summaryrefslogtreecommitdiffstats
path: root/fs/bcachefs/bcachefs.h
blob: c711d4c27a03f6ecde9a834e4c8cb42e72a4c39d (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _BCACHEFS_H
#define _BCACHEFS_H

/*
 * SOME HIGH LEVEL CODE DOCUMENTATION:
 *
 * Bcache mostly works with cache sets, cache devices, and backing devices.
 *
 * Support for multiple cache devices hasn't quite been finished off yet, but
 * it's about 95% plumbed through. A cache set and its cache devices is sort of
 * like a md raid array and its component devices. Most of the code doesn't care
 * about individual cache devices, the main abstraction is the cache set.
 *
 * Multiple cache devices is intended to give us the ability to mirror dirty
 * cached data and metadata, without mirroring clean cached data.
 *
 * Backing devices are different, in that they have a lifetime independent of a
 * cache set. When you register a newly formatted backing device it'll come up
 * in passthrough mode, and then you can attach and detach a backing device from
 * a cache set at runtime - while it's mounted and in use. Detaching implicitly
 * invalidates any cached data for that backing device.
 *
 * A cache set can have multiple (many) backing devices attached to it.
 *
 * There's also flash only volumes - this is the reason for the distinction
 * between struct cached_dev and struct bcache_device. A flash only volume
 * works much like a bcache device that has a backing device, except the
 * "cached" data is always dirty. The end result is that we get thin
 * provisioning with very little additional code.
 *
 * Flash only volumes work but they're not production ready because the moving
 * garbage collector needs more work. More on that later.
 *
 * BUCKETS/ALLOCATION:
 *
 * Bcache is primarily designed for caching, which means that in normal
 * operation all of our available space will be allocated. Thus, we need an
 * efficient way of deleting things from the cache so we can write new things to
 * it.
 *
 * To do this, we first divide the cache device up into buckets. A bucket is the
 * unit of allocation; they're typically around 1 mb - anywhere from 128k to 2M+
 * works efficiently.
 *
 * Each bucket has a 16 bit priority, and an 8 bit generation associated with
 * it. The gens and priorities for all the buckets are stored contiguously and
 * packed on disk (in a linked list of buckets - aside from the superblock, all
 * of bcache's metadata is stored in buckets).
 *
 * The priority is used to implement an LRU. We reset a bucket's priority when
 * we allocate it or on cache it, and every so often we decrement the priority
 * of each bucket. It could be used to implement something more sophisticated,
 * if anyone ever gets around to it.
 *
 * The generation is used for invalidating buckets. Each pointer also has an 8
 * bit generation embedded in it; for a pointer to be considered valid, its gen
 * must match the gen of the bucket it points into.  Thus, to reuse a bucket all
 * we have to do is increment its gen (and write its new gen to disk; we batch
 * this up).
 *
 * Bcache is entirely COW - we never write twice to a bucket, even buckets that
 * contain metadata (including btree nodes).
 *
 * THE BTREE:
 *
 * Bcache is in large part design around the btree.
 *
 * At a high level, the btree is just an index of key -> ptr tuples.
 *
 * Keys represent extents, and thus have a size field. Keys also have a variable
 * number of pointers attached to them (potentially zero, which is handy for
 * invalidating the cache).
 *
 * The key itself is an inode:offset pair. The inode number corresponds to a
 * backing device or a flash only volume. The offset is the ending offset of the
 * extent within the inode - not the starting offset; this makes lookups
 * slightly more convenient.
 *
 * Pointers contain the cache device id, the offset on that device, and an 8 bit
 * generation number. More on the gen later.
 *
 * Index lookups are not fully abstracted - cache lookups in particular are
 * still somewhat mixed in with the btree code, but things are headed in that
 * direction.
 *
 * Updates are fairly well abstracted, though. There are two different ways of
 * updating the btree; insert and replace.
 *
 * BTREE_INSERT will just take a list of keys and insert them into the btree -
 * overwriting (possibly only partially) any extents they overlap with. This is
 * used to update the index after a write.
 *
 * BTREE_REPLACE is really cmpxchg(); it inserts a key into the btree iff it is
 * overwriting a key that matches another given key. This is used for inserting
 * data into the cache after a cache miss, and for background writeback, and for
 * the moving garbage collector.
 *
 * There is no "delete" operation; deleting things from the index is
 * accomplished by either by invalidating pointers (by incrementing a bucket's
 * gen) or by inserting a key with 0 pointers - which will overwrite anything
 * previously present at that location in the index.
 *
 * This means that there are always stale/invalid keys in the btree. They're
 * filtered out by the code that iterates through a btree node, and removed when
 * a btree node is rewritten.
 *
 * BTREE NODES:
 *
 * Our unit of allocation is a bucket, and we can't arbitrarily allocate and
 * free smaller than a bucket - so, that's how big our btree nodes are.
 *
 * (If buckets are really big we'll only use part of the bucket for a btree node
 * - no less than 1/4th - but a bucket still contains no more than a single
 * btree node. I'd actually like to change this, but for now we rely on the
 * bucket's gen for deleting btree nodes when we rewrite/split a node.)
 *
 * Anyways, btree nodes are big - big enough to be inefficient with a textbook
 * btree implementation.
 *
 * The way this is solved is that btree nodes are internally log structured; we
 * can append new keys to an existing btree node without rewriting it. This
 * means each set of keys we write is sorted, but the node is not.
 *
 * We maintain this log structure in memory - keeping 1Mb of keys sorted would
 * be expensive, and we have to distinguish between the keys we have written and
 * the keys we haven't. So to do a lookup in a btree node, we have to search
 * each sorted set. But we do merge written sets together lazily, so the cost of
 * these extra searches is quite low (normally most of the keys in a btree node
 * will be in one big set, and then there'll be one or two sets that are much
 * smaller).
 *
 * This log structure makes bcache's btree more of a hybrid between a
 * conventional btree and a compacting data structure, with some of the
 * advantages of both.
 *
 * GARBAGE COLLECTION:
 *
 * We can't just invalidate any bucket - it might contain dirty data or
 * metadata. If it once contained dirty data, other writes might overwrite it
 * later, leaving no valid pointers into that bucket in the index.
 *
 * Thus, the primary purpose of garbage collection is to find buckets to reuse.
 * It also counts how much valid data it each bucket currently contains, so that
 * allocation can reuse buckets sooner when they've been mostly overwritten.
 *
 * It also does some things that are really internal to the btree
 * implementation. If a btree node contains pointers that are stale by more than
 * some threshold, it rewrites the btree node to avoid the bucket's generation
 * wrapping around. It also merges adjacent btree nodes if they're empty enough.
 *
 * THE JOURNAL:
 *
 * Bcache's journal is not necessary for consistency; we always strictly
 * order metadata writes so that the btree and everything else is consistent on
 * disk in the event of an unclean shutdown, and in fact bcache had writeback
 * caching (with recovery from unclean shutdown) before journalling was
 * implemented.
 *
 * Rather, the journal is purely a performance optimization; we can't complete a
 * write until we've updated the index on disk, otherwise the cache would be
 * inconsistent in the event of an unclean shutdown. This means that without the
 * journal, on random write workloads we constantly have to update all the leaf
 * nodes in the btree, and those writes will be mostly empty (appending at most
 * a few keys each) - highly inefficient in terms of amount of metadata writes,
 * and it puts more strain on the various btree resorting/compacting code.
 *
 * The journal is just a log of keys we've inserted; on startup we just reinsert
 * all the keys in the open journal entries. That means that when we're updating
 * a node in the btree, we can wait until a 4k block of keys fills up before
 * writing them out.
 *
 * For simplicity, we only journal updates to leaf nodes; updates to parent
 * nodes are rare enough (since our leaf nodes are huge) that it wasn't worth
 * the complexity to deal with journalling them (in particular, journal replay)
 * - updates to non leaf nodes just happen synchronously (see btree_split()).
 */

