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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
|
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BLK_MQ_H
#define BLK_MQ_H
#include <linux/blkdev.h>
#include <linux/sbitmap.h>
#include <linux/srcu.h>
#include <linux/lockdep.h>
#include <linux/scatterlist.h>
struct blk_mq_tags;
struct blk_flush_queue;
#define BLKDEV_MIN_RQ 4
#define BLKDEV_MAX_RQ 128 /* Default maximum */
typedef void (rq_end_io_fn)(struct request *, blk_status_t);
/*
* request flags */
typedef __u32 __bitwise req_flags_t;
/* drive already may have started this one */
#define RQF_STARTED ((__force req_flags_t)(1 << 1))
/* may not be passed by ioscheduler */
#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3))
/* request for flush sequence */
#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4))
/* merge of different types, fail separately */
#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5))
/* track inflight for MQ */
#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6))
/* don't call prep for this one */
#define RQF_DONTPREP ((__force req_flags_t)(1 << 7))
/* vaguely specified driver internal error. Ignored by the block layer */
#define RQF_FAILED ((__force req_flags_t)(1 << 10))
/* don't warn about errors */
#define RQF_QUIET ((__force req_flags_t)(1 << 11))
/* elevator private data attached */
#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12))
/* account into disk and partition IO statistics */
#define RQF_IO_STAT ((__force req_flags_t)(1 << 13))
/* runtime pm request */
#define RQF_PM ((__force req_flags_t)(1 << 15))
/* on IO scheduler merge hash */
#define RQF_HASHED ((__force req_flags_t)(1 << 16))
/* track IO completion time */
#define RQF_STATS ((__force req_flags_t)(1 << 17))
/* Look at ->special_vec for the actual data payload instead of the
bio chain. */
#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18))
/* The per-zone write lock is held for this request */
#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19))
/* already slept for hybrid poll */
#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20))
/* ->timeout has been called, don't expire again */
#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21))
/* flags that prevent us from merging requests: */
#define RQF_NOMERGE_FLAGS \
(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
enum mq_rq_state {
MQ_RQ_IDLE = 0,
MQ_RQ_IN_FLIGHT = 1,
MQ_RQ_COMPLETE = 2,
};
/*
* Try to put the fields that are referenced together in the same cacheline.
*
* If you modify this structure, make sure to update blk_rq_init() and
* especially blk_mq_rq_ctx_init() to take care of the added fields.
*/
struct request {
struct request_queue *q;
struct blk_mq_ctx *mq_ctx;
struct blk_mq_hw_ctx *mq_hctx;
unsigned int cmd_flags; /* op and common flags */
req_flags_t rq_flags;
int tag;
int internal_tag;
/* the following two fields are internal, NEVER access directly */
unsigned int __data_len; /* total data len */
sector_t __sector; /* sector cursor */
struct bio *bio;
struct bio *biotail;
struct list_head queuelist;
/*
* The hash is used inside the scheduler, and killed once the
* request reaches the dispatch list. The ipi_list is only used
* to queue the request for softirq completion, which is long
* after the request has been unhashed (and even removed from
* the dispatch list).
*/
union {
struct hlist_node hash; /* merge hash */
struct llist_node ipi_list;
};
/*
* The rb_node is only used inside the io scheduler, requests
* are pruned when moved to the dispatch queue. So let the
* completion_data share space with the rb_node.
*/
union {
struct rb_node rb_node; /* sort/lookup */
struct bio_vec special_vec;
void *completion_data;
int error_count; /* for legacy drivers, don't use */
};
/*
* Three pointers are available for the IO schedulers, if they need
* more they have to dynamically allocate it. Flush requests are
* never put on the IO scheduler. So let the flush fields share
* space with the elevator data.
*/
union {
struct {
struct io_cq *icq;
void *priv[2];
} elv;
struct {
unsigned int seq;
struct list_head list;
rq_end_io_fn *saved_end_io;
} flush;
};
struct gendisk *rq_disk;
struct block_device *part;
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
/* Time that the first bio started allocating this request. */
u64 alloc_time_ns;
#endif
/* Time that this request was allocated for this IO. */
u64 start_time_ns;
/* Time that I/O was submitted to the device. */
u64 io_start_time_ns;
#ifdef CONFIG_BLK_WBT
unsigned short wbt_flags;
#endif
/*
* rq sectors used for blk stats. It has the same value
* with blk_rq_sectors(rq), except that it never be zeroed
* by completion.
