summaryrefslogtreecommitdiffstats
path: root/fs/zonefs/super.c
blob: dbf03635869c30adefa8288271c8ef8cc35544a6 (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
// 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/parser.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 "zonefs.h"

#define CREATE_TRACE_POINTS
#include "trace.h"

static inline int zonefs_zone_mgmt(struct inode *inode,
				   enum req_opf op)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	int ret;

	lockdep_assert_held(&zi->i_truncate_mutex);

	trace_zonefs_zone_mgmt(inode, op);
	ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector,
			       zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS);
	if (ret) {
		zonefs_err(inode->i_sb,
			   "Zone management operation %s at %llu failed %d\n",
			   blk_op_str(op), zi->i_zsector, ret);
		return ret;
	}

	return 0;
}

static inline void zonefs_i_size_write(struct inode *inode, loff_t isize)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	i_size_write(inode, isize);
	/*
	 * A full zone is no longer open/active and does not need
	 * explicit closing.
	 */
	if (isize >= zi->i_max_size)
		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
}

static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
			      unsigned int flags, struct iomap *iomap,
			      struct iomap *srcmap)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct super_block *sb = inode->i_sb;
	loff_t isize;

	/* All I/Os should always be within the file maximum size */
	if (WARN_ON_ONCE(offset + length > zi->i_max_size))
		return -EIO;

	/*
	 * Sequential zones can only accept direct writes. This is already
	 * checked when writes are issued, so warn if we see a page writeback
	 * operation.
	 */
	if (WARN_ON_ONCE(zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
			 (flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)))
		return -EIO;

	/*
	 * For conventional zones, all blocks are always mapped. For sequential
	 * zones, all blocks after always mapped below the inode size (zone
	 * write pointer) and unwriten beyond.
	 */
	mutex_lock(&zi->i_truncate_mutex);
	isize = i_size_read(inode);
	if (offset >= isize)
		iomap->type = IOMAP_UNWRITTEN;
	else
		iomap->type = IOMAP_MAPPED;
	if (flags & IOMAP_WRITE)
		length = zi->i_max_size - offset;
	else
		length = min(length, isize - offset);
	mutex_unlock(&zi->i_truncate_mutex);

	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
	iomap->length = ALIGN(offset + length, sb->s_blocksize) - iomap->offset;
	iomap->bdev = inode->i_sb->s_bdev;
	iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;

	trace_zonefs_iomap_begin(inode, iomap);

	return 0;
}

static const struct iomap_ops zonefs_iomap_ops = {
	.iomap_begin	= zonefs_iomap_begin,
};

static int zonefs_readpage(struct file *unused, struct page *page)
{
	return iomap_readpage(page, &zonefs_iomap_ops);
}

static void zonefs_readahead(struct readahead_control *rac)
{
	iomap_readahead(rac, &zonefs_iomap_ops);
}

/*
 * Map blocks for page writeback. This is used only on conventional zone files,
 * which implies that the page range can only be within the fixed inode size.
 */
static int zonefs_map_blocks(struct iomap_writepage_ctx *wpc,
			     struct inode *inode, loff_t offset)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	if (WARN_ON_ONCE(zi->i_ztype != ZONEFS_ZTYPE_CNV))
		return -EIO;
	if (WARN_ON_ONCE(offset >= i_size_read(inode)))
		return -EIO;

	/* If the mapping is already OK, nothing needs to be done */
	if (offset >= wpc->iomap.offset &&
	    offset < wpc->iomap.offset + wpc->iomap.length)
		return 0;

	return zonefs_iomap_begin(inode, offset, zi->i_max_size - offset,
				  IOMAP_WRITE, &wpc->iomap, NULL);
}

static const struct iomap_writeback_ops zonefs_writeback_ops = {
	.map_blocks		= zonefs_map_blocks,
};

static int zonefs_writepage(struct page *page, struct writeback_control *wbc)
{
	struct iomap_writepage_ctx wpc = { };

	return iomap_writepage(page, wbc, &wpc, &zonefs_writeback_ops);
}

static int zonefs_writepages(struct address_space *mapping,
			     struct writeback_control *wbc)
{
	struct iomap_writepage_ctx wpc = { };

	return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
}

static int zonefs_swap_activate(struct swap_info_struct *sis,
				struct file *swap_file, sector_t *span)
{
	struct inode *inode = file_inode(swap_file);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	if (zi->i_ztype != ZONEFS_ZTYPE_CNV) {
		zonefs_err(inode->i_sb,
			   "swap file: not a conventional zone file\n");
		return -EINVAL;
	}

