forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
bio.c
1642 lines (1380 loc) · 38.3 KB
/
bio.c
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
/*
* Copyright (C) 2001 Jens Axboe <[email protected]>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public Licens
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-
*
*/
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/mempool.h>
#include <linux/workqueue.h>
#include <linux/blktrace_api.h>
#include <trace/block.h>
#include <scsi/sg.h> /* for struct sg_iovec */
DEFINE_TRACE(block_split);
/*
* Test patch to inline a certain number of bi_io_vec's inside the bio
* itself, to shrink a bio data allocation from two mempool calls to one
*/
#define BIO_INLINE_VECS 4
static mempool_t *bio_split_pool __read_mostly;
/*
* if you change this list, also change bvec_alloc or things will
* break badly! cannot be bigger than what you can fit into an
* unsigned short
*/
#define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
};
#undef BV
/*
* fs_bio_set is the bio_set containing bio and iovec memory pools used by
* IO code that does not need private memory pools.
*/
struct bio_set *fs_bio_set;
/*
* Our slab pool management
*/
struct bio_slab {
struct kmem_cache *slab;
unsigned int slab_ref;
unsigned int slab_size;
char name[8];
};
static DEFINE_MUTEX(bio_slab_lock);
static struct bio_slab *bio_slabs;
static unsigned int bio_slab_nr, bio_slab_max;
static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
{
unsigned int sz = sizeof(struct bio) + extra_size;
struct kmem_cache *slab = NULL;
struct bio_slab *bslab;
unsigned int i, entry = -1;
mutex_lock(&bio_slab_lock);
i = 0;
while (i < bio_slab_nr) {
struct bio_slab *bslab = &bio_slabs[i];
if (!bslab->slab && entry == -1)
entry = i;
else if (bslab->slab_size == sz) {
slab = bslab->slab;
bslab->slab_ref++;
break;
}
i++;
}
if (slab)
goto out_unlock;
if (bio_slab_nr == bio_slab_max && entry == -1) {
bio_slab_max <<= 1;
bio_slabs = krealloc(bio_slabs,
bio_slab_max * sizeof(struct bio_slab),
GFP_KERNEL);
if (!bio_slabs)
goto out_unlock;
}
if (entry == -1)
entry = bio_slab_nr++;
bslab = &bio_slabs[entry];
snprintf(bslab->name, sizeof(bslab->name), "bio-%d", entry);
slab = kmem_cache_create(bslab->name, sz, 0, SLAB_HWCACHE_ALIGN, NULL);
if (!slab)
goto out_unlock;
printk("bio: create slab <%s> at %d\n", bslab->name, entry);
bslab->slab = slab;
bslab->slab_ref = 1;
bslab->slab_size = sz;
out_unlock:
mutex_unlock(&bio_slab_lock);
return slab;
}
static void bio_put_slab(struct bio_set *bs)
{
struct bio_slab *bslab = NULL;
unsigned int i;
mutex_lock(&bio_slab_lock);
for (i = 0; i < bio_slab_nr; i++) {
if (bs->bio_slab == bio_slabs[i].slab) {
bslab = &bio_slabs[i];
break;
}
}
if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n"))
goto out;
WARN_ON(!bslab->slab_ref);
if (--bslab->slab_ref)
goto out;
kmem_cache_destroy(bslab->slab);
bslab->slab = NULL;
out:
mutex_unlock(&bio_slab_lock);
}
unsigned int bvec_nr_vecs(unsigned short idx)
{
return bvec_slabs[idx].nr_vecs;
}
void bvec_free_bs(struct bio_set *bs, struct bio_vec *bv, unsigned int idx)
{
BIO_BUG_ON(idx >= BIOVEC_NR_POOLS);
if (idx == BIOVEC_MAX_IDX)
mempool_free(bv, bs->bvec_pool);
else {
struct biovec_slab *bvs = bvec_slabs + idx;
kmem_cache_free(bvs->slab, bv);
}
}
struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx,
struct bio_set *bs)
{
struct bio_vec *bvl;
/*
* If 'bs' is given, lookup the pool and do the mempool alloc.
