summaryrefslogtreecommitdiff
path: root/fs/btrfs/block-group.h
blob: 74b61e663028a866ee5fc3577f3f37fc8b245999 (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
/* SPDX-License-Identifier: GPL-2.0 */

#ifndef BTRFS_BLOCK_GROUP_H
#define BTRFS_BLOCK_GROUP_H

#include "free-space-cache.h"

enum btrfs_disk_cache_state {
	BTRFS_DC_WRITTEN,
	BTRFS_DC_ERROR,
	BTRFS_DC_CLEAR,
	BTRFS_DC_SETUP,
};

enum btrfs_block_group_size_class {
	/* Unset */
	BTRFS_BG_SZ_NONE,
	/* 0 < size <= 128K */
	BTRFS_BG_SZ_SMALL,
	/* 128K < size <= 8M */
	BTRFS_BG_SZ_MEDIUM,
	/* 8M < size < BG_LENGTH */
	BTRFS_BG_SZ_LARGE,
};

/*
 * This describes the state of the block_group for async discard.  This is due
 * to the two pass nature of it where extent discarding is prioritized over
 * bitmap discarding.  BTRFS_DISCARD_RESET_CURSOR is set when we are resetting
 * between lists to prevent contention for discard state variables
 * (eg. discard_cursor).
 */
enum btrfs_discard_state {
	BTRFS_DISCARD_EXTENTS,
	BTRFS_DISCARD_BITMAPS,
	BTRFS_DISCARD_RESET_CURSOR,
};

/*
 * Control flags for do_chunk_alloc's force field CHUNK_ALLOC_NO_FORCE means to
 * only allocate a chunk if we really need one.
 *
 * CHUNK_ALLOC_LIMITED means to only try and allocate one if we have very few
 * chunks already allocated.  This is used as part of the clustering code to
 * help make sure we have a good pool of storage to cluster in, without filling
 * the FS with empty chunks
 *
 * CHUNK_ALLOC_FORCE means it must try to allocate one
 *
 * CHUNK_ALLOC_FORCE_FOR_EXTENT like CHUNK_ALLOC_FORCE but called from
 * find_free_extent() that also activaes the zone
 */
enum btrfs_chunk_alloc_enum {
	CHUNK_ALLOC_NO_FORCE,
	CHUNK_ALLOC_LIMITED,
	CHUNK_ALLOC_FORCE,
	CHUNK_ALLOC_FORCE_FOR_EXTENT,
};

/* Block group flags set at runtime */
enum btrfs_block_group_flags {
	BLOCK_GROUP_FLAG_IREF,
	BLOCK_GROUP_FLAG_REMOVED,
	BLOCK_GROUP_FLAG_TO_COPY,
	BLOCK_GROUP_FLAG_RELOCATING_REPAIR,
	BLOCK_GROUP_FLAG_CHUNK_ITEM_INSERTED,
	BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE,
	BLOCK_GROUP_FLAG_ZONED_DATA_RELOC,
	/* Does the block group need to be added to the free space tree? */
	BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE,
	/* Indicate that the block group is placed on a sequential zone */
	BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE,
	/*
	 * Indicate that block group is in the list of new block groups of a
	 * transaction.
	 */
	BLOCK_GROUP_FLAG_NEW,
};

enum btrfs_caching_type {
	BTRFS_CACHE_NO,
	BTRFS_CACHE_STARTED,
	BTRFS_CACHE_FINISHED,
	BTRFS_CACHE_ERROR,
};

struct btrfs_caching_control {
	struct list_head list;
	struct mutex mutex;
	wait_queue_head_t wait;
	struct btrfs_work work;
	struct btrfs_block_group *block_group;
	/* Track progress of caching during allocation. */
	atomic_t progress;
	refcount_t count;
};

