summaryrefslogtreecommitdiff
path: root/drivers/md/dm-thin-metadata.c
blob: 1a96a07cbf443ace91cd877abb3c26232504cef9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
/*
 * Copyright (C) 2011-2012 Red Hat, Inc.
 *
 * This file is released under the GPL.
 */

#include "dm-thin-metadata.h"
#include "persistent-data/dm-btree.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/list.h>
#include <linux/device-mapper.h>
#include <linux/workqueue.h>

/*--------------------------------------------------------------------------
 * As far as the metadata goes, there is:
 *
 * - A superblock in block zero, taking up fewer than 512 bytes for
 *   atomic writes.
 *
 * - A space map managing the metadata blocks.
 *
 * - A space map managing the data blocks.
 *
 * - A btree mapping our internal thin dev ids onto struct disk_device_details.
 *
 * - A hierarchical btree, with 2 levels which effectively maps (thin
 *   dev id, virtual block) -> block_time.  Block time is a 64-bit
 *   field holding the time in the low 24 bits, and block in the top 40
 *   bits.
 *
 * BTrees consist solely of btree_nodes, that fill a block.  Some are
 * internal nodes, as such their values are a __le64 pointing to other
 * nodes.  Leaf nodes can store data of any reasonable size (ie. much
 * smaller than the block size).  The nodes consist of the header,
 * followed by an array of keys, followed by an array of values.  We have
 * to binary search on the keys so they're all held together to help the
 * cpu cache.
 *
 * Space maps have 2 btrees:
 *
 * - One maps a uint64_t onto a struct index_entry.  Which points to a
 *   bitmap block, and has some details about how many free entries there
 *   are etc.
 *
 * - The bitmap blocks have a header (for the checksum).  Then the rest
 *   of the block is pairs of bits.  With the meaning being:
 *
 *   0 - ref count is 0
 *   1 - ref count is 1
 *   2 - ref count is 2
 *   3 - ref count is higher than 2
 *
 * - If the count is higher than 2 then the ref count is entered in a
 *   second btree that directly maps the block_address to a uint32_t ref
 *   count.
 *
 * The space map metadata variant doesn't have a bitmaps btree.  Instead
 * it has one single blocks worth of index_entries.  This avoids
 * recursive issues with the bitmap btree needing to allocate space in
 * order to insert.  With a small data block size such as 64k the
 * metadata support data devices that are hundreds of terrabytes.
 *
 * The space maps allocate space linearly from front to back.  Space that
 * is freed in a transaction is never recycled within that transaction.
 * To try and avoid fragmenting _free_ space the allocator always goes
 * back and fills in gaps.
 *
 * All metadata io is in THIN_METADATA_BLOCK_SIZE sized/aligned chunks
 * from the block manager.
 *--------------------------------------------------------------------------*/

#define DM_MSG_PREFIX   "thin metadata"

#define THIN_SUPERBLOCK_MAGIC 27022010
#define THIN_SUPERBLOCK_LOCATION 0
#define THIN_VERSION 2
#define SECTOR_TO_BLOCK_SHIFT 3

/*
 * For btree insert:
 *  3 for btree insert +
 *  2 for btree lookup used within space map
 * For btree remove:
 *  2 for shadow spine +
 *  4 for rebalance 3 child node
 */
#define THIN_MAX_CONCURRENT_LOCKS 6

/* This should be plenty */
#define SPACE_MAP_ROOT_SIZE 128

/*
 * Little endian on-disk superblock and device details.
 */
struct thin_disk_superblock {
	__le32 csum;	/* Checksum of superblock except for this field. */
	__le32 flags;
	__le64 blocknr;	/* This block number, dm_block_t. */

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

	__le64 trans_id;

	/*
	 * Root held by userspace transactions.
	 */
	__le64 held_root;

	__u8 data_space_map_root[SPACE_MAP_ROOT_SIZE];
	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];

	/*
	 * 2-level btree mapping (dev_id, (dev block, time)) -> data block
	 */
	__le64 data_mapping_root;

	/*
	 * Device detail root mapping dev_id -> device_details
	 */
	__le64 device_details_root;

	__le32 data_block_size;		/* In 512-byte sectors. */

	__le32 metadata_block_size;	/* In 512-byte sectors. */
	__le64 metadata_nr_blocks;

	__le32 compat_flags;
	__le32 compat_ro_flags;
	__le32 incompat_flags;
} __packed;

struct disk_device_details {
	__le64 mapped_blocks;
	__le64 transaction_id;		/* When created. */
	__le32 creation_time;
	__le32 snapshotted_time;
} __packed;

struct dm_pool_metadata {
	struct hlist_node hash;

	struct block_device *bdev;
	struct dm_block_manager *bm;
	struct dm_space_map *metadata_sm;
	struct dm_space_map *data_sm;
	struct dm_transaction_manager *tm;
	struct dm_transaction_manager *nb_tm;

	/*
	 * Two-level btree.
	 * First level holds thin_dev_t.
	 * Second level holds mappings.
	 */
	struct dm_btree_info info;

	/*
	 * Non-blocking version of the above.
	 */
	struct dm_btree_info nb_info;

	/*
	 * Just the top level for deleting whole devices.
	 */
	struct dm_btree_info tl_info;

	/*
	 * Just the bottom level for creating new devices.
	 */
	struct dm_btree_info bl_info;

	/*
	 * Describes the device details btree.
	 */
	struct dm_btree_info details_info;

	struct rw_semaphore root_lock;
	uint32_t time;
	dm_block_t root;
	dm_block_t details_root;
	struct list_head thin_devices;
	uint64_t trans_id;
	unsigned long flags;
	sector_t data_block_size;

	/*
	 * Pre-commit callback.
	 *
	 * This allows the thin provisioning target to run a callback before
	 * the metadata are committed.
	 */
	dm_pool_pre_commit_fn pre_commit_fn;
	void *pre_commit_context;

	/*
	 * We reserve a section of the metadata for commit overhead.
	 * All reported space does *not* include this.
	 */
	dm_block_t metadata_reserve;

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

	/*
	 * Set once a thin-pool has been accessed through one of the interfaces
	 * that imply the pool is in-service (e.g. thin devices created/deleted,
	 * thin-pool message, metadata snapshots, etc).
	 */
	bool in_service:1;

	/*
	 * Reading the space map roots can fail, so we read it into these
	 * buffers before the superblock is locked and updated.
	 */
	__u8 data_space_map_root[SPACE_MAP_ROOT_SIZE];
	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
};

struct dm_thin_device {
	struct list_head list;
	struct dm_pool_metadata *pmd;
	dm_thin_id id;

	int open_count;
	bool changed:1;
	bool aborted_with_changes:1;
	uint64_t mapped_blocks;
	uint64_t transaction_id;
	uint32_t creation_time;
	uint32_t snapshotted_time;
};

