summaryrefslogtreecommitdiff
path: root/libbcachefs/bcachefs.h
blob: 369d078c3d2e79199549eb00b15e120f20e9d7a3 (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
#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 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
#define pr_fmt(fmt) "bcachefs: %s() " fmt "\n", __func__

#include <linux/bug.h>
#include <linux/bio.h>
#include <linux/closure.h>
#include <linux/kobject.h>
#include <linux/lglock.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/percpu-refcount.h>
#include <linux/radix-tree.h>
#include <linux/rbtree.h>
#include <linux/rhashtable.h>
#include <linux/rwsem.h>
#include <linux/seqlock.h>
#include <linux/shrinker.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include <linux/zstd.h>

#include "bcachefs_format.h"
#include "bset.h"
#include "fifo.h"
#include "opts.h"
#include "util.h"

#include <linux/dynamic_fault.h>

#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 bch2_fmt(_c, fmt)	"bcachefs (%s): " fmt "\n", ((_c)->name)
#else
#define bch2_fmt(_c, fmt)	fmt "\n"
#endif

#define bch_info(c, fmt, ...) \
	printk(KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_notice(c, fmt, ...) \
	printk(KERN_NOTICE bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_warn(c, fmt, ...) \
	printk(KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_err(c, fmt, ...) \
	printk(KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)

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

#define pr_verbose_init(opts, fmt, ...)					\
do {									\
	if (opt_get(opts, verbose_init))				\
		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_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")

/* Parameters that should only be compiled in 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_bkeys,				\
		"Run bkey_debugcheck (primarily checking GC/allocation "\
		"information) when iterating over keys")		\
	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")					\

#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

/* name, frequency_units, duration_units */
#define BCH_TIME_STATS()						\
	BCH_TIME_STAT(btree_node_mem_alloc,	sec, us)		\
	BCH_TIME_STAT(btree_gc,			sec, ms)		\
	BCH_TIME_STAT(btree_split,		sec, us)		\
	BCH_TIME_STAT(btree_sort,		ms, us)			\
	BCH_TIME_STAT(btree_read,		ms, us)			\
	BCH_TIME_STAT(journal_write,		us, us)			\
	BCH_TIME_STAT(journal_delay,		ms, us)			\
	BCH_TIME_STAT(journal_blocked,		sec, ms)		\
	BCH_TIME_STAT(journal_flush_seq,	us, us)

#include "alloc_types.h"
#include "buckets_types.h"
#include "clock_types.h"
#include "journal_types.h"
#include "keylist_types.h"
#include "quota_types.h"
#include "super_types.h"

/*
 * Number of nodes we might have to allocate in a worst case btree split
 * operation - we split all the way up to the root, then allocate a new root.
 */
#define btree_reserve_required_nodes(depth)	(((depth) + 1) * 2 + 1)

/* 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_reserve_required_nodes(BTREE_MAX_DEPTH) + GC_MERGE_NODES)

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

struct btree;
struct crypto_blkcipher;
struct crypto_ahash;

enum gc_phase {
	GC_PHASE_SB		= BTREE_ID_NR + 1,
	GC_PHASE_PENDING_DELETE,
	GC_PHASE_ALLOC,
	GC_PHASE_DONE
};

struct gc_pos {
	enum gc_phase		phase;
	struct bpos		pos;
	unsigned		level;
};

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

struct bch_dev {
	struct kobject		kobj;
	struct percpu_ref	ref;
	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;
	uuid_le			uuid;
	char			name[BDEVNAME_SIZE];

	struct bch_sb_handle	disk_sb;
	int			sb_write_error;

	struct bch_devs_mask	self;

	/* biosets used in cloned bios for writing multiple replicas */
	struct bio_set		replica_set;

	/*
	 * Buckets:
	 * Per-bucket arrays are protected by c->usage_lock, bucket_lock and
	 * gc_lock, for device resize - holding any is sufficient for access:
	 * Or rcu_read_lock(), but only for ptr_stale():
	 */
	struct bucket_array __rcu *buckets;
	unsigned long		*buckets_dirty;
	/* most out of date gen in the btree */
	u8			*oldest_gens;
	struct rw_semaphore	bucket_lock;

	struct bch_dev_usage __percpu *usage_percpu;
	struct bch_dev_usage	usage_cached;

	/* Allocator: */
	struct task_struct	*alloc_thread;