	return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops);
}

static const struct address_space_operations zonefs_file_aops = {
	.readpage		= zonefs_readpage,
	.readahead		= zonefs_readahead,
	.writepage		= zonefs_writepage,
	.writepages		= zonefs_writepages,
	.set_page_dirty		= __set_page_dirty_nobuffers,
	.releasepage		= iomap_releasepage,
	.invalidatepage		= iomap_invalidatepage,
	.migratepage		= iomap_migrate_page,
	.is_partially_uptodate	= iomap_is_partially_uptodate,
	.error_remove_page	= generic_error_remove_page,
	.direct_IO		= noop_direct_IO,
	.swap_activate		= zonefs_swap_activate,
};

static 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 and adjust its file inode access permissions for
 * offline and readonly zones. Return the inode size corresponding to the
 * amount of readable data in the zone.
 */
static loff_t zonefs_check_zone_condition(struct inode *inode,
					  struct blk_zone *zone, bool warn,
					  bool mount)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	switch (zone->cond) {
	case BLK_ZONE_COND_OFFLINE:
		/*
		 * Dead zone: make the inode immutable, disable all accesses
		 * and set the file size to 0 (zone wp set to zone start).
		 */
		if (warn)
			zonefs_warn(inode->i_sb, "inode %lu: offline zone\n",
				    inode->i_ino);
		inode->i_flags |= S_IMMUTABLE;
		inode->i_mode &= ~0777;
		zone->wp = zone->start;
		return 0;
	case BLK_ZONE_COND_READONLY:
		/*
		 * The write pointer of read-only zones is invalid. If such a
		 * zone is found during mount, the file size cannot be retrieved
		 * so we treat the zone as offline (mount == true case).
		 * Otherwise, keep the file size as it was when last updated
		 * so that the user can recover data. In both cases, writes are
		 * always disabled for the zone.
		 */
		if (warn)
			zonefs_warn(inode->i_sb, "inode %lu: read-only zone\n",
				    inode->i_ino);
		inode->i_flags |= S_IMMUTABLE;
		if (mount) {
			zone->cond = BLK_ZONE_COND_OFFLINE;
			inode->i_mode &= ~0777;
			zone->wp = zone->start;
			return 0;
		}
		inode->i_mode &= ~0222;
		return i_size_read(inode);
	case BLK_ZONE_COND_FULL:
		/* The write pointer of full zones is invalid. */
		return zi->i_max_size;
	default:
		if (zi->i_ztype == ZONEFS_ZTYPE_CNV)
			return zi->i_max_size;
		return (zone->wp - zone->start) << SECTOR_SHIFT;
	}
}

struct zonefs_ioerr_data {
	struct inode	*inode;
	bool		write;
};

static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
			      void *data)
{
	struct zonefs_ioerr_data *err = data;
	struct inode *inode = err->inode;
	struct zonefs_inode_info *zi = ZONEFS_I(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(inode, zone, true, false);
	isize = i_size_read(inode);
	if (zone->cond != BLK_ZONE_COND_OFFLINE &&
	    zone->cond != BLK_ZONE_COND_READONLY &&
	    !err->write && isize == data_size)
		return 0;

	/*
	 * 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 (zi->i_ztype == ZONEFS_ZTYPE_SEQ && 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 (zone->cond == BLK_ZONE_COND_OFFLINE ||
	    sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL) {
		zonefs_warn(sb, "inode %lu: read/write access disabled\n",
			    inode->i_ino);
		if (zone->cond != BLK_ZONE_COND_OFFLINE) {
			zone->cond = BLK_ZONE_COND_OFFLINE;
			data_size = zonefs_check_zone_condition(inode, zone,
								false, false);
		}
	} else if (zone->cond == BLK_ZONE_COND_READONLY ||
		   sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO) {
		zonefs_warn(sb, "inode %lu: write access disabled\n",
			    inode->i_ino);
		if (zone->cond != BLK_ZONE_COND_READONLY) {
			zone->cond = BLK_ZONE_COND_READONLY;
			data_size = zonefs_check_zone_condition(inode, zone,
								false, false);
		}
	}

	/*
	 * 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) &&
	    (zone->cond == BLK_ZONE_COND_OFFLINE ||
	     zone->cond == BLK_ZONE_COND_READONLY))
		zi->i_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);
	zi->i_wpoffset = data_size;

	return 0;
}

/*
 * 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).
 */
static void __zonefs_io_error(struct inode *inode, bool write)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	unsigned int noio_flag;
	unsigned int nr_zones =
		zi->i_zone_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT);
	struct zonefs_ioerr_data err = {
		.inode = inode,
		.write = write,
	};
	int ret;

