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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Zoned block device handling
*
* Copyright (c) 2015, Hannes Reinecke
* Copyright (c) 2015, SUSE Linux GmbH
*
* Copyright (c) 2016, Damien Le Moal
* Copyright (c) 2016, Western Digital
* Copyright (c) 2024, Western Digital Corporation or its affiliates.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/sched/mm.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/mempool.h>
#include "blk.h"
#include "blk-mq-sched.h"
#define ZONE_COND_NAME(name) [BLK_ZONE_COND_##name] = #name
static const char *const zone_cond_name[] = {
ZONE_COND_NAME(NOT_WP),
ZONE_COND_NAME(EMPTY),
ZONE_COND_NAME(IMP_OPEN),
ZONE_COND_NAME(EXP_OPEN),
ZONE_COND_NAME(CLOSED),
ZONE_COND_NAME(READONLY),
ZONE_COND_NAME(FULL),
ZONE_COND_NAME(OFFLINE),
};
#undef ZONE_COND_NAME
/*
* Per-zone write plug.
* @node: hlist_node structure for managing the plug using a hash table.
* @link: To list the plug in the zone write plug error list of the disk.
* @ref: Zone write plug reference counter. A zone write plug reference is
* always at least 1 when the plug is hashed in the disk plug hash table.
* The reference is incremented whenever a new BIO needing plugging is
* submitted and when a function needs to manipulate a plug. The
* reference count is decremented whenever a plugged BIO completes and
* when a function that referenced the plug returns. The initial
* reference is dropped whenever the zone of the zone write plug is reset,
* finished and when the zone becomes full (last write BIO to the zone
* completes).
* @lock: Spinlock to atomically manipulate the plug.
* @flags: Flags indicating the plug state.
* @zone_no: The number of the zone the plug is managing.
* @wp_offset: The zone write pointer location relative to the start of the zone
* as a number of 512B sectors.
* @bio_list: The list of BIOs that are currently plugged.
* @bio_work: Work struct to handle issuing of plugged BIOs
* @rcu_head: RCU head to free zone write plugs with an RCU grace period.
* @disk: The gendisk the plug belongs to.
*/
struct blk_zone_wplug {
struct hlist_node node;
struct list_head link;
atomic_t ref;
spinlock_t lock;
unsigned int flags;
unsigned int zone_no;
unsigned int wp_offset;
struct bio_list bio_list;
struct work_struct bio_work;
struct rcu_head rcu_head;
struct gendisk *disk;
};
/*
* Zone write plug flags bits:
* - BLK_ZONE_WPLUG_PLUGGED: Indicates that the zone write plug is plugged,
* that is, that write BIOs are being throttled due to a write BIO already
* being executed or the zone write plug bio list is not empty.
* - BLK_ZONE_WPLUG_ERROR: Indicates that a write error happened which will be
* recovered with a report zone to update the zone write pointer offset.
* - BLK_ZONE_WPLUG_UNHASHED: Indicates that the zone write plug was removed
* from the disk hash table and that the initial reference to the zone
* write plug set when the plug was first added to the hash table has been
* dropped. This flag is set when a zone is reset, finished or become full,
* to prevent new references to the zone write plug to be taken for
* newly incoming BIOs. A zone write plug flagged with this flag will be
* freed once all remaining references from BIOs or functions are dropped.
*/
#define BLK_ZONE_WPLUG_PLUGGED (1U << 0)
#define BLK_ZONE_WPLUG_ERROR (1U << 1)
#define BLK_ZONE_WPLUG_UNHASHED (1U << 2)
#define BLK_ZONE_WPLUG_BUSY (BLK_ZONE_WPLUG_PLUGGED | BLK_ZONE_WPLUG_ERROR)
/**
* blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX.
* @zone_cond: BLK_ZONE_COND_XXX.
*
* Description: Centralize block layer function to convert BLK_ZONE_COND_XXX
* into string format. Useful in the debugging and tracing zone conditions. For
* invalid BLK_ZONE_COND_XXX it returns string "UNKNOWN".
*/
const char *blk_zone_cond_str(enum blk_zone_cond zone_cond)
{
static const char *zone_cond_str = "UNKNOWN";
if (zone_cond < ARRAY_SIZE(zone_cond_name) && zone_cond_name[zone_cond])
zone_cond_str = zone_cond_name[zone_cond];
return zone_cond_str;
}
EXPORT_SYMBOL_GPL(blk_zone_cond_str);
/*
* Return true if a request is a write requests that needs zone write locking.
*/
bool blk_req_needs_zone_write_lock(struct request *rq)
{
if (!rq->q->disk->seq_zones_wlock)
return false;
return blk_rq_is_seq_zoned_write(rq);
}
EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock);
bool blk_req_zone_write_trylock(struct request *rq)
{
unsigned int zno = blk_rq_zone_no(rq);
if (test_and_set_bit(zno, rq->q->disk->seq_zones_wlock))
return false;
WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;
return true;
}
EXPORT_SYMBOL_GPL(blk_req_zone_write_trylock);
void __blk_req_zone_write_lock(struct request *rq)
{
if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
rq->q->disk->seq_zones_wlock)))
return;
WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_lock);
void __blk_req_zone_write_unlock(struct request *rq)
{
rq->rq_flags &= ~RQF_ZONE_WRITE_LOCKED;
if (rq->q->disk->seq_zones_wlock)
WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq),
rq->q->disk->seq_zones_wlock));
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
/**
* bdev_nr_zones - Get number of zones
* @bdev: Target device
*
* Return the total number of zones of a zoned block device. For a block
* device without zone capabilities, the number of zones is always 0.
*/
unsigned int bdev_nr_zones(struct block_device *bdev)
{
sector_t zone_sectors = bdev_zone_sectors(bdev);
if (!bdev_is_zoned(bdev))
return 0;
return (bdev_nr_sectors(bdev) + zone_sectors - 1) >>
ilog2(zone_sectors);
}
EXPORT_SYMBOL_GPL(bdev_nr_zones);
/**
* blkdev_report_zones - Get zones information
* @bdev: Target block device
* @sector: Sector from which to report zones
* @nr_zones: Maximum number of zones to report
* @cb: Callback function called for each reported zone
* @data: Private data for the callback
*
* Description:
* Get zone information starting from the zone containing @sector for at most
* @nr_zones, and call @cb for each zone reported by the device.
* To report all zones in a device starting from @sector, the BLK_ALL_ZONES
* constant can be passed to @nr_zones.