#undef pr_fmt
#ifdef __KERNEL__
#define pr_fmt(fmt) "bcachefs: %s() " fmt "\n", __func__
#else
#define pr_fmt(fmt) "%s() " fmt "\n", __func__
#endif

#include <linux/backing-dev-defs.h>
#include <linux/bug.h>
#include <linux/bio.h>
#include <linux/closure.h>
#include <linux/kobject.h>
#include <linux/list.h>
#include <linux/math64.h>
#include <linux/mutex.h>
#include <linux/percpu-refcount.h>
#include <linux/percpu-rwsem.h>
#include <linux/refcount.h>
#include <linux/rhashtable.h>
#include <linux/rwsem.h>
#include <linux/semaphore.h>
#include <linux/seqlock.h>
#include <linux/shrinker.h>
#include <linux/srcu.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include <linux/zstd.h>

#include "bcachefs_format.h"
#include "disk_accounting_types.h"
#include "errcode.h"
#include "fifo.h"
#include "nocow_locking_types.h"
#include "opts.h"
#include "recovery_passes_types.h"
#include "sb-errors_types.h"
#include "seqmutex.h"
#include "time_stats.h"
#include "util.h"

#ifdef CONFIG_BCACHEFS_DEBUG
#define BCH_WRITE_REF_DEBUG
#endif

#ifndef dynamic_fault
#define dynamic_fault(...)		0
#endif

#define race_fault(...)			dynamic_fault("bcachefs:race")

#define count_event(_c, _name)	this_cpu_inc((_c)->counters[BCH_COUNTER_##_name])

#define trace_and_count(_c, _name, ...)					\
do {									\
	count_event(_c, _name);						\
	trace_##_name(__VA_ARGS__);					\
} while (0)

#define bch2_fs_init_fault(name)					\
	dynamic_fault("bcachefs:bch_fs_init:" name)
#define bch2_meta_read_fault(name)					\
	 dynamic_fault("bcachefs:meta:read:" name)
#define bch2_meta_write_fault(name)					\
	 dynamic_fault("bcachefs:meta:write:" name)

#ifdef __KERNEL__
#define BCACHEFS_LOG_PREFIX
#endif

#ifdef BCACHEFS_LOG_PREFIX

#define bch2_log_msg(_c, fmt)			"bcachefs (%s): " fmt, ((_c)->name)
#define bch2_fmt_dev(_ca, fmt)			"bcachefs (%s): " fmt "\n", ((_ca)->name)
#define bch2_fmt_dev_offset(_ca, _offset, fmt)	"bcachefs (%s sector %llu): " fmt "\n", ((_ca)->name), (_offset)
#define bch2_fmt_inum(_c, _inum, fmt)		"bcachefs (%s inum %llu): " fmt "\n", ((_c)->name), (_inum)
#define bch2_fmt_inum_offset(_c, _inum, _offset, fmt)			\
	 "bcachefs (%s inum %llu offset %llu): " fmt "\n", ((_c)->name), (_inum), (_offset)

