summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/core/rw.c
blob: 4fad732f9b3cc40041c7ba25139756ca425e7219 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2016 HGST, a Western Digital Company.
 */
#include <linux/moduleparam.h>
#include <linux/slab.h>
#include <linux/pci-p2pdma.h>
#include <rdma/mr_pool.h>
#include <rdma/rw.h>

enum {
	RDMA_RW_SINGLE_WR,
	RDMA_RW_MULTI_WR,
	RDMA_RW_MR,
	RDMA_RW_SIG_MR,
};

static bool rdma_rw_force_mr;
module_param_named(force_mr, rdma_rw_force_mr, bool, 0);
MODULE_PARM_DESC(force_mr, "Force usage of MRs for RDMA READ/WRITE operations");

/*
 * Report whether memory registration should be used. Memory registration must
 * be used for iWarp devices because of iWARP-specific limitations. Memory
 * registration is also enabled if registering memory might yield better
 * performance than using multiple SGE entries, see rdma_rw_io_needs_mr()
 */
static inline bool rdma_rw_can_use_mr(struct ib_device *dev, u8 port_num)
{
	if (rdma_protocol_iwarp(dev, port_num))
		return true;
	if (dev->attrs.max_sgl_rd)
		return true;
	if (unlikely(rdma_rw_force_mr))
		return true;
	return false;
}

/*
 * Check if the device will use memory registration for this RW operation.
 * For RDMA READs we must use MRs on iWarp and can optionally use them as an
 * optimization otherwise.  Additionally we have a debug option to force usage
 * of MRs to help testing this code path.
 */
static inline bool rdma_rw_io_needs_mr(struct ib_device *dev, u8 port_num,
		enum dma_data_direction dir, int dma_nents)
{
	if (dir == DMA_FROM_DEVICE) {
		if (rdma_protocol_iwarp(dev, port_num))
			return true;
		if (dev->attrs.max_sgl_rd && dma_nents > dev->attrs.max_sgl_rd)
			return true;
	}
	if (unlikely(rdma_rw_force_mr))
		return true;
	return false;
}

static inline u32 rdma_rw_fr_page_list_len(struct ib_device *dev,
					   bool pi_support)
{
	u32 max_pages;

	if (pi_support)
		max_pages = dev->attrs.max_pi_fast_reg_page_list_len;
	else
		max_pages = dev->attrs.max_fast_reg_page_list_len;

	/* arbitrary limit to avoid allocating gigantic resources */
	return min_t(u32, max_pages, 256);
}

static inline int rdma_rw_inv_key(struct rdma_rw_reg_ctx *reg)
{
	int count = 0;

	if (reg->mr->need_inval) {
		reg->inv_wr.opcode = IB_WR_LOCAL_INV;
		reg->inv_wr.ex.invalidate_rkey = reg->mr->lkey;
		reg->inv_wr.next = &reg->reg_wr.wr;
		count++;
	} else {
		reg->inv_wr.next = NULL;
	}

	return count;
}

/* Caller must have zero-initialized *reg. */
static int rdma_rw_init_one_mr(struct ib_qp *qp, u8 port_num,
		struct rdma_rw_reg_ctx *reg, struct scatterlist *sg,
		u32 sg_cnt, u32 offset)
{
	u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device,
						    qp->integrity_en);
	u32 nents = min(sg_cnt, pages_per_mr);
	int count = 0, ret;

	reg->mr = ib_mr_pool_get(qp, &qp->rdma_mrs);
	if (!reg->mr)
		return -EAGAIN;

	count += rdma_rw_inv_key(reg);

	ret = ib_map_mr_sg(reg->mr, sg, nents, &offset, PAGE_SIZE);
	if (ret < 0 || ret < nents) {
		ib_mr_pool_put(qp, &qp->rdma_mrs, reg->mr);
		return -EINVAL;
	}

	reg->reg_wr.wr.opcode = IB_WR_REG_MR;
	reg->reg_wr.mr = reg->mr;
	reg->reg_wr.access = IB_ACCESS_LOCAL_WRITE;
	if (rdma_protocol_iwarp(qp->device, port_num))
		reg->reg_wr.access |= IB_ACCESS_REMOTE_WRITE;
	count++;

