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
|
/*
* 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/fs.h>
#include <linux/blkdev.h>
#include <linux/crc32c.h>
#include <linux/scatterlist.h>
#include <linux/swap.h>
#include <linux/radix-tree.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h> // for block_sync_page
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#if 0
static int check_tree_block(struct btrfs_root *root, struct extent_buffer *buf)
{
if (extent_buffer_blocknr(buf) != btrfs_header_blocknr(buf)) {
printk(KERN_CRIT "buf blocknr(buf) is %llu, header is %llu\n",
(unsigned long long)extent_buffer_blocknr(buf),
(unsigned long long)btrfs_header_blocknr(buf));
return 1;
}
return 0;
}
#endif
struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
u64 blocknr)
{
struct inode *btree_inode = root->fs_info->btree_inode;
struct extent_buffer *eb;
eb = find_extent_buffer(&BTRFS_I(btree_inode)->extent_tree,
blocknr * root->sectorsize,
root->sectorsize, GFP_NOFS);
if (eb)
eb->alloc_addr = (unsigned long)__builtin_return_address(0);
return eb;
}
struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
u64 blocknr)
{
struct inode *btree_inode = root->fs_info->btree_inode;
struct extent_buffer *eb;
eb = alloc_extent_buffer(&BTRFS_I(btree_inode)->extent_tree,
blocknr * root->sectorsize,
root->sectorsize, GFP_NOFS);
eb->alloc_addr = (unsigned long)__builtin_return_address(0);
return eb;
}
struct extent_map *btree_get_extent(struct inode *inode, struct page *page,
size_t page_offset, u64 start, u64 end,
int create)
{
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct extent_map *em;
int ret;
again:
em = lookup_extent_mapping(em_tree, start, end);
if (em) {
goto out;
}
em = alloc_extent_map(GFP_NOFS);
if (!em) {
em = ERR_PTR(-ENOMEM);
goto out;
}
em->start = 0;
em->end = (i_size_read(inode) & ~((u64)PAGE_CACHE_SIZE -1)) - 1;
em->block_start = 0;
em->block_end = em->end;
em->bdev = inode->i_sb->s_bdev;
ret = add_extent_mapping(em_tree, em);
if (ret == -EEXIST) {
free_extent_map(em);
em = NULL;
goto again;
} else if (ret) {
em = ERR_PTR(ret);
}
out:
return em;
}
static int btree_writepage(struct page *page, struct writeback_control *wbc)
{
struct extent_map_tree *tree;
tree = &BTRFS_I(page->mapping->host)->extent_tree;
return extent_write_full_page(tree, page, btree_get_extent, wbc);
}
int btree_readpage(struct file *file, struct page *page)
{
struct extent_map_tree *tree;
tree = &BTRFS_I(page->mapping->host)->extent_tree;
return extent_read_full_page(tree, page, btree_get_extent);
}
static int btree_releasepage(struct page *page, gfp_t unused_gfp_flags)
{
struct extent_map_tree *tree;
int ret;
BUG_ON(page->private != 1);
tree = &BTRFS_I(page->mapping->host)->extent_tree;
ret = try_release_extent_mapping(tree, page);
if (ret == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
}
return ret;
}
static void btree_invalidatepage(struct page *page, unsigned long offset)
{
struct extent_map_tree *tree;
tree = &BTRFS_I(page->mapping->host)->extent_tree;
extent_invalidatepage(tree, page, offset);
btree_releasepage(page, GFP_NOFS);
}
int btrfs_csum_data(struct btrfs_root * root, char *data, size_t len,
char *result)
{
return 0;
#if 0
u32 crc;