*/
unsigned short stats_sectors;
/*
* Number of scatter-gather DMA addr+len pairs after
* physical address coalescing is performed.
*/
unsigned short nr_phys_segments;
#ifdef CONFIG_BLK_DEV_INTEGRITY
unsigned short nr_integrity_segments;
#endif
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
struct bio_crypt_ctx *crypt_ctx;
struct blk_ksm_keyslot *crypt_keyslot;
#endif
unsigned short write_hint;
unsigned short ioprio;
enum mq_rq_state state;
refcount_t ref;
unsigned int timeout;
unsigned long deadline;
union {
struct __call_single_data csd;
u64 fifo_time;
};
/*
* completion callback.
*/
rq_end_io_fn *end_io;
void *end_io_data;
};
#define req_op(req) \
((req)->cmd_flags & REQ_OP_MASK)
static inline bool blk_rq_is_passthrough(struct request *rq)
{
return blk_op_is_passthrough(req_op(rq));
}
static inline unsigned short req_get_ioprio(struct request *req)
{
return req->ioprio;
}
#define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ)
#define rq_dma_dir(rq) \
(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
enum blk_eh_timer_return {
BLK_EH_DONE, /* drivers has completed the command */
BLK_EH_RESET_TIMER, /* reset timer and try again */
};
#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
/**
* struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
* block device
*/
struct blk_mq_hw_ctx {
struct {
/** @lock: Protects the dispatch list. */
spinlock_t lock;
/**
* @dispatch: Used for requests that are ready to be
* dispatched to the hardware but for some reason (e.g. lack of
* resources) could not be sent to the hardware. As soon as the
* driver can send new requests, requests at this list will
* be sent first for a fairer dispatch.
*/
struct list_head dispatch;
/**
* @state: BLK_MQ_S_* flags. Defines the state of the hw
* queue (active, scheduled to restart, stopped).
*/
unsigned long state;
} ____cacheline_aligned_in_smp;
/**
* @run_work: Used for scheduling a hardware queue run at a later time.
*/
struct delayed_work run_work;
/** @cpumask: Map of available CPUs where this hctx can run. */
cpumask_var_t cpumask;
/**
* @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU
* selection from @cpumask.
*/
int next_cpu;
/**
* @next_cpu_batch: Counter of how many works left in the batch before
* changing to the next CPU.
*/
int next_cpu_batch;
/** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */
unsigned long flags;
/**
* @sched_data: Pointer owned by the IO scheduler attached to a request
* queue. It's up to the IO scheduler how to use this pointer.
*/
void *sched_data;
/**
* @queue: Pointer to the request queue that owns this hardware context.
*/
struct request_queue *queue;
/** @fq: Queue of requests that need to perform a flush operation. */
struct blk_flush_queue *fq;
/**
* @driver_data: Pointer to data owned by the block driver that created
* this hctx
*/
void *driver_data;
/**
* @ctx_map: Bitmap for each software queue. If bit is on, there is a
* pending request in that software queue.
*/
struct sbitmap ctx_map;
/**
* @dispatch_from: Software queue to be used when no scheduler was
* selected.
*/
struct blk_mq_ctx *dispatch_from;
/**
* @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to
* decide if the hw_queue is busy using Exponential Weighted Moving
* Average algorithm.
*/
unsigned int dispatch_busy;
/** @type: HCTX_TYPE_* flags. Type of hardware queue. */
unsigned short type;
/** @nr_ctx: Number of software queues. */
unsigned short nr_ctx;
/** @ctxs: Array of software queues. */
struct blk_mq_ctx **ctxs;
/** @dispatch_wait_lock: Lock for dispatch_wait queue. */
spinlock_t dispatch_wait_lock;
/**
* @dispatch_wait: Waitqueue to put requests when there is no tag
* available at the moment, to wait for another try in the future.
*/
wait_queue_entry_t dispatch_wait;
/**
* @wait_index: Index of next available dispatch_wait queue to insert
* requests.
*/
atomic_t wait_index;
/**
* @tags: Tags owned by the block driver. A tag at this set is only
* assigned when a request is dispatched from a hardware queue.
