summaryrefslogtreecommitdiff
path: root/fs/btrfs/block-rsv.c
blob: d07bd41a7c1e01b2b12254802702198606796108 (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
// SPDX-License-Identifier: GPL-2.0

#include "misc.h"
#include "ctree.h"
#include "block-rsv.h"
#include "space-info.h"
#include "transaction.h"

static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
				    struct btrfs_block_rsv *block_rsv,
				    struct btrfs_block_rsv *dest, u64 num_bytes,
				    u64 *qgroup_to_release_ret)
{
	struct btrfs_space_info *space_info = block_rsv->space_info;
	u64 qgroup_to_release = 0;
	u64 ret;

	spin_lock(&block_rsv->lock);
	if (num_bytes == (u64)-1) {
		num_bytes = block_rsv->size;
		qgroup_to_release = block_rsv->qgroup_rsv_size;
	}
	block_rsv->size -= num_bytes;
	if (block_rsv->reserved >= block_rsv->size) {
		num_bytes = block_rsv->reserved - block_rsv->size;
		block_rsv->reserved = block_rsv->size;
		block_rsv->full = 1;
	} else {
		num_bytes = 0;
	}
	if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) {
		qgroup_to_release = block_rsv->qgroup_rsv_reserved -
				    block_rsv->qgroup_rsv_size;
		block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size;
	} else {
		qgroup_to_release = 0;
	}
	spin_unlock(&block_rsv->lock);

	ret = num_bytes;
	if (num_bytes > 0) {
		if (dest) {
			spin_lock(&dest->lock);
			if (!dest->full) {
				u64 bytes_to_add;

				bytes_to_add = dest->size - dest->reserved;
				bytes_to_add = min(num_bytes, bytes_to_add);
				dest->reserved += bytes_to_add;
				if (dest->reserved >= dest->size)
					dest->full = 1;
				num_bytes -= bytes_to_add;
			}
			spin_unlock(&dest->lock);
		}
		if (num_bytes)
			btrfs_space_info_free_bytes_may_use(fs_info,
							    space_info,
							    num_bytes);
	}
	if (qgroup_to_release_ret)
		*qgroup_to_release_ret = qgroup_to_release;
	return ret;
}

int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src,
			    struct btrfs_block_rsv *dst, u64 num_bytes,
			    bool update_size)
{
	int ret;

	ret = btrfs_block_rsv_use_bytes(src, num_bytes);
	if (ret)
		return ret;

	btrfs_block_rsv_add_bytes(dst, num_bytes, update_size);
	return 0;
}

void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type)
{
	memset(rsv, 0, sizeof(*rsv));
	spin_lock_init(&rsv->lock);
	rsv->type = type;
}

void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info,
				   struct btrfs_block_rsv *rsv,
				   unsigned short type)
{
	btrfs_init_block_rsv(rsv, type);
	rsv->space_info = btrfs_find_space_info(fs_info,
					    BTRFS_BLOCK_GROUP_METADATA);
}

struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info,
					      unsigned short type)
{
	struct btrfs_block_rsv *block_rsv;

	block_rsv = kmalloc(sizeof(*block_rsv), GFP_NOFS);
	if (!block_rsv)
		return NULL;

	btrfs_init_metadata_block_rsv(fs_info, block_rsv, type);
	return block_rsv;
}

void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
			  struct btrfs_block_rsv *rsv)
{
	if (!rsv)
		return;
	btrfs_block_rsv_release(fs_info, rsv, (u64)-1);
	kfree(rsv);
}

int btrfs_block_rsv_add(struct btrfs_root *root,
			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
			enum btrfs_reserve_flush_enum flush)
{
	int ret;

	if (num_bytes == 0)
		return 0;

	ret = btrfs_reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
	if (!ret)
		btrfs_block_rsv_add_bytes(block_rsv, num_bytes, true);

	return ret;
}

int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_factor)
{
	u64 num_bytes = 0;
	int ret = -ENOSPC;

	if (!block_rsv)
		return 0;

	spin_lock(&block_rsv->lock);
	num_bytes = div_factor(block_rsv->size, min_factor);
	if (block_rsv->reserved >= num_bytes)
		ret = 0;
	spin_unlock(&block_rsv->lock);

	return ret;
}

int btrfs_block_rsv_refill(struct btrfs_root *root,
			   struct btrfs_block_rsv *block_rsv, u64 min_reserved,
			   enum btrfs_reserve_flush_enum flush)
{
	u64 num_bytes = 0;
	int ret = -ENOSPC;

	if (!block_rsv)
		return 0;

	spin_lock(&block_rsv->lock);
	num_bytes = min_reserved;
	if (block_rsv->reserved >= num_bytes)
		ret = 0;
	else
		num_bytes -= block_rsv->reserved;
	spin_unlock(&block_rsv->lock);

	if (!ret)
		return 0;

	ret = btrfs_reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
	if (!ret) {
		btrfs_block_rsv_add_bytes(block_rsv, num_bytes, false);
		return 0;
	}

	return ret;
}

u64 __btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
			      struct btrfs_block_rsv *block_rsv,
			      u64 num_bytes, u64 *qgroup_to_release)
{
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
	struct btrfs_block_rsv *target = NULL;

