aboutsummaryrefslogtreecommitdiff
path: root/block/blk-map.c
blob: 8584babf3ea0ca2590f30383b9594231266e9437 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Functions related to mapping data to requests
 */
#include <linux/kernel.h>
#include <linux/sched/task_stack.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/uio.h>

#include "blk.h"

struct bio_map_data {
	bool is_our_pages : 1;
	bool is_null_mapped : 1;
	struct iov_iter iter;
	struct iovec iov[];
};

static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data,
					       gfp_t gfp_mask)
{
	struct bio_map_data *bmd;

	if (data->nr_segs > UIO_MAXIOV)
		return NULL;

	bmd = kmalloc(struct_size(bmd, iov, data->nr_segs), gfp_mask);
	if (!bmd)
		return NULL;
	bmd->iter = *data;
	if (iter_is_iovec(data)) {
		memcpy(bmd->iov, iter_iov(data), sizeof(struct iovec) * data->nr_segs);
		bmd->iter.__iov = bmd->iov;
	}
	return bmd;
}

/**
 * bio_copy_from_iter - copy all pages from iov_iter to bio
 * @bio: The &struct bio which describes the I/O as destination
 * @iter: iov_iter as source
 *
 * Copy all pages from iov_iter to bio.
 * Returns 0 on success, or error on failure.
 */
static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
{
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bvec, bio, iter_all) {
		ssize_t ret;

		ret = copy_page_from_iter(bvec->bv_page,
					  bvec->bv_offset,
					  bvec->bv_len,
					  iter);

		if (!iov_iter_count(iter))
			break;

		if (ret < bvec->bv_len)
			return -EFAULT;
	}

	return 0;
}

/**
 * bio_copy_to_iter - copy all pages from bio to iov_iter
 * @bio: The &struct bio which describes the I/O as source
 * @iter: iov_iter as destination
 *
 * Copy all pages from bio to iov_iter.
 * Returns 0 on success, or error on failure.
 */
static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
{
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bvec, bio, iter_all) {
		ssize_t ret;

		ret = copy_page_to_iter(bvec->bv_page,
					bvec->bv_offset,
					bvec->bv_len,
					&iter);

		if (!iov_iter_count(&iter))
			break;

		if (ret < bvec->bv_len)
			return -EFAULT;
	}

	return 0;
}

/**
 *	bio_uncopy_user	-	finish previously mapped bio
 *	@bio: bio being terminated
 *
 *	Free pages allocated from bio_copy_user_iov() and write back data
 *	to user space in case of a read.
 */
static int bio_uncopy_user(struct bio *bio)
{
	struct bio_map_data *bmd = bio->bi_private;
	int ret = 0;

	if (!bmd->is_null_mapped) {
		/*
		 * if we're in a workqueue, the request is orphaned, so
		 * don't copy into a random user address space, just free
		 * and return -EINTR so user space doesn't expect any data.
		 */
		if (!current->mm)
			ret = -EINTR;
		else if (bio_data_dir(bio) == READ)
			ret = bio_copy_to_iter(bio, bmd->iter);
		if (bmd->is_our_pages)
			bio_free_pages(bio);
	}
	kfree(bmd);
	return ret;
}

static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
		struct iov_iter *iter, gfp_t gfp_mask)
{
	struct bio_map_data *bmd;
	struct page *page;
	struct bio *bio;
	int i = 0, ret;
	int nr_pages;
	unsigned int len = iter->count;
	unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0;

	bmd = bio_alloc_map_data(iter, gfp_mask);
	if (!bmd)
		return -ENOMEM;

	/*
	 * We need to do a deep copy of the iov_iter including the iovecs.
	 * The caller provided iov might point to an on-stack or otherwise
	 * shortlived one.
	 */
	bmd->is_our_pages = !map_data;
	bmd->is_null_mapped = (map_data && map_data->null_mapped);

	nr_pages = bio_max_segs(DIV_ROUND_UP(offset + len, PAGE_SIZE));

	ret = -ENOMEM;
	bio = bio_kmalloc(nr_pages, gfp_mask);
	if (!bio)
		goto out_bmd;
	bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, req_op(rq));

	if (map_data) {
		nr_pages = 1U << map_data->page_order;
		i = map_data->offset / PAGE_SIZE;
	}
	while (len) {
		unsigned int bytes = PAGE_SIZE;

		bytes -= offset;

		if (bytes > len)
			bytes = len;

		if (map_data) {
			if (i == map_data->nr_entries * nr_pages) {
				ret = -ENOMEM;
				goto cleanup;
			}

			page = map_data->pages[i / nr_pages];
			page += (i % nr_pages);

			i++;
		} else {
			page = alloc_page(GFP_NOIO | gfp_mask);
			if (!page) {
				ret = -ENOMEM;
				goto cleanup;
			}
		}

		if (bio_add_pc_page(rq->q, bio, page, bytes, offset) < bytes) {
			if (!map_data)
				__free_page(page);
			break;
		}

		len -= bytes;
		offset = 0;
	}

	if (map_data)
		map_data->offset += bio->bi_iter.bi_size;