crc = crc32c(0, data, len);
memcpy(result, &crc, BTRFS_CRC32_SIZE);
return 0;
#endif
}
#if 0
static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
int verify)
{
return 0;
char result[BTRFS_CRC32_SIZE];
int ret;
struct btrfs_node *node;
ret = btrfs_csum_data(root, bh->b_data + BTRFS_CSUM_SIZE,
bh->b_size - BTRFS_CSUM_SIZE, result);
if (ret)
return ret;
if (verify) {
if (memcmp(bh->b_data, result, BTRFS_CRC32_SIZE)) {
printk("btrfs: %s checksum verify failed on %llu\n",
root->fs_info->sb->s_id,
(unsigned long long)bh_blocknr(bh));
return 1;
}
} else {
node = btrfs_buffer_node(bh);
memcpy(node->header.csum, result, BTRFS_CRC32_SIZE);
}
return 0;
}
#endif
#if 0
static int btree_writepage(struct page *page, struct writeback_control *wbc)
{
struct buffer_head *bh;
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
struct buffer_head *head;
if (!page_has_buffers(page)) {
create_empty_buffers(page, root->fs_info->sb->s_blocksize,
(1 << BH_Dirty)|(1 << BH_Uptodate));
}
head = page_buffers(page);
bh = head;
do {
if (buffer_dirty(bh))
csum_tree_block(root, bh, 0);
bh = bh->b_this_page;
} while (bh != head);
return block_write_full_page(page, btree_get_block, wbc);
}
#endif
static struct address_space_operations btree_aops = {
.readpage = btree_readpage,
.writepage = btree_writepage,
.releasepage = btree_releasepage,
.invalidatepage = btree_invalidatepage,
.sync_page = block_sync_page,
};
int readahead_tree_block(struct btrfs_root *root, u64 blocknr)
{
struct extent_buffer *buf = NULL;
struct inode *btree_inode = root->fs_info->btree_inode;
int ret = 0;
buf = btrfs_find_create_tree_block(root, blocknr);
if (!buf)
return 0;
read_extent_buffer_pages(&BTRFS_I(btree_inode)->extent_tree,
buf, 0);
free_extent_buffer(buf);
return ret;
}
struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 blocknr)
{
struct extent_buffer *buf = NULL;
struct inode *btree_inode = root->fs_info->btree_inode;
buf = btrfs_find_create_tree_block(root, blocknr);
if (!buf)
return NULL;
read_extent_buffer_pages(&BTRFS_I(btree_inode)->extent_tree,
buf, 1);
buf->alloc_addr = (unsigned long)__builtin_return_address(0);
return buf;
}
int clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf)
{
struct inode *btree_inode = root->fs_info->btree_inode;
clear_extent_buffer_dirty(&BTRFS_I(btree_inode)->extent_tree, buf);
return 0;
}
int wait_on_tree_block_writeback(struct btrfs_root *root,
struct extent_buffer *buf)
{
struct inode *btree_inode = root->fs_info->btree_inode;
wait_on_extent_buffer_writeback(&BTRFS_I(btree_inode)->extent_tree,
buf);
return 0;
}
int set_tree_block_dirty(struct btrfs_root *root, struct extent_buffer *buf)
{
struct inode *btree_inode = root->fs_info->btree_inode;
set_extent_buffer_dirty(&BTRFS_I(btree_inode)->extent_tree, buf);
return 0;
}
static int __setup_root(int blocksize,
struct btrfs_root *root,
struct btrfs_fs_info *fs_info,
u64 objectid)
{
root->node = NULL;
root->inode = NULL;
root->commit_root = NULL;
root->sectorsize = blocksize;
root->nodesize = blocksize;
root->leafsize = blocksize;
root->ref_cows = 0;
root->fs_info = fs_info;
root->objectid = objectid;
root->last_trans = 0;
root->highest_inode = 0;
root->last_inode_alloc = 0;
root->name = NULL;
memset(&root->root_key, 0, sizeof(root->root_key));
