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
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
|
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_BLKDEV_H
#define _LINUX_BLKDEV_H
#include <linux/sched.h>
#include <linux/genhd.h>
#include <linux/list.h>
#include <linux/llist.h>
#include <linux/minmax.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/wait.h>
#include <linux/bio.h>
#include <linux/gfp.h>
#include <linux/rcupdate.h>
#include <linux/percpu-refcount.h>
#include <linux/scatterlist.h>
#include <linux/blkzoned.h>
#include <linux/sbitmap.h>
struct module;
struct request_queue;
struct elevator_queue;
struct blk_trace;
struct request;
struct sg_io_hdr;
struct blkcg_gq;
struct blk_flush_queue;
struct pr_ops;
struct rq_qos;
struct blk_queue_stats;
struct blk_stat_callback;
struct blk_keyslot_manager;
#define BLKDEV_MIN_RQ 4
#define BLKDEV_MAX_RQ 128 /* Default maximum */
/* Must be consistent with blk_mq_poll_stats_bkt() */
#define BLK_MQ_POLL_STATS_BKTS 16
/* Doing classic polling */
#define BLK_MQ_POLL_CLASSIC -1
/*
* Maximum number of blkcg policies allowed to be registered concurrently.
* Defined here to simplify include dependency.
*/
#define BLKCG_MAX_POLS 6
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)
/*
* Request state for blk-mq.
*/
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;
#if defined(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;
};
static inline bool blk_op_is_passthrough(unsigned int op)
{
op &= REQ_OP_MASK;
return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
}
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;
}
struct bio_vec;
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 */
/*
* Zoned block device models (zoned limit).
*
* Note: This needs to be ordered from the least to the most severe
* restrictions for the inheritance in blk_stack_limits() to work.
*/
enum blk_zoned_model {
BLK_ZONED_NONE = 0, /* Regular block device */
BLK_ZONED_HA, /* Host-aware zoned block device */
BLK_ZONED_HM, /* Host-managed zoned block device */
};
/*
* BLK_BOUNCE_NONE: never bounce (default)
* BLK_BOUNCE_HIGH: bounce all highmem pages
*/
enum blk_bounce {
BLK_BOUNCE_NONE,
BLK_BOUNCE_HIGH,
};
struct queue_limits {
enum blk_bounce bounce;
unsigned long seg_boundary_mask;
unsigned long virt_boundary_mask;
unsigned int max_hw_sectors;
unsigned int max_dev_sectors;
unsigned int chunk_sectors;
unsigned int max_sectors;
unsigned int max_segment_size;
unsigned int physical_block_size;
unsigned int logical_block_size;
unsigned int alignment_offset;
unsigned int io_min;
unsigned int io_opt;
unsigned int max_discard_sectors;
unsigned int max_hw_discard_sectors;
unsigned int max_write_same_sectors;
unsigned int max_write_zeroes_sectors;
unsigned int max_zone_append_sectors;
unsigned int discard_granularity;
unsigned int discard_alignment;
unsigned int zone_write_granularity;
unsigned short max_segments;
unsigned short max_integrity_segments;
unsigned short max_discard_segments;
unsigned char misaligned;
unsigned char discard_misaligned;
unsigned char raid_partial_stripes_expensive;
enum blk_zoned_model zoned;
};
typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
void *data);
void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
#ifdef CONFIG_BLK_DEV_ZONED
#define BLK_ALL_ZONES ((unsigned int)-1)
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
unsigned int blkdev_nr_zones(struct gendisk *disk);
extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
sector_t sectors, sector_t nr_sectors,
gfp_t gfp_mask);
int blk_revalidate_disk_zones(struct gendisk *disk,
void (*update_driver_data)(struct gendisk *disk));
extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg);
extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg);
#else /* CONFIG_BLK_DEV_ZONED */
static inline unsigned int blkdev_nr_zones(struct gendisk *disk)
{
return 0;
}
static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
fmode_t mode, unsigned int cmd,
unsigned long arg)
{
return -ENOTTY;
}
static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
fmode_t mode, unsigned int cmd,
unsigned long arg)
{
return -ENOTTY;
}
#endif /* CONFIG_BLK_DEV_ZONED */
struct request_queue {
struct request *last_merge;
struct elevator_queue *elevator;
struct percpu_ref q_usage_counter;
struct blk_queue_stats *stats;
struct rq_qos *rq_qos;
const struct blk_mq_ops *mq_ops;
/* sw queues */
struct blk_mq_ctx __percpu *queue_ctx;
unsigned int queue_depth;
/* hw dispatch queues */
struct blk_mq_hw_ctx **queue_hw_ctx;
unsigned int nr_hw_queues;
/*
* The queue owner gets to use this for whatever they like.