#else

#define bch2_log_msg(_c, fmt)			fmt
#define bch2_fmt_dev(_ca, fmt)			"%s: " fmt "\n", ((_ca)->name)
#define bch2_fmt_dev_offset(_ca, _offset, fmt)	"%s sector %llu: " fmt "\n", ((_ca)->name), (_offset)
#define bch2_fmt_inum(_c, _inum, fmt)		"inum %llu: " fmt "\n", (_inum)
#define bch2_fmt_inum_offset(_c, _inum, _offset, fmt)				\
	 "inum %llu offset %llu: " fmt "\n", (_inum), (_offset)

#endif

#define bch2_fmt(_c, fmt)		bch2_log_msg(_c, fmt "\n")

void bch2_print_str(struct bch_fs *, const char *);

__printf(2, 3)
void bch2_print_opts(struct bch_opts *, const char *, ...);

__printf(2, 3)
void __bch2_print(struct bch_fs *c, const char *fmt, ...);

#define maybe_dev_to_fs(_c)	_Generic((_c),				\
	struct bch_dev *:	((struct bch_dev *) (_c))->fs,		\
	struct bch_fs *:	(_c))

#define bch2_print(_c, ...) __bch2_print(maybe_dev_to_fs(_c), __VA_ARGS__)

#define bch2_print_ratelimited(_c, ...)					\
do {									\
	static DEFINE_RATELIMIT_STATE(_rs,				\
				      DEFAULT_RATELIMIT_INTERVAL,	\
				      DEFAULT_RATELIMIT_BURST);		\
									\
	if (__ratelimit(&_rs))						\
		bch2_print(_c, __VA_ARGS__);				\
} while (0)

#define bch_info(c, fmt, ...) \
	bch2_print(c, KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_notice(c, fmt, ...) \
	bch2_print(c, KERN_NOTICE bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_warn(c, fmt, ...) \
	bch2_print(c, KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_warn_ratelimited(c, fmt, ...) \
	bch2_print_ratelimited(c, KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)

#define bch_err(c, fmt, ...) \
	bch2_print(c, KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_err_dev(ca, fmt, ...) \
	bch2_print(c, KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
#define bch_err_dev_offset(ca, _offset, fmt, ...) \
	bch2_print(c, KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
#define bch_err_inum(c, _inum, fmt, ...) \
	bch2_print(c, KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
#define bch_err_inum_offset(c, _inum, _offset, fmt, ...) \
	bch2_print(c, KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)

#define bch_err_ratelimited(c, fmt, ...) \
	bch2_print_ratelimited(c, KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_err_dev_ratelimited(ca, fmt, ...) \
	bch2_print_ratelimited(ca, KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
#define bch_err_dev_offset_ratelimited(ca, _offset, fmt, ...) \
	bch2_print_ratelimited(ca, KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
#define bch_err_inum_ratelimited(c, _inum, fmt, ...) \
	bch2_print_ratelimited(c, KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
#define bch_err_inum_offset_ratelimited(c, _inum, _offset, fmt, ...) \
	bch2_print_ratelimited(c, KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)

static inline bool should_print_err(int err)
{
	return err && !bch2_err_matches(err, BCH_ERR_transaction_restart);
}

#define bch_err_fn(_c, _ret)						\
do {									\
	if (should_print_err(_ret))					\
		bch_err(_c, "%s(): error %s", __func__, bch2_err_str(_ret));\
} while (0)

#define bch_err_fn_ratelimited(_c, _ret)				\
do {									\
	if (should_print_err(_ret))					\
		bch_err_ratelimited(_c, "%s(): error %s", __func__, bch2_err_str(_ret));\
} while (0)

#define bch_err_msg(_c, _ret, _msg, ...)				\
do {									\
	if (should_print_err(_ret))					\
		bch_err(_c, "%s(): error " _msg " %s", __func__,	\
			##__VA_ARGS__, bch2_err_str(_ret));		\
} while (0)

#define bch_verbose(c, fmt, ...)					\
do {									\
	if ((c)->opts.verbose)						\
		bch_info(c, fmt, ##__VA_ARGS__);			\
} while (0)

#define pr_verbose_init(opts, fmt, ...)					\
do {									\
	if (opt_get(opts, verbose))					\
		pr_info(fmt, ##__VA_ARGS__);				\
} while (0)

/* Parameters that are useful for debugging, but should always be compiled in: */
#define BCH_DEBUG_PARAMS_ALWAYS()					\
	BCH_DEBUG_PARAM(key_merging_disabled,				\
		"Disables merging of extents")				\
	BCH_DEBUG_PARAM(btree_node_merging_disabled,			\
		"Disables merging of btree nodes")			\
	BCH_DEBUG_PARAM(btree_gc_always_rewrite,			\
		"Causes mark and sweep to compact and rewrite every "	\
		"btree node it traverses")				\
	BCH_DEBUG_PARAM(btree_gc_rewrite_disabled,			\
		"Disables rewriting of btree nodes during mark and sweep")\
	BCH_DEBUG_PARAM(btree_shrinker_disabled,			\
		"Disables the shrinker callback for the btree node cache")\
	BCH_DEBUG_PARAM(verify_btree_ondisk,				\
		"Reread btree nodes at various points to verify the "	\
		"mergesort in the read path against modifications "	\
		"done in memory")					\
	BCH_DEBUG_PARAM(verify_all_btree_replicas,			\
		"When reading btree nodes, read all replicas and "	\
		"compare them")						\
	BCH_DEBUG_PARAM(backpointers_no_use_write_buffer,		\
		"Don't use the write buffer for backpointers, enabling "\
		"extra runtime checks")