	/*
	 * 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, zi->i_zsector, nr_zones,
				  zonefs_io_error_cb, &err);
	if (ret != nr_zones)
		zonefs_err(sb, "Get inode %lu zone information failed %d\n",
			   inode->i_ino, ret);
	memalloc_noio_restore(noio_flag);
}

static void zonefs_io_error(struct inode *inode, bool write)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	mutex_lock(&zi->i_truncate_mutex);
	__zonefs_io_error(inode, write);
	mutex_unlock(&zi->i_truncate_mutex);
}

static int zonefs_file_truncate(struct inode *inode, loff_t isize)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	loff_t old_isize;
	enum req_opf op;
	int ret = 0;

	/*
	 * Only sequential zone files can be truncated and truncation is allowed
	 * only down to a 0 size, which is equivalent to a zone reset, and to
	 * the maximum file size, which is equivalent to a zone finish.
	 */
	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
		return -EPERM;

	if (!isize)
		op = REQ_OP_ZONE_RESET;
	else if (isize == zi->i_max_size)
		op = REQ_OP_ZONE_FINISH;
	else
		return -EPERM;

	inode_dio_wait(inode);

	/* Serialize against page faults */
	down_write(&zi->i_mmap_sem);

	/* Serialize against zonefs_iomap_begin() */
	mutex_lock(&zi->i_truncate_mutex);

	old_isize = i_size_read(inode);
	if (isize == old_isize)
		goto unlock;

	ret = zonefs_zone_mgmt(inode, op);
	if (ret)
		goto unlock;

	/*
	 * If the mount option ZONEFS_MNTOPT_EXPLICIT_OPEN is set,
	 * take care of open zones.
	 */
	if (zi->i_flags & ZONEFS_ZONE_OPEN) {
		/*
		 * Truncating a zone to EMPTY or FULL is the equivalent of
		 * closing the zone. For a truncation to 0, we need to
		 * re-open the zone to ensure new writes can be processed.
		 * For a truncation to the maximum file size, the zone is
		 * closed and writes cannot be accepted anymore, so clear
		 * the open flag.
		 */
		if (!isize)
			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
		else
			zi->i_flags &= ~ZONEFS_ZONE_OPEN;
	}

	zonefs_update_stats(inode, isize);
	truncate_setsize(inode, isize);
	zi->i_wpoffset = isize;

unlock:
	mutex_unlock(&zi->i_truncate_mutex);
	up_write(&zi->i_mmap_sem);

	return ret;
}

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

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

	ret = setattr_prepare(&init_user_ns, 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(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(&init_user_ns, inode, iattr);

	return 0;
}

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

static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end,
			     int datasync)
{
	struct inode *inode = file_inode(file);
	int ret = 0;

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

	/*
	 * Since only direct writes are allowed in sequential files, page cache
	 * flush is needed only for conventional zone files.
	 */
	if (ZONEFS_I(inode)->i_ztype == ZONEFS_ZTYPE_CNV)
		ret = file_write_and_wait_range(file, start, end);
	if (!ret)
		ret = blkdev_issue_flush(inode->i_sb->s_bdev);

	if (ret)
		zonefs_io_error(inode, true);

	return ret;
}

static vm_fault_t zonefs_filemap_fault(struct vm_fault *vmf)
{
	struct zonefs_inode_info *zi = ZONEFS_I(file_inode(vmf->vma->vm_file));
	vm_fault_t ret;

	down_read(&zi->i_mmap_sem);
	ret = filemap_fault(vmf);
	up_read(&zi->i_mmap_sem);

	return ret;
}

static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
{
	struct inode *inode = file_inode(vmf->vma->vm_file);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	vm_fault_t ret;

	if (unlikely(IS_IMMUTABLE(inode)))
		return VM_FAULT_SIGBUS;

	/*
	 * Sanity check: only conventional zone files can have shared
	 * writeable mappings.
	 */
	if (WARN_ON_ONCE(zi->i_ztype != ZONEFS_ZTYPE_CNV))
		return VM_FAULT_NOPAGE;

	sb_start_pagefault(inode->i_sb);
	file_update_time(vmf->vma->vm_file);