	reg->sge.addr = reg->mr->iova;
	reg->sge.length = reg->mr->length;
	return count;
}

static int rdma_rw_init_mr_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
		u8 port_num, struct scatterlist *sg, u32 sg_cnt, u32 offset,
		u64 remote_addr, u32 rkey, enum dma_data_direction dir)
{
	struct rdma_rw_reg_ctx *prev = NULL;
	u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device,
						    qp->integrity_en);
	int i, j, ret = 0, count = 0;

	ctx->nr_ops = (sg_cnt + pages_per_mr - 1) / pages_per_mr;
	ctx->reg = kcalloc(ctx->nr_ops, sizeof(*ctx->reg), GFP_KERNEL);
	if (!ctx->reg) {
		ret = -ENOMEM;
		goto out;
	}

	for (i = 0; i < ctx->nr_ops; i++) {
		struct rdma_rw_reg_ctx *reg = &ctx->reg[i];
		u32 nents = min(sg_cnt, pages_per_mr);

		ret = rdma_rw_init_one_mr(qp, port_num, reg, sg, sg_cnt,
				offset);
		if (ret < 0)
			goto out_free;
		count += ret;

		if (prev) {
			if (reg->mr->need_inval)
				prev->wr.wr.next = &reg->inv_wr;
			else
				prev->wr.wr.next = &reg->reg_wr.wr;
		}

		reg->reg_wr.wr.next = &reg->wr.wr;

		reg->wr.wr.sg_list = &reg->sge;
		reg->wr.wr.num_sge = 1;
		reg->wr.remote_addr = remote_addr;
		reg->wr.rkey = rkey;
		if (dir == DMA_TO_DEVICE) {
			reg->wr.wr.opcode = IB_WR_RDMA_WRITE;
		} else if (!rdma_cap_read_inv(qp->device, port_num)) {
			reg->wr.wr.opcode = IB_WR_RDMA_READ;
		} else {
			reg->wr.wr.opcode = IB_WR_RDMA_READ_WITH_INV;
			reg->wr.wr.ex.invalidate_rkey = reg->mr->lkey;
		}
		count++;

		remote_addr += reg->sge.length;
		sg_cnt -= nents;
		for (j = 0; j < nents; j++)
			sg = sg_next(sg);
		prev = reg;
		offset = 0;
	}

	if (prev)
		prev->wr.wr.next = NULL;

	ctx->type = RDMA_RW_MR;
	return count;

out_free:
	while (--i >= 0)
		ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->reg[i].mr);
	kfree(ctx->reg);
out:
	return ret;
}

static int rdma_rw_init_map_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
		struct scatterlist *sg, u32 sg_cnt, u32 offset,
		u64 remote_addr, u32 rkey, enum dma_data_direction dir)
{
	u32 max_sge = dir == DMA_TO_DEVICE ? qp->max_write_sge :
		      qp->max_read_sge;
	struct ib_sge *sge;
	u32 total_len = 0, i, j;

	ctx->nr_ops = DIV_ROUND_UP(sg_cnt, max_sge);

	ctx->map.sges = sge = kcalloc(sg_cnt, sizeof(*sge), GFP_KERNEL);
	if (!ctx->map.sges)
		goto out;

	ctx->map.wrs = kcalloc(ctx->nr_ops, sizeof(*ctx->map.wrs), GFP_KERNEL);
	if (!ctx->map.wrs)
		goto out_free_sges;

	for (i = 0; i < ctx->nr_ops; i++) {
		struct ib_rdma_wr *rdma_wr = &ctx->map.wrs[i];
		u32 nr_sge = min(sg_cnt, max_sge);

		if (dir == DMA_TO_DEVICE)
			rdma_wr->wr.opcode = IB_WR_RDMA_WRITE;
		else
			rdma_wr->wr.opcode = IB_WR_RDMA_READ;
		rdma_wr->remote_addr = remote_addr + total_len;
		rdma_wr->rkey = rkey;
		rdma_wr->wr.num_sge = nr_sge;
		rdma_wr->wr.sg_list = sge;