*/
struct blk_mq_tags *tags;
/**
* @sched_tags: Tags owned by I/O scheduler. If there is an I/O
* scheduler associated with a request queue, a tag is assigned when
* that request is allocated. Else, this member is not used.
*/
struct blk_mq_tags *sched_tags;
/** @queued: Number of queued requests. */
unsigned long queued;
/** @run: Number of dispatched requests. */
unsigned long run;
#define BLK_MQ_MAX_DISPATCH_ORDER 7
/** @dispatched: Number of dispatch requests by queue. */
unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
/** @numa_node: NUMA node the storage adapter has been connected to. */
unsigned int numa_node;
/** @queue_num: Index of this hardware queue. */
unsigned int queue_num;
/**
* @nr_active: Number of active requests. Only used when a tag set is
* shared across request queues.
*/
atomic_t nr_active;
/** @cpuhp_online: List to store request if CPU is going to die */
struct hlist_node cpuhp_online;
/** @cpuhp_dead: List to store request if some CPU die. */
struct hlist_node cpuhp_dead;
/** @kobj: Kernel object for sysfs. */
struct kobject kobj;
/** @poll_considered: Count times blk_poll() was called. */
unsigned long poll_considered;
/** @poll_invoked: Count how many requests blk_poll() polled. */
unsigned long poll_invoked;
/** @poll_success: Count how many polled requests were completed. */
unsigned long poll_success;
#ifdef CONFIG_BLK_DEBUG_FS
/**
* @debugfs_dir: debugfs directory for this hardware queue. Named
* as cpu<cpu_number>.
*/
struct dentry *debugfs_dir;
/** @sched_debugfs_dir: debugfs directory for the scheduler. */
struct dentry *sched_debugfs_dir;
#endif
/**
* @hctx_list: if this hctx is not in use, this is an entry in
* q->unused_hctx_list.
*/
struct list_head hctx_list;
/**
* @srcu: Sleepable RCU. Use as lock when type of the hardware queue is
* blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also
* blk_mq_hw_ctx_size().
*/
struct srcu_struct srcu[];
};
/**
* struct blk_mq_queue_map - Map software queues to hardware queues
* @mq_map: CPU ID to hardware queue index map. This is an array
* with nr_cpu_ids elements. Each element has a value in the range
* [@queue_offset, @queue_offset + @nr_queues).
* @nr_queues: Number of hardware queues to map CPU IDs onto.
* @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe
* driver to map each hardware queue type (enum hctx_type) onto a distinct
* set of hardware queues.
*/
struct blk_mq_queue_map {
unsigned int *mq_map;
unsigned int nr_queues;
unsigned int queue_offset;
};
/**
* enum hctx_type - Type of hardware queue
* @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for.
* @HCTX_TYPE_READ: Just for READ I/O.
* @HCTX_TYPE_POLL: Polled I/O of any kind.
* @HCTX_MAX_TYPES: Number of types of hctx.
*/
enum hctx_type {
HCTX_TYPE_DEFAULT,
HCTX_TYPE_READ,
HCTX_TYPE_POLL,
HCTX_MAX_TYPES,
};
/**
* struct blk_mq_tag_set - tag set that can be shared between request queues
* @map: One or more ctx -> hctx mappings. One map exists for each
* hardware queue type (enum hctx_type) that the driver wishes
* to support. There are no restrictions on maps being of the
* same size, and it's perfectly legal to share maps between
* types.
* @nr_maps: Number of elements in the @map array. A number in the range
* [1, HCTX_MAX_TYPES].
* @ops: Pointers to functions that implement block driver behavior.
* @nr_hw_queues: Number of hardware queues supported by the block driver that
* owns this data structure.
* @queue_depth: Number of tags per hardware queue, reserved tags included.
* @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag
* allocations.
* @cmd_size: Number of additional bytes to allocate per request. The block
* driver owns these additional bytes.
* @numa_node: NUMA node the storage adapter has been connected to.
* @timeout: Request processing timeout in jiffies.
* @flags: Zero or more BLK_MQ_F_* flags.
* @driver_data: Pointer to data owned by the block driver that created this
* tag set.
* @active_queues_shared_sbitmap:
* number of active request queues per tag set.
* @__bitmap_tags: A shared tags sbitmap, used over all hctx's
* @__breserved_tags:
* A shared reserved tags sbitmap, used over all hctx's
* @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues
* elements.
