summaryrefslogtreecommitdiff
path: root/zbd.c
blob: d1db9adc296a74a1bcd53203b7370eb767246406 (plain)
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
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
/*
 * Copyright (C) 2018 Western Digital Corporation or its affiliates.
 *
 * This file is released under the GPL.
 */

#include <errno.h>
#include <string.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <unistd.h>

#include "os/os.h"
#include "file.h"
#include "fio.h"
#include "lib/pow2.h"
#include "log.h"
#include "oslib/asprintf.h"
#include "smalloc.h"
#include "verify.h"
#include "pshared.h"
#include "zbd.h"

/**
 * zbd_get_zoned_model - Get a device zoned model
 * @td: FIO thread data
 * @f: FIO file for which to get model information
 */
int zbd_get_zoned_model(struct thread_data *td, struct fio_file *f,
			enum zbd_zoned_model *model)
{
	int ret;

	if (f->filetype == FIO_TYPE_PIPE) {
		log_err("zonemode=zbd does not support pipes\n");
		return -EINVAL;
	}

	/* If regular file, always emulate zones inside the file. */
	if (f->filetype == FIO_TYPE_FILE) {
		*model = ZBD_NONE;
		return 0;
	}

	if (td->io_ops && td->io_ops->get_zoned_model)
		ret = td->io_ops->get_zoned_model(td, f, model);
	else
		ret = blkzoned_get_zoned_model(td, f, model);
	if (ret < 0) {
		td_verror(td, errno, "get zoned model failed");
		log_err("%s: get zoned model failed (%d).\n",
			f->file_name, errno);
	}

	return ret;
}

/**
 * zbd_report_zones - Get zone information
 * @td: FIO thread data.
 * @f: FIO file for which to get zone information
 * @offset: offset from which to report zones
 * @zones: Array of struct zbd_zone
 * @nr_zones: Size of @zones array
 *
 * Get zone information into @zones starting from the zone at offset @offset
 * for the device specified by @f.
 *
 * Returns the number of zones reported upon success and a negative error code
 * upon failure. If the zone report is empty, always assume an error (device
 * problem) and return -EIO.
 */
int zbd_report_zones(struct thread_data *td, struct fio_file *f,
		     uint64_t offset, struct zbd_zone *zones,
		     unsigned int nr_zones)
{
	int ret;

	if (td->io_ops && td->io_ops->report_zones)
		ret = td->io_ops->report_zones(td, f, offset, zones, nr_zones);
	else
		ret = blkzoned_report_zones(td, f, offset, zones, nr_zones);
	if (ret < 0) {
		td_verror(td, errno, "report zones failed");
		log_err("%s: report zones from sector %llu failed (%d).\n",
			f->file_name, (unsigned long long)offset >> 9, errno);
	} else if (ret == 0) {
		td_verror(td, errno, "Empty zone report");
		log_err("%s: report zones from sector %llu is empty.\n",
			f->file_name, (unsigned long long)offset >> 9);
		ret = -EIO;
	}

	return ret;
}

/**
 * zbd_reset_wp - reset the write pointer of a range of zones
 * @td: FIO thread data.
 * @f: FIO file for which to reset zones
 * @offset: Starting offset of the first zone to reset
 * @length: Length of the range of zones to reset
 *
 * Reset the write pointer of all zones in the range @offset...@offset+@length.
 * Returns 0 upon success and a negative error code upon failure.
 */
int zbd_reset_wp(struct thread_data *td, struct fio_file *f,
		 uint64_t offset, uint64_t length)
{
	int ret;

	if (td->io_ops && td->io_ops->reset_wp)
		ret = td->io_ops->reset_wp(td, f, offset, length);
	else
		ret = blkzoned_reset_wp(td, f, offset, length);
	if (ret < 0) {
		td_verror(td, errno, "resetting wp failed");
		log_err("%s: resetting wp for %llu sectors at sector %llu failed (%d).\n",
			f->file_name, (unsigned long long)length >> 9,
			(unsigned long long)offset >> 9, errno);
	}

	return ret;
}

/**
 * zbd_get_max_open_zones - Get the maximum number of open zones
 * @td: FIO thread data
 * @f: FIO file for which to get max open zones
 * @max_open_zones: Upon success, result will be stored here.
 *
 * A @max_open_zones value set to zero means no limit.
 *
 * Returns 0 upon success and a negative error code upon failure.
 */
int zbd_get_max_open_zones(struct thread_data *td, struct fio_file *f,
			   unsigned int *max_open_zones)
{
	int ret;

	if (td->io_ops && td->io_ops->get_max_open_zones)
		ret = td->io_ops->get_max_open_zones(td, f, max_open_zones);
	else
		ret = blkzoned_get_max_open_zones(td, f, max_open_zones);
	if (ret < 0) {
		td_verror(td, errno, "get max open zones failed");
		log_err("%s: get max open zones failed (%d).\n",
			f->file_name, errno);
	}

	return ret;
}

/**
 * zbd_zone_idx - convert an offset into a zone number
 * @f: file pointer.
 * @offset: offset in bytes. If this offset is in the first zone_size bytes
 *	    past the disk size then the index of the sentinel is returned.
 */
static uint32_t zbd_zone_idx(const struct fio_file *f, uint64_t offset)
{
	uint32_t zone_idx;

	if (f->zbd_info->zone_size_log2 > 0)
		zone_idx = offset >> f->zbd_info->zone_size_log2;
	else
		zone_idx = offset / f->zbd_info->zone_size;

	return min(zone_idx, f->zbd_info->nr_zones);
}

/**
 * zbd_zone_end - Return zone end location
 * @z: zone info pointer.
 */
static inline uint64_t zbd_zone_end(const struct fio_zone_info *z)
{
	return (z+1)->start;
}

/**
 * zbd_zone_capacity_end - Return zone capacity limit end location
 * @z: zone info pointer.
 */
static inline uint64_t zbd_zone_capacity_end(const struct fio_zone_info *z)
{
	return z->start + z->capacity;
}

/**
 * zbd_zone_full - verify whether a minimum number of bytes remain in a zone
 * @f: file pointer.
 * @z: zone info pointer.
 * @required: minimum number of bytes that must remain in a zone.
 *
 * The caller must hold z->mutex.
 */
static bool zbd_zone_full(const struct fio_file *f, struct fio_zone_info *z,
			  uint64_t required)
{
	assert((required & 511) == 0);

	return z->has_wp &&
		z->wp + required > zbd_zone_capacity_end(z);
}

static void zone_lock(struct thread_data *td, const struct fio_file *f,
		      struct fio_zone_info *z)
{
	struct zoned_block_device_info *zbd = f->zbd_info;
	uint32_t nz = z - zbd->zone_info;

	/* A thread should never lock zones outside its working area. */
	assert(f->min_zone <= nz && nz < f->max_zone);

	assert(z->has_wp);

	/*
	 * Lock the io_u target zone. The zone will be unlocked if io_u offset
	 * is changed or when io_u completes and zbd_put_io() executed.
	 * To avoid multiple jobs doing asynchronous I/Os from deadlocking each
	 * other waiting for zone locks when building an io_u batch, first
	 * only trylock the zone. If the zone is already locked by another job,
	 * process the currently queued I/Os so that I/O progress is made and
	 * zones unlocked.
	 */
	if (pthread_mutex_trylock(&z->mutex) != 0) {
		if (!td_ioengine_flagged(td, FIO_SYNCIO))
			io_u_quiesce(td);
		pthread_mutex_lock(&z->mutex);
	}
}

static inline void zone_unlock(struct fio_zone_info *z)
{
	int ret;

	assert(z->has_wp);
	ret = pthread_mutex_unlock(&z->mutex);
	assert(!ret);
}

static bool is_valid_offset(const struct fio_file *f, uint64_t offset)
{
	return (uint64_t)(offset - f->file_offset) < f->io_size;
}

static inline struct fio_zone_info *get_zone(const struct fio_file *f,
					     unsigned int zone_nr)
{
	return &f->zbd_info->zone_info[zone_nr];
}