* ll_rw_blk doesn't touch it.
*/
void *queuedata;
/*
* various queue flags, see QUEUE_* below
*/
unsigned long queue_flags;
/*
* Number of contexts that have called blk_set_pm_only(). If this
* counter is above zero then only RQF_PM requests are processed.
*/
atomic_t pm_only;
/*
* ida allocated id for this queue. Used to index queues from
* ioctx.
*/
int id;
spinlock_t queue_lock;
struct gendisk *disk;
/*
* queue kobject
*/
struct kobject kobj;
/*
* mq queue kobject
*/
struct kobject *mq_kobj;
#ifdef CONFIG_BLK_DEV_INTEGRITY
struct blk_integrity integrity;
#endif /* CONFIG_BLK_DEV_INTEGRITY */
#ifdef CONFIG_PM
struct device *dev;
enum rpm_status rpm_status;
#endif
/*
* queue settings
*/
unsigned long nr_requests; /* Max # of requests */
unsigned int dma_pad_mask;
unsigned int dma_alignment;
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
/* Inline crypto capabilities */
struct blk_keyslot_manager *ksm;
#endif
unsigned int rq_timeout;
int poll_nsec;
struct blk_stat_callback *poll_cb;
struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS];
struct timer_list timeout;
struct work_struct timeout_work;
atomic_t nr_active_requests_shared_sbitmap;
struct sbitmap_queue sched_bitmap_tags;
struct sbitmap_queue sched_breserved_tags;
struct list_head icq_list;
#ifdef CONFIG_BLK_CGROUP
DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS);
struct blkcg_gq *root_blkg;
struct list_head blkg_list;
#endif
struct queue_limits limits;
unsigned int required_elevator_features;
#ifdef CONFIG_BLK_DEV_ZONED
/*
* Zoned block device information for request dispatch control.
* nr_zones is the total number of zones of the device. This is always
* 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones
* bits which indicates if a zone is conventional (bit set) or
* sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones
* bits which indicates if a zone is write locked, that is, if a write
* request targeting the zone was dispatched. All three fields are
* initialized by the low level device driver (e.g. scsi/sd.c).
* Stacking drivers (device mappers) may or may not initialize
* these fields.
*
* Reads of this information must be protected with blk_queue_enter() /
* blk_queue_exit(). Modifying this information is only allowed while
* no requests are being processed. See also blk_mq_freeze_queue() and
* blk_mq_unfreeze_queue().
*/
unsigned int nr_zones;
unsigned long *conv_zones_bitmap;
unsigned long *seq_zones_wlock;
unsigned int max_open_zones;
unsigned int max_active_zones;
#endif /* CONFIG_BLK_DEV_ZONED */
int node;
struct mutex debugfs_mutex;
#ifdef CONFIG_BLK_DEV_IO_TRACE
struct blk_trace __rcu *blk_trace;
#endif
/*
* for flush operations
*/
struct blk_flush_queue *fq;
struct list_head requeue_list;
spinlock_t requeue_lock;
struct delayed_work requeue_work;
struct mutex sysfs_lock;
struct mutex sysfs_dir_lock;
/*
* for reusing dead hctx instance in case of updating
* nr_hw_queues
*/
struct list_head unused_hctx_list;
spinlock_t unused_hctx_lock;
int mq_freeze_depth;
#ifdef CONFIG_BLK_DEV_THROTTLING
/* Throttle data */
struct throtl_data *td;
#endif
struct rcu_head rcu_head;
wait_queue_head_t mq_freeze_wq;
/*
* Protect concurrent access to q_usage_counter by
* percpu_ref_kill() and percpu_ref_reinit().
