summaryrefslogtreecommitdiffstats
path: root/drivers/md/dm-cache-metadata.c
blob: 9e0c69958587209a0fb3af47c42446f4d2b58910 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2012 Red Hat, Inc.
 *
 * This file is released under the GPL.
 */

#include "dm-cache-metadata.h"

#include "persistent-data/dm-array.h"
#include "persistent-data/dm-bitset.h"
#include "persistent-data/dm-space-map.h"
#include "persistent-data/dm-space-map-disk.h"
#include "persistent-data/dm-transaction-manager.h"

#include <linux/device-mapper.h>
#include <linux/refcount.h>

/*----------------------------------------------------------------*/

#define DM_MSG_PREFIX   "cache metadata"

#define CACHE_SUPERBLOCK_MAGIC 06142003
#define CACHE_SUPERBLOCK_LOCATION 0

/*
 * defines a range of metadata versions that this module can handle.
 */
#define MIN_CACHE_VERSION 1
#define MAX_CACHE_VERSION 2

/*
 *  3 for btree insert +
 *  2 for btree lookup used within space map
 */
#define CACHE_MAX_CONCURRENT_LOCKS 5
#define SPACE_MAP_ROOT_SIZE 128

enum superblock_flag_bits {
	/* for spotting crashes that would invalidate the dirty bitset */
	CLEAN_SHUTDOWN,
	/* metadata must be checked using the tools */
	NEEDS_CHECK,
};

/*
 * Each mapping from cache block -> origin block carries a set of flags.
 */
enum mapping_bits {
	/*
	 * A valid mapping.  Because we're using an array we clear this
	 * flag for an non existant mapping.
	 */
	M_VALID = 1,

	/*
	 * The data on the cache is different from that on the origin.
	 * This flag is only used by metadata format 1.
	 */
	M_DIRTY = 2
};

struct cache_disk_superblock {
	__le32 csum;
	__le32 flags;
	__le64 blocknr;

	__u8 uuid[16];
	__le64 magic;
	__le32 version;

	__u8 policy_name[CACHE_POLICY_NAME_SIZE];
	__le32 policy_hint_size;

	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
	__le64 mapping_root;
	__le64 hint_root;

	__le64 discard_root;
	__le64 discard_block_size;
	__le64 discard_nr_blocks;

	__le32 data_block_size;
	__le32 metadata_block_size;
	__le32 cache_blocks;

	__le32 compat_flags;
	__le32 compat_ro_flags;
	__le32 incompat_flags;

	__le32 read_hits;
	__le32 read_misses;
	__le32 write_hits;
	__le32 write_misses;

	__le32 policy_version[CACHE_POLICY_VERSION_SIZE];

	/*
	 * Metadata format 2 fields.
	 */
	__le64 dirty_root;
} __packed;

struct dm_cache_metadata {
	refcount_t ref_count;
	struct list_head list;

	unsigned int version;
	struct block_device *bdev;
	struct dm_block_manager *bm;
	struct dm_space_map *metadata_sm;
	struct dm_transaction_manager *tm;

	struct dm_array_info info;
	struct dm_array_info hint_info;
	struct dm_disk_bitset discard_info;

	struct rw_semaphore root_lock;
	unsigned long flags;
	dm_block_t root;
	dm_block_t hint_root;
	dm_block_t discard_root;

	sector_t discard_block_size;
	dm_dblock_t discard_nr_blocks;

	sector_t data_block_size;
	dm_cblock_t cache_blocks;
	bool changed:1;
	bool clean_when_opened:1;

	char policy_name[CACHE_POLICY_NAME_SIZE];
	unsigned int policy_version[CACHE_POLICY_VERSION_SIZE];
	size_t policy_hint_size;
	struct dm_cache_statistics stats;

	/*
	 * Reading the space map root can fail, so we read it into this
	 * buffer before the superblock is locked and updated.
	 */
	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];

	/*
	 * Set if a transaction has to be aborted but the attempt to roll
	 * back to the previous (good) transaction failed.  The only
	 * metadata operation permissible in this state is the closing of
	 * the device.
	 */
	bool fail_io:1;

	/*
	 * Metadata format 2 fields.
	 */
	dm_block_t dirty_root;
	struct dm_disk_bitset dirty_info;

	/*
	 * These structures are used when loading metadata.  They're too
	 * big to put on the stack.
	 */
	struct dm_array_cursor mapping_cursor;
	struct dm_array_cursor hint_cursor;
	struct dm_bitset_cursor dirty_cursor;
};

/*
 *-----------------------------------------------------------------
 * superblock validator
 *-----------------------------------------------------------------
 */
#define SUPERBLOCK_CSUM_XOR 9031977

static void sb_prepare_for_write(struct dm_block_validator *v,
				 struct dm_block *b,
				 size_t sb_block_size)
{
	struct cache_disk_superblock *disk_super = dm_block_data(b);

	disk_super->blocknr = cpu_to_le64(dm_block_location(b));
	disk_super->csum = cpu_to_le32(dm_bm_checksum(&disk_super->flags,
						      sb_block_size - sizeof(__le32),
						      SUPERBLOCK_CSUM_XOR));
}

static int check_metadata_version(struct cache_disk_superblock *disk_super)
{
	uint32_t metadata_version = le32_to_cpu(disk_super->version);

	if (metadata_version < MIN_CACHE_VERSION || metadata_version > MAX_CACHE_VERSION) {
		DMERR("Cache metadata version %u found, but only versions between %u and %u supported.",
		      metadata_version, MIN_CACHE_VERSION, MAX_CACHE_VERSION);
		return -EINVAL;
	}

	return 0;
}

static int sb_check(struct dm_block_validator *v,
		    struct dm_block *b,
		    size_t sb_block_size)
{
	struct cache_disk_superblock *disk_super = dm_block_data(b);
	__le32 csum_le;

	if (dm_block_location(b) != le64_to_cpu(disk_super->blocknr)) {
		DMERR("%s failed: blocknr %llu: wanted %llu",
		      __func__, le64_to_cpu(disk_super->blocknr),
		      (unsigned long long)dm_block_location(b));
		return -ENOTBLK;
	}

	if (le64_to_cpu(disk_super->magic) != CACHE_SUPERBLOCK_MAGIC) {
		DMERR("%s failed: magic %llu: wanted %llu",
		      __func__, le64_to_cpu(disk_super->magic),
		      (unsigned long long)CACHE_SUPERBLOCK_MAGIC);
		return -EILSEQ;
	}

	csum_le = cpu_to_le32(dm_bm_checksum(&disk_super->flags,
					     sb_block_size - sizeof(__le32),
					     SUPERBLOCK_CSUM_XOR));
	if (csum_le != disk_super->csum) {
		DMERR("%s failed: csum %u: wanted %u",
		      __func__, le32_to_cpu(csum_le), le32_to_cpu(disk_super->csum));
		return -EILSEQ;
	}

	return check_metadata_version(disk_super);
}

static struct dm_block_validator sb_validator = {
	.name = "superblock",
	.prepare_for_write = sb_prepare_for_write,
	.check = sb_check
};

