summaryrefslogtreecommitdiffstats
path: root/fs/zonefs/super.c
blob: c6a124e8d565febb690377ae982f60042ba2383b (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Simple file system for zoned block devices exposing zones as files.
 *
 * Copyright (C) 2019 Western Digital Corporation or its affiliates.
 */
#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/magic.h>
#include <linux/iomap.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/statfs.h>
#include <linux/writeback.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
#include <linux/uio.h>
#include <linux/mman.h>
#include <linux/sched/mm.h>
#include <linux/crc32.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/fs_parser.h>
#include <linux/fs_context.h>

#include "zonefs.h"

#define CREATE_TRACE_POINTS
#include "trace.h"

/*
 * Get the name of a zone group directory.
 */
static const char *zonefs_zgroup_name(enum zonefs_ztype ztype)
{
	switch (ztype) {
	case ZONEFS_ZTYPE_CNV:
		return "cnv";
	case ZONEFS_ZTYPE_SEQ:
		return "seq";
	default:
		WARN_ON_ONCE(1);
		return "???";
	}
}

/*
 * Manage the active zone count.
 */
static void zonefs_account_active(struct super_block *sb,
				  struct zonefs_zone *z)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);

	if (zonefs_zone_is_cnv(z))
		return;

	/*
	 * For zones that transitioned to the offline or readonly condition,
	 * we only need to clear the active state.
	 */
	if (z->z_flags & (ZONEFS_ZONE_OFFLINE | ZONEFS_ZONE_READONLY))
		goto out;

	/*
	 * If the zone is active, that is, if it is explicitly open or
	 * partially written, check if it was already accounted as active.
	 */
	if ((z->z_flags & ZONEFS_ZONE_OPEN) ||
	    (z->z_wpoffset > 0 && z->z_wpoffset < z->z_capacity)) {
		if (!(z->z_flags & ZONEFS_ZONE_ACTIVE)) {
			z->z_flags |= ZONEFS_ZONE_ACTIVE;
			atomic_inc(&sbi->s_active_seq_files);
		}
		return;
	}

out:
	/* The zone is not active. If it was, update the active count */
	if (z->z_flags & ZONEFS_ZONE_ACTIVE) {
		z->z_flags &= ~ZONEFS_ZONE_ACTIVE;
		atomic_dec(&sbi->s_active_seq_files);
	}
}

/*
 * Manage the active zone count. Called with zi->i_truncate_mutex held.
 */
void zonefs_inode_account_active(struct inode *inode)
{
	lockdep_assert_held(&ZONEFS_I(inode)->i_truncate_mutex);

	return zonefs_account_active(inode->i_sb, zonefs_inode_zone(inode));
}

/*
 * Execute a zone management operation.
 */
static int zonefs_zone_mgmt(struct super_block *sb,
			    struct zonefs_zone *z, enum req_op op)
{
	int ret;

	/*
	 * With ZNS drives, closing an explicitly open zone that has not been
	 * written will change the zone state to "closed", that is, the zone
	 * will remain active. Since this can then cause failure of explicit
	 * open operation on other zones if the drive active zone resources
	 * are exceeded, make sure that the zone does not remain active by
	 * resetting it.
	 */
	if (op == REQ_OP_ZONE_CLOSE && !z->z_wpoffset)
		op = REQ_OP_ZONE_RESET;

	trace_zonefs_zone_mgmt(sb, z, op);
	ret = blkdev_zone_mgmt(sb->s_bdev, op, z->z_sector,
			       z->z_size >> SECTOR_SHIFT);
	if (ret) {
		zonefs_err(sb,
			   "Zone management operation %s at %llu failed %d\n",
			   blk_op_str(op), z->z_sector, ret);
		return ret;
	}

	return 0;
}

int zonefs_inode_zone_mgmt(struct inode *inode, enum req_op op)
{
	lockdep_assert_held(&ZONEFS_I(inode)->i_truncate_mutex);

	return zonefs_zone_mgmt(inode->i_sb, zonefs_inode_zone(inode), op);
}

void zonefs_i_size_write(struct inode *inode, loff_t isize)
{
	struct zonefs_zone *z = zonefs_inode_zone(inode);

	i_size_write(inode, isize);

	/*
	 * A full zone is no longer open/active and does not need
	 * explicit closing.
	 */
	if (isize >= z->z_capacity) {
		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);

		if (z->z_flags & ZONEFS_ZONE_ACTIVE)
			atomic_dec(&sbi->s_active_seq_files);
		z->z_flags &= ~(ZONEFS_ZONE_OPEN | ZONEFS_ZONE_ACTIVE);
	}
}

void zonefs_update_stats(struct inode *inode, loff_t new_isize)
{
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	loff_t old_isize = i_size_read(inode);
	loff_t nr_blocks;

	if (new_isize == old_isize)
		return;

	spin_lock(&sbi->s_lock);

	/*
	 * This may be called for an update after an IO error.
	 * So beware of the values seen.
	 */
	if (new_isize < old_isize) {
		nr_blocks = (old_isize - new_isize) >> sb->s_blocksize_bits;
		if (sbi->s_used_blocks > nr_blocks)
			sbi->s_used_blocks -= nr_blocks;
		else
			sbi->s_used_blocks = 0;
	} else {
		sbi->s_used_blocks +=
			(new_isize - old_isize) >> sb->s_blocksize_bits;
		if (sbi->s_used_blocks > sbi->s_blocks)
			sbi->s_used_blocks = sbi->s_blocks;
	}