/* Verify whether direct I/O is used for all host-managed zoned drives. */
static bool zbd_using_direct_io(void)
{
	struct thread_data *td;
	struct fio_file *f;
	int i, j;

	for_each_td(td, i) {
		if (td->o.odirect || !(td->o.td_ddir & TD_DDIR_WRITE))
			continue;
		for_each_file(td, f, j) {
			if (f->zbd_info &&
			    f->zbd_info->model == ZBD_HOST_MANAGED)
				return false;
		}
	}

	return true;
}

/* Whether or not the I/O range for f includes one or more sequential zones */
static bool zbd_is_seq_job(struct fio_file *f)
{
	uint32_t zone_idx, zone_idx_b, zone_idx_e;

	assert(f->zbd_info);
	if (f->io_size == 0)
		return false;
	zone_idx_b = zbd_zone_idx(f, f->file_offset);
	zone_idx_e = zbd_zone_idx(f, f->file_offset + f->io_size - 1);
	for (zone_idx = zone_idx_b; zone_idx <= zone_idx_e; zone_idx++)
		if (get_zone(f, zone_idx)->has_wp)
			return true;

	return false;
}

/*
 * Verify whether offset and size parameters are aligned with zone boundaries.
 */
static bool zbd_verify_sizes(void)
{
	const struct fio_zone_info *z;
	struct thread_data *td;
	struct fio_file *f;
	uint64_t new_offset, new_end;
	uint32_t zone_idx;
	int i, j;

	for_each_td(td, i) {
		for_each_file(td, f, j) {
			if (!f->zbd_info)
				continue;
			if (f->file_offset >= f->real_file_size)
				continue;
			if (!zbd_is_seq_job(f))
				continue;

			if (!td->o.zone_size) {
				td->o.zone_size = f->zbd_info->zone_size;
				if (!td->o.zone_size) {
					log_err("%s: invalid 0 zone size\n",
						f->file_name);
					return false;
				}
			} else if (td->o.zone_size != f->zbd_info->zone_size) {
				log_err("%s: job parameter zonesize %llu does not match disk zone size %llu.\n",
					f->file_name, (unsigned long long) td->o.zone_size,
					(unsigned long long) f->zbd_info->zone_size);
				return false;
			}

			if (td->o.zone_skip % td->o.zone_size) {
				log_err("%s: zoneskip %llu is not a multiple of the device zone size %llu.\n",
					f->file_name, (unsigned long long) td->o.zone_skip,
					(unsigned long long) td->o.zone_size);
				return false;
			}

			zone_idx = zbd_zone_idx(f, f->file_offset);
			z = get_zone(f, zone_idx);
			if ((f->file_offset != z->start) &&
			    (td->o.td_ddir != TD_DDIR_READ)) {
				new_offset = zbd_zone_end(z);
				if (new_offset >= f->file_offset + f->io_size) {
					log_info("%s: io_size must be at least one zone\n",
						 f->file_name);
					return false;
				}
				log_info("%s: rounded up offset from %llu to %llu\n",
					 f->file_name, (unsigned long long) f->file_offset,
					 (unsigned long long) new_offset);
				f->io_size -= (new_offset - f->file_offset);
				f->file_offset = new_offset;
			}
			zone_idx = zbd_zone_idx(f, f->file_offset + f->io_size);
			z = get_zone(f, zone_idx);
			new_end = z->start;
			if ((td->o.td_ddir != TD_DDIR_READ) &&
			    (f->file_offset + f->io_size != new_end)) {
				if (new_end <= f->file_offset) {
					log_info("%s: io_size must be at least one zone\n",
						 f->file_name);
					return false;
				}
				log_info("%s: rounded down io_size from %llu to %llu\n",
					 f->file_name, (unsigned long long) f->io_size,
					 (unsigned long long) new_end - f->file_offset);
				f->io_size = new_end - f->file_offset;
			}
		}
	}

	return true;
}

static bool zbd_verify_bs(void)
{
	struct thread_data *td;
	struct fio_file *f;
	int i, j, k;

	for_each_td(td, i) {
		for_each_file(td, f, j) {
			uint64_t zone_size;

			if (!f->zbd_info)
				continue;
			zone_size = f->zbd_info->zone_size;
			for (k = 0; k < FIO_ARRAY_SIZE(td->o.bs); k++) {
				if (td->o.verify != VERIFY_NONE &&
				    zone_size % td->o.bs[k] != 0) {
					log_info("%s: block size %llu is not a divisor of the zone size %llu\n",
						 f->file_name, td->o.bs[k],
						 (unsigned long long)zone_size);
					return false;
				}
			}
		}
	}
	return true;
}

static int ilog2(uint64_t i)
{
	int log = -1;

	while (i) {
		i >>= 1;
		log++;
	}
	return log;
}

/*
 * Initialize f->zbd_info for devices that are not zoned block devices. This
 * allows to execute a ZBD workload against a non-ZBD device.
 */
static int init_zone_info(struct thread_data *td, struct fio_file *f)
{
	uint32_t nr_zones;
	struct fio_zone_info *p;
	uint64_t zone_size = td->o.zone_size;
	uint64_t zone_capacity = td->o.zone_capacity;
	struct zoned_block_device_info *zbd_info = NULL;
	int i;

	if (zone_size == 0) {
		log_err("%s: Specifying the zone size is mandatory for regular file/block device with --zonemode=zbd\n\n",
			f->file_name);
		return 1;
	}

	if (zone_size < 512) {
		log_err("%s: zone size must be at least 512 bytes for --zonemode=zbd\n\n",
			f->file_name);
		return 1;
	}

	if (zone_capacity == 0)
		zone_capacity = zone_size;

	if (zone_capacity > zone_size) {
		log_err("%s: job parameter zonecapacity %llu is larger than zone size %llu\n",
			f->file_name, (unsigned long long) td->o.zone_capacity,
			(unsigned long long) td->o.zone_size);
		return 1;
	}

	if (f->real_file_size < zone_size) {
		log_err("%s: file/device size %"PRIu64" is smaller than zone size %"PRIu64"\n",
			f->file_name, f->real_file_size, zone_size);
		return -EINVAL;
	}

	nr_zones = (f->real_file_size + zone_size - 1) / zone_size;
	zbd_info = scalloc(1, sizeof(*zbd_info) +
			   (nr_zones + 1) * sizeof(zbd_info->zone_info[0]));
	if (!zbd_info)
		return -ENOMEM;

	mutex_init_pshared(&zbd_info->mutex);
	zbd_info->refcount = 1;
	p = &zbd_info->zone_info[0];
	for (i = 0; i < nr_zones; i++, p++) {
		mutex_init_pshared_with_type(&p->mutex,
					     PTHREAD_MUTEX_RECURSIVE);
		p->start = i * zone_size;
		p->wp = p->start;
		p->type = ZBD_ZONE_TYPE_SWR;
		p->cond = ZBD_ZONE_COND_EMPTY;
		p->capacity = zone_capacity;
		p->has_wp = 1;
	}
	/* a sentinel */
	p->start = nr_zones * zone_size;

	f->zbd_info = zbd_info;
	f->zbd_info->zone_size = zone_size;
	f->zbd_info->zone_size_log2 = is_power_of_2(zone_size) ?
		ilog2(zone_size) : 0;
	f->zbd_info->nr_zones = nr_zones;
	return 0;
}

/*
 * Maximum number of zones to report in one operation.
 */
#define ZBD_REPORT_MAX_ZONES	8192U

