summaryrefslogtreecommitdiff
path: root/fs/btrfs/root-tree.c
blob: 3338407ef0f06c8852991e78757d92465ca588c3 (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
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/err.h>
#include <linux/uuid.h>
#include "ctree.h"
#include "transaction.h"
#include "disk-io.h"
#include "print-tree.h"

/*
 * Read a root item from the tree. In case we detect a root item smaller then
 * sizeof(root_item), we know it's an old version of the root structure and
 * initialize all new fields to zero. The same happens if we detect mismatching
 * generation numbers as then we know the root was once mounted with an older
 * kernel that was not aware of the root item structure change.
 */
static void btrfs_read_root_item(struct extent_buffer *eb, int slot,
				struct btrfs_root_item *item)
{
	uuid_le uuid;
	int len;
	int need_reset = 0;

	len = btrfs_item_size_nr(eb, slot);
	read_extent_buffer(eb, item, btrfs_item_ptr_offset(eb, slot),
			min_t(int, len, (int)sizeof(*item)));
	if (len < sizeof(*item))
		need_reset = 1;
	if (!need_reset && btrfs_root_generation(item)
		!= btrfs_root_generation_v2(item)) {
		if (btrfs_root_generation_v2(item) != 0) {
			btrfs_warn(eb->fs_info,
					"mismatching generation and generation_v2 found in root item. This root was probably mounted with an older kernel. Resetting all new fields.");
		}
		need_reset = 1;
	}
	if (need_reset) {
		memset(&item->generation_v2, 0,
			sizeof(*item) - offsetof(struct btrfs_root_item,
					generation_v2));

		uuid_le_gen(&uuid);
		memcpy(item->uuid, uuid.b, BTRFS_UUID_SIZE);
	}
}

/*
 * btrfs_find_root - lookup the root by the key.
 * root: the root of the root tree
 * search_key: the key to search
 * path: the path we search
 * root_item: the root item of the tree we look for
 * root_key: the root key of the tree we look for
 *
 * If ->offset of 'search_key' is -1ULL, it means we are not sure the offset
 * of the search key, just lookup the root with the highest offset for a
 * given objectid.
 *
 * If we find something return 0, otherwise > 0, < 0 on error.
 */
int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key,
		    struct btrfs_path *path, struct btrfs_root_item *root_item,
		    struct btrfs_key *root_key)
{
	struct btrfs_key found_key;
	struct extent_buffer *l;
	int ret;
	int slot;

	ret = btrfs_search_slot(NULL, root, search_key, path, 0, 0);
	if (ret < 0)
		return ret;

	if (search_key->offset != -1ULL) {	/* the search key is exact */
		if (ret > 0)
			goto out;
	} else {
		BUG_ON(ret == 0);		/* Logical error */
		if (path->slots[0] == 0)
			goto out;
		path->slots[0]--;
		ret = 0;
	}

	l = path->nodes[0];
	slot = path->slots[0];

	btrfs_item_key_to_cpu(l, &found_key, slot);
	if (found_key.objectid != search_key->objectid ||
	    found_key.type != BTRFS_ROOT_ITEM_KEY) {
		ret = 1;
		goto out;
	}

	if (root_item)
		btrfs_read_root_item(l, slot, root_item);
	if (root_key)
		memcpy(root_key, &found_key, sizeof(found_key));
out:
	btrfs_release_path(path);
	return ret;
}

void btrfs_set_root_node(struct btrfs_root_item *item,
			 struct extent_buffer *node)
{
	btrfs_set_root_bytenr(item, node->start);
	btrfs_set_root_level(item, btrfs_header_level(node));
	btrfs_set_root_generation(item, btrfs_header_generation(node));
}

/*
 * copy the data in 'item' into the btree
 */
int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
		      *root, struct btrfs_key *key, struct btrfs_root_item
		      *item)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	struct extent_buffer *l;
	int ret;
	int slot;
	unsigned long ptr;
	u32 old_len;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	ret = btrfs_search_slot(trans, root, key, path, 0, 1);
	if (ret < 0) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	if (ret != 0) {
		btrfs_print_leaf(path->nodes[0]);
		btrfs_crit(fs_info, "unable to update root key %llu %u %llu",
			   key->objectid, key->type, key->offset);
		BUG_ON(1);
	}

	l = path->nodes[0];
	slot = path->slots[0];
	ptr = btrfs_item_ptr_offset(l, slot);
	old_len = btrfs_item_size_nr(l, slot);