		for (j = 0; j < nr_sge; j++, sg = sg_next(sg)) {
			sge->addr = sg_dma_address(sg) + offset;
			sge->length = sg_dma_len(sg) - offset;
			sge->lkey = qp->pd->local_dma_lkey;

			total_len += sge->length;
			sge++;
			sg_cnt--;
			offset = 0;
		}

		rdma_wr->wr.next = i + 1 < ctx->nr_ops ?
			&ctx->map.wrs[i + 1].wr : NULL;
	}

	ctx->type = RDMA_RW_MULTI_WR;
	return ctx->nr_ops;

out_free_sges:
	kfree(ctx->map.sges);
out:
	return -ENOMEM;
}

static int rdma_rw_init_single_wr(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
		struct scatterlist *sg, u32 offset, u64 remote_addr, u32 rkey,
		enum dma_data_direction dir)
{
	struct ib_rdma_wr *rdma_wr = &ctx->single.wr;

	ctx->nr_ops = 1;

	ctx->single.sge.lkey = qp->pd->local_dma_lkey;
	ctx->single.sge.addr = sg_dma_address(sg) + offset;
	ctx->single.sge.length = sg_dma_len(sg) - offset;

	memset(rdma_wr, 0, sizeof(*rdma_wr));
	if (dir == DMA_TO_DEVICE)
		rdma_wr->wr.opcode = IB_WR_RDMA_WRITE;
	else
		rdma_wr->wr.opcode = IB_WR_RDMA_READ;
	rdma_wr->wr.sg_list = &ctx->single.sge;
	rdma_wr->wr.num_sge = 1;
	rdma_wr->remote_addr = remote_addr;
	rdma_wr->rkey = rkey;

	ctx->type = RDMA_RW_SINGLE_WR;
	return 1;
}

/**
 * rdma_rw_ctx_init - initialize a RDMA READ/WRITE context
 * @ctx:	context to initialize
 * @qp:		queue pair to operate on
 * @port_num:	port num to which the connection is bound
 * @sg:		scatterlist to READ/WRITE from/to
 * @sg_cnt:	number of entries in @sg
 * @sg_offset:	current byte offset into @sg
 * @remote_addr:remote address to read/write (relative to @rkey)
 * @rkey:	remote key to operate on
 * @dir:	%DMA_TO_DEVICE for RDMA WRITE, %DMA_FROM_DEVICE for RDMA READ
 *
 * Returns the number of WQEs that will be needed on the workqueue if
 * successful, or a negative error code.
 */
int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
		struct scatterlist *sg, u32 sg_cnt, u32 sg_offset,
		u64 remote_addr, u32 rkey, enum dma_data_direction dir)
{
	struct ib_device *dev = qp->pd->device;
	int ret;

	if (is_pci_p2pdma_page(sg_page(sg)))
		ret = pci_p2pdma_map_sg(dev->dma_device, sg, sg_cnt, dir);
	else
		ret = ib_dma_map_sg(dev, sg, sg_cnt, dir);

	if (!ret)
		return -ENOMEM;
	sg_cnt = ret;

	/*
	 * Skip to the S/G entry that sg_offset falls into:
	 */
	for (;;) {
		u32 len = sg_dma_len(sg);

		if (sg_offset < len)
			break;

		sg = sg_next(sg);
		sg_offset -= len;
		sg_cnt--;
	}

	ret = -EIO;
	if (WARN_ON_ONCE(sg_cnt == 0))
		goto out_unmap_sg;

	if (rdma_rw_io_needs_mr(qp->device, port_num, dir, sg_cnt)) {
		ret = rdma_rw_init_mr_wrs(ctx, qp, port_num, sg, sg_cnt,
				sg_offset, remote_addr, rkey, dir);
	} else if (sg_cnt > 1) {
		ret = rdma_rw_init_map_wrs(ctx, qp, sg, sg_cnt, sg_offset,
				remote_addr, rkey, dir);
	} else {
		ret = rdma_rw_init_single_wr(ctx, qp, sg, sg_offset,
				remote_addr, rkey, dir);
	}

	if (ret < 0)
		goto out_unmap_sg;
	return ret;

out_unmap_sg:
	ib_dma_unmap_sg(dev, sg, sg_cnt, dir);
	return ret;
}
EXPORT_SYMBOL(rdma_rw_ctx_init);

