-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathblk-core.c
1819 lines (1548 loc) · 48.2 KB
/
blk-core.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
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 1994, Karl Keyte: Added support for disk statistics
* Elevator latency, (C) 2000 Andrea Arcangeli <[email protected]> SuSE
* Queue request tables / lock, selectable elevator, Jens Axboe <[email protected]>
* kernel-doc documentation started by NeilBrown <[email protected]>
* - July2000
* bio rewrite, highmem i/o, etc, Jens Axboe <[email protected]> - may 2001
*/
/*
* This handles all read/write requests to block devices
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/kernel_stat.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/fault-inject.h>
#include <linux/list_sort.h>
#include <linux/delay.h>
#include <linux/ratelimit.h>
#include <linux/pm_runtime.h>
#include <linux/blk-cgroup.h>
#include <linux/t10-pi.h>
#include <linux/debugfs.h>
#include <linux/bpf.h>
#include <linux/psi.h>
#include <linux/sched/sysctl.h>
#include <linux/blk-crypto.h>
#define CREATE_TRACE_POINTS
#include <trace/events/block.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-sched.h"
#include "blk-pm.h"
#include "blk-rq-qos.h"
struct dentry *blk_debugfs_root;
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_split);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_queue);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_getrq);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_issue);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_merge);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_requeue);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_complete);
DEFINE_IDA(blk_queue_ida);
/*
* For queue allocation
*/
struct kmem_cache *blk_requestq_cachep;
/*
* Controlling structure to kblockd
*/
static struct workqueue_struct *kblockd_workqueue;
/**
* blk_queue_flag_set - atomically set a queue flag
* @flag: flag to be set
* @q: request queue
*/
void blk_queue_flag_set(unsigned int flag, struct request_queue *q)
{
set_bit(flag, &q->queue_flags);
}
EXPORT_SYMBOL(blk_queue_flag_set);
/**
* blk_queue_flag_clear - atomically clear a queue flag
* @flag: flag to be cleared
* @q: request queue
*/
void blk_queue_flag_clear(unsigned int flag, struct request_queue *q)
{
clear_bit(flag, &q->queue_flags);
}
EXPORT_SYMBOL(blk_queue_flag_clear);
/**
* blk_queue_flag_test_and_set - atomically test and set a queue flag
* @flag: flag to be set
* @q: request queue
*
* Returns the previous value of @flag - 0 if the flag was not set and 1 if
* the flag was already set.
*/
bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q)
{
return test_and_set_bit(flag, &q->queue_flags);
}
EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set);
void blk_rq_init(struct request_queue *q, struct request *rq)
{
memset(rq, 0, sizeof(*rq));
INIT_LIST_HEAD(&rq->queuelist);
rq->q = q;
rq->__sector = (sector_t) -1;
INIT_HLIST_NODE(&rq->hash);
RB_CLEAR_NODE(&rq->rb_node);
rq->tag = BLK_MQ_NO_TAG;
rq->internal_tag = BLK_MQ_NO_TAG;
rq->start_time_ns = ktime_get_ns();
rq->part = NULL;
blk_crypto_rq_set_defaults(rq);
}
EXPORT_SYMBOL(blk_rq_init);
#define REQ_OP_NAME(name) [REQ_OP_##name] = #name
static const char *const blk_op_name[] = {
REQ_OP_NAME(READ),
REQ_OP_NAME(WRITE),
REQ_OP_NAME(FLUSH),
REQ_OP_NAME(DISCARD),
REQ_OP_NAME(SECURE_ERASE),
REQ_OP_NAME(ZONE_RESET),
REQ_OP_NAME(ZONE_RESET_ALL),
REQ_OP_NAME(ZONE_OPEN),
REQ_OP_NAME(ZONE_CLOSE),
REQ_OP_NAME(ZONE_FINISH),
REQ_OP_NAME(ZONE_APPEND),
REQ_OP_NAME(WRITE_SAME),
REQ_OP_NAME(WRITE_ZEROES),
REQ_OP_NAME(SCSI_IN),
REQ_OP_NAME(SCSI_OUT),
REQ_OP_NAME(DRV_IN),
REQ_OP_NAME(DRV_OUT),
};
#undef REQ_OP_NAME
/**
* blk_op_str - Return string XXX in the REQ_OP_XXX.