/*----------------------------------------------------------------
 * superblock validator
 *--------------------------------------------------------------*/

#define SUPERBLOCK_CSUM_XOR 160774

static void sb_prepare_for_write(struct dm_block_validator *v,
				 struct dm_block *b,
				 size_t block_size)
{
	struct thin_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,
						      block_size - sizeof(__le32),
						      SUPERBLOCK_CSUM_XOR));
}

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

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

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

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

	return 0;
}

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

/*----------------------------------------------------------------
 * Methods for the btree value types
 *--------------------------------------------------------------*/

static uint64_t pack_block_time(dm_block_t b, uint32_t t)
{
	return (b << 24) | t;
}

static void unpack_block_time(uint64_t v, dm_block_t *b, uint32_t *t)
{
	*b = v >> 24;
	*t = v & ((1 << 24) - 1);
}

/*
 * It's more efficient to call dm_sm_{inc,dec}_blocks as few times as
 * possible.  'with_runs' reads contiguous runs of blocks, and calls the
 * given sm function.
 */
typedef int (*run_fn)(struct dm_space_map *, dm_block_t, dm_block_t);

static void with_runs(struct dm_space_map *sm, const __le64 *value_le, unsigned count, run_fn fn)
{
	uint64_t b, begin, end;
	uint32_t t;
	bool in_run = false;
	unsigned i;

	for (i = 0; i < count; i++, value_le++) {
		/* We know value_le is 8 byte aligned */
		unpack_block_time(le64_to_cpu(*value_le), &b, &t);

		if (in_run) {
			if (b == end) {
				end++;
			} else {
				fn(sm, begin, end);
				begin = b;
				end = b + 1;
			}
		} else {
			in_run = true;
			begin = b;
			end = b + 1;
		}
	}

	if (in_run)
		fn(sm, begin, end);
}

static void data_block_inc(void *context, const void *value_le, unsigned count)
{
	with_runs((struct dm_space_map *) context,
		  (const __le64 *) value_le, count, dm_sm_inc_blocks);
}

static void data_block_dec(void *context, const void *value_le, unsigned count)
{
	with_runs((struct dm_space_map *) context,
		  (const __le64 *) value_le, count, dm_sm_dec_blocks);
}

static int data_block_equal(void *context, const void *value1_le, const void *value2_le)
{
	__le64 v1_le, v2_le;
	uint64_t b1, b2;
	uint32_t t;

	memcpy(&v1_le, value1_le, sizeof(v1_le));
	memcpy(&v2_le, value2_le, sizeof(v2_le));
	unpack_block_time(le64_to_cpu(v1_le), &b1, &t);
	unpack_block_time(le64_to_cpu(v2_le), &b2, &t);

	return b1 == b2;
}

static void subtree_inc(void *context, const void *value, unsigned count)
{
	struct dm_btree_info *info = context;
	const __le64 *root_le = value;
	unsigned i;

	for (i = 0; i < count; i++, root_le++)
		dm_tm_inc(info->tm, le64_to_cpu(*root_le));
}

static void subtree_dec(void *context, const void *value, unsigned count)
{
	struct dm_btree_info *info = context;
	const __le64 *root_le = value;
	unsigned i;

	for (i = 0; i < count; i++, root_le++)
		if (dm_btree_del(info, le64_to_cpu(*root_le)))
			DMERR("btree delete failed");
}

static int subtree_equal(void *context, const void *value1_le, const void *value2_le)
{
	__le64 v1_le, v2_le;
	memcpy(&v1_le, value1_le, sizeof(v1_le));
	memcpy(&v2_le, value2_le, sizeof(v2_le));

	return v1_le == v2_le;
}

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

/*
 * Variant that is used for in-core only changes or code that
 * shouldn't put the pool in service on its own (e.g. commit).
 */
static inline void pmd_write_lock_in_core(struct dm_pool_metadata *pmd)
	__acquires(pmd->root_lock)
{
	down_write(&pmd->root_lock);
}

static inline void pmd_write_lock(struct dm_pool_metadata *pmd)
{
	pmd_write_lock_in_core(pmd);
	if (unlikely(!pmd->in_service))
		pmd->in_service = true;
}

static inline void pmd_write_unlock(struct dm_pool_metadata *pmd)
	__releases(pmd->root_lock)
{
	up_write(&pmd->root_lock);
}

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

static int superblock_lock_zero(struct dm_pool_metadata *pmd,
				struct dm_block **sblock)
{
	return dm_bm_write_lock_zero(pmd->bm, THIN_SUPERBLOCK_LOCATION,
				     &sb_validator, sblock);
}

static int superblock_lock(struct dm_pool_metadata *pmd,
			   struct dm_block **sblock)
{
	return dm_bm_write_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION,
				&sb_validator, sblock);
}

static int __superblock_all_zeroes(struct dm_block_manager *bm, int *result)
{
	int r;
	unsigned i;
	struct dm_block *b;
	__le64 *data_le, zero = cpu_to_le64(0);
	unsigned 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, THIN_SUPERBLOCK_LOCATION, NULL, &b);
	if (r)
		return r;

	data_le = dm_block_data(b);
	*result = 1;
	for (i = 0; i < block_size; i++) {
		if (data_le[i] != zero) {
			*result = 0;
			break;
		}
	}

	dm_bm_unlock(b);

	return 0;
}

static void __setup_btree_details(struct dm_pool_metadata *pmd)
{
	pmd->info.tm = pmd->tm;
	pmd->info.levels = 2;
	pmd->info.value_type.context = pmd->data_sm;
	pmd->info.value_type.size = sizeof(__le64);
	pmd->info.value_type.inc = data_block_inc;
	pmd->info.value_type.dec = data_block_dec;
	pmd->info.value_type.equal = data_block_equal;

	memcpy(&pmd->nb_info, &pmd->info, sizeof(pmd->nb_info));
	pmd->nb_info.tm = pmd->nb_tm;

	pmd->tl_info.tm = pmd->tm;
	pmd->tl_info.levels = 1;
	pmd->tl_info.value_type.context = &pmd->bl_info;
	pmd->tl_info.value_type.size = sizeof(__le64);
	pmd->tl_info.value_type.inc = subtree_inc;
	pmd->tl_info.value_type.dec = subtree_dec;
	pmd->tl_info.value_type.equal = subtree_equal;

	pmd->bl_info.tm = pmd->tm;
	pmd->bl_info.levels = 1;
	pmd->bl_info.value_type.context = pmd->data_sm;
	pmd->bl_info.value_type.size = sizeof(__le64);
	pmd->bl_info.value_type.inc = data_block_inc;
	pmd->bl_info.value_type.dec = data_block_dec;
	pmd->bl_info.value_type.equal = data_block_equal;