/*
 * Parse the device zone report and store it in f->zbd_info. Must be called
 * only for devices that are zoned, namely those with a model != ZBD_NONE.
 */
static int parse_zone_info(struct thread_data *td, struct fio_file *f)
{
	int nr_zones, nrz;
	struct zbd_zone *zones, *z;
	struct fio_zone_info *p;
	uint64_t zone_size, offset;
	struct zoned_block_device_info *zbd_info = NULL;
	int i, j, ret = -ENOMEM;

	zones = calloc(ZBD_REPORT_MAX_ZONES, sizeof(struct zbd_zone));
	if (!zones)
		goto out;

	nrz = zbd_report_zones(td, f, 0, zones, ZBD_REPORT_MAX_ZONES);
	if (nrz < 0) {
		ret = nrz;
		log_info("fio: report zones (offset 0) failed for %s (%d).\n",
			 f->file_name, -ret);
		goto out;
	}

	zone_size = zones[0].len;
	nr_zones = (f->real_file_size + zone_size - 1) / zone_size;

	if (td->o.zone_size == 0) {
		td->o.zone_size = zone_size;
	} else if (td->o.zone_size != zone_size) {
		log_err("fio: %s job parameter zonesize %llu does not match disk zone size %llu.\n",
			f->file_name, (unsigned long long) td->o.zone_size,
			(unsigned long long) zone_size);
		ret = -EINVAL;
		goto out;
	}

	dprint(FD_ZBD, "Device %s has %d zones of size %llu KB\n", f->file_name,
	       nr_zones, (unsigned long long) zone_size / 1024);

	zbd_info = scalloc(1, sizeof(*zbd_info) +
			   (nr_zones + 1) * sizeof(zbd_info->zone_info[0]));
	if (!zbd_info)
		goto out;
	mutex_init_pshared(&zbd_info->mutex);
	zbd_info->refcount = 1;
	p = &zbd_info->zone_info[0];
	for (offset = 0, j = 0; j < nr_zones;) {
		z = &zones[0];
		for (i = 0; i < nrz; i++, j++, z++, p++) {
			mutex_init_pshared_with_type(&p->mutex,
						     PTHREAD_MUTEX_RECURSIVE);
			p->start = z->start;
			p->capacity = z->capacity;
			switch (z->cond) {
			case ZBD_ZONE_COND_NOT_WP:
			case ZBD_ZONE_COND_FULL:
				p->wp = p->start + p->capacity;
				break;
			default:
				assert(z->start <= z->wp);
				assert(z->wp <= z->start + zone_size);
				p->wp = z->wp;
				break;
			}

			switch (z->type) {
			case ZBD_ZONE_TYPE_SWR:
				p->has_wp = 1;
				break;
			default:
				p->has_wp = 0;
			}
			p->type = z->type;
			p->cond = z->cond;

			if (j > 0 && p->start != p[-1].start + zone_size) {
				log_info("%s: invalid zone data\n",
					 f->file_name);
				ret = -EINVAL;
				goto out;
			}
		}
		z--;
		offset = z->start + z->len;
		if (j >= nr_zones)
			break;
		nrz = zbd_report_zones(td, f, offset, zones,
				       min((uint32_t)(nr_zones - j),
					   ZBD_REPORT_MAX_ZONES));
		if (nrz < 0) {
			ret = nrz;
			log_info("fio: report zones (offset %llu) failed for %s (%d).\n",
			 	 (unsigned long long)offset,
				 f->file_name, -ret);
			goto out;
		}
	}

	/* a sentinel */
	zbd_info->zone_info[nr_zones].start = offset;

	f->zbd_info = zbd_info;
	f->zbd_info->zone_size = zone_size;
	f->zbd_info->zone_size_log2 = is_power_of_2(zone_size) ?
		ilog2(zone_size) : 0;
	f->zbd_info->nr_zones = nr_zones;
	zbd_info = NULL;
	ret = 0;

out:
	sfree(zbd_info);
	free(zones);
	return ret;
}

static int zbd_set_max_open_zones(struct thread_data *td, struct fio_file *f)
{
	struct zoned_block_device_info *zbd = f->zbd_info;
	unsigned int max_open_zones;
	int ret;

	if (zbd->model != ZBD_HOST_MANAGED || td->o.ignore_zone_limits) {
		/* Only host-managed devices have a max open limit */
		zbd->max_open_zones = td->o.max_open_zones;
		goto out;
	}

	/* If host-managed, get the max open limit */
	ret = zbd_get_max_open_zones(td, f, &max_open_zones);
	if (ret)
		return ret;

	if (!max_open_zones) {
		/* No device limit */
		zbd->max_open_zones = td->o.max_open_zones;
	} else if (!td->o.max_open_zones) {
		/* No user limit. Set limit to device limit */
		zbd->max_open_zones = max_open_zones;
	} else if (td->o.max_open_zones <= max_open_zones) {
		/* Both user limit and dev limit. User limit not too large */
		zbd->max_open_zones = td->o.max_open_zones;
	} else {
		/* Both user limit and dev limit. User limit too large */
		td_verror(td, EINVAL,
			  "Specified --max_open_zones is too large");
		log_err("Specified --max_open_zones (%d) is larger than max (%u)\n",
			td->o.max_open_zones, max_open_zones);
		return -EINVAL;
	}

out:
	/* Ensure that the limit is not larger than FIO's internal limit */
	zbd->max_open_zones = min_not_zero(zbd->max_open_zones,
					   (uint32_t) ZBD_MAX_OPEN_ZONES);
	dprint(FD_ZBD, "%s: using max open zones limit: %"PRIu32"\n",
	       f->file_name, zbd->max_open_zones);

	return 0;
}

/*
 * Allocate zone information and store it into f->zbd_info if zonemode=zbd.
 *
 * Returns 0 upon success and a negative error code upon failure.
 */
static int zbd_create_zone_info(struct thread_data *td, struct fio_file *f)
{
	enum zbd_zoned_model zbd_model;
	int ret;

	assert(td->o.zone_mode == ZONE_MODE_ZBD);

	ret = zbd_get_zoned_model(td, f, &zbd_model);
	if (ret)
		return ret;

	switch (zbd_model) {
	case ZBD_IGNORE:
		return 0;
	case ZBD_HOST_AWARE:
	case ZBD_HOST_MANAGED:
		ret = parse_zone_info(td, f);
		if (ret)
			return ret;
		break;
	case ZBD_NONE:
		ret = init_zone_info(td, f);
		if (ret)
			return ret;
		break;
	default:
		td_verror(td, EINVAL, "Unsupported zoned model");
		log_err("Unsupported zoned model\n");
		return -EINVAL;
	}

	f->zbd_info->model = zbd_model;

	ret = zbd_set_max_open_zones(td, f);
	if (ret) {
		zbd_free_zone_info(f);
		return ret;
	}

	return 0;
}

void zbd_free_zone_info(struct fio_file *f)
{
	uint32_t refcount;

	assert(f->zbd_info);

	pthread_mutex_lock(&f->zbd_info->mutex);
	refcount = --f->zbd_info->refcount;
	pthread_mutex_unlock(&f->zbd_info->mutex);

	assert((int32_t)refcount >= 0);
	if (refcount == 0)
		sfree(f->zbd_info);
	f->zbd_info = NULL;
}

/*
 * Initialize f->zbd_info.
 *
 * Returns 0 upon success and a negative error code upon failure.
 *
 * Note: this function can only work correctly if it is called before the first
 * fio fork() call.
 */
static int zbd_init_zone_info(struct thread_data *td, struct fio_file *file)
{
	struct thread_data *td2;
	struct fio_file *f2;
	int i, j, ret;

	for_each_td(td2, i) {
		for_each_file(td2, f2, j) {
			if (td2 == td && f2 == file)
				continue;
			if (!f2->zbd_info ||
			    strcmp(f2->file_name, file->file_name) != 0)
				continue;
			file->zbd_info = f2->zbd_info;
			file->zbd_info->refcount++;
			return 0;
		}
	}

	ret = zbd_create_zone_info(td, file);
	if (ret < 0)
		td_verror(td, -ret, "zbd_create_zone_info() failed");
	return ret;
}

static bool zbd_open_zone(struct thread_data *td, const struct fio_file *f,
			  uint32_t zone_idx);
static int zbd_reset_zone(struct thread_data *td, struct fio_file *f,
			  struct fio_zone_info *z);

int zbd_init_files(struct thread_data *td)
{
	struct fio_file *f;
	int i;

	for_each_file(td, f, i) {
		if (zbd_init_zone_info(td, f))
			return 1;
	}
	return 0;
}

void zbd_recalc_options_with_zone_granularity(struct thread_data *td)
{
	struct fio_file *f;
	int i;