/*----------------------------------------------------------------*/

static int superblock_read_lock(struct dm_cache_metadata *cmd,
				struct dm_block **sblock)
{
	return dm_bm_read_lock(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
			       &sb_validator, sblock);
}

static int superblock_lock_zero(struct dm_cache_metadata *cmd,
				struct dm_block **sblock)
{
	return dm_bm_write_lock_zero(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
				     &sb_validator, sblock);
}

static int superblock_lock(struct dm_cache_metadata *cmd,
			   struct dm_block **sblock)
{
	return dm_bm_write_lock(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
				&sb_validator, sblock);
}

/*----------------------------------------------------------------*/

static int __superblock_all_zeroes(struct dm_block_manager *bm, bool *result)
{
	int r;
	unsigned int i;
	struct dm_block *b;
	__le64 *data_le, zero = cpu_to_le64(0);
	unsigned int sb_block_size = dm_bm_block_size(bm) / sizeof(__le64);

	/*
	 * We can't use a validator here - it may be all zeroes.
	 */
	r = dm_bm_read_lock(bm, CACHE_SUPERBLOCK_LOCATION, NULL, &b);
	if (r)
		return r;

	data_le = dm_block_data(b);
	*result = true;
	for (i = 0; i < sb_block_size; i++) {
		if (data_le[i] != zero) {
			*result = false;
			break;
		}
	}

	dm_bm_unlock(b);

	return 0;
}

static void __setup_mapping_info(struct dm_cache_metadata *cmd)
{
	struct dm_btree_value_type vt;

	vt.context = NULL;
	vt.size = sizeof(__le64);
	vt.inc = NULL;
	vt.dec = NULL;
	vt.equal = NULL;
	dm_array_info_init(&cmd->info, cmd->tm, &vt);

	if (cmd->policy_hint_size) {
		vt.size = sizeof(__le32);
		dm_array_info_init(&cmd->hint_info, cmd->tm, &vt);
	}
}

static int __save_sm_root(struct dm_cache_metadata *cmd)
{
	int r;
	size_t metadata_len;

	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
	if (r < 0)
		return r;

	return dm_sm_copy_root(cmd->metadata_sm, &cmd->metadata_space_map_root,
			       metadata_len);
}

static void __copy_sm_root(struct dm_cache_metadata *cmd,
			   struct cache_disk_superblock *disk_super)
{
	memcpy(&disk_super->metadata_space_map_root,
	       &cmd->metadata_space_map_root,
	       sizeof(cmd->metadata_space_map_root));
}

static bool separate_dirty_bits(struct dm_cache_metadata *cmd)
{
	return cmd->version >= 2;
}

static int __write_initial_superblock(struct dm_cache_metadata *cmd)
{
	int r;
	struct dm_block *sblock;
	struct cache_disk_superblock *disk_super;
	sector_t bdev_size = bdev_nr_sectors(cmd->bdev);

	/* FIXME: see if we can lose the max sectors limit */
	if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS)
		bdev_size = DM_CACHE_METADATA_MAX_SECTORS;

	r = dm_tm_pre_commit(cmd->tm);
	if (r < 0)
		return r;

	/*
	 * dm_sm_copy_root() can fail.  So we need to do it before we start
	 * updating the superblock.
	 */
	r = __save_sm_root(cmd);
	if (r)
		return r;

	r = superblock_lock_zero(cmd, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);
	disk_super->flags = 0;
	memset(disk_super->uuid, 0, sizeof(disk_super->uuid));
	disk_super->magic = cpu_to_le64(CACHE_SUPERBLOCK_MAGIC);
	disk_super->version = cpu_to_le32(cmd->version);
	memset(disk_super->policy_name, 0, sizeof(disk_super->policy_name));
	memset(disk_super->policy_version, 0, sizeof(disk_super->policy_version));
	disk_super->policy_hint_size = cpu_to_le32(0);

	__copy_sm_root(cmd, disk_super);

	disk_super->mapping_root = cpu_to_le64(cmd->root);
	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
	disk_super->discard_root = cpu_to_le64(cmd->discard_root);
	disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size);
	disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks));
	disk_super->metadata_block_size = cpu_to_le32(DM_CACHE_METADATA_BLOCK_SIZE);
	disk_super->data_block_size = cpu_to_le32(cmd->data_block_size);
	disk_super->cache_blocks = cpu_to_le32(0);

	disk_super->read_hits = cpu_to_le32(0);
	disk_super->read_misses = cpu_to_le32(0);
	disk_super->write_hits = cpu_to_le32(0);
	disk_super->write_misses = cpu_to_le32(0);

	if (separate_dirty_bits(cmd))
		disk_super->dirty_root = cpu_to_le64(cmd->dirty_root);

	return dm_tm_commit(cmd->tm, sblock);
}

static int __format_metadata(struct dm_cache_metadata *cmd)
{
	int r;

	r = dm_tm_create_with_sm(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
				 &cmd->tm, &cmd->metadata_sm);
	if (r < 0) {
		DMERR("tm_create_with_sm failed");
		return r;
	}

	__setup_mapping_info(cmd);

	r = dm_array_empty(&cmd->info, &cmd->root);
	if (r < 0)
		goto bad;

	if (separate_dirty_bits(cmd)) {
		dm_disk_bitset_init(cmd->tm, &cmd->dirty_info);
		r = dm_bitset_empty(&cmd->dirty_info, &cmd->dirty_root);
		if (r < 0)
			goto bad;
	}

	dm_disk_bitset_init(cmd->tm, &cmd->discard_info);
	r = dm_bitset_empty(&cmd->discard_info, &cmd->discard_root);
	if (r < 0)
		goto bad;

	cmd->discard_block_size = 0;
	cmd->discard_nr_blocks = 0;

	r = __write_initial_superblock(cmd);
	if (r)
		goto bad;

	cmd->clean_when_opened = true;
	return 0;

bad:
	dm_tm_destroy(cmd->tm);
	dm_sm_destroy(cmd->metadata_sm);

	return r;
}

static int __check_incompat_features(struct cache_disk_superblock *disk_super,
				     struct dm_cache_metadata *cmd)
{
	uint32_t incompat_flags, features;

	incompat_flags = le32_to_cpu(disk_super->incompat_flags);
	features = incompat_flags & ~DM_CACHE_FEATURE_INCOMPAT_SUPP;
	if (features) {
		DMERR("could not access metadata due to unsupported optional features (%lx).",
		      (unsigned long)features);
		return -EINVAL;
	}