* @op: REQ_OP_XXX.
*
* Description: Centralize block layer function to convert REQ_OP_XXX into
* string format. Useful in the debugging and tracing bio or request. For
* invalid REQ_OP_XXX it returns string "UNKNOWN".
*/
inline const char *blk_op_str(unsigned int op)
{
const char *op_str = "UNKNOWN";
if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op])
op_str = blk_op_name[op];
return op_str;
}
EXPORT_SYMBOL_GPL(blk_op_str);
static const struct {
int errno;
const char *name;
} blk_errors[] = {
[BLK_STS_OK] = { 0, "" },
[BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" },
[BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" },
[BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" },
[BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" },
[BLK_STS_TARGET] = { -EREMOTEIO, "critical target" },
[BLK_STS_NEXUS] = { -EBADE, "critical nexus" },
[BLK_STS_MEDIUM] = { -ENODATA, "critical medium" },
[BLK_STS_PROTECTION] = { -EILSEQ, "protection" },
[BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" },
[BLK_STS_DEV_RESOURCE] = { -EBUSY, "device resource" },
[BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" },
/* device mapper special case, should not leak out: */
[BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" },
/* zone device specific errors */
[BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" },
[BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" },
/* everything else not covered above: */
[BLK_STS_IOERR] = { -EIO, "I/O" },
};
blk_status_t errno_to_blk_status(int errno)
{
int i;
for (i = 0; i < ARRAY_SIZE(blk_errors); i++) {
if (blk_errors[i].errno == errno)
return (__force blk_status_t)i;
}
return BLK_STS_IOERR;
}
EXPORT_SYMBOL_GPL(errno_to_blk_status);
int blk_status_to_errno(blk_status_t status)
{
int idx = (__force int)status;
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
return -EIO;
return blk_errors[idx].errno;
}
EXPORT_SYMBOL_GPL(blk_status_to_errno);
static void print_req_error(struct request *req, blk_status_t status,
const char *caller)
{
int idx = (__force int)status;
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
return;
printk_ratelimited(KERN_ERR
"%s: %s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x "
"phys_seg %u prio class %u\n",
caller, blk_errors[idx].name,
req->rq_disk ? req->rq_disk->disk_name : "?",
blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)),
req->cmd_flags & ~REQ_OP_MASK,
req->nr_phys_segments,
IOPRIO_PRIO_CLASS(req->ioprio));
}
static void req_bio_endio(struct request *rq, struct bio *bio,
unsigned int nbytes, blk_status_t error)
{
if (error)
bio->bi_status = error;
if (unlikely(rq->rq_flags & RQF_QUIET))
bio_set_flag(bio, BIO_QUIET);
bio_advance(bio, nbytes);
if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) {
/*
* Partial zone append completions cannot be supported as the
* BIO fragments may end up not being written sequentially.
*/
if (bio->bi_iter.bi_size)
bio->bi_status = BLK_STS_IOERR;
else
bio->bi_iter.bi_sector = rq->__sector;
}
/* don't actually finish bio if it's part of flush sequence */
if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
bio_endio(bio);
}
void blk_dump_rq_flags(struct request *rq, char *msg)
{
printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
rq->rq_disk ? rq->rq_disk->disk_name : "?",
(unsigned long long) rq->cmd_flags);
printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n",
(unsigned long long)blk_rq_pos(rq),
blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
printk(KERN_INFO " bio %p, biotail %p, len %u\n",
rq->bio, rq->biotail, blk_rq_bytes(rq));
}
EXPORT_SYMBOL(blk_dump_rq_flags);
/**
* blk_sync_queue - cancel any pending callbacks on a queue
* @q: the queue
*
* Description:
* The block layer may perform asynchronous callback activity
* on a queue, such as calling the unplug function after a timeout.