	/*
	 * success
	 */
	if ((iov_iter_rw(iter) == WRITE &&
	     (!map_data || !map_data->null_mapped)) ||
	    (map_data && map_data->from_user)) {
		ret = bio_copy_from_iter(bio, iter);
		if (ret)
			goto cleanup;
	} else {
		if (bmd->is_our_pages)
			zero_fill_bio(bio);
		iov_iter_advance(iter, bio->bi_iter.bi_size);
	}

	bio->bi_private = bmd;

	ret = blk_rq_append_bio(rq, bio);
	if (ret)
		goto cleanup;
	return 0;
cleanup:
	if (!map_data)
		bio_free_pages(bio);
	bio_uninit(bio);
	kfree(bio);
out_bmd:
	kfree(bmd);
	return ret;
}

static void blk_mq_map_bio_put(struct bio *bio)
{
	if (bio->bi_opf & REQ_ALLOC_CACHE) {
		bio_put(bio);
	} else {
		bio_uninit(bio);
		kfree(bio);
	}
}

static struct bio *blk_rq_map_bio_alloc(struct request *rq,
		unsigned int nr_vecs, gfp_t gfp_mask)
{
	struct bio *bio;

	if (rq->cmd_flags & REQ_ALLOC_CACHE && (nr_vecs <= BIO_INLINE_VECS)) {
		bio = bio_alloc_bioset(NULL, nr_vecs, rq->cmd_flags, gfp_mask,
					&fs_bio_set);
		if (!bio)
			return NULL;
	} else {
		bio = bio_kmalloc(nr_vecs, gfp_mask);
		if (!bio)
			return NULL;
		bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq));
	}
	return bio;
}

static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
		gfp_t gfp_mask)
{
	iov_iter_extraction_t extraction_flags = 0;
	unsigned int max_sectors = queue_max_hw_sectors(rq->q);
	unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS);
	struct bio *bio;
	int ret;
	int j;

	if (!iov_iter_count(iter))
		return -EINVAL;

	bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask);
	if (bio == NULL)
		return -ENOMEM;

	if (blk_queue_pci_p2pdma(rq->q))
		extraction_flags |= ITER_ALLOW_P2PDMA;
	if (iov_iter_extract_will_pin(iter))
		bio_set_flag(bio, BIO_PAGE_PINNED);

	while (iov_iter_count(iter)) {
		struct page *stack_pages[UIO_FASTIOV];
		struct page **pages = stack_pages;
		ssize_t bytes;
		size_t offs;
		int npages;

		if (nr_vecs > ARRAY_SIZE(stack_pages))
			pages = NULL;

		bytes = iov_iter_extract_pages(iter, &pages, LONG_MAX,
					       nr_vecs, extraction_flags, &offs);
		if (unlikely(bytes <= 0)) {
			ret = bytes ? bytes : -EFAULT;
			goto out_unmap;
		}

		npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE);

		if (unlikely(offs & queue_dma_alignment(rq->q)))
			j = 0;
		else {
			for (j = 0; j < npages; j++) {
				struct page *page = pages[j];
				unsigned int n = PAGE_SIZE - offs;
				bool same_page = false;

				if (n > bytes)
					n = bytes;

				if (!bio_add_hw_page(rq->q, bio, page, n, offs,
						     max_sectors, &same_page))
					break;

				if (same_page)
					bio_release_page(bio, page);
				bytes -= n;
				offs = 0;
			}
		}
		/*
		 * release the pages we didn't map into the bio, if any
		 */
		while (j < npages)
			bio_release_page(bio, pages[j++]);
		if (pages != stack_pages)
			kvfree(pages);
		/* couldn't stuff something into bio? */
		if (bytes) {
			iov_iter_revert(iter, bytes);
			break;
		}
	}

	ret = blk_rq_append_bio(rq, bio);
	if (ret)
		goto out_unmap;
	return 0;

 out_unmap:
	bio_release_pages(bio, false);
	blk_mq_map_bio_put(bio);
	return ret;
}

static void bio_invalidate_vmalloc_pages(struct bio *bio)
{
#ifdef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE
	if (bio->bi_private && !op_is_write(bio_op(bio))) {
		unsigned long i, len = 0;

		for (i = 0; i < bio->bi_vcnt; i++)
			len += bio->bi_io_vec[i].bv_len;
		invalidate_kernel_vmap_range(bio->bi_private, len);
	}
#endif
}

static void bio_map_kern_endio(struct bio *bio)
{
	bio_invalidate_vmalloc_pages(bio);
	bio_uninit(bio);
	kfree(bio);
}

