forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
bio.c
2052 lines (1738 loc) · 49.5 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/uio.h>
#include <linux/iocontext.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mempool.h>
#include <linux/workqueue.h>
#include <linux/cgroup.h>
#include <scsi/sg.h> /* for struct sg_iovec */
#include <trace/events/block.h>
/*
* 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
/*
* 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) }
static 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;
EXPORT_SYMBOL(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, *new_bio_slabs;
unsigned int new_bio_slab_max;
unsigned int i, entry = -1;
mutex_lock(&bio_slab_lock);
i = 0;
while (i < bio_slab_nr) {
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) {
new_bio_slab_max = bio_slab_max << 1;
new_bio_slabs = krealloc(bio_slabs,
new_bio_slab_max * sizeof(struct bio_slab),
GFP_KERNEL);
if (!new_bio_slabs)
goto out_unlock;
bio_slab_max = new_bio_slab_max;
bio_slabs = new_bio_slabs;
}
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;
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(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
{
BIO_BUG_ON(idx >= BIOVEC_NR_POOLS);
if (idx == BIOVEC_MAX_IDX)
mempool_free(bv, pool);
else {
struct biovec_slab *bvs = bvec_slabs + idx;
kmem_cache_free(bvs->slab, bv);
}
}
struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
mempool_t *pool)
{
struct bio_vec *bvl;
/*
* 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(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;
}
static void __bio_free(struct bio *bio)
{
bio_disassociate_task(bio);
if (bio_integrity(bio))
bio_integrity_free(bio);
}
static void bio_free(struct bio *bio)
{
struct bio_set *bs = bio->bi_pool;
void *p;
__bio_free(bio);
if (bs) {
if (bio_flagged(bio, BIO_OWNS_VEC))
bvec_free(bs->bvec_pool, bio->bi_io_vec, BIO_POOL_IDX(bio));
/*
* If we have front padding, adjust the bio pointer before freeing
*/
p = bio;
p -= bs->front_pad;
mempool_free(p, bs->bio_pool);
} else {
/* Bio was allocated by bio_kmalloc() */
kfree(bio);
}
}
void bio_init(struct bio *bio)
{
memset(bio, 0, sizeof(*bio));
bio->bi_flags = 1 << BIO_UPTODATE;
atomic_set(&bio->bi_remaining, 1);
atomic_set(&bio->bi_cnt, 1);
}
EXPORT_SYMBOL(bio_init);
/**
* bio_reset - reinitialize a bio
* @bio: bio to reset
*
* Description:
* After calling bio_reset(), @bio will be in the same state as a freshly
* allocated bio returned bio bio_alloc_bioset() - the only fields that are
* preserved are the ones that are initialized by bio_alloc_bioset(). See
* comment in struct bio.
*/
void bio_reset(struct bio *bio)
{
unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS);
__bio_free(bio);
memset(bio, 0, BIO_RESET_BYTES);
bio->bi_flags = flags|(1 << BIO_UPTODATE);
atomic_set(&bio->bi_remaining, 1);
}
EXPORT_SYMBOL(bio_reset);
static void bio_chain_endio(struct bio *bio, int error)
{
bio_endio(bio->bi_private, error);
bio_put(bio);
}
/**
* bio_chain - chain bio completions
* @bio: the target bio
* @parent: the @bio's parent bio
*
* The caller won't have a bi_end_io called when @bio completes - instead,
* @parent's bi_end_io won't be called until both @parent and @bio have
* completed; the chained bio will also be freed when it completes.
*
* The caller must not set bi_private or bi_end_io in @bio.
*/
void bio_chain(struct bio *bio, struct bio *parent)
{
BUG_ON(bio->bi_private || bio->bi_end_io);
bio->bi_private = parent;
bio->bi_end_io = bio_chain_endio;
atomic_inc(&parent->bi_remaining);
}
EXPORT_SYMBOL(bio_chain);
static void bio_alloc_rescue(struct work_struct *work)
{
struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
struct bio *bio;
while (1) {
spin_lock(&bs->rescue_lock);
bio = bio_list_pop(&bs->rescue_list);
spin_unlock(&bs->rescue_lock);
if (!bio)
break;
generic_make_request(bio);
}
}
static void punt_bios_to_rescuer(struct bio_set *bs)
{
struct bio_list punt, nopunt;
struct bio *bio;
/*
* In order to guarantee forward progress we must punt only bios that
* were allocated from this bio_set; otherwise, if there was a bio on
* there for a stacking driver higher up in the stack, processing it
* could require allocating bios from this bio_set, and doing that from
* our own rescuer would be bad.