	pmd->details_info.tm = pmd->tm;
	pmd->details_info.levels = 1;
	pmd->details_info.value_type.context = NULL;
	pmd->details_info.value_type.size = sizeof(struct disk_device_details);
	pmd->details_info.value_type.inc = NULL;
	pmd->details_info.value_type.dec = NULL;
	pmd->details_info.value_type.equal = NULL;
}

static int save_sm_roots(struct dm_pool_metadata *pmd)
{
	int r;
	size_t len;

	r = dm_sm_root_size(pmd->metadata_sm, &len);
	if (r < 0)
		return r;

	r = dm_sm_copy_root(pmd->metadata_sm, &pmd->metadata_space_map_root, len);
	if (r < 0)
		return r;

	r = dm_sm_root_size(pmd->data_sm, &len);
	if (r < 0)
		return r;

	return dm_sm_copy_root(pmd->data_sm, &pmd->data_space_map_root, len);
}

static void copy_sm_roots(struct dm_pool_metadata *pmd,
			  struct thin_disk_superblock *disk)
{
	memcpy(&disk->metadata_space_map_root,
	       &pmd->metadata_space_map_root,
	       sizeof(pmd->metadata_space_map_root));

	memcpy(&disk->data_space_map_root,
	       &pmd->data_space_map_root,
	       sizeof(pmd->data_space_map_root));
}

static int __write_initial_superblock(struct dm_pool_metadata *pmd)
{
	int r;
	struct dm_block *sblock;
	struct thin_disk_superblock *disk_super;
	sector_t bdev_size = bdev_nr_sectors(pmd->bdev);

	if (bdev_size > THIN_METADATA_MAX_SECTORS)
		bdev_size = THIN_METADATA_MAX_SECTORS;

	r = dm_sm_commit(pmd->data_sm);
	if (r < 0)
		return r;

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

	r = save_sm_roots(pmd);
	if (r < 0)
		return r;

	r = superblock_lock_zero(pmd, &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(THIN_SUPERBLOCK_MAGIC);
	disk_super->version = cpu_to_le32(THIN_VERSION);
	disk_super->time = 0;
	disk_super->trans_id = 0;
	disk_super->held_root = 0;

	copy_sm_roots(pmd, disk_super);

	disk_super->data_mapping_root = cpu_to_le64(pmd->root);
	disk_super->device_details_root = cpu_to_le64(pmd->details_root);
	disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE);
	disk_super->metadata_nr_blocks = cpu_to_le64(bdev_size >> SECTOR_TO_BLOCK_SHIFT);
	disk_super->data_block_size = cpu_to_le32(pmd->data_block_size);

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

static int __format_metadata(struct dm_pool_metadata *pmd)
{
	int r;

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

	pmd->data_sm = dm_sm_disk_create(pmd->tm, 0);
	if (IS_ERR(pmd->data_sm)) {
		DMERR("sm_disk_create failed");
		r = PTR_ERR(pmd->data_sm);
		goto bad_cleanup_tm;
	}

	pmd->nb_tm = dm_tm_create_non_blocking_clone(pmd->tm);
	if (!pmd->nb_tm) {
		DMERR("could not create non-blocking clone tm");
		r = -ENOMEM;
		goto bad_cleanup_data_sm;
	}

	__setup_btree_details(pmd);

	r = dm_btree_empty(&pmd->info, &pmd->root);
	if (r < 0)
		goto bad_cleanup_nb_tm;

	r = dm_btree_empty(&pmd->details_info, &pmd->details_root);
	if (r < 0) {
		DMERR("couldn't create devices root");
		goto bad_cleanup_nb_tm;
	}

	r = __write_initial_superblock(pmd);
	if (r)
		goto bad_cleanup_nb_tm;

	return 0;

bad_cleanup_nb_tm:
	dm_tm_destroy(pmd->nb_tm);
bad_cleanup_data_sm:
	dm_sm_destroy(pmd->data_sm);
bad_cleanup_tm:
	dm_tm_destroy(pmd->tm);
	dm_sm_destroy(pmd->metadata_sm);

	return r;
}

static int __check_incompat_features(struct thin_disk_superblock *disk_super,
				     struct dm_pool_metadata *pmd)
{
	uint32_t features;

	features = le32_to_cpu(disk_super->incompat_flags) & ~THIN_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(pmd->bdev))
		return 0;

	features = le32_to_cpu(disk_super->compat_ro_flags) & ~THIN_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_pool_metadata *pmd)
{
	int r;
	struct dm_block *sblock;
	struct thin_disk_superblock *disk_super;

	r = dm_bm_read_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION,
			    &sb_validator, &sblock);
	if (r < 0) {
		DMERR("couldn't read 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) != pmd->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)pmd->data_block_size);
		r = -EINVAL;
		goto bad_unlock_sblock;
	}

	r = __check_incompat_features(disk_super, pmd);
	if (r < 0)
		goto bad_unlock_sblock;

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

	pmd->data_sm = dm_sm_disk_open(pmd->tm, disk_super->data_space_map_root,
				       sizeof(disk_super->data_space_map_root));
	if (IS_ERR(pmd->data_sm)) {
		DMERR("sm_disk_open failed");
		r = PTR_ERR(pmd->data_sm);
		goto bad_cleanup_tm;
	}

	pmd->nb_tm = dm_tm_create_non_blocking_clone(pmd->tm);
	if (!pmd->nb_tm) {
		DMERR("could not create non-blocking clone tm");
		r = -ENOMEM;
		goto bad_cleanup_data_sm;
	}

	__setup_btree_details(pmd);
	dm_bm_unlock(sblock);

	return 0;

bad_cleanup_data_sm:
	dm_sm_destroy(pmd->data_sm);
bad_cleanup_tm:
	dm_tm_destroy(pmd->tm);
	dm_sm_destroy(pmd->metadata_sm);
bad_unlock_sblock:
	dm_bm_unlock(sblock);

	return r;
}

static int __open_or_format_metadata(struct dm_pool_metadata *pmd, bool format_device)
{
	int r, unformatted;

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

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

	return __open_metadata(pmd);
}

static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool format_device)
{
	int r;

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

	r = __open_or_format_metadata(pmd, format_device);
	if (r) {
		dm_block_manager_destroy(pmd->bm);
		pmd->bm = NULL;
	}

	return r;
}

static void __destroy_persistent_data_objects(struct dm_pool_metadata *pmd)
{
	dm_sm_destroy(pmd->data_sm);
	dm_sm_destroy(pmd->metadata_sm);
	dm_tm_destroy(pmd->nb_tm);
	dm_tm_destroy(pmd->tm);
	dm_block_manager_destroy(pmd->bm);
}

static int __begin_transaction(struct dm_pool_metadata *pmd)
{
	int r;
	struct thin_disk_superblock *disk_super;
	struct dm_block *sblock;