/* Parameters that should only be compiled in debug mode: */
#define BCH_DEBUG_PARAMS_DEBUG()					\
	BCH_DEBUG_PARAM(expensive_debug_checks,				\
		"Enables various runtime debugging checks that "	\
		"significantly affect performance")			\
	BCH_DEBUG_PARAM(debug_check_iterators,				\
		"Enables extra verification for btree iterators")	\
	BCH_DEBUG_PARAM(debug_check_btree_accounting,			\
		"Verify btree accounting for keys within a node")	\
	BCH_DEBUG_PARAM(journal_seq_verify,				\
		"Store the journal sequence number in the version "	\
		"number of every btree key, and verify that btree "	\
		"update ordering is preserved during recovery")		\
	BCH_DEBUG_PARAM(inject_invalid_keys,				\
		"Store the journal sequence number in the version "	\
		"number of every btree key, and verify that btree "	\
		"update ordering is preserved during recovery")		\
	BCH_DEBUG_PARAM(test_alloc_startup,				\
		"Force allocator startup to use the slowpath where it"	\
		"can't find enough free buckets without invalidating"	\
		"cached data")						\
	BCH_DEBUG_PARAM(force_reconstruct_read,				\
		"Force reads to use the reconstruct path, when reading"	\
		"from erasure coded extents")				\
	BCH_DEBUG_PARAM(test_restart_gc,				\
		"Test restarting mark and sweep gc when bucket gens change")

#define BCH_DEBUG_PARAMS_ALL() BCH_DEBUG_PARAMS_ALWAYS() BCH_DEBUG_PARAMS_DEBUG()

#ifdef CONFIG_BCACHEFS_DEBUG
#define BCH_DEBUG_PARAMS() BCH_DEBUG_PARAMS_ALL()
#else
#define BCH_DEBUG_PARAMS() BCH_DEBUG_PARAMS_ALWAYS()
#endif

#define BCH_DEBUG_PARAM(name, description) extern bool bch2_##name;
BCH_DEBUG_PARAMS()
#undef BCH_DEBUG_PARAM

#ifndef CONFIG_BCACHEFS_DEBUG
#define BCH_DEBUG_PARAM(name, description) static const __maybe_unused bool bch2_##name;
BCH_DEBUG_PARAMS_DEBUG()
#undef BCH_DEBUG_PARAM
#endif

#define BCH_TIME_STATS()			\
	x(btree_node_mem_alloc)			\
	x(btree_node_split)			\
	x(btree_node_compact)			\
	x(btree_node_merge)			\
	x(btree_node_sort)			\
	x(btree_node_read)			\
	x(btree_node_read_done)			\
	x(btree_interior_update_foreground)	\
	x(btree_interior_update_total)		\
	x(btree_gc)				\
	x(data_write)				\
	x(data_read)				\
	x(data_promote)				\
	x(journal_flush_write)			\
	x(journal_noflush_write)		\
	x(journal_flush_seq)			\
	x(blocked_journal_low_on_space)		\
	x(blocked_journal_low_on_pin)		\
	x(blocked_journal_max_in_flight)	\
	x(blocked_key_cache_flush)		\
	x(blocked_allocate)			\
	x(blocked_allocate_open_bucket)		\
	x(blocked_write_buffer_full)		\
	x(nocow_lock_contended)

enum bch_time_stats {
#define x(name) BCH_TIME_##name,
	BCH_TIME_STATS()
#undef x
	BCH_TIME_STAT_NR
};

#include "alloc_types.h"
#include "btree_gc_types.h"
#include "btree_types.h"
#include "btree_node_scan_types.h"
#include "btree_write_buffer_types.h"
#include "buckets_types.h"
#include "buckets_waiting_for_journal_types.h"
#include "clock_types.h"
#include "disk_groups_types.h"
#include "ec_types.h"
#include "journal_types.h"
#include "keylist_types.h"
#include "quota_types.h"
#include "rebalance_types.h"
#include "replicas_types.h"
#include "sb-members_types.h"
#include "subvolume_types.h"
#include "super_types.h"
#include "thread_with_file_types.h"

/* Number of nodes btree coalesce will try to coalesce at once */
#define GC_MERGE_NODES		4U

/* Maximum number of nodes we might need to allocate atomically: */
#define BTREE_RESERVE_MAX	(BTREE_MAX_DEPTH + (BTREE_MAX_DEPTH - 1))

/* Size of the freelist we allocate btree nodes from: */
#define BTREE_NODE_RESERVE	(BTREE_RESERVE_MAX * 4)

#define BTREE_NODE_OPEN_BUCKET_RESERVE	(BTREE_RESERVE_MAX * BCH_REPLICAS_MAX)

struct btree;

struct io_count {
	u64			sectors[2][BCH_DATA_NR];
};

struct discard_in_flight {
	bool			in_progress:1;
	u64			bucket:63;
};

struct bch_dev {
	struct kobject		kobj;
#ifdef CONFIG_BCACHEFS_DEBUG
	atomic_long_t		ref;
	bool			dying;
	unsigned long		last_put;
#else
	struct percpu_ref	ref;
#endif
	struct completion	ref_completion;
	struct percpu_ref	io_ref;
	struct completion	io_ref_completion;

	struct bch_fs		*fs;

	u8			dev_idx;
	/*
	 * Cached version of this device's member info from superblock
	 * Committed by bch2_write_super() -> bch_fs_mi_update()
	 */
	struct bch_member_cpu	mi;
	atomic64_t		errors[BCH_MEMBER_ERROR_NR];

	__uuid_t		uuid;
	char			name[BDEVNAME_SIZE];

	struct bch_sb_handle	disk_sb;
	struct bch_sb		*sb_read_scratch;
	int			sb_write_error;
	dev_t			dev;
	atomic_t		flush_seq;

	struct bch_devs_mask	self;