	spin_unlock(&sbi->s_lock);
}

/*
 * Check a zone condition. Return the amount of written (and still readable)
 * data in the zone.
 */
static loff_t zonefs_check_zone_condition(struct super_block *sb,
					  struct zonefs_zone *z,
					  struct blk_zone *zone)
{
	switch (zone->cond) {
	case BLK_ZONE_COND_OFFLINE:
		zonefs_warn(sb, "Zone %llu: offline zone\n",
			    z->z_sector);
		z->z_flags |= ZONEFS_ZONE_OFFLINE;
		return 0;
	case BLK_ZONE_COND_READONLY:
		/*
		 * The write pointer of read-only zones is invalid, so we cannot
		 * determine the zone wpoffset (inode size). We thus keep the
		 * zone wpoffset as is, which leads to an empty file
		 * (wpoffset == 0) on mount. For a runtime error, this keeps
		 * the inode size as it was when last updated so that the user
		 * can recover data.
		 */
		zonefs_warn(sb, "Zone %llu: read-only zone\n",
			    z->z_sector);
		z->z_flags |= ZONEFS_ZONE_READONLY;
		if (zonefs_zone_is_cnv(z))
			return z->z_capacity;
		return z->z_wpoffset;
	case BLK_ZONE_COND_FULL:
		/* The write pointer of full zones is invalid. */
		return z->z_capacity;
	default:
		if (zonefs_zone_is_cnv(z))
			return z->z_capacity;
		return (zone->wp - zone->start) << SECTOR_SHIFT;
	}
}

/*
 * Check a zone condition and adjust its inode access permissions for
 * offline and readonly zones.
 */
static void zonefs_inode_update_mode(struct inode *inode)
{
	struct zonefs_zone *z = zonefs_inode_zone(inode);

	if (z->z_flags & ZONEFS_ZONE_OFFLINE) {
		/* Offline zones cannot be read nor written */
		inode->i_flags |= S_IMMUTABLE;
		inode->i_mode &= ~0777;
	} else if (z->z_flags & ZONEFS_ZONE_READONLY) {
		/* Readonly zones cannot be written */
		inode->i_flags |= S_IMMUTABLE;
		if (z->z_flags & ZONEFS_ZONE_INIT_MODE)
			inode->i_mode &= ~0777;
		else
			inode->i_mode &= ~0222;
	}

	z->z_flags &= ~ZONEFS_ZONE_INIT_MODE;
	z->z_mode = inode->i_mode;
}

static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
			      void *data)
{
	struct blk_zone *z = data;

	*z = *zone;
	return 0;
}

static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone,
				   bool write)
{
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	loff_t isize, data_size;

	/*
	 * Check the zone condition: if the zone is not "bad" (offline or
	 * read-only), read errors are simply signaled to the IO issuer as long
	 * as there is no inconsistency between the inode size and the amount of
	 * data writen in the zone (data_size).
	 */
	data_size = zonefs_check_zone_condition(sb, z, zone);
	isize = i_size_read(inode);
	if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) &&
	    !write && isize == data_size)
		return;

	/*
	 * At this point, we detected either a bad zone or an inconsistency
	 * between the inode size and the amount of data written in the zone.
	 * For the latter case, the cause may be a write IO error or an external
	 * action on the device. Two error patterns exist:
	 * 1) The inode size is lower than the amount of data in the zone:
	 *    a write operation partially failed and data was writen at the end
	 *    of the file. This can happen in the case of a large direct IO
	 *    needing several BIOs and/or write requests to be processed.
	 * 2) The inode size is larger than the amount of data in the zone:
	 *    this can happen with a deferred write error with the use of the
	 *    device side write cache after getting successful write IO
	 *    completions. Other possibilities are (a) an external corruption,
	 *    e.g. an application reset the zone directly, or (b) the device
	 *    has a serious problem (e.g. firmware bug).
	 *
	 * In all cases, warn about inode size inconsistency and handle the
	 * IO error according to the zone condition and to the mount options.
	 */
	if (isize != data_size)
		zonefs_warn(sb,
			    "inode %lu: invalid size %lld (should be %lld)\n",
			    inode->i_ino, isize, data_size);

	/*
	 * First handle bad zones signaled by hardware. The mount options
	 * errors=zone-ro and errors=zone-offline result in changing the
	 * zone condition to read-only and offline respectively, as if the
	 * condition was signaled by the hardware.
	 */
	if ((z->z_flags & ZONEFS_ZONE_OFFLINE) ||
	    (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL)) {
		zonefs_warn(sb, "inode %lu: read/write access disabled\n",
			    inode->i_ino);
		if (!(z->z_flags & ZONEFS_ZONE_OFFLINE))
			z->z_flags |= ZONEFS_ZONE_OFFLINE;
		zonefs_inode_update_mode(inode);
		data_size = 0;
	} else if ((z->z_flags & ZONEFS_ZONE_READONLY) ||
		   (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO)) {
		zonefs_warn(sb, "inode %lu: write access disabled\n",
			    inode->i_ino);
		if (!(z->z_flags & ZONEFS_ZONE_READONLY))
			z->z_flags |= ZONEFS_ZONE_READONLY;
		zonefs_inode_update_mode(inode);
		data_size = isize;
	} else if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO &&
		   data_size > isize) {
		/* Do not expose garbage data */
		data_size = isize;
	}

	/*
	 * If the filesystem is mounted with the explicit-open mount option, we
	 * need to clear the ZONEFS_ZONE_OPEN flag if the zone transitioned to
	 * the read-only or offline condition, to avoid attempting an explicit
	 * close of the zone when the inode file is closed.
	 */
	if ((sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) &&
	    (z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)))
		z->z_flags &= ~ZONEFS_ZONE_OPEN;

	/*
	 * If error=remount-ro was specified, any error result in remounting
	 * the volume as read-only.
	 */
	if ((sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO) && !sb_rdonly(sb)) {
		zonefs_warn(sb, "remounting filesystem read-only\n");
		sb->s_flags |= SB_RDONLY;
	}

