summaryrefslogtreecommitdiff
path: root/include/linux/bcache.h
blob: f4c2f275bf780247cb8f4dec9fa66535ee6da884 (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
#ifndef _LINUX_BCACHE_H
#define _LINUX_BCACHE_H

/*
 * Bcache on disk data structures
 */

#ifdef __cplusplus
typedef bool _Bool;
extern "C" {
#endif

#include <asm/types.h>
#include <asm/byteorder.h>
#include <linux/uuid.h>

#define LE32_BITMASK(name, type, field, offset, end)			\
static const unsigned	name##_OFFSET = offset;				\
static const unsigned	name##_BITS = (end - offset);			\
static const __u64	name##_MAX = (1ULL << (end - offset)) - 1;	\
									\
static inline __u64 name(const type *k)					\
{									\
	return (__le32_to_cpu(k->field) >> offset) &			\
		~(~0ULL << (end - offset));				\
}									\
									\
static inline void SET_##name(type *k, __u64 v)				\
{									\
	__u64 new = __le32_to_cpu(k->field);				\
									\
	new &= ~(~(~0ULL << (end - offset)) << offset);			\
	new |= (v & ~(~0ULL << (end - offset))) << offset;		\
	k->field = __cpu_to_le32(new);					\
}

#define LE64_BITMASK(name, type, field, offset, end)			\
static const unsigned	name##_OFFSET = offset;				\
static const unsigned	name##_BITS = (end - offset);			\
static const __u64	name##_MAX = (1ULL << (end - offset)) - 1;	\
									\
static inline __u64 name(const type *k)					\
{									\
	return (__le64_to_cpu(k->field) >> offset) &			\
		~(~0ULL << (end - offset));				\
}									\
									\
static inline void SET_##name(type *k, __u64 v)				\
{									\
	__u64 new = __le64_to_cpu(k->field);				\
									\
	new &= ~(~(~0ULL << (end - offset)) << offset);			\
	new |= (v & ~(~0ULL << (end - offset))) << offset;		\
	k->field = __cpu_to_le64(new);					\
}

struct bkey_format {
	__u8		key_u64s;
	__u8		nr_fields;
	/* One unused slot for now: */
	__u8		bits_per_field[6];
	__le64		field_offset[6];
};

/* Btree keys - all units are in sectors */

struct bpos {
	/* Word order matches machine byte order */
#if defined(__LITTLE_ENDIAN)
	__u32		snapshot;
	__u64		offset;
	__u64		inode;
#elif defined(__BIG_ENDIAN)
	__u64		inode;
	__u64		offset;		/* Points to end of extent - sectors */
	__u32		snapshot;
#else
#error edit for your odd byteorder.
#endif
} __attribute__((packed, aligned(4)));

#define KEY_INODE_MAX			((__u64)~0ULL)
#define KEY_OFFSET_MAX			((__u64)~0ULL)
#define KEY_SNAPSHOT_MAX		((__u32)~0U)

static inline struct bpos POS(__u64 inode, __u64 offset)
{
	struct bpos ret;

	ret.inode	= inode;
	ret.offset	= offset;
	ret.snapshot	= 0;

	return ret;
}

#define POS_MIN				POS(0, 0)
#define POS_MAX				POS(KEY_INODE_MAX, KEY_OFFSET_MAX)

/* Empty placeholder struct, for container_of() */
struct bch_val {
	__u64		__nothing[0];
};

struct bversion {
#if defined(__LITTLE_ENDIAN)
	__u64		lo;
	__u32		hi;
#elif defined(__BIG_ENDIAN)
	__u32		hi;
	__u64		lo;
#endif
} __attribute__((packed, aligned(4)));

struct bkey {
	/* Size of combined key and value, in u64s */
	__u8		u64s;

	/* Format of key (0 for format local to btree node) */
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u8		format:7,
			needs_whiteout:1;
#elif defined (__BIG_ENDIAN_BITFIELD)
	__u8		needs_whiteout:1,
			format:7;
#else
#error edit for your odd byteorder.
#endif

	/* Type of the value */
	__u8		type;

#if defined(__LITTLE_ENDIAN)
	__u8		pad[1];

	struct bversion	version;
	__u32		size;		/* extent size, in sectors */
	struct bpos	p;
#elif defined(__BIG_ENDIAN)
	struct bpos	p;
	__u32		size;		/* extent size, in sectors */
	struct bversion	version;

	__u8		pad[1];
#endif
} __attribute__((packed, aligned(8)));

struct bkey_packed {
	__u64		_data[0];

	/* Size of combined key and value, in u64s */
	__u8		u64s;

	/* Format of key (0 for format local to btree node) */

	/*
	 * XXX: next incompat on disk format change, switch format and
	 * needs_whiteout - bkey_packed() will be cheaper if format is the high
	 * bits of the bitfield
	 */
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u8		format:7,
			needs_whiteout:1;
#elif defined (__BIG_ENDIAN_BITFIELD)
	__u8		needs_whiteout:1,
			format:7;
#endif

	/* Type of the value */
	__u8		type;
	__u8		key_start[0];

	/*
	 * We copy bkeys with struct assignment in various places, and while
	 * that shouldn't be done with packed bkeys we can't disallow it in C,
	 * and it's legal to cast a bkey to a bkey_packed  - so padding it out
	 * to the same size as struct bkey should hopefully be safest.
	 */
	__u8		pad[sizeof(struct bkey) - 3];
} __attribute__((packed, aligned(8)));

#define BKEY_U64s			(sizeof(struct bkey) / sizeof(__u64))
#define KEY_PACKED_BITS_START		24

#define KEY_SIZE_MAX			((__u32)~0U)

#define KEY_FORMAT_LOCAL_BTREE		0
#define KEY_FORMAT_CURRENT		1

enum bch_bkey_fields {
	BKEY_FIELD_INODE,
	BKEY_FIELD_OFFSET,
	BKEY_FIELD_SNAPSHOT,
	BKEY_FIELD_SIZE,
	BKEY_FIELD_VERSION_HI,
	BKEY_FIELD_VERSION_LO,
	BKEY_NR_FIELDS,
};