	/*
	 * If this is the first time we update the root item which originated
	 * from an older kernel, we need to enlarge the item size to make room
	 * for the added fields.
	 */
	if (old_len < sizeof(*item)) {
		btrfs_release_path(path);
		ret = btrfs_search_slot(trans, root, key, path,
				-1, 1);
		if (ret < 0) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}

		ret = btrfs_del_item(trans, root, path);
		if (ret < 0) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}
		btrfs_release_path(path);
		ret = btrfs_insert_empty_item(trans, root, path,
				key, sizeof(*item));
		if (ret < 0) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}
		l = path->nodes[0];
		slot = path->slots[0];
		ptr = btrfs_item_ptr_offset(l, slot);
	}

	/*
	 * Update generation_v2 so at the next mount we know the new root
	 * fields are valid.
	 */
	btrfs_set_root_generation_v2(item, btrfs_root_generation(item));

	write_extent_buffer(l, item, ptr, sizeof(*item));
	btrfs_mark_buffer_dirty(path->nodes[0]);
out:
	btrfs_free_path(path);
	return ret;
}

int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		      const struct btrfs_key *key, struct btrfs_root_item *item)
{
	/*
	 * Make sure generation v1 and v2 match. See update_root for details.
	 */
	btrfs_set_root_generation_v2(item, btrfs_root_generation(item));
	return btrfs_insert_item(trans, root, key, item, sizeof(*item));
}

int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct extent_buffer *leaf;
	struct btrfs_path *path;
	struct btrfs_key key;
	struct btrfs_key root_key;
	struct btrfs_root *root;
	int err = 0;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	key.objectid = BTRFS_ORPHAN_OBJECTID;
	key.type = BTRFS_ORPHAN_ITEM_KEY;
	key.offset = 0;

	root_key.type = BTRFS_ROOT_ITEM_KEY;
	root_key.offset = (u64)-1;

	while (1) {
		ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0);
		if (ret < 0) {
			err = ret;
			break;
		}

		leaf = path->nodes[0];
		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(tree_root, path);
			if (ret < 0)
				err = ret;
			if (ret != 0)
				break;
			leaf = path->nodes[0];
		}

		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
		btrfs_release_path(path);

		if (key.objectid != BTRFS_ORPHAN_OBJECTID ||
		    key.type != BTRFS_ORPHAN_ITEM_KEY)
			break;

		root_key.objectid = key.offset;
		key.offset++;

		/*
		 * The root might have been inserted already, as before we look
		 * for orphan roots, log replay might have happened, which
		 * triggers a transaction commit and qgroup accounting, which
		 * in turn reads and inserts fs roots while doing backref
		 * walking.
		 */
		root = btrfs_lookup_fs_root(fs_info, root_key.objectid);
		if (root) {
			WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
					  &root->state));
			if (btrfs_root_refs(&root->root_item) == 0)
				btrfs_add_dead_root(root);
			continue;
		}

		root = btrfs_read_fs_root(tree_root, &root_key);
		err = PTR_ERR_OR_ZERO(root);
		if (err && err != -ENOENT) {
			break;
		} else if (err == -ENOENT) {
			struct btrfs_trans_handle *trans;

			btrfs_release_path(path);

			trans = btrfs_join_transaction(tree_root);
			if (IS_ERR(trans)) {
				err = PTR_ERR(trans);
				btrfs_handle_fs_error(fs_info, err,
					    "Failed to start trans to delete orphan item");
				break;
			}
			err = btrfs_del_orphan_item(trans, tree_root,
						    root_key.objectid);
			btrfs_end_transaction(trans);
			if (err) {
				btrfs_handle_fs_error(fs_info, err,
					    "Failed to delete root orphan item");
				break;
			}
			continue;
		}

		err = btrfs_init_fs_root(root);
		if (err) {
			btrfs_free_fs_root(root);
			break;
		}

		set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);

		err = btrfs_insert_fs_root(fs_info, root);
		if (err) {
			BUG_ON(err == -EEXIST);
			btrfs_free_fs_root(root);
			break;
		}

		if (btrfs_root_refs(&root->root_item) == 0)
			btrfs_add_dead_root(root);
	}

	btrfs_free_path(path);
	return err;
}

/* drop the root item for 'key' from the tree root */
int btrfs_del_root(struct btrfs_trans_handle *trans,
		   struct btrfs_fs_info *fs_info, const struct btrfs_key *key)
{
	struct btrfs_root *root = fs_info->tree_root;
	struct btrfs_path *path;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
	ret = btrfs_search_slot(trans, root, key, path, -1, 1);
	if (ret < 0)
		goto out;

	BUG_ON(ret != 0);

	ret = btrfs_del_item(trans, root, path);
out:
	btrfs_free_path(path);
	return ret;
}

int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
		       struct btrfs_fs_info *fs_info,
		       u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
		       const char *name, int name_len)