* @tag_list_lock: Serializes tag_list accesses.
* @tag_list: List of the request queues that use this tag set. See also
* request_queue.tag_set_list.
*/
struct blk_mq_tag_set {
struct blk_mq_queue_map map[HCTX_MAX_TYPES];
unsigned int nr_maps;
const struct blk_mq_ops *ops;
unsigned int nr_hw_queues;
unsigned int queue_depth;
unsigned int reserved_tags;
unsigned int cmd_size;
int numa_node;
unsigned int timeout;
unsigned int flags;
void *driver_data;
atomic_t active_queues_shared_sbitmap;
struct sbitmap_queue __bitmap_tags;
struct sbitmap_queue __breserved_tags;
struct blk_mq_tags **tags;
struct mutex tag_list_lock;
struct list_head tag_list;
};
/**
* struct blk_mq_queue_data - Data about a request inserted in a queue
*
* @rq: Request pointer.
* @last: If it is the last request in the queue.
*/
struct blk_mq_queue_data {
struct request *rq;
bool last;
};
typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
bool);
typedef bool (busy_tag_iter_fn)(struct request *, void *, bool);
/**
* struct blk_mq_ops - Callback functions that implements block driver
* behaviour.
*/
struct blk_mq_ops {
/**
* @queue_rq: Queue a new request from block IO.
*/
blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *,
const struct blk_mq_queue_data *);
/**
* @commit_rqs: If a driver uses bd->last to judge when to submit
* requests to hardware, it must define this function. In case of errors
* that make us stop issuing further requests, this hook serves the
* purpose of kicking the hardware (which the last request otherwise
* would have done).
*/
void (*commit_rqs)(struct blk_mq_hw_ctx *);
/**
* @get_budget: Reserve budget before queue request, once .queue_rq is
* run, it is driver's responsibility to release the
* reserved budget. Also we have to handle failure case
* of .get_budget for avoiding I/O deadlock.
*/
int (*get_budget)(struct request_queue *);
/**
* @put_budget: Release the reserved budget.
*/
void (*put_budget)(struct request_queue *, int);
/**
* @set_rq_budget_token: store rq's budget token
*/
void (*set_rq_budget_token)(struct request *, int);
/**
* @get_rq_budget_token: retrieve rq's budget token
*/
int (*get_rq_budget_token)(struct request *);
/**
* @timeout: Called on request timeout.
*/
enum blk_eh_timer_return (*timeout)(struct request *, bool);
/**
* @poll: Called to poll for completion of a specific tag.
*/
int (*poll)(struct blk_mq_hw_ctx *);
/**
* @complete: Mark the request as complete.
*/
void (*complete)(struct request *);
/**
* @init_hctx: Called when the block layer side of a hardware queue has
* been set up, allowing the driver to allocate/init matching
* structures.
*/
int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int);
/**
* @exit_hctx: Ditto for exit/teardown.
*/
void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
/**
* @init_request: Called for every command allocated by the block layer
* to allow the driver to set up driver specific data.
*
* Tag greater than or equal to queue_depth is for setting up
* flush request.
*/
int (*init_request)(struct blk_mq_tag_set *set, struct request *,
unsigned int, unsigned int);
/**
* @exit_request: Ditto for exit/teardown.
*/
void (*exit_request)(struct blk_mq_tag_set *set, struct request *,
unsigned int);
/**
* @initialize_rq_fn: Called from inside blk_get_request().
*/
void (*initialize_rq_fn)(struct request *rq);
/**
* @cleanup_rq: Called before freeing one request which isn't completed
* yet, and usually for freeing the driver private data.
*/
void (*cleanup_rq)(struct request *);
/**
* @busy: If set, returns whether or not this queue currently is busy.
*/
bool (*busy)(struct request_queue *);
/**
* @map_queues: This allows drivers specify their own queue mapping by
* overriding the setup-time function that builds the mq_map.
*/
int (*map_queues)(struct blk_mq_tag_set *set);
#ifdef CONFIG_BLK_DEBUG_FS
/**
* @show_rq: Used by the debugfs implementation to show driver-specific
* information about a request.