	/*
	 * Check for read-only metadata to skip the following RDWR checks.
	 */
	if (bdev_read_only(cmd->bdev))
		return 0;

	features = le32_to_cpu(disk_super->compat_ro_flags) & ~DM_CACHE_FEATURE_COMPAT_RO_SUPP;
	if (features) {
		DMERR("could not access metadata RDWR due to unsupported optional features (%lx).",
		      (unsigned long)features);
		return -EINVAL;
	}

	return 0;
}

static int __open_metadata(struct dm_cache_metadata *cmd)
{
	int r;
	struct dm_block *sblock;
	struct cache_disk_superblock *disk_super;
	unsigned long sb_flags;

	r = superblock_read_lock(cmd, &sblock);
	if (r < 0) {
		DMERR("couldn't read lock superblock");
		return r;
	}

	disk_super = dm_block_data(sblock);

	/* Verify the data block size hasn't changed */
	if (le32_to_cpu(disk_super->data_block_size) != cmd->data_block_size) {
		DMERR("changing the data block size (from %u to %llu) is not supported",
		      le32_to_cpu(disk_super->data_block_size),
		      (unsigned long long)cmd->data_block_size);
		r = -EINVAL;
		goto bad;
	}

	r = __check_incompat_features(disk_super, cmd);
	if (r < 0)
		goto bad;

	r = dm_tm_open_with_sm(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
			       disk_super->metadata_space_map_root,
			       sizeof(disk_super->metadata_space_map_root),
			       &cmd->tm, &cmd->metadata_sm);
	if (r < 0) {
		DMERR("tm_open_with_sm failed");
		goto bad;
	}

	__setup_mapping_info(cmd);
	dm_disk_bitset_init(cmd->tm, &cmd->dirty_info);
	dm_disk_bitset_init(cmd->tm, &cmd->discard_info);
	sb_flags = le32_to_cpu(disk_super->flags);
	cmd->clean_when_opened = test_bit(CLEAN_SHUTDOWN, &sb_flags);
	dm_bm_unlock(sblock);

	return 0;

bad:
	dm_bm_unlock(sblock);
	return r;
}

static int __open_or_format_metadata(struct dm_cache_metadata *cmd,
				     bool format_device)
{
	int r;
	bool unformatted = false;

	r = __superblock_all_zeroes(cmd->bm, &unformatted);
	if (r)
		return r;

	if (unformatted)
		return format_device ? __format_metadata(cmd) : -EPERM;

	return __open_metadata(cmd);
}

static int __create_persistent_data_objects(struct dm_cache_metadata *cmd,
					    bool may_format_device)
{
	int r;

	cmd->bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
					  CACHE_MAX_CONCURRENT_LOCKS);
	if (IS_ERR(cmd->bm)) {
		DMERR("could not create block manager");
		r = PTR_ERR(cmd->bm);
		cmd->bm = NULL;
		return r;
	}

	r = __open_or_format_metadata(cmd, may_format_device);
	if (r) {
		dm_block_manager_destroy(cmd->bm);
		cmd->bm = NULL;
	}

	return r;
}

static void __destroy_persistent_data_objects(struct dm_cache_metadata *cmd,
					      bool destroy_bm)
{
	dm_sm_destroy(cmd->metadata_sm);
	dm_tm_destroy(cmd->tm);
	if (destroy_bm)
		dm_block_manager_destroy(cmd->bm);
}

typedef unsigned long (*flags_mutator)(unsigned long);

static void update_flags(struct cache_disk_superblock *disk_super,
			 flags_mutator mutator)
{
	uint32_t sb_flags = mutator(le32_to_cpu(disk_super->flags));

	disk_super->flags = cpu_to_le32(sb_flags);
}

static unsigned long set_clean_shutdown(unsigned long flags)
{
	set_bit(CLEAN_SHUTDOWN, &flags);
	return flags;
}

static unsigned long clear_clean_shutdown(unsigned long flags)
{
	clear_bit(CLEAN_SHUTDOWN, &flags);
	return flags;
}

static void read_superblock_fields(struct dm_cache_metadata *cmd,
				   struct cache_disk_superblock *disk_super)
{
	cmd->version = le32_to_cpu(disk_super->version);
	cmd->flags = le32_to_cpu(disk_super->flags);
	cmd->root = le64_to_cpu(disk_super->mapping_root);
	cmd->hint_root = le64_to_cpu(disk_super->hint_root);
	cmd->discard_root = le64_to_cpu(disk_super->discard_root);
	cmd->discard_block_size = le64_to_cpu(disk_super->discard_block_size);
	cmd->discard_nr_blocks = to_dblock(le64_to_cpu(disk_super->discard_nr_blocks));
	cmd->data_block_size = le32_to_cpu(disk_super->data_block_size);
	cmd->cache_blocks = to_cblock(le32_to_cpu(disk_super->cache_blocks));
	strncpy(cmd->policy_name, disk_super->policy_name, sizeof(cmd->policy_name));
	cmd->policy_version[0] = le32_to_cpu(disk_super->policy_version[0]);
	cmd->policy_version[1] = le32_to_cpu(disk_super->policy_version[1]);
	cmd->policy_version[2] = le32_to_cpu(disk_super->policy_version[2]);
	cmd->policy_hint_size = le32_to_cpu(disk_super->policy_hint_size);

	cmd->stats.read_hits = le32_to_cpu(disk_super->read_hits);
	cmd->stats.read_misses = le32_to_cpu(disk_super->read_misses);
	cmd->stats.write_hits = le32_to_cpu(disk_super->write_hits);
	cmd->stats.write_misses = le32_to_cpu(disk_super->write_misses);

	if (separate_dirty_bits(cmd))
		cmd->dirty_root = le64_to_cpu(disk_super->dirty_root);

	cmd->changed = false;
}

/*
 * The mutator updates the superblock flags.
 */
static int __begin_transaction_flags(struct dm_cache_metadata *cmd,
				     flags_mutator mutator)
{
	int r;
	struct cache_disk_superblock *disk_super;
	struct dm_block *sblock;

	r = superblock_lock(cmd, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);
	update_flags(disk_super, mutator);
	read_superblock_fields(cmd, disk_super);
	dm_bm_unlock(sblock);

	return dm_bm_flush(cmd->bm);
}

static int __begin_transaction(struct dm_cache_metadata *cmd)
{
	int r;
	struct cache_disk_superblock *disk_super;
	struct dm_block *sblock;

