = sc_to_vlt(ppd->dd, sc5);
	pbc = create_pbc(ppd, pbc_flags, qp->srate_mbps, vl, plen);
	if (ctxt) {
		pbuf = sc_buffer_alloc(ctxt, plen, NULL, NULL);
		if (!IS_ERR_OR_NULL(pbuf)) {
			trace_pio_output_ibhdr(ppd->dd, &hdr, sc5);
			ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc,
						 &hdr, hwords);
		}
	}
}

void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
		u16 pkey, u32 slid, u32 dlid, u8 sc5,
		const struct ib_grh *old_grh)
{
	u64 pbc, pbc_flags = 0;
	u32 bth0, plen, vl, hwords = 5;
	u16 lrh0;
	u8 sl = ibp->sc_to_sl[sc5];
	struct hfi1_opa_header hdr;
	struct ib_other_headers *ohdr;
	struct pio_buf *pbuf;
	struct send_context *ctxt = qp_to_send_context(qp, sc5);
	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);

	hdr.hdr_type = HFI1_PKT_TYPE_9B;
	if (old_grh) {
		struct ib_grh *grh = &hdr.ibh.u.l.grh;

		grh->version_tclass_flow = old_grh->version_tclass_flow;
		grh->paylen = cpu_to_be16(
			(hwords - LRH_9B_DWORDS + SIZE_OF_CRC) << 2);
		grh->hop_limit = 0xff;
		grh->sgid = old_grh->dgid;
		grh->dgid = old_grh->sgid;
		ohdr = &hdr.ibh.u.l.oth;
		lrh0 = HFI1_LRH_GRH;
		hwords += sizeof(struct ib_grh) / sizeof(u32);
	} else {
		ohdr = &hdr.ibh.u.oth;
		lrh0 = HFI1_LRH_BTH;
	}

	lrh0 |= (sc5 & 0xf) << 12 | sl << 4;

	bth0 = pkey | (IB_OPCODE_CNP << 24);
	ohdr->bth[0] = cpu_to_be32(bth0);

	ohdr->bth[1] = cpu_to_be32(remote_qpn | (1 << IB_BECN_SHIFT));
	ohdr->bth[2] = 0; /* PSN 0 */

	hfi1_make_ib_hdr(&hdr.ibh, lrh0, hwords + SIZE_OF_CRC, dlid, slid);
	plen = 2 /* PBC */ + hwords;
	pbc_flags |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT);
	vl = sc_to_vlt(ppd->dd, sc5);
	pbc = create_pbc(ppd, pbc_flags, qp->srate_mbps, vl, plen);
	if (ctxt) {
		pbuf = sc_buffer_alloc(ctxt, plen, NULL, NULL);
		if (!IS_ERR_OR_NULL(pbuf)) {
			trace_pio_output_ibhdr(ppd->dd, &hdr, sc5);
			ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc,
						 &hdr, hwords);
		}
	}
}

/*
 * opa_smp_check() - Do the regular pkey checking, and the additional
 * checks for SMPs specified in OPAv1 rev 1.0, 9/19/2016 update, section
 * 9.10.25 ("SMA Packet Checks").
 *
 * Note that:
 *   - Checks are done using the pkey directly from the packet's BTH,
 *     and specifically _not_ the pkey that we attach to the completion,
 *     which may be different.
 *   - These checks are specifically for "non-local" SMPs (i.e., SMPs
 *     which originated on another node). SMPs which are sent from, and
 *     destined to this node are checked in opa_local_smp_check().
 *
 * At the point where opa_smp_check() is called, we know:
 *   - destination QP is QP0
 *
 * opa_smp_check() returns 0 if all checks succeed, 1 otherwise.
 */
static int opa_smp_check(struct hfi1_ibport *ibp, u16 pkey, u8 sc5,
			 struct rvt_qp *qp, u16 slid, struct opa_smp *smp)
{
	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);

	/*
	 * I don't think it's possible for us to get here with sc != 0xf,
	 * but check it to be certain.
	 */
	if (sc5 != 0xf)
		return 1;

	if (rcv_pkey_check(ppd, pkey, sc5, slid))
		return 1;

	/*
	 * At this point we know (and so don't need to check again) that
	 * the pkey is either LIM_MGMT_P_KEY, or FULL_MGMT_P_KEY
	 * (see ingress_pkey_check).
	 */
	if (smp->mgmt_class != IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE &&
	    smp->mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED) {
		ingress_pkey_table_fail(ppd, pkey, slid);
		return 1;
	}