/* Once caching_thread() finds this much free space, it will wake up waiters. */
#define CACHING_CTL_WAKE_UP SZ_2M

struct btrfs_block_group {
	struct btrfs_fs_info *fs_info;
	struct inode *inode;
	spinlock_t lock;
	u64 start;
	u64 length;
	u64 pinned;
	u64 reserved;
	u64 used;
	u64 delalloc_bytes;
	u64 bytes_super;
	u64 flags;
	u64 cache_generation;
	u64 global_root_id;

	/*
	 * The last committed used bytes of this block group, if the above @used
	 * is still the same as @commit_used, we don't need to update block
	 * group item of this block group.
	 */
	u64 commit_used;
	/*
	 * If the free space extent count exceeds this number, convert the block
	 * group to bitmaps.
	 */
	u32 bitmap_high_thresh;

	/*
	 * If the free space extent count drops below this number, convert the
	 * block group back to extents.
	 */
	u32 bitmap_low_thresh;

	/*
	 * It is just used for the delayed data space allocation because
	 * only the data space allocation and the relative metadata update
	 * can be done cross the transaction.
	 */
	struct rw_semaphore data_rwsem;

	/* For raid56, this is a full stripe, without parity */
	unsigned long full_stripe_len;
	unsigned long runtime_flags;

	unsigned int ro;

	int disk_cache_state;

	/* Cache tracking stuff */
	int cached;
	struct btrfs_caching_control *caching_ctl;

	struct btrfs_space_info *space_info;

	/* Free space cache stuff */
	struct btrfs_free_space_ctl *free_space_ctl;

	/* Block group cache stuff */
	struct rb_node cache_node;

	/* For block groups in the same raid type */
	struct list_head list;

	refcount_t refs;

	/*
	 * List of struct btrfs_free_clusters for this block group.
	 * Today it will only have one thing on it, but that may change
	 */
	struct list_head cluster_list;

	/*
	 * Used for several lists:
	 *
	 * 1) struct btrfs_fs_info::unused_bgs
	 * 2) struct btrfs_fs_info::reclaim_bgs
	 * 3) struct btrfs_transaction::deleted_bgs
	 * 4) struct btrfs_trans_handle::new_bgs
	 */
	struct list_head bg_list;

	/* For read-only block groups */
	struct list_head ro_list;

	/*
	 * When non-zero it means the block group's logical address and its
	 * device extents can not be reused for future block group allocations
	 * until the counter goes down to 0. This is to prevent them from being
	 * reused while some task is still using the block group after it was
	 * deleted - we want to make sure they can only be reused for new block
	 * groups after that task is done with the deleted block group.
	 */
	atomic_t frozen;

	/* For discard operations */
	struct list_head discard_list;
	int discard_index;
	u64 discard_eligible_time;
	u64 discard_cursor;
	enum btrfs_discard_state discard_state;

	/* For dirty block groups */
	struct list_head dirty_list;
	struct list_head io_list;

	struct btrfs_io_ctl io_ctl;

	/*
	 * Incremented when doing extent allocations and holding a read lock
	 * on the space_info's groups_sem semaphore.
	 * Decremented when an ordered extent that represents an IO against this
	 * block group's range is created (after it's added to its inode's
	 * root's list of ordered extents) or immediately after the allocation
	 * if it's a metadata extent or fallocate extent (for these cases we
	 * don't create ordered extents).
	 */
	atomic_t reservations;

	/*
	 * Incremented while holding the spinlock *lock* by a task checking if
	 * it can perform a nocow write (incremented if the value for the *ro*
	 * field is 0). Decremented by such tasks once they create an ordered
	 * extent or before that if some error happens before reaching that step.
	 * This is to prevent races between block group relocation and nocow
	 * writes through direct IO.
	 */
	atomic_t nocow_writers;

	/* Lock for free space tree operations. */
	struct mutex free_space_lock;

	/*
	 * Number of extents in this block group used for swap files.
	 * All accesses protected by the spinlock 'lock'.
	 */
	int swap_extents;