* If not, this is a bio_kmalloc() allocation and just do a
* kzalloc() for the exact number of vecs right away.
*/
if (!bs)
bvl = kmalloc(nr * sizeof(struct bio_vec), gfp_mask);
/*
* see comment near bvec_array define!
*/
switch (nr) {
case 1:
*idx = 0;
break;
case 2 ... 4:
*idx = 1;
break;
case 5 ... 16:
*idx = 2;
break;
case 17 ... 64:
*idx = 3;
break;
case 65 ... 128:
*idx = 4;
break;
case 129 ... BIO_MAX_PAGES:
*idx = 5;
break;
default:
return NULL;
}
/*
* idx now points to the pool we want to allocate from. only the
* 1-vec entry pool is mempool backed.
*/
if (*idx == BIOVEC_MAX_IDX) {
fallback:
bvl = mempool_alloc(bs->bvec_pool, gfp_mask);
} else {
struct biovec_slab *bvs = bvec_slabs + *idx;
gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
/*
* Make this allocation restricted and don't dump info on
* allocation failures, since we'll fallback to the mempool
* in case of failure.
*/
__gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
/*
* Try a slab allocation. If this fails and __GFP_WAIT
* is set, retry with the 1-entry mempool
*/
bvl = kmem_cache_alloc(bvs->slab, __gfp_mask);
if (unlikely(!bvl && (gfp_mask & __GFP_WAIT))) {
*idx = BIOVEC_MAX_IDX;
goto fallback;
}
}
return bvl;
}
void bio_free(struct bio *bio, struct bio_set *bs)
{
void *p;
if (bio_has_allocated_vec(bio))
bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
if (bio_integrity(bio))
bio_integrity_free(bio, bs);
/*
* If we have front padding, adjust the bio pointer before freeing
*/
p = bio;
if (bs->front_pad)
p -= bs->front_pad;
mempool_free(p, bs->bio_pool);
}
/*
* default destructor for a bio allocated with bio_alloc_bioset()
*/
static void bio_fs_destructor(struct bio *bio)
{
bio_free(bio, fs_bio_set);
}
static void bio_kmalloc_destructor(struct bio *bio)
{
if (bio_has_allocated_vec(bio))
kfree(bio->bi_io_vec);
kfree(bio);
}
void bio_init(struct bio *bio)
{
memset(bio, 0, sizeof(*bio));
bio->bi_flags = 1 << BIO_UPTODATE;
bio->bi_comp_cpu = -1;
atomic_set(&bio->bi_cnt, 1);
}
/**
* bio_alloc_bioset - allocate a bio for I/O
* @gfp_mask: the GFP_ mask given to the slab allocator
* @nr_iovecs: number of iovecs to pre-allocate
* @bs: the bio_set to allocate from. If %NULL, just use kmalloc
*
* Description:
* bio_alloc_bioset will first try its own mempool to satisfy the allocation.
* If %__GFP_WAIT is set then we will block on the internal pool waiting
* for a &struct bio to become free. If a %NULL @bs is passed in, we will
* fall back to just using @kmalloc to allocate the required memory.
*
* Note that the caller must set ->bi_destructor on succesful return
* of a bio, to do the appropriate freeing of the bio once the reference
* count drops to zero.
**/
struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
{
struct bio *bio = NULL;
void *uninitialized_var(p);
if (bs) {
p = mempool_alloc(bs->bio_pool, gfp_mask);
if (p)
bio = p + bs->front_pad;
} else
bio = kmalloc(sizeof(*bio), gfp_mask);
if (likely(bio)) {
struct bio_vec *bvl = NULL;
bio_init(bio);
if (likely(nr_iovecs)) {
unsigned long uninitialized_var(idx);
if (nr_iovecs <= BIO_INLINE_VECS) {
idx = 0;
bvl = bio->bi_inline_vecs;
nr_iovecs = BIO_INLINE_VECS;
} else {
bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx,
bs);
nr_iovecs = bvec_nr_vecs(idx);
}
if (unlikely(!bvl)) {
if (bs)
mempool_free(p, bs->bio_pool);
else
kfree(bio);
bio = NULL;
goto out;
}
bio->bi_flags |= idx << BIO_POOL_OFFSET;
bio->bi_max_vecs = nr_iovecs;
}
bio->bi_io_vec = bvl;
}
out:
return bio;
}
struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
{
struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
if (bio)
bio->bi_destructor = bio_fs_destructor;
return bio;
}
/*
* Like bio_alloc(), but doesn't use a mempool backing. This means that
* it CAN fail, but while bio_alloc() can only be used for allocations
* that have a short (finite) life span, bio_kmalloc() should be used
* for more permanent bio allocations (like allocating some bio's for
* initalization or setup purposes).
