summaryrefslogtreecommitdiff
path: root/net/sunrpc/xprtrdma/svc_rdma_sendto.c
blob: 7e024a51617e034811a950bb245d1f615e9809a9 (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
/*
 * Copyright (c) 2005-2006 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/debug.h>
#include <linux/sunrpc/rpc_rdma.h>
#include <linux/spinlock.h>
#include <asm/unaligned.h>
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
#include <linux/sunrpc/svc_rdma.h>

#define RPCDBG_FACILITY	RPCDBG_SVCXPRT

/* Encode an XDR as an array of IB SGE
 *
 * Assumptions:
 * - head[0] is physically contiguous.
 * - tail[0] is physically contiguous.
 * - pages[] is not physically or virtually contiguous and consists of
 *   PAGE_SIZE elements.
 *
 * Output:
 * SGE[0]              reserved for RCPRDMA header
 * SGE[1]              data from xdr->head[]
 * SGE[2..sge_count-2] data from xdr->pages[]
 * SGE[sge_count-1]    data from xdr->tail.
 *
 * The max SGE we need is the length of the XDR / pagesize + one for
 * head + one for tail + one for RPCRDMA header. Since RPCSVC_MAXPAGES
 * reserves a page for both the request and the reply header, and this
 * array is only concerned with the reply we are assured that we have
 * on extra page for the RPCRMDA header.
 */
static int fast_reg_xdr(struct svcxprt_rdma *xprt,
			struct xdr_buf *xdr,
			struct svc_rdma_req_map *vec)
{
	int sge_no;
	u32 sge_bytes;
	u32 page_bytes;
	u32 page_off;
	int page_no = 0;
	u8 *frva;
	struct svc_rdma_fastreg_mr *frmr;

	frmr = svc_rdma_get_frmr(xprt);
	if (IS_ERR(frmr))
		return -ENOMEM;
	vec->frmr = frmr;

	/* Skip the RPCRDMA header */
	sge_no = 1;

	/* Map the head. */
	frva = (void *)((unsigned long)(xdr->head[0].iov_base) & PAGE_MASK);
	vec->sge[sge_no].iov_base = xdr->head[0].iov_base;
	vec->sge[sge_no].iov_len = xdr->head[0].iov_len;
	vec->count = 2;
	sge_no++;

	/* Map the XDR head */
	frmr->kva = frva;
	frmr->direction = DMA_TO_DEVICE;
	frmr->access_flags = 0;
	frmr->map_len = PAGE_SIZE;
	frmr->page_list_len = 1;
	page_off = (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK;
	frmr->page_list->page_list[page_no] =
		ib_dma_map_page(xprt->sc_cm_id->device,
				virt_to_page(xdr->head[0].iov_base),
				page_off,
				PAGE_SIZE - page_off,
				DMA_TO_DEVICE);
	if (ib_dma_mapping_error(xprt->sc_cm_id->device,
				 frmr->page_list->page_list[page_no]))
		goto fatal_err;
	atomic_inc(&xprt->sc_dma_used);

	/* Map the XDR page list */
	page_off = xdr->page_base;
	page_bytes = xdr->page_len + page_off;
	if (!page_bytes)
		goto encode_tail;

	/* Map the pages */
	vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off;
	vec->sge[sge_no].iov_len = page_bytes;
	sge_no++;
	while (page_bytes) {
		struct page *page;

		page = xdr->pages[page_no++];
		sge_bytes = min_t(u32, page_bytes, (PAGE_SIZE - page_off));
		page_bytes -= sge_bytes;

		frmr->page_list->page_list[page_no] =
			ib_dma_map_page(xprt->sc_cm_id->device,
					page, page_off,
					sge_bytes, DMA_TO_DEVICE);
		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
					 frmr->page_list->page_list[page_no]))
			goto fatal_err;

		atomic_inc(&xprt->sc_dma_used);
		page_off = 0; /* reset for next time through loop */
		frmr->map_len += PAGE_SIZE;
		frmr->page_list_len++;
	}
	vec->count++;

 encode_tail:
	/* Map tail */
	if (0 == xdr->tail[0].iov_len)
		goto done;

	vec->count++;
	vec->sge[sge_no].iov_len = xdr->tail[0].iov_len;

	if (((unsigned long)xdr->tail[0].iov_base & PAGE_MASK) ==
	    ((unsigned long)xdr->head[0].iov_base & PAGE_MASK)) {
		/*
		 * If head and tail use the same page, we don't need
		 * to map it again.
		 */
		vec->sge[sge_no].iov_base = xdr->tail[0].iov_base;
	} else {
		void *va;