*/
struct mutex mq_freeze_lock;
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
struct bio_set bio_split;
struct dentry *debugfs_dir;
#ifdef CONFIG_BLK_DEBUG_FS
struct dentry *sched_debugfs_dir;
struct dentry *rqos_debugfs_dir;
#endif
bool mq_sysfs_init_done;
#define BLK_MAX_WRITE_HINTS 5
u64 write_hints[BLK_MAX_WRITE_HINTS];
};
/* Keep blk_queue_flag_name[] in sync with the definitions below */
#define QUEUE_FLAG_STOPPED 0 /* queue is stopped */
#define QUEUE_FLAG_DYING 1 /* queue being torn down */
#define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */
#define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */
#define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */
#define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */
#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */
#define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */
#define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */
#define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */
#define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */
#define QUEUE_FLAG_SECERASE 11 /* supports secure erase */
#define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */
#define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */
#define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */
#define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */
#define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */
#define QUEUE_FLAG_WC 17 /* Write back caching */
#define QUEUE_FLAG_FUA 18 /* device supports FUA writes */
#define QUEUE_FLAG_DAX 19 /* device supports DAX */
#define QUEUE_FLAG_STATS 20 /* track IO start and completion times */
#define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */
#define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */
#define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */
#define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */
#define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */
#define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */
#define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */
#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */
#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */
#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_SAME_COMP) | \
(1 << QUEUE_FLAG_NOWAIT))
void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
#define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
#define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
#define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
#define blk_queue_noxmerges(q) \
test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
#define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
#define blk_queue_stable_writes(q) \
test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
#define blk_queue_zone_resetall(q) \
test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
#define blk_queue_secure_erase(q) \
(test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags))
#define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
#define blk_queue_scsi_passthrough(q) \
test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags)
#define blk_queue_pci_p2pdma(q) \
test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
#define blk_queue_rq_alloc_time(q) \
test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags)
#else
#define blk_queue_rq_alloc_time(q) false
#endif
#define blk_noretry_request(rq) \
((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
REQ_FAILFAST_DRIVER))
#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
#define blk_queue_pm_only(q) atomic_read(&(q)->pm_only)
#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
#define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
#define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
extern void blk_set_pm_only(struct request_queue *q);
extern void blk_clear_pm_only(struct request_queue *q);
#define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist)
#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)
#define dma_map_bvec(dev, bv, dir, attrs) \
dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \
(dir), (attrs))
static inline bool queue_is_mq(struct request_queue *q)
{
return q->mq_ops;
}
#ifdef CONFIG_PM
static inline enum rpm_status queue_rpm_status(struct request_queue *q)
{
return q->rpm_status;
}
#else
static inline enum rpm_status queue_rpm_status(struct request_queue *q)
{
return RPM_ACTIVE;
}
#endif
static inline enum blk_zoned_model
blk_queue_zoned_model(struct request_queue *q)
{
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
return q->limits.zoned;
return BLK_ZONED_NONE;
}