* A block device may call blk_sync_queue to ensure that any
* such activity is cancelled, thus allowing it to release resources
* that the callbacks might use. The caller must already have made sure
* that its ->submit_bio will not re-add plugging prior to calling
* this function.
*
* This function does not cancel any asynchronous activity arising
* out of elevator or throttling code. That would require elevator_exit()
* and blkcg_exit_queue() to be called with queue lock initialized.
*
*/
void blk_sync_queue(struct request_queue *q)
{
del_timer_sync(&q->timeout);
cancel_work_sync(&q->timeout_work);
}
EXPORT_SYMBOL(blk_sync_queue);
/**
* blk_set_pm_only - increment pm_only counter
* @q: request queue pointer
*/
void blk_set_pm_only(struct request_queue *q)
{
atomic_inc(&q->pm_only);
}
EXPORT_SYMBOL_GPL(blk_set_pm_only);
void blk_clear_pm_only(struct request_queue *q)
{
int pm_only;
pm_only = atomic_dec_return(&q->pm_only);
WARN_ON_ONCE(pm_only < 0);
if (pm_only == 0)
wake_up_all(&q->mq_freeze_wq);
}
EXPORT_SYMBOL_GPL(blk_clear_pm_only);
/**
* blk_put_queue - decrement the request_queue refcount
* @q: the request_queue structure to decrement the refcount for
*
* Decrements the refcount of the request_queue kobject. When this reaches 0
* we'll have blk_release_queue() called.
*
* Context: Any context, but the last reference must not be dropped from
* atomic context.
*/
void blk_put_queue(struct request_queue *q)
{
kobject_put(&q->kobj);
}
EXPORT_SYMBOL(blk_put_queue);
void blk_set_queue_dying(struct request_queue *q)
{
blk_queue_flag_set(QUEUE_FLAG_DYING, q);
/*
* When queue DYING flag is set, we need to block new req
* entering queue, so we call blk_freeze_queue_start() to
* prevent I/O from crossing blk_queue_enter().
*/
blk_freeze_queue_start(q);
if (queue_is_mq(q))
blk_mq_wake_waiters(q);
/* Make blk_queue_enter() reexamine the DYING flag. */
wake_up_all(&q->mq_freeze_wq);
}
EXPORT_SYMBOL_GPL(blk_set_queue_dying);
/**
* blk_cleanup_queue - shutdown a request queue
* @q: request queue to shutdown
*
* Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and
* put it. All future requests will be failed immediately with -ENODEV.
*
* Context: can sleep
*/
void blk_cleanup_queue(struct request_queue *q)
{
/* cannot be called from atomic context */
might_sleep();
WARN_ON_ONCE(blk_queue_registered(q));
/* mark @q DYING, no new request or merges will be allowed afterwards */
blk_set_queue_dying(q);
blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
/*
* Drain all requests queued before DYING marking. Set DEAD flag to
* prevent that blk_mq_run_hw_queues() accesses the hardware queues
* after draining finished.
*/
blk_freeze_queue(q);
rq_qos_exit(q);
blk_queue_flag_set(QUEUE_FLAG_DEAD, q);
/* for synchronous bio-based driver finish in-flight integrity i/o */
blk_flush_integrity();
/* @q won't process any more request, flush async actions */
del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer);
blk_sync_queue(q);
if (queue_is_mq(q))
blk_mq_exit_queue(q);
/*
* In theory, request pool of sched_tags belongs to request queue.
* However, the current implementation requires tag_set for freeing
* requests, so free the pool now.
*
* Queue has become frozen, there can't be any in-queue requests, so
* it is safe to free requests now.