		/* Map another page for the tail */
		page_off = (unsigned long)xdr->tail[0].iov_base & ~PAGE_MASK;
		va = (void *)((unsigned long)xdr->tail[0].iov_base & PAGE_MASK);
		vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off;

		frmr->page_list->page_list[page_no] =
		    ib_dma_map_page(xprt->sc_cm_id->device, virt_to_page(va),
				    page_off,
				    PAGE_SIZE,
				    DMA_TO_DEVICE);
		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
					 frmr->page_list->page_list[page_no]))
			goto fatal_err;
		atomic_inc(&xprt->sc_dma_used);
		frmr->map_len += PAGE_SIZE;
		frmr->page_list_len++;
	}

 done:
	if (svc_rdma_fastreg(xprt, frmr))
		goto fatal_err;

	return 0;

 fatal_err:
	printk("svcrdma: Error fast registering memory for xprt %p\n", xprt);
	vec->frmr = NULL;
	svc_rdma_put_frmr(xprt, frmr);
	return -EIO;
}

static int map_xdr(struct svcxprt_rdma *xprt,
		   struct xdr_buf *xdr,
		   struct svc_rdma_req_map *vec)
{
	int sge_no;
	u32 sge_bytes;
	u32 page_bytes;
	u32 page_off;
	int page_no;

	BUG_ON(xdr->len !=
	       (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len));

	if (xprt->sc_frmr_pg_list_len)
		return fast_reg_xdr(xprt, xdr, vec);

	/* Skip the first sge, this is for the RPCRDMA header */
	sge_no = 1;

	/* Head SGE */
	vec->sge[sge_no].iov_base = xdr->head[0].iov_base;
	vec->sge[sge_no].iov_len = xdr->head[0].iov_len;
	sge_no++;

	/* pages SGE */
	page_no = 0;
	page_bytes = xdr->page_len;
	page_off = xdr->page_base;
	while (page_bytes) {
		vec->sge[sge_no].iov_base =
			page_address(xdr->pages[page_no]) + page_off;
		sge_bytes = min_t(u32, page_bytes, (PAGE_SIZE - page_off));
		page_bytes -= sge_bytes;
		vec->sge[sge_no].iov_len = sge_bytes;

		sge_no++;
		page_no++;
		page_off = 0; /* reset for next time through loop */
	}

	/* Tail SGE */
	if (xdr->tail[0].iov_len) {
		vec->sge[sge_no].iov_base = xdr->tail[0].iov_base;
		vec->sge[sge_no].iov_len = xdr->tail[0].iov_len;
		sge_no++;
	}

	dprintk("svcrdma: map_xdr: sge_no %d page_no %d "
		"page_base %u page_len %u head_len %zu tail_len %zu\n",
		sge_no, page_no, xdr->page_base, xdr->page_len,
		xdr->head[0].iov_len, xdr->tail[0].iov_len);

	vec->count = sge_no;
	return 0;
}

static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt,
			      struct xdr_buf *xdr,
			      u32 xdr_off, size_t len, int dir)
{
	struct page *page;
	dma_addr_t dma_addr;
	if (xdr_off < xdr->head[0].iov_len) {
		/* This offset is in the head */
		xdr_off += (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK;
		page = virt_to_page(xdr->head[0].iov_base);
	} else {
		xdr_off -= xdr->head[0].iov_len;
		if (xdr_off < xdr->page_len) {
			/* This offset is in the page list */
			xdr_off += xdr->page_base;
			page = xdr->pages[xdr_off >> PAGE_SHIFT];
			xdr_off &= ~PAGE_MASK;
		} else {
			/* This offset is in the tail */
			xdr_off -= xdr->page_len;
			xdr_off += (unsigned long)
				xdr->tail[0].iov_base & ~PAGE_MASK;
			page = virt_to_page(xdr->tail[0].iov_base);
		}
	}
	dma_addr = ib_dma_map_page(xprt->sc_cm_id->device, page, xdr_off,
				   min_t(size_t, PAGE_SIZE, len), dir);
	return dma_addr;
}