#define bkey_format_field(name, field)					\
	[BKEY_FIELD_##name] = (sizeof(((struct bkey *) NULL)->field) * 8)

#define BKEY_FORMAT_CURRENT						\
((struct bkey_format) {							\
	.key_u64s	= BKEY_U64s,					\
	.nr_fields	= BKEY_NR_FIELDS,				\
	.bits_per_field = {						\
		bkey_format_field(INODE,	p.inode),		\
		bkey_format_field(OFFSET,	p.offset),		\
		bkey_format_field(SNAPSHOT,	p.snapshot),		\
		bkey_format_field(SIZE,		size),			\
		bkey_format_field(VERSION_HI,	version.hi),		\
		bkey_format_field(VERSION_LO,	version.lo),		\
	},								\
})

/* bkey with inline value */
struct bkey_i {
	__u64			_data[0];

	union {
	struct {
		/* Size of combined key and value, in u64s */
		__u8		u64s;
	};
	struct {
		struct bkey	k;
		struct bch_val	v;
	};
	};
};

#ifndef __cplusplus

#define KEY(_inode, _offset, _size)					\
((struct bkey) {							\
	.u64s		= BKEY_U64s,					\
	.format		= KEY_FORMAT_CURRENT,				\
	.p		= POS(_inode, _offset),				\
	.size		= _size,					\
})

#else

static inline struct bkey KEY(__u64 inode, __u64 offset, __u64 size)
{
	struct bkey ret;

	memset(&ret, 0, sizeof(ret));
	ret.u64s	= BKEY_U64s;
	ret.format	= KEY_FORMAT_CURRENT;
	ret.p.inode	= inode;
	ret.p.offset	= offset;
	ret.size	= size;

	return ret;
}

#endif

static inline void bkey_init(struct bkey *k)
{
	*k = KEY(0, 0, 0);
}

#define bkey_bytes(_k)		((_k)->u64s * sizeof(__u64))

#define __BKEY_PADDED(key, pad)					\
	struct { struct bkey_i key; __u64 key ## _pad[pad]; }

#define BKEY_VAL_TYPE(name, nr)						\
struct bkey_i_##name {							\
	union {								\
		struct bkey		k;				\
		struct bkey_i		k_i;				\
	};								\
	struct bch_##name		v;				\
}

/*
 * - DELETED keys are used internally to mark keys that should be ignored but
 *   override keys in composition order.  Their version number is ignored.
 *
 * - DISCARDED keys indicate that the data is all 0s because it has been
 *   discarded. DISCARDs may have a version; if the version is nonzero the key
 *   will be persistent, otherwise the key will be dropped whenever the btree
 *   node is rewritten (like DELETED keys).
 *
 * - ERROR: any read of the data returns a read error, as the data was lost due
 *   to a failing device. Like DISCARDED keys, they can be removed (overridden)
 *   by new writes or cluster-wide GC. Node repair can also overwrite them with
 *   the same or a more recent version number, but not with an older version
 *   number.
*/
#define KEY_TYPE_DELETED		0
#define KEY_TYPE_DISCARD		1
#define KEY_TYPE_ERROR			2
#define KEY_TYPE_COOKIE			3
#define KEY_TYPE_PERSISTENT_DISCARD	4
#define KEY_TYPE_GENERIC_NR		128

struct bch_cookie {
	struct bch_val		v;
	__le64			cookie;
};
BKEY_VAL_TYPE(cookie,		KEY_TYPE_COOKIE);

/* Extents */

/*
 * In extent bkeys, the value is a list of pointers (bch_extent_ptr), optionally
 * preceded by checksum/compression information (bch_extent_crc32 or
 * bch_extent_crc64).
 *
 * One major determining factor in the format of extents is how we handle and
 * represent extents that have been partially overwritten and thus trimmed:
 *
 * If an extent is not checksummed or compressed, when the extent is trimmed we
 * don't have to remember the extent we originally allocated and wrote: we can
 * merely adjust ptr->offset to point to the start of the start of the data that
 * is currently live. The size field in struct bkey records the current (live)
 * size of the extent, and is also used to mean "size of region on disk that we
 * point to" in this case.
 *
 * Thus an extent that is not checksummed or compressed will consist only of a
 * list of bch_extent_ptrs, with none of the fields in
 * bch_extent_crc32/bch_extent_crc64.
 *
 * When an extent is checksummed or compressed, it's not possible to read only
 * the data that is currently live: we have to read the entire extent that was
 * originally written, and then return only the part of the extent that is
 * currently live.
 *
 * Thus, in addition to the current size of the extent in struct bkey, we need
 * to store the size of the originally allocated space - this is the
 * compressed_size and uncompressed_size fields in bch_extent_crc32/64. Also,
 * when the extent is trimmed, instead of modifying the offset field of the
 * pointer, we keep a second smaller offset field - "offset into the original
 * extent of the currently live region".
 *
 * The other major determining factor is replication and data migration:
 *
 * Each pointer may have its own bch_extent_crc32/64. When doing a replicated
 * write, we will initially write all the replicas in the same format, with the
 * same checksum type and compression format - however, when copygc runs later (or
 * tiering/cache promotion, anything that moves data), it is not in general
 * going to rewrite all the pointers at once - one of the replicas may be in a
 * bucket on one device that has very little fragmentation while another lives
 * in a bucket that has become heavily fragmented, and thus is being rewritten
 * sooner than the rest.
 *
 * Thus it will only move a subset of the pointers (or in the case of
 * tiering/cache promotion perhaps add a single pointer without dropping any
 * current pointers), and if the extent has been partially overwritten it must
 * write only the currently live portion (or copygc would not be able to reduce
 * fragmentation!) - which necessitates a different bch_extent_crc format for
 * the new pointer.
 *
 * But in the interests of space efficiency, we don't want to store one
 * bch_extent_crc for each pointer if we don't have to.
 *
 * Thus, a bch_extent consists of bch_extent_crc32s, bch_extent_crc64s, and
 * bch_extent_ptrs appended arbitrarily one after the other. We determine the
 * type of a given entry with a scheme similar to utf8 (except we're encoding a
 * type, not a size), encoding the type in the position of the first set bit:
 *
 * bch_extent_crc32	- 0b1
 * bch_extent_ptr	- 0b10
 * bch_extent_crc64	- 0b100
 *
 * We do it this way because bch_extent_crc32 is _very_ constrained on bits (and
 * bch_extent_crc64 is the least constrained).
 *
 * Then, each bch_extent_crc32/64 applies to the pointers that follow after it,
 * until the next bch_extent_crc32/64.
 *
 * If there are no bch_extent_crcs preceding a bch_extent_ptr, then that pointer
 * is neither checksummed nor compressed.
 */