	/*
	 * Buckets:
	 * Per-bucket arrays are protected by c->mark_lock, bucket_lock and
	 * gc_gens_lock, for device resize - holding any is sufficient for
	 * access: Or rcu_read_lock(), but only for dev_ptr_stale():
	 */
	GENRADIX(struct bucket)	buckets_gc;
	struct bucket_gens __rcu *bucket_gens;
	u8			*oldest_gen;
	unsigned long		*buckets_nouse;
	struct rw_semaphore	bucket_lock;

	struct bch_dev_usage __percpu	*usage;

	/* Allocator: */
	u64			new_fs_bucket_idx;
	u64			alloc_cursor[3];

	unsigned		nr_open_buckets;
	unsigned		nr_btree_reserve;

	size_t			inc_gen_needs_gc;
	size_t			inc_gen_really_needs_gc;
	size_t			buckets_waiting_on_journal;

	struct work_struct	invalidate_work;
	struct work_struct	discard_work;
	struct mutex		discard_buckets_in_flight_lock;
	DARRAY(struct discard_in_flight)	discard_buckets_in_flight;
	struct work_struct	discard_fast_work;

	atomic64_t		rebalance_work;

	struct journal_device	journal;
	u64			prev_journal_sector;

	struct work_struct	io_error_work;

	/* The rest of this all shows up in sysfs */
	atomic64_t		cur_latency[2];
	struct bch2_time_stats_quantiles io_latency[2];

#define CONGESTED_MAX		1024
	atomic_t		congested;
	u64			congested_last;

	struct io_count __percpu *io_done;
};

/*
 * initial_gc_unfixed
 * error
 * topology error
 */

#define BCH_FS_FLAGS()			\
	x(new_fs)			\
	x(started)			\
	x(btree_running)		\
	x(accounting_replay_done)	\
	x(may_go_rw)			\
	x(rw)				\
	x(was_rw)			\
	x(stopping)			\
	x(emergency_ro)			\
	x(going_ro)			\
	x(write_disable_complete)	\
	x(clean_shutdown)		\
	x(fsck_running)			\
	x(initial_gc_unfixed)		\
	x(need_delete_dead_snapshots)	\
	x(error)			\
	x(topology_error)		\
	x(errors_fixed)			\
	x(errors_not_fixed)		\
	x(no_invalid_checks)

enum bch_fs_flags {
#define x(n)		BCH_FS_##n,
	BCH_FS_FLAGS()
#undef x
};

struct btree_debug {
	unsigned		id;
};

#define BCH_TRANSACTIONS_NR 128

struct btree_transaction_stats {
	struct bch2_time_stats	duration;
	struct bch2_time_stats	lock_hold_times;
	struct mutex		lock;
	unsigned		nr_max_paths;
	unsigned		journal_entries_size;
	unsigned		max_mem;
	char			*max_paths_text;
};

struct bch_fs_pcpu {
	u64			sectors_available;
};

struct journal_seq_blacklist_table {
	size_t			nr;
	struct journal_seq_blacklist_table_entry {
		u64		start;
		u64		end;
		bool		dirty;
	}			entries[];
};

struct journal_keys {
	/* must match layout in darray_types.h */
	size_t			nr, size;
	struct journal_key {
		u64		journal_seq;
		u32		journal_offset;
		enum btree_id	btree_id:8;
		unsigned	level:8;
		bool		allocated;
		bool		overwritten;
		struct bkey_i	*k;
	}			*data;
	/*
	 * Gap buffer: instead of all the empty space in the array being at the
	 * end of the buffer - from @nr to @size - the empty space is at @gap.
	 * This means that sequential insertions are O(n) instead of O(n^2).
	 */
	size_t			gap;
	atomic_t		ref;
	bool			initial_ref_held;
};

struct btree_trans_buf {
	struct btree_trans	*trans;
};

#define BCACHEFS_ROOT_SUBVOL_INUM					\
	((subvol_inum) { BCACHEFS_ROOT_SUBVOL,	BCACHEFS_ROOT_INO })

#define BCH_WRITE_REFS()						\
	x(trans)							\
	x(write)							\
	x(promote)							\
	x(node_rewrite)							\
	x(stripe_create)						\
	x(stripe_delete)						\
	x(reflink)							\
	x(fallocate)							\
	x(fsync)							\
	x(dio_write)							\
	x(discard)							\
	x(discard_fast)							\
	x(invalidate)							\
	x(delete_dead_snapshots)					\
	x(gc_gens)							\
	x(snapshot_delete_pagecache)					\
	x(sysfs)							\
	x(btree_write_buffer)

enum bch_write_ref {
#define x(n) BCH_WRITE_REF_##n,
	BCH_WRITE_REFS()
#undef x
	BCH_WRITE_REF_NR,
};

struct bch_fs {
	struct closure		cl;

	struct list_head	list;
	struct kobject		kobj;
	struct kobject		counters_kobj;
	struct kobject		internal;
	struct kobject		opts_dir;
	struct kobject		time_stats;
	unsigned long		flags;

	int			minor;
	struct device		*chardev;
	struct super_block	*vfs_sb;
	dev_t			dev;
	char			name[40];
	struct stdio_redirect	*stdio;
	struct task_struct	*stdio_filter;

	/* ro/rw, add/remove/resize devices: */
	struct rw_semaphore	state_lock;