/* Assumptions:
 * - We are using FRMR
 *     - or -
 * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE
 */
static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
		      u32 rmr, u64 to,
		      u32 xdr_off, int write_len,
		      struct svc_rdma_req_map *vec)
{
	struct ib_send_wr write_wr;
	struct ib_sge *sge;
	int xdr_sge_no;
	int sge_no;
	int sge_bytes;
	int sge_off;
	int bc;
	struct svc_rdma_op_ctxt *ctxt;

	BUG_ON(vec->count > RPCSVC_MAXPAGES);
	dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, "
		"write_len=%d, vec->sge=%p, vec->count=%lu\n",
		rmr, (unsigned long long)to, xdr_off,
		write_len, vec->sge, vec->count);

	ctxt = svc_rdma_get_context(xprt);
	ctxt->direction = DMA_TO_DEVICE;
	sge = ctxt->sge;

	/* Find the SGE associated with xdr_off */
	for (bc = xdr_off, xdr_sge_no = 1; bc && xdr_sge_no < vec->count;
	     xdr_sge_no++) {
		if (vec->sge[xdr_sge_no].iov_len > bc)
			break;
		bc -= vec->sge[xdr_sge_no].iov_len;
	}

	sge_off = bc;
	bc = write_len;
	sge_no = 0;

	/* Copy the remaining SGE */
	while (bc != 0) {
		sge_bytes = min_t(size_t,
			  bc, vec->sge[xdr_sge_no].iov_len-sge_off);
		sge[sge_no].length = sge_bytes;
		if (!vec->frmr) {
			sge[sge_no].addr =
				dma_map_xdr(xprt, &rqstp->rq_res, xdr_off,
					    sge_bytes, DMA_TO_DEVICE);
			xdr_off += sge_bytes;
			if (ib_dma_mapping_error(xprt->sc_cm_id->device,
						 sge[sge_no].addr))
				goto err;
			atomic_inc(&xprt->sc_dma_used);
			sge[sge_no].lkey = xprt->sc_dma_lkey;
		} else {
			sge[sge_no].addr = (unsigned long)
				vec->sge[xdr_sge_no].iov_base + sge_off;
			sge[sge_no].lkey = vec->frmr->mr->lkey;
		}
		ctxt->count++;
		ctxt->frmr = vec->frmr;
		sge_off = 0;
		sge_no++;
		xdr_sge_no++;
		BUG_ON(xdr_sge_no > vec->count);
		bc -= sge_bytes;
	}

	/* Prepare WRITE WR */
	memset(&write_wr, 0, sizeof write_wr);
	ctxt->wr_op = IB_WR_RDMA_WRITE;
	write_wr.wr_id = (unsigned long)ctxt;
	write_wr.sg_list = &sge[0];
	write_wr.num_sge = sge_no;
	write_wr.opcode = IB_WR_RDMA_WRITE;
	write_wr.send_flags = IB_SEND_SIGNALED;
	write_wr.wr.rdma.rkey = rmr;
	write_wr.wr.rdma.remote_addr = to;

	/* Post It */
	atomic_inc(&rdma_stat_write);
	if (svc_rdma_send(xprt, &write_wr))
		goto err;
	return 0;
 err:
	svc_rdma_unmap_dma(ctxt);
	svc_rdma_put_frmr(xprt, vec->frmr);
	svc_rdma_put_context(ctxt, 0);
	/* Fatal error, close transport */
	return -EIO;
}

static int send_write_chunks(struct svcxprt_rdma *xprt,
			     struct rpcrdma_msg *rdma_argp,
			     struct rpcrdma_msg *rdma_resp,
			     struct svc_rqst *rqstp,
			     struct svc_rdma_req_map *vec)
{
	u32 xfer_len = rqstp->rq_res.page_len + rqstp->rq_res.tail[0].iov_len;
	int write_len;
	int max_write;
	u32 xdr_off;
	int chunk_off;
	int chunk_no;
	struct rpcrdma_write_array *arg_ary;
	struct rpcrdma_write_array *res_ary;
	int ret;

	arg_ary = svc_rdma_get_write_array(rdma_argp);
	if (!arg_ary)
		return 0;
	res_ary = (struct rpcrdma_write_array *)
		&rdma_resp->rm_body.rm_chunks[1];

	if (vec->frmr)
		max_write = vec->frmr->map_len;
	else
		max_write = xprt->sc_max_sge * PAGE_SIZE;