/* 128 bits, sufficient for cryptographic MACs: */
struct bch_csum {
	__le64			lo;
	__le64			hi;
} __attribute__((packed, aligned(8)));

#define BCH_CSUM_NONE			0U
#define BCH_CSUM_CRC32C			1U
#define BCH_CSUM_CRC64			2U
#define BCH_CSUM_CHACHA20_POLY1305_80	3U
#define BCH_CSUM_CHACHA20_POLY1305_128	4U
#define BCH_CSUM_NR			5U

static inline _Bool bch_csum_type_is_encryption(unsigned type)
{
	switch (type) {
	case BCH_CSUM_CHACHA20_POLY1305_80:
	case BCH_CSUM_CHACHA20_POLY1305_128:
		return true;
	default:
		return false;
	}
}

enum bch_extent_entry_type {
	BCH_EXTENT_ENTRY_ptr		= 0,
	BCH_EXTENT_ENTRY_crc32		= 1,
	BCH_EXTENT_ENTRY_crc64		= 2,
	BCH_EXTENT_ENTRY_crc128		= 3,
};

#define BCH_EXTENT_ENTRY_MAX		4

/* Compressed/uncompressed size are stored biased by 1: */
struct bch_extent_crc32 {
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u32			type:2,
				_compressed_size:7,
				_uncompressed_size:7,
				offset:7,
				_unused:1,
				csum_type:4,
				compression_type:4;
	__u32			csum;
#elif defined (__BIG_ENDIAN_BITFIELD)
	__u32			csum;
	__u32			compression_type:4,
				csum_type:4,
				_unused:1,
				offset:7,
				_uncompressed_size:7,
				_compressed_size:7,
				type:2;
#endif
} __attribute__((packed, aligned(8)));

#define CRC32_SIZE_MAX		(1U << 7)
#define CRC32_NONCE_MAX		0

struct bch_extent_crc64 {
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u64			type:3,
				_compressed_size:9,
				_uncompressed_size:9,
				offset:9,
				nonce:10,
				csum_type:4,
				compression_type:4,
				csum_hi:16;
#elif defined (__BIG_ENDIAN_BITFIELD)
	__u64			csum_hi:16,
				compression_type:4,
				csum_type:4,
				nonce:10,
				offset:9,
				_uncompressed_size:9,
				_compressed_size:9,
				type:3;
#endif
	__u64			csum_lo;
} __attribute__((packed, aligned(8)));

#define CRC64_SIZE_MAX		(1U << 9)
#define CRC64_NONCE_MAX		((1U << 10) - 1)

struct bch_extent_crc128 {
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u64			type:4,
				_compressed_size:13,
				_uncompressed_size:13,
				offset:13,
				nonce:13,
				csum_type:4,
				compression_type:4;
#elif defined (__BIG_ENDIAN_BITFIELD)
	__u64			compression_type:4,
				csum_type:4,
				nonce:14,
				offset:13,
				_uncompressed_size:13,
				_compressed_size:13,
				type:3;
#endif
	struct bch_csum		csum;
} __attribute__((packed, aligned(8)));

#define CRC128_SIZE_MAX		(1U << 13)
#define CRC128_NONCE_MAX	((1U << 13) - 1)

/*
 * Max size of an extent that may require bouncing to read or write
 * (checksummed, compressed): 64k
 */
#define BCH_ENCODED_EXTENT_MAX	128U

/*
 * @reservation - pointer hasn't been written to, just reserved
 */
struct bch_extent_ptr {
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u64			type:1,
				cached:1,
				erasure_coded:1,
				reservation:1,
				offset:44, /* 8 petabytes */
				dev:8,
				gen:8;
#elif defined (__BIG_ENDIAN_BITFIELD)
	__u64			gen:8,
				dev:8,
				offset:44,
				reservation:1,
				erasure_coded:1,
				cached:1,
				type:1;
#endif
} __attribute__((packed, aligned(8)));

struct bch_extent_reservation {
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u64			type:5,
				unused:23,
				replicas:4,
				generation:32;
#elif defined (__BIG_ENDIAN_BITFIELD)
	__u64			generation:32,
				replicas:4,
				unused:23,
				type:5;
#endif
};

union bch_extent_entry {
#if defined(__LITTLE_ENDIAN) ||  __BITS_PER_LONG == 64
	unsigned long			type;
#elif __BITS_PER_LONG == 32
	struct {
		unsigned long		pad;
		unsigned long		type;
	};
#else
#error edit for your odd byteorder.
#endif
	struct bch_extent_crc32		crc32;
	struct bch_extent_crc64		crc64;
	struct bch_extent_crc128	crc128;
	struct bch_extent_ptr		ptr;
};

enum {
	BCH_EXTENT		= 128,

	/*
	 * This is kind of a hack, we're overloading the type for a boolean that
	 * really should be part of the value - BCH_EXTENT and BCH_EXTENT_CACHED
	 * have the same value type:
	 */
	BCH_EXTENT_CACHED	= 129,

	/*
	 * Persistent reservation:
	 */
	BCH_RESERVATION		= 130,
};

struct bch_extent {
	struct bch_val		v;

	union bch_extent_entry	start[0];
	__u64			_data[0];
} __attribute__((packed, aligned(8)));
BKEY_VAL_TYPE(extent,		BCH_EXTENT);

struct bch_reservation {
	struct bch_val		v;

	__le32			generation;
	__u8			nr_replicas;
	__u8			pad[3];
} __attribute__((packed, aligned(8)));
BKEY_VAL_TYPE(reservation,	BCH_RESERVATION);