	/* Serialize against truncates */
	down_read(&zi->i_mmap_sem);
	ret = iomap_page_mkwrite(vmf, &zonefs_iomap_ops);
	up_read(&zi->i_mmap_sem);

	sb_end_pagefault(inode->i_sb);
	return ret;
}

static const struct vm_operations_struct zonefs_file_vm_ops = {
	.fault		= zonefs_filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= zonefs_filemap_page_mkwrite,
};

static int zonefs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	/*
	 * Conventional zones accept random writes, so their files can support
	 * shared writable mappings. For sequential zone files, only read
	 * mappings are possible since there are no guarantees for write
	 * ordering between msync() and page cache writeback.
	 */
	if (ZONEFS_I(file_inode(file))->i_ztype == ZONEFS_ZTYPE_SEQ &&
	    (vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
		return -EINVAL;

	file_accessed(file);
	vma->vm_ops = &zonefs_file_vm_ops;

	return 0;
}

static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence)
{
	loff_t isize = i_size_read(file_inode(file));

	/*
	 * Seeks are limited to below the zone size for conventional zones
	 * and below the zone write pointer for sequential zones. In both
	 * cases, this limit is the inode size.
	 */
	return generic_file_llseek_size(file, offset, whence, isize, isize);
}

static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
					int error, unsigned int flags)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	if (error) {
		zonefs_io_error(inode, true);
		return error;
	}

	if (size && zi->i_ztype != ZONEFS_ZTYPE_CNV) {
		/*
		 * Note that we may be seeing completions out of order,
		 * but that is not a problem since a write completed
		 * successfully necessarily means that all preceding writes
		 * were also successful. So we can safely increase the inode
		 * size to the write end location.
		 */
		mutex_lock(&zi->i_truncate_mutex);
		if (i_size_read(inode) < iocb->ki_pos + size) {
			zonefs_update_stats(inode, iocb->ki_pos + size);
			zonefs_i_size_write(inode, iocb->ki_pos + size);
		}
		mutex_unlock(&zi->i_truncate_mutex);
	}

	return 0;
}

static const struct iomap_dio_ops zonefs_write_dio_ops = {
	.end_io			= zonefs_file_write_dio_end_io,
};

static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct block_device *bdev = inode->i_sb->s_bdev;
	unsigned int max;
	struct bio *bio;
	ssize_t size;
	int nr_pages;
	ssize_t ret;

	max = queue_max_zone_append_sectors(bdev_get_queue(bdev));
	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
	iov_iter_truncate(from, max);

	nr_pages = iov_iter_npages(from, BIO_MAX_VECS);
	if (!nr_pages)
		return 0;

	bio = bio_alloc(GFP_NOFS, nr_pages);
	if (!bio)
		return -ENOMEM;

	bio_set_dev(bio, bdev);
	bio->bi_iter.bi_sector = zi->i_zsector;
	bio->bi_write_hint = iocb->ki_hint;
	bio->bi_ioprio = iocb->ki_ioprio;
	bio->bi_opf = REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE;
	if (iocb->ki_flags & IOCB_DSYNC)
		bio->bi_opf |= REQ_FUA;

	ret = bio_iov_iter_get_pages(bio, from);
	if (unlikely(ret))
		goto out_release;

	size = bio->bi_iter.bi_size;
	task_io_account_write(size);

	if (iocb->ki_flags & IOCB_HIPRI)
		bio_set_polled(bio, iocb);

	ret = submit_bio_wait(bio);

	zonefs_file_write_dio_end_io(iocb, size, ret, 0);
	trace_zonefs_file_dio_append(inode, size, ret);

out_release:
	bio_release_pages(bio, false);
	bio_put(bio);

	if (ret >= 0) {
		iocb->ki_pos += size;
		return size;
	}

	return ret;
}

/*
 * Do not exceed the LFS limits nor the file zone size. If pos is under the
 * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
 */
static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
					loff_t count)
{
	struct inode *inode = file_inode(file);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	loff_t limit = rlimit(RLIMIT_FSIZE);
	loff_t max_size = zi->i_max_size;

	if (limit != RLIM_INFINITY) {
		if (pos >= limit) {
			send_sig(SIGXFSZ, current, 0);
			return -EFBIG;
		}
		count = min(count, limit - pos);
	}

	if (!(file->f_flags & O_LARGEFILE))
		max_size = min_t(loff_t, MAX_NON_LFS, max_size);

	if (unlikely(pos >= max_size))
		return -EFBIG;

	return min(count, max_size - pos);
}

static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	loff_t count;

	if (IS_SWAPFILE(inode))
		return -ETXTBSY;

	if (!iov_iter_count(from))
		return 0;