	/*
	 * Allocation offset for the block group to implement sequential
	 * allocation. This is used only on a zoned filesystem.
	 */
	u64 alloc_offset;
	u64 zone_unusable;
	u64 zone_capacity;
	u64 meta_write_pointer;
	struct map_lookup *physical_map;
	struct list_head active_bg_list;
	struct work_struct zone_finish_work;
	struct extent_buffer *last_eb;
	enum btrfs_block_group_size_class size_class;
};

static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
{
	return (block_group->start + block_group->length);
}

static inline bool btrfs_is_block_group_data_only(
					struct btrfs_block_group *block_group)
{
	/*
	 * In mixed mode the fragmentation is expected to be high, lowering the
	 * efficiency, so only proper data block groups are considered.
	 */
	return (block_group->flags & BTRFS_BLOCK_GROUP_DATA) &&
	       !(block_group->flags & BTRFS_BLOCK_GROUP_METADATA);
}

#ifdef CONFIG_BTRFS_DEBUG
int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group);
#endif

struct btrfs_block_group *btrfs_lookup_first_block_group(
		struct btrfs_fs_info *info, u64 bytenr);
struct btrfs_block_group *btrfs_lookup_block_group(
		struct btrfs_fs_info *info, u64 bytenr);
struct btrfs_block_group *btrfs_next_block_group(
		struct btrfs_block_group *cache);
void btrfs_get_block_group(struct btrfs_block_group *cache);
void btrfs_put_block_group(struct btrfs_block_group *cache);
void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
					const u64 start);
void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg);
struct btrfs_block_group *btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info,
						  u64 bytenr);
void btrfs_dec_nocow_writers(struct btrfs_block_group *bg);
void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
				           u64 num_bytes);
int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait);
void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
struct btrfs_caching_control *btrfs_get_caching_control(
		struct btrfs_block_group *cache);
int add_new_free_space(struct btrfs_block_group *block_group,
		       u64 start, u64 end, u64 *total_added_ret);
struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
				struct btrfs_fs_info *fs_info,
				const u64 chunk_offset);
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
			     u64 group_start, struct extent_map *em);
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
void btrfs_reclaim_bgs_work(struct work_struct *work);
void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info);
void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans,
						 u64 type,
						 u64 chunk_offset, u64 size);
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
			     bool do_chunk_alloc);
void btrfs_dec_block_group_ro(struct btrfs_block_group *cache);
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
int btrfs_update_block_group(struct btrfs_trans_handle *trans,
			     u64 bytenr, u64 num_bytes, bool alloc);
int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
			     u64 ram_bytes, u64 num_bytes, int delalloc,
			     bool force_wrong_size_class);
void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
			       u64 num_bytes, int delalloc);
int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
		      enum btrfs_chunk_alloc_enum force);
int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
void btrfs_reserve_chunk_metadata(struct btrfs_trans_handle *trans,
				  bool is_item_insertion);
u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags);
void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
int btrfs_free_block_groups(struct btrfs_fs_info *info);
int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
		     u64 physical, u64 **logical, int *naddrs, int *stripe_len);

static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
{
	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA);
}

static inline u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info)
{
	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA);
}

static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
{
	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
}

static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
{
	smp_mb();
	return cache->cached == BTRFS_CACHE_FINISHED ||
		cache->cached == BTRFS_CACHE_ERROR;
}

void btrfs_freeze_block_group(struct btrfs_block_group *cache);
void btrfs_unfreeze_block_group(struct btrfs_block_group *cache);

bool btrfs_inc_block_group_swap_extents(struct btrfs_block_group *bg);
void btrfs_dec_block_group_swap_extents(struct btrfs_block_group *bg, int amount);

enum btrfs_block_group_size_class btrfs_calc_block_group_size_class(u64 size);
int btrfs_use_block_group_size_class(struct btrfs_block_group *bg,
				     enum btrfs_block_group_size_class size_class,
				     bool force_wrong_size_class);
bool btrfs_block_group_should_use_size_class(struct btrfs_block_group *bg);

#endif /* BTRFS_BLOCK_GROUP_H */