	/*
	 * Update block usage stats and the inode size  to prevent access to
	 * invalid data.
	 */
	zonefs_update_stats(inode, data_size);
	zonefs_i_size_write(inode, data_size);
	z->z_wpoffset = data_size;
	zonefs_inode_account_active(inode);
}

/*
 * When an file IO error occurs, check the file zone to see if there is a change
 * in the zone condition (e.g. offline or read-only). For a failed write to a
 * sequential zone, the zone write pointer position must also be checked to
 * eventually correct the file size and zonefs inode write pointer offset
 * (which can be out of sync with the drive due to partial write failures).
 */
void __zonefs_io_error(struct inode *inode, bool write)
{
	struct zonefs_zone *z = zonefs_inode_zone(inode);
	struct super_block *sb = inode->i_sb;
	unsigned int noio_flag;
	struct blk_zone zone;
	int ret;

	/*
	 * Conventional zone have no write pointer and cannot become read-only
	 * or offline. So simply fake a report for a single or aggregated zone
	 * and let zonefs_handle_io_error() correct the zone inode information
	 * according to the mount options.
	 */
	if (!zonefs_zone_is_seq(z)) {
		zone.start = z->z_sector;
		zone.len = z->z_size >> SECTOR_SHIFT;
		zone.wp = zone.start + zone.len;
		zone.type = BLK_ZONE_TYPE_CONVENTIONAL;
		zone.cond = BLK_ZONE_COND_NOT_WP;
		zone.capacity = zone.len;
		goto handle_io_error;
	}

	/*
	 * Memory allocations in blkdev_report_zones() can trigger a memory
	 * reclaim which may in turn cause a recursion into zonefs as well as
	 * struct request allocations for the same device. The former case may
	 * end up in a deadlock on the inode truncate mutex, while the latter
	 * may prevent IO forward progress. Executing the report zones under
	 * the GFP_NOIO context avoids both problems.
	 */
	noio_flag = memalloc_noio_save();
	ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1,
				  zonefs_io_error_cb, &zone);
	memalloc_noio_restore(noio_flag);

	if (ret != 1) {
		zonefs_err(sb, "Get inode %lu zone information failed %d\n",
			   inode->i_ino, ret);
		zonefs_warn(sb, "remounting filesystem read-only\n");
		sb->s_flags |= SB_RDONLY;
		return;
	}

handle_io_error:
	zonefs_handle_io_error(inode, &zone, write);
}

static struct kmem_cache *zonefs_inode_cachep;

static struct inode *zonefs_alloc_inode(struct super_block *sb)
{
	struct zonefs_inode_info *zi;

	zi = alloc_inode_sb(sb, zonefs_inode_cachep, GFP_KERNEL);
	if (!zi)
		return NULL;

	inode_init_once(&zi->i_vnode);
	mutex_init(&zi->i_truncate_mutex);
	zi->i_wr_refcnt = 0;

	return &zi->i_vnode;
}

static void zonefs_free_inode(struct inode *inode)
{
	kmem_cache_free(zonefs_inode_cachep, ZONEFS_I(inode));
}

/*
 * File system stat.
 */
static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	enum zonefs_ztype t;

	buf->f_type = ZONEFS_MAGIC;
	buf->f_bsize = sb->s_blocksize;
	buf->f_namelen = ZONEFS_NAME_MAX;

	spin_lock(&sbi->s_lock);

	buf->f_blocks = sbi->s_blocks;
	if (WARN_ON(sbi->s_used_blocks > sbi->s_blocks))
		buf->f_bfree = 0;
	else
		buf->f_bfree = buf->f_blocks - sbi->s_used_blocks;
	buf->f_bavail = buf->f_bfree;

	for (t = 0; t < ZONEFS_ZTYPE_MAX; t++) {
		if (sbi->s_zgroup[t].g_nr_zones)
			buf->f_files += sbi->s_zgroup[t].g_nr_zones + 1;
	}
	buf->f_ffree = 0;

	spin_unlock(&sbi->s_lock);

	buf->f_fsid = uuid_to_fsid(sbi->s_uuid.b);

	return 0;
}

enum {
	Opt_errors, Opt_explicit_open,
};

struct zonefs_context {
	unsigned long s_mount_opts;
};

static const struct constant_table zonefs_param_errors[] = {
	{"remount-ro",		ZONEFS_MNTOPT_ERRORS_RO},
	{"zone-ro",		ZONEFS_MNTOPT_ERRORS_ZRO},
	{"zone-offline",	ZONEFS_MNTOPT_ERRORS_ZOL},
	{"repair", 		ZONEFS_MNTOPT_ERRORS_REPAIR},
	{}
};

static const struct fs_parameter_spec zonefs_param_spec[] = {
	fsparam_enum	("errors",		Opt_errors, zonefs_param_errors),
	fsparam_flag	("explicit-open",	Opt_explicit_open),
	{}
};

static int zonefs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
	struct zonefs_context *ctx = fc->fs_private;
	struct fs_parse_result result;
	int opt;

	opt = fs_parse(fc, zonefs_param_spec, param, &result);
	if (opt < 0)
		return opt;

	switch (opt) {
	case Opt_errors:
		ctx->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
		ctx->s_mount_opts |= result.uint_32;
		break;
	case Opt_explicit_open:
		ctx->s_mount_opts |= ZONEFS_MNTOPT_EXPLICIT_OPEN;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int zonefs_show_options(struct seq_file *seq, struct dentry *root)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(root->d_sb);

	if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO)
		seq_puts(seq, ",errors=remount-ro");
	if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO)
		seq_puts(seq, ",errors=zone-ro");
	if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL)
		seq_puts(seq, ",errors=zone-offline");
	if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_REPAIR)
		seq_puts(seq, ",errors=repair");

	return 0;
}

static int zonefs_inode_setattr(struct mnt_idmap *idmap,
				struct dentry *dentry, struct iattr *iattr)
{
	struct inode *inode = d_inode(dentry);
	int ret;

	if (unlikely(IS_IMMUTABLE(inode)))
		return -EPERM;

	ret = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
	if (ret)
		return ret;