	/*
	 * We re-read the superblock every time.  Shouldn't need to do this
	 * really.
	 */
	r = superblock_read_lock(cmd, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);
	read_superblock_fields(cmd, disk_super);
	dm_bm_unlock(sblock);

	return 0;
}

static int __commit_transaction(struct dm_cache_metadata *cmd,
				flags_mutator mutator)
{
	int r;
	struct cache_disk_superblock *disk_super;
	struct dm_block *sblock;

	/*
	 * We need to know if the cache_disk_superblock exceeds a 512-byte sector.
	 */
	BUILD_BUG_ON(sizeof(struct cache_disk_superblock) > 512);

	if (separate_dirty_bits(cmd)) {
		r = dm_bitset_flush(&cmd->dirty_info, cmd->dirty_root,
				    &cmd->dirty_root);
		if (r)
			return r;
	}

	r = dm_bitset_flush(&cmd->discard_info, cmd->discard_root,
			    &cmd->discard_root);
	if (r)
		return r;

	r = dm_tm_pre_commit(cmd->tm);
	if (r < 0)
		return r;

	r = __save_sm_root(cmd);
	if (r)
		return r;

	r = superblock_lock(cmd, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);

	disk_super->flags = cpu_to_le32(cmd->flags);
	if (mutator)
		update_flags(disk_super, mutator);

	disk_super->mapping_root = cpu_to_le64(cmd->root);
	if (separate_dirty_bits(cmd))
		disk_super->dirty_root = cpu_to_le64(cmd->dirty_root);
	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
	disk_super->discard_root = cpu_to_le64(cmd->discard_root);
	disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size);
	disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks));
	disk_super->cache_blocks = cpu_to_le32(from_cblock(cmd->cache_blocks));
	strncpy(disk_super->policy_name, cmd->policy_name, sizeof(disk_super->policy_name));
	disk_super->policy_version[0] = cpu_to_le32(cmd->policy_version[0]);
	disk_super->policy_version[1] = cpu_to_le32(cmd->policy_version[1]);
	disk_super->policy_version[2] = cpu_to_le32(cmd->policy_version[2]);
	disk_super->policy_hint_size = cpu_to_le32(cmd->policy_hint_size);

	disk_super->read_hits = cpu_to_le32(cmd->stats.read_hits);
	disk_super->read_misses = cpu_to_le32(cmd->stats.read_misses);
	disk_super->write_hits = cpu_to_le32(cmd->stats.write_hits);
	disk_super->write_misses = cpu_to_le32(cmd->stats.write_misses);
	__copy_sm_root(cmd, disk_super);

	return dm_tm_commit(cmd->tm, sblock);
}

/*----------------------------------------------------------------*/

/*
 * The mappings are held in a dm-array that has 64-bit values stored in
 * little-endian format.  The index is the cblock, the high 48bits of the
 * value are the oblock and the low 16 bit the flags.
 */
#define FLAGS_MASK ((1 << 16) - 1)

static __le64 pack_value(dm_oblock_t block, unsigned int flags)
{
	uint64_t value = from_oblock(block);

	value <<= 16;
	value = value | (flags & FLAGS_MASK);
	return cpu_to_le64(value);
}

static void unpack_value(__le64 value_le, dm_oblock_t *block, unsigned int *flags)
{
	uint64_t value = le64_to_cpu(value_le);
	uint64_t b = value >> 16;

	*block = to_oblock(b);
	*flags = value & FLAGS_MASK;
}

/*----------------------------------------------------------------*/

static struct dm_cache_metadata *metadata_open(struct block_device *bdev,
					       sector_t data_block_size,
					       bool may_format_device,
					       size_t policy_hint_size,
					       unsigned int metadata_version)
{
	int r;
	struct dm_cache_metadata *cmd;

	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
	if (!cmd) {
		DMERR("could not allocate metadata struct");
		return ERR_PTR(-ENOMEM);
	}

	cmd->version = metadata_version;
	refcount_set(&cmd->ref_count, 1);
	init_rwsem(&cmd->root_lock);
	cmd->bdev = bdev;
	cmd->data_block_size = data_block_size;
	cmd->cache_blocks = 0;
	cmd->policy_hint_size = policy_hint_size;
	cmd->changed = true;
	cmd->fail_io = false;

	r = __create_persistent_data_objects(cmd, may_format_device);
	if (r) {
		kfree(cmd);
		return ERR_PTR(r);
	}

	r = __begin_transaction_flags(cmd, clear_clean_shutdown);
	if (r < 0) {
		dm_cache_metadata_close(cmd);
		return ERR_PTR(r);
	}

	return cmd;
}

/*
 * We keep a little list of ref counted metadata objects to prevent two
 * different target instances creating separate bufio instances.  This is
 * an issue if a table is reloaded before the suspend.
 */
static DEFINE_MUTEX(table_lock);
static LIST_HEAD(table);

static struct dm_cache_metadata *lookup(struct block_device *bdev)
{
	struct dm_cache_metadata *cmd;

	list_for_each_entry(cmd, &table, list)
		if (cmd->bdev == bdev) {
			refcount_inc(&cmd->ref_count);
			return cmd;
		}

	return NULL;
}

static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev,
						sector_t data_block_size,
						bool may_format_device,
						size_t policy_hint_size,
						unsigned int metadata_version)
{
	struct dm_cache_metadata *cmd, *cmd2;

	mutex_lock(&table_lock);
	cmd = lookup(bdev);
	mutex_unlock(&table_lock);

	if (cmd)
		return cmd;

	cmd = metadata_open(bdev, data_block_size, may_format_device,
			    policy_hint_size, metadata_version);
	if (!IS_ERR(cmd)) {
		mutex_lock(&table_lock);
		cmd2 = lookup(bdev);
		if (cmd2) {
			mutex_unlock(&table_lock);
			__destroy_persistent_data_objects(cmd, true);
			kfree(cmd);
			return cmd2;
		}
		list_add(&cmd->list, &table);
		mutex_unlock(&table_lock);
	}

	return cmd;
}

static bool same_params(struct dm_cache_metadata *cmd, sector_t data_block_size)
{
	if (cmd->data_block_size != data_block_size) {
		DMERR("data_block_size (%llu) different from that in metadata (%llu)",
		      (unsigned long long) data_block_size,
		      (unsigned long long) cmd->data_block_size);
		return false;
	}

	return true;
}

struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
						 sector_t data_block_size,
						 bool may_format_device,
						 size_t policy_hint_size,
						 unsigned int metadata_version)
{
	struct dm_cache_metadata *cmd = lookup_or_open(bdev, data_block_size, may_format_device,
						       policy_hint_size, metadata_version);

	if (!IS_ERR(cmd) && !same_params(cmd, data_block_size)) {
		dm_cache_metadata_close(cmd);
		return ERR_PTR(-EINVAL);
	}

	return cmd;
}

void dm_cache_metadata_close(struct dm_cache_metadata *cmd)
{
	if (refcount_dec_and_test(&cmd->ref_count)) {
		mutex_lock(&table_lock);
		list_del(&cmd->list);
		mutex_unlock(&table_lock);

		if (!cmd->fail_io)
			__destroy_persistent_data_objects(cmd, true);
		kfree(cmd);
	}
}

