summaryrefslogtreecommitdiffstats
path: root/net/sunrpc/xprtrdma/svc_rdma_transport.c
blob: e660d4965b18aa2b40af11576405d4d14c283d9d (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
/*
 * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved.
 * Copyright (c) 2005-2007 Network Appliance, Inc. 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 BSD-type
 * 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.
 *
 *      Neither the name of the Network Appliance, Inc. 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.
 *
 * Author: Tom Tucker <tom@opengridcomputing.com>
 */

#include <linux/sunrpc/svc_xprt.h>
#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/debug.h>
#include <linux/sunrpc/rpc_rdma.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/workqueue.h>
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
#include <linux/sunrpc/svc_rdma.h>
#include <linux/export.h>
#include "xprt_rdma.h"

#define RPCDBG_FACILITY	RPCDBG_SVCXPRT

static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *, int);
static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
					struct net *net,
					struct sockaddr *sa, int salen,
					int flags);
static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt);
static void svc_rdma_release_rqst(struct svc_rqst *);
static void svc_rdma_detach(struct svc_xprt *xprt);
static void svc_rdma_free(struct svc_xprt *xprt);
static int svc_rdma_has_wspace(struct svc_xprt *xprt);
static int svc_rdma_secure_port(struct svc_rqst *);
static void svc_rdma_kill_temp_xprt(struct svc_xprt *);

static struct svc_xprt_ops svc_rdma_ops = {
	.xpo_create = svc_rdma_create,
	.xpo_recvfrom = svc_rdma_recvfrom,
	.xpo_sendto = svc_rdma_sendto,
	.xpo_release_rqst = svc_rdma_release_rqst,
	.xpo_detach = svc_rdma_detach,
	.xpo_free = svc_rdma_free,
	.xpo_prep_reply_hdr = svc_rdma_prep_reply_hdr,
	.xpo_has_wspace = svc_rdma_has_wspace,
	.xpo_accept = svc_rdma_accept,
	.xpo_secure_port = svc_rdma_secure_port,
	.xpo_kill_temp_xprt = svc_rdma_kill_temp_xprt,
};

struct svc_xprt_class svc_rdma_class = {
	.xcl_name = "rdma",
	.xcl_owner = THIS_MODULE,
	.xcl_ops = &svc_rdma_ops,
	.xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA,
	.xcl_ident = XPRT_TRANSPORT_RDMA,
};

#if defined(CONFIG_SUNRPC_BACKCHANNEL)
static struct svc_xprt *svc_rdma_bc_create(struct svc_serv *, struct net *,
					   struct sockaddr *, int, int);
static void svc_rdma_bc_detach(struct svc_xprt *);
static void svc_rdma_bc_free(struct svc_xprt *);

static struct svc_xprt_ops svc_rdma_bc_ops = {
	.xpo_create = svc_rdma_bc_create,
	.xpo_detach = svc_rdma_bc_detach,
	.xpo_free = svc_rdma_bc_free,
	.xpo_prep_reply_hdr = svc_rdma_prep_reply_hdr,
	.xpo_secure_port = svc_rdma_secure_port,
};

struct svc_xprt_class svc_rdma_bc_class = {
	.xcl_name = "rdma-bc",
	.xcl_owner = THIS_MODULE,
	.xcl_ops = &svc_rdma_bc_ops,
	.xcl_max_payload = (1024 - RPCRDMA_HDRLEN_MIN)
};

static struct svc_xprt *svc_rdma_bc_create(struct svc_serv *serv,
					   struct net *net,
					   struct sockaddr *sa, int salen,
					   int flags)
{
	struct svcxprt_rdma *cma_xprt;
	struct svc_xprt *xprt;

	cma_xprt = rdma_create_xprt(serv, 0);
	if (!cma_xprt)
		return ERR_PTR(-ENOMEM);
	xprt = &cma_xprt->sc_xprt;

	svc_xprt_init(net, &svc_rdma_bc_class, xprt, serv);
	set_bit(XPT_CONG_CTRL, &xprt->xpt_flags);
	serv->sv_bc_xprt = xprt;

	dprintk("svcrdma: %s(%p)\n", __func__, xprt);
	return xprt;
}

static void svc_rdma_bc_detach(struct svc_xprt *xprt)
{
	dprintk("svcrdma: %s(%p)\n", __func__, xprt);
}

static void svc_rdma_bc_free(struct svc_xprt *xprt)
{
	struct svcxprt_rdma *rdma =
		container_of(xprt, struct svcxprt_rdma, sc_xprt);

	dprintk("svcrdma: %s(%p)\n", __func__, xprt);
	if (xprt)
		kfree(rdma);
}
#endif	/* CONFIG_SUNRPC_BACKCHANNEL */

static struct svc_rdma_op_ctxt *alloc_ctxt(struct svcxprt_rdma *xprt,
					   gfp_t flags)
{
	struct svc_rdma_op_ctxt *ctxt;

	ctxt = kmalloc(sizeof(*ctxt), flags);
	if (ctxt) {
		ctxt->xprt = xprt;
		INIT_LIST_HEAD(&ctxt->list);
	}
	return ctxt;
}

static bool svc_rdma_prealloc_ctxts(struct svcxprt_rdma *xprt)
{
	unsigned int i;