* Returns the number of zones reported by the device, or a negative errno
* value in case of failure.
*
* Note: The caller must use memalloc_noXX_save/restore() calls to control
* memory allocations done within this function.
*/
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct gendisk *disk = bdev->bd_disk;
sector_t capacity = get_capacity(disk);
if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones))
return -EOPNOTSUPP;
if (!nr_zones || sector >= capacity)
return 0;
return disk->fops->report_zones(disk, sector, nr_zones, cb, data);
}
EXPORT_SYMBOL_GPL(blkdev_report_zones);
static inline unsigned long *blk_alloc_zone_bitmap(int node,
unsigned int nr_zones)
{
return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
GFP_NOIO, node);
}
static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
void *data)
{
/*
* For an all-zones reset, ignore conventional, empty, read-only
* and offline zones.
*/
switch (zone->cond) {
case BLK_ZONE_COND_NOT_WP:
case BLK_ZONE_COND_EMPTY:
case BLK_ZONE_COND_READONLY:
case BLK_ZONE_COND_OFFLINE:
return 0;
default:
set_bit(idx, (unsigned long *)data);
return 0;
}
}
static int blkdev_zone_reset_all_emulated(struct block_device *bdev)
{
struct gendisk *disk = bdev->bd_disk;
sector_t capacity = bdev_nr_sectors(bdev);
sector_t zone_sectors = bdev_zone_sectors(bdev);
unsigned long *need_reset;
struct bio *bio = NULL;
sector_t sector = 0;
int ret;
need_reset = blk_alloc_zone_bitmap(disk->queue->node, disk->nr_zones);
if (!need_reset)
return -ENOMEM;
ret = disk->fops->report_zones(disk, 0, disk->nr_zones,
blk_zone_need_reset_cb, need_reset);
if (ret < 0)
goto out_free_need_reset;
ret = 0;
while (sector < capacity) {
if (!test_bit(disk_zone_no(disk, sector), need_reset)) {
sector += zone_sectors;
continue;
}
bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC,
GFP_KERNEL);
bio->bi_iter.bi_sector = sector;
sector += zone_sectors;
/* This may take a while, so be nice to others */
cond_resched();
}
if (bio) {
ret = submit_bio_wait(bio);
bio_put(bio);
}
out_free_need_reset:
kfree(need_reset);
return ret;
}
static int blkdev_zone_reset_all(struct block_device *bdev)
{
struct bio bio;
bio_init(&bio, bdev, NULL, 0, REQ_OP_ZONE_RESET_ALL | REQ_SYNC);
return submit_bio_wait(&bio);
}
/**
* blkdev_zone_mgmt - Execute a zone management operation on a range of zones
* @bdev: Target block device
* @op: Operation to be performed on the zones
* @sector: Start sector of the first zone to operate on
* @nr_sectors: Number of sectors, should be at least the length of one zone and
* must be zone size aligned.
*
* Description:
* Perform the specified operation on the range of zones specified by
* @sector..@sector+@nr_sectors. Specifying the entire disk sector range
* is valid, but the specified range should not contain conventional zones.
* The operation to execute on each zone can be a zone reset, open, close
* or finish request.
*/
int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
sector_t sector, sector_t nr_sectors)
{
struct request_queue *q = bdev_get_queue(bdev);
sector_t zone_sectors = bdev_zone_sectors(bdev);
sector_t capacity = bdev_nr_sectors(bdev);
sector_t end_sector = sector + nr_sectors;
struct bio *bio = NULL;
int ret = 0;
if (!bdev_is_zoned(bdev))
return -EOPNOTSUPP;
if (bdev_read_only(bdev))
return -EPERM;
if (!op_is_zone_mgmt(op))
return -EOPNOTSUPP;
if (end_sector <= sector || end_sector > capacity)
/* Out of range */
return -EINVAL;
/* Check alignment (handle eventual smaller last zone) */
if (!bdev_is_zone_start(bdev, sector))
return -EINVAL;
if (!bdev_is_zone_start(bdev, nr_sectors) && end_sector != capacity)
return -EINVAL;
/*
* In the case of a zone reset operation over all zones,
* REQ_OP_ZONE_RESET_ALL can be used with devices supporting this
* command. For other devices, we emulate this command behavior by
* identifying the zones needing a reset.
*/
if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
if (!blk_queue_zone_resetall(q))
return blkdev_zone_reset_all_emulated(bdev);
return blkdev_zone_reset_all(bdev);
}
while (sector < end_sector) {
bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, GFP_KERNEL);
bio->bi_iter.bi_sector = sector;
sector += zone_sectors;
/* This may take a while, so be nice to others */
cond_resched();
}
ret = submit_bio_wait(bio);
bio_put(bio);
return ret;
}
EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);
struct zone_report_args {
struct blk_zone __user *zones;
};
static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx,
void *data)
{
struct zone_report_args *args = data;
if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone)))
return -EFAULT;
return 0;
}
/*
* BLKREPORTZONE ioctl processing.
* Called from blkdev_ioctl.
*/
int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct zone_report_args args;
struct blk_zone_report rep;
int ret;
if (!argp)
return -EINVAL;
if (!bdev_is_zoned(bdev))
return -ENOTTY;
if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report)))
return -EFAULT;
if (!rep.nr_zones)
return -EINVAL;
args.zones = argp + sizeof(struct blk_zone_report);
ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones,
blkdev_copy_zone_to_user, &args);
if (ret < 0)
return ret;
rep.nr_zones = ret;
rep.flags = BLK_ZONE_REP_CAPACITY;
if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
return -EFAULT;
return 0;
}
static int blkdev_truncate_zone_range(struct block_device *bdev,
blk_mode_t mode, const struct blk_zone_range *zrange)
{
loff_t start, end;
if (zrange->sector + zrange->nr_sectors <= zrange->sector ||
zrange->sector + zrange->nr_sectors > get_capacity(bdev->bd_disk))
/* Out of range */
return -EINVAL;
start = zrange->sector << SECTOR_SHIFT;
end = ((zrange->sector + zrange->nr_sectors) << SECTOR_SHIFT) - 1;
return truncate_bdev_range(bdev, mode, start, end);
}
/*
* BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
* Called from blkdev_ioctl.