/*
 * Checks that the given cache block is either unmapped or clean.
 */
static int block_clean_combined_dirty(struct dm_cache_metadata *cmd, dm_cblock_t b,
				      bool *result)
{
	int r;
	__le64 value;
	dm_oblock_t ob;
	unsigned int flags;

	r = dm_array_get_value(&cmd->info, cmd->root, from_cblock(b), &value);
	if (r)
		return r;

	unpack_value(value, &ob, &flags);
	*result = !((flags & M_VALID) && (flags & M_DIRTY));

	return 0;
}

static int blocks_are_clean_combined_dirty(struct dm_cache_metadata *cmd,
					   dm_cblock_t begin, dm_cblock_t end,
					   bool *result)
{
	int r;
	*result = true;

	while (begin != end) {
		r = block_clean_combined_dirty(cmd, begin, result);
		if (r) {
			DMERR("block_clean_combined_dirty failed");
			return r;
		}

		if (!*result) {
			DMERR("cache block %llu is dirty",
			      (unsigned long long) from_cblock(begin));
			return 0;
		}

		begin = to_cblock(from_cblock(begin) + 1);
	}

	return 0;
}

static int blocks_are_clean_separate_dirty(struct dm_cache_metadata *cmd,
					   dm_cblock_t begin, dm_cblock_t end,
					   bool *result)
{
	int r;
	bool dirty_flag;
	*result = true;

	if (from_cblock(cmd->cache_blocks) == 0)
		/* Nothing to do */
		return 0;

	r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root,
				   from_cblock(cmd->cache_blocks), &cmd->dirty_cursor);
	if (r) {
		DMERR("%s: dm_bitset_cursor_begin for dirty failed", __func__);
		return r;
	}

	r = dm_bitset_cursor_skip(&cmd->dirty_cursor, from_cblock(begin));
	if (r) {
		DMERR("%s: dm_bitset_cursor_skip for dirty failed", __func__);
		dm_bitset_cursor_end(&cmd->dirty_cursor);
		return r;
	}

	while (begin != end) {
		/*
		 * We assume that unmapped blocks have their dirty bit
		 * cleared.
		 */
		dirty_flag = dm_bitset_cursor_get_value(&cmd->dirty_cursor);
		if (dirty_flag) {
			DMERR("%s: cache block %llu is dirty", __func__,
			      (unsigned long long) from_cblock(begin));
			dm_bitset_cursor_end(&cmd->dirty_cursor);
			*result = false;
			return 0;
		}

		begin = to_cblock(from_cblock(begin) + 1);
		if (begin == end)
			break;

		r = dm_bitset_cursor_next(&cmd->dirty_cursor);
		if (r) {
			DMERR("%s: dm_bitset_cursor_next for dirty failed", __func__);
			dm_bitset_cursor_end(&cmd->dirty_cursor);
			return r;
		}
	}

	dm_bitset_cursor_end(&cmd->dirty_cursor);

	return 0;
}

static int blocks_are_unmapped_or_clean(struct dm_cache_metadata *cmd,
					dm_cblock_t begin, dm_cblock_t end,
					bool *result)
{
	if (separate_dirty_bits(cmd))
		return blocks_are_clean_separate_dirty(cmd, begin, end, result);
	else
		return blocks_are_clean_combined_dirty(cmd, begin, end, result);
}

static bool cmd_write_lock(struct dm_cache_metadata *cmd)
{
	down_write(&cmd->root_lock);
	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) {
		up_write(&cmd->root_lock);
		return false;
	}
	return true;
}

#define WRITE_LOCK(cmd)				\
	do {					\
		if (!cmd_write_lock((cmd)))	\
			return -EINVAL;		\
	} while (0)

#define WRITE_LOCK_VOID(cmd)			\
	do {					\
		if (!cmd_write_lock((cmd)))	\
			return;			\
	} while (0)

#define WRITE_UNLOCK(cmd) \
	up_write(&(cmd)->root_lock)

static bool cmd_read_lock(struct dm_cache_metadata *cmd)
{
	down_read(&cmd->root_lock);
	if (cmd->fail_io) {
		up_read(&cmd->root_lock);
		return false;
	}
	return true;
}

#define READ_LOCK(cmd)				\
	do {					\
		if (!cmd_read_lock((cmd)))	\
			return -EINVAL;		\
	} while (0)

#define READ_LOCK_VOID(cmd)			\
	do {					\
		if (!cmd_read_lock((cmd)))	\
			return;			\
	} while (0)

#define READ_UNLOCK(cmd) \
	up_read(&(cmd)->root_lock)

int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size)
{
	int r;
	bool clean;
	__le64 null_mapping = pack_value(0, 0);

	WRITE_LOCK(cmd);
	__dm_bless_for_disk(&null_mapping);

	if (from_cblock(new_cache_size) < from_cblock(cmd->cache_blocks)) {
		r = blocks_are_unmapped_or_clean(cmd, new_cache_size, cmd->cache_blocks, &clean);
		if (r) {
			__dm_unbless_for_disk(&null_mapping);
			goto out;
		}

		if (!clean) {
			DMERR("unable to shrink cache due to dirty blocks");
			r = -EINVAL;
			__dm_unbless_for_disk(&null_mapping);
			goto out;
		}
	}

	r = dm_array_resize(&cmd->info, cmd->root, from_cblock(cmd->cache_blocks),
			    from_cblock(new_cache_size),
			    &null_mapping, &cmd->root);
	if (r)
		goto out;

	if (separate_dirty_bits(cmd)) {
		r = dm_bitset_resize(&cmd->dirty_info, cmd->dirty_root,
				     from_cblock(cmd->cache_blocks), from_cblock(new_cache_size),
				     false, &cmd->dirty_root);
		if (r)
			goto out;
	}

	cmd->cache_blocks = new_cache_size;
	cmd->changed = true;

out:
	WRITE_UNLOCK(cmd);

	return r;
}

int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
				   sector_t discard_block_size,
				   dm_dblock_t new_nr_entries)
{
	int r;