/**
 *	bio_map_kern	-	map kernel address into bio
 *	@q: the struct request_queue for the bio
 *	@data: pointer to buffer to map
 *	@len: length in bytes
 *	@gfp_mask: allocation flags for bio allocation
 *
 *	Map the kernel address into a bio suitable for io to a block
 *	device. Returns an error pointer in case of error.
 */
static struct bio *bio_map_kern(struct request_queue *q, void *data,
		unsigned int len, gfp_t gfp_mask)
{
	unsigned long kaddr = (unsigned long)data;
	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
	unsigned long start = kaddr >> PAGE_SHIFT;
	const int nr_pages = end - start;
	bool is_vmalloc = is_vmalloc_addr(data);
	struct page *page;
	int offset, i;
	struct bio *bio;

	bio = bio_kmalloc(nr_pages, gfp_mask);
	if (!bio)
		return ERR_PTR(-ENOMEM);
	bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0);

	if (is_vmalloc) {
		flush_kernel_vmap_range(data, len);
		bio->bi_private = data;
	}

	offset = offset_in_page(kaddr);
	for (i = 0; i < nr_pages; i++) {
		unsigned int bytes = PAGE_SIZE - offset;

		if (len <= 0)
			break;

		if (bytes > len)
			bytes = len;

		if (!is_vmalloc)
			page = virt_to_page(data);
		else
			page = vmalloc_to_page(data);
		if (bio_add_pc_page(q, bio, page, bytes,
				    offset) < bytes) {
			/* we don't support partial mappings */
			bio_uninit(bio);
			kfree(bio);
			return ERR_PTR(-EINVAL);
		}

		data += bytes;
		len -= bytes;
		offset = 0;
	}

	bio->bi_end_io = bio_map_kern_endio;
	return bio;
}

static void bio_copy_kern_endio(struct bio *bio)
{
	bio_free_pages(bio);
	bio_uninit(bio);
	kfree(bio);
}

static void bio_copy_kern_endio_read(struct bio *bio)
{
	char *p = bio->bi_private;
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bvec, bio, iter_all) {
		memcpy_from_bvec(p, bvec);
		p += bvec->bv_len;
	}

	bio_copy_kern_endio(bio);
}

/**
 *	bio_copy_kern	-	copy kernel address into bio
 *	@q: the struct request_queue for the bio
 *	@data: pointer to buffer to copy
 *	@len: length in bytes
 *	@gfp_mask: allocation flags for bio and page allocation
 *	@reading: data direction is READ
 *
 *	copy the kernel address into a bio suitable for io to a block
 *	device. Returns an error pointer in case of error.
 */
static struct bio *bio_copy_kern(struct request_queue *q, void *data,
		unsigned int len, gfp_t gfp_mask, int reading)
{
	unsigned long kaddr = (unsigned long)data;
	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
	unsigned long start = kaddr >> PAGE_SHIFT;
	struct bio *bio;
	void *p = data;
	int nr_pages = 0;

	/*
	 * Overflow, abort
	 */
	if (end < start)
		return ERR_PTR(-EINVAL);

	nr_pages = end - start;
	bio = bio_kmalloc(nr_pages, gfp_mask);
	if (!bio)
		return ERR_PTR(-ENOMEM);
	bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0);

	while (len) {
		struct page *page;
		unsigned int bytes = PAGE_SIZE;

		if (bytes > len)
			bytes = len;

		page = alloc_page(GFP_NOIO | __GFP_ZERO | gfp_mask);
		if (!page)
			goto cleanup;

		if (!reading)
			memcpy(page_address(page), p, bytes);

		if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes)
			break;

		len -= bytes;
		p += bytes;
	}

	if (reading) {
		bio->bi_end_io = bio_copy_kern_endio_read;
		bio->bi_private = data;
	} else {
		bio->bi_end_io = bio_copy_kern_endio;
	}

	return bio;

cleanup:
	bio_free_pages(bio);
	bio_uninit(bio);
	kfree(bio);
	return ERR_PTR(-ENOMEM);
}