	/* Each RPC/RDMA credit can consume a number of send
	 * and receive WQEs. One ctxt is allocated for each.
	 */
	i = xprt->sc_sq_depth + xprt->sc_rq_depth;

	while (i--) {
		struct svc_rdma_op_ctxt *ctxt;

		ctxt = alloc_ctxt(xprt, GFP_KERNEL);
		if (!ctxt) {
			dprintk("svcrdma: No memory for RDMA ctxt\n");
			return false;
		}
		list_add(&ctxt->list, &xprt->sc_ctxts);
	}
	return true;
}

struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
{
	struct svc_rdma_op_ctxt *ctxt = NULL;

	spin_lock(&xprt->sc_ctxt_lock);
	xprt->sc_ctxt_used++;
	if (list_empty(&xprt->sc_ctxts))
		goto out_empty;

	ctxt = list_first_entry(&xprt->sc_ctxts,
				struct svc_rdma_op_ctxt, list);
	list_del(&ctxt->list);
	spin_unlock(&xprt->sc_ctxt_lock);

out:
	ctxt->count = 0;
	ctxt->mapped_sges = 0;
	return ctxt;

out_empty:
	/* Either pre-allocation missed the mark, or send
	 * queue accounting is broken.
	 */
	spin_unlock(&xprt->sc_ctxt_lock);

	ctxt = alloc_ctxt(xprt, GFP_NOIO);
	if (ctxt)
		goto out;

	spin_lock(&xprt->sc_ctxt_lock);
	xprt->sc_ctxt_used--;
	spin_unlock(&xprt->sc_ctxt_lock);
	WARN_ONCE(1, "svcrdma: empty RDMA ctxt list?\n");
	return NULL;
}

void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt)
{
	struct svcxprt_rdma *xprt = ctxt->xprt;
	struct ib_device *device = xprt->sc_cm_id->device;
	unsigned int i;

	for (i = 0; i < ctxt->mapped_sges; i++)
		ib_dma_unmap_page(device,
				  ctxt->sge[i].addr,
				  ctxt->sge[i].length,
				  ctxt->direction);
	ctxt->mapped_sges = 0;
}

void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
{
	struct svcxprt_rdma *xprt = ctxt->xprt;
	int i;

	if (free_pages)
		for (i = 0; i < ctxt->count; i++)
			put_page(ctxt->pages[i]);

	spin_lock(&xprt->sc_ctxt_lock);
	xprt->sc_ctxt_used--;
	list_add(&ctxt->list, &xprt->sc_ctxts);
	spin_unlock(&xprt->sc_ctxt_lock);
}

static void svc_rdma_destroy_ctxts(struct svcxprt_rdma *xprt)
{
	while (!list_empty(&xprt->sc_ctxts)) {
		struct svc_rdma_op_ctxt *ctxt;

		ctxt = list_first_entry(&xprt->sc_ctxts,
					struct svc_rdma_op_ctxt, list);
		list_del(&ctxt->list);
		kfree(ctxt);
	}
}

/* QP event handler */
static void qp_event_handler(struct ib_event *event, void *context)
{
	struct svc_xprt *xprt = context;

	switch (event->event) {
	/* These are considered benign events */
	case IB_EVENT_PATH_MIG:
	case IB_EVENT_COMM_EST:
	case IB_EVENT_SQ_DRAINED:
	case IB_EVENT_QP_LAST_WQE_REACHED:
		dprintk("svcrdma: QP event %s (%d) received for QP=%p\n",
			ib_event_msg(event->event), event->event,
			event->element.qp);
		break;
	/* These are considered fatal events */
	case IB_EVENT_PATH_MIG_ERR:
	case IB_EVENT_QP_FATAL:
	case IB_EVENT_QP_REQ_ERR:
	case IB_EVENT_QP_ACCESS_ERR:
	case IB_EVENT_DEVICE_FATAL:
	default:
		dprintk("svcrdma: QP ERROR event %s (%d) received for QP=%p, "
			"closing transport\n",
			ib_event_msg(event->event), event->event,
			event->element.qp);
		set_bit(XPT_CLOSE, &xprt->xpt_flags);
		break;
	}
}

/**
 * svc_rdma_wc_receive - Invoked by RDMA provider for each polled Receive WC
 * @cq:        completion queue
 * @wc:        completed WR
 *
 */
static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
{
	struct svcxprt_rdma *xprt = cq->cq_context;
	struct ib_cqe *cqe = wc->wr_cqe;
	struct svc_rdma_op_ctxt *ctxt;