/**
 * rdma_rw_ctx_signature_init - initialize a RW context with signature offload
 * @ctx:	context to initialize
 * @qp:		queue pair to operate on
 * @port_num:	port num to which the connection is bound
 * @sg:		scatterlist to READ/WRITE from/to
 * @sg_cnt:	number of entries in @sg
 * @prot_sg:	scatterlist to READ/WRITE protection information from/to
 * @prot_sg_cnt: number of entries in @prot_sg
 * @sig_attrs:	signature offloading algorithms
 * @remote_addr:remote address to read/write (relative to @rkey)
 * @rkey:	remote key to operate on
 * @dir:	%DMA_TO_DEVICE for RDMA WRITE, %DMA_FROM_DEVICE for RDMA READ
 *
 * Returns the number of WQEs that will be needed on the workqueue if
 * successful, or a negative error code.
 */
int rdma_rw_ctx_signature_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
		u8 port_num, struct scatterlist *sg, u32 sg_cnt,
		struct scatterlist *prot_sg, u32 prot_sg_cnt,
		struct ib_sig_attrs *sig_attrs,
		u64 remote_addr, u32 rkey, enum dma_data_direction dir)
{
	struct ib_device *dev = qp->pd->device;
	u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device,
						    qp->integrity_en);
	struct ib_rdma_wr *rdma_wr;
	int count = 0, ret;

	if (sg_cnt > pages_per_mr || prot_sg_cnt > pages_per_mr) {
		pr_err("SG count too large: sg_cnt=%d, prot_sg_cnt=%d, pages_per_mr=%d\n",
		       sg_cnt, prot_sg_cnt, pages_per_mr);
		return -EINVAL;
	}

	ret = ib_dma_map_sg(dev, sg, sg_cnt, dir);
	if (!ret)
		return -ENOMEM;
	sg_cnt = ret;

	if (prot_sg_cnt) {
		ret = ib_dma_map_sg(dev, prot_sg, prot_sg_cnt, dir);
		if (!ret) {
			ret = -ENOMEM;
			goto out_unmap_sg;
		}
		prot_sg_cnt = ret;
	}

	ctx->type = RDMA_RW_SIG_MR;
	ctx->nr_ops = 1;
	ctx->reg = kcalloc(1, sizeof(*ctx->reg), GFP_KERNEL);
	if (!ctx->reg) {
		ret = -ENOMEM;
		goto out_unmap_prot_sg;
	}

	ctx->reg->mr = ib_mr_pool_get(qp, &qp->sig_mrs);
	if (!ctx->reg->mr) {
		ret = -EAGAIN;
		goto out_free_ctx;
	}

	count += rdma_rw_inv_key(ctx->reg);

	memcpy(ctx->reg->mr->sig_attrs, sig_attrs, sizeof(struct ib_sig_attrs));

	ret = ib_map_mr_sg_pi(ctx->reg->mr, sg, sg_cnt, NULL, prot_sg,
			      prot_sg_cnt, NULL, SZ_4K);
	if (unlikely(ret)) {
		pr_err("failed to map PI sg (%d)\n", sg_cnt + prot_sg_cnt);
		goto out_destroy_sig_mr;
	}

	ctx->reg->reg_wr.wr.opcode = IB_WR_REG_MR_INTEGRITY;
	ctx->reg->reg_wr.wr.wr_cqe = NULL;
	ctx->reg->reg_wr.wr.num_sge = 0;
	ctx->reg->reg_wr.wr.send_flags = 0;
	ctx->reg->reg_wr.access = IB_ACCESS_LOCAL_WRITE;
	if (rdma_protocol_iwarp(qp->device, port_num))
		ctx->reg->reg_wr.access |= IB_ACCESS_REMOTE_WRITE;
	ctx->reg->reg_wr.mr = ctx->reg->mr;
	ctx->reg->reg_wr.key = ctx->reg->mr->lkey;
	count++;

