summaryrefslogtreecommitdiff
path: root/fs/bcachefs/buckets.h
blob: 617ffde2fb7ad96f3c4c0e0b101df98a8cba7b51 (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
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Code for manipulating bucket marks for garbage collection.
 *
 * Copyright 2014 Datera, Inc.
 */

#ifndef _BUCKETS_H
#define _BUCKETS_H

#include "buckets_types.h"
#include "extents.h"
#include "sb-members.h"

static inline u64 sector_to_bucket(const struct bch_dev *ca, sector_t s)
{
	return div_u64(s, ca->mi.bucket_size);
}

static inline sector_t bucket_to_sector(const struct bch_dev *ca, size_t b)
{
	return ((sector_t) b) * ca->mi.bucket_size;
}

static inline sector_t bucket_remainder(const struct bch_dev *ca, sector_t s)
{
	u32 remainder;

	div_u64_rem(s, ca->mi.bucket_size, &remainder);
	return remainder;
}

static inline u64 sector_to_bucket_and_offset(const struct bch_dev *ca, sector_t s, u32 *offset)
{
	return div_u64_rem(s, ca->mi.bucket_size, offset);
}

#define for_each_bucket(_b, _buckets)				\
	for (_b = (_buckets)->b + (_buckets)->first_bucket;	\
	     _b < (_buckets)->b + (_buckets)->nbuckets; _b++)

/*
 * Ugly hack alert:
 *
 * We need to cram a spinlock in a single byte, because that's what we have left
 * in struct bucket, and we care about the size of these - during fsck, we need
 * in memory state for every single bucket on every device.
 *
 * We used to do
 *   while (xchg(&b->lock, 1) cpu_relax();
 * but, it turns out not all architectures support xchg on a single byte.
 *
 * So now we use bit_spin_lock(), with fun games since we can't burn a whole
 * ulong for this - we just need to make sure the lock bit always ends up in the
 * first byte.
 */

#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
#define BUCKET_LOCK_BITNR	0
#else
#define BUCKET_LOCK_BITNR	(BITS_PER_LONG - 1)
#endif

union ulong_byte_assert {
	ulong	ulong;
	u8	byte;
};

static inline void bucket_unlock(struct bucket *b)
{
	BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);

	clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &b->lock);
	wake_up_bit((void *) &b->lock, BUCKET_LOCK_BITNR);
}

static inline void bucket_lock(struct bucket *b)
{
	wait_on_bit_lock((void *) &b->lock, BUCKET_LOCK_BITNR,
			 TASK_UNINTERRUPTIBLE);
}

static inline struct bucket_array *gc_bucket_array(struct bch_dev *ca)
{
	return rcu_dereference_check(ca->buckets_gc,
				     !ca->fs ||
				     percpu_rwsem_is_held(&ca->fs->mark_lock) ||
				     lockdep_is_held(&ca->fs->gc_lock) ||
				     lockdep_is_held(&ca->bucket_lock));
}

static inline struct bucket *gc_bucket(struct bch_dev *ca, size_t b)
{
	struct bucket_array *buckets = gc_bucket_array(ca);

	BUG_ON(!bucket_valid(ca, b));
	return buckets->b + b;
}

static inline struct bucket_gens *bucket_gens(struct bch_dev *ca)
{
	return rcu_dereference_check(ca->bucket_gens,
				     !ca->fs ||
				     percpu_rwsem_is_held(&ca->fs->mark_lock) ||
				     lockdep_is_held(&ca->fs->gc_lock) ||
				     lockdep_is_held(&ca->bucket_lock));
}

static inline u8 *bucket_gen(struct bch_dev *ca, size_t b)
{
	struct bucket_gens *gens = bucket_gens(ca);