	/* WARNING: Only wc->wr_cqe and wc->status are reliable */
	ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe);
	svc_rdma_unmap_dma(ctxt);

	if (wc->status != IB_WC_SUCCESS)
		goto flushed;

	/* All wc fields are now known to be valid */
	ctxt->byte_len = wc->byte_len;
	spin_lock(&xprt->sc_rq_dto_lock);
	list_add_tail(&ctxt->list, &xprt->sc_rq_dto_q);
	spin_unlock(&xprt->sc_rq_dto_lock);

	set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
	if (test_bit(RDMAXPRT_CONN_PENDING, &xprt->sc_flags))
		goto out;
	svc_xprt_enqueue(&xprt->sc_xprt);
	goto out;

flushed:
	if (wc->status != IB_WC_WR_FLUSH_ERR)
		pr_warn("svcrdma: receive: %s (%u/0x%x)\n",
			ib_wc_status_msg(wc->status),
			wc->status, wc->vendor_err);
	set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
	svc_rdma_put_context(ctxt, 1);

out:
	svc_xprt_put(&xprt->sc_xprt);
}

/**
 * svc_rdma_wc_send - Invoked by RDMA provider for each polled Send WC
 * @cq:        completion queue
 * @wc:        completed WR
 *
 */
void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
{
	struct svcxprt_rdma *xprt = cq->cq_context;
	struct ib_cqe *cqe = wc->wr_cqe;
	struct svc_rdma_op_ctxt *ctxt;

	atomic_inc(&xprt->sc_sq_avail);
	wake_up(&xprt->sc_send_wait);

	ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe);
	svc_rdma_unmap_dma(ctxt);
	svc_rdma_put_context(ctxt, 1);

	if (unlikely(wc->status != IB_WC_SUCCESS)) {
		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
		if (wc->status != IB_WC_WR_FLUSH_ERR)
			pr_err("svcrdma: Send: %s (%u/0x%x)\n",
			       ib_wc_status_msg(wc->status),
			       wc->status, wc->vendor_err);
	}

	svc_xprt_put(&xprt->sc_xprt);
}

static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
					     int listener)
{
	struct svcxprt_rdma *cma_xprt = kzalloc(sizeof *cma_xprt, GFP_KERNEL);

	if (!cma_xprt)
		return NULL;
	svc_xprt_init(&init_net, &svc_rdma_class, &cma_xprt->sc_xprt, serv);
	INIT_LIST_HEAD(&cma_xprt->sc_accept_q);
	INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q);
	INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q);
	INIT_LIST_HEAD(&cma_xprt->sc_ctxts);
	INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts);
	init_waitqueue_head(&cma_xprt->sc_send_wait);

	spin_lock_init(&cma_xprt->sc_lock);
	spin_lock_init(&cma_xprt->sc_rq_dto_lock);
	spin_lock_init(&cma_xprt->sc_ctxt_lock);
	spin_lock_init(&cma_xprt->sc_rw_ctxt_lock);

	/*
	 * Note that this implies that the underlying transport support
	 * has some form of congestion control (see RFC 7530 section 3.1
	 * paragraph 2). For now, we assume that all supported RDMA
	 * transports are suitable here.
	 */
	set_bit(XPT_CONG_CTRL, &cma_xprt->sc_xprt.xpt_flags);

	if (listener)
		set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags);

	return cma_xprt;
}

int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags)
{
	struct ib_recv_wr recv_wr, *bad_recv_wr;
	struct svc_rdma_op_ctxt *ctxt;
	struct page *page;
	dma_addr_t pa;
	int sge_no;
	int buflen;
	int ret;

	ctxt = svc_rdma_get_context(xprt);
	buflen = 0;
	ctxt->direction = DMA_FROM_DEVICE;
	ctxt->cqe.done = svc_rdma_wc_receive;
	for (sge_no = 0; buflen < xprt->sc_max_req_size; sge_no++) {
		if (sge_no >= xprt->sc_max_sge) {
			pr_err("svcrdma: Too many sges (%d)\n", sge_no);
			goto err_put_ctxt;
		}
		page = alloc_page(flags);
		if (!page)
			goto err_put_ctxt;
		ctxt->pages[sge_no] = page;
		pa = ib_dma_map_page(xprt->sc_cm_id->device,
				     page, 0, PAGE_SIZE,
				     DMA_FROM_DEVICE);
		if (ib_dma_mapping_error(xprt->sc_cm_id->device, pa))
			goto err_put_ctxt;
		svc_rdma_count_mappings(xprt, ctxt);
		ctxt->sge[sge_no].addr = pa;
		ctxt->sge[sge_no].length = PAGE_SIZE;
		ctxt->sge[sge_no].lkey = xprt->sc_pd->local_dma_lkey;
		ctxt->count = sge_no + 1;
		buflen += PAGE_SIZE;
	}
	recv_wr.next = NULL;
	recv_wr.sg_list = &ctxt->sge[0];
	recv_wr.num_sge = ctxt->count;
	recv_wr.wr_cqe = &ctxt->cqe;