	/*
	 * free: Buckets that are ready to be used
	 *
	 * free_inc: Incoming buckets - these are buckets that currently have
	 * cached data in them, and we can't reuse them until after we write
	 * their new gen to disk. After prio_write() finishes writing the new
	 * gens/prios, they'll be moved to the free list (and possibly discarded
	 * in the process)
	 */
	alloc_fifo		free[RESERVE_NR];
	alloc_fifo		free_inc;
	spinlock_t		freelist_lock;
	unsigned		nr_invalidated;

	u8			open_buckets_partial[OPEN_BUCKETS_COUNT];
	unsigned		open_buckets_partial_nr;

	size_t			fifo_last_bucket;

	/* last calculated minimum prio */
	u16			min_prio[2];

	atomic_long_t		saturated_count;
	size_t			inc_gen_needs_gc;
	size_t			inc_gen_really_needs_gc;
	u64			allocator_journal_seq_flush;
	bool			allocator_invalidating_data;
	bool			allocator_blocked;

	alloc_heap		alloc_heap;

	/* Copying GC: */
	struct task_struct	*copygc_thread;
	copygc_heap		copygc_heap;
	struct bch_pd_controller copygc_pd;
	struct write_point	copygc_write_point;

	atomic64_t		rebalance_work;

	struct journal_device	journal;

	struct work_struct	io_error_work;

	/* The rest of this all shows up in sysfs */
	atomic_t		latency[2];

	struct io_count __percpu *io_done;
};

/*
 * Flag bits for what phase of startup/shutdown the cache set is at, how we're
 * shutting down, etc.:
 *
 * BCH_FS_UNREGISTERING means we're not just shutting down, we're detaching
 * all the backing devices first (their cached data gets invalidated, and they
 * won't automatically reattach).
 */
enum {
	/* startup: */
	BCH_FS_BRAND_NEW_FS,
	BCH_FS_ALLOC_READ_DONE,
	BCH_FS_ALLOCATOR_STARTED,
	BCH_FS_INITIAL_GC_DONE,
	BCH_FS_FSCK_DONE,

	/* shutdown: */
	BCH_FS_EMERGENCY_RO,
	BCH_FS_WRITE_DISABLE_COMPLETE,
	BCH_FS_GC_STOPPING,

	/* errors: */
	BCH_FS_ERROR,
	BCH_FS_GC_FAILURE,

	/* misc: */
	BCH_FS_BDEV_MOUNTED,
	BCH_FS_FSCK_FIXED_ERRORS,
	BCH_FS_FIXED_GENS,
	BCH_FS_REBUILD_REPLICAS,
	BCH_FS_HOLD_BTREE_WRITES,
};

struct btree_debug {
	unsigned		id;
	struct dentry		*btree;
	struct dentry		*btree_format;
	struct dentry		*failed;
};

enum bch_fs_state {
	BCH_FS_STARTING		= 0,
	BCH_FS_STOPPING,
	BCH_FS_RO,
	BCH_FS_RW,
};

struct bch_fs {
	struct closure		cl;

	struct list_head	list;
	struct kobject		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;
	char			name[40];

	/* ro/rw, add/remove devices: */
	struct mutex		state_lock;
	enum bch_fs_state	state;

	/* Counts outstanding writes, for clean transition to read-only */
	struct percpu_ref	writes;
	struct work_struct	read_only_work;

	struct bch_dev __rcu	*devs[BCH_SB_MEMBERS_MAX];

	struct bch_replicas_cpu __rcu *replicas;
	struct bch_replicas_cpu __rcu *replicas_gc;
	struct mutex		replicas_gc_lock;

	struct bch_disk_groups_cpu __rcu *disk_groups;

	struct bch_opts		opts;

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

		u16		encoded_extent_max;

		u8		nr_devices;
		u8		clean;

		u8		encryption_type;

		u64		time_base_lo;
		u32		time_base_hi;
		u32		time_precision;
		u64		features;
	}			sb;

	struct bch_sb		*disk_sb;
	unsigned		disk_sb_order;

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

	u16			btree_foreground_merge_threshold;

	struct closure		sb_write;
	struct mutex		sb_lock;

	/* BTREE CACHE */
	struct bio_set		btree_bio;

	struct btree_root	btree_roots[BTREE_ID_NR];
	bool			btree_roots_dirty;
	struct mutex		btree_root_lock;

	struct btree_cache	btree_cache;

	mempool_t		btree_reserve_pool;