*/
int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
unsigned int cmd, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct blk_zone_range zrange;
enum req_op op;
int ret;
if (!argp)
return -EINVAL;
if (!bdev_is_zoned(bdev))
return -ENOTTY;
if (!(mode & BLK_OPEN_WRITE))
return -EBADF;
if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
return -EFAULT;
switch (cmd) {
case BLKRESETZONE:
op = REQ_OP_ZONE_RESET;
/* Invalidate the page cache, including dirty pages. */
filemap_invalidate_lock(bdev->bd_inode->i_mapping);
ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
if (ret)
goto fail;
break;
case BLKOPENZONE:
op = REQ_OP_ZONE_OPEN;
break;
case BLKCLOSEZONE:
op = REQ_OP_ZONE_CLOSE;
break;
case BLKFINISHZONE:
op = REQ_OP_ZONE_FINISH;
break;
default:
return -ENOTTY;
}
ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
fail:
if (cmd == BLKRESETZONE)
filemap_invalidate_unlock(bdev->bd_inode->i_mapping);
return ret;
}
static inline bool disk_zone_is_conv(struct gendisk *disk, sector_t sector)
{
if (!disk->conv_zones_bitmap)
return false;
return test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap);
}
static bool disk_insert_zone_wplug(struct gendisk *disk,
struct blk_zone_wplug *zwplug)
{
struct blk_zone_wplug *zwplg;
unsigned long flags;
unsigned int idx =
hash_32(zwplug->zone_no, disk->zone_wplugs_hash_bits);
/*
* Add the new zone write plug to the hash table, but carefully as we
* are racing with other submission context, so we may already have a
* zone write plug for the same zone.
*/
spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
hlist_for_each_entry_rcu(zwplg, &disk->zone_wplugs_hash[idx], node) {
if (zwplg->zone_no == zwplug->zone_no) {
spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
return false;
}
}
hlist_add_head_rcu(&zwplug->node, &disk->zone_wplugs_hash[idx]);
spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
return true;
}
static void disk_remove_zone_wplug(struct gendisk *disk,
struct blk_zone_wplug *zwplug)
{
unsigned long flags;
spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
zwplug->flags |= BLK_ZONE_WPLUG_UNHASHED;
atomic_dec(&zwplug->ref);
hlist_del_init_rcu(&zwplug->node);
spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
}
static inline bool disk_should_remove_zone_wplug(struct gendisk *disk,
struct blk_zone_wplug *zwplug)
{
/* If the zone is still busy, the plug cannot be removed. */
if (zwplug->flags & BLK_ZONE_WPLUG_BUSY)
return false;
/* We can remove zone write plugs for zones that are empty or full. */
return !zwplug->wp_offset || zwplug->wp_offset >= disk->zone_capacity;
}
static struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk,
sector_t sector)
{
unsigned int zno = disk_zone_no(disk, sector);
unsigned int idx = hash_32(zno, disk->zone_wplugs_hash_bits);
struct blk_zone_wplug *zwplug;
rcu_read_lock();
hlist_for_each_entry_rcu(zwplug, &disk->zone_wplugs_hash[idx], node) {
if (zwplug->zone_no == zno &&
atomic_inc_not_zero(&zwplug->ref)) {
rcu_read_unlock();
return zwplug;
}
}
rcu_read_unlock();
return NULL;
}
static void disk_free_zone_wplug_rcu(struct rcu_head *rcu_head)
{
struct blk_zone_wplug *zwplug =
container_of(rcu_head, struct blk_zone_wplug, rcu_head);
mempool_free(zwplug, zwplug->disk->zone_wplugs_pool);
}
static inline void disk_put_zone_wplug(struct blk_zone_wplug *zwplug)
{
if (atomic_dec_and_test(&zwplug->ref)) {
WARN_ON_ONCE(!bio_list_empty(&zwplug->bio_list));
WARN_ON_ONCE(!list_empty(&zwplug->link));
call_rcu(&zwplug->rcu_head, disk_free_zone_wplug_rcu);
}
}
static void blk_zone_wplug_bio_work(struct work_struct *work);
/*
* Get a reference on the write plug for the zone containing @sector.
* If the plug does not exist, it is allocated and hashed.
* Return a pointer to the zone write plug with the plug spinlock held.
*/
static struct blk_zone_wplug *disk_get_and_lock_zone_wplug(struct gendisk *disk,
sector_t sector, gfp_t gfp_mask,
unsigned long *flags)
{
unsigned int zno = disk_zone_no(disk, sector);
struct blk_zone_wplug *zwplug;
again:
zwplug = disk_get_zone_wplug(disk, sector);
if (zwplug) {
/*
* Check that a BIO completion or a zone reset or finish
* operation has not already removed the zone write plug from
* the hash table and dropped its reference count. In such case,
* we need to get a new plug so start over from the beginning.
*/
spin_lock_irqsave(&zwplug->lock, *flags);
if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) {
spin_unlock_irqrestore(&zwplug->lock, *flags);
disk_put_zone_wplug(zwplug);
goto again;
}
return zwplug;
}
/*
* Allocate and initialize a zone write plug with an extra reference
* so that it is not freed when the zone write plug becomes idle without
* the zone being full.
*/
zwplug = mempool_alloc(disk->zone_wplugs_pool, gfp_mask);
if (!zwplug)
return NULL;
INIT_HLIST_NODE(&zwplug->node);
INIT_LIST_HEAD(&zwplug->link);
atomic_set(&zwplug->ref, 2);
spin_lock_init(&zwplug->lock);
zwplug->flags = 0;
zwplug->zone_no = zno;
zwplug->wp_offset = sector & (disk->queue->limits.chunk_sectors - 1);
bio_list_init(&zwplug->bio_list);
INIT_WORK(&zwplug->bio_work, blk_zone_wplug_bio_work);
zwplug->disk = disk;
spin_lock_irqsave(&zwplug->lock, *flags);
/*
* Insert the new zone write plug in the hash table. This can fail only
* if another context already inserted a plug. Retry from the beginning
* in such case.
*/
if (!disk_insert_zone_wplug(disk, zwplug)) {
spin_unlock_irqrestore(&zwplug->lock, *flags);
mempool_free(zwplug, disk->zone_wplugs_pool);
goto again;
}
return zwplug;
}
static inline void blk_zone_wplug_bio_io_error(struct bio *bio)
{
struct request_queue *q = bio->bi_bdev->bd_disk->queue;
bio_clear_flag(bio, BIO_ZONE_WRITE_PLUGGING);
bio_io_error(bio);
blk_queue_exit(q);
}
/*
* Abort (fail) all plugged BIOs of a zone write plug.