*/
struct bio *bio_kmalloc(gfp_t gfp_mask, int nr_iovecs)
{
struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
if (bio)
bio->bi_destructor = bio_kmalloc_destructor;
return bio;
}
void zero_fill_bio(struct bio *bio)
{
unsigned long flags;
struct bio_vec *bv;
int i;
bio_for_each_segment(bv, bio, i) {
char *data = bvec_kmap_irq(bv, &flags);
memset(data, 0, bv->bv_len);
flush_dcache_page(bv->bv_page);
bvec_kunmap_irq(data, &flags);
}
}
EXPORT_SYMBOL(zero_fill_bio);
/**
* bio_put - release a reference to a bio
* @bio: bio to release reference to
*
* Description:
* Put a reference to a &struct bio, either one you have gotten with
* bio_alloc or bio_get. The last put of a bio will free it.
**/
void bio_put(struct bio *bio)
{
BIO_BUG_ON(!atomic_read(&bio->bi_cnt));
/*
* last put frees it
*/
if (atomic_dec_and_test(&bio->bi_cnt)) {
bio->bi_next = NULL;
bio->bi_destructor(bio);
}
}
inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
{
if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
blk_recount_segments(q, bio);
return bio->bi_phys_segments;
}
/**
* __bio_clone - clone a bio
* @bio: destination bio
* @bio_src: bio to clone
*
* Clone a &bio. Caller will own the returned bio, but not
* the actual data it points to. Reference count of returned
* bio will be one.
*/
void __bio_clone(struct bio *bio, struct bio *bio_src)
{
memcpy(bio->bi_io_vec, bio_src->bi_io_vec,
bio_src->bi_max_vecs * sizeof(struct bio_vec));
/*
* most users will be overriding ->bi_bdev with a new target,
* so we don't set nor calculate new physical/hw segment counts here
*/
bio->bi_sector = bio_src->bi_sector;
bio->bi_bdev = bio_src->bi_bdev;
bio->bi_flags |= 1 << BIO_CLONED;
bio->bi_rw = bio_src->bi_rw;
bio->bi_vcnt = bio_src->bi_vcnt;
bio->bi_size = bio_src->bi_size;
bio->bi_idx = bio_src->bi_idx;
}
/**
* bio_clone - clone a bio
* @bio: bio to clone
* @gfp_mask: allocation priority
*
* Like __bio_clone, only also allocates the returned bio
*/
struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
{
struct bio *b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, fs_bio_set);
if (!b)
return NULL;
b->bi_destructor = bio_fs_destructor;
__bio_clone(b, bio);
if (bio_integrity(bio)) {
int ret;
ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set);
if (ret < 0) {
bio_put(b);
return NULL;
}
}
return b;
}
/**
* bio_get_nr_vecs - return approx number of vecs
* @bdev: I/O target
*
* Return the approximate number of pages we can send to this target.
* There's no guarantee that you will be able to fit this number of pages
* into a bio, it does not account for dynamic restrictions that vary
* on offset.
*/
int bio_get_nr_vecs(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
int nr_pages;
nr_pages = ((q->max_sectors << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (nr_pages > q->max_phys_segments)
nr_pages = q->max_phys_segments;
if (nr_pages > q->max_hw_segments)
nr_pages = q->max_hw_segments;
return nr_pages;
}
static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
*page, unsigned int len, unsigned int offset,
unsigned short max_sectors)
{
int retried_segments = 0;
struct bio_vec *bvec;
/*
* cloned bio must not modify vec list
*/
if (unlikely(bio_flagged(bio, BIO_CLONED)))
return 0;
if (((bio->bi_size + len) >> 9) > max_sectors)
return 0;
/*
* For filesystems with a blocksize smaller than the pagesize
* we will often be called with the same page as last time and
* a consecutive offset. Optimize this special case.