	/*
	 * Since files and directories cannot be created nor deleted, do not
	 * allow setting any write attributes on the sub-directories grouping
	 * files by zone type.
	 */
	if ((iattr->ia_valid & ATTR_MODE) && S_ISDIR(inode->i_mode) &&
	    (iattr->ia_mode & 0222))
		return -EPERM;

	if (((iattr->ia_valid & ATTR_UID) &&
	     !uid_eq(iattr->ia_uid, inode->i_uid)) ||
	    ((iattr->ia_valid & ATTR_GID) &&
	     !gid_eq(iattr->ia_gid, inode->i_gid))) {
		ret = dquot_transfer(&nop_mnt_idmap, inode, iattr);
		if (ret)
			return ret;
	}

	if (iattr->ia_valid & ATTR_SIZE) {
		ret = zonefs_file_truncate(inode, iattr->ia_size);
		if (ret)
			return ret;
	}

	setattr_copy(&nop_mnt_idmap, inode, iattr);

	if (S_ISREG(inode->i_mode)) {
		struct zonefs_zone *z = zonefs_inode_zone(inode);

		z->z_mode = inode->i_mode;
		z->z_uid = inode->i_uid;
		z->z_gid = inode->i_gid;
	}

	return 0;
}

static const struct inode_operations zonefs_file_inode_operations = {
	.setattr	= zonefs_inode_setattr,
};

static long zonefs_fname_to_fno(const struct qstr *fname)
{
	const char *name = fname->name;
	unsigned int len = fname->len;
	long fno = 0, shift = 1;
	const char *rname;
	char c = *name;
	unsigned int i;

	/*
	 * File names are always a base-10 number string without any
	 * leading 0s.
	 */
	if (!isdigit(c))
		return -ENOENT;

	if (len > 1 && c == '0')
		return -ENOENT;

	if (len == 1)
		return c - '0';

	for (i = 0, rname = name + len - 1; i < len; i++, rname--) {
		c = *rname;
		if (!isdigit(c))
			return -ENOENT;
		fno += (c - '0') * shift;
		shift *= 10;
	}

	return fno;
}

static struct inode *zonefs_get_file_inode(struct inode *dir,
					   struct dentry *dentry)
{
	struct zonefs_zone_group *zgroup = dir->i_private;
	struct super_block *sb = dir->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct zonefs_zone *z;
	struct inode *inode;
	ino_t ino;
	long fno;

	/* Get the file number from the file name */
	fno = zonefs_fname_to_fno(&dentry->d_name);
	if (fno < 0)
		return ERR_PTR(fno);

	if (!zgroup->g_nr_zones || fno >= zgroup->g_nr_zones)
		return ERR_PTR(-ENOENT);

	z = &zgroup->g_zones[fno];
	ino = z->z_sector >> sbi->s_zone_sectors_shift;
	inode = iget_locked(sb, ino);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW)) {
		WARN_ON_ONCE(inode->i_private != z);
		return inode;
	}

	inode->i_ino = ino;
	inode->i_mode = z->z_mode;
	inode_set_mtime_to_ts(inode,
			      inode_set_atime_to_ts(inode, inode_set_ctime_to_ts(inode, inode_get_ctime(dir))));
	inode->i_uid = z->z_uid;
	inode->i_gid = z->z_gid;
	inode->i_size = z->z_wpoffset;
	inode->i_blocks = z->z_capacity >> SECTOR_SHIFT;
	inode->i_private = z;

	inode->i_op = &zonefs_file_inode_operations;
	inode->i_fop = &zonefs_file_operations;
	inode->i_mapping->a_ops = &zonefs_file_aops;

	/* Update the inode access rights depending on the zone condition */
	zonefs_inode_update_mode(inode);

	unlock_new_inode(inode);

	return inode;
}

static struct inode *zonefs_get_zgroup_inode(struct super_block *sb,
					     enum zonefs_ztype ztype)
{
	struct inode *root = d_inode(sb->s_root);
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct inode *inode;
	ino_t ino = bdev_nr_zones(sb->s_bdev) + ztype + 1;

	inode = iget_locked(sb, ino);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW))
		return inode;

	inode->i_ino = ino;
	inode_init_owner(&nop_mnt_idmap, inode, root, S_IFDIR | 0555);
	inode->i_size = sbi->s_zgroup[ztype].g_nr_zones;
	inode_set_mtime_to_ts(inode,
			      inode_set_atime_to_ts(inode, inode_set_ctime_to_ts(inode, inode_get_ctime(root))));
	inode->i_private = &sbi->s_zgroup[ztype];
	set_nlink(inode, 2);

	inode->i_op = &zonefs_dir_inode_operations;
	inode->i_fop = &zonefs_dir_operations;

	unlock_new_inode(inode);

	return inode;
}


static struct inode *zonefs_get_dir_inode(struct inode *dir,
					  struct dentry *dentry)
{
	struct super_block *sb = dir->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	const char *name = dentry->d_name.name;
	enum zonefs_ztype ztype;

	/*
	 * We only need to check for the "seq" directory and
	 * the "cnv" directory if we have conventional zones.
	 */
	if (dentry->d_name.len != 3)
		return ERR_PTR(-ENOENT);