*
* Since bio lists are singly linked, pop them all instead of trying to
* remove from the middle of the list:
*/
bio_list_init(&punt);
bio_list_init(&nopunt);
while ((bio = bio_list_pop(current->bio_list)))
bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
*current->bio_list = nopunt;
spin_lock(&bs->rescue_lock);
bio_list_merge(&bs->rescue_list, &punt);
spin_unlock(&bs->rescue_lock);
queue_work(bs->rescue_workqueue, &bs->rescue_work);
}
/**
* 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.
*
* Description:
* If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
* backed by the @bs's mempool.
*
* When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be
* able to allocate a bio. This is due to the mempool guarantees. To make this
* work, callers must never allocate more than 1 bio at a time from this pool.
* Callers that need to allocate more than 1 bio must always submit the
* previously allocated bio for IO before attempting to allocate a new one.
* Failure to do so can cause deadlocks under memory pressure.
*
* Note that when running under generic_make_request() (i.e. any block
* driver), bios are not submitted until after you return - see the code in
* generic_make_request() that converts recursion into iteration, to prevent
* stack overflows.
*
* This would normally mean allocating multiple bios under
* generic_make_request() would be susceptible to deadlocks, but we have
* deadlock avoidance code that resubmits any blocked bios from a rescuer
* thread.
*
* However, we do not guarantee forward progress for allocations from other
* mempools. Doing multiple allocations from the same mempool under
* generic_make_request() should be avoided - instead, use bio_set's front_pad
* for per bio allocations.
*
* RETURNS:
* Pointer to new bio on success, NULL on failure.
*/
struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
{
gfp_t saved_gfp = gfp_mask;
unsigned front_pad;
unsigned inline_vecs;
unsigned long idx = BIO_POOL_NONE;
struct bio_vec *bvl = NULL;
struct bio *bio;
void *p;
if (!bs) {
if (nr_iovecs > UIO_MAXIOV)
return NULL;
p = kmalloc(sizeof(struct bio) +
nr_iovecs * sizeof(struct bio_vec),
gfp_mask);
front_pad = 0;
inline_vecs = nr_iovecs;
} else {
/*
* generic_make_request() converts recursion to iteration; this
* means if we're running beneath it, any bios we allocate and
* submit will not be submitted (and thus freed) until after we
* return.
*
* This exposes us to a potential deadlock if we allocate
* multiple bios from the same bio_set() while running
* underneath generic_make_request(). If we were to allocate
* multiple bios (say a stacking block driver that was splitting
* bios), we would deadlock if we exhausted the mempool's
* reserve.
*
* We solve this, and guarantee forward progress, with a rescuer
* workqueue per bio_set. If we go to allocate and there are
* bios on current->bio_list, we first try the allocation
* without __GFP_WAIT; if that fails, we punt those bios we
* would be blocking to the rescuer workqueue before we retry
* with the original gfp_flags.
*/
if (current->bio_list && !bio_list_empty(current->bio_list))
gfp_mask &= ~__GFP_WAIT;
p = mempool_alloc(bs->bio_pool, gfp_mask);
if (!p && gfp_mask != saved_gfp) {
punt_bios_to_rescuer(bs);
gfp_mask = saved_gfp;
p = mempool_alloc(bs->bio_pool, gfp_mask);
}
front_pad = bs->front_pad;
inline_vecs = BIO_INLINE_VECS;
}
if (unlikely(!p))
return NULL;
bio = p + front_pad;
bio_init(bio);
if (nr_iovecs > inline_vecs) {
bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
if (!bvl && gfp_mask != saved_gfp) {
punt_bios_to_rescuer(bs);
gfp_mask = saved_gfp;
bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
}
if (unlikely(!bvl))
goto err_free;
bio->bi_flags |= 1 << BIO_OWNS_VEC;
} else if (nr_iovecs) {
bvl = bio->bi_inline_vecs;
}
bio->bi_pool = bs;
bio->bi_flags |= idx << BIO_POOL_OFFSET;
bio->bi_max_vecs = nr_iovecs;
bio->bi_io_vec = bvl;
return bio;
err_free:
mempool_free(p, bs->bio_pool);
return NULL;
}
EXPORT_SYMBOL(bio_alloc_bioset);
void zero_fill_bio(struct bio *bio)
{
unsigned long flags;
struct bio_vec bv;
struct bvec_iter iter;
bio_for_each_segment(bv, bio, iter) {
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, bio_get or bio_clone. 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_free(bio);
}
EXPORT_SYMBOL(bio_put);
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;
}
EXPORT_SYMBOL(bio_phys_segments);
/**
* __bio_clone_fast - clone a bio that shares the original bio's biovec
* @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.