	/* Write chunks start at the pagelist */
	for (xdr_off = rqstp->rq_res.head[0].iov_len, chunk_no = 0;
	     xfer_len && chunk_no < arg_ary->wc_nchunks;
	     chunk_no++) {
		struct rpcrdma_segment *arg_ch;
		u64 rs_offset;

		arg_ch = &arg_ary->wc_array[chunk_no].wc_target;
		write_len = min(xfer_len, ntohl(arg_ch->rs_length));

		/* Prepare the response chunk given the length actually
		 * written */
		xdr_decode_hyper((__be32 *)&arg_ch->rs_offset, &rs_offset);
		svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
						arg_ch->rs_handle,
						arg_ch->rs_offset,
						write_len);
		chunk_off = 0;
		while (write_len) {
			int this_write;
			this_write = min(write_len, max_write);
			ret = send_write(xprt, rqstp,
					 ntohl(arg_ch->rs_handle),
					 rs_offset + chunk_off,
					 xdr_off,
					 this_write,
					 vec);
			if (ret) {
				dprintk("svcrdma: RDMA_WRITE failed, ret=%d\n",
					ret);
				return -EIO;
			}
			chunk_off += this_write;
			xdr_off += this_write;
			xfer_len -= this_write;
			write_len -= this_write;
		}
	}
	/* Update the req with the number of chunks actually used */
	svc_rdma_xdr_encode_write_list(rdma_resp, chunk_no);

	return rqstp->rq_res.page_len + rqstp->rq_res.tail[0].iov_len;
}

static int send_reply_chunks(struct svcxprt_rdma *xprt,
			     struct rpcrdma_msg *rdma_argp,
			     struct rpcrdma_msg *rdma_resp,
			     struct svc_rqst *rqstp,
			     struct svc_rdma_req_map *vec)
{
	u32 xfer_len = rqstp->rq_res.len;
	int write_len;
	int max_write;
	u32 xdr_off;
	int chunk_no;
	int chunk_off;
	int nchunks;
	struct rpcrdma_segment *ch;
	struct rpcrdma_write_array *arg_ary;
	struct rpcrdma_write_array *res_ary;
	int ret;

	arg_ary = svc_rdma_get_reply_array(rdma_argp);
	if (!arg_ary)
		return 0;
	/* XXX: need to fix when reply lists occur with read-list and or
	 * write-list */
	res_ary = (struct rpcrdma_write_array *)
		&rdma_resp->rm_body.rm_chunks[2];

	if (vec->frmr)
		max_write = vec->frmr->map_len;
	else
		max_write = xprt->sc_max_sge * PAGE_SIZE;

	/* xdr offset starts at RPC message */
	nchunks = ntohl(arg_ary->wc_nchunks);
	for (xdr_off = 0, chunk_no = 0;
	     xfer_len && chunk_no < nchunks;
	     chunk_no++) {
		u64 rs_offset;
		ch = &arg_ary->wc_array[chunk_no].wc_target;
		write_len = min(xfer_len, htonl(ch->rs_length));

		/* Prepare the reply chunk given the length actually
		 * written */
		xdr_decode_hyper((__be32 *)&ch->rs_offset, &rs_offset);
		svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
						ch->rs_handle, ch->rs_offset,
						write_len);
		chunk_off = 0;
		while (write_len) {
			int this_write;

			this_write = min(write_len, max_write);
			ret = send_write(xprt, rqstp,
					 ntohl(ch->rs_handle),
					 rs_offset + chunk_off,
					 xdr_off,
					 this_write,
					 vec);
			if (ret) {
				dprintk("svcrdma: RDMA_WRITE failed, ret=%d\n",
					ret);
				return -EIO;
			}
			chunk_off += this_write;
			xdr_off += this_write;
			xfer_len -= this_write;
			write_len -= this_write;
		}
	}
	/* Update the req with the number of chunks actually used */
	svc_rdma_xdr_encode_reply_array(res_ary, chunk_no);