	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
		if (sbi->s_zgroup[ztype].g_nr_zones &&
		    memcmp(name, zonefs_zgroup_name(ztype), 3) == 0)
			break;
	}
	if (ztype == ZONEFS_ZTYPE_MAX)
		return ERR_PTR(-ENOENT);

	return zonefs_get_zgroup_inode(sb, ztype);
}

static struct dentry *zonefs_lookup(struct inode *dir, struct dentry *dentry,
				    unsigned int flags)
{
	struct inode *inode;

	if (dentry->d_name.len > ZONEFS_NAME_MAX)
		return ERR_PTR(-ENAMETOOLONG);

	if (dir == d_inode(dir->i_sb->s_root))
		inode = zonefs_get_dir_inode(dir, dentry);
	else
		inode = zonefs_get_file_inode(dir, dentry);

	return d_splice_alias(inode, dentry);
}

static int zonefs_readdir_root(struct file *file, struct dir_context *ctx)
{
	struct inode *inode = file_inode(file);
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	enum zonefs_ztype ztype = ZONEFS_ZTYPE_CNV;
	ino_t base_ino = bdev_nr_zones(sb->s_bdev) + 1;

	if (ctx->pos >= inode->i_size)
		return 0;

	if (!dir_emit_dots(file, ctx))
		return 0;

	if (ctx->pos == 2) {
		if (!sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones)
			ztype = ZONEFS_ZTYPE_SEQ;

		if (!dir_emit(ctx, zonefs_zgroup_name(ztype), 3,
			      base_ino + ztype, DT_DIR))
			return 0;
		ctx->pos++;
	}

	if (ctx->pos == 3 && ztype != ZONEFS_ZTYPE_SEQ) {
		ztype = ZONEFS_ZTYPE_SEQ;
		if (!dir_emit(ctx, zonefs_zgroup_name(ztype), 3,
			      base_ino + ztype, DT_DIR))
			return 0;
		ctx->pos++;
	}

	return 0;
}

static int zonefs_readdir_zgroup(struct file *file,
				 struct dir_context *ctx)
{
	struct inode *inode = file_inode(file);
	struct zonefs_zone_group *zgroup = inode->i_private;
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct zonefs_zone *z;
	int fname_len;
	char *fname;
	ino_t ino;
	int f;

	/*
	 * The size of zone group directories is equal to the number
	 * of zone files in the group and does note include the "." and
	 * ".." entries. Hence the "+ 2" here.
	 */
	if (ctx->pos >= inode->i_size + 2)
		return 0;

	if (!dir_emit_dots(file, ctx))
		return 0;

	fname = kmalloc(ZONEFS_NAME_MAX, GFP_KERNEL);
	if (!fname)
		return -ENOMEM;

	for (f = ctx->pos - 2; f < zgroup->g_nr_zones; f++) {
		z = &zgroup->g_zones[f];
		ino = z->z_sector >> sbi->s_zone_sectors_shift;
		fname_len = snprintf(fname, ZONEFS_NAME_MAX - 1, "%u", f);
		if (!dir_emit(ctx, fname, fname_len, ino, DT_REG))
			break;
		ctx->pos++;
	}

	kfree(fname);

	return 0;
}

static int zonefs_readdir(struct file *file, struct dir_context *ctx)
{
	struct inode *inode = file_inode(file);

	if (inode == d_inode(inode->i_sb->s_root))
		return zonefs_readdir_root(file, ctx);

	return zonefs_readdir_zgroup(file, ctx);
}

const struct inode_operations zonefs_dir_inode_operations = {
	.lookup		= zonefs_lookup,
	.setattr	= zonefs_inode_setattr,
};

const struct file_operations zonefs_dir_operations = {
	.llseek		= generic_file_llseek,
	.read		= generic_read_dir,
	.iterate_shared	= zonefs_readdir,
};

struct zonefs_zone_data {
	struct super_block	*sb;
	unsigned int		nr_zones[ZONEFS_ZTYPE_MAX];
	sector_t		cnv_zone_start;
	struct blk_zone		*zones;
};

static int zonefs_get_zone_info_cb(struct blk_zone *zone, unsigned int idx,
				   void *data)
{
	struct zonefs_zone_data *zd = data;
	struct super_block *sb = zd->sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);

	/*
	 * We do not care about the first zone: it contains the super block
	 * and not exposed as a file.
	 */
	if (!idx)
		return 0;

	/*
	 * Count the number of zones that will be exposed as files.
	 * For sequential zones, we always have as many files as zones.
	 * FOr conventional zones, the number of files depends on if we have
	 * conventional zones aggregation enabled.
	 */
	switch (zone->type) {
	case BLK_ZONE_TYPE_CONVENTIONAL:
		if (sbi->s_features & ZONEFS_F_AGGRCNV) {
			/* One file per set of contiguous conventional zones */
			if (!(sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones) ||
			    zone->start != zd->cnv_zone_start)
				sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones++;
			zd->cnv_zone_start = zone->start + zone->len;
		} else {
			/* One file per zone */
			sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones++;
		}
		break;
	case BLK_ZONE_TYPE_SEQWRITE_REQ:
	case BLK_ZONE_TYPE_SEQWRITE_PREF:
		sbi->s_zgroup[ZONEFS_ZTYPE_SEQ].g_nr_zones++;
		break;
	default:
		zonefs_err(zd->sb, "Unsupported zone type 0x%x\n",
			   zone->type);
		return -EIO;
	}

	memcpy(&zd->zones[idx], zone, sizeof(struct blk_zone));

	return 0;
}

static int zonefs_get_zone_info(struct zonefs_zone_data *zd)
{
	struct block_device *bdev = zd->sb->s_bdev;
	int ret;

	zd->zones = kvcalloc(bdev_nr_zones(bdev), sizeof(struct blk_zone),
			     GFP_KERNEL);
	if (!zd->zones)
		return -ENOMEM;