	svc_xprt_get(&xprt->sc_xprt);
	ret = ib_post_recv(xprt->sc_qp, &recv_wr, &bad_recv_wr);
	if (ret) {
		svc_rdma_unmap_dma(ctxt);
		svc_rdma_put_context(ctxt, 1);
		svc_xprt_put(&xprt->sc_xprt);
	}
	return ret;

 err_put_ctxt:
	svc_rdma_unmap_dma(ctxt);
	svc_rdma_put_context(ctxt, 1);
	return -ENOMEM;
}

int svc_rdma_repost_recv(struct svcxprt_rdma *xprt, gfp_t flags)
{
	int ret = 0;

	ret = svc_rdma_post_recv(xprt, flags);
	if (ret) {
		pr_err("svcrdma: could not post a receive buffer, err=%d.\n",
		       ret);
		pr_err("svcrdma: closing transport %p.\n", xprt);
		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
		ret = -ENOTCONN;
	}
	return ret;
}

static void
svc_rdma_parse_connect_private(struct svcxprt_rdma *newxprt,
			       struct rdma_conn_param *param)
{
	const struct rpcrdma_connect_private *pmsg = param->private_data;

	if (pmsg &&
	    pmsg->cp_magic == rpcrdma_cmp_magic &&
	    pmsg->cp_version == RPCRDMA_CMP_VERSION) {
		newxprt->sc_snd_w_inv = pmsg->cp_flags &
					RPCRDMA_CMP_F_SND_W_INV_OK;

		dprintk("svcrdma: client send_size %u, recv_size %u "
			"remote inv %ssupported\n",
			rpcrdma_decode_buffer_size(pmsg->cp_send_size),
			rpcrdma_decode_buffer_size(pmsg->cp_recv_size),
			newxprt->sc_snd_w_inv ? "" : "un");
	}
}

/*
 * This function handles the CONNECT_REQUEST event on a listening
 * endpoint. It is passed the cma_id for the _new_ connection. The context in
 * this cma_id is inherited from the listening cma_id and is the svc_xprt
 * structure for the listening endpoint.
 *
 * This function creates a new xprt for the new connection and enqueues it on
 * the accept queue for the listent xprt. When the listen thread is kicked, it
 * will call the recvfrom method on the listen xprt which will accept the new
 * connection.
 */
static void handle_connect_req(struct rdma_cm_id *new_cma_id,
			       struct rdma_conn_param *param)
{
	struct svcxprt_rdma *listen_xprt = new_cma_id->context;
	struct svcxprt_rdma *newxprt;
	struct sockaddr *sa;

	/* Create a new transport */
	newxprt = rdma_create_xprt(listen_xprt->sc_xprt.xpt_server, 0);
	if (!newxprt) {
		dprintk("svcrdma: failed to create new transport\n");
		return;
	}
	newxprt->sc_cm_id = new_cma_id;
	new_cma_id->context = newxprt;
	dprintk("svcrdma: Creating newxprt=%p, cm_id=%p, listenxprt=%p\n",
		newxprt, newxprt->sc_cm_id, listen_xprt);
	svc_rdma_parse_connect_private(newxprt, param);

	/* Save client advertised inbound read limit for use later in accept. */
	newxprt->sc_ord = param->initiator_depth;

	/* Set the local and remote addresses in the transport */
	sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr;
	svc_xprt_set_remote(&newxprt->sc_xprt, sa, svc_addr_len(sa));
	sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr;
	svc_xprt_set_local(&newxprt->sc_xprt, sa, svc_addr_len(sa));

	/*
	 * Enqueue the new transport on the accept queue of the listening
	 * transport
	 */
	spin_lock_bh(&listen_xprt->sc_lock);
	list_add_tail(&newxprt->sc_accept_q, &listen_xprt->sc_accept_q);
	spin_unlock_bh(&listen_xprt->sc_lock);

	set_bit(XPT_CONN, &listen_xprt->sc_xprt.xpt_flags);
	svc_xprt_enqueue(&listen_xprt->sc_xprt);
}