	BUG_ON(!bucket_valid(ca, b));
	return gens->b + b;
}

static inline size_t PTR_BUCKET_NR(const struct bch_dev *ca,
				   const struct bch_extent_ptr *ptr)
{
	return sector_to_bucket(ca, ptr->offset);
}

static inline struct bpos PTR_BUCKET_POS(const struct bch_dev *ca,
					 const struct bch_extent_ptr *ptr)
{
	return POS(ptr->dev, PTR_BUCKET_NR(ca, ptr));
}

static inline struct bpos PTR_BUCKET_POS_OFFSET(const struct bch_dev *ca,
						const struct bch_extent_ptr *ptr,
						u32 *bucket_offset)
{
	return POS(ptr->dev, sector_to_bucket_and_offset(ca, ptr->offset, bucket_offset));
}

static inline struct bucket *PTR_GC_BUCKET(struct bch_dev *ca,
					   const struct bch_extent_ptr *ptr)
{
	return gc_bucket(ca, PTR_BUCKET_NR(ca, ptr));
}

static inline enum bch_data_type ptr_data_type(const struct bkey *k,
					       const struct bch_extent_ptr *ptr)
{
	if (bkey_is_btree_ptr(k))
		return BCH_DATA_btree;

	return ptr->cached ? BCH_DATA_cached : BCH_DATA_user;
}

static inline s64 ptr_disk_sectors(s64 sectors, struct extent_ptr_decoded p)
{
	EBUG_ON(sectors < 0);

	return crc_is_compressed(p.crc)
		? DIV_ROUND_UP_ULL(sectors * p.crc.compressed_size,
				   p.crc.uncompressed_size)
		: sectors;
}

static inline int gen_cmp(u8 a, u8 b)
{
	return (s8) (a - b);
}

static inline int gen_after(u8 a, u8 b)
{
	int r = gen_cmp(a, b);

	return r > 0 ? r : 0;
}

static inline u8 dev_ptr_stale_rcu(struct bch_dev *ca, const struct bch_extent_ptr *ptr)
{
	return gen_after(*bucket_gen(ca, PTR_BUCKET_NR(ca, ptr)), ptr->gen);
}

/**
 * dev_ptr_stale() - check if a pointer points into a bucket that has been
 * invalidated.
 */
static inline u8 dev_ptr_stale(struct bch_dev *ca, const struct bch_extent_ptr *ptr)
{
	rcu_read_lock();
	u8 ret = dev_ptr_stale_rcu(ca, ptr);
	rcu_read_unlock();

	return ret;
}

/* Device usage: */

void bch2_dev_usage_read_fast(struct bch_dev *, struct bch_dev_usage *);
static inline struct bch_dev_usage bch2_dev_usage_read(struct bch_dev *ca)
{
	struct bch_dev_usage ret;

	bch2_dev_usage_read_fast(ca, &ret);
	return ret;
}

void bch2_dev_usage_init(struct bch_dev *);
void bch2_dev_usage_to_text(struct printbuf *, struct bch_dev_usage *);

static inline u64 bch2_dev_buckets_reserved(struct bch_dev *ca, enum bch_watermark watermark)
{
	s64 reserved = 0;

	switch (watermark) {
	case BCH_WATERMARK_NR:
		BUG();
	case BCH_WATERMARK_stripe:
		reserved += ca->mi.nbuckets >> 6;
		fallthrough;
	case BCH_WATERMARK_normal:
		reserved += ca->mi.nbuckets >> 6;
		fallthrough;
	case BCH_WATERMARK_copygc:
		reserved += ca->nr_btree_reserve;
		fallthrough;
	case BCH_WATERMARK_btree:
		reserved += ca->nr_btree_reserve;
		fallthrough;
	case BCH_WATERMARK_btree_copygc:
	case BCH_WATERMARK_reclaim:
	case BCH_WATERMARK_interior_updates:
		break;
	}

	return reserved;
}

static inline u64 dev_buckets_free(struct bch_dev *ca,
				   struct bch_dev_usage usage,
				   enum bch_watermark watermark)
{
	return max_t(s64, 0,
		     usage.d[BCH_DATA_free].buckets -
		     ca->nr_open_buckets -
		     bch2_dev_buckets_reserved(ca, watermark));
}

static inline u64 __dev_buckets_available(struct bch_dev *ca,
					  struct bch_dev_usage usage,
					  enum bch_watermark watermark)
{
	return max_t(s64, 0,
		       usage.d[BCH_DATA_free].buckets
		     + usage.d[BCH_DATA_cached].buckets
		     + usage.d[BCH_DATA_need_gc_gens].buckets
		     + usage.d[BCH_DATA_need_discard].buckets
		     - ca->nr_open_buckets
		     - bch2_dev_buckets_reserved(ca, watermark));
}

static inline u64 dev_buckets_available(struct bch_dev *ca,
					enum bch_watermark watermark)
{
	return __dev_buckets_available(ca, bch2_dev_usage_read(ca), watermark);
}