*/
static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug)
{
struct bio *bio;
while ((bio = bio_list_pop(&zwplug->bio_list))) {
blk_zone_wplug_bio_io_error(bio);
disk_put_zone_wplug(zwplug);
}
}
/*
* Abort (fail) all plugged BIOs of a zone write plug that are not aligned
* with the assumed write pointer location of the zone when the BIO will
* be unplugged.
*/
static void disk_zone_wplug_abort_unaligned(struct gendisk *disk,
struct blk_zone_wplug *zwplug)
{
unsigned int zone_capacity = disk->zone_capacity;
unsigned int wp_offset = zwplug->wp_offset;
struct bio_list bl = BIO_EMPTY_LIST;
struct bio *bio;
while ((bio = bio_list_pop(&zwplug->bio_list))) {
if (wp_offset >= zone_capacity ||
bio_offset_from_zone_start(bio) != wp_offset) {
blk_zone_wplug_bio_io_error(bio);
disk_put_zone_wplug(zwplug);
continue;
}
wp_offset += bio_sectors(bio);
bio_list_add(&bl, bio);
}
bio_list_merge(&zwplug->bio_list, &bl);
}
/*
* Set a zone write plug write pointer offset to either 0 (zone reset case)
* or to the zone size (zone finish case). This aborts all plugged BIOs, which
* is fine to do as doing a zone reset or zone finish while writes are in-flight
* is a mistake from the user which will most likely cause all plugged BIOs to
* fail anyway.
*/
static void disk_zone_wplug_set_wp_offset(struct gendisk *disk,
struct blk_zone_wplug *zwplug,
unsigned int wp_offset)
{
unsigned long flags;
spin_lock_irqsave(&zwplug->lock, flags);
/*
* Make sure that a BIO completion or another zone reset or finish
* operation has not already removed the plug from the hash table.
*/
if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) {
spin_unlock_irqrestore(&zwplug->lock, flags);
return;
}
/* Update the zone write pointer and abort all plugged BIOs. */
zwplug->wp_offset = wp_offset;
disk_zone_wplug_abort(zwplug);
/*
* Updating the write pointer offset puts back the zone
* in a good state. So clear the error flag and decrement the
* error count if we were in error state.
*/
if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) {
zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR;
spin_lock(&disk->zone_wplugs_lock);
list_del_init(&zwplug->link);
spin_unlock(&disk->zone_wplugs_lock);
}
/*
* The zone write plug now has no BIO plugged: remove it from the
* hash table so that it cannot be seen. The plug will be freed
* when the last reference is dropped.
*/
if (disk_should_remove_zone_wplug(disk, zwplug))
disk_remove_zone_wplug(disk, zwplug);
spin_unlock_irqrestore(&zwplug->lock, flags);
}
static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio,
unsigned int wp_offset)
{
struct gendisk *disk = bio->bi_bdev->bd_disk;
sector_t sector = bio->bi_iter.bi_sector;
struct blk_zone_wplug *zwplug;
/* Conventional zones cannot be reset nor finished. */
if (disk_zone_is_conv(disk, sector)) {
bio_io_error(bio);
return true;
}
/*
* If we have a zone write plug, set its write pointer offset to 0
* (reset case) or to the zone size (finish case). This will abort all
* BIOs plugged for the target zone. It is fine as resetting or
* finishing zones while writes are still in-flight will result in the
* writes failing anyway.
*/
zwplug = disk_get_zone_wplug(disk, sector);
if (zwplug) {
disk_zone_wplug_set_wp_offset(disk, zwplug, wp_offset);
disk_put_zone_wplug(zwplug);
}
return false;
}
static bool blk_zone_wplug_handle_reset_all(struct bio *bio)
{
struct gendisk *disk = bio->bi_bdev->bd_disk;
struct blk_zone_wplug *zwplug;
sector_t sector;
/*
* Set the write pointer offset of all zone write plugs to 0. This will
* abort all plugged BIOs. It is fine as resetting zones while writes
* are still in-flight will result in the writes failing anyway.
*/
for (sector = 0; sector < get_capacity(disk);
sector += disk->queue->limits.chunk_sectors) {
zwplug = disk_get_zone_wplug(disk, sector);
if (zwplug) {
disk_zone_wplug_set_wp_offset(disk, zwplug, 0);
disk_put_zone_wplug(zwplug);
}
}
return false;
}
static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug,
struct bio *bio, unsigned int nr_segs)
{
/*
* Grab an extra reference on the BIO request queue usage counter.
* This reference will be reused to submit a request for the BIO for
* blk-mq devices and dropped when the BIO is failed and after
* it is issued in the case of BIO-based devices.
*/
percpu_ref_get(&bio->bi_bdev->bd_disk->queue->q_usage_counter);
/*
* The BIO is being plugged and thus will have to wait for the on-going
* write and for all other writes already plugged. So polling makes
* no sense.
*/
bio_clear_polled(bio);
/*
* Reuse the poll cookie field to store the number of segments when
* split to the hardware limits.
*/
bio->__bi_nr_segments = nr_segs;
/*
* We always receive BIOs after they are split and ready to be issued.
* The block layer passes the parts of a split BIO in order, and the
* user must also issue write sequentially. So simply add the new BIO
* at the tail of the list to preserve the sequential write order.
*/
bio_list_add(&zwplug->bio_list, bio);
}
/*
* Called from bio_attempt_back_merge() when a BIO was merged with a request.
*/
void blk_zone_write_plug_bio_merged(struct bio *bio)
{
struct blk_zone_wplug *zwplug;
unsigned long flags;
/*
* If the BIO was already plugged, then we were called through
* blk_zone_write_plug_attempt_merge() -> blk_attempt_bio_merge().
* For this case, blk_zone_write_plug_attempt_merge() will handle the
* zone write pointer offset update.
*/
if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING))
return;
bio_set_flag(bio, BIO_ZONE_WRITE_PLUGGING);
/*
* Increase the plug reference count and advance the zone write
* pointer offset.
*/
zwplug = disk_get_zone_wplug(bio->bi_bdev->bd_disk,
bio->bi_iter.bi_sector);
spin_lock_irqsave(&zwplug->lock, flags);
zwplug->wp_offset += bio_sectors(bio);
spin_unlock_irqrestore(&zwplug->lock, flags);
}
/*
* Attempt to merge plugged BIOs with a newly prepared request for a BIO that
* already went through zone write plugging (either a new BIO or one that was
* unplugged).