	/*
	 * We re-read the superblock every time.  Shouldn't need to do this
	 * really.
	 */
	r = dm_bm_read_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION,
			    &sb_validator, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);
	pmd->time = le32_to_cpu(disk_super->time);
	pmd->root = le64_to_cpu(disk_super->data_mapping_root);
	pmd->details_root = le64_to_cpu(disk_super->device_details_root);
	pmd->trans_id = le64_to_cpu(disk_super->trans_id);
	pmd->flags = le32_to_cpu(disk_super->flags);
	pmd->data_block_size = le32_to_cpu(disk_super->data_block_size);

	dm_bm_unlock(sblock);
	return 0;
}

static int __write_changed_details(struct dm_pool_metadata *pmd)
{
	int r;
	struct dm_thin_device *td, *tmp;
	struct disk_device_details details;
	uint64_t key;

	list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
		if (!td->changed)
			continue;

		key = td->id;

		details.mapped_blocks = cpu_to_le64(td->mapped_blocks);
		details.transaction_id = cpu_to_le64(td->transaction_id);
		details.creation_time = cpu_to_le32(td->creation_time);
		details.snapshotted_time = cpu_to_le32(td->snapshotted_time);
		__dm_bless_for_disk(&details);

		r = dm_btree_insert(&pmd->details_info, pmd->details_root,
				    &key, &details, &pmd->details_root);
		if (r)
			return r;

		if (td->open_count)
			td->changed = false;
		else {
			list_del(&td->list);
			kfree(td);
		}
	}

	return 0;
}

static int __commit_transaction(struct dm_pool_metadata *pmd)
{
	int r;
	struct thin_disk_superblock *disk_super;
	struct dm_block *sblock;

	/*
	 * We need to know if the thin_disk_superblock exceeds a 512-byte sector.
	 */
	BUILD_BUG_ON(sizeof(struct thin_disk_superblock) > 512);
	BUG_ON(!rwsem_is_locked(&pmd->root_lock));

	if (unlikely(!pmd->in_service))
		return 0;

	if (pmd->pre_commit_fn) {
		r = pmd->pre_commit_fn(pmd->pre_commit_context);
		if (r < 0) {
			DMERR("pre-commit callback failed");
			return r;
		}
	}

	r = __write_changed_details(pmd);
	if (r < 0)
		return r;

	r = dm_sm_commit(pmd->data_sm);
	if (r < 0)
		return r;

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

	r = save_sm_roots(pmd);
	if (r < 0)
		return r;

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

	disk_super = dm_block_data(sblock);
	disk_super->time = cpu_to_le32(pmd->time);
	disk_super->data_mapping_root = cpu_to_le64(pmd->root);
	disk_super->device_details_root = cpu_to_le64(pmd->details_root);
	disk_super->trans_id = cpu_to_le64(pmd->trans_id);
	disk_super->flags = cpu_to_le32(pmd->flags);

	copy_sm_roots(pmd, disk_super);

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

static void __set_metadata_reserve(struct dm_pool_metadata *pmd)
{
	int r;
	dm_block_t total;
	dm_block_t max_blocks = 4096; /* 16M */

	r = dm_sm_get_nr_blocks(pmd->metadata_sm, &total);
	if (r) {
		DMERR("could not get size of metadata device");
		pmd->metadata_reserve = max_blocks;
	} else
		pmd->metadata_reserve = min(max_blocks, div_u64(total, 10));
}

struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
					       sector_t data_block_size,
					       bool format_device)
{
	int r;
	struct dm_pool_metadata *pmd;

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

	init_rwsem(&pmd->root_lock);
	pmd->time = 0;
	INIT_LIST_HEAD(&pmd->thin_devices);
	pmd->fail_io = false;
	pmd->in_service = false;
	pmd->bdev = bdev;
	pmd->data_block_size = data_block_size;
	pmd->pre_commit_fn = NULL;
	pmd->pre_commit_context = NULL;

	r = __create_persistent_data_objects(pmd, format_device);
	if (r) {
		kfree(pmd);
		return ERR_PTR(r);
	}

	r = __begin_transaction(pmd);
	if (r < 0) {
		if (dm_pool_metadata_close(pmd) < 0)
			DMWARN("%s: dm_pool_metadata_close() failed.", __func__);
		return ERR_PTR(r);
	}

	__set_metadata_reserve(pmd);

	return pmd;
}

int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
{
	int r;
	unsigned open_devices = 0;
	struct dm_thin_device *td, *tmp;

	down_read(&pmd->root_lock);
	list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
		if (td->open_count)
			open_devices++;
		else {
			list_del(&td->list);
			kfree(td);
		}
	}
	up_read(&pmd->root_lock);

	if (open_devices) {
		DMERR("attempt to close pmd when %u device(s) are still open",
		       open_devices);
		return -EBUSY;
	}

	pmd_write_lock_in_core(pmd);
	if (!pmd->fail_io && !dm_bm_is_read_only(pmd->bm)) {
		r = __commit_transaction(pmd);
		if (r < 0)
			DMWARN("%s: __commit_transaction() failed, error = %d",
			       __func__, r);
	}
	pmd_write_unlock(pmd);
	if (!pmd->fail_io)
		__destroy_persistent_data_objects(pmd);

	kfree(pmd);
	return 0;
}

/*
 * __open_device: Returns @td corresponding to device with id @dev,
 * creating it if @create is set and incrementing @td->open_count.
 * On failure, @td is undefined.
 */
static int __open_device(struct dm_pool_metadata *pmd,
			 dm_thin_id dev, int create,
			 struct dm_thin_device **td)
{
	int r, changed = 0;
	struct dm_thin_device *td2;
	uint64_t key = dev;
	struct disk_device_details details_le;

	/*
	 * If the device is already open, return it.
	 */
	list_for_each_entry(td2, &pmd->thin_devices, list)
		if (td2->id == dev) {
			/*
			 * May not create an already-open device.
			 */
			if (create)
				return -EEXIST;

			td2->open_count++;
			*td = td2;
			return 0;
		}

	/*
	 * Check the device exists.
	 */
	r = dm_btree_lookup(&pmd->details_info, pmd->details_root,
			    &key, &details_le);
	if (r) {
		if (r != -ENODATA || !create)
			return r;

		/*
		 * Create new device.
		 */
		changed = 1;
		details_le.mapped_blocks = 0;
		details_le.transaction_id = cpu_to_le64(pmd->trans_id);
		details_le.creation_time = cpu_to_le32(pmd->time);
		details_le.snapshotted_time = cpu_to_le32(pmd->time);
	}

	*td = kmalloc(sizeof(**td), GFP_NOIO);
	if (!*td)
		return -ENOMEM;