	/*
	 * If we are the delayed_rsv then push to the global rsv, otherwise dump
	 * into the delayed rsv if it is not full.
	 */
	if (block_rsv == delayed_rsv)
		target = global_rsv;
	else if (block_rsv != global_rsv && !delayed_rsv->full)
		target = delayed_rsv;

	if (target && block_rsv->space_info != target->space_info)
		target = NULL;

	return block_rsv_release_bytes(fs_info, block_rsv, target, num_bytes,
				       qgroup_to_release);
}

int btrfs_block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes)
{
	int ret = -ENOSPC;

	spin_lock(&block_rsv->lock);
	if (block_rsv->reserved >= num_bytes) {
		block_rsv->reserved -= num_bytes;
		if (block_rsv->reserved < block_rsv->size)
			block_rsv->full = 0;
		ret = 0;
	}
	spin_unlock(&block_rsv->lock);
	return ret;
}

void btrfs_block_rsv_add_bytes(struct btrfs_block_rsv *block_rsv,
			       u64 num_bytes, bool update_size)
{
	spin_lock(&block_rsv->lock);
	block_rsv->reserved += num_bytes;
	if (update_size)
		block_rsv->size += num_bytes;
	else if (block_rsv->reserved >= block_rsv->size)
		block_rsv->full = 1;
	spin_unlock(&block_rsv->lock);
}

int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
			     struct btrfs_block_rsv *dest, u64 num_bytes,
			     int min_factor)
{
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	u64 min_bytes;

	if (global_rsv->space_info != dest->space_info)
		return -ENOSPC;

	spin_lock(&global_rsv->lock);
	min_bytes = div_factor(global_rsv->size, min_factor);
	if (global_rsv->reserved < min_bytes + num_bytes) {
		spin_unlock(&global_rsv->lock);
		return -ENOSPC;
	}
	global_rsv->reserved -= num_bytes;
	if (global_rsv->reserved < global_rsv->size)
		global_rsv->full = 0;
	spin_unlock(&global_rsv->lock);

	btrfs_block_rsv_add_bytes(dest, num_bytes, true);
	return 0;
}

void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info)
{
	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
	struct btrfs_space_info *sinfo = block_rsv->space_info;
	u64 num_bytes;
	unsigned min_items;

	/*
	 * The global block rsv is based on the size of the extent tree, the
	 * checksum tree and the root tree.  If the fs is empty we want to set
	 * it to a minimal amount for safety.
	 */
	num_bytes = btrfs_root_used(&fs_info->extent_root->root_item) +
		btrfs_root_used(&fs_info->csum_root->root_item) +
		btrfs_root_used(&fs_info->tree_root->root_item);

	/*
	 * We at a minimum are going to modify the csum root, the tree root, and
	 * the extent root.
	 */
	min_items = 3;

	/*
	 * But we also want to reserve enough space so we can do the fallback
	 * global reserve for an unlink, which is an additional 5 items (see the
	 * comment in __unlink_start_trans for what we're modifying.)
	 *
	 * But we also need space for the delayed ref updates from the unlink,
	 * so its 10, 5 for the actual operation, and 5 for the delayed ref
	 * updates.
	 */
	min_items += 10;

	num_bytes = max_t(u64, num_bytes,
			  btrfs_calc_insert_metadata_size(fs_info, min_items));

	spin_lock(&sinfo->lock);
	spin_lock(&block_rsv->lock);

	block_rsv->size = min_t(u64, num_bytes, SZ_512M);

	if (block_rsv->reserved < block_rsv->size) {
		num_bytes = block_rsv->size - block_rsv->reserved;
		block_rsv->reserved += num_bytes;
		btrfs_space_info_update_bytes_may_use(fs_info, sinfo,
						      num_bytes);
	} else if (block_rsv->reserved > block_rsv->size) {
		num_bytes = block_rsv->reserved - block_rsv->size;
		btrfs_space_info_update_bytes_may_use(fs_info, sinfo,
						      -num_bytes);
		block_rsv->reserved = block_rsv->size;
		btrfs_try_granting_tickets(fs_info, sinfo);
	}