	/* Counts outstanding writes, for clean transition to read-only */
#ifdef BCH_WRITE_REF_DEBUG
	atomic_long_t		writes[BCH_WRITE_REF_NR];
#else
	struct percpu_ref	writes;
#endif
	/*
	 * Analagous to c->writes, for asynchronous ops that don't necessarily
	 * need fs to be read-write
	 */
	refcount_t		ro_ref;
	wait_queue_head_t	ro_ref_wait;

	struct work_struct	read_only_work;

	struct bch_dev __rcu	*devs[BCH_SB_MEMBERS_MAX];

	struct bch_accounting_mem accounting;

	struct bch_replicas_cpu replicas;
	struct bch_replicas_cpu replicas_gc;
	struct mutex		replicas_gc_lock;

	struct journal_entry_res btree_root_journal_res;
	struct journal_entry_res clock_journal_res;

	struct bch_disk_groups_cpu __rcu *disk_groups;

	struct bch_opts		opts;

	/* Updated by bch2_sb_update():*/
	struct {
		__uuid_t	uuid;
		__uuid_t	user_uuid;

		u16		version;
		u16		version_min;
		u16		version_upgrade_complete;

		u8		nr_devices;
		u8		clean;

		u8		encryption_type;

		u64		time_base_lo;
		u32		time_base_hi;
		unsigned	time_units_per_sec;
		unsigned	nsec_per_time_unit;
		u64		features;
		u64		compat;
		unsigned long	errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)];
		u64		btrees_lost_data;
	}			sb;


	struct bch_sb_handle	disk_sb;

	unsigned short		block_bits;	/* ilog2(block_size) */

	u16			btree_foreground_merge_threshold;

	struct closure		sb_write;
	struct mutex		sb_lock;

	/* snapshot.c: */
	struct snapshot_table __rcu *snapshots;
	struct mutex		snapshot_table_lock;
	struct rw_semaphore	snapshot_create_lock;

	struct work_struct	snapshot_delete_work;
	struct work_struct	snapshot_wait_for_pagecache_and_delete_work;
	snapshot_id_list	snapshots_unlinked;
	struct mutex		snapshots_unlinked_lock;

	/* BTREE CACHE */
	struct bio_set		btree_bio;
	struct workqueue_struct	*btree_read_complete_wq;
	struct workqueue_struct	*btree_write_submit_wq;

	struct btree_root	btree_roots_known[BTREE_ID_NR];
	DARRAY(struct btree_root) btree_roots_extra;
	struct mutex		btree_root_lock;

	struct btree_cache	btree_cache;

	/*
	 * Cache of allocated btree nodes - if we allocate a btree node and
	 * don't use it, if we free it that space can't be reused until going
	 * _all_ the way through the allocator (which exposes us to a livelock
	 * when allocating btree reserves fail halfway through) - instead, we
	 * can stick them here:
	 */
	struct btree_alloc	btree_reserve_cache[BTREE_NODE_RESERVE * 2];
	unsigned		btree_reserve_cache_nr;
	struct mutex		btree_reserve_cache_lock;

	mempool_t		btree_interior_update_pool;
	struct list_head	btree_interior_update_list;
	struct list_head	btree_interior_updates_unwritten;
	struct mutex		btree_interior_update_lock;
	struct closure_waitlist	btree_interior_update_wait;

	struct workqueue_struct	*btree_interior_update_worker;
	struct work_struct	btree_interior_update_work;

	struct workqueue_struct	*btree_node_rewrite_worker;

	struct list_head	pending_node_rewrites;
	struct mutex		pending_node_rewrites_lock;

	/* btree_io.c: */
	spinlock_t		btree_write_error_lock;
	struct btree_write_stats {
		atomic64_t	nr;
		atomic64_t	bytes;
	}			btree_write_stats[BTREE_WRITE_TYPE_NR];

	/* btree_iter.c: */
	struct seqmutex		btree_trans_lock;
	struct list_head	btree_trans_list;
	mempool_t		btree_trans_pool;
	mempool_t		btree_trans_mem_pool;
	struct btree_trans_buf  __percpu	*btree_trans_bufs;

	struct srcu_struct	btree_trans_barrier;
	bool			btree_trans_barrier_initialized;

	struct btree_key_cache	btree_key_cache;
	unsigned		btree_key_cache_btrees;

	struct btree_write_buffer btree_write_buffer;

	struct workqueue_struct	*btree_update_wq;
	struct workqueue_struct	*btree_io_complete_wq;
	/* copygc needs its own workqueue for index updates.. */
	struct workqueue_struct	*copygc_wq;
	/*
	 * Use a dedicated wq for write ref holder tasks. Required to avoid
	 * dependency problems with other wq tasks that can block on ref
	 * draining, such as read-only transition.
	 */
	struct workqueue_struct *write_ref_wq;

	/* ALLOCATION */
	struct bch_devs_mask	rw_devs[BCH_DATA_NR];
	unsigned long		rw_devs_change_count;

	u64			capacity; /* sectors */
	u64			reserved; /* sectors */

	/*
	 * When capacity _decreases_ (due to a disk being removed), we
	 * increment capacity_gen - this invalidates outstanding reservations
	 * and forces them to be revalidated
	 */
	u32			capacity_gen;
	unsigned		bucket_size_max;

	atomic64_t		sectors_available;
	struct mutex		sectors_available_lock;

	struct bch_fs_pcpu __percpu	*pcpu;

	struct percpu_rw_semaphore	mark_lock;

	seqcount_t			usage_lock;
	struct bch_fs_usage_base __percpu *usage;
	u64 __percpu		*online_reserved;

	unsigned long		allocator_last_stuck;

	struct io_clock		io_clock[2];

	/* JOURNAL SEQ BLACKLIST */
	struct journal_seq_blacklist_table *
				journal_seq_blacklist_table;