	/* Get zones information from the device */
	ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES,
				  zonefs_get_zone_info_cb, zd);
	if (ret < 0) {
		zonefs_err(zd->sb, "Zone report failed %d\n", ret);
		return ret;
	}

	if (ret != bdev_nr_zones(bdev)) {
		zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n",
			   ret, bdev_nr_zones(bdev));
		return -EIO;
	}

	return 0;
}

static inline void zonefs_free_zone_info(struct zonefs_zone_data *zd)
{
	kvfree(zd->zones);
}

/*
 * Create a zone group and populate it with zone files.
 */
static int zonefs_init_zgroup(struct super_block *sb,
			      struct zonefs_zone_data *zd,
			      enum zonefs_ztype ztype)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct zonefs_zone_group *zgroup = &sbi->s_zgroup[ztype];
	struct blk_zone *zone, *next, *end;
	struct zonefs_zone *z;
	unsigned int n = 0;
	int ret;

	/* Allocate the zone group. If it is empty, we have nothing to do. */
	if (!zgroup->g_nr_zones)
		return 0;

	zgroup->g_zones = kvcalloc(zgroup->g_nr_zones,
				   sizeof(struct zonefs_zone), GFP_KERNEL);
	if (!zgroup->g_zones)
		return -ENOMEM;

	/*
	 * Initialize the zone groups using the device zone information.
	 * We always skip the first zone as it contains the super block
	 * and is not use to back a file.
	 */
	end = zd->zones + bdev_nr_zones(sb->s_bdev);
	for (zone = &zd->zones[1]; zone < end; zone = next) {

		next = zone + 1;
		if (zonefs_zone_type(zone) != ztype)
			continue;

		if (WARN_ON_ONCE(n >= zgroup->g_nr_zones))
			return -EINVAL;

		/*
		 * For conventional zones, contiguous zones can be aggregated
		 * together to form larger files. Note that this overwrites the
		 * length of the first zone of the set of contiguous zones
		 * aggregated together. If one offline or read-only zone is
		 * found, assume that all zones aggregated have the same
		 * condition.
		 */
		if (ztype == ZONEFS_ZTYPE_CNV &&
		    (sbi->s_features & ZONEFS_F_AGGRCNV)) {
			for (; next < end; next++) {
				if (zonefs_zone_type(next) != ztype)
					break;
				zone->len += next->len;
				zone->capacity += next->capacity;
				if (next->cond == BLK_ZONE_COND_READONLY &&
				    zone->cond != BLK_ZONE_COND_OFFLINE)
					zone->cond = BLK_ZONE_COND_READONLY;
				else if (next->cond == BLK_ZONE_COND_OFFLINE)
					zone->cond = BLK_ZONE_COND_OFFLINE;
			}
		}

		z = &zgroup->g_zones[n];
		if (ztype == ZONEFS_ZTYPE_CNV)
			z->z_flags |= ZONEFS_ZONE_CNV;
		z->z_sector = zone->start;
		z->z_size = zone->len << SECTOR_SHIFT;
		if (z->z_size > bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT &&
		    !(sbi->s_features & ZONEFS_F_AGGRCNV)) {
			zonefs_err(sb,
				"Invalid zone size %llu (device zone sectors %llu)\n",
				z->z_size,
				bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT);
			return -EINVAL;
		}

		z->z_capacity = min_t(loff_t, MAX_LFS_FILESIZE,
				      zone->capacity << SECTOR_SHIFT);
		z->z_wpoffset = zonefs_check_zone_condition(sb, z, zone);

		z->z_mode = S_IFREG | sbi->s_perm;
		z->z_uid = sbi->s_uid;
		z->z_gid = sbi->s_gid;

		/*
		 * Let zonefs_inode_update_mode() know that we will need
		 * special initialization of the inode mode the first time
		 * it is accessed.
		 */
		z->z_flags |= ZONEFS_ZONE_INIT_MODE;

		sb->s_maxbytes = max(z->z_capacity, sb->s_maxbytes);
		sbi->s_blocks += z->z_capacity >> sb->s_blocksize_bits;
		sbi->s_used_blocks += z->z_wpoffset >> sb->s_blocksize_bits;

		/*
		 * For sequential zones, make sure that any open zone is closed
		 * first to ensure that the initial number of open zones is 0,
		 * in sync with the open zone accounting done when the mount
		 * option ZONEFS_MNTOPT_EXPLICIT_OPEN is used.
		 */
		if (ztype == ZONEFS_ZTYPE_SEQ &&
		    (zone->cond == BLK_ZONE_COND_IMP_OPEN ||
		     zone->cond == BLK_ZONE_COND_EXP_OPEN)) {
			ret = zonefs_zone_mgmt(sb, z, REQ_OP_ZONE_CLOSE);
			if (ret)
				return ret;
		}

		zonefs_account_active(sb, z);

		n++;
	}

	if (WARN_ON_ONCE(n != zgroup->g_nr_zones))
		return -EINVAL;

	zonefs_info(sb, "Zone group \"%s\" has %u file%s\n",
		    zonefs_zgroup_name(ztype),
		    zgroup->g_nr_zones,
		    zgroup->g_nr_zones > 1 ? "s" : "");

	return 0;
}

static void zonefs_free_zgroups(struct super_block *sb)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	enum zonefs_ztype ztype;

	if (!sbi)
		return;

	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
		kvfree(sbi->s_zgroup[ztype].g_zones);
		sbi->s_zgroup[ztype].g_zones = NULL;
	}
}

/*
 * Create a zone group and populate it with zone files.
 */
static int zonefs_init_zgroups(struct super_block *sb)
{
	struct zonefs_zone_data zd;
	enum zonefs_ztype ztype;
	int ret;