	if (block_rsv->reserved == block_rsv->size)
		block_rsv->full = 1;
	else
		block_rsv->full = 0;

	spin_unlock(&block_rsv->lock);
	spin_unlock(&sinfo->lock);
}

void btrfs_init_global_block_rsv(struct btrfs_fs_info *fs_info)
{
	struct btrfs_space_info *space_info;

	space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
	fs_info->chunk_block_rsv.space_info = space_info;

	space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
	fs_info->global_block_rsv.space_info = space_info;
	fs_info->trans_block_rsv.space_info = space_info;
	fs_info->empty_block_rsv.space_info = space_info;
	fs_info->delayed_block_rsv.space_info = space_info;
	fs_info->delayed_refs_rsv.space_info = space_info;

	fs_info->extent_root->block_rsv = &fs_info->delayed_refs_rsv;
	fs_info->csum_root->block_rsv = &fs_info->delayed_refs_rsv;
	fs_info->dev_root->block_rsv = &fs_info->global_block_rsv;
	fs_info->tree_root->block_rsv = &fs_info->global_block_rsv;
	if (fs_info->quota_root)
		fs_info->quota_root->block_rsv = &fs_info->global_block_rsv;
	fs_info->chunk_root->block_rsv = &fs_info->chunk_block_rsv;

	btrfs_update_global_block_rsv(fs_info);
}

void btrfs_release_global_block_rsv(struct btrfs_fs_info *fs_info)
{
	btrfs_block_rsv_release(fs_info, &fs_info->global_block_rsv, (u64)-1);
	WARN_ON(fs_info->trans_block_rsv.size > 0);
	WARN_ON(fs_info->trans_block_rsv.reserved > 0);
	WARN_ON(fs_info->chunk_block_rsv.size > 0);
	WARN_ON(fs_info->chunk_block_rsv.reserved > 0);
	WARN_ON(fs_info->delayed_block_rsv.size > 0);
	WARN_ON(fs_info->delayed_block_rsv.reserved > 0);
	WARN_ON(fs_info->delayed_refs_rsv.reserved > 0);
	WARN_ON(fs_info->delayed_refs_rsv.size > 0);
}

static struct btrfs_block_rsv *get_block_rsv(
					const struct btrfs_trans_handle *trans,
					const struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *block_rsv = NULL;

	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
	    (root == fs_info->csum_root && trans->adding_csums) ||
	    (root == fs_info->uuid_root))
		block_rsv = trans->block_rsv;

	if (!block_rsv)
		block_rsv = root->block_rsv;

	if (!block_rsv)
		block_rsv = &fs_info->empty_block_rsv;

	return block_rsv;
}

struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans,
					    struct btrfs_root *root,
					    u32 blocksize)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *block_rsv;
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	int ret;
	bool global_updated = false;

	block_rsv = get_block_rsv(trans, root);

	if (unlikely(block_rsv->size == 0))
		goto try_reserve;
again:
	ret = btrfs_block_rsv_use_bytes(block_rsv, blocksize);
	if (!ret)
		return block_rsv;

	if (block_rsv->failfast)
		return ERR_PTR(ret);

	if (block_rsv->type == BTRFS_BLOCK_RSV_GLOBAL && !global_updated) {
		global_updated = true;
		btrfs_update_global_block_rsv(fs_info);
		goto again;
	}

	/*
	 * The global reserve still exists to save us from ourselves, so don't
	 * warn_on if we are short on our delayed refs reserve.
	 */
	if (block_rsv->type != BTRFS_BLOCK_RSV_DELREFS &&
	    btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
		static DEFINE_RATELIMIT_STATE(_rs,
				DEFAULT_RATELIMIT_INTERVAL * 10,
				/*DEFAULT_RATELIMIT_BURST*/ 1);
		if (__ratelimit(&_rs))
			WARN(1, KERN_DEBUG
				"BTRFS: block rsv returned %d\n", ret);
	}
try_reserve:
	ret = btrfs_reserve_metadata_bytes(root, block_rsv, blocksize,
					   BTRFS_RESERVE_NO_FLUSH);
	if (!ret)
		return block_rsv;
	/*
	 * If we couldn't reserve metadata bytes try and use some from
	 * the global reserve if its space type is the same as the global
	 * reservation.
	 */
	if (block_rsv->type != BTRFS_BLOCK_RSV_GLOBAL &&
	    block_rsv->space_info == global_rsv->space_info) {
		ret = btrfs_block_rsv_use_bytes(global_rsv, blocksize);
		if (!ret)
			return global_rsv;
	}
	return ERR_PTR(ret);
}