	ctx->reg->sge.addr = ctx->reg->mr->iova;
	ctx->reg->sge.length = ctx->reg->mr->length;
	if (sig_attrs->wire.sig_type == IB_SIG_TYPE_NONE)
		ctx->reg->sge.length -= ctx->reg->mr->sig_attrs->meta_length;

	rdma_wr = &ctx->reg->wr;
	rdma_wr->wr.sg_list = &ctx->reg->sge;
	rdma_wr->wr.num_sge = 1;
	rdma_wr->remote_addr = remote_addr;
	rdma_wr->rkey = rkey;
	if (dir == DMA_TO_DEVICE)
		rdma_wr->wr.opcode = IB_WR_RDMA_WRITE;
	else
		rdma_wr->wr.opcode = IB_WR_RDMA_READ;
	ctx->reg->reg_wr.wr.next = &rdma_wr->wr;
	count++;

	return count;

out_destroy_sig_mr:
	ib_mr_pool_put(qp, &qp->sig_mrs, ctx->reg->mr);
out_free_ctx:
	kfree(ctx->reg);
out_unmap_prot_sg:
	if (prot_sg_cnt)
		ib_dma_unmap_sg(dev, prot_sg, prot_sg_cnt, dir);
out_unmap_sg:
	ib_dma_unmap_sg(dev, sg, sg_cnt, dir);
	return ret;
}
EXPORT_SYMBOL(rdma_rw_ctx_signature_init);

/*
 * Now that we are going to post the WRs we can update the lkey and need_inval
 * state on the MRs.  If we were doing this at init time, we would get double
 * or missing invalidations if a context was initialized but not actually
 * posted.
 */
static void rdma_rw_update_lkey(struct rdma_rw_reg_ctx *reg, bool need_inval)
{
	reg->mr->need_inval = need_inval;
	ib_update_fast_reg_key(reg->mr, ib_inc_rkey(reg->mr->lkey));
	reg->reg_wr.key = reg->mr->lkey;
	reg->sge.lkey = reg->mr->lkey;
}

/**
 * rdma_rw_ctx_wrs - return chain of WRs for a RDMA READ or WRITE operation
 * @ctx:	context to operate on
 * @qp:		queue pair to operate on
 * @port_num:	port num to which the connection is bound
 * @cqe:	completion queue entry for the last WR
 * @chain_wr:	WR to append to the posted chain
 *
 * Return the WR chain for the set of RDMA READ/WRITE operations described by
 * @ctx, as well as any memory registration operations needed.  If @chain_wr
 * is non-NULL the WR it points to will be appended to the chain of WRs posted.
 * If @chain_wr is not set @cqe must be set so that the caller gets a
 * completion notification.
 */
struct ib_send_wr *rdma_rw_ctx_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
		u8 port_num, struct ib_cqe *cqe, struct ib_send_wr *chain_wr)
{
	struct ib_send_wr *first_wr, *last_wr;
	int i;

	switch (ctx->type) {
	case RDMA_RW_SIG_MR:
	case RDMA_RW_MR:
		/* fallthrough */
		for (i = 0; i < ctx->nr_ops; i++) {
			rdma_rw_update_lkey(&ctx->reg[i],
				ctx->reg[i].wr.wr.opcode !=
					IB_WR_RDMA_READ_WITH_INV);
		}

		if (ctx->reg[0].inv_wr.next)
			first_wr = &ctx->reg[0].inv_wr;
		else
			first_wr = &ctx->reg[0].reg_wr.wr;
		last_wr = &ctx->reg[ctx->nr_ops - 1].wr.wr;
		break;
	case RDMA_RW_MULTI_WR:
		first_wr = &ctx->map.wrs[0].wr;
		last_wr = &ctx->map.wrs[ctx->nr_ops - 1].wr;
		break;
	case RDMA_RW_SINGLE_WR:
		first_wr = &ctx->single.wr.wr;
		last_wr = &ctx->single.wr.wr;
		break;
	default:
		BUG();
	}

	if (chain_wr) {
		last_wr->next = chain_wr;
	} else {
		last_wr->wr_cqe = cqe;
		last_wr->send_flags |= IB_SEND_SIGNALED;
	}

	return first_wr;
}
EXPORT_SYMBOL(rdma_rw_ctx_wrs);