	/*
	 * 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 mutex		btree_interior_update_lock;
	struct closure_waitlist	btree_interior_update_wait;

	struct workqueue_struct	*wq;
	/* copygc needs its own workqueue for index updates.. */
	struct workqueue_struct	*copygc_wq;

	/* ALLOCATION */
	struct delayed_work	pd_controllers_update;
	unsigned		pd_controllers_update_seconds;

	/* REBALANCE */
	struct task_struct	*rebalance_thread;
	struct bch_pd_controller rebalance_pd;

	atomic64_t		rebalance_work_unknown_dev;

	struct bch_devs_mask	rw_devs[BCH_DATA_NR];

	u64			capacity; /* 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;

	atomic64_t		sectors_available;

	struct bch_fs_usage __percpu *usage_percpu;
	struct bch_fs_usage	usage_cached;
	struct lglock		usage_lock;

	struct closure_waitlist	freelist_wait;

	/*
	 * When we invalidate buckets, we use both the priority and the amount
	 * of good data to determine which buckets to reuse first - to weight
	 * those together consistently we keep track of the smallest nonzero
	 * priority of any bucket.
	 */
	struct prio_clock	prio_clock[2];

	struct io_clock		io_clock[2];

	/* ALLOCATOR */
	spinlock_t		freelist_lock;
	u8			open_buckets_freelist;
	u8			open_buckets_nr_free;
	struct closure_waitlist	open_buckets_wait;
	struct open_bucket	open_buckets[OPEN_BUCKETS_COUNT];

	struct write_point	btree_write_point;
	struct write_point	rebalance_write_point;

	struct write_point	write_points[WRITE_POINT_COUNT];
	struct hlist_head	write_points_hash[WRITE_POINT_COUNT];
	struct mutex		write_points_hash_lock;

	/* GARBAGE COLLECTION */
	struct task_struct	*gc_thread;
	atomic_t		kick_gc;
	unsigned long		gc_count;

	/*
	 * 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.)
	 *
	 * gc_cur_phase == GC_PHASE_DONE indicates that gc is finished/not
	 * currently running, and gc marks are currently valid
	 *
	 * 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;

	/* IO PATH */
	struct bio_set		bio_read;
	struct bio_set		bio_read_split;
	struct bio_set		bio_write;
	struct mutex		bio_bounce_pages_lock;
	mempool_t		bio_bounce_pages;

	mempool_t		compression_bounce[2];
	mempool_t		compress_workspace[BCH_COMPRESSION_NR];
	mempool_t		decompress_workspace;
	ZSTD_parameters		zstd_params;

	struct crypto_shash	*sha256;
	struct crypto_skcipher	*chacha20;
	struct crypto_shash	*poly1305;

	atomic64_t		key_version;

	/* 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_list		btree_write_error_list;
	struct work_struct	btree_write_error_work;
	spinlock_t		btree_write_error_lock;

	/* ERRORS */
	struct list_head	fsck_errors;
	struct mutex		fsck_error_lock;
	bool			fsck_alloc_err;

	/* FILESYSTEM */
	atomic_long_t		nr_inodes;

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

	/* DEBUG JUNK */
	struct dentry		*debug;
	struct btree_debug	btree_debug[BTREE_ID_NR];
#ifdef CONFIG_BCACHEFS_DEBUG
	struct btree		*verify_data;
	struct btree_node	*verify_ondisk;
	struct mutex		verify_lock;
#endif

	u64			unused_inode_hint;

	/*
	 * 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;

	unsigned		bucket_journal_seq;

	/* The rest of this all shows up in sysfs */
	atomic_long_t		read_realloc_races;
	atomic_long_t		extent_migrate_done;
	atomic_long_t		extent_migrate_raced;

	unsigned		btree_gc_periodic:1;
	unsigned		copy_gc_enabled:1;
	unsigned		rebalance_enabled:1;
	unsigned		rebalance_percent;

#define BCH_DEBUG_PARAM(name, description) bool name;
	BCH_DEBUG_PARAMS_ALL()
#undef BCH_DEBUG_PARAM

#define BCH_TIME_STAT(name, frequency_units, duration_units)		\
	struct time_stats	name##_time;
	BCH_TIME_STATS()
#undef BCH_TIME_STAT
};

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 bool bch2_fs_running(struct bch_fs *c)
{
	return c->state == BCH_FS_RO || c->state == BCH_FS_RW;
}

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 << 9;
}

#endif /* _BCACHEFS_H */