*/
if (bio->bi_vcnt > 0) {
struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1];
if (page == prev->bv_page &&
offset == prev->bv_offset + prev->bv_len) {
prev->bv_len += len;
if (q->merge_bvec_fn) {
struct bvec_merge_data bvm = {
.bi_bdev = bio->bi_bdev,
.bi_sector = bio->bi_sector,
.bi_size = bio->bi_size,
.bi_rw = bio->bi_rw,
};
if (q->merge_bvec_fn(q, &bvm, prev) < len) {
prev->bv_len -= len;
return 0;
}
}
goto done;
}
}
if (bio->bi_vcnt >= bio->bi_max_vecs)
return 0;
/*
* we might lose a segment or two here, but rather that than
* make this too complex.
*/
while (bio->bi_phys_segments >= q->max_phys_segments
|| bio->bi_phys_segments >= q->max_hw_segments) {
if (retried_segments)
return 0;
retried_segments = 1;
blk_recount_segments(q, bio);
}
/*
* setup the new entry, we might clear it again later if we
* cannot add the page
*/
bvec = &bio->bi_io_vec[bio->bi_vcnt];
bvec->bv_page = page;
bvec->bv_len = len;
bvec->bv_offset = offset;
/*
* if queue has other restrictions (eg varying max sector size
* depending on offset), it can specify a merge_bvec_fn in the
* queue to get further control
*/
if (q->merge_bvec_fn) {
struct bvec_merge_data bvm = {
.bi_bdev = bio->bi_bdev,
.bi_sector = bio->bi_sector,
.bi_size = bio->bi_size,
.bi_rw = bio->bi_rw,
};
/*
* merge_bvec_fn() returns number of bytes it can accept
* at this offset
*/
if (q->merge_bvec_fn(q, &bvm, bvec) < len) {
bvec->bv_page = NULL;
bvec->bv_len = 0;
bvec->bv_offset = 0;
return 0;
}
}
/* If we may be able to merge these biovecs, force a recount */
if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
bio->bi_flags &= ~(1 << BIO_SEG_VALID);
bio->bi_vcnt++;
bio->bi_phys_segments++;
done:
bio->bi_size += len;
return len;
}
/**
* bio_add_pc_page - attempt to add page to bio
* @q: the target queue
* @bio: destination bio
* @page: page to add
* @len: vec entry length
* @offset: vec entry offset
*
* Attempt to add a page to the bio_vec maplist. This can fail for a
* number of reasons, such as the bio being full or target block
* device limitations. The target block device must allow bio's
* smaller than PAGE_SIZE, so it is always possible to add a single
* page to an empty bio. This should only be used by REQ_PC bios.
*/
int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
return __bio_add_page(q, bio, page, len, offset, q->max_hw_sectors);
}
/**
* bio_add_page - attempt to add page to bio
* @bio: destination bio
* @page: page to add
* @len: vec entry length
* @offset: vec entry offset
*
* Attempt to add a page to the bio_vec maplist. This can fail for a
* number of reasons, such as the bio being full or target block
* device limitations. The target block device must allow bio's
* smaller than PAGE_SIZE, so it is always possible to add a single
* page to an empty bio.