static inline bool blk_queue_is_zoned(struct request_queue *q)
{
switch (blk_queue_zoned_model(q)) {
case BLK_ZONED_HA:
case BLK_ZONED_HM:
return true;
default:
return false;
}
}
static inline sector_t blk_queue_zone_sectors(struct request_queue *q)
{
return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
}
#ifdef CONFIG_BLK_DEV_ZONED
static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
{
return blk_queue_is_zoned(q) ? q->nr_zones : 0;
}
static inline unsigned int blk_queue_zone_no(struct request_queue *q,
sector_t sector)
{
if (!blk_queue_is_zoned(q))
return 0;
return sector >> ilog2(q->limits.chunk_sectors);
}
static inline bool blk_queue_zone_is_seq(struct request_queue *q,
sector_t sector)
{
if (!blk_queue_is_zoned(q))
return false;
if (!q->conv_zones_bitmap)
return true;
return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap);
}
static inline void blk_queue_max_open_zones(struct request_queue *q,
unsigned int max_open_zones)
{
q->max_open_zones = max_open_zones;
}
static inline unsigned int queue_max_open_zones(const struct request_queue *q)
{
return q->max_open_zones;
}
static inline void blk_queue_max_active_zones(struct request_queue *q,
unsigned int max_active_zones)
{
q->max_active_zones = max_active_zones;
}
static inline unsigned int queue_max_active_zones(const struct request_queue *q)
{
return q->max_active_zones;
}
#else /* CONFIG_BLK_DEV_ZONED */
static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
{
return 0;
}
static inline bool blk_queue_zone_is_seq(struct request_queue *q,
sector_t sector)
{
return false;
}
static inline unsigned int blk_queue_zone_no(struct request_queue *q,
sector_t sector)
{
return 0;
}
static inline unsigned int queue_max_open_zones(const struct request_queue *q)
{
return 0;
}
static inline unsigned int queue_max_active_zones(const struct request_queue *q)
{
return 0;
}
#endif /* CONFIG_BLK_DEV_ZONED */
static inline bool rq_is_sync(struct request *rq)
{
return op_is_sync(rq->cmd_flags);
}
static inline unsigned int blk_queue_depth(struct request_queue *q)
{
if (q->queue_depth)
return q->queue_depth;
return q->nr_requests;
}
/*
* default timeout for SG_IO if none specified
*/
#define BLK_DEFAULT_SG_TIMEOUT (60 * HZ)
#define BLK_MIN_SG_TIMEOUT (7 * HZ)
struct rq_map_data {
struct page **pages;
int page_order;
int nr_entries;
unsigned long offset;
int null_mapped;
int from_user;
};
struct req_iterator {
struct bvec_iter iter;
struct bio *bio;
};
/* This should not be used directly - use rq_for_each_segment */
#define for_each_bio(_bio) \
for (; _bio; _bio = _bio->bi_next)
#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))
#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
extern void rq_flush_dcache_pages(struct request *rq);
#else
static inline void rq_flush_dcache_pages(struct request *rq)
{
}
#endif
extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
blk_qc_t submit_bio_noacct(struct bio *bio);
extern void blk_rq_init(struct request_queue *q, struct request *rq);
extern void blk_put_request(struct request *);
extern struct request *blk_get_request(struct request_queue *, unsigned int op,
blk_mq_req_flags_t flags);
extern int blk_lld_busy(struct request_queue *q);
extern 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);
extern void blk_rq_unprep_clone(struct request *rq);
extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
struct request *rq);
int blk_rq_append_bio(struct request *rq, struct bio *bio);
extern void blk_queue_split(struct bio **);
extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags);
extern void blk_queue_exit(struct request_queue *q);
extern void blk_sync_queue(struct request_queue *q);
extern int blk_rq_map_user(struct request_queue *, struct request *,
struct rq_map_data *, void __user *, unsigned long,
gfp_t);
extern int blk_rq_unmap_user(struct bio *);
extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
struct rq_map_data *, const struct iov_iter *,
gfp_t);
extern 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);
/* Helper to convert REQ_OP_XXX to its string format XXX */
extern const char *blk_op_str(unsigned int op);
int blk_status_to_errno(blk_status_t status);
blk_status_t errno_to_blk_status(int errno);
int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin);
static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
{
return bdev->bd_disk->queue; /* this is never NULL */
}
/*
* The basic unit of block I/O is a sector. It is used in a number of contexts
* in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9
* bytes. Variables of type sector_t represent an offset or size that is a
* multiple of 512 bytes. Hence these two constants.