/* Maximum size (in u64s) a single pointer could be: */
#define BKEY_EXTENT_PTR_U64s_MAX\
	((sizeof(struct bch_extent_crc128) +			\
	  sizeof(struct bch_extent_ptr)) / sizeof(u64))

/* Maximum possible size of an entire extent value: */
/* There's a hack in the keylist code that needs to be fixed.. */
#define BKEY_EXTENT_VAL_U64s_MAX				\
	(BKEY_EXTENT_PTR_U64s_MAX * BCH_REPLICAS_MAX)

/* * Maximum possible size of an entire extent, key + value: */
#define BKEY_EXTENT_U64s_MAX		(BKEY_U64s + BKEY_EXTENT_VAL_U64s_MAX)

/* Btree pointers don't carry around checksums: */
#define BKEY_BTREE_PTR_VAL_U64s_MAX				\
	((sizeof(struct bch_extent_ptr)) / sizeof(u64) * BCH_REPLICAS_MAX)
#define BKEY_BTREE_PTR_U64s_MAX					\
	(BKEY_U64s + BKEY_BTREE_PTR_VAL_U64s_MAX)

/* Inodes */

#define BLOCKDEV_INODE_MAX	4096

#define BCACHE_ROOT_INO		4096

enum bch_inode_types {
	BCH_INODE_FS		= 128,
	BCH_INODE_BLOCKDEV	= 129,
};

struct bch_inode {
	struct bch_val		v;

	__le64			i_hash_seed;
	__le32			i_flags;
	__le16			i_mode;
	__u8			fields[0];
} __attribute__((packed));
BKEY_VAL_TYPE(inode,		BCH_INODE_FS);

#define BCH_INODE_FIELDS()				\
	BCH_INODE_FIELD(i_atime,	64)		\
	BCH_INODE_FIELD(i_ctime,	64)		\
	BCH_INODE_FIELD(i_mtime,	64)		\
	BCH_INODE_FIELD(i_otime,	64)		\
	BCH_INODE_FIELD(i_size,		64)		\
	BCH_INODE_FIELD(i_sectors,	64)		\
	BCH_INODE_FIELD(i_uid,		32)		\
	BCH_INODE_FIELD(i_gid,		32)		\
	BCH_INODE_FIELD(i_nlink,	32)		\
	BCH_INODE_FIELD(i_generation,	32)		\
	BCH_INODE_FIELD(i_dev,		32)

enum {
	/*
	 * User flags (get/settable with FS_IOC_*FLAGS, correspond to FS_*_FL
	 * flags)
	 */
	__BCH_INODE_SYNC	= 0,
	__BCH_INODE_IMMUTABLE	= 1,
	__BCH_INODE_APPEND	= 2,
	__BCH_INODE_NODUMP	= 3,
	__BCH_INODE_NOATIME	= 4,

	__BCH_INODE_I_SIZE_DIRTY= 5,
	__BCH_INODE_I_SECTORS_DIRTY= 6,

	/* not implemented yet: */
	__BCH_INODE_HAS_XATTRS	= 7, /* has xattrs in xattr btree */

	/* bits 20+ reserved for packed fields below: */
};

#define BCH_INODE_SYNC		(1 << __BCH_INODE_SYNC)
#define BCH_INODE_IMMUTABLE	(1 << __BCH_INODE_IMMUTABLE)
#define BCH_INODE_APPEND	(1 << __BCH_INODE_APPEND)
#define BCH_INODE_NODUMP	(1 << __BCH_INODE_NODUMP)
#define BCH_INODE_NOATIME	(1 << __BCH_INODE_NOATIME)
#define BCH_INODE_I_SIZE_DIRTY	(1 << __BCH_INODE_I_SIZE_DIRTY)
#define BCH_INODE_I_SECTORS_DIRTY (1 << __BCH_INODE_I_SECTORS_DIRTY)
#define BCH_INODE_HAS_XATTRS	(1 << __BCH_INODE_HAS_XATTRS)

LE32_BITMASK(INODE_STR_HASH,	struct bch_inode, i_flags, 20, 24);
LE32_BITMASK(INODE_NR_FIELDS,	struct bch_inode, i_flags, 24, 32);

struct bch_inode_blockdev {
	struct bch_val		v;

	__le64			i_size;
	__le64			i_flags;

	/* Seconds: */
	__le64			i_ctime;
	__le64			i_mtime;

	uuid_le			i_uuid;
	__u8			i_label[32];
} __attribute__((packed, aligned(8)));
BKEY_VAL_TYPE(inode_blockdev,	BCH_INODE_BLOCKDEV);

/* Thin provisioned volume, or cache for another block device? */
LE64_BITMASK(CACHED_DEV,	struct bch_inode_blockdev, i_flags, 0,  1)

/* Dirents */

/*
 * Dirents (and xattrs) have to implement string lookups; since our b-tree
 * doesn't support arbitrary length strings for the key, we instead index by a
 * 64 bit hash (currently truncated sha1) of the string, stored in the offset
 * field of the key - using linear probing to resolve hash collisions. This also
 * provides us with the readdir cookie posix requires.
 *
 * Linear probing requires us to use whiteouts for deletions, in the event of a
 * collision:
 */

enum {
	BCH_DIRENT		= 128,
	BCH_DIRENT_WHITEOUT	= 129,
};

struct bch_dirent {
	struct bch_val		v;

	/* Target inode number: */
	__le64			d_inum;

	/*
	 * Copy of mode bits 12-15 from the target inode - so userspace can get
	 * the filetype without having to do a stat()
	 */
	__u8			d_type;

	__u8			d_name[];
} __attribute__((packed));
BKEY_VAL_TYPE(dirent,		BCH_DIRENT);

/* Xattrs */

enum {
	BCH_XATTR		= 128,
	BCH_XATTR_WHITEOUT	= 129,
};

#define BCH_XATTR_INDEX_USER			0
#define BCH_XATTR_INDEX_POSIX_ACL_ACCESS	1
#define BCH_XATTR_INDEX_POSIX_ACL_DEFAULT	2
#define BCH_XATTR_INDEX_TRUSTED			3
#define BCH_XATTR_INDEX_SECURITY	        4

struct bch_xattr {
	struct bch_val		v;
	__u8			x_type;
	__u8			x_name_len;
	__le16			x_val_len;
	__u8			x_name[];
} __attribute__((packed));
BKEY_VAL_TYPE(xattr,		BCH_XATTR);