	(*td)->pmd = pmd;
	(*td)->id = dev;
	(*td)->open_count = 1;
	(*td)->changed = changed;
	(*td)->aborted_with_changes = false;
	(*td)->mapped_blocks = le64_to_cpu(details_le.mapped_blocks);
	(*td)->transaction_id = le64_to_cpu(details_le.transaction_id);
	(*td)->creation_time = le32_to_cpu(details_le.creation_time);
	(*td)->snapshotted_time = le32_to_cpu(details_le.snapshotted_time);

	list_add(&(*td)->list, &pmd->thin_devices);

	return 0;
}

static void __close_device(struct dm_thin_device *td)
{
	--td->open_count;
}

static int __create_thin(struct dm_pool_metadata *pmd,
			 dm_thin_id dev)
{
	int r;
	dm_block_t dev_root;
	uint64_t key = dev;
	struct dm_thin_device *td;
	__le64 value;

	r = dm_btree_lookup(&pmd->details_info, pmd->details_root,
			    &key, NULL);
	if (!r)
		return -EEXIST;

	/*
	 * Create an empty btree for the mappings.
	 */
	r = dm_btree_empty(&pmd->bl_info, &dev_root);
	if (r)
		return r;

	/*
	 * Insert it into the main mapping tree.
	 */
	value = cpu_to_le64(dev_root);
	__dm_bless_for_disk(&value);
	r = dm_btree_insert(&pmd->tl_info, pmd->root, &key, &value, &pmd->root);
	if (r) {
		dm_btree_del(&pmd->bl_info, dev_root);
		return r;
	}

	r = __open_device(pmd, dev, 1, &td);
	if (r) {
		dm_btree_remove(&pmd->tl_info, pmd->root, &key, &pmd->root);
		dm_btree_del(&pmd->bl_info, dev_root);
		return r;
	}
	__close_device(td);

	return r;
}

int dm_pool_create_thin(struct dm_pool_metadata *pmd, dm_thin_id dev)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);
	if (!pmd->fail_io)
		r = __create_thin(pmd, dev);
	pmd_write_unlock(pmd);

	return r;
}

static int __set_snapshot_details(struct dm_pool_metadata *pmd,
				  struct dm_thin_device *snap,
				  dm_thin_id origin, uint32_t time)
{
	int r;
	struct dm_thin_device *td;

	r = __open_device(pmd, origin, 0, &td);
	if (r)
		return r;

	td->changed = true;
	td->snapshotted_time = time;

	snap->mapped_blocks = td->mapped_blocks;
	snap->snapshotted_time = time;
	__close_device(td);

	return 0;
}

static int __create_snap(struct dm_pool_metadata *pmd,
			 dm_thin_id dev, dm_thin_id origin)
{
	int r;
	dm_block_t origin_root;
	uint64_t key = origin, dev_key = dev;
	struct dm_thin_device *td;
	__le64 value;

	/* check this device is unused */
	r = dm_btree_lookup(&pmd->details_info, pmd->details_root,
			    &dev_key, NULL);
	if (!r)
		return -EEXIST;

	/* find the mapping tree for the origin */
	r = dm_btree_lookup(&pmd->tl_info, pmd->root, &key, &value);
	if (r)
		return r;
	origin_root = le64_to_cpu(value);

	/* clone the origin, an inc will do */
	dm_tm_inc(pmd->tm, origin_root);

	/* insert into the main mapping tree */
	value = cpu_to_le64(origin_root);
	__dm_bless_for_disk(&value);
	key = dev;
	r = dm_btree_insert(&pmd->tl_info, pmd->root, &key, &value, &pmd->root);
	if (r) {
		dm_tm_dec(pmd->tm, origin_root);
		return r;
	}

	pmd->time++;

	r = __open_device(pmd, dev, 1, &td);
	if (r)
		goto bad;

	r = __set_snapshot_details(pmd, td, origin, pmd->time);
	__close_device(td);

	if (r)
		goto bad;

	return 0;

bad:
	dm_btree_remove(&pmd->tl_info, pmd->root, &key, &pmd->root);
	dm_btree_remove(&pmd->details_info, pmd->details_root,
			&key, &pmd->details_root);
	return r;
}

int dm_pool_create_snap(struct dm_pool_metadata *pmd,
				 dm_thin_id dev,
				 dm_thin_id origin)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);
	if (!pmd->fail_io)
		r = __create_snap(pmd, dev, origin);
	pmd_write_unlock(pmd);

	return r;
}

static int __delete_device(struct dm_pool_metadata *pmd, dm_thin_id dev)
{
	int r;
	uint64_t key = dev;
	struct dm_thin_device *td;

	/* TODO: failure should mark the transaction invalid */
	r = __open_device(pmd, dev, 0, &td);
	if (r)
		return r;

	if (td->open_count > 1) {
		__close_device(td);
		return -EBUSY;
	}

	list_del(&td->list);
	kfree(td);
	r = dm_btree_remove(&pmd->details_info, pmd->details_root,
			    &key, &pmd->details_root);
	if (r)
		return r;

	r = dm_btree_remove(&pmd->tl_info, pmd->root, &key, &pmd->root);
	if (r)
		return r;

	return 0;
}

int dm_pool_delete_thin_device(struct dm_pool_metadata *pmd,
			       dm_thin_id dev)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);
	if (!pmd->fail_io)
		r = __delete_device(pmd, dev);
	pmd_write_unlock(pmd);

	return r;
}

int dm_pool_set_metadata_transaction_id(struct dm_pool_metadata *pmd,
					uint64_t current_id,
					uint64_t new_id)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);

	if (pmd->fail_io)
		goto out;

	if (pmd->trans_id != current_id) {
		DMERR("mismatched transaction id");
		goto out;
	}

	pmd->trans_id = new_id;
	r = 0;

out:
	pmd_write_unlock(pmd);

	return r;
}

int dm_pool_get_metadata_transaction_id(struct dm_pool_metadata *pmd,
					uint64_t *result)
{
	int r = -EINVAL;

	down_read(&pmd->root_lock);
	if (!pmd->fail_io) {
		*result = pmd->trans_id;
		r = 0;
	}
	up_read(&pmd->root_lock);

	return r;
}

static int __reserve_metadata_snap(struct dm_pool_metadata *pmd)
{
	int r, inc;
	struct thin_disk_superblock *disk_super;
	struct dm_block *copy, *sblock;
	dm_block_t held_root;

	/*
	 * We commit to ensure the btree roots which we increment in a
	 * moment are up to date.
	 */
	r = __commit_transaction(pmd);
	if (r < 0) {
		DMWARN("%s: __commit_transaction() failed, error = %d",
		       __func__, r);
		return r;
	}