*/
#ifndef SECTOR_SHIFT
#define SECTOR_SHIFT 9
#endif
#ifndef SECTOR_SIZE
#define SECTOR_SIZE (1 << SECTOR_SHIFT)
#endif
#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT)
#define SECTOR_MASK (PAGE_SECTORS - 1)
/*
* 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;
}
extern 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;
}
#ifdef CONFIG_BLK_DEV_ZONED
/* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */
const char *blk_zone_cond_str(enum blk_zone_cond zone_cond);
static inline unsigned int bio_zone_no(struct bio *bio)
{
return blk_queue_zone_no(bdev_get_queue(bio->bi_bdev),
bio->bi_iter.bi_sector);
}
static inline unsigned int bio_zone_is_seq(struct bio *bio)
{
return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev),
bio->bi_iter.bi_sector);
}
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));
}
#endif /* CONFIG_BLK_DEV_ZONED */
/*
* 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_queue_get_max_sectors(struct request_queue *q,
int op)
{
if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
return min(q->limits.max_discard_sectors,
UINT_MAX >> SECTOR_SHIFT);
if (unlikely(op == REQ_OP_WRITE_SAME))
return q->limits.max_write_same_sectors;
if (unlikely(op == REQ_OP_WRITE_ZEROES))
return q->limits.max_write_zeroes_sectors;
return q->limits.max_sectors;
}
/*
* Return maximum size of a request at given offset. Only valid for
* file system requests.
*/
static inline unsigned int blk_max_size_offset(struct request_queue *q,
sector_t offset,
unsigned int chunk_sectors)
{
if (!chunk_sectors) {
if (q->limits.chunk_sectors)
chunk_sectors = q->limits.chunk_sectors;
else
return q->limits.max_sectors;
}
if (likely(is_power_of_2(chunk_sectors)))
chunk_sectors -= offset & (chunk_sectors - 1);
else
chunk_sectors -= sector_div(offset, chunk_sectors);
return min(q->limits.max_sectors, chunk_sectors);
}
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.
*/
extern bool blk_update_request(struct request *rq, blk_status_t error,
unsigned int nr_bytes);
extern void blk_abort_request(struct request *);
/*
* Access functions for manipulating queue properties
*/
extern void blk_cleanup_queue(struct request_queue *);
void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit);
extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
extern void blk_queue_max_segments(struct request_queue *, unsigned short);
extern void blk_queue_max_discard_segments(struct request_queue *,
unsigned short);
extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
extern void blk_queue_max_discard_sectors(struct request_queue *q,
unsigned int max_discard_sectors);
extern void blk_queue_max_write_same_sectors(struct request_queue *q,
unsigned int max_write_same_sectors);
extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
unsigned int max_write_same_sectors);
extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
unsigned int max_zone_append_sectors);
extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
void blk_queue_zone_write_granularity(struct request_queue *q,
unsigned int size);
extern void blk_queue_alignment_offset(struct request_queue *q,
unsigned int alignment);
void disk_update_readahead(struct gendisk *disk);
extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
extern void blk_set_default_limits(struct queue_limits *lim);
extern void blk_set_stacking_limits(struct queue_limits *lim);
extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
sector_t offset);
extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
sector_t offset);
extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
extern void blk_queue_dma_alignment(struct request_queue *, int);
extern void blk_queue_update_dma_alignment(struct request_queue *, int);
extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
/*
* Elevator features for blk_queue_required_elevator_features:
*/
/* Supports zoned block devices sequential write constraint */
#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0)
/* Supports scheduling on multiple hardware queues */
#define ELEVATOR_F_MQ_AWARE (1U << 1)
extern void blk_queue_required_elevator_features(struct request_queue *q,
unsigned int features);
extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
struct device *dev);
/*
* 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);
}
extern void blk_dump_rq_flags(struct request *, char *);
bool __must_check blk_get_queue(struct request_queue *);
extern void blk_put_queue(struct request_queue *);
extern void blk_set_queue_dying(struct request_queue *);
#ifdef CONFIG_BLOCK
/*
* blk_plug permits building a queue of related requests by holding the I/O
* fragments for a short period. This allows merging of sequential requests
* into single larger request. As the requests are moved from a per-task list to
* the device's request_queue in a batch, this results in improved scalability
* as the lock contention for request_queue lock is reduced.
*
* It is ok not to disable preemption when adding the request to the plug list
* or when attempting a merge, because blk_schedule_flush_list() will only flush
* the plug list when the task sleeps by itself. For details, please see
* schedule() where blk_schedule_flush_plug() is called.