	/* ALLOCATOR */
	spinlock_t		freelist_lock;
	struct closure_waitlist	freelist_wait;

	open_bucket_idx_t	open_buckets_freelist;
	open_bucket_idx_t	open_buckets_nr_free;
	struct closure_waitlist	open_buckets_wait;
	struct open_bucket	open_buckets[OPEN_BUCKETS_COUNT];
	open_bucket_idx_t	open_buckets_hash[OPEN_BUCKETS_COUNT];

	open_bucket_idx_t	open_buckets_partial[OPEN_BUCKETS_COUNT];
	open_bucket_idx_t	open_buckets_partial_nr;

	struct write_point	btree_write_point;
	struct write_point	rebalance_write_point;

	struct write_point	write_points[WRITE_POINT_MAX];
	struct hlist_head	write_points_hash[WRITE_POINT_HASH_NR];
	struct mutex		write_points_hash_lock;
	unsigned		write_points_nr;

	struct buckets_waiting_for_journal buckets_waiting_for_journal;

	/* GARBAGE COLLECTION */
	struct work_struct	gc_gens_work;
	unsigned long		gc_count;

	enum btree_id		gc_gens_btree;
	struct bpos		gc_gens_pos;

	/*
	 * Tracks GC's progress - everything in the range [ZERO_KEY..gc_cur_pos]
	 * has been marked by GC.
	 *
	 * gc_cur_phase is a superset of btree_ids (BTREE_ID_extents etc.)
	 *
	 * Protected by gc_pos_lock. Only written to by GC thread, so GC thread
	 * can read without a lock.
	 */
	seqcount_t		gc_pos_lock;
	struct gc_pos		gc_pos;

	/*
	 * The allocation code needs gc_mark in struct bucket to be correct, but
	 * it's not while a gc is in progress.
	 */
	struct rw_semaphore	gc_lock;
	struct mutex		gc_gens_lock;

	/* IO PATH */
	struct semaphore	io_in_flight;
	struct bio_set		bio_read;
	struct bio_set		bio_read_split;
	struct bio_set		bio_write;
	struct bio_set		replica_set;
	struct mutex		bio_bounce_pages_lock;
	mempool_t		bio_bounce_pages;
	struct bucket_nocow_lock_table
				nocow_locks;
	struct rhashtable	promote_table;

	mempool_t		compression_bounce[2];
	mempool_t		compress_workspace[BCH_COMPRESSION_TYPE_NR];
	mempool_t		decompress_workspace;
	size_t			zstd_workspace_size;

	struct crypto_shash	*sha256;
	struct crypto_sync_skcipher *chacha20;
	struct crypto_shash	*poly1305;

	atomic64_t		key_version;

	mempool_t		large_bkey_pool;

	/* MOVE.C */
	struct list_head	moving_context_list;
	struct mutex		moving_context_lock;

	/* REBALANCE */
	struct bch_fs_rebalance	rebalance;

	/* COPYGC */
	struct task_struct	*copygc_thread;
	struct write_point	copygc_write_point;
	s64			copygc_wait_at;
	s64			copygc_wait;
	bool			copygc_running;
	wait_queue_head_t	copygc_running_wq;

	/* STRIPES: */
	GENRADIX(struct stripe) stripes;
	GENRADIX(struct gc_stripe) gc_stripes;

	struct hlist_head	ec_stripes_new[32];
	spinlock_t		ec_stripes_new_lock;

	ec_stripes_heap		ec_stripes_heap;
	struct mutex		ec_stripes_heap_lock;

	/* ERASURE CODING */
	struct list_head	ec_stripe_head_list;
	struct mutex		ec_stripe_head_lock;

	struct list_head	ec_stripe_new_list;
	struct mutex		ec_stripe_new_lock;
	wait_queue_head_t	ec_stripe_new_wait;

	struct work_struct	ec_stripe_create_work;
	u64			ec_stripe_hint;

	struct work_struct	ec_stripe_delete_work;

	struct bio_set		ec_bioset;

	/* REFLINK */
	reflink_gc_table	reflink_gc_table;
	size_t			reflink_gc_nr;

	/* fs.c */
	struct list_head	vfs_inodes_list;
	struct mutex		vfs_inodes_lock;
	struct rhashtable	vfs_inodes_table;

	/* VFS IO PATH - fs-io.c */
	struct bio_set		writepage_bioset;
	struct bio_set		dio_write_bioset;
	struct bio_set		dio_read_bioset;
	struct bio_set		nocow_flush_bioset;

	/* QUOTAS */
	struct bch_memquota_type quotas[QTYP_NR];

	/* RECOVERY */
	u64			journal_replay_seq_start;
	u64			journal_replay_seq_end;
	/*
	 * Two different uses:
	 * "Has this fsck pass?" - i.e. should this type of error be an
	 * emergency read-only
	 * And, in certain situations fsck will rewind to an earlier pass: used
	 * for signaling to the toplevel code which pass we want to run now.
	 */
	enum bch_recovery_pass	curr_recovery_pass;
	/* bitmask of recovery passes that we actually ran */
	u64			recovery_passes_complete;
	/* never rewinds version of curr_recovery_pass */
	enum bch_recovery_pass	recovery_pass_done;
	struct semaphore	online_fsck_mutex;

	/* DEBUG JUNK */
	struct dentry		*fs_debug_dir;
	struct dentry		*btree_debug_dir;
	struct btree_debug	btree_debug[BTREE_ID_NR];
	struct btree		*verify_data;
	struct btree_node	*verify_ondisk;
	struct mutex		verify_lock;

	u64			*unused_inode_hints;
	unsigned		inode_shard_bits;