	return rqstp->rq_res.len;
}

/* This function prepares the portion of the RPCRDMA message to be
 * sent in the RDMA_SEND. This function is called after data sent via
 * RDMA has already been transmitted. There are three cases:
 * - The RPCRDMA header, RPC header, and payload are all sent in a
 *   single RDMA_SEND. This is the "inline" case.
 * - The RPCRDMA header and some portion of the RPC header and data
 *   are sent via this RDMA_SEND and another portion of the data is
 *   sent via RDMA.
 * - The RPCRDMA header [NOMSG] is sent in this RDMA_SEND and the RPC
 *   header and data are all transmitted via RDMA.
 * In all three cases, this function prepares the RPCRDMA header in
 * sge[0], the 'type' parameter indicates the type to place in the
 * RPCRDMA header, and the 'byte_count' field indicates how much of
 * the XDR to include in this RDMA_SEND. NB: The offset of the payload
 * to send is zero in the XDR.
 */
static int send_reply(struct svcxprt_rdma *rdma,
		      struct svc_rqst *rqstp,
		      struct page *page,
		      struct rpcrdma_msg *rdma_resp,
		      struct svc_rdma_op_ctxt *ctxt,
		      struct svc_rdma_req_map *vec,
		      int byte_count)
{
	struct ib_send_wr send_wr;
	struct ib_send_wr inv_wr;
	int sge_no;
	int sge_bytes;
	int page_no;
	int pages;
	int ret;

	/* Post a recv buffer to handle another request. */
	ret = svc_rdma_post_recv(rdma);
	if (ret) {
		printk(KERN_INFO
		       "svcrdma: could not post a receive buffer, err=%d."
		       "Closing transport %p.\n", ret, rdma);
		set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
		svc_rdma_put_frmr(rdma, vec->frmr);
		svc_rdma_put_context(ctxt, 0);
		return -ENOTCONN;
	}

	/* Prepare the context */
	ctxt->pages[0] = page;
	ctxt->count = 1;
	ctxt->frmr = vec->frmr;
	if (vec->frmr)
		set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
	else
		clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);

	/* Prepare the SGE for the RPCRDMA Header */
	ctxt->sge[0].lkey = rdma->sc_dma_lkey;
	ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp);
	ctxt->sge[0].addr =
	    ib_dma_map_page(rdma->sc_cm_id->device, page, 0,
			    ctxt->sge[0].length, DMA_TO_DEVICE);
	if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr))
		goto err;
	atomic_inc(&rdma->sc_dma_used);

	ctxt->direction = DMA_TO_DEVICE;

	/* Map the payload indicated by 'byte_count' */
	for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) {
		int xdr_off = 0;
		sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
		byte_count -= sge_bytes;
		if (!vec->frmr) {
			ctxt->sge[sge_no].addr =
				dma_map_xdr(rdma, &rqstp->rq_res, xdr_off,
					    sge_bytes, DMA_TO_DEVICE);
			xdr_off += sge_bytes;
			if (ib_dma_mapping_error(rdma->sc_cm_id->device,
						 ctxt->sge[sge_no].addr))
				goto err;
			atomic_inc(&rdma->sc_dma_used);
			ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey;
		} else {
			ctxt->sge[sge_no].addr = (unsigned long)
				vec->sge[sge_no].iov_base;
			ctxt->sge[sge_no].lkey = vec->frmr->mr->lkey;
		}
		ctxt->sge[sge_no].length = sge_bytes;
	}
	BUG_ON(byte_count != 0);