*/
void (*show_rq)(struct seq_file *m, struct request *rq);
#endif
};
enum {
BLK_MQ_F_SHOULD_MERGE = 1 << 0,
BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1,
/*
* Set when this device requires underlying blk-mq device for
* completing IO:
*/
BLK_MQ_F_STACKING = 1 << 2,
BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
BLK_MQ_F_BLOCKING = 1 << 5,
/* Do not allow an I/O scheduler to be configured. */
BLK_MQ_F_NO_SCHED = 1 << 6,
/*
* Select 'none' during queue registration in case of a single hwq
* or shared hwqs instead of 'mq-deadline'.
*/
BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 7,
BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
BLK_MQ_F_ALLOC_POLICY_BITS = 1,
BLK_MQ_S_STOPPED = 0,
BLK_MQ_S_TAG_ACTIVE = 1,
BLK_MQ_S_SCHED_RESTART = 2,
/* hw queue is inactive after all its CPUs become offline */
BLK_MQ_S_INACTIVE = 3,
BLK_MQ_MAX_DEPTH = 10240,
BLK_MQ_CPU_WORK_BATCH = 8,
};
#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \
((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \
((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1))
#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \
((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
struct lock_class_key *lkclass);
#define blk_mq_alloc_disk(set, queuedata) \
({ \
static struct lock_class_key __key; \
\
__blk_mq_alloc_disk(set, queuedata, &__key); \
})
struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
struct request_queue *q);
void blk_mq_unregister_dev(struct device *, struct request_queue *);
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set);
int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
const struct blk_mq_ops *ops, unsigned int queue_depth,
unsigned int set_flags);
void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
void blk_mq_free_request(struct request *rq);
bool blk_mq_queue_inflight(struct request_queue *q);
enum {
/* return when out of requests */
BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0),
/* allocate from reserved pool */
BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1),
/* set RQF_PM */
BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2),
};
struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
blk_mq_req_flags_t flags);
struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
unsigned int op, blk_mq_req_flags_t flags,
unsigned int hctx_idx);
struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
enum {
BLK_MQ_UNIQUE_TAG_BITS = 16,
BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1,
};
u32 blk_mq_unique_tag(struct request *rq);
static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag)
{
return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS;
}
static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
{
return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
}
/**
* blk_mq_rq_state() - read the current MQ_RQ_* state of a request
* @rq: target request.
*/
static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
{
return READ_ONCE(rq->state);
}
static inline int blk_mq_request_started(struct request *rq)
{
return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
}
static inline int blk_mq_request_completed(struct request *rq)
{
return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
}
/*
*
* Set the state to complete when completing a request from inside ->queue_rq.
* This is used by drivers that want to ensure special complete actions that
* need access to the request are called on failure, e.g. by nvme for
* multipathing.
*/
static inline void blk_mq_set_request_complete(struct request *rq)
{
WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
}
void blk_mq_start_request(struct request *rq);
void blk_mq_end_request(struct request *rq, blk_status_t error);
void __blk_mq_end_request(struct request *rq, blk_status_t error);
void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
void blk_mq_complete_request(struct request *rq);
bool blk_mq_complete_request_remote(struct request *rq);
bool blk_mq_queue_stopped(struct request_queue *q);
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_stop_hw_queues(struct request_queue *q);
void blk_mq_start_hw_queues(struct request_queue *q);
void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
void blk_mq_quiesce_queue(struct request_queue *q);
void blk_mq_unquiesce_queue(struct request_queue *q);
void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_run_hw_queues(struct request_queue *q, bool async);
void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs);
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
busy_tag_iter_fn *fn, void *priv);
void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset);
void blk_mq_freeze_queue(struct request_queue *q);
void blk_mq_unfreeze_queue(struct request_queue *q);
void blk_freeze_queue_start(struct request_queue *q);
void blk_mq_freeze_queue_wait(struct request_queue *q);
int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
unsigned long timeout);
int blk_mq_map_queues(struct blk_mq_queue_map *qmap);
void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
void blk_mq_quiesce_queue_nowait(struct request_queue *q);
unsigned int blk_mq_rq_cpu(struct request *rq);
bool __blk_should_fake_timeout(struct request_queue *q);
static inline bool blk_should_fake_timeout(struct request_queue *q)
{
if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) &&
test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
return __blk_should_fake_timeout(q);
return false;
}
/**
* blk_mq_rq_from_pdu - cast a PDU to a request
* @pdu: the PDU (Protocol Data Unit) to be casted
*
* Return: request
*
* Driver command data is immediately after the request. So subtract request
* size to get back to the original request.