	for_each_file(td, f, i) {
		struct zoned_block_device_info *zbd = f->zbd_info;
		// zonemode=strided doesn't get per-file zone size.
		uint64_t zone_size = zbd ? zbd->zone_size : td->o.zone_size;

		if (zone_size == 0)
			continue;

		if (td->o.size_nz > 0) {
			td->o.size = td->o.size_nz * zone_size;
		}
		if (td->o.io_size_nz > 0) {
			td->o.io_size = td->o.io_size_nz * zone_size;
		}
		if (td->o.start_offset_nz > 0) {
			td->o.start_offset = td->o.start_offset_nz * zone_size;
		}
		if (td->o.offset_increment_nz > 0) {
			td->o.offset_increment = td->o.offset_increment_nz * zone_size;
		}
		if (td->o.zone_skip_nz > 0) {
			td->o.zone_skip = td->o.zone_skip_nz * zone_size;
		}
	}
}

int zbd_setup_files(struct thread_data *td)
{
	struct fio_file *f;
	int i;

	if (!zbd_using_direct_io()) {
		log_err("Using direct I/O is mandatory for writing to ZBD drives\n\n");
		return 1;
	}

	if (!zbd_verify_sizes())
		return 1;

	if (!zbd_verify_bs())
		return 1;

	for_each_file(td, f, i) {
		struct zoned_block_device_info *zbd = f->zbd_info;
		struct fio_zone_info *z;
		int zi;

		if (!zbd)
			continue;

		f->min_zone = zbd_zone_idx(f, f->file_offset);
		f->max_zone = zbd_zone_idx(f, f->file_offset + f->io_size);

		/*
		 * When all zones in the I/O range are conventional, io_size
		 * can be smaller than zone size, making min_zone the same
		 * as max_zone. This is why the assert below needs to be made
		 * conditional.
		 */
		if (zbd_is_seq_job(f))
			assert(f->min_zone < f->max_zone);

		if (td->o.max_open_zones > 0 &&
		    zbd->max_open_zones != td->o.max_open_zones) {
			log_err("Different 'max_open_zones' values\n");
			return 1;
		}
		if (zbd->max_open_zones > ZBD_MAX_OPEN_ZONES) {
			log_err("'max_open_zones' value is limited by %u\n", ZBD_MAX_OPEN_ZONES);
			return 1;
		}

		for (zi = f->min_zone; zi < f->max_zone; zi++) {
			z = &zbd->zone_info[zi];
			if (z->cond != ZBD_ZONE_COND_IMP_OPEN &&
			    z->cond != ZBD_ZONE_COND_EXP_OPEN)
				continue;
			if (zbd_open_zone(td, f, zi))
				continue;
			/*
			 * If the number of open zones exceeds specified limits,
			 * reset all extra open zones.
			 */
			if (zbd_reset_zone(td, f, z) < 0) {
				log_err("Failed to reest zone %d\n", zi);
				return 1;
			}
		}
	}

	return 0;
}

static inline unsigned int zbd_zone_nr(const struct fio_file *f,
				       struct fio_zone_info *zone)
{
	return zone - f->zbd_info->zone_info;
}

/**
 * zbd_reset_zone - reset the write pointer of a single zone
 * @td: FIO thread data.
 * @f: FIO file associated with the disk for which to reset a write pointer.
 * @z: Zone to reset.
 *
 * Returns 0 upon success and a negative error code upon failure.
 *
 * The caller must hold z->mutex.
 */
static int zbd_reset_zone(struct thread_data *td, struct fio_file *f,
			  struct fio_zone_info *z)
{
	uint64_t offset = z->start;
	uint64_t length = (z+1)->start - offset;
	uint64_t data_in_zone = z->wp - z->start;
	int ret = 0;

	if (!data_in_zone)
		return 0;

	assert(is_valid_offset(f, offset + length - 1));

	dprint(FD_ZBD, "%s: resetting wp of zone %u.\n", f->file_name,
		zbd_zone_nr(f, z));
	switch (f->zbd_info->model) {
	case ZBD_HOST_AWARE:
	case ZBD_HOST_MANAGED:
		ret = zbd_reset_wp(td, f, offset, length);
		if (ret < 0)
			return ret;
		break;
	default:
		break;
	}

	pthread_mutex_lock(&f->zbd_info->mutex);
	f->zbd_info->sectors_with_data -= data_in_zone;
	f->zbd_info->wp_sectors_with_data -= data_in_zone;
	pthread_mutex_unlock(&f->zbd_info->mutex);
	z->wp = z->start;
	z->verify_block = 0;

	td->ts.nr_zone_resets++;

	return ret;
}

/* The caller must hold f->zbd_info->mutex */
static void zbd_close_zone(struct thread_data *td, const struct fio_file *f,
			   unsigned int zone_idx)
{
	uint32_t open_zone_idx = 0;

	for (; open_zone_idx < f->zbd_info->num_open_zones; open_zone_idx++) {
		if (f->zbd_info->open_zones[open_zone_idx] == zone_idx)
			break;
	}
	if (open_zone_idx == f->zbd_info->num_open_zones)
		return;

	dprint(FD_ZBD, "%s: closing zone %d\n", f->file_name, zone_idx);
	memmove(f->zbd_info->open_zones + open_zone_idx,
		f->zbd_info->open_zones + open_zone_idx + 1,
		(ZBD_MAX_OPEN_ZONES - (open_zone_idx + 1)) *
		sizeof(f->zbd_info->open_zones[0]));
	f->zbd_info->num_open_zones--;
	td->num_open_zones--;
	get_zone(f, zone_idx)->open = 0;
}

/*
 * Reset a range of zones. Returns 0 upon success and 1 upon failure.
 * @td: fio thread data.
 * @f: fio file for which to reset zones
 * @zb: first zone to reset.
 * @ze: first zone not to reset.
 */
static int zbd_reset_zones(struct thread_data *td, struct fio_file *f,
			   struct fio_zone_info *const zb,
			   struct fio_zone_info *const ze)
{
	struct fio_zone_info *z;
	const uint32_t min_bs = td->o.min_bs[DDIR_WRITE];
	int res = 0;

	assert(min_bs);

	dprint(FD_ZBD, "%s: examining zones %u .. %u\n", f->file_name,
		zbd_zone_nr(f, zb), zbd_zone_nr(f, ze));
	for (z = zb; z < ze; z++) {
		uint32_t nz = zbd_zone_nr(f, z);

		if (!z->has_wp)
			continue;
		zone_lock(td, f, z);
		pthread_mutex_lock(&f->zbd_info->mutex);
		zbd_close_zone(td, f, nz);
		pthread_mutex_unlock(&f->zbd_info->mutex);
		if (z->wp != z->start) {
			dprint(FD_ZBD, "%s: resetting zone %u\n",
			       f->file_name, zbd_zone_nr(f, z));
			if (zbd_reset_zone(td, f, z) < 0)
				res = 1;
		}
		zone_unlock(z);
	}

	return res;
}

/*
 * Reset zbd_info.write_cnt, the counter that counts down towards the next
 * zone reset.
 */
static void _zbd_reset_write_cnt(const struct thread_data *td,
				 const struct fio_file *f)
{
	assert(0 <= td->o.zrf.u.f && td->o.zrf.u.f <= 1);

	f->zbd_info->write_cnt = td->o.zrf.u.f ?
		min(1.0 / td->o.zrf.u.f, 0.0 + UINT_MAX) : UINT_MAX;
}

static void zbd_reset_write_cnt(const struct thread_data *td,
				const struct fio_file *f)
{
	pthread_mutex_lock(&f->zbd_info->mutex);
	_zbd_reset_write_cnt(td, f);
	pthread_mutex_unlock(&f->zbd_info->mutex);
}

static bool zbd_dec_and_reset_write_cnt(const struct thread_data *td,
					const struct fio_file *f)
{
	uint32_t write_cnt = 0;

	pthread_mutex_lock(&f->zbd_info->mutex);
	assert(f->zbd_info->write_cnt);
	if (f->zbd_info->write_cnt)
		write_cnt = --f->zbd_info->write_cnt;
	if (write_cnt == 0)
		_zbd_reset_write_cnt(td, f);
	pthread_mutex_unlock(&f->zbd_info->mutex);

	return write_cnt == 0;
}

enum swd_action {
	CHECK_SWD,
	SET_SWD,
};