	WRITE_LOCK(cmd);
	r = dm_bitset_resize(&cmd->discard_info,
			     cmd->discard_root,
			     from_dblock(cmd->discard_nr_blocks),
			     from_dblock(new_nr_entries),
			     false, &cmd->discard_root);
	if (!r) {
		cmd->discard_block_size = discard_block_size;
		cmd->discard_nr_blocks = new_nr_entries;
	}

	cmd->changed = true;
	WRITE_UNLOCK(cmd);

	return r;
}

static int __set_discard(struct dm_cache_metadata *cmd, dm_dblock_t b)
{
	return dm_bitset_set_bit(&cmd->discard_info, cmd->discard_root,
				 from_dblock(b), &cmd->discard_root);
}

static int __clear_discard(struct dm_cache_metadata *cmd, dm_dblock_t b)
{
	return dm_bitset_clear_bit(&cmd->discard_info, cmd->discard_root,
				   from_dblock(b), &cmd->discard_root);
}

static int __discard(struct dm_cache_metadata *cmd,
		     dm_dblock_t dblock, bool discard)
{
	int r;

	r = (discard ? __set_discard : __clear_discard)(cmd, dblock);
	if (r)
		return r;

	cmd->changed = true;
	return 0;
}

int dm_cache_set_discard(struct dm_cache_metadata *cmd,
			 dm_dblock_t dblock, bool discard)
{
	int r;

	WRITE_LOCK(cmd);
	r = __discard(cmd, dblock, discard);
	WRITE_UNLOCK(cmd);

	return r;
}

static int __load_discards(struct dm_cache_metadata *cmd,
			   load_discard_fn fn, void *context)
{
	int r = 0;
	uint32_t b;
	struct dm_bitset_cursor c;

	if (from_dblock(cmd->discard_nr_blocks) == 0)
		/* nothing to do */
		return 0;

	if (cmd->clean_when_opened) {
		r = dm_bitset_flush(&cmd->discard_info, cmd->discard_root, &cmd->discard_root);
		if (r)
			return r;

		r = dm_bitset_cursor_begin(&cmd->discard_info, cmd->discard_root,
					   from_dblock(cmd->discard_nr_blocks), &c);
		if (r)
			return r;

		for (b = 0; ; b++) {
			r = fn(context, cmd->discard_block_size, to_dblock(b),
			       dm_bitset_cursor_get_value(&c));
			if (r)
				break;

			if (b >= (from_dblock(cmd->discard_nr_blocks) - 1))
				break;

			r = dm_bitset_cursor_next(&c);
			if (r)
				break;
		}

		dm_bitset_cursor_end(&c);

	} else {
		for (b = 0; b < from_dblock(cmd->discard_nr_blocks); b++) {
			r = fn(context, cmd->discard_block_size, to_dblock(b), false);
			if (r)
				return r;
		}
	}

	return r;
}

int dm_cache_load_discards(struct dm_cache_metadata *cmd,
			   load_discard_fn fn, void *context)
{
	int r;

	READ_LOCK(cmd);
	r = __load_discards(cmd, fn, context);
	READ_UNLOCK(cmd);

	return r;
}

int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result)
{
	READ_LOCK(cmd);
	*result = cmd->cache_blocks;
	READ_UNLOCK(cmd);

	return 0;
}

static int __remove(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
{
	int r;
	__le64 value = pack_value(0, 0);

	__dm_bless_for_disk(&value);
	r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock),
			       &value, &cmd->root);
	if (r)
		return r;

	cmd->changed = true;
	return 0;
}

int dm_cache_remove_mapping(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
{
	int r;

	WRITE_LOCK(cmd);
	r = __remove(cmd, cblock);
	WRITE_UNLOCK(cmd);

	return r;
}

static int __insert(struct dm_cache_metadata *cmd,
		    dm_cblock_t cblock, dm_oblock_t oblock)
{
	int r;
	__le64 value = pack_value(oblock, M_VALID);

	__dm_bless_for_disk(&value);

	r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock),
			       &value, &cmd->root);
	if (r)
		return r;

	cmd->changed = true;
	return 0;
}

int dm_cache_insert_mapping(struct dm_cache_metadata *cmd,
			    dm_cblock_t cblock, dm_oblock_t oblock)
{
	int r;

	WRITE_LOCK(cmd);
	r = __insert(cmd, cblock, oblock);
	WRITE_UNLOCK(cmd);

	return r;
}

struct thunk {
	load_mapping_fn fn;
	void *context;

	struct dm_cache_metadata *cmd;
	bool respect_dirty_flags;
	bool hints_valid;
};

static bool policy_unchanged(struct dm_cache_metadata *cmd,
			     struct dm_cache_policy *policy)
{
	const char *policy_name = dm_cache_policy_get_name(policy);
	const unsigned int *policy_version = dm_cache_policy_get_version(policy);
	size_t policy_hint_size = dm_cache_policy_get_hint_size(policy);

	/*
	 * Ensure policy names match.
	 */
	if (strncmp(cmd->policy_name, policy_name, sizeof(cmd->policy_name)))
		return false;

	/*
	 * Ensure policy major versions match.
	 */
	if (cmd->policy_version[0] != policy_version[0])
		return false;

	/*
	 * Ensure policy hint sizes match.
	 */
	if (cmd->policy_hint_size != policy_hint_size)
		return false;

	return true;
}

static bool hints_array_initialized(struct dm_cache_metadata *cmd)
{
	return cmd->hint_root && cmd->policy_hint_size;
}

static bool hints_array_available(struct dm_cache_metadata *cmd,
				  struct dm_cache_policy *policy)
{
	return cmd->clean_when_opened && policy_unchanged(cmd, policy) &&
		hints_array_initialized(cmd);
}

static int __load_mapping_v1(struct dm_cache_metadata *cmd,
			     uint64_t cb, bool hints_valid,
			     struct dm_array_cursor *mapping_cursor,
			     struct dm_array_cursor *hint_cursor,
			     load_mapping_fn fn, void *context)
{
	int r = 0;

	__le64 mapping;
	__le32 hint = 0;

	__le64 *mapping_value_le;
	__le32 *hint_value_le;

	dm_oblock_t oblock;
	unsigned int flags;
	bool dirty = true;

	dm_array_cursor_get_value(mapping_cursor, (void **) &mapping_value_le);
	memcpy(&mapping, mapping_value_le, sizeof(mapping));
	unpack_value(mapping, &oblock, &flags);

	if (flags & M_VALID) {
		if (hints_valid) {
			dm_array_cursor_get_value(hint_cursor, (void **) &hint_value_le);
			memcpy(&hint, hint_value_le, sizeof(hint));
		}
		if (cmd->clean_when_opened)
			dirty = flags & M_DIRTY;

		r = fn(context, oblock, to_cblock(cb), dirty,
		       le32_to_cpu(hint), hints_valid);
		if (r) {
			DMERR("policy couldn't load cache block %llu",
			      (unsigned long long) from_cblock(to_cblock(cb)));
		}
	}

	return r;
}

static int __load_mapping_v2(struct dm_cache_metadata *cmd,
			     uint64_t cb, bool hints_valid,
			     struct dm_array_cursor *mapping_cursor,
			     struct dm_array_cursor *hint_cursor,
			     struct dm_bitset_cursor *dirty_cursor,
			     load_mapping_fn fn, void *context)
{
	int r = 0;