	/*
	 * Copy the superblock.
	 */
	dm_sm_inc_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION);
	r = dm_tm_shadow_block(pmd->tm, THIN_SUPERBLOCK_LOCATION,
			       &sb_validator, &copy, &inc);
	if (r)
		return r;

	BUG_ON(!inc);

	held_root = dm_block_location(copy);
	disk_super = dm_block_data(copy);

	if (le64_to_cpu(disk_super->held_root)) {
		DMWARN("Pool metadata snapshot already exists: release this before taking another.");

		dm_tm_dec(pmd->tm, held_root);
		dm_tm_unlock(pmd->tm, copy);
		return -EBUSY;
	}

	/*
	 * Wipe the spacemap since we're not publishing this.
	 */
	memset(&disk_super->data_space_map_root, 0,
	       sizeof(disk_super->data_space_map_root));
	memset(&disk_super->metadata_space_map_root, 0,
	       sizeof(disk_super->metadata_space_map_root));

	/*
	 * Increment the data structures that need to be preserved.
	 */
	dm_tm_inc(pmd->tm, le64_to_cpu(disk_super->data_mapping_root));
	dm_tm_inc(pmd->tm, le64_to_cpu(disk_super->device_details_root));
	dm_tm_unlock(pmd->tm, copy);

	/*
	 * Write the held root into the superblock.
	 */
	r = superblock_lock(pmd, &sblock);
	if (r) {
		dm_tm_dec(pmd->tm, held_root);
		return r;
	}

	disk_super = dm_block_data(sblock);
	disk_super->held_root = cpu_to_le64(held_root);
	dm_bm_unlock(sblock);
	return 0;
}

int dm_pool_reserve_metadata_snap(struct dm_pool_metadata *pmd)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);
	if (!pmd->fail_io)
		r = __reserve_metadata_snap(pmd);
	pmd_write_unlock(pmd);

	return r;
}

static int __release_metadata_snap(struct dm_pool_metadata *pmd)
{
	int r;
	struct thin_disk_superblock *disk_super;
	struct dm_block *sblock, *copy;
	dm_block_t held_root;

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

	disk_super = dm_block_data(sblock);
	held_root = le64_to_cpu(disk_super->held_root);
	disk_super->held_root = cpu_to_le64(0);

	dm_bm_unlock(sblock);

	if (!held_root) {
		DMWARN("No pool metadata snapshot found: nothing to release.");
		return -EINVAL;
	}

	r = dm_tm_read_lock(pmd->tm, held_root, &sb_validator, &copy);
	if (r)
		return r;

	disk_super = dm_block_data(copy);
	dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root));
	dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root));
	dm_sm_dec_block(pmd->metadata_sm, held_root);

	dm_tm_unlock(pmd->tm, copy);

	return 0;
}

int dm_pool_release_metadata_snap(struct dm_pool_metadata *pmd)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);
	if (!pmd->fail_io)
		r = __release_metadata_snap(pmd);
	pmd_write_unlock(pmd);

	return r;
}

static int __get_metadata_snap(struct dm_pool_metadata *pmd,
			       dm_block_t *result)
{
	int r;
	struct thin_disk_superblock *disk_super;
	struct dm_block *sblock;

	r = dm_bm_read_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION,
			    &sb_validator, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);
	*result = le64_to_cpu(disk_super->held_root);

	dm_bm_unlock(sblock);

	return 0;
}

int dm_pool_get_metadata_snap(struct dm_pool_metadata *pmd,
			      dm_block_t *result)
{
	int r = -EINVAL;

	down_read(&pmd->root_lock);
	if (!pmd->fail_io)
		r = __get_metadata_snap(pmd, result);
	up_read(&pmd->root_lock);

	return r;
}

int dm_pool_open_thin_device(struct dm_pool_metadata *pmd, dm_thin_id dev,
			     struct dm_thin_device **td)
{
	int r = -EINVAL;

	pmd_write_lock_in_core(pmd);
	if (!pmd->fail_io)
		r = __open_device(pmd, dev, 0, td);
	pmd_write_unlock(pmd);

	return r;
}

int dm_pool_close_thin_device(struct dm_thin_device *td)
{
	pmd_write_lock_in_core(td->pmd);
	__close_device(td);
	pmd_write_unlock(td->pmd);

	return 0;
}

dm_thin_id dm_thin_dev_id(struct dm_thin_device *td)
{
	return td->id;
}

/*
 * Check whether @time (of block creation) is older than @td's last snapshot.
 * If so then the associated block is shared with the last snapshot device.
 * Any block on a device created *after* the device last got snapshotted is
 * necessarily not shared.
 */
static bool __snapshotted_since(struct dm_thin_device *td, uint32_t time)
{
	return td->snapshotted_time > time;
}

static void unpack_lookup_result(struct dm_thin_device *td, __le64 value,
				 struct dm_thin_lookup_result *result)
{
	uint64_t block_time = 0;
	dm_block_t exception_block;
	uint32_t exception_time;

	block_time = le64_to_cpu(value);
	unpack_block_time(block_time, &exception_block, &exception_time);
	result->block = exception_block;
	result->shared = __snapshotted_since(td, exception_time);
}

static int __find_block(struct dm_thin_device *td, dm_block_t block,
			int can_issue_io, struct dm_thin_lookup_result *result)
{
	int r;
	__le64 value;
	struct dm_pool_metadata *pmd = td->pmd;
	dm_block_t keys[2] = { td->id, block };
	struct dm_btree_info *info;

	if (can_issue_io) {
		info = &pmd->info;
	} else
		info = &pmd->nb_info;

	r = dm_btree_lookup(info, pmd->root, keys, &value);
	if (!r)
		unpack_lookup_result(td, value, result);

	return r;
}

int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block,
		       int can_issue_io, struct dm_thin_lookup_result *result)
{
	int r;
	struct dm_pool_metadata *pmd = td->pmd;

	down_read(&pmd->root_lock);
	if (pmd->fail_io) {
		up_read(&pmd->root_lock);
		return -EINVAL;
	}

	r = __find_block(td, block, can_issue_io, result);

	up_read(&pmd->root_lock);
	return r;
}

static int __find_next_mapped_block(struct dm_thin_device *td, dm_block_t block,
					  dm_block_t *vblock,
					  struct dm_thin_lookup_result *result)
{
	int r;
	__le64 value;
	struct dm_pool_metadata *pmd = td->pmd;
	dm_block_t keys[2] = { td->id, block };

	r = dm_btree_lookup_next(&pmd->info, pmd->root, keys, vblock, &value);
	if (!r)
		unpack_lookup_result(td, value, result);

	return r;
}

static int __find_mapped_range(struct dm_thin_device *td,
			       dm_block_t begin, dm_block_t end,
			       dm_block_t *thin_begin, dm_block_t *thin_end,
			       dm_block_t *pool_begin, bool *maybe_shared)
{
	int r;
	dm_block_t pool_end;
	struct dm_thin_lookup_result lookup;

	if (end < begin)
		return -ENODATA;

	r = __find_next_mapped_block(td, begin, &begin, &lookup);
	if (r)
		return r;

	if (begin >= end)
		return -ENODATA;