/*
 * Handles events generated on the listening endpoint. These events will be
 * either be incoming connect requests or adapter removal  events.
 */
static int rdma_listen_handler(struct rdma_cm_id *cma_id,
			       struct rdma_cm_event *event)
{
	struct svcxprt_rdma *xprt = cma_id->context;
	int ret = 0;

	switch (event->event) {
	case RDMA_CM_EVENT_CONNECT_REQUEST:
		dprintk("svcrdma: Connect request on cma_id=%p, xprt = %p, "
			"event = %s (%d)\n", cma_id, cma_id->context,
			rdma_event_msg(event->event), event->event);
		handle_connect_req(cma_id, &event->param.conn);
		break;

	case RDMA_CM_EVENT_ESTABLISHED:
		/* Accept complete */
		dprintk("svcrdma: Connection completed on LISTEN xprt=%p, "
			"cm_id=%p\n", xprt, cma_id);
		break;

	case RDMA_CM_EVENT_DEVICE_REMOVAL:
		dprintk("svcrdma: Device removal xprt=%p, cm_id=%p\n",
			xprt, cma_id);
		if (xprt)
			set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
		break;

	default:
		dprintk("svcrdma: Unexpected event on listening endpoint %p, "
			"event = %s (%d)\n", cma_id,
			rdma_event_msg(event->event), event->event);
		break;
	}

	return ret;
}

static int rdma_cma_handler(struct rdma_cm_id *cma_id,
			    struct rdma_cm_event *event)
{
	struct svc_xprt *xprt = cma_id->context;
	struct svcxprt_rdma *rdma =
		container_of(xprt, struct svcxprt_rdma, sc_xprt);
	switch (event->event) {
	case RDMA_CM_EVENT_ESTABLISHED:
		/* Accept complete */
		svc_xprt_get(xprt);
		dprintk("svcrdma: Connection completed on DTO xprt=%p, "
			"cm_id=%p\n", xprt, cma_id);
		clear_bit(RDMAXPRT_CONN_PENDING, &rdma->sc_flags);
		svc_xprt_enqueue(xprt);
		break;
	case RDMA_CM_EVENT_DISCONNECTED:
		dprintk("svcrdma: Disconnect on DTO xprt=%p, cm_id=%p\n",
			xprt, cma_id);
		if (xprt) {
			set_bit(XPT_CLOSE, &xprt->xpt_flags);
			svc_xprt_enqueue(xprt);
			svc_xprt_put(xprt);
		}
		break;
	case RDMA_CM_EVENT_DEVICE_REMOVAL:
		dprintk("svcrdma: Device removal cma_id=%p, xprt = %p, "
			"event = %s (%d)\n", cma_id, xprt,
			rdma_event_msg(event->event), event->event);
		if (xprt) {
			set_bit(XPT_CLOSE, &xprt->xpt_flags);
			svc_xprt_enqueue(xprt);
			svc_xprt_put(xprt);
		}
		break;
	default:
		dprintk("svcrdma: Unexpected event on DTO endpoint %p, "
			"event = %s (%d)\n", cma_id,
			rdma_event_msg(event->event), event->event);
		break;
	}
	return 0;
}

/*
 * Create a listening RDMA service endpoint.
 */
static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
					struct net *net,
					struct sockaddr *sa, int salen,
					int flags)
{
	struct rdma_cm_id *listen_id;
	struct svcxprt_rdma *cma_xprt;
	int ret;

	dprintk("svcrdma: Creating RDMA socket\n");
	if ((sa->sa_family != AF_INET) && (sa->sa_family != AF_INET6)) {
		dprintk("svcrdma: Address family %d is not supported.\n", sa->sa_family);
		return ERR_PTR(-EAFNOSUPPORT);
	}
	cma_xprt = rdma_create_xprt(serv, 1);
	if (!cma_xprt)
		return ERR_PTR(-ENOMEM);

	listen_id = rdma_create_id(&init_net, rdma_listen_handler, cma_xprt,
				   RDMA_PS_TCP, IB_QPT_RC);
	if (IS_ERR(listen_id)) {
		ret = PTR_ERR(listen_id);
		dprintk("svcrdma: rdma_create_id failed = %d\n", ret);
		goto err0;
	}

	/* Allow both IPv4 and IPv6 sockets to bind a single port
	 * at the same time.
	 */
#if IS_ENABLED(CONFIG_IPV6)
	ret = rdma_set_afonly(listen_id, 1);
	if (ret) {
		dprintk("svcrdma: rdma_set_afonly failed = %d\n", ret);
		goto err1;
	}
#endif
	ret = rdma_bind_addr(listen_id, sa);
	if (ret) {
		dprintk("svcrdma: rdma_bind_addr failed = %d\n", ret);
		goto err1;
	}
	cma_xprt->sc_cm_id = listen_id;

	ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG);
	if (ret) {
		dprintk("svcrdma: rdma_listen failed = %d\n", ret);
		goto err1;
	}

	/*
	 * We need to use the address from the cm_id in case the
	 * caller specified 0 for the port number.
	 */
	sa = (struct sockaddr *)&cma_xprt->sc_cm_id->route.addr.src_addr;
	svc_xprt_set_local(&cma_xprt->sc_xprt, sa, salen);

	return &cma_xprt->sc_xprt;

 err1:
	rdma_destroy_id(listen_id);
 err0:
	kfree(cma_xprt);
	return ERR_PTR(ret);
}