/**
 * rdma_rw_ctx_post - post a RDMA READ or RDMA WRITE operation
 * @ctx:	context to operate on
 * @qp:		queue pair to operate on
 * @port_num:	port num to which the connection is bound
 * @cqe:	completion queue entry for the last WR
 * @chain_wr:	WR to append to the posted chain
 *
 * Post the set of RDMA READ/WRITE operations described by @ctx, as well as
 * any memory registration operations needed.  If @chain_wr is non-NULL the
 * WR it points to will be appended to the chain of WRs posted.  If @chain_wr
 * is not set @cqe must be set so that the caller gets a completion
 * notification.
 */
int rdma_rw_ctx_post(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
		struct ib_cqe *cqe, struct ib_send_wr *chain_wr)
{
	struct ib_send_wr *first_wr;

	first_wr = rdma_rw_ctx_wrs(ctx, qp, port_num, cqe, chain_wr);
	return ib_post_send(qp, first_wr, NULL);
}
EXPORT_SYMBOL(rdma_rw_ctx_post);

/**
 * rdma_rw_ctx_destroy - release all resources allocated by rdma_rw_ctx_init
 * @ctx:	context to release
 * @qp:		queue pair to operate on
 * @port_num:	port num to which the connection is bound
 * @sg:		scatterlist that was used for the READ/WRITE
 * @sg_cnt:	number of entries in @sg
 * @dir:	%DMA_TO_DEVICE for RDMA WRITE, %DMA_FROM_DEVICE for RDMA READ
 */
void rdma_rw_ctx_destroy(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
		struct scatterlist *sg, u32 sg_cnt, enum dma_data_direction dir)
{
	int i;

	switch (ctx->type) {
	case RDMA_RW_MR:
		for (i = 0; i < ctx->nr_ops; i++)
			ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->reg[i].mr);
		kfree(ctx->reg);
		break;
	case RDMA_RW_MULTI_WR:
		kfree(ctx->map.wrs);
		kfree(ctx->map.sges);
		break;
	case RDMA_RW_SINGLE_WR:
		break;
	default:
		BUG();
		break;
	}

	if (is_pci_p2pdma_page(sg_page(sg)))
		pci_p2pdma_unmap_sg(qp->pd->device->dma_device, sg,
				    sg_cnt, dir);
	else
		ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
}
EXPORT_SYMBOL(rdma_rw_ctx_destroy);

/**
 * rdma_rw_ctx_destroy_signature - release all resources allocated by
 *	rdma_rw_ctx_signature_init
 * @ctx:	context to release
 * @qp:		queue pair to operate on
 * @port_num:	port num to which the connection is bound
 * @sg:		scatterlist that was used for the READ/WRITE
 * @sg_cnt:	number of entries in @sg
 * @prot_sg:	scatterlist that was used for the READ/WRITE of the PI
 * @prot_sg_cnt: number of entries in @prot_sg
 * @dir:	%DMA_TO_DEVICE for RDMA WRITE, %DMA_FROM_DEVICE for RDMA READ
 */
void rdma_rw_ctx_destroy_signature(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
		u8 port_num, struct scatterlist *sg, u32 sg_cnt,
		struct scatterlist *prot_sg, u32 prot_sg_cnt,
		enum dma_data_direction dir)
{
	if (WARN_ON_ONCE(ctx->type != RDMA_RW_SIG_MR))
		return;

	ib_mr_pool_put(qp, &qp->sig_mrs, ctx->reg->mr);
	kfree(ctx->reg);

	ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
	if (prot_sg_cnt)
		ib_dma_unmap_sg(qp->pd->device, prot_sg, prot_sg_cnt, dir);
}
EXPORT_SYMBOL(rdma_rw_ctx_destroy_signature);