*/
struct blk_plug {
struct list_head mq_list; /* blk-mq requests */
struct list_head cb_list; /* md requires an unplug callback */
unsigned short rq_count;
bool multiple_queues;
bool nowait;
};
#define BLK_MAX_REQUEST_COUNT 16
#define BLK_PLUG_FLUSH_SIZE (128 * 1024)
struct blk_plug_cb;
typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool);
struct blk_plug_cb {
struct list_head list;
blk_plug_cb_fn callback;
void *data;
};
extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug,
void *data, int size);
extern void blk_start_plug(struct blk_plug *);
extern void blk_finish_plug(struct blk_plug *);
extern void blk_flush_plug_list(struct blk_plug *, bool);
static inline void blk_flush_plug(struct task_struct *tsk)
{
struct blk_plug *plug = tsk->plug;
if (plug)
blk_flush_plug_list(plug, false);
}
static inline void blk_schedule_flush_plug(struct task_struct *tsk)
{
struct blk_plug *plug = tsk->plug;
if (plug)
blk_flush_plug_list(plug, true);
}
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
struct blk_plug *plug = tsk->plug;
return plug &&
(!list_empty(&plug->mq_list) ||
!list_empty(&plug->cb_list));
}
int blkdev_issue_flush(struct block_device *bdev);
long nr_blockdev_pages(void);
#else /* CONFIG_BLOCK */
struct blk_plug {
};
static inline void blk_start_plug(struct blk_plug *plug)
{
}
static inline void blk_finish_plug(struct blk_plug *plug)
{
}
static inline void blk_flush_plug(struct task_struct *task)
{
}
static inline void blk_schedule_flush_plug(struct task_struct *task)
{
}
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
return false;
}
static inline int blkdev_issue_flush(struct block_device *bdev)
{
return 0;
}
static inline long nr_blockdev_pages(void)
{
return 0;
}
#endif /* CONFIG_BLOCK */
extern void blk_io_schedule(void);
extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct page *page);
#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */
extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, int flags,
struct bio **biop);
#define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */
#define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */
extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
unsigned flags);
extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, unsigned flags);
static inline int sb_issue_discard(struct super_block *sb, sector_t block,
sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
{
return blkdev_issue_discard(sb->s_bdev,
block << (sb->s_blocksize_bits -
SECTOR_SHIFT),
nr_blocks << (sb->s_blocksize_bits -
SECTOR_SHIFT),
gfp_mask, flags);
}
static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
sector_t nr_blocks, gfp_t gfp_mask)
{
return blkdev_issue_zeroout(sb->s_bdev,
block << (sb->s_blocksize_bits -
SECTOR_SHIFT),
nr_blocks << (sb->s_blocksize_bits -
SECTOR_SHIFT),
gfp_mask, 0);
}
static inline bool bdev_is_partition(struct block_device *bdev)
{
return bdev->bd_partno;
}
enum blk_default_limits {
BLK_MAX_SEGMENTS = 128,
BLK_SAFE_MAX_SECTORS = 255,
BLK_DEF_MAX_SECTORS = 2560,
BLK_MAX_SEGMENT_SIZE = 65536,
BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL,
};
static inline unsigned long queue_segment_boundary(const struct request_queue *q)
{
return q->limits.seg_boundary_mask;
}
static inline unsigned long queue_virt_boundary(const struct request_queue *q)
{
return q->limits.virt_boundary_mask;
}
static inline unsigned int queue_max_sectors(const struct request_queue *q)
{
return q->limits.max_sectors;
}
static inline unsigned int queue_max_bytes(struct request_queue *q)
{
return min_t(unsigned int, queue_max_sectors(q), INT_MAX >> 9) << 9;
}
static inline unsigned int queue_max_hw_sectors(const struct request_queue *q)
{
return q->limits.max_hw_sectors;
}
static inline unsigned short queue_max_segments(const struct request_queue *q)
{
return q->limits.max_segments;
}
static inline unsigned short queue_max_discard_segments(const struct request_queue *q)
{
return q->limits.max_discard_segments;
}
static inline unsigned int queue_max_segment_size(const struct request_queue *q)
{
return q->limits.max_segment_size;
}
static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
{
const struct queue_limits *l = &q->limits;
return min(l->max_zone_append_sectors, l->max_sectors);
}
static inline unsigned queue_logical_block_size(const struct request_queue *q)
{
int retval = 512;
if (q && q->limits.logical_block_size)
retval = q->limits.logical_block_size;
return retval;
}
static inline unsigned int bdev_logical_block_size(struct block_device *bdev)
{
return queue_logical_block_size(bdev_get_queue(bdev));
}
static inline unsigned int queue_physical_block_size(const struct request_queue *q)
{
return q->limits.physical_block_size;
}
static inline unsigned int bdev_physical_block_size(struct block_device *bdev)
{
return queue_physical_block_size(bdev_get_queue(bdev));
}
static inline unsigned int queue_io_min(const struct request_queue *q)
{
return q->limits.io_min;
}
static inline int bdev_io_min(struct block_device *bdev)
{
return queue_io_min(bdev_get_queue(bdev));
}
static inline unsigned int queue_io_opt(const struct request_queue *q)