/*
 * This is the xpo_recvfrom function for listening endpoints. Its
 * purpose is to accept incoming connections. The CMA callback handler
 * has already created a new transport and attached it to the new CMA
 * ID.
 *
 * There is a queue of pending connections hung on the listening
 * transport. This queue contains the new svc_xprt structure. This
 * function takes svc_xprt structures off the accept_q and completes
 * the connection.
 */
static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
{
	struct svcxprt_rdma *listen_rdma;
	struct svcxprt_rdma *newxprt = NULL;
	struct rdma_conn_param conn_param;
	struct rpcrdma_connect_private pmsg;
	struct ib_qp_init_attr qp_attr;
	struct ib_device *dev;
	struct sockaddr *sap;
	unsigned int i;
	int ret = 0;

	listen_rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt);
	clear_bit(XPT_CONN, &xprt->xpt_flags);
	/* Get the next entry off the accept list */
	spin_lock_bh(&listen_rdma->sc_lock);
	if (!list_empty(&listen_rdma->sc_accept_q)) {
		newxprt = list_entry(listen_rdma->sc_accept_q.next,
				     struct svcxprt_rdma, sc_accept_q);
		list_del_init(&newxprt->sc_accept_q);
	}
	if (!list_empty(&listen_rdma->sc_accept_q))
		set_bit(XPT_CONN, &listen_rdma->sc_xprt.xpt_flags);
	spin_unlock_bh(&listen_rdma->sc_lock);
	if (!newxprt)
		return NULL;

	dprintk("svcrdma: newxprt from accept queue = %p, cm_id=%p\n",
		newxprt, newxprt->sc_cm_id);

	dev = newxprt->sc_cm_id->device;
	newxprt->sc_port_num = newxprt->sc_cm_id->port_num;

	/* Qualify the transport resource defaults with the
	 * capabilities of this particular device */
	newxprt->sc_max_sge = min((size_t)dev->attrs.max_sge,
				  (size_t)RPCSVC_MAXPAGES);
	newxprt->sc_max_req_size = svcrdma_max_req_size;
	newxprt->sc_max_requests = min_t(u32, dev->attrs.max_qp_wr,
					 svcrdma_max_requests);
	newxprt->sc_fc_credits = cpu_to_be32(newxprt->sc_max_requests);
	newxprt->sc_max_bc_requests = min_t(u32, dev->attrs.max_qp_wr,
					    svcrdma_max_bc_requests);
	newxprt->sc_rq_depth = newxprt->sc_max_requests +
			       newxprt->sc_max_bc_requests;
	newxprt->sc_sq_depth = newxprt->sc_rq_depth;
	atomic_set(&newxprt->sc_sq_avail, newxprt->sc_sq_depth);

	if (!svc_rdma_prealloc_ctxts(newxprt))
		goto errout;

	/*
	 * Limit ORD based on client limit, local device limit, and
	 * configured svcrdma limit.
	 */
	newxprt->sc_ord = min_t(size_t, dev->attrs.max_qp_rd_atom, newxprt->sc_ord);
	newxprt->sc_ord = min_t(size_t,	svcrdma_ord, newxprt->sc_ord);

	newxprt->sc_pd = ib_alloc_pd(dev, 0);
	if (IS_ERR(newxprt->sc_pd)) {
		dprintk("svcrdma: error creating PD for connect request\n");
		goto errout;
	}
	newxprt->sc_sq_cq = ib_alloc_cq(dev, newxprt, newxprt->sc_sq_depth,
					0, IB_POLL_WORKQUEUE);
	if (IS_ERR(newxprt->sc_sq_cq)) {
		dprintk("svcrdma: error creating SQ CQ for connect request\n");
		goto errout;
	}
	newxprt->sc_rq_cq = ib_alloc_cq(dev, newxprt, newxprt->sc_rq_depth,
					0, IB_POLL_WORKQUEUE);
	if (IS_ERR(newxprt->sc_rq_cq)) {
		dprintk("svcrdma: error creating RQ CQ for connect request\n");
		goto errout;
	}

	memset(&qp_attr, 0, sizeof qp_attr);
	qp_attr.event_handler = qp_event_handler;
	qp_attr.qp_context = &newxprt->sc_xprt;
	qp_attr.port_num = newxprt->sc_port_num;
	qp_attr.cap.max_rdma_ctxs = newxprt->sc_max_requests;
	qp_attr.cap.max_send_wr = newxprt->sc_sq_depth;
	qp_attr.cap.max_recv_wr = newxprt->sc_rq_depth;
	qp_attr.cap.max_send_sge = newxprt->sc_max_sge;
	qp_attr.cap.max_recv_sge = newxprt->sc_max_sge;
	qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
	qp_attr.qp_type = IB_QPT_RC;
	qp_attr.send_cq = newxprt->sc_sq_cq;
	qp_attr.recv_cq = newxprt->sc_rq_cq;
	dprintk("svcrdma: newxprt->sc_cm_id=%p, newxprt->sc_pd=%p\n",
		newxprt->sc_cm_id, newxprt->sc_pd);
	dprintk("    cap.max_send_wr = %d, cap.max_recv_wr = %d\n",
		qp_attr.cap.max_send_wr, qp_attr.cap.max_recv_wr);
	dprintk("    cap.max_send_sge = %d, cap.max_recv_sge = %d\n",
		qp_attr.cap.max_send_sge, qp_attr.cap.max_recv_sge);