/*
 * Append a bio to a passthrough request.  Only works if the bio can be merged
 * into the request based on the driver constraints.
 */
int blk_rq_append_bio(struct request *rq, struct bio *bio)
{
	struct bvec_iter iter;
	struct bio_vec bv;
	unsigned int nr_segs = 0;

	bio_for_each_bvec(bv, bio, iter)
		nr_segs++;

	if (!rq->bio) {
		blk_rq_bio_prep(rq, bio, nr_segs);
	} else {
		if (!ll_back_merge_fn(rq, bio, nr_segs))
			return -EINVAL;
		rq->biotail->bi_next = bio;
		rq->biotail = bio;
		rq->__data_len += (bio)->bi_iter.bi_size;
		bio_crypt_free_ctx(bio);
	}

	return 0;
}
EXPORT_SYMBOL(blk_rq_append_bio);

/* Prepare bio for passthrough IO given ITER_BVEC iter */
static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
{
	struct request_queue *q = rq->q;
	size_t nr_iter = iov_iter_count(iter);
	size_t nr_segs = iter->nr_segs;
	struct bio_vec *bvecs, *bvprvp = NULL;
	const struct queue_limits *lim = &q->limits;
	unsigned int nsegs = 0, bytes = 0;
	struct bio *bio;
	size_t i;

	if (!nr_iter || (nr_iter >> SECTOR_SHIFT) > queue_max_hw_sectors(q))
		return -EINVAL;
	if (nr_segs > queue_max_segments(q))
		return -EINVAL;

	/* no iovecs to alloc, as we already have a BVEC iterator */
	bio = blk_rq_map_bio_alloc(rq, 0, GFP_KERNEL);
	if (bio == NULL)
		return -ENOMEM;

	bio_iov_bvec_set(bio, (struct iov_iter *)iter);
	blk_rq_bio_prep(rq, bio, nr_segs);

	/* loop to perform a bunch of sanity checks */
	bvecs = (struct bio_vec *)iter->bvec;
	for (i = 0; i < nr_segs; i++) {
		struct bio_vec *bv = &bvecs[i];

		/*
		 * If the queue doesn't support SG gaps and adding this
		 * offset would create a gap, fallback to copy.
		 */
		if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv->bv_offset)) {
			blk_mq_map_bio_put(bio);
			return -EREMOTEIO;
		}
		/* check full condition */
		if (nsegs >= nr_segs || bytes > UINT_MAX - bv->bv_len)
			goto put_bio;
		if (bytes + bv->bv_len > nr_iter)
			goto put_bio;
		if (bv->bv_offset + bv->bv_len > PAGE_SIZE)
			goto put_bio;

		nsegs++;
		bytes += bv->bv_len;
		bvprvp = bv;
	}
	return 0;
put_bio:
	blk_mq_map_bio_put(bio);
	return -EINVAL;
}

/**
 * blk_rq_map_user_iov - map user data to a request, for passthrough requests
 * @q:		request queue where request should be inserted
 * @rq:		request to map data to
 * @map_data:   pointer to the rq_map_data holding pages (if necessary)
 * @iter:	iovec iterator
 * @gfp_mask:	memory allocation flags
 *
 * Description:
 *    Data will be mapped directly for zero copy I/O, if possible. Otherwise
 *    a kernel bounce buffer is used.
 *
 *    A matching blk_rq_unmap_user() must be issued at the end of I/O, while
 *    still in process context.
 */
int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
			struct rq_map_data *map_data,
			const struct iov_iter *iter, gfp_t gfp_mask)
{
	bool copy = false, map_bvec = false;
	unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
	struct bio *bio = NULL;
	struct iov_iter i;
	int ret = -EINVAL;

	if (map_data)
		copy = true;
	else if (blk_queue_may_bounce(q))
		copy = true;
	else if (iov_iter_alignment(iter) & align)
		copy = true;
	else if (iov_iter_is_bvec(iter))
		map_bvec = true;
	else if (!user_backed_iter(iter))
		copy = true;
	else if (queue_virt_boundary(q))
		copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter);

	if (map_bvec) {
		ret = blk_rq_map_user_bvec(rq, iter);
		if (!ret)
			return 0;
		if (ret != -EREMOTEIO)
			goto fail;
		/* fall back to copying the data on limits mismatches */
		copy = true;
	}