	__le64 mapping;
	__le32 hint = 0;

	__le64 *mapping_value_le;
	__le32 *hint_value_le;

	dm_oblock_t oblock;
	unsigned int flags;
	bool dirty = true;

	dm_array_cursor_get_value(mapping_cursor, (void **) &mapping_value_le);
	memcpy(&mapping, mapping_value_le, sizeof(mapping));
	unpack_value(mapping, &oblock, &flags);

	if (flags & M_VALID) {
		if (hints_valid) {
			dm_array_cursor_get_value(hint_cursor, (void **) &hint_value_le);
			memcpy(&hint, hint_value_le, sizeof(hint));
		}
		if (cmd->clean_when_opened)
			dirty = dm_bitset_cursor_get_value(dirty_cursor);

		r = fn(context, oblock, to_cblock(cb), dirty,
		       le32_to_cpu(hint), hints_valid);
		if (r) {
			DMERR("policy couldn't load cache block %llu",
			      (unsigned long long) from_cblock(to_cblock(cb)));
		}
	}

	return r;
}

static int __load_mappings(struct dm_cache_metadata *cmd,
			   struct dm_cache_policy *policy,
			   load_mapping_fn fn, void *context)
{
	int r;
	uint64_t cb;

	bool hints_valid = hints_array_available(cmd, policy);

	if (from_cblock(cmd->cache_blocks) == 0)
		/* Nothing to do */
		return 0;

	r = dm_array_cursor_begin(&cmd->info, cmd->root, &cmd->mapping_cursor);
	if (r)
		return r;

	if (hints_valid) {
		r = dm_array_cursor_begin(&cmd->hint_info, cmd->hint_root, &cmd->hint_cursor);
		if (r) {
			dm_array_cursor_end(&cmd->mapping_cursor);
			return r;
		}
	}

	if (separate_dirty_bits(cmd)) {
		r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root,
					   from_cblock(cmd->cache_blocks),
					   &cmd->dirty_cursor);
		if (r) {
			dm_array_cursor_end(&cmd->hint_cursor);
			dm_array_cursor_end(&cmd->mapping_cursor);
			return r;
		}
	}

	for (cb = 0; ; cb++) {
		if (separate_dirty_bits(cmd))
			r = __load_mapping_v2(cmd, cb, hints_valid,
					      &cmd->mapping_cursor,
					      &cmd->hint_cursor,
					      &cmd->dirty_cursor,
					      fn, context);
		else
			r = __load_mapping_v1(cmd, cb, hints_valid,
					      &cmd->mapping_cursor, &cmd->hint_cursor,
					      fn, context);
		if (r)
			goto out;

		/*
		 * We need to break out before we move the cursors.
		 */
		if (cb >= (from_cblock(cmd->cache_blocks) - 1))
			break;

		r = dm_array_cursor_next(&cmd->mapping_cursor);
		if (r) {
			DMERR("dm_array_cursor_next for mapping failed");
			goto out;
		}

		if (hints_valid) {
			r = dm_array_cursor_next(&cmd->hint_cursor);
			if (r) {
				dm_array_cursor_end(&cmd->hint_cursor);
				hints_valid = false;
			}
		}

		if (separate_dirty_bits(cmd)) {
			r = dm_bitset_cursor_next(&cmd->dirty_cursor);
			if (r) {
				DMERR("dm_bitset_cursor_next for dirty failed");
				goto out;
			}
		}
	}
out:
	dm_array_cursor_end(&cmd->mapping_cursor);
	if (hints_valid)
		dm_array_cursor_end(&cmd->hint_cursor);

	if (separate_dirty_bits(cmd))
		dm_bitset_cursor_end(&cmd->dirty_cursor);

	return r;
}

int dm_cache_load_mappings(struct dm_cache_metadata *cmd,
			   struct dm_cache_policy *policy,
			   load_mapping_fn fn, void *context)
{
	int r;

	READ_LOCK(cmd);
	r = __load_mappings(cmd, policy, fn, context);
	READ_UNLOCK(cmd);

	return r;
}

static int __dump_mapping(void *context, uint64_t cblock, void *leaf)
{
	__le64 value;
	dm_oblock_t oblock;
	unsigned int flags;

	memcpy(&value, leaf, sizeof(value));
	unpack_value(value, &oblock, &flags);

	return 0;
}

static int __dump_mappings(struct dm_cache_metadata *cmd)
{
	return dm_array_walk(&cmd->info, cmd->root, __dump_mapping, NULL);
}

void dm_cache_dump(struct dm_cache_metadata *cmd)
{
	READ_LOCK_VOID(cmd);
	__dump_mappings(cmd);
	READ_UNLOCK(cmd);
}

int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd)
{
	int r;

	READ_LOCK(cmd);
	r = cmd->changed;
	READ_UNLOCK(cmd);

	return r;
}

static int __dirty(struct dm_cache_metadata *cmd, dm_cblock_t cblock, bool dirty)
{
	int r;
	unsigned int flags;
	dm_oblock_t oblock;
	__le64 value;

	r = dm_array_get_value(&cmd->info, cmd->root, from_cblock(cblock), &value);
	if (r)
		return r;

	unpack_value(value, &oblock, &flags);

	if (((flags & M_DIRTY) && dirty) || (!(flags & M_DIRTY) && !dirty))
		/* nothing to be done */
		return 0;

	value = pack_value(oblock, (flags & ~M_DIRTY) | (dirty ? M_DIRTY : 0));
	__dm_bless_for_disk(&value);

	r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock),
			       &value, &cmd->root);
	if (r)
		return r;

	cmd->changed = true;
	return 0;

}

static int __set_dirty_bits_v1(struct dm_cache_metadata *cmd, unsigned int nr_bits, unsigned long *bits)
{
	int r;
	unsigned int i;

	for (i = 0; i < nr_bits; i++) {
		r = __dirty(cmd, to_cblock(i), test_bit(i, bits));
		if (r)
			return r;
	}

	return 0;
}

static int is_dirty_callback(uint32_t index, bool *value, void *context)
{
	unsigned long *bits = context;
	*value = test_bit(index, bits);
	return 0;
}

static int __set_dirty_bits_v2(struct dm_cache_metadata *cmd, unsigned int nr_bits, unsigned long *bits)
{
	int r = 0;