*/
mutex_lock(&q->sysfs_lock);
if (q->elevator)
blk_mq_sched_free_requests(q);
mutex_unlock(&q->sysfs_lock);
percpu_ref_exit(&q->q_usage_counter);
/* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
}
EXPORT_SYMBOL(blk_cleanup_queue);
/**
* blk_queue_enter() - try to increase q->q_usage_counter
* @q: request queue pointer
* @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM
*/
int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
{
const bool pm = flags & BLK_MQ_REQ_PM;
while (true) {
bool success = false;
rcu_read_lock();
if (percpu_ref_tryget_live(&q->q_usage_counter)) {
/*
* The code that increments the pm_only counter is
* responsible for ensuring that that counter is
* globally visible before the queue is unfrozen.
*/
if (pm || !blk_queue_pm_only(q)) {
success = true;
} else {
percpu_ref_put(&q->q_usage_counter);
}
}
rcu_read_unlock();
if (success)
return 0;
if (flags & BLK_MQ_REQ_NOWAIT)
return -EBUSY;
/*
* read pair of barrier in blk_freeze_queue_start(),
* we need to order reading __PERCPU_REF_DEAD flag of
* .q_usage_counter and reading .mq_freeze_depth or
* queue dying flag, otherwise the following wait may
* never return if the two reads are reordered.
*/
smp_rmb();
wait_event(q->mq_freeze_wq,
(!q->mq_freeze_depth &&
(pm || (blk_pm_request_resume(q),
!blk_queue_pm_only(q)))) ||
blk_queue_dying(q));
if (blk_queue_dying(q))
return -ENODEV;
}
}
static inline int bio_queue_enter(struct bio *bio)
{
struct request_queue *q = bio->bi_disk->queue;
bool nowait = bio->bi_opf & REQ_NOWAIT;
int ret;
ret = blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0);
if (unlikely(ret)) {
if (nowait && !blk_queue_dying(q))
bio_wouldblock_error(bio);
else
bio_io_error(bio);
}
return ret;
}
void blk_queue_exit(struct request_queue *q)
{
percpu_ref_put(&q->q_usage_counter);
}
static void blk_queue_usage_counter_release(struct percpu_ref *ref)
{
struct request_queue *q =
container_of(ref, struct request_queue, q_usage_counter);
wake_up_all(&q->mq_freeze_wq);
}
static void blk_rq_timed_out_timer(struct timer_list *t)
{
struct request_queue *q = from_timer(q, t, timeout);
kblockd_schedule_work(&q->timeout_work);
}
static void blk_timeout_work(struct work_struct *work)
{
}
struct request_queue *blk_alloc_queue(int node_id)
{
struct request_queue *q;
int ret;
q = kmem_cache_alloc_node(blk_requestq_cachep,
GFP_KERNEL | __GFP_ZERO, node_id);
if (!q)
return NULL;
q->last_merge = NULL;
q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL);
if (q->id < 0)
goto fail_q;
ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
if (ret)
goto fail_id;
q->backing_dev_info = bdi_alloc(node_id);
if (!q->backing_dev_info)
goto fail_split;
q->stats = blk_alloc_queue_stats();
if (!q->stats)
goto fail_stats;
q->node = node_id;
atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
timer_setup(&q->backing_dev_info->laptop_mode_wb_timer,
laptop_mode_timer_fn, 0);
timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
INIT_WORK(&q->timeout_work, blk_timeout_work);
INIT_LIST_HEAD(&q->icq_list);
#ifdef CONFIG_BLK_CGROUP
INIT_LIST_HEAD(&q->blkg_list);
#endif
kobject_init(&q->kobj, &blk_queue_ktype);
mutex_init(&q->debugfs_mutex);
mutex_init(&q->sysfs_lock);
mutex_init(&q->sysfs_dir_lock);
spin_lock_init(&q->queue_lock);
init_waitqueue_head(&q->mq_freeze_wq);
mutex_init(&q->mq_freeze_lock);
/*
* Init percpu_ref in atomic mode so that it's faster to shutdown.