/* Filesystem usage: */

static inline unsigned __fs_usage_u64s(unsigned nr_replicas)
{
	return sizeof(struct bch_fs_usage) / sizeof(u64) + nr_replicas;
}

static inline unsigned fs_usage_u64s(struct bch_fs *c)
{
	return __fs_usage_u64s(READ_ONCE(c->replicas.nr));
}

static inline unsigned __fs_usage_online_u64s(unsigned nr_replicas)
{
	return sizeof(struct bch_fs_usage_online) / sizeof(u64) + nr_replicas;
}

static inline unsigned fs_usage_online_u64s(struct bch_fs *c)
{
	return __fs_usage_online_u64s(READ_ONCE(c->replicas.nr));
}

static inline unsigned dev_usage_u64s(void)
{
	return sizeof(struct bch_dev_usage) / sizeof(u64);
}

u64 bch2_fs_usage_read_one(struct bch_fs *, u64 *);

struct bch_fs_usage_online *bch2_fs_usage_read(struct bch_fs *);

void bch2_fs_usage_acc_to_base(struct bch_fs *, unsigned);

void bch2_fs_usage_to_text(struct printbuf *,
			   struct bch_fs *, struct bch_fs_usage_online *);

u64 bch2_fs_sectors_used(struct bch_fs *, struct bch_fs_usage_online *);

struct bch_fs_usage_short
bch2_fs_usage_read_short(struct bch_fs *);

void bch2_dev_usage_update(struct bch_fs *, struct bch_dev *,
			   const struct bch_alloc_v4 *,
			   const struct bch_alloc_v4 *, u64, bool);

/* key/bucket marking: */

static inline struct bch_fs_usage *fs_usage_ptr(struct bch_fs *c,
						unsigned journal_seq,
						bool gc)
{
	percpu_rwsem_assert_held(&c->mark_lock);
	BUG_ON(!gc && !journal_seq);

	return this_cpu_ptr(gc
			    ? c->usage_gc
			    : c->usage[journal_seq & JOURNAL_BUF_MASK]);
}

int bch2_update_replicas(struct bch_fs *, struct bkey_s_c,
			 struct bch_replicas_entry_v1 *, s64,
			 unsigned, bool);
int bch2_update_replicas_list(struct btree_trans *,
			 struct bch_replicas_entry_v1 *, s64);
int bch2_update_cached_sectors_list(struct btree_trans *, unsigned, s64);
int bch2_replicas_deltas_realloc(struct btree_trans *, unsigned);

void bch2_fs_usage_initialize(struct bch_fs *);

int bch2_bucket_ref_update(struct btree_trans *, struct bch_dev *,
			   struct bkey_s_c, const struct bch_extent_ptr *,
			   s64, enum bch_data_type, u8, u8, u32 *);

int bch2_check_fix_ptrs(struct btree_trans *,
			enum btree_id, unsigned, struct bkey_s_c,
			enum btree_iter_update_trigger_flags);

int bch2_trigger_extent(struct btree_trans *, enum btree_id, unsigned,
			struct bkey_s_c, struct bkey_s,
			enum btree_iter_update_trigger_flags);
int bch2_trigger_reservation(struct btree_trans *, enum btree_id, unsigned,
			  struct bkey_s_c, struct bkey_s,
			  enum btree_iter_update_trigger_flags);