	/* nr_bits is really just a sanity check */
	if (nr_bits != from_cblock(cmd->cache_blocks)) {
		DMERR("dirty bitset is wrong size");
		return -EINVAL;
	}

	r = dm_bitset_del(&cmd->dirty_info, cmd->dirty_root);
	if (r)
		return r;

	cmd->changed = true;
	return dm_bitset_new(&cmd->dirty_info, &cmd->dirty_root, nr_bits, is_dirty_callback, bits);
}

int dm_cache_set_dirty_bits(struct dm_cache_metadata *cmd,
			    unsigned int nr_bits,
			    unsigned long *bits)
{
	int r;

	WRITE_LOCK(cmd);
	if (separate_dirty_bits(cmd))
		r = __set_dirty_bits_v2(cmd, nr_bits, bits);
	else
		r = __set_dirty_bits_v1(cmd, nr_bits, bits);
	WRITE_UNLOCK(cmd);

	return r;
}

void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd,
				 struct dm_cache_statistics *stats)
{
	READ_LOCK_VOID(cmd);
	*stats = cmd->stats;
	READ_UNLOCK(cmd);
}

void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd,
				 struct dm_cache_statistics *stats)
{
	WRITE_LOCK_VOID(cmd);
	cmd->stats = *stats;
	WRITE_UNLOCK(cmd);
}

int dm_cache_commit(struct dm_cache_metadata *cmd, bool clean_shutdown)
{
	int r = -EINVAL;
	flags_mutator mutator = (clean_shutdown ? set_clean_shutdown :
				 clear_clean_shutdown);

	WRITE_LOCK(cmd);
	if (cmd->fail_io)
		goto out;

	r = __commit_transaction(cmd, mutator);
	if (r)
		goto out;

	r = __begin_transaction(cmd);
out:
	WRITE_UNLOCK(cmd);
	return r;
}

int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd,
					   dm_block_t *result)
{
	int r = -EINVAL;

	READ_LOCK(cmd);
	if (!cmd->fail_io)
		r = dm_sm_get_nr_free(cmd->metadata_sm, result);
	READ_UNLOCK(cmd);

	return r;
}

int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd,
				   dm_block_t *result)
{
	int r = -EINVAL;

	READ_LOCK(cmd);
	if (!cmd->fail_io)
		r = dm_sm_get_nr_blocks(cmd->metadata_sm, result);
	READ_UNLOCK(cmd);

	return r;
}

/*----------------------------------------------------------------*/

static int get_hint(uint32_t index, void *value_le, void *context)
{
	uint32_t value;
	struct dm_cache_policy *policy = context;

	value = policy_get_hint(policy, to_cblock(index));
	*((__le32 *) value_le) = cpu_to_le32(value);

	return 0;
}

/*
 * It's quicker to always delete the hint array, and recreate with
 * dm_array_new().
 */
static int write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
{
	int r;
	size_t hint_size;
	const char *policy_name = dm_cache_policy_get_name(policy);
	const unsigned int *policy_version = dm_cache_policy_get_version(policy);

	if (!policy_name[0] ||
	    (strlen(policy_name) > sizeof(cmd->policy_name) - 1))
		return -EINVAL;

	strncpy(cmd->policy_name, policy_name, sizeof(cmd->policy_name));
	memcpy(cmd->policy_version, policy_version, sizeof(cmd->policy_version));

	hint_size = dm_cache_policy_get_hint_size(policy);
	if (!hint_size)
		return 0; /* short-circuit hints initialization */
	cmd->policy_hint_size = hint_size;

	if (cmd->hint_root) {
		r = dm_array_del(&cmd->hint_info, cmd->hint_root);
		if (r)
			return r;
	}

	return dm_array_new(&cmd->hint_info, &cmd->hint_root,
			    from_cblock(cmd->cache_blocks),
			    get_hint, policy);
}

int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
{
	int r;

	WRITE_LOCK(cmd);
	r = write_hints(cmd, policy);
	WRITE_UNLOCK(cmd);

	return r;
}

int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result)
{
	int r;

	READ_LOCK(cmd);
	r = blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result);
	READ_UNLOCK(cmd);

	return r;
}

void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd)
{
	WRITE_LOCK_VOID(cmd);
	dm_bm_set_read_only(cmd->bm);
	WRITE_UNLOCK(cmd);
}

void dm_cache_metadata_set_read_write(struct dm_cache_metadata *cmd)
{
	WRITE_LOCK_VOID(cmd);
	dm_bm_set_read_write(cmd->bm);
	WRITE_UNLOCK(cmd);
}

int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd)
{
	int r;
	struct dm_block *sblock;
	struct cache_disk_superblock *disk_super;

	WRITE_LOCK(cmd);
	set_bit(NEEDS_CHECK, &cmd->flags);

	r = superblock_lock(cmd, &sblock);
	if (r) {
		DMERR("couldn't read superblock");
		goto out;
	}

	disk_super = dm_block_data(sblock);
	disk_super->flags = cpu_to_le32(cmd->flags);

	dm_bm_unlock(sblock);

out:
	WRITE_UNLOCK(cmd);
	return r;
}

int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result)
{
	READ_LOCK(cmd);
	*result = !!test_bit(NEEDS_CHECK, &cmd->flags);
	READ_UNLOCK(cmd);

	return 0;
}

int dm_cache_metadata_abort(struct dm_cache_metadata *cmd)
{
	int r = -EINVAL;
	struct dm_block_manager *old_bm = NULL, *new_bm = NULL;

	/* fail_io is double-checked with cmd->root_lock held below */
	if (unlikely(cmd->fail_io))
		return r;

	/*
	 * Replacement block manager (new_bm) is created and old_bm destroyed outside of
	 * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of
	 * shrinker associated with the block manager's bufio client vs cmd root_lock).
	 * - must take shrinker_mutex without holding cmd->root_lock
	 */
	new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
					 CACHE_MAX_CONCURRENT_LOCKS);

	WRITE_LOCK(cmd);
	if (cmd->fail_io) {
		WRITE_UNLOCK(cmd);
		goto out;
	}

	__destroy_persistent_data_objects(cmd, false);
	old_bm = cmd->bm;
	if (IS_ERR(new_bm)) {
		DMERR("could not create block manager during abort");
		cmd->bm = NULL;
		r = PTR_ERR(new_bm);
		goto out_unlock;
	}

	cmd->bm = new_bm;
	r = __open_or_format_metadata(cmd, false);
	if (r) {
		cmd->bm = NULL;
		goto out_unlock;
	}
	new_bm = NULL;
out_unlock:
	if (r)
		cmd->fail_io = true;
	WRITE_UNLOCK(cmd);
	dm_block_manager_destroy(old_bm);
out:
	if (new_bm && !IS_ERR(new_bm))
		dm_block_manager_destroy(new_bm);

	return r;
}