*
* Caller must ensure that @bio_src is not freed before @bio.
*/
void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
{
BUG_ON(bio->bi_pool && BIO_POOL_IDX(bio) != BIO_POOL_NONE);
/*
* 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_bdev = bio_src->bi_bdev;
bio->bi_flags |= 1 << BIO_CLONED;
bio->bi_rw = bio_src->bi_rw;
bio->bi_iter = bio_src->bi_iter;
bio->bi_io_vec = bio_src->bi_io_vec;
}
EXPORT_SYMBOL(__bio_clone_fast);
/**
* bio_clone_fast - clone a bio that shares the original bio's biovec
* @bio: bio to clone
* @gfp_mask: allocation priority
* @bs: bio_set to allocate from
*
* Like __bio_clone_fast, only also allocates the returned bio
*/
struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
{
struct bio *b;
b = bio_alloc_bioset(gfp_mask, 0, bs);
if (!b)
return NULL;
__bio_clone_fast(b, bio);
if (bio_integrity(bio)) {
int ret;
ret = bio_integrity_clone(b, bio, gfp_mask);
if (ret < 0) {
bio_put(b);
return NULL;
}
}
return b;
}
EXPORT_SYMBOL(bio_clone_fast);
/**
* bio_clone_bioset - clone a bio
* @bio_src: bio to clone
* @gfp_mask: allocation priority
* @bs: bio_set to allocate from
*
* Clone bio. Caller will own the returned bio, but not the actual data it
* points to. Reference count of returned bio will be one.
*/
struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
struct bio_set *bs)
{
struct bvec_iter iter;
struct bio_vec bv;
struct bio *bio;
/*
* Pre immutable biovecs, __bio_clone() used to just do a memcpy from
* bio_src->bi_io_vec to bio->bi_io_vec.
*
* We can't do that anymore, because:
*
* - The point of cloning the biovec is to produce a bio with a biovec
* the caller can modify: bi_idx and bi_bvec_done should be 0.
*
* - The original bio could've had more than BIO_MAX_PAGES biovecs; if
* we tried to clone the whole thing bio_alloc_bioset() would fail.
* But the clone should succeed as long as the number of biovecs we
* actually need to allocate is fewer than BIO_MAX_PAGES.
*
* - Lastly, bi_vcnt should not be looked at or relied upon by code
* that does not own the bio - reason being drivers don't use it for
* iterating over the biovec anymore, so expecting it to be kept up
* to date (i.e. for clones that share the parent biovec) is just
* asking for trouble and would force extra work on
* __bio_clone_fast() anyways.
*/
bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
if (!bio)
return NULL;
bio->bi_bdev = bio_src->bi_bdev;
bio->bi_rw = bio_src->bi_rw;
bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector;
bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
if (bio->bi_rw & REQ_DISCARD)
goto integrity_clone;
if (bio->bi_rw & REQ_WRITE_SAME) {
bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
goto integrity_clone;
}
bio_for_each_segment(bv, bio_src, iter)
bio->bi_io_vec[bio->bi_vcnt++] = bv;
integrity_clone:
if (bio_integrity(bio_src)) {
int ret;
ret = bio_integrity_clone(bio, bio_src, gfp_mask);
if (ret < 0) {
bio_put(bio);
return NULL;
}
}
return bio;
}
EXPORT_SYMBOL(bio_clone_bioset);
/**
* 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 = min_t(unsigned,
queue_max_segments(q),
queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1);
return min_t(unsigned, nr_pages, BIO_MAX_PAGES);
}
EXPORT_SYMBOL(bio_get_nr_vecs);
static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
*page, unsigned int len, unsigned int offset,
unsigned int 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_iter.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) {
unsigned int prev_bv_len = prev->bv_len;
prev->bv_len += len;
if (q->merge_bvec_fn) {
struct bvec_merge_data bvm = {
/* prev_bvec is already charged in
bi_size, discharge it in order to
simulate merging updated prev_bvec
as new bvec. */
.bi_bdev = bio->bi_bdev,
.bi_sector = bio->bi_iter.bi_sector,
.bi_size = bio->bi_iter.bi_size -
prev_bv_len,
.bi_rw = bio->bi_rw,
};
if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) {
prev->bv_len -= len;
return 0;
}
}
goto done;
}
/*
* If the queue doesn't support SG gaps and adding this
* offset would create a gap, disallow it.