	*thin_begin = begin;
	*pool_begin = lookup.block;
	*maybe_shared = lookup.shared;

	begin++;
	pool_end = *pool_begin + 1;
	while (begin != end) {
		r = __find_block(td, begin, true, &lookup);
		if (r) {
			if (r == -ENODATA)
				break;
			else
				return r;
		}

		if ((lookup.block != pool_end) ||
		    (lookup.shared != *maybe_shared))
			break;

		pool_end++;
		begin++;
	}

	*thin_end = begin;
	return 0;
}

int dm_thin_find_mapped_range(struct dm_thin_device *td,
			      dm_block_t begin, dm_block_t end,
			      dm_block_t *thin_begin, dm_block_t *thin_end,
			      dm_block_t *pool_begin, bool *maybe_shared)
{
	int r = -EINVAL;
	struct dm_pool_metadata *pmd = td->pmd;

	down_read(&pmd->root_lock);
	if (!pmd->fail_io) {
		r = __find_mapped_range(td, begin, end, thin_begin, thin_end,
					pool_begin, maybe_shared);
	}
	up_read(&pmd->root_lock);

	return r;
}

static int __insert(struct dm_thin_device *td, dm_block_t block,
		    dm_block_t data_block)
{
	int r, inserted;
	__le64 value;
	struct dm_pool_metadata *pmd = td->pmd;
	dm_block_t keys[2] = { td->id, block };

	value = cpu_to_le64(pack_block_time(data_block, pmd->time));
	__dm_bless_for_disk(&value);

	r = dm_btree_insert_notify(&pmd->info, pmd->root, keys, &value,
				   &pmd->root, &inserted);
	if (r)
		return r;

	td->changed = true;
	if (inserted)
		td->mapped_blocks++;

	return 0;
}

int dm_thin_insert_block(struct dm_thin_device *td, dm_block_t block,
			 dm_block_t data_block)
{
	int r = -EINVAL;

	pmd_write_lock(td->pmd);
	if (!td->pmd->fail_io)
		r = __insert(td, block, data_block);
	pmd_write_unlock(td->pmd);

	return r;
}

static int __remove(struct dm_thin_device *td, dm_block_t block)
{
	int r;
	struct dm_pool_metadata *pmd = td->pmd;
	dm_block_t keys[2] = { td->id, block };

	r = dm_btree_remove(&pmd->info, pmd->root, keys, &pmd->root);
	if (r)
		return r;

	td->mapped_blocks--;
	td->changed = true;

	return 0;
}

static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end)
{
	int r;
	unsigned count, total_count = 0;
	struct dm_pool_metadata *pmd = td->pmd;
	dm_block_t keys[1] = { td->id };
	__le64 value;
	dm_block_t mapping_root;

	/*
	 * Find the mapping tree
	 */
	r = dm_btree_lookup(&pmd->tl_info, pmd->root, keys, &value);
	if (r)
		return r;

	/*
	 * Remove from the mapping tree, taking care to inc the
	 * ref count so it doesn't get deleted.
	 */
	mapping_root = le64_to_cpu(value);
	dm_tm_inc(pmd->tm, mapping_root);
	r = dm_btree_remove(&pmd->tl_info, pmd->root, keys, &pmd->root);
	if (r)
		return r;

	/*
	 * Remove leaves stops at the first unmapped entry, so we have to
	 * loop round finding mapped ranges.
	 */
	while (begin < end) {
		r = dm_btree_lookup_next(&pmd->bl_info, mapping_root, &begin, &begin, &value);
		if (r == -ENODATA)
			break;

		if (r)
			return r;

		if (begin >= end)
			break;

		r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count);
		if (r)
			return r;

		total_count += count;
	}

	td->mapped_blocks -= total_count;
	td->changed = true;

	/*
	 * Reinsert the mapping tree.
	 */
	value = cpu_to_le64(mapping_root);
	__dm_bless_for_disk(&value);
	return dm_btree_insert(&pmd->tl_info, pmd->root, keys, &value, &pmd->root);
}

int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block)
{
	int r = -EINVAL;

	pmd_write_lock(td->pmd);
	if (!td->pmd->fail_io)
		r = __remove(td, block);
	pmd_write_unlock(td->pmd);

	return r;
}

int dm_thin_remove_range(struct dm_thin_device *td,
			 dm_block_t begin, dm_block_t end)
{
	int r = -EINVAL;

	pmd_write_lock(td->pmd);
	if (!td->pmd->fail_io)
		r = __remove_range(td, begin, end);
	pmd_write_unlock(td->pmd);

	return r;
}

int dm_pool_block_is_shared(struct dm_pool_metadata *pmd, dm_block_t b, bool *result)
{
	int r;
	uint32_t ref_count;

	down_read(&pmd->root_lock);
	r = dm_sm_get_count(pmd->data_sm, b, &ref_count);
	if (!r)
		*result = (ref_count > 1);
	up_read(&pmd->root_lock);

	return r;
}

int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e)
{
	int r = 0;

	pmd_write_lock(pmd);
	r = dm_sm_inc_blocks(pmd->data_sm, b, e);
	pmd_write_unlock(pmd);

	return r;
}

int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e)
{
	int r = 0;

	pmd_write_lock(pmd);
	r = dm_sm_dec_blocks(pmd->data_sm, b, e);
	pmd_write_unlock(pmd);

	return r;
}

bool dm_thin_changed_this_transaction(struct dm_thin_device *td)
{
	int r;

	down_read(&td->pmd->root_lock);
	r = td->changed;
	up_read(&td->pmd->root_lock);

	return r;
}

bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd)
{
	bool r = false;
	struct dm_thin_device *td, *tmp;

	down_read(&pmd->root_lock);
	list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
		if (td->changed) {
			r = td->changed;
			break;
		}
	}
	up_read(&pmd->root_lock);

	return r;
}

bool dm_thin_aborted_changes(struct dm_thin_device *td)
{
	bool r;

	down_read(&td->pmd->root_lock);
	r = td->aborted_with_changes;
	up_read(&td->pmd->root_lock);

	return r;
}

int dm_pool_alloc_data_block(struct dm_pool_metadata *pmd, dm_block_t *result)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);
	if (!pmd->fail_io)
		r = dm_sm_new_block(pmd->data_sm, result);
	pmd_write_unlock(pmd);

	return r;
}

int dm_pool_commit_metadata(struct dm_pool_metadata *pmd)
{
	int r = -EINVAL;