/* Superblock */

/* Version 0: Cache device
 * Version 1: Backing device
 * Version 2: Seed pointer into btree node checksum
 * Version 3: Cache device with new UUID format
 * Version 4: Backing device with data offset
 * Version 5: All the incompat changes
 * Version 6: Cache device UUIDs all in superblock, another incompat bset change
 * Version 7: Encryption (expanded checksum fields), other random things
 */
#define BCACHE_SB_VERSION_CDEV_V0	0
#define BCACHE_SB_VERSION_BDEV		1
#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3
#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4
#define BCACHE_SB_VERSION_CDEV_V2	5
#define BCACHE_SB_VERSION_CDEV_V3	6
#define BCACHE_SB_VERSION_CDEV_V4	7
#define BCACHE_SB_VERSION_CDEV		7
#define BCACHE_SB_MAX_VERSION		7

#define BCH_SB_SECTOR			8
#define BCH_SB_LABEL_SIZE		32
#define BCH_SB_MEMBERS_MAX		64 /* XXX kill */

struct bch_member {
	uuid_le			uuid;
	__le64			nbuckets;	/* device size */
	__le16			first_bucket;   /* index of first bucket used */
	__le16			bucket_size;	/* sectors */
	__le32			pad;
	__le64			last_mount;	/* time_t */

	__le64			flags[2];
};

LE64_BITMASK(BCH_MEMBER_STATE,		struct bch_member, flags[0],  0,  4)
LE64_BITMASK(BCH_MEMBER_TIER,		struct bch_member, flags[0],  4,  8)
LE64_BITMASK(BCH_MEMBER_HAS_METADATA,	struct bch_member, flags[0],  8,  9)
LE64_BITMASK(BCH_MEMBER_HAS_DATA,	struct bch_member, flags[0],  9, 10)
LE64_BITMASK(BCH_MEMBER_REPLACEMENT,	struct bch_member, flags[0], 10, 14)
LE64_BITMASK(BCH_MEMBER_DISCARD,	struct bch_member, flags[0], 14, 15);

#if 0
LE64_BITMASK(BCH_MEMBER_NR_READ_ERRORS,	struct bch_member, flags[1], 0,  20);
LE64_BITMASK(BCH_MEMBER_NR_WRITE_ERRORS,struct bch_member, flags[1], 20, 40);
#endif

enum bch_member_state {
	BCH_MEMBER_STATE_RW		= 0,
	BCH_MEMBER_STATE_RO		= 1,
	BCH_MEMBER_STATE_FAILED		= 2,
	BCH_MEMBER_STATE_SPARE		= 3,
	BCH_MEMBER_STATE_NR		= 4,
};

#define BCH_TIER_MAX			4U

enum cache_replacement {
	CACHE_REPLACEMENT_LRU		= 0,
	CACHE_REPLACEMENT_FIFO		= 1,
	CACHE_REPLACEMENT_RANDOM	= 2,
	CACHE_REPLACEMENT_NR		= 3,
};

struct bch_sb_layout {
	uuid_le			magic;	/* bcache superblock UUID */
	__u8			layout_type;
	__u8			sb_max_size_bits; /* base 2 of 512 byte sectors */
	__u8			nr_superblocks;
	__u8			pad[5];
	__u64			sb_offset[61];
} __attribute__((packed));

#define BCH_SB_LAYOUT_SECTOR	7

struct bch_sb_field {
	__u64			_data[0];
	__le32			u64s;
	__le32			type;
};

enum bch_sb_field_type {
	BCH_SB_FIELD_journal	= 0,
	BCH_SB_FIELD_members	= 1,
	BCH_SB_FIELD_crypt	= 2,
	BCH_SB_FIELD_NR		= 3,
};

struct bch_sb_field_journal {
	struct bch_sb_field	field;
	__le64			buckets[0];
};

struct bch_sb_field_members {
	struct bch_sb_field	field;
	struct bch_member	members[0];
};

/* Crypto: */

struct nonce {
	__le32			d[4];
};

struct bch_key {
	__le64			key[4];
};

#define BCH_KEY_MAGIC					\
	(((u64) 'b' <<  0)|((u64) 'c' <<  8)|		\
	 ((u64) 'h' << 16)|((u64) '*' << 24)|		\
	 ((u64) '*' << 32)|((u64) 'k' << 40)|		\
	 ((u64) 'e' << 48)|((u64) 'y' << 56))

struct bch_encrypted_key {
	__le64			magic;
	struct bch_key		key;
};

/*
 * If this field is present in the superblock, it stores an encryption key which
 * is used encrypt all other data/metadata. The key will normally be encrypted
 * with the key userspace provides, but if encryption has been turned off we'll
 * just store the master key unencrypted in the superblock so we can access the
 * previously encrypted data.
 */
struct bch_sb_field_crypt {
	struct bch_sb_field	field;

	__le64			flags;
	__le64			kdf_flags;
	struct bch_encrypted_key key;
};

LE64_BITMASK(BCH_CRYPT_KDF_TYPE,	struct bch_sb_field_crypt, flags, 0, 4);

enum bch_kdf_types {
	BCH_KDF_SCRYPT		= 0,
	BCH_KDF_NR		= 1,
};

/* stored as base 2 log of scrypt params: */
LE64_BITMASK(BCH_KDF_SCRYPT_N,	struct bch_sb_field_crypt, kdf_flags,  0, 16);
LE64_BITMASK(BCH_KDF_SCRYPT_R,	struct bch_sb_field_crypt, kdf_flags, 16, 32);
LE64_BITMASK(BCH_KDF_SCRYPT_P,	struct bch_sb_field_crypt, kdf_flags, 32, 48);