*/
if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) &&
bvec_gap_to_prev(prev, offset))
return 0;
}
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 >= queue_max_segments(q)) {
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_iter.bi_sector,
.bi_size = bio->bi_iter.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) < bvec->bv_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_iter.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 up to 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,
queue_max_hw_sectors(q));
}
EXPORT_SYMBOL(bio_add_pc_page);
/**
* 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 up to 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);
unsigned int max_sectors;
max_sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
if ((max_sectors < (len >> 9)) && !bio->bi_iter.bi_size)
max_sectors = len >> 9;
return __bio_add_page(q, bio, page, len, offset, max_sectors);
}
EXPORT_SYMBOL(bio_add_page);
struct submit_bio_ret {
struct completion event;
int error;
};
static void submit_bio_wait_endio(struct bio *bio, int error)
{
struct submit_bio_ret *ret = bio->bi_private;
ret->error = error;
complete(&ret->event);
}
/**
* submit_bio_wait - submit a bio, and wait until it completes
* @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
* @bio: The &struct bio which describes the I/O
*
* Simple wrapper around submit_bio(). Returns 0 on success, or the error from
* bio_endio() on failure.
*/
int submit_bio_wait(int rw, struct bio *bio)
{
struct submit_bio_ret ret;
rw |= REQ_SYNC;
init_completion(&ret.event);
bio->bi_private = &ret;
bio->bi_end_io = submit_bio_wait_endio;
submit_bio(rw, bio);
wait_for_completion(&ret.event);
return ret.error;
}
EXPORT_SYMBOL(submit_bio_wait);
/**
* bio_advance - increment/complete a bio by some number of bytes
* @bio: bio to advance
* @bytes: number of bytes to complete
*
* This updates bi_sector, bi_size and bi_idx; if the number of bytes to
* complete doesn't align with a bvec boundary, then bv_len and bv_offset will
* be updated on the last bvec as well.
*
* @bio will then represent the remaining, uncompleted portion of the io.
*/
void bio_advance(struct bio *bio, unsigned bytes)
{
if (bio_integrity(bio))
bio_integrity_advance(bio, bytes);
bio_advance_iter(bio, &bio->bi_iter, bytes);
}
EXPORT_SYMBOL(bio_advance);
/**
* bio_alloc_pages - allocates a single page for each bvec in a bio
* @bio: bio to allocate pages for
* @gfp_mask: flags for allocation
*
* Allocates pages up to @bio->bi_vcnt.
*
* Returns 0 on success, -ENOMEM on failure. On failure, any allocated pages are
* freed.
*/
int bio_alloc_pages(struct bio *bio, gfp_t gfp_mask)
{
int i;
struct bio_vec *bv;
bio_for_each_segment_all(bv, bio, i) {
bv->bv_page = alloc_page(gfp_mask);
if (!bv->bv_page) {
while (--bv >= bio->bi_io_vec)
__free_page(bv->bv_page);
return -ENOMEM;
}
}
return 0;
}
EXPORT_SYMBOL(bio_alloc_pages);
/**
* bio_copy_data - copy contents of data buffers from one chain of bios to
* another
* @src: source bio list
* @dst: destination bio list
*
* If @src and @dst are single bios, bi_next must be NULL - otherwise, treats
* @src and @dst as linked lists of bios.
*
* Stops when it reaches the end of either @src or @dst - that is, copies
* min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios).
*/
void bio_copy_data(struct bio *dst, struct bio *src)
{
struct bvec_iter src_iter, dst_iter;
struct bio_vec src_bv, dst_bv;
void *src_p, *dst_p;
unsigned bytes;
src_iter = src->bi_iter;
dst_iter = dst->bi_iter;
while (1) {
if (!src_iter.bi_size) {
src = src->bi_next;
if (!src)
break;
src_iter = src->bi_iter;
}
if (!dst_iter.bi_size) {
dst = dst->bi_next;
if (!dst)
break;
dst_iter = dst->bi_iter;
}
src_bv = bio_iter_iovec(src, src_iter);
dst_bv = bio_iter_iovec(dst, dst_iter);
bytes = min(src_bv.bv_len, dst_bv.bv_len);
src_p = kmap_atomic(src_bv.bv_page);
dst_p = kmap_atomic(dst_bv.bv_page);