/* Calculate the number of sectors with data (swd) and perform action 'a' */
static uint64_t zbd_process_swd(struct thread_data *td,
				const struct fio_file *f, enum swd_action a)
{
	struct fio_zone_info *zb, *ze, *z;
	uint64_t swd = 0;
	uint64_t wp_swd = 0;

	zb = get_zone(f, f->min_zone);
	ze = get_zone(f, f->max_zone);
	for (z = zb; z < ze; z++) {
		if (z->has_wp) {
			zone_lock(td, f, z);
			wp_swd += z->wp - z->start;
		}
		swd += z->wp - z->start;
	}
	pthread_mutex_lock(&f->zbd_info->mutex);
	switch (a) {
	case CHECK_SWD:
		assert(f->zbd_info->sectors_with_data == swd);
		assert(f->zbd_info->wp_sectors_with_data == wp_swd);
		break;
	case SET_SWD:
		f->zbd_info->sectors_with_data = swd;
		f->zbd_info->wp_sectors_with_data = wp_swd;
		break;
	}
	pthread_mutex_unlock(&f->zbd_info->mutex);
	for (z = zb; z < ze; z++)
		if (z->has_wp)
			zone_unlock(z);

	return swd;
}

/*
 * The swd check is useful for debugging but takes too much time to leave
 * it enabled all the time. Hence it is disabled by default.
 */
static const bool enable_check_swd = false;

/* Check whether the values of zbd_info.*sectors_with_data are correct. */
static void zbd_check_swd(struct thread_data *td, const struct fio_file *f)
{
	if (!enable_check_swd)
		return;

	zbd_process_swd(td, f, CHECK_SWD);
}

void zbd_file_reset(struct thread_data *td, struct fio_file *f)
{
	struct fio_zone_info *zb, *ze;
	uint64_t swd;

	if (!f->zbd_info || !td_write(td))
		return;

	zb = get_zone(f, f->min_zone);
	ze = get_zone(f, f->max_zone);
	swd = zbd_process_swd(td, f, SET_SWD);
	dprint(FD_ZBD, "%s(%s): swd = %" PRIu64 "\n", __func__, f->file_name,
	       swd);
	/*
	 * If data verification is enabled reset the affected zones before
	 * writing any data to avoid that a zone reset has to be issued while
	 * writing data, which causes data loss.
	 */
	if (td->o.verify != VERIFY_NONE && td->runstate != TD_VERIFYING)
		zbd_reset_zones(td, f, zb, ze);
	zbd_reset_write_cnt(td, f);
}

/* The caller must hold f->zbd_info->mutex. */
static bool is_zone_open(const struct thread_data *td, const struct fio_file *f,
			 unsigned int zone_idx)
{
	struct zoned_block_device_info *zbdi = f->zbd_info;
	int i;

	assert(td->o.job_max_open_zones == 0 || td->num_open_zones <= td->o.job_max_open_zones);
	assert(td->o.job_max_open_zones <= zbdi->max_open_zones);
	assert(zbdi->num_open_zones <= zbdi->max_open_zones);

	for (i = 0; i < zbdi->num_open_zones; i++)
		if (zbdi->open_zones[i] == zone_idx)
			return true;

	return false;
}

/*
 * Open a ZBD zone if it was not yet open. Returns true if either the zone was
 * already open or if opening a new zone is allowed. Returns false if the zone
 * was not yet open and opening a new zone would cause the zone limit to be
 * exceeded.
 */
static bool zbd_open_zone(struct thread_data *td, const struct fio_file *f,
			  uint32_t zone_idx)
{
	const uint32_t min_bs = td->o.min_bs[DDIR_WRITE];
	struct fio_zone_info *z = get_zone(f, zone_idx);
	bool res = true;

	if (z->cond == ZBD_ZONE_COND_OFFLINE)
		return false;

	/*
	 * Skip full zones with data verification enabled because resetting a
	 * zone causes data loss and hence causes verification to fail.
	 */
	if (td->o.verify != VERIFY_NONE && zbd_zone_full(f, z, min_bs))
		return false;

	pthread_mutex_lock(&f->zbd_info->mutex);
	if (is_zone_open(td, f, zone_idx)) {
		/*
		 * If the zone is already open and going to be full by writes
		 * in-flight, handle it as a full zone instead of an open zone.
		 */
		if (z->wp >= zbd_zone_capacity_end(z))
			res = false;
		goto out;
	}
	res = false;
	/* Zero means no limit */
	if (td->o.job_max_open_zones > 0 &&
	    td->num_open_zones >= td->o.job_max_open_zones)
		goto out;
	if (f->zbd_info->num_open_zones >= f->zbd_info->max_open_zones)
		goto out;
	dprint(FD_ZBD, "%s: opening zone %d\n", f->file_name, zone_idx);
	f->zbd_info->open_zones[f->zbd_info->num_open_zones++] = zone_idx;
	td->num_open_zones++;
	z->open = 1;
	res = true;

out:
	pthread_mutex_unlock(&f->zbd_info->mutex);
	return res;
}

/* Anything goes as long as it is not a constant. */
static uint32_t pick_random_zone_idx(const struct fio_file *f,
				     const struct io_u *io_u)
{
	return io_u->offset * f->zbd_info->num_open_zones / f->real_file_size;
}

/*
 * Modify the offset of an I/O unit that does not refer to an open zone such
 * that it refers to an open zone. Close an open zone and open a new zone if
 * necessary. The open zone is searched across sequential zones.
 * This algorithm can only work correctly if all write pointers are
 * a multiple of the fio block size. The caller must neither hold z->mutex
 * nor f->zbd_info->mutex. Returns with z->mutex held upon success.
 */
static struct fio_zone_info *zbd_convert_to_open_zone(struct thread_data *td,
						      struct io_u *io_u)
{
	const uint32_t min_bs = td->o.min_bs[io_u->ddir];
	struct fio_file *f = io_u->file;
	struct fio_zone_info *z;
	unsigned int open_zone_idx = -1;
	uint32_t zone_idx, new_zone_idx;
	int i;
	bool wait_zone_close;

	assert(is_valid_offset(f, io_u->offset));

	if (td->o.max_open_zones || td->o.job_max_open_zones) {
		/*
		 * This statement accesses f->zbd_info->open_zones[] on purpose
		 * without locking.
		 */
		zone_idx = f->zbd_info->open_zones[pick_random_zone_idx(f, io_u)];
	} else {
		zone_idx = zbd_zone_idx(f, io_u->offset);
	}
	if (zone_idx < f->min_zone)
		zone_idx = f->min_zone;
	else if (zone_idx >= f->max_zone)
		zone_idx = f->max_zone - 1;
	dprint(FD_ZBD, "%s(%s): starting from zone %d (offset %lld, buflen %lld)\n",
	       __func__, f->file_name, zone_idx, io_u->offset, io_u->buflen);

	/*
	 * Since z->mutex is the outer lock and f->zbd_info->mutex the inner
	 * lock it can happen that the state of the zone with index zone_idx
	 * has changed after 'z' has been assigned and before f->zbd_info->mutex
	 * has been obtained. Hence the loop.
	 */
	for (;;) {
		uint32_t tmp_idx;

		z = get_zone(f, zone_idx);
		if (z->has_wp)
			zone_lock(td, f, z);
		pthread_mutex_lock(&f->zbd_info->mutex);
		if (z->has_wp) {
			if (z->cond != ZBD_ZONE_COND_OFFLINE &&
			    td->o.max_open_zones == 0 && td->o.job_max_open_zones == 0)
				goto examine_zone;
			if (f->zbd_info->num_open_zones == 0) {
				dprint(FD_ZBD, "%s(%s): no zones are open\n",
				       __func__, f->file_name);
				goto open_other_zone;
			}
		}