	/* First get the device zone information */
	memset(&zd, 0, sizeof(struct zonefs_zone_data));
	zd.sb = sb;
	ret = zonefs_get_zone_info(&zd);
	if (ret)
		goto cleanup;

	/* Allocate and initialize the zone groups */
	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
		ret = zonefs_init_zgroup(sb, &zd, ztype);
		if (ret) {
			zonefs_info(sb,
				    "Zone group \"%s\" initialization failed\n",
				    zonefs_zgroup_name(ztype));
			break;
		}
	}

cleanup:
	zonefs_free_zone_info(&zd);
	if (ret)
		zonefs_free_zgroups(sb);

	return ret;
}

/*
 * Read super block information from the device.
 */
static int zonefs_read_super(struct super_block *sb)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct zonefs_super *super;
	u32 crc, stored_crc;
	struct page *page;
	struct bio_vec bio_vec;
	struct bio bio;
	int ret;

	page = alloc_page(GFP_KERNEL);
	if (!page)
		return -ENOMEM;

	bio_init(&bio, sb->s_bdev, &bio_vec, 1, REQ_OP_READ);
	bio.bi_iter.bi_sector = 0;
	__bio_add_page(&bio, page, PAGE_SIZE, 0);

	ret = submit_bio_wait(&bio);
	if (ret)
		goto free_page;

	super = page_address(page);

	ret = -EINVAL;
	if (le32_to_cpu(super->s_magic) != ZONEFS_MAGIC)
		goto free_page;

	stored_crc = le32_to_cpu(super->s_crc);
	super->s_crc = 0;
	crc = crc32(~0U, (unsigned char *)super, sizeof(struct zonefs_super));
	if (crc != stored_crc) {
		zonefs_err(sb, "Invalid checksum (Expected 0x%08x, got 0x%08x)",
			   crc, stored_crc);
		goto free_page;
	}

	sbi->s_features = le64_to_cpu(super->s_features);
	if (sbi->s_features & ~ZONEFS_F_DEFINED_FEATURES) {
		zonefs_err(sb, "Unknown features set 0x%llx\n",
			   sbi->s_features);
		goto free_page;
	}

	if (sbi->s_features & ZONEFS_F_UID) {
		sbi->s_uid = make_kuid(current_user_ns(),
				       le32_to_cpu(super->s_uid));
		if (!uid_valid(sbi->s_uid)) {
			zonefs_err(sb, "Invalid UID feature\n");
			goto free_page;
		}
	}

	if (sbi->s_features & ZONEFS_F_GID) {
		sbi->s_gid = make_kgid(current_user_ns(),
				       le32_to_cpu(super->s_gid));
		if (!gid_valid(sbi->s_gid)) {
			zonefs_err(sb, "Invalid GID feature\n");
			goto free_page;
		}
	}

	if (sbi->s_features & ZONEFS_F_PERM)
		sbi->s_perm = le32_to_cpu(super->s_perm);

	if (memchr_inv(super->s_reserved, 0, sizeof(super->s_reserved))) {
		zonefs_err(sb, "Reserved area is being used\n");
		goto free_page;
	}

	import_uuid(&sbi->s_uuid, super->s_uuid);
	ret = 0;

free_page:
	__free_page(page);

	return ret;
}

static const struct super_operations zonefs_sops = {
	.alloc_inode	= zonefs_alloc_inode,
	.free_inode	= zonefs_free_inode,
	.statfs		= zonefs_statfs,
	.show_options	= zonefs_show_options,
};

static int zonefs_get_zgroup_inodes(struct super_block *sb)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct inode *dir_inode;
	enum zonefs_ztype ztype;

	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
		if (!sbi->s_zgroup[ztype].g_nr_zones)
			continue;

		dir_inode = zonefs_get_zgroup_inode(sb, ztype);
		if (IS_ERR(dir_inode))
			return PTR_ERR(dir_inode);

		sbi->s_zgroup[ztype].g_inode = dir_inode;
	}

	return 0;
}

static void zonefs_release_zgroup_inodes(struct super_block *sb)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	enum zonefs_ztype ztype;

	if (!sbi)
		return;

	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
		if (sbi->s_zgroup[ztype].g_inode) {
			iput(sbi->s_zgroup[ztype].g_inode);
			sbi->s_zgroup[ztype].g_inode = NULL;
		}
	}
}

/*
 * Check that the device is zoned. If it is, get the list of zones and create
 * sub-directories and files according to the device zone configuration and
 * format options.
 */
static int zonefs_fill_super(struct super_block *sb, struct fs_context *fc)
{
	struct zonefs_sb_info *sbi;
	struct zonefs_context *ctx = fc->fs_private;
	struct inode *inode;
	enum zonefs_ztype ztype;
	int ret;

	if (!bdev_is_zoned(sb->s_bdev)) {
		zonefs_err(sb, "Not a zoned block device\n");
		return -EINVAL;
	}

	/*
	 * Initialize super block information: the maximum file size is updated
	 * when the zone files are created so that the format option
	 * ZONEFS_F_AGGRCNV which increases the maximum file size of a file
	 * beyond the zone size is taken into account.
	 */
	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;

	spin_lock_init(&sbi->s_lock);
	sb->s_fs_info = sbi;
	sb->s_magic = ZONEFS_MAGIC;
	sb->s_maxbytes = 0;
	sb->s_op = &zonefs_sops;
	sb->s_time_gran	= 1;