* See blk_register_queue() for details.
*/
if (percpu_ref_init(&q->q_usage_counter,
blk_queue_usage_counter_release,
PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
goto fail_bdi;
if (blkcg_init_queue(q))
goto fail_ref;
blk_queue_dma_alignment(q, 511);
blk_set_default_limits(&q->limits);
q->nr_requests = BLKDEV_MAX_RQ;
return q;
fail_ref:
percpu_ref_exit(&q->q_usage_counter);
fail_bdi:
blk_free_queue_stats(q->stats);
fail_stats:
bdi_put(q->backing_dev_info);
fail_split:
bioset_exit(&q->bio_split);
fail_id:
ida_simple_remove(&blk_queue_ida, q->id);
fail_q:
kmem_cache_free(blk_requestq_cachep, q);
return NULL;
}
EXPORT_SYMBOL(blk_alloc_queue);
/**
* blk_get_queue - increment the request_queue refcount
* @q: the request_queue structure to increment the refcount for
*
* Increment the refcount of the request_queue kobject.
*
* Context: Any context.
*/
bool blk_get_queue(struct request_queue *q)
{
if (likely(!blk_queue_dying(q))) {
__blk_get_queue(q);
return true;
}
return false;
}
EXPORT_SYMBOL(blk_get_queue);
/**
* blk_get_request - allocate a request
* @q: request queue to allocate a request for
* @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC.
* @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT.
*/
struct request *blk_get_request(struct request_queue *q, unsigned int op,
blk_mq_req_flags_t flags)
{
struct request *req;
WARN_ON_ONCE(op & REQ_NOWAIT);
WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM));
req = blk_mq_alloc_request(q, op, flags);
if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
q->mq_ops->initialize_rq_fn(req);
return req;
}
EXPORT_SYMBOL(blk_get_request);
void blk_put_request(struct request *req)
{
blk_mq_free_request(req);
}
EXPORT_SYMBOL(blk_put_request);
static void handle_bad_sector(struct bio *bio, sector_t maxsector)
{
char b[BDEVNAME_SIZE];
pr_info_ratelimited("attempt to access beyond end of device\n"
"%s: rw=%d, want=%llu, limit=%llu\n",
bio_devname(bio, b), bio->bi_opf,
bio_end_sector(bio), maxsector);
}
#ifdef CONFIG_FAIL_MAKE_REQUEST
static DECLARE_FAULT_ATTR(fail_make_request);
static int __init setup_fail_make_request(char *str)
{
return setup_fault_attr(&fail_make_request, str);
}
__setup("fail_make_request=", setup_fail_make_request);
static bool should_fail_request(struct hd_struct *part, unsigned int bytes)
{
return part->make_it_fail && should_fail(&fail_make_request, bytes);
}
static int __init fail_make_request_debugfs(void)
{
struct dentry *dir = fault_create_debugfs_attr("fail_make_request",
NULL, &fail_make_request);
return PTR_ERR_OR_ZERO(dir);
}
late_initcall(fail_make_request_debugfs);
#else /* CONFIG_FAIL_MAKE_REQUEST */
static inline bool should_fail_request(struct hd_struct *part,
unsigned int bytes)
{
return false;
}
#endif /* CONFIG_FAIL_MAKE_REQUEST */
static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
{
const int op = bio_op(bio);
if (part->policy && op_is_write(op)) {
char b[BDEVNAME_SIZE];
if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
return false;
WARN_ONCE(1,
"Trying to write to read-only block-device %s (partno %d)\n",
bio_devname(bio, b), part->partno);
/* Older lvm-tools actually trigger this */
return false;
}
return false;
}
static noinline int should_fail_bio(struct bio *bio)
{
if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
return -EIO;
return 0;
}
ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO);
/*
* Check whether this bio extends beyond the end of the device or partition.