	/*
	 * SMPs fall into one of four (disjoint) categories:
	 * SMA request, SMA response, SMA trap, or SMA trap repress.
	 * Our response depends, in part, on which type of SMP we're
	 * processing.
	 *
	 * If this is an SMA response, skip the check here.
	 *
	 * If this is an SMA request or SMA trap repress:
	 *   - pkey != FULL_MGMT_P_KEY =>
	 *       increment port recv constraint errors, drop MAD
	 *
	 * Otherwise:
	 *    - accept if the port is running an SM
	 *    - drop MAD if it's an SMA trap
	 *    - pkey == FULL_MGMT_P_KEY =>
	 *        reply with unsupported method
	 *    - pkey != FULL_MGMT_P_KEY =>
	 *	  increment port recv constraint errors, drop MAD
	 */
	switch (smp->method) {
	case IB_MGMT_METHOD_GET_RESP:
	case IB_MGMT_METHOD_REPORT_RESP:
		break;
	case IB_MGMT_METHOD_GET:
	case IB_MGMT_METHOD_SET:
	case IB_MGMT_METHOD_REPORT:
	case IB_MGMT_METHOD_TRAP_REPRESS:
		if (pkey != FULL_MGMT_P_KEY) {
			ingress_pkey_table_fail(ppd, pkey, slid);
			return 1;
		}
		break;
	default:
		if (ibp->rvp.port_cap_flags & IB_PORT_SM)
			return 0;
		if (smp->method == IB_MGMT_METHOD_TRAP)
			return 1;
		if (pkey == FULL_MGMT_P_KEY) {
			smp->status |= IB_SMP_UNSUP_METHOD;
			return 0;
		}
		ingress_pkey_table_fail(ppd, pkey, slid);
		return 1;
	}
	return 0;
}

/**
 * hfi1_ud_rcv - receive an incoming UD packet
 * @ibp: the port the packet came in on
 * @hdr: the packet header
 * @rcv_flags: flags relevant to rcv processing
 * @data: the packet data
 * @tlen: the packet length
 * @qp: the QP the packet came on
 *
 * This is called from qp_rcv() to process an incoming UD packet
 * for the given QP.
 * Called at interrupt level.
 */
void hfi1_ud_rcv(struct hfi1_packet *packet)
{
	u32 hdrsize = packet->hlen;
	struct ib_wc wc;
	u32 src_qp;
	u16 pkey;
	int mgmt_pkey_idx = -1;
	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
	void *data = packet->payload;
	u32 tlen = packet->tlen;
	struct rvt_qp *qp = packet->qp;
	u8 sc5 = packet->sc;
	u8 sl_from_sc;
	u8 opcode = packet->opcode;
	u8 sl = packet->sl;
	u32 dlid = packet->dlid;
	u32 slid = packet->slid;
	u8 extra_bytes;
	u8 l4 = 0;
	bool dlid_is_permissive;
	bool slid_is_permissive;
	bool solicited = false;

	extra_bytes = packet->pad + packet->extra_byte + (SIZE_OF_CRC << 2);

	if (packet->etype == RHF_RCV_TYPE_BYPASS) {
		u32 permissive_lid =
			opa_get_lid(be32_to_cpu(OPA_LID_PERMISSIVE), 16B);

		l4 = hfi1_16B_get_l4(packet->hdr);
		pkey = hfi1_16B_get_pkey(packet->hdr);
		dlid_is_permissive = (dlid == permissive_lid);
		slid_is_permissive = (slid == permissive_lid);
	} else {
		pkey = ib_bth_get_pkey(packet->ohdr);
		dlid_is_permissive = (dlid == be16_to_cpu(IB_LID_PERMISSIVE));
		slid_is_permissive = (slid == be16_to_cpu(IB_LID_PERMISSIVE));
	}
	sl_from_sc = ibp->sc_to_sl[sc5];

	if (likely(l4 != OPA_16B_L4_FM)) {
		src_qp = ib_get_sqpn(packet->ohdr);
		solicited = ib_bth_is_solicited(packet->ohdr);
	} else {
		src_qp = hfi1_16B_get_src_qpn(packet->mgmt);
	}

	process_ecn(qp, packet);
	/*
	 * Get the number of bytes the message was padded by
	 * and drop incomplete packets.
	 */
	if (unlikely(tlen < (hdrsize + extra_bytes)))
		goto drop;

	tlen -= hdrsize + extra_bytes;

	/*
	 * Check that the permissive LID is only used on QP0
	 * and the QKEY matches (see 9.6.1.4.1 and 9.6.1.5.1).
	 */
	if (qp->ibqp.qp_num) {
		if (unlikely(dlid_is_permissive || slid_is_permissive))
			goto drop;
		if (qp->ibqp.qp_num > 1) {
			if (unlikely(rcv_pkey_check(ppd, pkey, sc5, slid))) {
				/*
				 * Traps will not be sent for packets dropped
				 * by the HW. This is fine, as sending trap
				 * for invalid pkeys is optional according to
				 * IB spec (release 1.3, section 10.9.4)
				 */
				hfi1_bad_pkey(ibp,
					      pkey, sl,
					      src_qp, qp->ibqp.qp_num,
					      slid, dlid);
				return;
			}
		} else {
			/* GSI packet */
			mgmt_pkey_idx = hfi1_lookup_pkey_idx(ibp, pkey);
			if (mgmt_pkey_idx < 0)
				goto drop;
		}
		if (unlikely(l4 != OPA_16B_L4_FM &&
			     ib_get_qkey(packet->ohdr) != qp->qkey))
			return; /* Silent drop */