		/*
		 * List of opened zones is per-device, shared across all threads.
		 * Start with quasi-random candidate zone.
		 * Ignore zones which don't belong to thread's offset/size area.
		 */
		open_zone_idx = pick_random_zone_idx(f, io_u);
		assert(!open_zone_idx ||
		       open_zone_idx < f->zbd_info->num_open_zones);
		tmp_idx = open_zone_idx;
		for (i = 0; i < f->zbd_info->num_open_zones; i++) {
			uint32_t tmpz;

			if (tmp_idx >= f->zbd_info->num_open_zones)
				tmp_idx = 0;
			tmpz = f->zbd_info->open_zones[tmp_idx];
			if (f->min_zone <= tmpz && tmpz < f->max_zone) {
				open_zone_idx = tmp_idx;
				goto found_candidate_zone;
			}

			tmp_idx++;
		}

		dprint(FD_ZBD, "%s(%s): no candidate zone\n",
			__func__, f->file_name);
		pthread_mutex_unlock(&f->zbd_info->mutex);
		if (z->has_wp)
			zone_unlock(z);
		return NULL;

found_candidate_zone:
		new_zone_idx = f->zbd_info->open_zones[open_zone_idx];
		if (new_zone_idx == zone_idx)
			break;
		zone_idx = new_zone_idx;
		pthread_mutex_unlock(&f->zbd_info->mutex);
		if (z->has_wp)
			zone_unlock(z);
	}

	/* Both z->mutex and f->zbd_info->mutex are held. */

examine_zone:
	if (z->wp + min_bs <= zbd_zone_capacity_end(z)) {
		pthread_mutex_unlock(&f->zbd_info->mutex);
		goto out;
	}

open_other_zone:
	/* Check if number of open zones reaches one of limits. */
	wait_zone_close =
		f->zbd_info->num_open_zones == f->max_zone - f->min_zone ||
		(td->o.max_open_zones &&
		 f->zbd_info->num_open_zones == td->o.max_open_zones) ||
		(td->o.job_max_open_zones &&
		 td->num_open_zones == td->o.job_max_open_zones);

	pthread_mutex_unlock(&f->zbd_info->mutex);

	/* Only z->mutex is held. */

	/*
	 * When number of open zones reaches to one of limits, wait for
	 * zone close before opening a new zone.
	 */
	if (wait_zone_close) {
		dprint(FD_ZBD, "%s(%s): quiesce to allow open zones to close\n",
		       __func__, f->file_name);
		io_u_quiesce(td);
	}

	/* Zone 'z' is full, so try to open a new zone. */
	for (i = f->io_size / f->zbd_info->zone_size; i > 0; i--) {
		zone_idx++;
		if (z->has_wp)
			zone_unlock(z);
		z++;
		if (!is_valid_offset(f, z->start)) {
			/* Wrap-around. */
			zone_idx = f->min_zone;
			z = get_zone(f, zone_idx);
		}
		assert(is_valid_offset(f, z->start));
		if (!z->has_wp)
			continue;
		zone_lock(td, f, z);
		if (z->open)
			continue;
		if (zbd_open_zone(td, f, zone_idx))
			goto out;
	}

	/* Only z->mutex is held. */

	/* Check whether the write fits in any of the already opened zones. */
	pthread_mutex_lock(&f->zbd_info->mutex);
	for (i = 0; i < f->zbd_info->num_open_zones; i++) {
		zone_idx = f->zbd_info->open_zones[i];
		if (zone_idx < f->min_zone || zone_idx >= f->max_zone)
			continue;
		pthread_mutex_unlock(&f->zbd_info->mutex);
		zone_unlock(z);

		z = get_zone(f, zone_idx);

		zone_lock(td, f, z);
		if (z->wp + min_bs <= zbd_zone_capacity_end(z))
			goto out;
		pthread_mutex_lock(&f->zbd_info->mutex);
	}
	pthread_mutex_unlock(&f->zbd_info->mutex);
	zone_unlock(z);
	dprint(FD_ZBD, "%s(%s): did not open another zone\n", __func__,
	       f->file_name);
	return NULL;

out:
	dprint(FD_ZBD, "%s(%s): returning zone %d\n", __func__, f->file_name,
	       zone_idx);
	io_u->offset = z->start;
	assert(z->has_wp);
	assert(z->cond != ZBD_ZONE_COND_OFFLINE);
	return z;
}

/* The caller must hold z->mutex. */
static struct fio_zone_info *zbd_replay_write_order(struct thread_data *td,
						    struct io_u *io_u,
						    struct fio_zone_info *z)
{
	const struct fio_file *f = io_u->file;
	const uint32_t min_bs = td->o.min_bs[DDIR_WRITE];

	if (!zbd_open_zone(td, f, zbd_zone_nr(f, z))) {
		zone_unlock(z);
		z = zbd_convert_to_open_zone(td, io_u);
		assert(z);
	}

	if (z->verify_block * min_bs >= z->capacity) {
		log_err("%s: %d * %d >= %llu\n", f->file_name, z->verify_block,
			min_bs, (unsigned long long)z->capacity);
		/*
		 * If the assertion below fails during a test run, adding
		 * "--experimental_verify=1" to the command line may help.
		 */
		assert(false);
	}
	io_u->offset = z->start + z->verify_block * min_bs;
	if (io_u->offset + io_u->buflen >= zbd_zone_capacity_end(z)) {
		log_err("%s: %llu + %llu >= %llu\n", f->file_name, io_u->offset,
			io_u->buflen, (unsigned long long) zbd_zone_capacity_end(z));
		assert(false);
	}
	z->verify_block += io_u->buflen / min_bs;

	return z;
}

/*
 * Find another zone for which @io_u fits in the readable data in the zone.
 * Search in zones @zb + 1 .. @zl. For random workload, also search in zones
 * @zb - 1 .. @zf.
 *
 * Either returns NULL or returns a zone pointer. When the zone has write
 * pointer, hold the mutex for the zone.
 */
static struct fio_zone_info *
zbd_find_zone(struct thread_data *td, struct io_u *io_u,
	      struct fio_zone_info *zb, struct fio_zone_info *zl)
{
	const uint32_t min_bs = td->o.min_bs[io_u->ddir];
	struct fio_file *f = io_u->file;
	struct fio_zone_info *z1, *z2;
	const struct fio_zone_info *const zf = get_zone(f, f->min_zone);

	/*
	 * Skip to the next non-empty zone in case of sequential I/O and to
	 * the nearest non-empty zone in case of random I/O.
	 */
	for (z1 = zb + 1, z2 = zb - 1; z1 < zl || z2 >= zf; z1++, z2--) {
		if (z1 < zl && z1->cond != ZBD_ZONE_COND_OFFLINE) {
			if (z1->has_wp)
				zone_lock(td, f, z1);
			if (z1->start + min_bs <= z1->wp)
				return z1;
			if (z1->has_wp)
				zone_unlock(z1);
		} else if (!td_random(td)) {
			break;
		}
		if (td_random(td) && z2 >= zf &&
		    z2->cond != ZBD_ZONE_COND_OFFLINE) {
			if (z2->has_wp)
				zone_lock(td, f, z2);
			if (z2->start + min_bs <= z2->wp)
				return z2;
			if (z2->has_wp)
				zone_unlock(z2);
		}
	}
	dprint(FD_ZBD, "%s: adjusting random read offset failed\n",
	       f->file_name);
	return NULL;
}

/**
 * zbd_end_zone_io - update zone status at command completion
 * @io_u: I/O unit
 * @z: zone info pointer
 *
 * If the write command made the zone full, close it.
 *
 * The caller must hold z->mutex.
 */
static void zbd_end_zone_io(struct thread_data *td, const struct io_u *io_u,
			    struct fio_zone_info *z)
{
	const struct fio_file *f = io_u->file;

	if (io_u->ddir == DDIR_WRITE &&
	    io_u->offset + io_u->buflen >= zbd_zone_capacity_end(z)) {
		pthread_mutex_lock(&f->zbd_info->mutex);
		zbd_close_zone(td, f, zbd_zone_nr(f, z));
		pthread_mutex_unlock(&f->zbd_info->mutex);
	}
}