*/
static inline struct request *blk_mq_rq_from_pdu(void *pdu)
{
return pdu - sizeof(struct request);
}
/**
* blk_mq_rq_to_pdu - cast a request to a PDU
* @rq: the request to be casted
*
* Return: pointer to the PDU
*
* Driver command data is immediately after the request. So add request to get
* the PDU.
*/
static inline void *blk_mq_rq_to_pdu(struct request *rq)
{
return rq + 1;
}
#define queue_for_each_hw_ctx(q, hctx, i) \
for ((i) = 0; (i) < (q)->nr_hw_queues && \
({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++)
#define hctx_for_each_ctx(hctx, ctx, i) \
for ((i) = 0; (i) < (hctx)->nr_ctx && \
({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
if (rq->tag != -1)
return rq->tag | (hctx->queue_num << BLK_QC_T_SHIFT);
return rq->internal_tag | (hctx->queue_num << BLK_QC_T_SHIFT) |
BLK_QC_T_INTERNAL;
}
static inline void blk_mq_cleanup_rq(struct request *rq)
{
if (rq->q->mq_ops->cleanup_rq)
rq->q->mq_ops->cleanup_rq(rq);
}
static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
unsigned int nr_segs)
{
rq->nr_phys_segments = nr_segs;
rq->__data_len = bio->bi_iter.bi_size;
rq->bio = rq->biotail = bio;
rq->ioprio = bio_prio(bio);
if (bio->bi_bdev)
rq->rq_disk = bio->bi_bdev->bd_disk;
}
blk_qc_t blk_mq_submit_bio(struct bio *bio);
void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
struct lock_class_key *key);
static inline bool rq_is_sync(struct request *rq)
{
return op_is_sync(rq->cmd_flags);
}
void blk_rq_init(struct request_queue *q, struct request *rq);
void blk_put_request(struct request *rq);
struct request *blk_get_request(struct request_queue *q, unsigned int op,
blk_mq_req_flags_t flags);
int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
struct bio_set *bs, gfp_t gfp_mask,
int (*bio_ctr)(struct bio *, struct bio *, void *), void *data);
void blk_rq_unprep_clone(struct request *rq);
blk_status_t blk_insert_cloned_request(struct request_queue *q,
struct request *rq);
struct rq_map_data {
struct page **pages;
int page_order;
int nr_entries;
unsigned long offset;
int null_mapped;
int from_user;
};
int blk_rq_map_user(struct request_queue *, struct request *,
struct rq_map_data *, void __user *, unsigned long, gfp_t);
int blk_rq_map_user_iov(struct request_queue *, struct request *,
struct rq_map_data *, const struct iov_iter *, gfp_t);
int blk_rq_unmap_user(struct bio *);
int blk_rq_map_kern(struct request_queue *, struct request *, void *,
unsigned int, gfp_t);
int blk_rq_append_bio(struct request *rq, struct bio *bio);
void blk_execute_rq_nowait(struct gendisk *, struct request *, int,
rq_end_io_fn *);
blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
int at_head);
struct req_iterator {
struct bvec_iter iter;
struct bio *bio;
};
#define __rq_for_each_bio(_bio, rq) \
if ((rq->bio)) \
for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
#define rq_for_each_segment(bvl, _rq, _iter) \
__rq_for_each_bio(_iter.bio, _rq) \
bio_for_each_segment(bvl, _iter.bio, _iter.iter)
#define rq_for_each_bvec(bvl, _rq, _iter) \
__rq_for_each_bio(_iter.bio, _rq) \
bio_for_each_bvec(bvl, _iter.bio, _iter.iter)
#define rq_iter_last(bvec, _iter) \
(_iter.bio->bi_next == NULL && \
bio_iter_last(bvec, _iter.iter))
/*
* blk_rq_pos() : the current sector
* blk_rq_bytes() : bytes left in the entire request
* blk_rq_cur_bytes() : bytes left in the current segment
* blk_rq_err_bytes() : bytes left till the next error boundary
* blk_rq_sectors() : sectors left in the entire request
* blk_rq_cur_sectors() : sectors left in the current segment
* blk_rq_stats_sectors() : sectors of the entire request used for stats
*/
static inline sector_t blk_rq_pos(const struct request *rq)
{
return rq->__sector;
}
static inline unsigned int blk_rq_bytes(const struct request *rq)
{
return rq->__data_len;
}
static inline int blk_rq_cur_bytes(const struct request *rq)
{
return rq->bio ? bio_cur_bytes(rq->bio) : 0;
}
unsigned int blk_rq_err_bytes(const struct request *rq);
static inline unsigned int blk_rq_sectors(const struct request *rq)
{
return blk_rq_bytes(rq) >> SECTOR_SHIFT;
}
static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
{
return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
}
static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
{
return rq->stats_sectors;
}
/*
* Some commands like WRITE SAME have a payload or data transfer size which
* is different from the size of the request. Any driver that supports such
* commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to
* calculate the data transfer size.