*/
void blk_zone_write_plug_attempt_merge(struct request *req)
{
sector_t req_back_sector = blk_rq_pos(req) + blk_rq_sectors(req);
struct request_queue *q = req->q;
struct gendisk *disk = q->disk;
unsigned int zone_capacity = disk->zone_capacity;
struct blk_zone_wplug *zwplug =
disk_get_zone_wplug(disk, blk_rq_pos(req));
unsigned long flags;
struct bio *bio;
/*
* Completion of this request needs to be handled with
* blk_zone_write_plug_complete_request().
*/
req->rq_flags |= RQF_ZONE_WRITE_PLUGGING;
if (blk_queue_nomerges(q))
return;
/*
* Walk through the list of plugged BIOs to check if they can be merged
* into the back of the request.
*/
spin_lock_irqsave(&zwplug->lock, flags);
while (zwplug->wp_offset < zone_capacity) {
bio = bio_list_peek(&zwplug->bio_list);
if (!bio)
break;
if (bio->bi_iter.bi_sector != req_back_sector ||
!blk_rq_merge_ok(req, bio))
break;
WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE_ZEROES &&
!bio->__bi_nr_segments);
bio_list_pop(&zwplug->bio_list);
if (bio_attempt_back_merge(req, bio, bio->__bi_nr_segments) !=
BIO_MERGE_OK) {
bio_list_add_head(&zwplug->bio_list, bio);
break;
}
/*
* Drop the extra reference on the queue usage we got when
* plugging the BIO and advance the write pointer offset.
*/
blk_queue_exit(q);
zwplug->wp_offset += bio_sectors(bio);
req_back_sector += bio_sectors(bio);
}
spin_unlock_irqrestore(&zwplug->lock, flags);
}
static inline void disk_zone_wplug_set_error(struct gendisk *disk,
struct blk_zone_wplug *zwplug)
{
if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR)) {
unsigned long flags;
/*
* Increase the plug reference count. The reference will be
* dropped in disk_zone_wplugs_work() once the error state
* is handled.
*/
zwplug->flags |= BLK_ZONE_WPLUG_ERROR;
atomic_inc(&zwplug->ref);
spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
list_add_tail(&zwplug->link, &disk->zone_wplugs_err_list);
spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
}
}
/*
* Check and prepare a BIO for submission by incrementing the write pointer
* offset of its zone write plug.
*/
static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug,
struct bio *bio)
{
struct gendisk *disk = bio->bi_bdev->bd_disk;
/*
* Check that the user is not attempting to write to a full zone.
* We know such BIO will fail, and that would potentially overflow our
* write pointer offset beyond the end of the zone.
*/
if (zwplug->wp_offset >= disk->zone_capacity)
goto err;
/*
* Check for non-sequential writes early because we avoid a
* whole lot of error handling trouble if we don't send it off
* to the driver.
*/
if (bio_offset_from_zone_start(bio) != zwplug->wp_offset)
goto err;
/* Advance the zone write pointer offset. */
zwplug->wp_offset += bio_sectors(bio);
return true;
err:
/* We detected an invalid write BIO: schedule error recovery. */
disk_zone_wplug_set_error(disk, zwplug);
kblockd_schedule_work(&disk->zone_wplugs_work);
return false;
}
static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs)
{
struct gendisk *disk = bio->bi_bdev->bd_disk;
sector_t sector = bio->bi_iter.bi_sector;
struct blk_zone_wplug *zwplug;
gfp_t gfp_mask = GFP_NOIO;
unsigned long flags;
/*
* BIOs must be fully contained within a zone so that we use the correct
* zone write plug for the entire BIO. For blk-mq devices, the block
* layer should already have done any splitting required to ensure this
* and this BIO should thus not be straddling zone boundaries. For
* BIO-based devices, it is the responsibility of the driver to split
* the bio before submitting it.
*/
if (WARN_ON_ONCE(bio_straddles_zones(bio))) {
bio_io_error(bio);
return true;
}
/* Conventional zones do not need write plugging. */
if (disk_zone_is_conv(disk, sector))
return false;
if (bio->bi_opf & REQ_NOWAIT)
gfp_mask = GFP_NOWAIT;
zwplug = disk_get_and_lock_zone_wplug(disk, sector, gfp_mask, &flags);
if (!zwplug) {
bio_io_error(bio);
return true;
}
/* Indicate that this BIO is being handled using zone write plugging. */
bio_set_flag(bio, BIO_ZONE_WRITE_PLUGGING);
/*
* If the zone is already plugged or has a pending error, add the BIO
* to the plug BIO list. Otherwise, plug and let the BIO execute.
*/
if (zwplug->flags & BLK_ZONE_WPLUG_BUSY)
goto plug;
/*
* If an error is detected when preparing the BIO, add it to the BIO
* list so that error recovery can deal with it.
*/
if (!blk_zone_wplug_prepare_bio(zwplug, bio))
goto plug;
zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED;
spin_unlock_irqrestore(&zwplug->lock, flags);
return false;
plug:
zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED;
blk_zone_wplug_add_bio(zwplug, bio, nr_segs);
spin_unlock_irqrestore(&zwplug->lock, flags);
return true;
}
/**
* blk_zone_plug_bio - Handle a zone write BIO with zone write plugging
* @bio: The BIO being submitted
* @nr_segs: The number of physical segments of @bio
*
* Handle write and write zeroes operations using zone write plugging.
*
* Return true whenever @bio execution needs to be delayed through the zone
* write plug. Otherwise, return false to let the submission path process
* @bio normally.
*/
bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
{
struct block_device *bdev = bio->bi_bdev;
if (!bdev->bd_disk->zone_wplugs_hash)
return false;
/*
* If the BIO already has the plugging flag set, then it was already
* handled through this path and this is a submission from the zone
* plug bio submit work.
*/
if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING))
return false;
/*
* We do not need to do anything special for empty flush BIOs, e.g
* BIOs such as issued by blkdev_issue_flush(). The is because it is
* the responsibility of the user to first wait for the completion of
* write operations for flush to have any effect on the persistence of
* the written data.
*/
if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
return false;
/*
* Regular writes and write zeroes need to be handled through the target
* zone write plug. This includes writes with REQ_FUA | REQ_PREFLUSH
* which may need to go through the flush machinery depending on the
* target device capabilities. Plugging such writes is fine as the flush
* machinery operates at the request level, below the plug, and
* completion of the flush sequence will go through the regular BIO
* completion, which will handle zone write plugging.