	/*
	 * A btree node on disk could have too many bsets for an iterator to fit
	 * on the stack - have to dynamically allocate them
	 */
	mempool_t		fill_iter;

	mempool_t		btree_bounce_pool;

	struct journal		journal;
	GENRADIX(struct journal_replay *) journal_entries;
	u64			journal_entries_base_seq;
	struct journal_keys	journal_keys;
	struct list_head	journal_iters;

	struct find_btree_nodes	found_btree_nodes;

	u64			last_bucket_seq_cleanup;

	u64			counters_on_mount[BCH_COUNTER_NR];
	u64 __percpu		*counters;

	unsigned		copy_gc_enabled:1;

	struct bch2_time_stats	times[BCH_TIME_STAT_NR];

	struct btree_transaction_stats btree_transaction_stats[BCH_TRANSACTIONS_NR];

	/* ERRORS */
	struct list_head	fsck_error_msgs;
	struct mutex		fsck_error_msgs_lock;
	bool			fsck_alloc_msgs_err;

	bch_sb_errors_cpu	fsck_error_counts;
	struct mutex		fsck_error_counts_lock;
};

extern struct wait_queue_head bch2_read_only_wait;

static inline void bch2_write_ref_get(struct bch_fs *c, enum bch_write_ref ref)
{
#ifdef BCH_WRITE_REF_DEBUG
	atomic_long_inc(&c->writes[ref]);
#else
	percpu_ref_get(&c->writes);
#endif
}

static inline bool __bch2_write_ref_tryget(struct bch_fs *c, enum bch_write_ref ref)
{
#ifdef BCH_WRITE_REF_DEBUG
	return !test_bit(BCH_FS_going_ro, &c->flags) &&
		atomic_long_inc_not_zero(&c->writes[ref]);
#else
	return percpu_ref_tryget(&c->writes);
#endif
}

static inline bool bch2_write_ref_tryget(struct bch_fs *c, enum bch_write_ref ref)
{
#ifdef BCH_WRITE_REF_DEBUG
	return !test_bit(BCH_FS_going_ro, &c->flags) &&
		atomic_long_inc_not_zero(&c->writes[ref]);
#else
	return percpu_ref_tryget_live(&c->writes);
#endif
}

static inline void bch2_write_ref_put(struct bch_fs *c, enum bch_write_ref ref)
{
#ifdef BCH_WRITE_REF_DEBUG
	long v = atomic_long_dec_return(&c->writes[ref]);

	BUG_ON(v < 0);
	if (v)
		return;
	for (unsigned i = 0; i < BCH_WRITE_REF_NR; i++)
		if (atomic_long_read(&c->writes[i]))
			return;

	set_bit(BCH_FS_write_disable_complete, &c->flags);
	wake_up(&bch2_read_only_wait);
#else
	percpu_ref_put(&c->writes);
#endif
}

static inline bool bch2_ro_ref_tryget(struct bch_fs *c)
{
	if (test_bit(BCH_FS_stopping, &c->flags))
		return false;

	return refcount_inc_not_zero(&c->ro_ref);
}

static inline void bch2_ro_ref_put(struct bch_fs *c)
{
	if (refcount_dec_and_test(&c->ro_ref))
		wake_up(&c->ro_ref_wait);
}

static inline void bch2_set_ra_pages(struct bch_fs *c, unsigned ra_pages)
{
#ifndef NO_BCACHEFS_FS
	if (c->vfs_sb)
		c->vfs_sb->s_bdi->ra_pages = ra_pages;
#endif
}

static inline unsigned bucket_bytes(const struct bch_dev *ca)
{
	return ca->mi.bucket_size << 9;
}

static inline unsigned block_bytes(const struct bch_fs *c)
{
	return c->opts.block_size;
}

static inline unsigned block_sectors(const struct bch_fs *c)
{
	return c->opts.block_size >> 9;
}

static inline bool btree_id_cached(const struct bch_fs *c, enum btree_id btree)
{
	return c->btree_key_cache_btrees & (1U << btree);
}

static inline struct timespec64 bch2_time_to_timespec(const struct bch_fs *c, s64 time)
{
	struct timespec64 t;
	s64 sec;
	s32 rem;

	time += c->sb.time_base_lo;

	sec = div_s64_rem(time, c->sb.time_units_per_sec, &rem);

	set_normalized_timespec64(&t, sec, rem * (s64)c->sb.nsec_per_time_unit);

	return t;
}

static inline s64 timespec_to_bch2_time(const struct bch_fs *c, struct timespec64 ts)
{
	return (ts.tv_sec * c->sb.time_units_per_sec +
		(int) ts.tv_nsec / c->sb.nsec_per_time_unit) - c->sb.time_base_lo;
}

static inline s64 bch2_current_time(const struct bch_fs *c)
{
	struct timespec64 now;

	ktime_get_coarse_real_ts64(&now);
	return timespec_to_bch2_time(c, now);
}

static inline u64 bch2_current_io_time(const struct bch_fs *c, int rw)
{
	return max(1ULL, (u64) atomic64_read(&c->io_clock[rw].now) & LRU_TIME_MAX);
}

static inline struct stdio_redirect *bch2_fs_stdio_redirect(struct bch_fs *c)
{
	struct stdio_redirect *stdio = c->stdio;

	if (c->stdio_filter && c->stdio_filter != current)
		stdio = NULL;
	return stdio;
}

static inline unsigned metadata_replicas_required(struct bch_fs *c)
{
	return min(c->opts.metadata_replicas,
		   c->opts.metadata_replicas_required);
}

static inline unsigned data_replicas_required(struct bch_fs *c)
{
	return min(c->opts.data_replicas,
		   c->opts.data_replicas_required);
}

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

#endif /* _BCACHEFS_H */