		/* Drop invalid MAD packets (see 13.5.3.1). */
		if (unlikely(qp->ibqp.qp_num == 1 &&
			     (tlen > 2048 || (sc5 == 0xF))))
			goto drop;
	} else {
		/* Received on QP0, and so by definition, this is an SMP */
		struct opa_smp *smp = (struct opa_smp *)data;

		if (opa_smp_check(ibp, pkey, sc5, qp, slid, smp))
			goto drop;

		if (tlen > 2048)
			goto drop;
		if ((dlid_is_permissive || slid_is_permissive) &&
		    smp->mgmt_class != IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
			goto drop;

		/* look up SMI pkey */
		mgmt_pkey_idx = hfi1_lookup_pkey_idx(ibp, pkey);
		if (mgmt_pkey_idx < 0)
			goto drop;
	}

	if (qp->ibqp.qp_num > 1 &&
	    opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) {
		wc.ex.imm_data = packet->ohdr->u.ud.imm_data;
		wc.wc_flags = IB_WC_WITH_IMM;
	} else if (opcode == IB_OPCODE_UD_SEND_ONLY) {
		wc.ex.imm_data = 0;
		wc.wc_flags = 0;
	} else {
		goto drop;
	}

	/*
	 * A GRH is expected to precede the data even if not
	 * present on the wire.
	 */
	wc.byte_len = tlen + sizeof(struct ib_grh);

	/*
	 * Get the next work request entry to find where to put the data.
	 */
	if (qp->r_flags & RVT_R_REUSE_SGE) {
		qp->r_flags &= ~RVT_R_REUSE_SGE;
	} else {
		int ret;

		ret = rvt_get_rwqe(qp, false);
		if (ret < 0) {
			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
			return;
		}
		if (!ret) {
			if (qp->ibqp.qp_num == 0)
				ibp->rvp.n_vl15_dropped++;
			return;
		}
	}
	/* Silently drop packets which are too big. */
	if (unlikely(wc.byte_len > qp->r_len)) {
		qp->r_flags |= RVT_R_REUSE_SGE;
		goto drop;
	}
	if (packet->grh) {
		rvt_copy_sge(qp, &qp->r_sge, packet->grh,
			     sizeof(struct ib_grh), true, false);
		wc.wc_flags |= IB_WC_GRH;
	} else if (packet->etype == RHF_RCV_TYPE_BYPASS) {
		struct ib_grh grh;
		/*
		 * Assuming we only created 16B on the send side
		 * if we want to use large LIDs, since GRH was stripped
		 * out when creating 16B, add back the GRH here.
		 */
		hfi1_make_ext_grh(packet, &grh, slid, dlid);
		rvt_copy_sge(qp, &qp->r_sge, &grh,
			     sizeof(struct ib_grh), true, false);
		wc.wc_flags |= IB_WC_GRH;
	} else {
		rvt_skip_sge(&qp->r_sge, sizeof(struct ib_grh), true);
	}
	rvt_copy_sge(qp, &qp->r_sge, data, wc.byte_len - sizeof(struct ib_grh),
		     true, false);
	rvt_put_ss(&qp->r_sge);
	if (!test_and_clear_bit(RVT_R_WRID_VALID, &qp->r_aflags))
		return;
	wc.wr_id = qp->r_wr_id;
	wc.status = IB_WC_SUCCESS;
	wc.opcode = IB_WC_RECV;
	wc.vendor_err = 0;
	wc.qp = &qp->ibqp;
	wc.src_qp = src_qp;

	if (qp->ibqp.qp_type == IB_QPT_GSI ||
	    qp->ibqp.qp_type == IB_QPT_SMI) {
		if (mgmt_pkey_idx < 0) {
			if (net_ratelimit()) {
				struct hfi1_devdata *dd = ppd->dd;

				dd_dev_err(dd, "QP type %d mgmt_pkey_idx < 0 and packet not dropped???\n",
					   qp->ibqp.qp_type);
				mgmt_pkey_idx = 0;
			}
		}
		wc.pkey_index = (unsigned)mgmt_pkey_idx;
	} else {
		wc.pkey_index = 0;
	}
	if (slid_is_permissive)
		slid = be32_to_cpu(OPA_LID_PERMISSIVE);
	wc.slid = slid & U16_MAX;
	wc.sl = sl_from_sc;

	/*
	 * Save the LMC lower bits if the destination LID is a unicast LID.
	 */
	wc.dlid_path_bits = hfi1_check_mcast(dlid) ? 0 :
		dlid & ((1 << ppd_from_ibp(ibp)->lmc) - 1);
	wc.port_num = qp->port_num;
	/* Signal completion event if the solicited bit is set. */
	rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc, solicited);
	return;

drop:
	ibp->rvp.n_pkt_drops++;
}