/**
 * rdma_rw_mr_factor - return number of MRs required for a payload
 * @device:	device handling the connection
 * @port_num:	port num to which the connection is bound
 * @maxpages:	maximum payload pages per rdma_rw_ctx
 *
 * Returns the number of MRs the device requires to move @maxpayload
 * bytes. The returned value is used during transport creation to
 * compute max_rdma_ctxts and the size of the transport's Send and
 * Send Completion Queues.
 */
unsigned int rdma_rw_mr_factor(struct ib_device *device, u8 port_num,
			       unsigned int maxpages)
{
	unsigned int mr_pages;

	if (rdma_rw_can_use_mr(device, port_num))
		mr_pages = rdma_rw_fr_page_list_len(device, false);
	else
		mr_pages = device->attrs.max_sge_rd;
	return DIV_ROUND_UP(maxpages, mr_pages);
}
EXPORT_SYMBOL(rdma_rw_mr_factor);

void rdma_rw_init_qp(struct ib_device *dev, struct ib_qp_init_attr *attr)
{
	u32 factor;

	WARN_ON_ONCE(attr->port_num == 0);

	/*
	 * Each context needs at least one RDMA READ or WRITE WR.
	 *
	 * For some hardware we might need more, eventually we should ask the
	 * HCA driver for a multiplier here.
	 */
	factor = 1;

	/*
	 * If the devices needs MRs to perform RDMA READ or WRITE operations,
	 * we'll need two additional MRs for the registrations and the
	 * invalidation.
	 */
	if (attr->create_flags & IB_QP_CREATE_INTEGRITY_EN ||
	    rdma_rw_can_use_mr(dev, attr->port_num))
		factor += 2;	/* inv + reg */

	attr->cap.max_send_wr += factor * attr->cap.max_rdma_ctxs;

	/*
	 * But maybe we were just too high in the sky and the device doesn't
	 * even support all we need, and we'll have to live with what we get..
	 */
	attr->cap.max_send_wr =
		min_t(u32, attr->cap.max_send_wr, dev->attrs.max_qp_wr);
}

int rdma_rw_init_mrs(struct ib_qp *qp, struct ib_qp_init_attr *attr)
{
	struct ib_device *dev = qp->pd->device;
	u32 nr_mrs = 0, nr_sig_mrs = 0, max_num_sg = 0;
	int ret = 0;

	if (attr->create_flags & IB_QP_CREATE_INTEGRITY_EN) {
		nr_sig_mrs = attr->cap.max_rdma_ctxs;
		nr_mrs = attr->cap.max_rdma_ctxs;
		max_num_sg = rdma_rw_fr_page_list_len(dev, true);
	} else if (rdma_rw_can_use_mr(dev, attr->port_num)) {
		nr_mrs = attr->cap.max_rdma_ctxs;
		max_num_sg = rdma_rw_fr_page_list_len(dev, false);
	}

	if (nr_mrs) {
		ret = ib_mr_pool_init(qp, &qp->rdma_mrs, nr_mrs,
				IB_MR_TYPE_MEM_REG,
				max_num_sg, 0);
		if (ret) {
			pr_err("%s: failed to allocated %d MRs\n",
				__func__, nr_mrs);
			return ret;
		}
	}

	if (nr_sig_mrs) {
		ret = ib_mr_pool_init(qp, &qp->sig_mrs, nr_sig_mrs,
				IB_MR_TYPE_INTEGRITY, max_num_sg, max_num_sg);
		if (ret) {
			pr_err("%s: failed to allocated %d SIG MRs\n",
				__func__, nr_sig_mrs);
			goto out_free_rdma_mrs;
		}
	}

	return 0;

out_free_rdma_mrs:
	ib_mr_pool_destroy(qp, &qp->rdma_mrs);
	return ret;
}

void rdma_rw_cleanup_mrs(struct ib_qp *qp)
{
	ib_mr_pool_destroy(qp, &qp->sig_mrs);
	ib_mr_pool_destroy(qp, &qp->rdma_mrs);
}