/**
 * zbd_queue_io - update the write pointer of a sequential zone
 * @io_u: I/O unit
 * @success: Whether or not the I/O unit has been queued successfully
 * @q: queueing status (busy, completed or queued).
 *
 * For write and trim operations, update the write pointer of the I/O unit
 * target zone.
 */
static void zbd_queue_io(struct thread_data *td, struct io_u *io_u, int q,
			 bool success)
{
	const struct fio_file *f = io_u->file;
	struct zoned_block_device_info *zbd_info = f->zbd_info;
	struct fio_zone_info *z;
	uint32_t zone_idx;
	uint64_t zone_end;

	if (!zbd_info)
		return;

	zone_idx = zbd_zone_idx(f, io_u->offset);
	assert(zone_idx < zbd_info->nr_zones);
	z = get_zone(f, zone_idx);

	assert(z->has_wp);

	if (!success)
		goto unlock;

	dprint(FD_ZBD,
	       "%s: queued I/O (%lld, %llu) for zone %u\n",
	       f->file_name, io_u->offset, io_u->buflen, zone_idx);

	switch (io_u->ddir) {
	case DDIR_WRITE:
		zone_end = min((uint64_t)(io_u->offset + io_u->buflen),
			       zbd_zone_capacity_end(z));
		pthread_mutex_lock(&zbd_info->mutex);
		/*
		 * z->wp > zone_end means that one or more I/O errors
		 * have occurred.
		 */
		if (z->wp <= zone_end) {
			zbd_info->sectors_with_data += zone_end - z->wp;
			zbd_info->wp_sectors_with_data += zone_end - z->wp;
		}
		pthread_mutex_unlock(&zbd_info->mutex);
		z->wp = zone_end;
		break;
	case DDIR_TRIM:
		assert(z->wp == z->start);
		break;
	default:
		break;
	}

	if (q == FIO_Q_COMPLETED && !io_u->error)
		zbd_end_zone_io(td, io_u, z);

unlock:
	if (!success || q != FIO_Q_QUEUED) {
		/* BUSY or COMPLETED: unlock the zone */
		zone_unlock(z);
		io_u->zbd_put_io = NULL;
	}
}

/**
 * zbd_put_io - Unlock an I/O unit target zone lock
 * @io_u: I/O unit
 */
static void zbd_put_io(struct thread_data *td, const struct io_u *io_u)
{
	const struct fio_file *f = io_u->file;
	struct zoned_block_device_info *zbd_info = f->zbd_info;
	struct fio_zone_info *z;
	uint32_t zone_idx;

	if (!zbd_info)
		return;

	zone_idx = zbd_zone_idx(f, io_u->offset);
	assert(zone_idx < zbd_info->nr_zones);
	z = get_zone(f, zone_idx);

	assert(z->has_wp);

	dprint(FD_ZBD,
	       "%s: terminate I/O (%lld, %llu) for zone %u\n",
	       f->file_name, io_u->offset, io_u->buflen, zone_idx);

	zbd_end_zone_io(td, io_u, z);

	zone_unlock(z);
	zbd_check_swd(td, f);
}

/*
 * Windows and MacOS do not define this.
 */
#ifndef EREMOTEIO
#define EREMOTEIO	121	/* POSIX value */
#endif

bool zbd_unaligned_write(int error_code)
{
	switch (error_code) {
	case EIO:
	case EREMOTEIO:
		return true;
	}
	return false;
}

/**
 * setup_zbd_zone_mode - handle zoneskip as necessary for ZBD drives
 * @td: FIO thread data.
 * @io_u: FIO I/O unit.
 *
 * For sequential workloads, change the file offset to skip zoneskip bytes when
 * no more IO can be performed in the current zone.
 * - For read workloads, zoneskip is applied when the io has reached the end of
 *   the zone or the zone write position (when td->o.read_beyond_wp is false).
 * - For write workloads, zoneskip is applied when the zone is full.
 * This applies only to read and write operations.
 */
void setup_zbd_zone_mode(struct thread_data *td, struct io_u *io_u)
{
	struct fio_file *f = io_u->file;
	enum fio_ddir ddir = io_u->ddir;
	struct fio_zone_info *z;
	uint32_t zone_idx;

	assert(td->o.zone_mode == ZONE_MODE_ZBD);
	assert(td->o.zone_size);

	zone_idx = zbd_zone_idx(f, f->last_pos[ddir]);
	z = get_zone(f, zone_idx);

	/*
	 * When the zone capacity is smaller than the zone size and the I/O is
	 * sequential write, skip to zone end if the latest position is at the
	 * zone capacity limit.
	 */
	if (z->capacity < f->zbd_info->zone_size && !td_random(td) &&
	    ddir == DDIR_WRITE &&
	    f->last_pos[ddir] >= zbd_zone_capacity_end(z)) {
		dprint(FD_ZBD,
		       "%s: Jump from zone capacity limit to zone end:"
		       " (%llu -> %llu) for zone %u (%llu)\n",
		       f->file_name, (unsigned long long) f->last_pos[ddir],
		       (unsigned long long) zbd_zone_end(z), zone_idx,
		       (unsigned long long) z->capacity);
		td->io_skip_bytes += zbd_zone_end(z) - f->last_pos[ddir];
		f->last_pos[ddir] = zbd_zone_end(z);
	}

	/*
	 * zone_skip is valid only for sequential workloads.
	 */
	if (td_random(td) || !td->o.zone_skip)
		return;

	/*
	 * It is time to switch to a new zone if:
	 * - zone_bytes == zone_size bytes have already been accessed
	 * - The last position reached the end of the current zone.
	 * - For reads with td->o.read_beyond_wp == false, the last position
	 *   reached the zone write pointer.
	 */
	if (td->zone_bytes >= td->o.zone_size ||
	    f->last_pos[ddir] >= zbd_zone_end(z) ||
	    (ddir == DDIR_READ &&
	     (!td->o.read_beyond_wp) && f->last_pos[ddir] >= z->wp)) {
		/*
		 * Skip zones.
		 */
		td->zone_bytes = 0;
		f->file_offset += td->o.zone_size + td->o.zone_skip;

		/*
		 * Wrap from the beginning, if we exceed the file size
		 */
		if (f->file_offset >= f->real_file_size)
			f->file_offset = get_start_offset(td, f);

		f->last_pos[ddir] = f->file_offset;
		td->io_skip_bytes += td->o.zone_skip;
	}
}

/**
 * zbd_adjust_ddir - Adjust an I/O direction for zonemode=zbd.
 *
 * @td: FIO thread data.
 * @io_u: FIO I/O unit.
 * @ddir: I/O direction before adjustment.
 *
 * Return adjusted I/O direction.
 */
enum fio_ddir zbd_adjust_ddir(struct thread_data *td, struct io_u *io_u,
			      enum fio_ddir ddir)
{
	/*
	 * In case read direction is chosen for the first random I/O, fio with
	 * zonemode=zbd stops because no data can be read from zoned block
	 * devices with all empty zones. Overwrite the first I/O direction as
	 * write to make sure data to read exists.
	 */
	if (ddir != DDIR_READ || !td_rw(td))
		return ddir;

	if (io_u->file->zbd_info->sectors_with_data ||
	    td->o.read_beyond_wp)
		return DDIR_READ;

	return DDIR_WRITE;
}

/**
 * zbd_adjust_block - adjust the offset and length as necessary for ZBD drives
 * @td: FIO thread data.
 * @io_u: FIO I/O unit.
 *
 * Locking strategy: returns with z->mutex locked if and only if z refers
 * to a sequential zone and if io_u_accept is returned. z is the zone that
 * corresponds to io_u->offset at the end of this function.
 */
enum io_u_action zbd_adjust_block(struct thread_data *td, struct io_u *io_u)
{
	struct fio_file *f = io_u->file;
	uint32_t zone_idx_b;
	struct fio_zone_info *zb, *zl, *orig_zb;
	uint32_t orig_len = io_u->buflen;
	uint32_t min_bs = td->o.min_bs[io_u->ddir];
	uint64_t new_len;
	int64_t range;

	if (!f->zbd_info)
		return io_u_accept;

	assert(min_bs);
	assert(is_valid_offset(f, io_u->offset));
	assert(io_u->buflen);
	zone_idx_b = zbd_zone_idx(f, io_u->offset);
	zb = get_zone(f, zone_idx_b);
	orig_zb = zb;

	if (!zb->has_wp) {
		/* Accept non-write I/Os for conventional zones. */
		if (io_u->ddir != DDIR_WRITE)
			return io_u_accept;
		/*
		 * Make sure that writes to conventional zones
		 * don't cross over to any sequential zones.
		 */
		if (!(zb + 1)->has_wp ||
		    io_u->offset + io_u->buflen <= (zb + 1)->start)
			return io_u_accept;

		if (io_u->offset + min_bs > (zb + 1)->start) {
			dprint(FD_IO,
			       "%s: off=%llu + min_bs=%u > next zone %llu\n",
			       f->file_name, io_u->offset,
			       min_bs, (unsigned long long) (zb + 1)->start);
			io_u->offset = zb->start + (zb + 1)->start - io_u->offset;
			new_len = min(io_u->buflen, (zb + 1)->start - io_u->offset);
		} else {
			new_len = (zb + 1)->start - io_u->offset;
		}
		io_u->buflen = new_len / min_bs * min_bs;
		return io_u_accept;
	}