memset(&root->root_item, 0, sizeof(root->root_item));
memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
memset(&root->root_kobj, 0, sizeof(root->root_kobj));
init_completion(&root->kobj_unregister);
init_rwsem(&root->snap_sem);
root->defrag_running = 0;
root->defrag_level = 0;
root->root_key.objectid = objectid;
return 0;
}
static int find_and_setup_root(int blocksize,
struct btrfs_root *tree_root,
struct btrfs_fs_info *fs_info,
u64 objectid,
struct btrfs_root *root)
{
int ret;
__setup_root(blocksize, root, fs_info, objectid);
ret = btrfs_find_last_root(tree_root, objectid,
&root->root_item, &root->root_key);
BUG_ON(ret);
root->node = read_tree_block(root,
btrfs_root_blocknr(&root->root_item));
BUG_ON(!root->node);
return 0;
}
struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_fs_info *fs_info,
struct btrfs_key *location)
{
struct btrfs_root *root;
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_path *path;
struct extent_buffer *l;
u64 highest_inode;
int ret = 0;
root = kzalloc(sizeof(*root), GFP_NOFS);
if (!root)
return ERR_PTR(-ENOMEM);
if (location->offset == (u64)-1) {
ret = find_and_setup_root(fs_info->sb->s_blocksize,
fs_info->tree_root, fs_info,
location->objectid, root);
if (ret) {
kfree(root);
return ERR_PTR(ret);
}
goto insert;
}
__setup_root(fs_info->sb->s_blocksize, root, fs_info,
location->objectid);
path = btrfs_alloc_path();
BUG_ON(!path);
ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0);
if (ret != 0) {
if (ret > 0)
ret = -ENOENT;
goto out;
}
l = path->nodes[0];
read_extent_buffer(l, &root->root_item,
btrfs_item_ptr_offset(l, path->slots[0]),
sizeof(root->root_item));
ret = 0;
out:
btrfs_release_path(root, path);
btrfs_free_path(path);
if (ret) {
kfree(root);
return ERR_PTR(ret);
}
root->node = read_tree_block(root,
btrfs_root_blocknr(&root->root_item));
BUG_ON(!root->node);
insert:
root->ref_cows = 1;
ret = btrfs_find_highest_inode(root, &highest_inode);
if (ret == 0) {
root->highest_inode = highest_inode;
root->last_inode_alloc = highest_inode;
}
return root;
}
struct btrfs_root *btrfs_read_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_key *location,
const char *name, int namelen)
{
struct btrfs_root *root;
int ret;
root = radix_tree_lookup(&fs_info->fs_roots_radix,
(unsigned long)location->objectid);
if (root)
return root;
root = btrfs_read_fs_root_no_radix(fs_info, location);
if (IS_ERR(root))
return root;
ret = radix_tree_insert(&fs_info->fs_roots_radix,
(unsigned long)root->root_key.objectid,
root);
if (ret) {
free_extent_buffer(root->node);
kfree(root);
return ERR_PTR(ret);
}
ret = btrfs_set_root_name(root, name, namelen);
if (ret) {
free_extent_buffer(root->node);
kfree(root);
return ERR_PTR(ret);
}
ret = btrfs_sysfs_add_root(root);
if (ret) {
free_extent_buffer(root->node);
kfree(root->name);
kfree(root);
return ERR_PTR(ret);
}
ret = btrfs_find_dead_roots(fs_info->tree_root,
root->root_key.objectid, root);
BUG_ON(ret);
return root;
}
struct btrfs_root *open_ctree(struct super_block *sb)
{
struct btrfs_root *extent_root = kmalloc(sizeof(struct btrfs_root),
GFP_NOFS);
struct btrfs_root *tree_root = kmalloc(sizeof(struct btrfs_root),
GFP_NOFS);
struct btrfs_fs_info *fs_info = kmalloc(sizeof(*fs_info),