	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
		return -EINVAL;

	if (iocb->ki_flags & IOCB_APPEND) {
		if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
			return -EINVAL;
		mutex_lock(&zi->i_truncate_mutex);
		iocb->ki_pos = zi->i_wpoffset;
		mutex_unlock(&zi->i_truncate_mutex);
	}

	count = zonefs_write_check_limits(file, iocb->ki_pos,
					  iov_iter_count(from));
	if (count < 0)
		return count;

	iov_iter_truncate(from, count);
	return iov_iter_count(from);
}

/*
 * Handle direct writes. For sequential zone files, this is the only possible
 * write path. For these files, check that the user is issuing writes
 * sequentially from the end of the file. This code assumes that the block layer
 * delivers write requests to the device in sequential order. This is always the
 * case if a block IO scheduler implementing the ELEVATOR_F_ZBD_SEQ_WRITE
 * elevator feature is being used (e.g. mq-deadline). The block layer always
 * automatically select such an elevator for zoned block devices during the
 * device initialization.
 */
static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct super_block *sb = inode->i_sb;
	bool sync = is_sync_kiocb(iocb);
	bool append = false;
	ssize_t ret, count;

	/*
	 * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
	 * as this can cause write reordering (e.g. the first aio gets EAGAIN
	 * on the inode lock but the second goes through but is now unaligned).
	 */
	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !sync &&
	    (iocb->ki_flags & IOCB_NOWAIT))
		return -EOPNOTSUPP;

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!inode_trylock(inode))
			return -EAGAIN;
	} else {
		inode_lock(inode);
	}

	count = zonefs_write_checks(iocb, from);
	if (count <= 0) {
		ret = count;
		goto inode_unlock;
	}

	if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
		ret = -EINVAL;
		goto inode_unlock;
	}

	/* Enforce sequential writes (append only) in sequential zones */
	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ) {
		mutex_lock(&zi->i_truncate_mutex);
		if (iocb->ki_pos != zi->i_wpoffset) {
			mutex_unlock(&zi->i_truncate_mutex);
			ret = -EINVAL;
			goto inode_unlock;
		}
		mutex_unlock(&zi->i_truncate_mutex);
		append = sync;
	}

	if (append)
		ret = zonefs_file_dio_append(iocb, from);
	else
		ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
				   &zonefs_write_dio_ops, 0);
	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
	    (ret > 0 || ret == -EIOCBQUEUED)) {
		if (ret > 0)
			count = ret;
		mutex_lock(&zi->i_truncate_mutex);
		zi->i_wpoffset += count;
		mutex_unlock(&zi->i_truncate_mutex);
	}

inode_unlock:
	inode_unlock(inode);

	return ret;
}

static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
					  struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	ssize_t ret;

	/*
	 * Direct IO writes are mandatory for sequential zone files so that the
	 * write IO issuing order is preserved.
	 */
	if (zi->i_ztype != ZONEFS_ZTYPE_CNV)
		return -EIO;

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!inode_trylock(inode))
			return -EAGAIN;
	} else {
		inode_lock(inode);
	}

	ret = zonefs_write_checks(iocb, from);
	if (ret <= 0)
		goto inode_unlock;

	ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
	if (ret > 0)
		iocb->ki_pos += ret;
	else if (ret == -EIO)
		zonefs_io_error(inode, true);

inode_unlock:
	inode_unlock(inode);
	if (ret > 0)
		ret = generic_write_sync(iocb, ret);

	return ret;
}

static ssize_t zonefs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);

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

	if (sb_rdonly(inode->i_sb))
		return -EROFS;

	/* Write operations beyond the zone size are not allowed */
	if (iocb->ki_pos >= ZONEFS_I(inode)->i_max_size)
		return -EFBIG;

	if (iocb->ki_flags & IOCB_DIRECT) {
		ssize_t ret = zonefs_file_dio_write(iocb, from);
		if (ret != -ENOTBLK)
			return ret;
	}

	return zonefs_file_buffered_write(iocb, from);
}

static int zonefs_file_read_dio_end_io(struct kiocb *iocb, ssize_t size,
				       int error, unsigned int flags)
{
	if (error) {
		zonefs_io_error(file_inode(iocb->ki_filp), false);
		return error;
	}

	return 0;
}

static const struct iomap_dio_ops zonefs_read_dio_ops = {
	.end_io			= zonefs_file_read_dio_end_io,
};

static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct super_block *sb = inode->i_sb;
	loff_t isize;
	ssize_t ret;