	/*
	 * Accept the I/O offset for reads if reading beyond the write pointer
	 * is enabled.
	 */
	if (zb->cond != ZBD_ZONE_COND_OFFLINE &&
	    io_u->ddir == DDIR_READ && td->o.read_beyond_wp)
		return io_u_accept;

	zbd_check_swd(td, f);

	zone_lock(td, f, zb);

	switch (io_u->ddir) {
	case DDIR_READ:
		if (td->runstate == TD_VERIFYING && td_write(td)) {
			zb = zbd_replay_write_order(td, io_u, zb);
			goto accept;
		}
		/*
		 * Check that there is enough written data in the zone to do an
		 * I/O of at least min_bs B. If there isn't, find a new zone for
		 * the I/O.
		 */
		range = zb->cond != ZBD_ZONE_COND_OFFLINE ?
			zb->wp - zb->start : 0;
		if (range < min_bs ||
		    ((!td_random(td)) && (io_u->offset + min_bs > zb->wp))) {
			zone_unlock(zb);
			zl = get_zone(f, f->max_zone);
			zb = zbd_find_zone(td, io_u, zb, zl);
			if (!zb) {
				dprint(FD_ZBD,
				       "%s: zbd_find_zone(%lld, %llu) failed\n",
				       f->file_name, io_u->offset,
				       io_u->buflen);
				goto eof;
			}
			/*
			 * zbd_find_zone() returned a zone with a range of at
			 * least min_bs.
			 */
			range = zb->wp - zb->start;
			assert(range >= min_bs);

			if (!td_random(td))
				io_u->offset = zb->start;
		}
		/*
		 * Make sure the I/O is within the zone valid data range while
		 * maximizing the I/O size and preserving randomness.
		 */
		if (range <= io_u->buflen)
			io_u->offset = zb->start;
		else if (td_random(td))
			io_u->offset = zb->start +
				((io_u->offset - orig_zb->start) %
				 (range - io_u->buflen)) / min_bs * min_bs;
		/*
		 * When zbd_find_zone() returns a conventional zone,
		 * we can simply accept the new i/o offset here.
		 */
		if (!zb->has_wp)
			return io_u_accept;
		/*
		 * Make sure the I/O does not cross over the zone wp position.
		 */
		new_len = min((unsigned long long)io_u->buflen,
			      (unsigned long long)(zb->wp - io_u->offset));
		new_len = new_len / min_bs * min_bs;
		if (new_len < io_u->buflen) {
			io_u->buflen = new_len;
			dprint(FD_IO, "Changed length from %u into %llu\n",
			       orig_len, io_u->buflen);
		}
		assert(zb->start <= io_u->offset);
		assert(io_u->offset + io_u->buflen <= zb->wp);
		goto accept;
	case DDIR_WRITE:
		if (io_u->buflen > f->zbd_info->zone_size) {
			td_verror(td, EINVAL, "I/O buflen exceeds zone size");
			dprint(FD_IO,
			       "%s: I/O buflen %llu exceeds zone size %llu\n",
			       f->file_name, io_u->buflen,
			       (unsigned long long) f->zbd_info->zone_size);
			goto eof;
		}
		if (!zbd_open_zone(td, f, zone_idx_b)) {
			zone_unlock(zb);
			zb = zbd_convert_to_open_zone(td, io_u);
			if (!zb) {
				dprint(FD_IO, "%s: can't convert to open zone",
				       f->file_name);
				goto eof;
			}
			zone_idx_b = zbd_zone_nr(f, zb);
		}
		/* Check whether the zone reset threshold has been exceeded */
		if (td->o.zrf.u.f) {
			if (f->zbd_info->wp_sectors_with_data >=
			    f->io_size * td->o.zrt.u.f &&
			    zbd_dec_and_reset_write_cnt(td, f)) {
				zb->reset_zone = 1;
			}
		}
		/* Reset the zone pointer if necessary */
		if (zb->reset_zone || zbd_zone_full(f, zb, min_bs)) {
			assert(td->o.verify == VERIFY_NONE);
			/*
			 * Since previous write requests may have been submitted
			 * asynchronously and since we will submit the zone
			 * reset synchronously, wait until previously submitted
			 * write requests have completed before issuing a
			 * zone reset.
			 */
			io_u_quiesce(td);
			zb->reset_zone = 0;
			if (zbd_reset_zone(td, f, zb) < 0)
				goto eof;

			if (zb->capacity < min_bs) {
				td_verror(td, EINVAL, "ZCAP is less min_bs");
				log_err("zone capacity %llu smaller than minimum block size %d\n",
					(unsigned long long)zb->capacity,
					min_bs);
				goto eof;
			}
		}
		/* Make writes occur at the write pointer */
		assert(!zbd_zone_full(f, zb, min_bs));
		io_u->offset = zb->wp;
		if (!is_valid_offset(f, io_u->offset)) {
			td_verror(td, EINVAL, "invalid WP value");
			dprint(FD_ZBD, "%s: dropped request with offset %llu\n",
			       f->file_name, io_u->offset);
			goto eof;
		}
		/*
		 * Make sure that the buflen is a multiple of the minimal
		 * block size. Give up if shrinking would make the request too
		 * small.
		 */
		new_len = min((unsigned long long)io_u->buflen,
			      zbd_zone_capacity_end(zb) - io_u->offset);
		new_len = new_len / min_bs * min_bs;
		if (new_len == io_u->buflen)
			goto accept;
		if (new_len >= min_bs) {
			io_u->buflen = new_len;
			dprint(FD_IO, "Changed length from %u into %llu\n",
			       orig_len, io_u->buflen);
			goto accept;
		}
		td_verror(td, EIO, "zone remainder too small");
		log_err("zone remainder %lld smaller than min block size %d\n",
			(zbd_zone_capacity_end(zb) - io_u->offset), min_bs);
		goto eof;
	case DDIR_TRIM:
		/* fall-through */
	case DDIR_SYNC:
	case DDIR_DATASYNC:
	case DDIR_SYNC_FILE_RANGE:
	case DDIR_WAIT:
	case DDIR_LAST:
	case DDIR_INVAL:
		goto accept;
	}

	assert(false);

accept:
	assert(zb->has_wp);
	assert(zb->cond != ZBD_ZONE_COND_OFFLINE);
	assert(!io_u->zbd_queue_io);
	assert(!io_u->zbd_put_io);
	io_u->zbd_queue_io = zbd_queue_io;
	io_u->zbd_put_io = zbd_put_io;
	/*
	 * Since we return with the zone lock still held,
	 * add an annotation to let Coverity know that it
	 * is intentional.
	 */
	/* coverity[missing_unlock] */
	return io_u_accept;

eof:
	if (zb && zb->has_wp)
		zone_unlock(zb);
	return io_u_eof;
}

/* Return a string with ZBD statistics */
char *zbd_write_status(const struct thread_stat *ts)
{
	char *res;

	if (asprintf(&res, "; %llu zone resets", (unsigned long long) ts->nr_zone_resets) < 0)
		return NULL;
	return res;
}