*/
static inline unsigned int blk_rq_payload_bytes(struct request *rq)
{
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
return rq->special_vec.bv_len;
return blk_rq_bytes(rq);
}
/*
* Return the first full biovec in the request. The caller needs to check that
* there are any bvecs before calling this helper.
*/
static inline struct bio_vec req_bvec(struct request *rq)
{
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
return rq->special_vec;
return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
}
static inline unsigned int blk_rq_count_bios(struct request *rq)
{
unsigned int nr_bios = 0;
struct bio *bio;
__rq_for_each_bio(bio, rq)
nr_bios++;
return nr_bios;
}
void blk_steal_bios(struct bio_list *list, struct request *rq);
/*
* Request completion related functions.
*
* blk_update_request() completes given number of bytes and updates
* the request without completing it.
*/
bool blk_update_request(struct request *rq, blk_status_t error,
unsigned int nr_bytes);
void blk_abort_request(struct request *);
/*
* Number of physical segments as sent to the device.
*
* Normally this is the number of discontiguous data segments sent by the
* submitter. But for data-less command like discard we might have no
* actual data segments submitted, but the driver might have to add it's
* own special payload. In that case we still return 1 here so that this
* special payload will be mapped.
*/
static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
{
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
return 1;
return rq->nr_phys_segments;
}
/*
* Number of discard segments (or ranges) the driver needs to fill in.
* Each discard bio merged into a request is counted as one segment.
*/
static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
{
return max_t(unsigned short, rq->nr_phys_segments, 1);
}
int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
struct scatterlist *sglist, struct scatterlist **last_sg);
static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
struct scatterlist *sglist)
{
struct scatterlist *last_sg = NULL;
return __blk_rq_map_sg(q, rq, sglist, &last_sg);
}
void blk_dump_rq_flags(struct request *, char *);
#ifdef CONFIG_BLK_DEV_ZONED
static inline unsigned int blk_rq_zone_no(struct request *rq)
{
return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
}
static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
{
return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
}
bool blk_req_needs_zone_write_lock(struct request *rq);
bool blk_req_zone_write_trylock(struct request *rq);
void __blk_req_zone_write_lock(struct request *rq);
void __blk_req_zone_write_unlock(struct request *rq);
static inline void blk_req_zone_write_lock(struct request *rq)
{
if (blk_req_needs_zone_write_lock(rq))
__blk_req_zone_write_lock(rq);
}
static inline void blk_req_zone_write_unlock(struct request *rq)
{
if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
__blk_req_zone_write_unlock(rq);
}
static inline bool blk_req_zone_is_write_locked(struct request *rq)
{
return rq->q->seq_zones_wlock &&
test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock);
}
static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
{
if (!blk_req_needs_zone_write_lock(rq))
return true;
return !blk_req_zone_is_write_locked(rq);
}
#else /* CONFIG_BLK_DEV_ZONED */
static inline bool blk_req_needs_zone_write_lock(struct request *rq)
{
return false;
}
static inline void blk_req_zone_write_lock(struct request *rq)
{
}
static inline void blk_req_zone_write_unlock(struct request *rq)
{
}
static inline bool blk_req_zone_is_write_locked(struct request *rq)
{
return false;
}
static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
{
return true;
}
#endif /* CONFIG_BLK_DEV_ZONED */
#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
#endif
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
void rq_flush_dcache_pages(struct request *rq);
#else
static inline void rq_flush_dcache_pages(struct request *rq)
{
}
#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */
#endif /* BLK_MQ_H */
|