{
return q->limits.io_opt;
}
static inline int bdev_io_opt(struct block_device *bdev)
{
return queue_io_opt(bdev_get_queue(bdev));
}
static inline unsigned int
queue_zone_write_granularity(const struct request_queue *q)
{
return q->limits.zone_write_granularity;
}
static inline unsigned int
bdev_zone_write_granularity(struct block_device *bdev)
{
return queue_zone_write_granularity(bdev_get_queue(bdev));
}
static inline int queue_alignment_offset(const struct request_queue *q)
{
if (q->limits.misaligned)
return -1;
return q->limits.alignment_offset;
}
static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
{
unsigned int granularity = max(lim->physical_block_size, lim->io_min);
unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT)
<< SECTOR_SHIFT;
return (granularity + lim->alignment_offset - alignment) % granularity;
}
static inline int bdev_alignment_offset(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q->limits.misaligned)
return -1;
if (bdev_is_partition(bdev))
return queue_limit_alignment_offset(&q->limits,
bdev->bd_start_sect);
return q->limits.alignment_offset;
}
static inline int queue_discard_alignment(const struct request_queue *q)
{
if (q->limits.discard_misaligned)
return -1;
return q->limits.discard_alignment;
}
static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector)
{
unsigned int alignment, granularity, offset;
if (!lim->max_discard_sectors)
return 0;
/* Why are these in bytes, not sectors? */
alignment = lim->discard_alignment >> SECTOR_SHIFT;
granularity = lim->discard_granularity >> SECTOR_SHIFT;
if (!granularity)
return 0;
/* Offset of the partition start in 'granularity' sectors */
offset = sector_div(sector, granularity);
/* And why do we do this modulus *again* in blkdev_issue_discard()? */
offset = (granularity + alignment - offset) % granularity;
/* Turn it back into bytes, gaah */
return offset << SECTOR_SHIFT;
}
static inline int bdev_discard_alignment(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (bdev_is_partition(bdev))
return queue_limit_discard_alignment(&q->limits,
bdev->bd_start_sect);
return q->limits.discard_alignment;
}
static inline unsigned int bdev_write_same(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return q->limits.max_write_same_sectors;
return 0;
}
static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return q->limits.max_write_zeroes_sectors;
return 0;
}
static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return blk_queue_zoned_model(q);
return BLK_ZONED_NONE;
}
static inline bool bdev_is_zoned(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return blk_queue_is_zoned(q);
return false;
}
static inline sector_t bdev_zone_sectors(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return blk_queue_zone_sectors(q);
return 0;
}
static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return queue_max_open_zones(q);
return 0;
}
static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return queue_max_active_zones(q);
return 0;
}
static inline int queue_dma_alignment(const struct request_queue *q)
{
return q ? q->dma_alignment : 511;
}
static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
unsigned int len)
{
unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask;
return !(addr & alignment) && !(len & alignment);
}
/* assumes size > 256 */
static inline unsigned int blksize_bits(unsigned int size)
{
unsigned int bits = 8;
do {
bits++;
size >>= 1;
} while (size > 256);
return bits;
}
static inline unsigned int block_size(struct block_device *bdev)
{
return 1 << bdev->bd_inode->i_blkbits;
}
int kblockd_schedule_work(struct work_struct *work);
int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
#define MODULE_ALIAS_BLOCKDEV(major,minor) \
MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
MODULE_ALIAS("block-major-" __stringify(major) "-*")
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q);
void blk_ksm_unregister(struct request_queue *q);
#else /* CONFIG_BLK_INLINE_ENCRYPTION */
static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm,
struct request_queue *q)
{
return true;
}
static inline void blk_ksm_unregister(struct request_queue *q) { }
#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
struct block_device_operations {
blk_qc_t (*submit_bio) (struct bio *bio);
int (*open) (struct block_device *, fmode_t);
void (*release) (struct gendisk *, fmode_t);
int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
unsigned int (*check_events) (struct gendisk *disk,
unsigned int clearing);
void (*unlock_native_capacity) (struct gendisk *);
int (*getgeo)(struct block_device *, struct hd_geometry *);
int (*set_read_only)(struct block_device *bdev, bool ro);
/* this callback is with swap_lock and sometimes page table lock held */
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
int (*report_zones)(struct gendisk *, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
char *(*devnode)(struct gendisk *disk, umode_t *mode);
struct module *owner;
const struct pr_ops *pr_ops;
/*
* Special callback for probing GPT entry at a given sector.