	ret = rdma_create_qp(newxprt->sc_cm_id, newxprt->sc_pd, &qp_attr);
	if (ret) {
		dprintk("svcrdma: failed to create QP, ret=%d\n", ret);
		goto errout;
	}
	newxprt->sc_qp = newxprt->sc_cm_id->qp;

	if (!(dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS))
		newxprt->sc_snd_w_inv = false;
	if (!rdma_protocol_iwarp(dev, newxprt->sc_port_num) &&
	    !rdma_ib_or_roce(dev, newxprt->sc_port_num))
		goto errout;

	/* Post receive buffers */
	for (i = 0; i < newxprt->sc_max_requests; i++) {
		ret = svc_rdma_post_recv(newxprt, GFP_KERNEL);
		if (ret) {
			dprintk("svcrdma: failure posting receive buffers\n");
			goto errout;
		}
	}

	/* Swap out the handler */
	newxprt->sc_cm_id->event_handler = rdma_cma_handler;

	/* Construct RDMA-CM private message */
	pmsg.cp_magic = rpcrdma_cmp_magic;
	pmsg.cp_version = RPCRDMA_CMP_VERSION;
	pmsg.cp_flags = 0;
	pmsg.cp_send_size = pmsg.cp_recv_size =
		rpcrdma_encode_buffer_size(newxprt->sc_max_req_size);

	/* Accept Connection */
	set_bit(RDMAXPRT_CONN_PENDING, &newxprt->sc_flags);
	memset(&conn_param, 0, sizeof conn_param);
	conn_param.responder_resources = 0;
	conn_param.initiator_depth = newxprt->sc_ord;
	conn_param.private_data = &pmsg;
	conn_param.private_data_len = sizeof(pmsg);
	ret = rdma_accept(newxprt->sc_cm_id, &conn_param);
	if (ret) {
		dprintk("svcrdma: failed to accept new connection, ret=%d\n",
		       ret);
		goto errout;
	}

	dprintk("svcrdma: new connection %p accepted:\n", newxprt);
	sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr;
	dprintk("    local address   : %pIS:%u\n", sap, rpc_get_port(sap));
	sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr;
	dprintk("    remote address  : %pIS:%u\n", sap, rpc_get_port(sap));
	dprintk("    max_sge         : %d\n", newxprt->sc_max_sge);
	dprintk("    sq_depth        : %d\n", newxprt->sc_sq_depth);
	dprintk("    max_requests    : %d\n", newxprt->sc_max_requests);
	dprintk("    ord             : %d\n", newxprt->sc_ord);

	return &newxprt->sc_xprt;

 errout:
	dprintk("svcrdma: failure accepting new connection rc=%d.\n", ret);
	/* Take a reference in case the DTO handler runs */
	svc_xprt_get(&newxprt->sc_xprt);
	if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp))
		ib_destroy_qp(newxprt->sc_qp);
	rdma_destroy_id(newxprt->sc_cm_id);
	/* This call to put will destroy the transport */
	svc_xprt_put(&newxprt->sc_xprt);
	return NULL;
}

static void svc_rdma_release_rqst(struct svc_rqst *rqstp)
{
}

/*
 * When connected, an svc_xprt has at least two references:
 *
 * - A reference held by the cm_id between the ESTABLISHED and
 *   DISCONNECTED events. If the remote peer disconnected first, this
 *   reference could be gone.
 *
 * - A reference held by the svc_recv code that called this function
 *   as part of close processing.
 *
 * At a minimum one references should still be held.
 */
static void svc_rdma_detach(struct svc_xprt *xprt)
{
	struct svcxprt_rdma *rdma =
		container_of(xprt, struct svcxprt_rdma, sc_xprt);
	dprintk("svc: svc_rdma_detach(%p)\n", xprt);

	/* Disconnect and flush posted WQE */
	rdma_disconnect(rdma->sc_cm_id);
}

static void __svc_rdma_free(struct work_struct *work)
{
	struct svcxprt_rdma *rdma =
		container_of(work, struct svcxprt_rdma, sc_work);
	struct svc_xprt *xprt = &rdma->sc_xprt;

	dprintk("svcrdma: %s(%p)\n", __func__, rdma);

	if (rdma->sc_qp && !IS_ERR(rdma->sc_qp))
		ib_drain_qp(rdma->sc_qp);