*/
int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
unsigned int offset)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
return __bio_add_page(q, bio, page, len, offset, q->max_sectors);
}
struct bio_map_data {
struct bio_vec *iovecs;
struct sg_iovec *sgvecs;
int nr_sgvecs;
int is_our_pages;
};
static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
struct sg_iovec *iov, int iov_count,
int is_our_pages)
{
memcpy(bmd->iovecs, bio->bi_io_vec, sizeof(struct bio_vec) * bio->bi_vcnt);
memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
bmd->nr_sgvecs = iov_count;
bmd->is_our_pages = is_our_pages;
bio->bi_private = bmd;
}
static void bio_free_map_data(struct bio_map_data *bmd)
{
kfree(bmd->iovecs);
kfree(bmd->sgvecs);
kfree(bmd);
}
static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count,
gfp_t gfp_mask)
{
struct bio_map_data *bmd = kmalloc(sizeof(*bmd), gfp_mask);
if (!bmd)
return NULL;
bmd->iovecs = kmalloc(sizeof(struct bio_vec) * nr_segs, gfp_mask);
if (!bmd->iovecs) {
kfree(bmd);
return NULL;
}
bmd->sgvecs = kmalloc(sizeof(struct sg_iovec) * iov_count, gfp_mask);
if (bmd->sgvecs)
return bmd;
kfree(bmd->iovecs);
kfree(bmd);
return NULL;
}
static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
struct sg_iovec *iov, int iov_count, int uncopy,
int do_free_page)
{
int ret = 0, i;
struct bio_vec *bvec;
int iov_idx = 0;
unsigned int iov_off = 0;
int read = bio_data_dir(bio) == READ;
__bio_for_each_segment(bvec, bio, i, 0) {
char *bv_addr = page_address(bvec->bv_page);
unsigned int bv_len = iovecs[i].bv_len;
while (bv_len && iov_idx < iov_count) {
unsigned int bytes;
char *iov_addr;
bytes = min_t(unsigned int,
iov[iov_idx].iov_len - iov_off, bv_len);
iov_addr = iov[iov_idx].iov_base + iov_off;
if (!ret) {
if (!read && !uncopy)
ret = copy_from_user(bv_addr, iov_addr,
bytes);
if (read && uncopy)
ret = copy_to_user(iov_addr, bv_addr,
bytes);
if (ret)
ret = -EFAULT;
}
bv_len -= bytes;
bv_addr += bytes;
iov_addr += bytes;
iov_off += bytes;
if (iov[iov_idx].iov_len == iov_off) {
iov_idx++;
iov_off = 0;
}
}
if (do_free_page)
__free_page(bvec->bv_page);
}
return ret;
}
/**
* bio_uncopy_user - finish previously mapped bio
* @bio: bio being terminated
*
* Free pages allocated from bio_copy_user() and write back data
* to user space in case of a read.
*/
int bio_uncopy_user(struct bio *bio)
{
struct bio_map_data *bmd = bio->bi_private;
int ret = 0;
if (!bio_flagged(bio, BIO_NULL_MAPPED))
ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
bmd->nr_sgvecs, 1, bmd->is_our_pages);
bio_free_map_data(bmd);
bio_put(bio);
return ret;
}
/**
* bio_copy_user_iov - copy user data to bio
* @q: destination block queue
* @map_data: pointer to the rq_map_data holding pages (if necessary)
* @iov: the iovec.
* @iov_count: number of elements in the iovec
* @write_to_vm: bool indicating writing to pages or not
* @gfp_mask: memory allocation flags
*
* Prepares and returns a bio for indirect user io, bouncing data
* to/from kernel pages as necessary. Must be paired with
* call bio_uncopy_user() on io completion.