* This may well happen - the kernel calls bread() without checking the size of
* the device, e.g., when mounting a file system.
*/
static inline int bio_check_eod(struct bio *bio, sector_t maxsector)
{
unsigned int nr_sectors = bio_sectors(bio);
if (nr_sectors && maxsector &&
(nr_sectors > maxsector ||
bio->bi_iter.bi_sector > maxsector - nr_sectors)) {
handle_bad_sector(bio, maxsector);
return -EIO;
}
return 0;
}
/*
* Remap block n of partition p to block n+start(p) of the disk.
*/
static inline int blk_partition_remap(struct bio *bio)
{
struct hd_struct *p;
int ret = -EIO;
rcu_read_lock();
p = __disk_get_part(bio->bi_disk, bio->bi_partno);
if (unlikely(!p))
goto out;
if (unlikely(should_fail_request(p, bio->bi_iter.bi_size)))
goto out;
if (unlikely(bio_check_ro(bio, p)))
goto out;
if (bio_sectors(bio)) {
if (bio_check_eod(bio, part_nr_sects_read(p)))
goto out;
bio->bi_iter.bi_sector += p->start_sect;
trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
bio->bi_iter.bi_sector - p->start_sect);
}
bio->bi_partno = 0;
ret = 0;
out:
rcu_read_unlock();
return ret;
}
/*
* Check write append to a zoned block device.
*/
static inline blk_status_t blk_check_zone_append(struct request_queue *q,
struct bio *bio)
{
sector_t pos = bio->bi_iter.bi_sector;
int nr_sectors = bio_sectors(bio);
/* Only applicable to zoned block devices */
if (!blk_queue_is_zoned(q))
return BLK_STS_NOTSUPP;
/* The bio sector must point to the start of a sequential zone */
if (pos & (blk_queue_zone_sectors(q) - 1) ||
!blk_queue_zone_is_seq(q, pos))
return BLK_STS_IOERR;
/*
* Not allowed to cross zone boundaries. Otherwise, the BIO will be
* split and could result in non-contiguous sectors being written in
* different zones.
*/
if (nr_sectors > q->limits.chunk_sectors)
return BLK_STS_IOERR;
/* Make sure the BIO is small enough and will not get split */
if (nr_sectors > q->limits.max_zone_append_sectors)
return BLK_STS_IOERR;
bio->bi_opf |= REQ_NOMERGE;
return BLK_STS_OK;
}
static noinline_for_stack bool submit_bio_checks(struct bio *bio)
{
struct request_queue *q = bio->bi_disk->queue;
blk_status_t status = BLK_STS_IOERR;
struct blk_plug *plug;
might_sleep();
plug = blk_mq_plug(q, bio);
if (plug && plug->nowait)
bio->bi_opf |= REQ_NOWAIT;
/*
* For a REQ_NOWAIT based request, return -EOPNOTSUPP
* if queue does not support NOWAIT.
*/
if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q))
goto not_supported;
if (should_fail_bio(bio))
goto end_io;
if (bio->bi_partno) {
if (unlikely(blk_partition_remap(bio)))
goto end_io;
} else {
if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0)))
goto end_io;
if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk))))
goto end_io;
}
/*
* Filter flush bio's early so that bio based drivers without flush
* support don't have to worry about them.