	/* Offline zones cannot be read */
	if (unlikely(IS_IMMUTABLE(inode) && !(inode->i_mode & 0777)))
		return -EPERM;

	if (iocb->ki_pos >= zi->i_max_size)
		return 0;

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!inode_trylock_shared(inode))
			return -EAGAIN;
	} else {
		inode_lock_shared(inode);
	}

	/* Limit read operations to written data */
	mutex_lock(&zi->i_truncate_mutex);
	isize = i_size_read(inode);
	if (iocb->ki_pos >= isize) {
		mutex_unlock(&zi->i_truncate_mutex);
		ret = 0;
		goto inode_unlock;
	}
	iov_iter_truncate(to, isize - iocb->ki_pos);
	mutex_unlock(&zi->i_truncate_mutex);

	if (iocb->ki_flags & IOCB_DIRECT) {
		size_t count = iov_iter_count(to);

		if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
			ret = -EINVAL;
			goto inode_unlock;
		}
		file_accessed(iocb->ki_filp);
		ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
				   &zonefs_read_dio_ops, 0);
	} else {
		ret = generic_file_read_iter(iocb, to);
		if (ret == -EIO)
			zonefs_io_error(inode, false);
	}

inode_unlock:
	inode_unlock_shared(inode);

	return ret;
}

static inline bool zonefs_file_use_exp_open(struct inode *inode, struct file *file)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);

	if (!(sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN))
		return false;

	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
		return false;

	if (!(file->f_mode & FMODE_WRITE))
		return false;

	return true;
}

static int zonefs_open_zone(struct inode *inode)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
	int ret = 0;

	mutex_lock(&zi->i_truncate_mutex);

	if (!zi->i_wr_refcnt) {
		if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) {
			atomic_dec(&sbi->s_open_zones);
			ret = -EBUSY;
			goto unlock;
		}

		if (i_size_read(inode) < zi->i_max_size) {
			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
			if (ret) {
				atomic_dec(&sbi->s_open_zones);
				goto unlock;
			}
			zi->i_flags |= ZONEFS_ZONE_OPEN;
		}
	}

	zi->i_wr_refcnt++;

unlock:
	mutex_unlock(&zi->i_truncate_mutex);

	return ret;
}

static int zonefs_file_open(struct inode *inode, struct file *file)
{
	int ret;

	ret = generic_file_open(inode, file);
	if (ret)
		return ret;

	if (zonefs_file_use_exp_open(inode, file))
		return zonefs_open_zone(inode);

	return 0;
}

static void zonefs_close_zone(struct inode *inode)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	int ret = 0;

	mutex_lock(&zi->i_truncate_mutex);
	zi->i_wr_refcnt--;
	if (!zi->i_wr_refcnt) {
		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
		struct super_block *sb = inode->i_sb;

		/*
		 * If the file zone is full, it is not open anymore and we only
		 * need to decrement the open count.
		 */
		if (!(zi->i_flags & ZONEFS_ZONE_OPEN))
			goto dec;

		ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
		if (ret) {
			__zonefs_io_error(inode, false);
			/*
			 * Leaving zones explicitly open may lead to a state
			 * where most zones cannot be written (zone resources
			 * exhausted). So take preventive action by remounting
			 * read-only.
			 */
			if (zi->i_flags & ZONEFS_ZONE_OPEN &&
			    !(sb->s_flags & SB_RDONLY)) {
				zonefs_warn(sb, "closing zone failed, remounting filesystem read-only\n");
				sb->s_flags |= SB_RDONLY;
			}
		}
		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
dec:
		atomic_dec(&sbi->s_open_zones);
	}
	mutex_unlock(&zi->i_truncate_mutex);
}

static int zonefs_file_release(struct inode *inode, struct file *file)
{
	/*
	 * If we explicitly open a zone we must close it again as well, but the
	 * zone management operation can fail (either due to an IO error or as
	 * the zone has gone offline or read-only). Make sure we don't fail the
	 * close(2) for user-space.
	 */
	if (zonefs_file_use_exp_open(inode, file))
		zonefs_close_zone(inode);

	return 0;
}

static const struct file_operations zonefs_file_operations = {
	.open		= zonefs_file_open,
	.release	= zonefs_file_release,
	.fsync		= zonefs_file_fsync,
	.mmap		= zonefs_file_mmap,
	.llseek		= zonefs_file_llseek,
	.read_iter	= zonefs_file_read_iter,
	.write_iter	= zonefs_file_write_iter,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.iopoll		= iomap_dio_iopoll,
};

static struct kmem_cache *zonefs_inode_cachep;