#define trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, _new, _flags)\
({												\
	int ret = 0;										\
												\
	if (_old.k->type)									\
		ret = _fn(_trans, _btree_id, _level, _old, _flags & ~BTREE_TRIGGER_insert);	\
	if (!ret && _new.k->type)								\
		ret = _fn(_trans, _btree_id, _level, _new.s_c, _flags & ~BTREE_TRIGGER_overwrite);\
	ret;											\
})

void bch2_trans_account_disk_usage_change(struct btree_trans *);

void bch2_trans_fs_usage_revert(struct btree_trans *, struct replicas_delta_list *);
int bch2_trans_fs_usage_apply(struct btree_trans *, struct replicas_delta_list *);

int bch2_trans_mark_metadata_bucket(struct btree_trans *, struct bch_dev *, u64,
				    enum bch_data_type, unsigned,
				    enum btree_iter_update_trigger_flags);
int bch2_trans_mark_dev_sb(struct bch_fs *, struct bch_dev *,
				    enum btree_iter_update_trigger_flags);
int bch2_trans_mark_dev_sbs_flags(struct bch_fs *,
				    enum btree_iter_update_trigger_flags);
int bch2_trans_mark_dev_sbs(struct bch_fs *);

static inline bool is_superblock_bucket(struct bch_dev *ca, u64 b)
{
	struct bch_sb_layout *layout = &ca->disk_sb.sb->layout;
	u64 b_offset	= bucket_to_sector(ca, b);
	u64 b_end	= bucket_to_sector(ca, b + 1);
	unsigned i;

	if (!b)
		return true;

	for (i = 0; i < layout->nr_superblocks; i++) {
		u64 offset = le64_to_cpu(layout->sb_offset[i]);
		u64 end = offset + (1 << layout->sb_max_size_bits);

		if (!(offset >= b_end || end <= b_offset))
			return true;
	}

	return false;
}

static inline const char *bch2_data_type_str(enum bch_data_type type)
{
	return type < BCH_DATA_NR
		? __bch2_data_types[type]
		: "(invalid data type)";
}

/* disk reservations: */

static inline void bch2_disk_reservation_put(struct bch_fs *c,
					     struct disk_reservation *res)
{
	if (res->sectors) {
		this_cpu_sub(*c->online_reserved, res->sectors);
		res->sectors = 0;
	}
}

#define BCH_DISK_RESERVATION_NOFAIL		(1 << 0)

int __bch2_disk_reservation_add(struct bch_fs *,
				struct disk_reservation *,
				u64, int);

static inline int bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res,
					    u64 sectors, int flags)
{
#ifdef __KERNEL__
	u64 old, new;

	do {
		old = this_cpu_read(c->pcpu->sectors_available);
		if (sectors > old)
			return __bch2_disk_reservation_add(c, res, sectors, flags);

		new = old - sectors;
	} while (this_cpu_cmpxchg(c->pcpu->sectors_available, old, new) != old);

	this_cpu_add(*c->online_reserved, sectors);
	res->sectors			+= sectors;
	return 0;
#else
	return __bch2_disk_reservation_add(c, res, sectors, flags);
#endif
}

static inline struct disk_reservation
bch2_disk_reservation_init(struct bch_fs *c, unsigned nr_replicas)
{
	return (struct disk_reservation) {
		.sectors	= 0,
#if 0
		/* not used yet: */
		.gen		= c->capacity_gen,
#endif
		.nr_replicas	= nr_replicas,
	};
}

static inline int bch2_disk_reservation_get(struct bch_fs *c,
					    struct disk_reservation *res,
					    u64 sectors, unsigned nr_replicas,
					    int flags)
{
	*res = bch2_disk_reservation_init(c, nr_replicas);

	return bch2_disk_reservation_add(c, res, sectors * nr_replicas, flags);
}

#define RESERVE_FACTOR	6

static inline u64 avail_factor(u64 r)
{
	return div_u64(r << RESERVE_FACTOR, (1 << RESERVE_FACTOR) + 1);
}

void bch2_buckets_nouse_free(struct bch_fs *);
int bch2_buckets_nouse_alloc(struct bch_fs *);

int bch2_dev_buckets_resize(struct bch_fs *, struct bch_dev *, u64);
void bch2_dev_buckets_free(struct bch_dev *);
int bch2_dev_buckets_alloc(struct bch_fs *, struct bch_dev *);

#endif /* _BUCKETS_H */