	/*
	 * The block size is set to the device zone write granularity to ensure
	 * that write operations are always aligned according to the device
	 * interface constraints.
	 */
	sb_set_blocksize(sb, bdev_zone_write_granularity(sb->s_bdev));
	sbi->s_zone_sectors_shift = ilog2(bdev_zone_sectors(sb->s_bdev));
	sbi->s_uid = GLOBAL_ROOT_UID;
	sbi->s_gid = GLOBAL_ROOT_GID;
	sbi->s_perm = 0640;
	sbi->s_mount_opts = ctx->s_mount_opts;

	atomic_set(&sbi->s_wro_seq_files, 0);
	sbi->s_max_wro_seq_files = bdev_max_open_zones(sb->s_bdev);
	atomic_set(&sbi->s_active_seq_files, 0);
	sbi->s_max_active_seq_files = bdev_max_active_zones(sb->s_bdev);

	ret = zonefs_read_super(sb);
	if (ret)
		return ret;

	zonefs_info(sb, "Mounting %u zones", bdev_nr_zones(sb->s_bdev));

	if (!sbi->s_max_wro_seq_files &&
	    !sbi->s_max_active_seq_files &&
	    sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
		zonefs_info(sb,
			"No open and active zone limits. Ignoring explicit_open mount option\n");
		sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
	}

	/* Initialize the zone groups */
	ret = zonefs_init_zgroups(sb);
	if (ret)
		goto cleanup;

	/* Create the root directory inode */
	ret = -ENOMEM;
	inode = new_inode(sb);
	if (!inode)
		goto cleanup;

	inode->i_ino = bdev_nr_zones(sb->s_bdev);
	inode->i_mode = S_IFDIR | 0555;
	simple_inode_init_ts(inode);
	inode->i_op = &zonefs_dir_inode_operations;
	inode->i_fop = &zonefs_dir_operations;
	inode->i_size = 2;
	set_nlink(inode, 2);
	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
		if (sbi->s_zgroup[ztype].g_nr_zones) {
			inc_nlink(inode);
			inode->i_size++;
		}
	}

	sb->s_root = d_make_root(inode);
	if (!sb->s_root)
		goto cleanup;

	/*
	 * Take a reference on the zone groups directory inodes
	 * to keep them in the inode cache.
	 */
	ret = zonefs_get_zgroup_inodes(sb);
	if (ret)
		goto cleanup;

	ret = zonefs_sysfs_register(sb);
	if (ret)
		goto cleanup;

	return 0;

cleanup:
	zonefs_release_zgroup_inodes(sb);
	zonefs_free_zgroups(sb);

	return ret;
}

static void zonefs_kill_super(struct super_block *sb)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);

	/* Release the reference on the zone group directory inodes */
	zonefs_release_zgroup_inodes(sb);

	kill_block_super(sb);

	zonefs_sysfs_unregister(sb);
	zonefs_free_zgroups(sb);
	kfree(sbi);
}

static void zonefs_free_fc(struct fs_context *fc)
{
	struct zonefs_context *ctx = fc->fs_private;

	kfree(ctx);
}

static int zonefs_get_tree(struct fs_context *fc)
{
	return get_tree_bdev(fc, zonefs_fill_super);
}

static int zonefs_reconfigure(struct fs_context *fc)
{
	struct zonefs_context *ctx = fc->fs_private;
	struct super_block *sb = fc->root->d_sb;
	struct zonefs_sb_info *sbi = sb->s_fs_info;

	sync_filesystem(fc->root->d_sb);
	/* Copy new options from ctx into sbi. */
	sbi->s_mount_opts = ctx->s_mount_opts;

	return 0;
}

static const struct fs_context_operations zonefs_context_ops = {
	.parse_param    = zonefs_parse_param,
	.get_tree       = zonefs_get_tree,
	.reconfigure	= zonefs_reconfigure,
	.free           = zonefs_free_fc,
};

/*
 * Set up the filesystem mount context.
 */
static int zonefs_init_fs_context(struct fs_context *fc)
{
	struct zonefs_context *ctx;

	ctx = kzalloc(sizeof(struct zonefs_context), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;
	ctx->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO;
	fc->ops = &zonefs_context_ops;
	fc->fs_private = ctx;

	return 0;
}

/*
 * File system definition and registration.
 */
static struct file_system_type zonefs_type = {
	.owner			= THIS_MODULE,
	.name			= "zonefs",
	.kill_sb		= zonefs_kill_super,
	.fs_flags		= FS_REQUIRES_DEV,
	.init_fs_context	= zonefs_init_fs_context,
	.parameters		= zonefs_param_spec,
};

static int __init zonefs_init_inodecache(void)
{
	zonefs_inode_cachep = kmem_cache_create("zonefs_inode_cache",
			sizeof(struct zonefs_inode_info), 0,
			SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
			NULL);
	if (zonefs_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void zonefs_destroy_inodecache(void)
{
	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy the inode cache.
	 */
	rcu_barrier();
	kmem_cache_destroy(zonefs_inode_cachep);
}

static int __init zonefs_init(void)
{
	int ret;

	BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE);

	ret = zonefs_init_inodecache();
	if (ret)
		return ret;

	ret = zonefs_sysfs_init();
	if (ret)
		goto destroy_inodecache;

	ret = register_filesystem(&zonefs_type);
	if (ret)
		goto sysfs_exit;

	return 0;

sysfs_exit:
	zonefs_sysfs_exit();
destroy_inodecache:
	zonefs_destroy_inodecache();

	return ret;
}

static void __exit zonefs_exit(void)
{
	unregister_filesystem(&zonefs_type);
	zonefs_sysfs_exit();
	zonefs_destroy_inodecache();
}

MODULE_AUTHOR("Damien Le Moal");
MODULE_DESCRIPTION("Zone file system for zoned block devices");
MODULE_LICENSE("GPL");
MODULE_ALIAS_FS("zonefs");
module_init(zonefs_init);
module_exit(zonefs_exit);