	i = *iter;
	do {
		if (copy)
			ret = bio_copy_user_iov(rq, map_data, &i, gfp_mask);
		else
			ret = bio_map_user_iov(rq, &i, gfp_mask);
		if (ret)
			goto unmap_rq;
		if (!bio)
			bio = rq->bio;
	} while (iov_iter_count(&i));

	return 0;

unmap_rq:
	blk_rq_unmap_user(bio);
fail:
	rq->bio = NULL;
	return ret;
}
EXPORT_SYMBOL(blk_rq_map_user_iov);

int blk_rq_map_user(struct request_queue *q, struct request *rq,
		    struct rq_map_data *map_data, void __user *ubuf,
		    unsigned long len, gfp_t gfp_mask)
{
	struct iov_iter i;
	int ret = import_ubuf(rq_data_dir(rq), ubuf, len, &i);

	if (unlikely(ret < 0))
		return ret;

	return blk_rq_map_user_iov(q, rq, map_data, &i, gfp_mask);
}
EXPORT_SYMBOL(blk_rq_map_user);

int blk_rq_map_user_io(struct request *req, struct rq_map_data *map_data,
		void __user *ubuf, unsigned long buf_len, gfp_t gfp_mask,
		bool vec, int iov_count, bool check_iter_count, int rw)
{
	int ret = 0;

	if (vec) {
		struct iovec fast_iov[UIO_FASTIOV];
		struct iovec *iov = fast_iov;
		struct iov_iter iter;

		ret = import_iovec(rw, ubuf, iov_count ? iov_count : buf_len,
				UIO_FASTIOV, &iov, &iter);
		if (ret < 0)
			return ret;

		if (iov_count) {
			/* SG_IO howto says that the shorter of the two wins */
			iov_iter_truncate(&iter, buf_len);
			if (check_iter_count && !iov_iter_count(&iter)) {
				kfree(iov);
				return -EINVAL;
			}
		}

		ret = blk_rq_map_user_iov(req->q, req, map_data, &iter,
				gfp_mask);
		kfree(iov);
	} else if (buf_len) {
		ret = blk_rq_map_user(req->q, req, map_data, ubuf, buf_len,
				gfp_mask);
	}
	return ret;
}
EXPORT_SYMBOL(blk_rq_map_user_io);

/**
 * blk_rq_unmap_user - unmap a request with user data
 * @bio:	       start of bio list
 *
 * Description:
 *    Unmap a rq previously mapped by blk_rq_map_user(). The caller must
 *    supply the original rq->bio from the blk_rq_map_user() return, since
 *    the I/O completion may have changed rq->bio.
 */
int blk_rq_unmap_user(struct bio *bio)
{
	struct bio *next_bio;
	int ret = 0, ret2;

	while (bio) {
		if (bio->bi_private) {
			ret2 = bio_uncopy_user(bio);
			if (ret2 && !ret)
				ret = ret2;
		} else {
			bio_release_pages(bio, bio_data_dir(bio) == READ);
		}

		next_bio = bio;
		bio = bio->bi_next;
		blk_mq_map_bio_put(next_bio);
	}

	return ret;
}
EXPORT_SYMBOL(blk_rq_unmap_user);

/**
 * blk_rq_map_kern - map kernel data to a request, for passthrough requests
 * @q:		request queue where request should be inserted
 * @rq:		request to fill
 * @kbuf:	the kernel buffer
 * @len:	length of user data
 * @gfp_mask:	memory allocation flags
 *
 * Description:
 *    Data will be mapped directly if possible. Otherwise a bounce
 *    buffer is used. Can be called multiple times to append multiple
 *    buffers.
 */
int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
		    unsigned int len, gfp_t gfp_mask)
{
	int reading = rq_data_dir(rq) == READ;
	unsigned long addr = (unsigned long) kbuf;
	struct bio *bio;
	int ret;

	if (len > (queue_max_hw_sectors(q) << 9))
		return -EINVAL;
	if (!len || !kbuf)
		return -EINVAL;

	if (!blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf) ||
	    blk_queue_may_bounce(q))
		bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading);
	else
		bio = bio_map_kern(q, kbuf, len, gfp_mask);

	if (IS_ERR(bio))
		return PTR_ERR(bio);

	bio->bi_opf &= ~REQ_OP_MASK;
	bio->bi_opf |= req_op(rq);

	ret = blk_rq_append_bio(rq, bio);
	if (unlikely(ret)) {
		bio_uninit(bio);
		kfree(bio);
	}
	return ret;
}
EXPORT_SYMBOL(blk_rq_map_kern);