*/
struct bio *bio_copy_user_iov(struct request_queue *q,
struct rq_map_data *map_data,
struct sg_iovec *iov, int iov_count,
int write_to_vm, gfp_t gfp_mask)
{
struct bio_map_data *bmd;
struct bio_vec *bvec;
struct page *page;
struct bio *bio;
int i, ret;
int nr_pages = 0;
unsigned int len = 0;
unsigned int offset = map_data ? map_data->offset & ~PAGE_MASK : 0;
for (i = 0; i < iov_count; i++) {
unsigned long uaddr;
unsigned long end;
unsigned long start;
uaddr = (unsigned long)iov[i].iov_base;
end = (uaddr + iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
start = uaddr >> PAGE_SHIFT;
nr_pages += end - start;
len += iov[i].iov_len;
}
bmd = bio_alloc_map_data(nr_pages, iov_count, gfp_mask);
if (!bmd)
return ERR_PTR(-ENOMEM);
ret = -ENOMEM;
bio = bio_alloc(gfp_mask, nr_pages);
if (!bio)
goto out_bmd;
bio->bi_rw |= (!write_to_vm << BIO_RW);
ret = 0;
if (map_data) {
nr_pages = 1 << 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;
break;
}
page = map_data->pages[i / nr_pages];
page += (i % nr_pages);
i++;
} else {
page = alloc_page(q->bounce_gfp | gfp_mask);
if (!page) {
ret = -ENOMEM;
break;
}
}
if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
break;
len -= bytes;
offset = 0;
}
if (ret)
goto cleanup;
/*
* success
*/
if (!write_to_vm && (!map_data || !map_data->null_mapped)) {
ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 0);
if (ret)
goto cleanup;
}
bio_set_map_data(bmd, bio, iov, iov_count, map_data ? 0 : 1);
return bio;
cleanup:
if (!map_data)
bio_for_each_segment(bvec, bio, i)
__free_page(bvec->bv_page);
bio_put(bio);
out_bmd:
bio_free_map_data(bmd);
return ERR_PTR(ret);
}
/**
* bio_copy_user - copy user data to bio
* @q: destination block queue
* @map_data: pointer to the rq_map_data holding pages (if necessary)
* @uaddr: start of user address
* @len: length in bytes
* @write_to_vm: bool indicating writing to pages or not
* @gfp_mask: memory allocation flags
*
* Prepares and returns a bio for indirect user io, bouncing data
* to/from kernel pages as necessary. Must be paired with
* call bio_uncopy_user() on io completion.
*/
struct bio *bio_copy_user(struct request_queue *q, struct rq_map_data *map_data,
unsigned long uaddr, unsigned int len,
int write_to_vm, gfp_t gfp_mask)
{
struct sg_iovec iov;
iov.iov_base = (void __user *)uaddr;
iov.iov_len = len;
return bio_copy_user_iov(q, map_data, &iov, 1, write_to_vm, gfp_mask);
}
static struct bio *__bio_map_user_iov(struct request_queue *q,
struct block_device *bdev,
struct sg_iovec *iov, int iov_count,
int write_to_vm, gfp_t gfp_mask)
{
int i, j;
int nr_pages = 0;
struct page **pages;
struct bio *bio;
int cur_page = 0;
int ret, offset;
for (i = 0; i < iov_count; i++) {
unsigned long uaddr = (unsigned long)iov[i].iov_base;
unsigned long len = iov[i].iov_len;
unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
unsigned long start = uaddr >> PAGE_SHIFT;
nr_pages += end - start;
/*
* buffer must be aligned to at least hardsector size for now
*/
if (uaddr & queue_dma_alignment(q))
return ERR_PTR(-EINVAL);
}
if (!nr_pages)
return ERR_PTR(-EINVAL);
bio = bio_alloc(gfp_mask, nr_pages);
if (!bio)
return ERR_PTR(-ENOMEM);
ret = -ENOMEM;
pages = kcalloc(nr_pages, sizeof(struct page *), gfp_mask);
if (!pages)
goto out;
for (i = 0; i < iov_count; i++) {
unsigned long uaddr = (unsigned long)iov[i].iov_base;
unsigned long len = iov[i].iov_len;
unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
unsigned long start = uaddr >> PAGE_SHIFT;
const int local_nr_pages = end - start;
const int page_limit = cur_page + local_nr_pages;
ret = get_user_pages_fast(uaddr, local_nr_pages,
write_to_vm, &pages[cur_page]);
if (ret < local_nr_pages) {
ret = -EFAULT;
goto out_unmap;
}
offset = uaddr & ~PAGE_MASK;
for (j = cur_page; j < page_limit; j++) {
unsigned int bytes = PAGE_SIZE - offset;
if (len <= 0)
break;
if (bytes > len)
bytes = len;
/*
* sorry...
*/
if (bio_add_pc_page(q, bio, pages[j], bytes, offset) <
bytes)
break;
len -= bytes;
offset = 0;
}
cur_page = j;
/*
* release the pages we didn't map into the bio, if any
*/
while (j < page_limit)
page_cache_release(pages[j++]);
}
kfree(pages);
/*
* set data direction, and check if mapped pages need bouncing
*/
if (!write_to_vm)
bio->bi_rw |= (1 << BIO_RW);
bio->bi_bdev = bdev;
bio->bi_flags |= (1 << BIO_USER_MAPPED);