{
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_path *path;
	struct btrfs_root_ref *ref;
	struct extent_buffer *leaf;
	struct btrfs_key key;
	unsigned long ptr;
	int err = 0;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	key.objectid = root_id;
	key.type = BTRFS_ROOT_BACKREF_KEY;
	key.offset = ref_id;
again:
	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
	BUG_ON(ret < 0);
	if (ret == 0) {
		leaf = path->nodes[0];
		ref = btrfs_item_ptr(leaf, path->slots[0],
				     struct btrfs_root_ref);

		WARN_ON(btrfs_root_ref_dirid(leaf, ref) != dirid);
		WARN_ON(btrfs_root_ref_name_len(leaf, ref) != name_len);
		ptr = (unsigned long)(ref + 1);
		ret = btrfs_is_name_len_valid(leaf, path->slots[0], ptr,
					      name_len);
		if (!ret) {
			err = -EIO;
			goto out;
		}

		WARN_ON(memcmp_extent_buffer(leaf, name, ptr, name_len));
		*sequence = btrfs_root_ref_sequence(leaf, ref);

		ret = btrfs_del_item(trans, tree_root, path);
		if (ret) {
			err = ret;
			goto out;
		}
	} else
		err = -ENOENT;

	if (key.type == BTRFS_ROOT_BACKREF_KEY) {
		btrfs_release_path(path);
		key.objectid = ref_id;
		key.type = BTRFS_ROOT_REF_KEY;
		key.offset = root_id;
		goto again;
	}

out:
	btrfs_free_path(path);
	return err;
}

/*
 * add a btrfs_root_ref item.  type is either BTRFS_ROOT_REF_KEY
 * or BTRFS_ROOT_BACKREF_KEY.
 *
 * The dirid, sequence, name and name_len refer to the directory entry
 * that is referencing the root.
 *
 * For a forward ref, the root_id is the id of the tree referencing
 * the root and ref_id is the id of the subvol  or snapshot.
 *
 * For a back ref the root_id is the id of the subvol or snapshot and
 * ref_id is the id of the tree referencing it.
 *
 * Will return 0, -ENOMEM, or anything from the CoW path
 */
int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
		       struct btrfs_fs_info *fs_info,
		       u64 root_id, u64 ref_id, u64 dirid, u64 sequence,
		       const char *name, int name_len)
{
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_key key;
	int ret;
	struct btrfs_path *path;
	struct btrfs_root_ref *ref;
	struct extent_buffer *leaf;
	unsigned long ptr;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	key.objectid = root_id;
	key.type = BTRFS_ROOT_BACKREF_KEY;
	key.offset = ref_id;
again:
	ret = btrfs_insert_empty_item(trans, tree_root, path, &key,
				      sizeof(*ref) + name_len);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		btrfs_free_path(path);
		return ret;
	}

	leaf = path->nodes[0];
	ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref);
	btrfs_set_root_ref_dirid(leaf, ref, dirid);
	btrfs_set_root_ref_sequence(leaf, ref, sequence);
	btrfs_set_root_ref_name_len(leaf, ref, name_len);
	ptr = (unsigned long)(ref + 1);
	write_extent_buffer(leaf, name, ptr, name_len);
	btrfs_mark_buffer_dirty(leaf);

	if (key.type == BTRFS_ROOT_BACKREF_KEY) {
		btrfs_release_path(path);
		key.objectid = ref_id;
		key.type = BTRFS_ROOT_REF_KEY;
		key.offset = root_id;
		goto again;
	}

	btrfs_free_path(path);
	return 0;
}

/*
 * Old btrfs forgets to init root_item->flags and root_item->byte_limit
 * for subvolumes. To work around this problem, we steal a bit from
 * root_item->inode_item->flags, and use it to indicate if those fields
 * have been properly initialized.
 */
void btrfs_check_and_init_root_item(struct btrfs_root_item *root_item)
{
	u64 inode_flags = btrfs_stack_inode_flags(&root_item->inode);

	if (!(inode_flags & BTRFS_INODE_ROOT_ITEM_INIT)) {
		inode_flags |= BTRFS_INODE_ROOT_ITEM_INIT;
		btrfs_set_stack_inode_flags(&root_item->inode, inode_flags);
		btrfs_set_root_flags(root_item, 0);
		btrfs_set_root_limit(root_item, 0);
	}
}

void btrfs_update_root_times(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root)
{
	struct btrfs_root_item *item = &root->root_item;
	struct timespec ct;

	ktime_get_real_ts(&ct);
	spin_lock(&root->root_item_lock);
	btrfs_set_root_ctransid(item, trans->transid);
	btrfs_set_stack_timespec_sec(&item->ctime, ct.tv_sec);
	btrfs_set_stack_timespec_nsec(&item->ctime, ct.tv_nsec);
	spin_unlock(&root->root_item_lock);
}