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

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

	inode_init_once(&zi->i_vnode);
	mutex_init(&zi->i_truncate_mutex);
	init_rwsem(&zi->i_mmap_sem);
	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_nr_files[t])
			buf->f_files += sbi->s_nr_files[t] + 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_ro, Opt_errors_zro, Opt_errors_zol, Opt_errors_repair,
	Opt_explicit_open, Opt_err,
};

static const match_table_t tokens = {
	{ Opt_errors_ro,	"errors=remount-ro"},
	{ Opt_errors_zro,	"errors=zone-ro"},
	{ Opt_errors_zol,	"errors=zone-offline"},
	{ Opt_errors_repair,	"errors=repair"},
	{ Opt_explicit_open,	"explicit-open" },
	{ Opt_err,		NULL}
};

static int zonefs_parse_options(struct super_block *sb, char *options)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	substring_t args[MAX_OPT_ARGS];
	char *p;

	if (!options)
		return 0;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;

		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_errors_ro:
			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_RO;
			break;
		case Opt_errors_zro:
			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZRO;
			break;
		case Opt_errors_zol:
			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZOL;
			break;
		case Opt_errors_repair:
			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_REPAIR;
			break;
		case Opt_explicit_open:
			sbi->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_remount(struct super_block *sb, int *flags, char *data)
{
	sync_filesystem(sb);

	return zonefs_parse_options(sb, data);
}

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

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

static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode,
				  enum zonefs_ztype type)
{
	struct super_block *sb = parent->i_sb;

	inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1;
	inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555);
	inode->i_op = &zonefs_dir_inode_operations;
	inode->i_fop = &simple_dir_operations;
	set_nlink(inode, 2);
	inc_nlink(parent);
}

static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone,
				   enum zonefs_ztype type)
{
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	inode->i_ino = zone->start >> sbi->s_zone_sectors_shift;
	inode->i_mode = S_IFREG | sbi->s_perm;

	zi->i_ztype = type;
	zi->i_zsector = zone->start;
	zi->i_zone_size = zone->len << SECTOR_SHIFT;

	zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE,
			       zone->capacity << SECTOR_SHIFT);
	zi->i_wpoffset = zonefs_check_zone_condition(inode, zone, true, true);

	inode->i_uid = sbi->s_uid;
	inode->i_gid = sbi->s_gid;
	inode->i_size = zi->i_wpoffset;
	inode->i_blocks = zi->i_max_size >> SECTOR_SHIFT;

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

	sb->s_maxbytes = max(zi->i_max_size, sb->s_maxbytes);
	sbi->s_blocks += zi->i_max_size >> sb->s_blocksize_bits;
	sbi->s_used_blocks += zi->i_wpoffset >> sb->s_blocksize_bits;
}

static struct dentry *zonefs_create_inode(struct dentry *parent,
					const char *name, struct blk_zone *zone,
					enum zonefs_ztype type)
{
	struct inode *dir = d_inode(parent);
	struct dentry *dentry;
	struct inode *inode;

	dentry = d_alloc_name(parent, name);
	if (!dentry)
		return NULL;

	inode = new_inode(parent->d_sb);
	if (!inode)
		goto dput;

	inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime;
	if (zone)
		zonefs_init_file_inode(inode, zone, type);
	else
		zonefs_init_dir_inode(dir, inode, type);
	d_add(dentry, inode);
	dir->i_size++;

	return dentry;

dput:
	dput(dentry);

	return NULL;
}

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

/*
 * Create a zone group and populate it with zone files.
 */
static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
				enum zonefs_ztype type)
{
	struct super_block *sb = zd->sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct blk_zone *zone, *next, *end;
	const char *zgroup_name;
	char *file_name;
	struct dentry *dir;
	unsigned int n = 0;
	int ret;

	/* If the group is empty, there is nothing to do */
	if (!zd->nr_zones[type])
		return 0;

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

	if (type == ZONEFS_ZTYPE_CNV)
		zgroup_name = "cnv";
	else
		zgroup_name = "seq";

	dir = zonefs_create_inode(sb->s_root, zgroup_name, NULL, type);
	if (!dir) {
		ret = -ENOMEM;
		goto free;
	}

	/*
	 * The first zone contains the super block: skip it.
	 */
	end = zd->zones + blkdev_nr_zones(sb->s_bdev->bd_disk);
	for (zone = &zd->zones[1]; zone < end; zone = next) {