* Zone reset, reset all and finish commands need special treatment
* to correctly track the write pointer offset of zones. These commands
* are not plugged as we do not need serialization with write
* operations. It is the responsibility of the user to not issue reset
* and finish commands when write operations are in flight.
*/
switch (bio_op(bio)) {
case REQ_OP_WRITE:
case REQ_OP_WRITE_ZEROES:
return blk_zone_wplug_handle_write(bio, nr_segs);
case REQ_OP_ZONE_RESET:
return blk_zone_wplug_handle_reset_or_finish(bio, 0);
case REQ_OP_ZONE_FINISH:
return blk_zone_wplug_handle_reset_or_finish(bio,
bdev_zone_sectors(bdev));
case REQ_OP_ZONE_RESET_ALL:
return blk_zone_wplug_handle_reset_all(bio);
default:
return false;
}
return false;
}
EXPORT_SYMBOL_GPL(blk_zone_plug_bio);
static void disk_zone_wplug_unplug_bio(struct gendisk *disk,
struct blk_zone_wplug *zwplug)
{
unsigned long flags;
spin_lock_irqsave(&zwplug->lock, flags);
/*
* If we had an error, schedule error recovery. The recovery work
* will restart submission of plugged BIOs.
*/
if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) {
spin_unlock_irqrestore(&zwplug->lock, flags);
kblockd_schedule_work(&disk->zone_wplugs_work);
return;
}
/* Schedule submission of the next plugged BIO if we have one. */
if (!bio_list_empty(&zwplug->bio_list)) {
spin_unlock_irqrestore(&zwplug->lock, flags);
kblockd_schedule_work(&zwplug->bio_work);
return;
}
zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED;
/*
* If the zone is full (it was fully written or finished, or empty
* (it was reset), remove its zone write plug from the hash table.
*/
if (disk_should_remove_zone_wplug(disk, zwplug))
disk_remove_zone_wplug(disk, zwplug);
spin_unlock_irqrestore(&zwplug->lock, flags);
}
void blk_zone_write_plug_bio_endio(struct bio *bio)
{
struct gendisk *disk = bio->bi_bdev->bd_disk;
struct blk_zone_wplug *zwplug =
disk_get_zone_wplug(bio->bi_bdev->bd_disk,
bio->bi_iter.bi_sector);
unsigned long flags;
if (WARN_ON_ONCE(!zwplug))
return;
/* Make sure we do not see this BIO again by clearing the plug flag. */
bio_clear_flag(bio, BIO_ZONE_WRITE_PLUGGING);
/*
* If the BIO failed, mark the plug as having an error to trigger
* recovery.
*/
if (bio->bi_status != BLK_STS_OK) {
spin_lock_irqsave(&zwplug->lock, flags);
disk_zone_wplug_set_error(disk, zwplug);
spin_unlock_irqrestore(&zwplug->lock, flags);
}
/*
* For BIO-based devices, blk_zone_write_plug_complete_request()
* is not called. So we need to schedule execution of the next
* plugged BIO here.
*/
if (bio->bi_bdev->bd_has_submit_bio)
disk_zone_wplug_unplug_bio(disk, zwplug);
/* Drop the reference we took when the BIO was issued. */
atomic_dec(&zwplug->ref);
disk_put_zone_wplug(zwplug);
}
void blk_zone_write_plug_complete_request(struct request *req)
{
struct gendisk *disk = req->q->disk;
struct blk_zone_wplug *zwplug = disk_get_zone_wplug(disk, req->__sector);
if (WARN_ON_ONCE(!zwplug))
return;
req->rq_flags &= ~RQF_ZONE_WRITE_PLUGGING;
disk_zone_wplug_unplug_bio(disk, zwplug);
/*
* Drop the reference we took when the request was initialized in
* blk_zone_write_plug_attempt_merge().
*/
atomic_dec(&zwplug->ref);
disk_put_zone_wplug(zwplug);
}
static void blk_zone_wplug_bio_work(struct work_struct *work)
{
struct blk_zone_wplug *zwplug =
container_of(work, struct blk_zone_wplug, bio_work);
struct block_device *bdev;
unsigned long flags;
struct bio *bio;
/*
* Submit the next plugged BIO. If we do not have any, clear
* the plugged flag.
*/
spin_lock_irqsave(&zwplug->lock, flags);
bio = bio_list_pop(&zwplug->bio_list);
if (!bio) {
zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED;
spin_unlock_irqrestore(&zwplug->lock, flags);
return;
}
if (!blk_zone_wplug_prepare_bio(zwplug, bio)) {
/* Error recovery will decide what to do with the BIO. */
bio_list_add_head(&zwplug->bio_list, bio);
spin_unlock_irqrestore(&zwplug->lock, flags);
return;
}
spin_unlock_irqrestore(&zwplug->lock, flags);
bdev = bio->bi_bdev;
submit_bio_noacct_nocheck(bio);
/*
* blk-mq devices will reuse the extra reference on the request queue
* usage counter we took when the BIO was plugged, but the submission
* path for BIO-based devices will not do that. So drop this extra
* reference here.
*/
if (bdev->bd_has_submit_bio)
blk_queue_exit(bdev->bd_disk->queue);
}
static unsigned int blk_zone_wp_offset(struct blk_zone *zone)
{
switch (zone->cond) {
case BLK_ZONE_COND_IMP_OPEN:
case BLK_ZONE_COND_EXP_OPEN:
case BLK_ZONE_COND_CLOSED:
return zone->wp - zone->start;
case BLK_ZONE_COND_FULL:
return zone->len;
case BLK_ZONE_COND_EMPTY:
return 0;
case BLK_ZONE_COND_NOT_WP:
case BLK_ZONE_COND_OFFLINE:
case BLK_ZONE_COND_READONLY:
default:
/*
* Conventional, offline and read-only zones do not have a valid
* write pointer.
*/
return UINT_MAX;
}
}
static int blk_zone_wplug_report_zone_cb(struct blk_zone *zone,
unsigned int idx, void *data)
{
struct blk_zone *zonep = data;
*zonep = *zone;
return 0;
}
static void disk_zone_wplug_handle_error(struct gendisk *disk,
struct blk_zone_wplug *zwplug)
{
sector_t zone_start_sector =
bdev_zone_sectors(disk->part0) * zwplug->zone_no;
unsigned int noio_flag;
struct blk_zone zone;
unsigned long flags;
int ret;
/* Get the current zone information from the device. */
noio_flag = memalloc_noio_save();
ret = disk->fops->report_zones(disk, zone_start_sector, 1,
blk_zone_wplug_report_zone_cb, &zone);
memalloc_noio_restore(noio_flag);
spin_lock_irqsave(&zwplug->lock, flags);
/*
* A zone reset or finish may have cleared the error already. In such
* case, do nothing as the report zones may have seen the "old" write
* pointer value before the reset/finish operation completed.