* Needed by Android devices, used by GPT scanner and MMC blk
* driver.
*/
int (*alternative_gpt_sector)(struct gendisk *disk, sector_t *sector);
};
#ifdef CONFIG_COMPAT
extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t,
unsigned int, unsigned long);
#else
#define blkdev_compat_ptr_ioctl NULL
#endif
extern int bdev_read_page(struct block_device *, sector_t, struct page *);
extern int bdev_write_page(struct block_device *, sector_t, struct page *,
struct writeback_control *);
#ifdef CONFIG_BLK_DEV_ZONED
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
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 */
static inline void blk_wake_io_task(struct task_struct *waiter)
{
/*
* If we're polling, the task itself is doing the completions. For
* that case, we don't need to signal a wakeup, it's enough to just
* mark us as RUNNING.
*/
if (waiter == current)
__set_current_state(TASK_RUNNING);
else
wake_up_process(waiter);
}
unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
unsigned int op);
void disk_end_io_acct(struct gendisk *disk, unsigned int op,
unsigned long start_time);
unsigned long bio_start_io_acct(struct bio *bio);
void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
struct block_device *orig_bdev);
/**
* bio_end_io_acct - end I/O accounting for bio based drivers
* @bio: bio to end account for
* @start: start time returned by bio_start_io_acct()
*/
static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
{
return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev);
}
int bdev_read_only(struct block_device *bdev);
int set_blocksize(struct block_device *bdev, int size);
const char *bdevname(struct block_device *bdev, char *buffer);
int lookup_bdev(const char *pathname, dev_t *dev);
void blkdev_show(struct seq_file *seqf, off_t offset);
#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */
#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */
#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_MAX 512
#else
#define BLKDEV_MAJOR_MAX 0
#endif
struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
void *holder);
struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
int bd_prepare_to_claim(struct block_device *bdev, void *holder);
void bd_abort_claiming(struct block_device *bdev, void *holder);
void blkdev_put(struct block_device *bdev, fmode_t mode);
/* just for blk-cgroup, don't use elsewhere */
struct block_device *blkdev_get_no_open(dev_t dev);
void blkdev_put_no_open(struct block_device *bdev);
struct block_device *bdev_alloc(struct gendisk *disk, u8 partno);
void bdev_add(struct block_device *bdev, dev_t dev);
struct block_device *I_BDEV(struct inode *inode);
int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
loff_t lend);
#ifdef CONFIG_BLOCK
void invalidate_bdev(struct block_device *bdev);
int sync_blockdev(struct block_device *bdev);
#else
static inline void invalidate_bdev(struct block_device *bdev)
{
}
static inline int sync_blockdev(struct block_device *bdev)
{
return 0;
}
#endif
int fsync_bdev(struct block_device *bdev);
int freeze_bdev(struct block_device *bdev);
int thaw_bdev(struct block_device *bdev);
#endif /* _LINUX_BLKDEV_H */
|