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

		/*
		 * 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 (type == ZONEFS_ZTYPE_CNV &&
		    (sbi->s_features & ZONEFS_F_AGGRCNV)) {
			for (; next < end; next++) {
				if (zonefs_zone_type(next) != type)
					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;
			}
			if (zone->capacity != zone->len) {
				zonefs_err(sb, "Invalid conventional zone capacity\n");
				ret = -EINVAL;
				goto free;
			}
		}

		/*
		 * Use the file number within its group as file name.
		 */
		snprintf(file_name, ZONEFS_NAME_MAX - 1, "%u", n);
		if (!zonefs_create_inode(dir, file_name, zone, type)) {
			ret = -ENOMEM;
			goto free;
		}

		n++;
	}

	zonefs_info(sb, "Zone group \"%s\" has %u file%s\n",
		    zgroup_name, n, n > 1 ? "s" : "");

	sbi->s_nr_files[type] = n;
	ret = 0;

free:
	kfree(file_name);

	return ret;
}

static int zonefs_get_zone_info_cb(struct blk_zone *zone, unsigned int idx,
				   void *data)
{
	struct zonefs_zone_data *zd = data;

	/*
	 * Count the number of usable zones: the first zone at index 0 contains
	 * the super block and is ignored.
	 */
	switch (zone->type) {
	case BLK_ZONE_TYPE_CONVENTIONAL:
		zone->wp = zone->start + zone->len;
		if (idx)
			zd->nr_zones[ZONEFS_ZTYPE_CNV]++;
		break;
	case BLK_ZONE_TYPE_SEQWRITE_REQ:
	case BLK_ZONE_TYPE_SEQWRITE_PREF:
		if (idx)
			zd->nr_zones[ZONEFS_ZTYPE_SEQ]++;
		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(blkdev_nr_zones(bdev->bd_disk),
			     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 != blkdev_nr_zones(bdev->bd_disk)) {
		zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n",
			   ret, blkdev_nr_zones(bdev->bd_disk));
		return -EIO;
	}

	return 0;
}

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

/*
 * 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, &bio_vec, 1);
	bio.bi_iter.bi_sector = 0;
	bio.bi_opf = REQ_OP_READ;
	bio_set_dev(&bio, sb->s_bdev);
	bio_add_page(&bio, page, PAGE_SIZE, 0);

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

	super = kmap(page);

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

	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 unmap;
	}

	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 unmap;
	}

	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 unmap;
		}
	}

	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 unmap;
		}
	}

	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 unmap;
	}

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

unmap:
	kunmap(page);
free_page:
	__free_page(page);

	return ret;
}

/*
 * 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, void *data, int silent)
{
	struct zonefs_zone_data zd;
	struct zonefs_sb_info *sbi;
	struct inode *inode;
	enum zonefs_ztype t;
	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 = ZONEFS_MNTOPT_ERRORS_RO;
	sbi->s_max_open_zones = bdev_max_open_zones(sb->s_bdev);
	atomic_set(&sbi->s_open_zones, 0);
	if (!sbi->s_max_open_zones &&
	    sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
		zonefs_info(sb, "No open zones limit. Ignoring explicit_open mount option\n");
		sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
	}

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

	ret = zonefs_parse_options(sb, data);
	if (ret)
		return ret;

	memset(&zd, 0, sizeof(struct zonefs_zone_data));
	zd.sb = sb;
	ret = zonefs_get_zone_info(&zd);
	if (ret)
		goto cleanup;

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

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

	inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk);
	inode->i_mode = S_IFDIR | 0555;
	inode->i_ctime = inode->i_mtime = inode->i_atime = current_time(inode);
	inode->i_op = &zonefs_dir_inode_operations;
	inode->i_fop = &simple_dir_operations;
	set_nlink(inode, 2);

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

	/* Create and populate files in zone groups directories */
	for (t = 0; t < ZONEFS_ZTYPE_MAX; t++) {
		ret = zonefs_create_zgroup(&zd, t);
		if (ret)
			break;
	}

cleanup:
	zonefs_cleanup_zone_info(&zd);

	return ret;
}

static struct dentry *zonefs_mount(struct file_system_type *fs_type,
				   int flags, const char *dev_name, void *data)
{
	return mount_bdev(fs_type, flags, dev_name, data, zonefs_fill_super);
}

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

	if (sb->s_root)
		d_genocide(sb->s_root);
	kill_block_super(sb);
	kfree(sbi);
}

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

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_MEM_SPREAD | 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 = register_filesystem(&zonefs_type);
	if (ret) {
		zonefs_destroy_inodecache();
		return ret;
	}

	return 0;
}

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

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