*/
if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR))
goto unlock;
zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR;
if (ret != 1) {
/*
* We failed to get the zone information, meaning that something
* is likely really wrong with the device. Abort all remaining
* plugged BIOs as otherwise we could endup waiting forever on
* plugged BIOs to complete if there is a queue freeze on-going.
*/
disk_zone_wplug_abort(zwplug);
goto unplug;
}
/* Update the zone write pointer offset. */
zwplug->wp_offset = blk_zone_wp_offset(&zone);
disk_zone_wplug_abort_unaligned(disk, zwplug);
/* Restart BIO submission if we still have any BIO left. */
if (!bio_list_empty(&zwplug->bio_list)) {
WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED));
kblockd_schedule_work(&zwplug->bio_work);
goto unlock;
}
unplug:
zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED;
if (disk_should_remove_zone_wplug(disk, zwplug))
disk_remove_zone_wplug(disk, zwplug);
unlock:
spin_unlock_irqrestore(&zwplug->lock, flags);
}
static void disk_zone_wplugs_work(struct work_struct *work)
{
struct gendisk *disk =
container_of(work, struct gendisk, zone_wplugs_work);
struct blk_zone_wplug *zwplug;
unsigned long flags;
spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
while (!list_empty(&disk->zone_wplugs_err_list)) {
zwplug = list_first_entry(&disk->zone_wplugs_err_list,
struct blk_zone_wplug, link);
list_del_init(&zwplug->link);
spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
disk_zone_wplug_handle_error(disk, zwplug);
disk_put_zone_wplug(zwplug);
spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
}
spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
}
static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk)
{
return 1U << disk->zone_wplugs_hash_bits;
}
void disk_init_zone_resources(struct gendisk *disk)
{
spin_lock_init(&disk->zone_wplugs_lock);
INIT_LIST_HEAD(&disk->zone_wplugs_err_list);
INIT_WORK(&disk->zone_wplugs_work, disk_zone_wplugs_work);
}
/*
* For the size of a disk zone write plug hash table, use the size of the
* zone write plug mempool, which is the maximum of the disk open zones and
* active zones limits. But do not exceed 4KB (512 hlist head entries), that is,
* 9 bits. For a disk that has no limits, mempool size defaults to 128.
*/
#define BLK_ZONE_WPLUG_MAX_HASH_BITS 9
#define BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE 128
static int disk_alloc_zone_resources(struct gendisk *disk,
unsigned int pool_size)
{
unsigned int i;
disk->zone_wplugs_hash_bits =
min(ilog2(pool_size) + 1, BLK_ZONE_WPLUG_MAX_HASH_BITS);
disk->zone_wplugs_hash =
kcalloc(disk_zone_wplugs_hash_size(disk),
sizeof(struct hlist_head), GFP_KERNEL);
if (!disk->zone_wplugs_hash)
return -ENOMEM;
for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++)
INIT_HLIST_HEAD(&disk->zone_wplugs_hash[i]);
disk->zone_wplugs_pool = mempool_create_kmalloc_pool(pool_size,
sizeof(struct blk_zone_wplug));
if (!disk->zone_wplugs_pool) {
kfree(disk->zone_wplugs_hash);
disk->zone_wplugs_hash = NULL;
disk->zone_wplugs_hash_bits = 0;
return -ENOMEM;
}
return 0;
}
static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk)
{
struct blk_zone_wplug *zwplug;
unsigned int i;
if (!disk->zone_wplugs_hash)
return;
/* Free all the zone write plugs we have. */
for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) {
while (!hlist_empty(&disk->zone_wplugs_hash[i])) {
zwplug = hlist_entry(disk->zone_wplugs_hash[i].first,
struct blk_zone_wplug, node);
atomic_inc(&zwplug->ref);
disk_remove_zone_wplug(disk, zwplug);
disk_put_zone_wplug(zwplug);
}
}
kfree(disk->zone_wplugs_hash);
disk->zone_wplugs_hash = NULL;
disk->zone_wplugs_hash_bits = 0;
}
void disk_free_zone_resources(struct gendisk *disk)
{
cancel_work_sync(&disk->zone_wplugs_work);
disk_destroy_zone_wplugs_hash_table(disk);
/*
* Wait for the zone write plugs to be RCU-freed before
* destorying the mempool.
*/
rcu_barrier();
mempool_destroy(disk->zone_wplugs_pool);
disk->zone_wplugs_pool = NULL;
kfree(disk->conv_zones_bitmap);
disk->conv_zones_bitmap = NULL;
kfree(disk->seq_zones_wlock);
disk->seq_zones_wlock = NULL;
disk->zone_capacity = 0;
disk->nr_zones = 0;
}
static int disk_revalidate_zone_resources(struct gendisk *disk,
unsigned int nr_zones)
{
struct queue_limits *lim = &disk->queue->limits;
unsigned int pool_size;
/*
* If the device has no limit on the maximum number of open and active
* zones, use BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE.
*/
pool_size = max(lim->max_open_zones, lim->max_active_zones);
if (!pool_size)
pool_size = min(BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE, nr_zones);
if (!disk->zone_wplugs_hash)
return disk_alloc_zone_resources(disk, pool_size);
/* Resize the zone write plug memory pool if needed. */
if (disk->zone_wplugs_pool->min_nr != pool_size)
return mempool_resize(disk->zone_wplugs_pool, pool_size);
return 0;
}
struct blk_revalidate_zone_args {
struct gendisk *disk;
unsigned long *conv_zones_bitmap;
unsigned long *seq_zones_wlock;
unsigned int nr_zones;
unsigned int zone_capacity;
sector_t sector;
};
/*
* Helper function to check the validity of zones of a zoned block device.