	/*
	 * Care is taken to not have commit be what
	 * triggers putting the thin-pool in-service.
	 */
	pmd_write_lock_in_core(pmd);
	if (pmd->fail_io)
		goto out;

	r = __commit_transaction(pmd);
	if (r < 0)
		goto out;

	/*
	 * Open the next transaction.
	 */
	r = __begin_transaction(pmd);
out:
	pmd_write_unlock(pmd);
	return r;
}

static void __set_abort_with_changes_flags(struct dm_pool_metadata *pmd)
{
	struct dm_thin_device *td;

	list_for_each_entry(td, &pmd->thin_devices, list)
		td->aborted_with_changes = td->changed;
}

int dm_pool_abort_metadata(struct dm_pool_metadata *pmd)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);
	if (pmd->fail_io)
		goto out;

	__set_abort_with_changes_flags(pmd);
	__destroy_persistent_data_objects(pmd);
	r = __create_persistent_data_objects(pmd, false);
	if (r)
		pmd->fail_io = true;

out:
	pmd_write_unlock(pmd);

	return r;
}

int dm_pool_get_free_block_count(struct dm_pool_metadata *pmd, dm_block_t *result)
{
	int r = -EINVAL;

	down_read(&pmd->root_lock);
	if (!pmd->fail_io)
		r = dm_sm_get_nr_free(pmd->data_sm, result);
	up_read(&pmd->root_lock);

	return r;
}

int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd,
					  dm_block_t *result)
{
	int r = -EINVAL;

	down_read(&pmd->root_lock);
	if (!pmd->fail_io)
		r = dm_sm_get_nr_free(pmd->metadata_sm, result);

	if (!r) {
		if (*result < pmd->metadata_reserve)
			*result = 0;
		else
			*result -= pmd->metadata_reserve;
	}
	up_read(&pmd->root_lock);

	return r;
}

int dm_pool_get_metadata_dev_size(struct dm_pool_metadata *pmd,
				  dm_block_t *result)
{
	int r = -EINVAL;

	down_read(&pmd->root_lock);
	if (!pmd->fail_io)
		r = dm_sm_get_nr_blocks(pmd->metadata_sm, result);
	up_read(&pmd->root_lock);

	return r;
}

int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result)
{
	int r = -EINVAL;

	down_read(&pmd->root_lock);
	if (!pmd->fail_io)
		r = dm_sm_get_nr_blocks(pmd->data_sm, result);
	up_read(&pmd->root_lock);

	return r;
}

int dm_thin_get_mapped_count(struct dm_thin_device *td, dm_block_t *result)
{
	int r = -EINVAL;
	struct dm_pool_metadata *pmd = td->pmd;

	down_read(&pmd->root_lock);
	if (!pmd->fail_io) {
		*result = td->mapped_blocks;
		r = 0;
	}
	up_read(&pmd->root_lock);

	return r;
}

static int __highest_block(struct dm_thin_device *td, dm_block_t *result)
{
	int r;
	__le64 value_le;
	dm_block_t thin_root;
	struct dm_pool_metadata *pmd = td->pmd;

	r = dm_btree_lookup(&pmd->tl_info, pmd->root, &td->id, &value_le);
	if (r)
		return r;

	thin_root = le64_to_cpu(value_le);

	return dm_btree_find_highest_key(&pmd->bl_info, thin_root, result);
}

int dm_thin_get_highest_mapped_block(struct dm_thin_device *td,
				     dm_block_t *result)
{
	int r = -EINVAL;
	struct dm_pool_metadata *pmd = td->pmd;

	down_read(&pmd->root_lock);
	if (!pmd->fail_io)
		r = __highest_block(td, result);
	up_read(&pmd->root_lock);

	return r;
}

static int __resize_space_map(struct dm_space_map *sm, dm_block_t new_count)
{
	int r;
	dm_block_t old_count;

	r = dm_sm_get_nr_blocks(sm, &old_count);
	if (r)
		return r;

	if (new_count == old_count)
		return 0;

	if (new_count < old_count) {
		DMERR("cannot reduce size of space map");
		return -EINVAL;
	}

	return dm_sm_extend(sm, new_count - old_count);
}

int dm_pool_resize_data_dev(struct dm_pool_metadata *pmd, dm_block_t new_count)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);
	if (!pmd->fail_io)
		r = __resize_space_map(pmd->data_sm, new_count);
	pmd_write_unlock(pmd);

	return r;
}

int dm_pool_resize_metadata_dev(struct dm_pool_metadata *pmd, dm_block_t new_count)
{
	int r = -EINVAL;

	pmd_write_lock(pmd);
	if (!pmd->fail_io) {
		r = __resize_space_map(pmd->metadata_sm, new_count);
		if (!r)
			__set_metadata_reserve(pmd);
	}
	pmd_write_unlock(pmd);

	return r;
}

void dm_pool_metadata_read_only(struct dm_pool_metadata *pmd)
{
	pmd_write_lock_in_core(pmd);
	dm_bm_set_read_only(pmd->bm);
	pmd_write_unlock(pmd);
}

void dm_pool_metadata_read_write(struct dm_pool_metadata *pmd)
{
	pmd_write_lock_in_core(pmd);
	dm_bm_set_read_write(pmd->bm);
	pmd_write_unlock(pmd);
}

int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd,
					dm_block_t threshold,
					dm_sm_threshold_fn fn,
					void *context)
{
	int r;

	pmd_write_lock_in_core(pmd);
	r = dm_sm_register_threshold_callback(pmd->metadata_sm, threshold, fn, context);
	pmd_write_unlock(pmd);

	return r;
}

void dm_pool_register_pre_commit_callback(struct dm_pool_metadata *pmd,
					  dm_pool_pre_commit_fn fn,
					  void *context)
{
	pmd_write_lock_in_core(pmd);
	pmd->pre_commit_fn = fn;
	pmd->pre_commit_context = context;
	pmd_write_unlock(pmd);
}

int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd)
{
	int r = -EINVAL;
	struct dm_block *sblock;
	struct thin_disk_superblock *disk_super;

	pmd_write_lock(pmd);
	if (pmd->fail_io)
		goto out;

	pmd->flags |= THIN_METADATA_NEEDS_CHECK_FLAG;

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

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

	dm_bm_unlock(sblock);
out:
	pmd_write_unlock(pmd);
	return r;
}

bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd)
{
	bool needs_check;

	down_read(&pmd->root_lock);
	needs_check = pmd->flags & THIN_METADATA_NEEDS_CHECK_FLAG;
	up_read(&pmd->root_lock);

	return needs_check;
}

void dm_pool_issue_prefetches(struct dm_pool_metadata *pmd)
{
	down_read(&pmd->root_lock);
	if (!pmd->fail_io)
		dm_tm_issue_prefetches(pmd->tm);
	up_read(&pmd->root_lock);
}