/*
 * @offset	- sector where this sb was written
 * @version	- on disk format version
 * @magic	- identifies as a bcache superblock (BCACHE_MAGIC)
 * @seq		- incremented each time superblock is written
 * @uuid	- used for generating various magic numbers and identifying
 *                member devices, never changes
 * @user_uuid	- user visible UUID, may be changed
 * @label	- filesystem label
 * @seq		- identifies most recent superblock, incremented each time
 *		  superblock is written
 * @features	- enabled incompatible features
 */
struct bch_sb {
	struct bch_csum		csum;
	__le64			version;
	uuid_le			magic;
	uuid_le			uuid;
	uuid_le			user_uuid;
	__u8			label[BCH_SB_LABEL_SIZE];
	__le64			offset;
	__le64			seq;

	__le16			block_size;
	__u8			dev_idx;
	__u8			nr_devices;
	__le32			u64s;

	__le64			time_base_lo;
	__le32			time_base_hi;
	__le32			time_precision;

	__le64			flags[8];
	__le64			features[2];
	__le64			compat[2];

	struct bch_sb_layout	layout;

	union {
		struct bch_sb_field start[0];
		__le64		_data[0];
	};
} __attribute__((packed, aligned(8)));

/*
 * Flags:
 * BCH_SB_INITALIZED	- set on first mount
 * BCH_SB_CLEAN		- did we shut down cleanly? Just a hint, doesn't affect
 *			  behaviour of mount/recovery path:
 * BCH_SB_INODE_32BIT	- limit inode numbers to 32 bits
 * BCH_SB_128_BIT_MACS	- 128 bit macs instead of 80
 * BCH_SB_ENCRYPTION_TYPE - if nonzero encryption is enabled; overrides
 *			   DATA/META_CSUM_TYPE. Also indicates encryption
 *			   algorithm in use, if/when we get more than one
 */

LE64_BITMASK(BCH_SB_INITIALIZED,	struct bch_sb, flags[0],  0,  1);
LE64_BITMASK(BCH_SB_CLEAN,		struct bch_sb, flags[0],  1,  2);
LE64_BITMASK(BCH_SB_CSUM_TYPE,		struct bch_sb, flags[0],  2,  8);
LE64_BITMASK(BCH_SB_ERROR_ACTION,	struct bch_sb, flags[0],  8, 12);

LE64_BITMASK(BCH_SB_BTREE_NODE_SIZE,	struct bch_sb, flags[0], 12, 28);

LE64_BITMASK(BCH_SB_GC_RESERVE,		struct bch_sb, flags[0], 28, 33);
LE64_BITMASK(BCH_SB_ROOT_RESERVE,	struct bch_sb, flags[0], 33, 40);

LE64_BITMASK(BCH_SB_META_CSUM_TYPE,	struct bch_sb, flags[0], 40, 44);
LE64_BITMASK(BCH_SB_DATA_CSUM_TYPE,	struct bch_sb, flags[0], 44, 48);

LE64_BITMASK(BCH_SB_META_REPLICAS_WANT,	struct bch_sb, flags[0], 48, 52);
LE64_BITMASK(BCH_SB_DATA_REPLICAS_WANT,	struct bch_sb, flags[0], 52, 56);

LE64_BITMASK(BCH_SB_META_REPLICAS_HAVE,	struct bch_sb, flags[0], 56, 60);
LE64_BITMASK(BCH_SB_DATA_REPLICAS_HAVE,	struct bch_sb, flags[0], 60, 64);

LE64_BITMASK(BCH_SB_STR_HASH_TYPE,	struct bch_sb, flags[1],  0,  4);
LE64_BITMASK(BCH_SB_COMPRESSION_TYPE,	struct bch_sb, flags[1],  4,  8);
LE64_BITMASK(BCH_SB_INODE_32BIT,	struct bch_sb, flags[1],  8,  9);

LE64_BITMASK(BCH_SB_128_BIT_MACS,	struct bch_sb, flags[1],  9, 10);
LE64_BITMASK(BCH_SB_ENCRYPTION_TYPE,	struct bch_sb, flags[1], 10, 14);
LE64_BITMASK(BCH_SB_JOURNAL_ENTRY_SIZE,	struct bch_sb, flags[1], 14, 20);

LE64_BITMASK(BCH_SB_META_REPLICAS_REQ,	struct bch_sb, flags[1], 20, 24);
LE64_BITMASK(BCH_SB_DATA_REPLICAS_REQ,	struct bch_sb, flags[1], 24, 28);

/* Features: */
enum bch_sb_features {
	BCH_FEATURE_LZ4			= 0,
	BCH_FEATURE_GZIP		= 1,
};

/* options: */

#define BCH_REPLICAS_MAX		4U

#if 0
#define BCH_ERROR_ACTIONS()					\
	x(BCH_ON_ERROR_CONTINUE,	0, "continue")		\
	x(BCH_ON_ERROR_RO,		1, "remount-ro")	\
	x(BCH_ON_ERROR_PANIC,		2, "panic")		\
	x(BCH_NR_ERROR_ACTIONS,		3, NULL)

enum bch_error_actions {
#define x(_opt, _nr, _str)	_opt = _nr,
	BCH_ERROR_ACTIONS()
#undef x
};
#endif

enum bch_error_actions {
	BCH_ON_ERROR_CONTINUE		= 0,
	BCH_ON_ERROR_RO			= 1,
	BCH_ON_ERROR_PANIC		= 2,
	BCH_NR_ERROR_ACTIONS		= 3,
};

enum bch_csum_opts {
	BCH_CSUM_OPT_NONE		= 0,
	BCH_CSUM_OPT_CRC32C		= 1,
	BCH_CSUM_OPT_CRC64		= 2,
	BCH_CSUM_OPT_NR			= 3,
};

enum bch_str_hash_opts {
	BCH_STR_HASH_CRC32C		= 0,
	BCH_STR_HASH_CRC64		= 1,
	BCH_STR_HASH_SIPHASH		= 2,
	BCH_STR_HASH_NR			= 3,
};

enum bch_compression_opts {
	BCH_COMPRESSION_NONE		= 0,
	BCH_COMPRESSION_LZ4		= 1,
	BCH_COMPRESSION_GZIP		= 2,
	BCH_COMPRESSION_NR		= 3,
};