	/* Save all respages in the ctxt and remove them from the
	 * respages array. They are our pages until the I/O
	 * completes.
	 */
	pages = rqstp->rq_next_page - rqstp->rq_respages;
	for (page_no = 0; page_no < pages; page_no++) {
		ctxt->pages[page_no+1] = rqstp->rq_respages[page_no];
		ctxt->count++;
		rqstp->rq_respages[page_no] = NULL;
		/*
		 * If there are more pages than SGE, terminate SGE
		 * list so that svc_rdma_unmap_dma doesn't attempt to
		 * unmap garbage.
		 */
		if (page_no+1 >= sge_no)
			ctxt->sge[page_no+1].length = 0;
	}
	rqstp->rq_next_page = rqstp->rq_respages + 1;
	BUG_ON(sge_no > rdma->sc_max_sge);
	memset(&send_wr, 0, sizeof send_wr);
	ctxt->wr_op = IB_WR_SEND;
	send_wr.wr_id = (unsigned long)ctxt;
	send_wr.sg_list = ctxt->sge;
	send_wr.num_sge = sge_no;
	send_wr.opcode = IB_WR_SEND;
	send_wr.send_flags =  IB_SEND_SIGNALED;
	if (vec->frmr) {
		/* Prepare INVALIDATE WR */
		memset(&inv_wr, 0, sizeof inv_wr);
		inv_wr.opcode = IB_WR_LOCAL_INV;
		inv_wr.send_flags = IB_SEND_SIGNALED;
		inv_wr.ex.invalidate_rkey =
			vec->frmr->mr->lkey;
		send_wr.next = &inv_wr;
	}

	ret = svc_rdma_send(rdma, &send_wr);
	if (ret)
		goto err;

	return 0;

 err:
	svc_rdma_unmap_dma(ctxt);
	svc_rdma_put_frmr(rdma, vec->frmr);
	svc_rdma_put_context(ctxt, 1);
	return -EIO;
}

void svc_rdma_prep_reply_hdr(struct svc_rqst *rqstp)
{
}

/*
 * Return the start of an xdr buffer.
 */
static void *xdr_start(struct xdr_buf *xdr)
{
	return xdr->head[0].iov_base -
		(xdr->len -
		 xdr->page_len -
		 xdr->tail[0].iov_len -
		 xdr->head[0].iov_len);
}

int svc_rdma_sendto(struct svc_rqst *rqstp)
{
	struct svc_xprt *xprt = rqstp->rq_xprt;
	struct svcxprt_rdma *rdma =
		container_of(xprt, struct svcxprt_rdma, sc_xprt);
	struct rpcrdma_msg *rdma_argp;
	struct rpcrdma_msg *rdma_resp;
	struct rpcrdma_write_array *reply_ary;
	enum rpcrdma_proc reply_type;
	int ret;
	int inline_bytes;
	struct page *res_page;
	struct svc_rdma_op_ctxt *ctxt;
	struct svc_rdma_req_map *vec;

	dprintk("svcrdma: sending response for rqstp=%p\n", rqstp);

	/* Get the RDMA request header. */
	rdma_argp = xdr_start(&rqstp->rq_arg);

	/* Build an req vec for the XDR */
	ctxt = svc_rdma_get_context(rdma);
	ctxt->direction = DMA_TO_DEVICE;
	vec = svc_rdma_get_req_map();
	ret = map_xdr(rdma, &rqstp->rq_res, vec);
	if (ret)
		goto err0;
	inline_bytes = rqstp->rq_res.len;

	/* Create the RDMA response header */
	res_page = svc_rdma_get_page();
	rdma_resp = page_address(res_page);
	reply_ary = svc_rdma_get_reply_array(rdma_argp);
	if (reply_ary)
		reply_type = RDMA_NOMSG;
	else
		reply_type = RDMA_MSG;
	svc_rdma_xdr_encode_reply_header(rdma, rdma_argp,
					 rdma_resp, reply_type);

	/* Send any write-chunk data and build resp write-list */
	ret = send_write_chunks(rdma, rdma_argp, rdma_resp,
				rqstp, vec);
	if (ret < 0) {
		printk(KERN_ERR "svcrdma: failed to send write chunks, rc=%d\n",
		       ret);
		goto err1;
	}
	inline_bytes -= ret;

	/* Send any reply-list data and update resp reply-list */
	ret = send_reply_chunks(rdma, rdma_argp, rdma_resp,
				rqstp, vec);
	if (ret < 0) {
		printk(KERN_ERR "svcrdma: failed to send reply chunks, rc=%d\n",
		       ret);
		goto err1;
	}
	inline_bytes -= ret;

	ret = send_reply(rdma, rqstp, res_page, rdma_resp, ctxt, vec,
			 inline_bytes);
	svc_rdma_put_req_map(vec);
	dprintk("svcrdma: send_reply returns %d\n", ret);
	return ret;

 err1:
	put_page(res_page);
 err0:
	svc_rdma_put_req_map(vec);
	svc_rdma_put_context(ctxt, 0);
	return ret;
}