*/
static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
void *data)
{
struct blk_revalidate_zone_args *args = data;
struct gendisk *disk = args->disk;
struct request_queue *q = disk->queue;
sector_t capacity = get_capacity(disk);
sector_t zone_sectors = q->limits.chunk_sectors;
struct blk_zone_wplug *zwplug;
unsigned long flags;
unsigned int wp_offset;
/* Check for bad zones and holes in the zone report */
if (zone->start != args->sector) {
pr_warn("%s: Zone gap at sectors %llu..%llu\n",
disk->disk_name, args->sector, zone->start);
return -ENODEV;
}
if (zone->start >= capacity || !zone->len) {
pr_warn("%s: Invalid zone start %llu, length %llu\n",
disk->disk_name, zone->start, zone->len);
return -ENODEV;
}
/*
* All zones must have the same size, with the exception on an eventual
* smaller last zone.
*/
if (zone->start + zone->len < capacity) {
if (zone->len != zone_sectors) {
pr_warn("%s: Invalid zoned device with non constant zone size\n",
disk->disk_name);
return -ENODEV;
}
} else if (zone->len > zone_sectors) {
pr_warn("%s: Invalid zoned device with larger last zone size\n",
disk->disk_name);
return -ENODEV;
}
if (!zone->capacity || zone->capacity > zone->len) {
pr_warn("%s: Invalid zone capacity\n",
disk->disk_name);
return -ENODEV;
}
/* Check zone type */
switch (zone->type) {
case BLK_ZONE_TYPE_CONVENTIONAL:
if (zone->capacity != zone->len) {
pr_warn("%s: Invalid conventional zone capacity\n",
disk->disk_name);
return -ENODEV;
}
if (!args->conv_zones_bitmap) {
args->conv_zones_bitmap =
blk_alloc_zone_bitmap(q->node, args->nr_zones);
if (!args->conv_zones_bitmap)
return -ENOMEM;
}
set_bit(idx, args->conv_zones_bitmap);
break;
case BLK_ZONE_TYPE_SEQWRITE_REQ:
if (!args->seq_zones_wlock) {
args->seq_zones_wlock =
blk_alloc_zone_bitmap(q->node, args->nr_zones);
if (!args->seq_zones_wlock)
return -ENOMEM;
}
/*
* Remember the capacity of the first sequential zone and check
* if it is constant for all zones.
*/
if (!args->zone_capacity)
args->zone_capacity = zone->capacity;
if (zone->capacity != args->zone_capacity) {
pr_warn("%s: Invalid variable zone capacity\n",
disk->disk_name);
return -ENODEV;
}
/*
* We need to track the write pointer of all zones that are not
* empty nor full. So make sure we have a zone write plug for
* such zone.
*/
wp_offset = blk_zone_wp_offset(zone);
if (wp_offset && wp_offset < zone_sectors) {
zwplug = disk_get_and_lock_zone_wplug(disk, zone->start,
GFP_NOIO, &flags);
if (!zwplug)
return -ENOMEM;
spin_unlock_irqrestore(&zwplug->lock, flags);
disk_put_zone_wplug(zwplug);
}
break;
case BLK_ZONE_TYPE_SEQWRITE_PREF:
default:
pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
disk->disk_name, (int)zone->type, zone->start);
return -ENODEV;
}
args->sector += zone->len;
return 0;
}
/**
* blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps
* @disk: Target disk
* @update_driver_data: Callback to update driver data on the frozen disk
*
* Helper function for low-level device drivers to check and (re) allocate and
* initialize a disk request queue zone bitmaps. This functions should normally
* be called within the disk ->revalidate method for blk-mq based drivers.
* Before calling this function, the device driver must already have set the
* device zone size (chunk_sector limit) and the max zone append limit.
* For BIO based drivers, this function cannot be used. BIO based device drivers
* only need to set disk->nr_zones so that the sysfs exposed value is correct.
* If the @update_driver_data callback function is not NULL, the callback is
* executed with the device request queue frozen after all zones have been
* checked.
*/
int blk_revalidate_disk_zones(struct gendisk *disk,
void (*update_driver_data)(struct gendisk *disk))
{
struct request_queue *q = disk->queue;
sector_t zone_sectors = q->limits.chunk_sectors;
sector_t capacity = get_capacity(disk);
struct blk_revalidate_zone_args args = { };
unsigned int noio_flag;
int ret = -ENOMEM;
if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
return -EIO;
if (WARN_ON_ONCE(!queue_is_mq(q)))
return -EIO;
if (!capacity)
return -ENODEV;
/*
* Checks that the device driver indicated a valid zone size and that
* the max zone append limit is set.
*/
if (!zone_sectors || !is_power_of_2(zone_sectors)) {
pr_warn("%s: Invalid non power of two zone size (%llu)\n",
disk->disk_name, zone_sectors);
return -ENODEV;
}
if (!q->limits.max_zone_append_sectors) {
pr_warn("%s: Invalid 0 maximum zone append limit\n",
disk->disk_name);
return -ENODEV;
}
/*
* Ensure that all memory allocations in this context are done as if
* GFP_NOIO was specified.
*/
args.disk = disk;
args.nr_zones = (capacity + zone_sectors - 1) >> ilog2(zone_sectors);
noio_flag = memalloc_noio_save();
ret = disk_revalidate_zone_resources(disk, args.nr_zones);
if (ret) {
memalloc_noio_restore(noio_flag);
return ret;
}
ret = disk->fops->report_zones(disk, 0, UINT_MAX,
blk_revalidate_zone_cb, &args);
if (!ret) {
pr_warn("%s: No zones reported\n", disk->disk_name);
ret = -ENODEV;
}
memalloc_noio_restore(noio_flag);
/*
* If zones where reported, make sure that the entire disk capacity
* has been checked.
*/
if (ret > 0 && args.sector != capacity) {
pr_warn("%s: Missing zones from sector %llu\n",
disk->disk_name, args.sector);
ret = -ENODEV;
}
/*
* Install the new bitmaps and update nr_zones only once the queue is
* stopped and all I/Os are completed (i.e. a scheduler is not
* referencing the bitmaps).
*/
blk_mq_freeze_queue(q);
if (ret > 0) {
disk->nr_zones = args.nr_zones;
disk->zone_capacity = args.zone_capacity;
swap(disk->seq_zones_wlock, args.seq_zones_wlock);
swap(disk->conv_zones_bitmap, args.conv_zones_bitmap);
if (update_driver_data)
update_driver_data(disk);
ret = 0;
} else {
pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
disk_free_zone_resources(disk);
}
blk_mq_unfreeze_queue(q);
kfree(args.seq_zones_wlock);
kfree(args.conv_zones_bitmap);
return ret;
}
EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
|