/* backing device specific stuff: */

struct backingdev_sb {
	__le64			csum;
	__le64			offset;	/* sector where this sb was written */
	__le64			version; /* of on disk format */

	uuid_le			magic;	/* bcache superblock UUID */

	uuid_le			disk_uuid;

	/*
	 * Internal cache set UUID - xored with various magic numbers and thus
	 * must never change:
	 */
	union {
		uuid_le		set_uuid;
		__le64		set_magic;
	};
	__u8			label[BCH_SB_LABEL_SIZE];

	__le64			flags;

	/* Incremented each time superblock is written: */
	__le64			seq;

	/*
	 * User visible UUID for identifying the cache set the user is allowed
	 * to change:
	 *
	 * XXX hooked up?
	 */
	uuid_le			user_uuid;
	__le64			pad1[6];

	__le64			data_offset;
	__le16			block_size;	/* sectors */
	__le16			pad2[3];

	__le32			last_mount;	/* time_t */
	__le16			pad3;
	/* size of variable length portion - always 0 for backingdev superblock */
	__le16			u64s;
	__u64			_data[0];
};

LE64_BITMASK(BDEV_CACHE_MODE,		struct backingdev_sb, flags, 0, 4);
#define CACHE_MODE_WRITETHROUGH		0U
#define CACHE_MODE_WRITEBACK		1U
#define CACHE_MODE_WRITEAROUND		2U
#define CACHE_MODE_NONE			3U

LE64_BITMASK(BDEV_STATE,		struct backingdev_sb, flags, 61, 63);
#define BDEV_STATE_NONE			0U
#define BDEV_STATE_CLEAN		1U
#define BDEV_STATE_DIRTY		2U
#define BDEV_STATE_STALE		3U

#define BDEV_DATA_START_DEFAULT		16	/* sectors */

static inline _Bool __SB_IS_BDEV(__u64 version)
{
	return version == BCACHE_SB_VERSION_BDEV
		|| version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET;
}

static inline _Bool SB_IS_BDEV(const struct bch_sb *sb)
{
	return __SB_IS_BDEV(sb->version);
}

/*
 * Magic numbers
 *
 * The various other data structures have their own magic numbers, which are
 * xored with the first part of the cache set's UUID
 */

#define BCACHE_MAGIC							\
	UUID_LE(0xf67385c6, 0x1a4e, 0xca45,				\
		0x82, 0x65, 0xf5, 0x7f, 0x48, 0xba, 0x6d, 0x81)

#define BCACHE_STATFS_MAGIC		0xca451a4e

#define JSET_MAGIC		__cpu_to_le64(0x245235c1a3625032ULL)
#define PSET_MAGIC		__cpu_to_le64(0x6750e15f87337f91ULL)
#define BSET_MAGIC		__cpu_to_le64(0x90135c78b99e07f5ULL)

static inline __le64 __bch_sb_magic(struct bch_sb *sb)
{
	__le64 ret;
	memcpy(&ret, &sb->uuid, sizeof(ret));
	return ret;
}

static inline __u64 __jset_magic(struct bch_sb *sb)
{
	return __le64_to_cpu(__bch_sb_magic(sb) ^ JSET_MAGIC);
}

static inline __u64 __pset_magic(struct bch_sb *sb)
{
	return __le64_to_cpu(__bch_sb_magic(sb) ^ PSET_MAGIC);
}

static inline __u64 __bset_magic(struct bch_sb *sb)
{
	return __le64_to_cpu(__bch_sb_magic(sb) ^ BSET_MAGIC);
}

/* Journal */

#define BCACHE_JSET_VERSION_UUIDv1	1
#define BCACHE_JSET_VERSION_UUID	1	/* Always latest UUID format */
#define BCACHE_JSET_VERSION_JKEYS	2
#define BCACHE_JSET_VERSION		2

struct jset_entry {
	__le16			u64s;
	__u8			btree_id;
	__u8			level;
	__le32			flags; /* designates what this jset holds */

	union {
		struct bkey_i	start[0];
		__u64		_data[0];
	};
};

#define JSET_KEYS_U64s	(sizeof(struct jset_entry) / sizeof(__u64))

LE32_BITMASK(JOURNAL_ENTRY_TYPE,	struct jset_entry, flags, 0, 8);
enum {
	JOURNAL_ENTRY_BTREE_KEYS	= 0,
	JOURNAL_ENTRY_BTREE_ROOT	= 1,
	JOURNAL_ENTRY_PRIO_PTRS		= 2,

	/*
	 * Journal sequence numbers can be blacklisted: bsets record the max
	 * sequence number of all the journal entries they contain updates for,
	 * so that on recovery we can ignore those bsets that contain index
	 * updates newer that what made it into the journal.
	 *
	 * This means that we can't reuse that journal_seq - we have to skip it,
	 * and then record that we skipped it so that the next time we crash and
	 * recover we don't think there was a missing journal entry.
	 */
	JOURNAL_ENTRY_JOURNAL_SEQ_BLACKLISTED = 3,
};

/*
 * On disk format for a journal entry:
 * seq is monotonically increasing; every journal entry has its own unique
 * sequence number.
 *
 * last_seq is the oldest journal entry that still has keys the btree hasn't
 * flushed to disk yet.
 *
 * version is for on disk format changes.
 */
struct jset {
	struct bch_csum		csum;

	__le64			magic;
	__le64			seq;
	__le32			version;
	__le32			flags;

	__le32			u64s; /* size of d[] in u64s */

	__u8			encrypted_start[0];

	__le16			read_clock;
	__le16			write_clock;

	/* Sequence number of oldest dirty journal entry */
	__le64			last_seq;


	union {
		struct jset_entry start[0];
		__u64		_data[0];
	};
} __attribute__((packed));

LE32_BITMASK(JSET_CSUM_TYPE,	struct jset, flags, 0, 4);
LE32_BITMASK(JSET_BIG_ENDIAN,	struct jset, flags, 4, 5);

#define BCH_JOURNAL_BUCKETS_MIN		20

/* Bucket prios/gens */

struct prio_set {
	struct bch_csum		csum;