	/* We should only be called from kref_put */
	if (kref_read(&xprt->xpt_ref) != 0)
		pr_err("svcrdma: sc_xprt still in use? (%d)\n",
		       kref_read(&xprt->xpt_ref));

	while (!list_empty(&rdma->sc_read_complete_q)) {
		struct svc_rdma_op_ctxt *ctxt;
		ctxt = list_first_entry(&rdma->sc_read_complete_q,
					struct svc_rdma_op_ctxt, list);
		list_del(&ctxt->list);
		svc_rdma_put_context(ctxt, 1);
	}
	while (!list_empty(&rdma->sc_rq_dto_q)) {
		struct svc_rdma_op_ctxt *ctxt;
		ctxt = list_first_entry(&rdma->sc_rq_dto_q,
					struct svc_rdma_op_ctxt, list);
		list_del(&ctxt->list);
		svc_rdma_put_context(ctxt, 1);
	}

	/* Warn if we leaked a resource or under-referenced */
	if (rdma->sc_ctxt_used != 0)
		pr_err("svcrdma: ctxt still in use? (%d)\n",
		       rdma->sc_ctxt_used);

	/* Final put of backchannel client transport */
	if (xprt->xpt_bc_xprt) {
		xprt_put(xprt->xpt_bc_xprt);
		xprt->xpt_bc_xprt = NULL;
	}

	svc_rdma_destroy_rw_ctxts(rdma);
	svc_rdma_destroy_ctxts(rdma);

	/* Destroy the QP if present (not a listener) */
	if (rdma->sc_qp && !IS_ERR(rdma->sc_qp))
		ib_destroy_qp(rdma->sc_qp);

	if (rdma->sc_sq_cq && !IS_ERR(rdma->sc_sq_cq))
		ib_free_cq(rdma->sc_sq_cq);

	if (rdma->sc_rq_cq && !IS_ERR(rdma->sc_rq_cq))
		ib_free_cq(rdma->sc_rq_cq);

	if (rdma->sc_pd && !IS_ERR(rdma->sc_pd))
		ib_dealloc_pd(rdma->sc_pd);

	/* Destroy the CM ID */
	rdma_destroy_id(rdma->sc_cm_id);

	kfree(rdma);
}

static void svc_rdma_free(struct svc_xprt *xprt)
{
	struct svcxprt_rdma *rdma =
		container_of(xprt, struct svcxprt_rdma, sc_xprt);
	INIT_WORK(&rdma->sc_work, __svc_rdma_free);
	queue_work(svc_rdma_wq, &rdma->sc_work);
}

static int svc_rdma_has_wspace(struct svc_xprt *xprt)
{
	struct svcxprt_rdma *rdma =
		container_of(xprt, struct svcxprt_rdma, sc_xprt);

	/*
	 * If there are already waiters on the SQ,
	 * return false.
	 */
	if (waitqueue_active(&rdma->sc_send_wait))
		return 0;

	/* Otherwise return true. */
	return 1;
}

static int svc_rdma_secure_port(struct svc_rqst *rqstp)
{
	return 1;
}

static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt)
{
}

int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
{
	struct ib_send_wr *bad_wr, *n_wr;
	int wr_count;
	int i;
	int ret;

	if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags))
		return -ENOTCONN;

	wr_count = 1;
	for (n_wr = wr->next; n_wr; n_wr = n_wr->next)
		wr_count++;

	/* If the SQ is full, wait until an SQ entry is available */
	while (1) {
		if ((atomic_sub_return(wr_count, &xprt->sc_sq_avail) < 0)) {
			atomic_inc(&rdma_stat_sq_starve);

			/* Wait until SQ WR available if SQ still full */
			atomic_add(wr_count, &xprt->sc_sq_avail);
			wait_event(xprt->sc_send_wait,
				   atomic_read(&xprt->sc_sq_avail) > wr_count);
			if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags))
				return -ENOTCONN;
			continue;
		}
		/* Take a transport ref for each WR posted */
		for (i = 0; i < wr_count; i++)
			svc_xprt_get(&xprt->sc_xprt);

		/* Bump used SQ WR count and post */
		ret = ib_post_send(xprt->sc_qp, wr, &bad_wr);
		if (ret) {
			set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
			for (i = 0; i < wr_count; i ++)
				svc_xprt_put(&xprt->sc_xprt);
			dprintk("svcrdma: failed to post SQ WR rc=%d\n", ret);
			dprintk("    sc_sq_avail=%d, sc_sq_depth=%d\n",
				atomic_read(&xprt->sc_sq_avail),
				xprt->sc_sq_depth);
			wake_up(&xprt->sc_send_wait);
		}
		break;
	}
	return ret;
}