*/
if (op_is_flush(bio->bi_opf) &&
!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
if (!bio_sectors(bio)) {
status = BLK_STS_OK;
goto end_io;
}
}
if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
bio->bi_opf &= ~REQ_HIPRI;
switch (bio_op(bio)) {
case REQ_OP_DISCARD:
if (!blk_queue_discard(q))
goto not_supported;
break;
case REQ_OP_SECURE_ERASE:
if (!blk_queue_secure_erase(q))
goto not_supported;
break;
case REQ_OP_WRITE_SAME:
if (!q->limits.max_write_same_sectors)
goto not_supported;
break;
case REQ_OP_ZONE_APPEND:
status = blk_check_zone_append(q, bio);
if (status != BLK_STS_OK)
goto end_io;
break;
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_OPEN:
case REQ_OP_ZONE_CLOSE:
case REQ_OP_ZONE_FINISH:
if (!blk_queue_is_zoned(q))
goto not_supported;
break;
case REQ_OP_ZONE_RESET_ALL:
if (!blk_queue_is_zoned(q) || !blk_queue_zone_resetall(q))
goto not_supported;
break;
case REQ_OP_WRITE_ZEROES:
if (!q->limits.max_write_zeroes_sectors)
goto not_supported;
break;
default:
break;
}
/*
* Various block parts want %current->io_context, so allocate it up
* front rather than dealing with lots of pain to allocate it only
* where needed. This may fail and the block layer knows how to live
* with it.
*/
if (unlikely(!current->io_context))
create_task_io_context(current, GFP_ATOMIC, q->node);
if (blk_throtl_bio(bio))
return false;
blk_cgroup_bio_start(bio);
blkcg_bio_issue_init(bio);
if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
trace_block_bio_queue(q, bio);
/* Now that enqueuing has been traced, we need to trace
* completion as well.
*/
bio_set_flag(bio, BIO_TRACE_COMPLETION);
}
return true;
not_supported:
status = BLK_STS_NOTSUPP;
end_io:
bio->bi_status = status;
bio_endio(bio);
return false;
}
static blk_qc_t __submit_bio(struct bio *bio)
{
struct gendisk *disk = bio->bi_disk;
blk_qc_t ret = BLK_QC_T_NONE;
if (blk_crypto_bio_prep(&bio)) {
if (!disk->fops->submit_bio)
return blk_mq_submit_bio(bio);
ret = disk->fops->submit_bio(bio);
}
blk_queue_exit(disk->queue);
return ret;
}
/*
* The loop in this function may be a bit non-obvious, and so deserves some
* explanation:
*
* - Before entering the loop, bio->bi_next is NULL (as all callers ensure
* that), so we have a list with a single bio.
* - We pretend that we have just taken it off a longer list, so we assign
* bio_list to a pointer to the bio_list_on_stack, thus initialising the
* bio_list of new bios to be added. ->submit_bio() may indeed add some more
* bios through a recursive call to submit_bio_noacct. If it did, we find a
* non-NULL value in bio_list and re-enter the loop from the top.
* - In this case we really did just take the bio of the top of the list (no
* pretending) and so remove it from bio_list, and call into ->submit_bio()
* again.
*
* bio_list_on_stack[0] contains bios submitted by the current ->submit_bio.
* bio_list_on_stack[1] contains bios that were submitted before the current
* ->submit_bio_bio, but that haven't been processed yet.
*/
static blk_qc_t __submit_bio_noacct(struct bio *bio)
{
struct bio_list bio_list_on_stack[2];
blk_qc_t ret = BLK_QC_T_NONE;
BUG_ON(bio->bi_next);
bio_list_init(&bio_list_on_stack[0]);
current->bio_list = bio_list_on_stack;
do {
struct request_queue *q = bio->bi_disk->queue;
struct bio_list lower, same;
if (unlikely(bio_queue_enter(bio) != 0))
continue;
/*
* Create a fresh bio_list for all subordinate requests.
*/
bio_list_on_stack[1] = bio_list_on_stack[0];
bio_list_init(&bio_list_on_stack[0]);
ret = __submit_bio(bio);
/*
* Sort new bios into those for a lower level and those for the
* same level.
*/
bio_list_init(&lower);
bio_list_init(&same);
while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
if (q == bio->bi_disk->queue)
bio_list_add(&same, bio);
else
bio_list_add(&lower, bio);
/*
* Now assemble so we handle the lowest level first.