	__le64			magic;
	__le32			nonce[3];
	__le16			version;
	__le16			flags;

	__u8			encrypted_start[0];

	__le64			next_bucket;

	struct bucket_disk {
		__le16		read_prio;
		__le16		write_prio;
		__u8		gen;
	} __attribute__((packed)) data[];
} __attribute__((packed));

LE32_BITMASK(PSET_CSUM_TYPE,	struct prio_set, flags, 0, 4);

/* Btree: */

#define DEFINE_BCH_BTREE_IDS()					\
	DEF_BTREE_ID(EXTENTS, 0, "extents")			\
	DEF_BTREE_ID(INODES,  1, "inodes")			\
	DEF_BTREE_ID(DIRENTS, 2, "dirents")			\
	DEF_BTREE_ID(XATTRS,  3, "xattrs")

#define DEF_BTREE_ID(kwd, val, name) BTREE_ID_##kwd = val,

enum btree_id {
	DEFINE_BCH_BTREE_IDS()
	BTREE_ID_NR
};

#undef DEF_BTREE_ID

#define BTREE_MAX_DEPTH		4U

/* Btree nodes */

/* Version 1: Seed pointer into btree node checksum
 */
#define BCACHE_BSET_CSUM		1
#define BCACHE_BSET_KEY_v1		2
#define BCACHE_BSET_JOURNAL_SEQ		3
#define BCACHE_BSET_VERSION		3

/*
 * Btree nodes
 *
 * On disk a btree node is a list/log of these; within each set the keys are
 * sorted
 */
struct bset {
	__le64			seq;

	/*
	 * Highest journal entry this bset contains keys for.
	 * If on recovery we don't see that journal entry, this bset is ignored:
	 * this allows us to preserve the order of all index updates after a
	 * crash, since the journal records a total order of all index updates
	 * and anything that didn't make it to the journal doesn't get used.
	 */
	__le64			journal_seq;

	__le32			flags;
	__le16			version;
	__le16			u64s; /* count of d[] in u64s */

	union {
		struct bkey_packed start[0];
		__u64		_data[0];
	};
} __attribute__((packed));

LE32_BITMASK(BSET_CSUM_TYPE,	struct bset, flags, 0, 4);

LE32_BITMASK(BSET_BIG_ENDIAN,	struct bset, flags, 4, 5);
LE32_BITMASK(BSET_SEPARATE_WHITEOUTS,
				struct bset, flags, 5, 6);

struct btree_node {
	struct bch_csum		csum;
	__le64			magic;

	/* this flags field is encrypted, unlike bset->flags: */
	__le64			flags;

	/* Closed interval: */
	struct bpos		min_key;
	struct bpos		max_key;
	struct bch_extent_ptr	ptr;
	struct bkey_format	format;

	union {
	struct bset		keys;
	struct {
		__u8		pad[22];
		__le16		u64s;
		__u64		_data[0];

	};
	};
} __attribute__((packed));

LE64_BITMASK(BTREE_NODE_ID,	struct btree_node, flags, 0, 4);
LE64_BITMASK(BTREE_NODE_LEVEL,	struct btree_node, flags, 4, 8);

struct btree_node_entry {
	struct bch_csum		csum;

	union {
	struct bset		keys;
	struct {
		__u8		pad[22];
		__le16		u64s;
		__u64		_data[0];

	};
	};
} __attribute__((packed));

/* OBSOLETE */

#define BITMASK(name, type, field, offset, end)				\
static const unsigned	name##_OFFSET = offset;				\
static const unsigned	name##_BITS = (end - offset);			\
static const __u64	name##_MAX = (1ULL << (end - offset)) - 1;	\
									\
static inline __u64 name(const type *k)					\
{ return (k->field >> offset) & ~(~0ULL << (end - offset)); }		\
									\
static inline void SET_##name(type *k, __u64 v)				\
{									\
	k->field &= ~(~(~0ULL << (end - offset)) << offset);		\
	k->field |= (v & ~(~0ULL << (end - offset))) << offset;		\
}

struct bkey_v0 {
	__u64	high;
	__u64	low;
	__u64	ptr[];
};

#define KEY0_FIELD(name, field, offset, size)				\
	BITMASK(name, struct bkey_v0, field, offset, size)

KEY0_FIELD(KEY0_PTRS,		high, 60, 63)
KEY0_FIELD(KEY0_CSUM,		high, 56, 58)
KEY0_FIELD(KEY0_DIRTY,		high, 36, 37)

KEY0_FIELD(KEY0_SIZE,		high, 20, 36)
KEY0_FIELD(KEY0_INODE,		high, 0,  20)

static inline unsigned long bkey_v0_u64s(const struct bkey_v0 *k)
{
	return (sizeof(struct bkey_v0) / sizeof(__u64)) + KEY0_PTRS(k);
}

static inline struct bkey_v0 *bkey_v0_next(const struct bkey_v0 *k)
{
	__u64 *d = (__u64 *) k;

	return (struct bkey_v0 *) (d + bkey_v0_u64s(k));
}

struct jset_v0 {
	__u64			csum;
	__u64			magic;
	__u64			seq;
	__u32			version;
	__u32			keys;

	__u64			last_seq;

	__BKEY_PADDED(uuid_bucket, 4);
	__BKEY_PADDED(btree_root, 4);
	__u16			btree_level;
	__u16			pad[3];

	__u64			prio_bucket[64];

	union {
		struct bkey	start[0];
		__u64		d[0];
	};
};

/* UUIDS - per backing device/flash only volume metadata */

struct uuid_entry_v0 {
	uuid_le		uuid;
	__u8		label[32];
	__u32		first_reg;
	__u32		last_reg;
	__u32		invalidated;
	__u32		pad;
};

struct uuid_entry {
	union {
		struct {
			uuid_le	uuid;
			__u8	label[32];
			__u32	first_reg;
			__u32	last_reg;
			__u32	invalidated;

			__u32	flags;
			/* Size of flash only volumes */
			__u64	sectors;
		};

		__u8		pad[128];
	};
};

BITMASK(UUID_FLASH_ONLY,	struct uuid_entry, flags, 0, 1);

#ifdef __cplusplus
}
#endif
#endif /* _LINUX_BCACHE_H */

/* vim: set foldnestmax=2: */