GFP_NOFS);
int ret;
int err = -EIO;
struct btrfs_super_block *disk_super;
if (!extent_root || !tree_root || !fs_info) {
err = -ENOMEM;
goto fail;
}
INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_NOFS);
INIT_LIST_HEAD(&fs_info->trans_list);
INIT_LIST_HEAD(&fs_info->dead_roots);
memset(&fs_info->super_kobj, 0, sizeof(fs_info->super_kobj));
init_completion(&fs_info->kobj_unregister);
sb_set_blocksize(sb, 4096);
fs_info->running_transaction = NULL;
fs_info->last_trans_committed = 0;
fs_info->tree_root = tree_root;
fs_info->extent_root = extent_root;
fs_info->sb = sb;
fs_info->btree_inode = new_inode(sb);
fs_info->btree_inode->i_ino = 1;
fs_info->btree_inode->i_nlink = 1;
fs_info->btree_inode->i_size = sb->s_bdev->bd_inode->i_size;
fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree,
fs_info->btree_inode->i_mapping,
GFP_NOFS);
extent_map_tree_init(&fs_info->free_space_cache,
fs_info->btree_inode->i_mapping, GFP_NOFS);
extent_map_tree_init(&fs_info->block_group_cache,
fs_info->btree_inode->i_mapping, GFP_NOFS);
extent_map_tree_init(&fs_info->pinned_extents,
fs_info->btree_inode->i_mapping, GFP_NOFS);
extent_map_tree_init(&fs_info->pending_del,
fs_info->btree_inode->i_mapping, GFP_NOFS);
extent_map_tree_init(&fs_info->extent_ins,
fs_info->btree_inode->i_mapping, GFP_NOFS);
fs_info->do_barriers = 1;
fs_info->closing = 0;
INIT_DELAYED_WORK(&fs_info->trans_work, btrfs_transaction_cleaner);
BTRFS_I(fs_info->btree_inode)->root = tree_root;
memset(&BTRFS_I(fs_info->btree_inode)->location, 0,
sizeof(struct btrfs_key));
insert_inode_hash(fs_info->btree_inode);
mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
mutex_init(&fs_info->trans_mutex);
mutex_init(&fs_info->fs_mutex);
__setup_root(sb->s_blocksize, tree_root,
fs_info, BTRFS_ROOT_TREE_OBJECTID);
fs_info->sb_buffer = read_tree_block(tree_root,
BTRFS_SUPER_INFO_OFFSET /
sb->s_blocksize);
if (!fs_info->sb_buffer)
goto fail_iput;
read_extent_buffer(fs_info->sb_buffer, &fs_info->super_copy, 0,
sizeof(fs_info->super_copy));
read_extent_buffer(fs_info->sb_buffer, fs_info->fsid,
(unsigned long)btrfs_super_fsid(fs_info->sb_buffer),
BTRFS_FSID_SIZE);
disk_super = &fs_info->super_copy;
if (!btrfs_super_root(disk_super))
goto fail_sb_buffer;
i_size_write(fs_info->btree_inode,
btrfs_super_total_blocks(disk_super) <<
fs_info->btree_inode->i_blkbits);
if (strncmp((char *)(&disk_super->magic), BTRFS_MAGIC,
sizeof(disk_super->magic))) {
printk("btrfs: valid FS not found on %s\n", sb->s_id);
goto fail_sb_buffer;
}
tree_root->node = read_tree_block(tree_root,
btrfs_super_root(disk_super));
if (!tree_root->node)
goto fail_sb_buffer;
mutex_lock(&fs_info->fs_mutex);
ret = find_and_setup_root(sb->s_blocksize, tree_root, fs_info,
BTRFS_EXTENT_TREE_OBJECTID, extent_root);
if (ret) {
mutex_unlock(&fs_info->fs_mutex);
goto fail_tree_root;
}
btrfs_read_block_groups(extent_root);
fs_info->generation = btrfs_super_generation(disk_super) + 1;
mutex_unlock(&fs_info->fs_mutex);
return tree_root;
fail_tree_root:
free_extent_buffer(tree_root->node);
fail_sb_buffer:
free_extent_buffer(fs_info->sb_buffer);
fail_iput:
iput(fs_info->btree_inode);
fail:
kfree(extent_root);
kfree(tree_root);
kfree(fs_info);
return ERR_PTR(err);
}
int write_ctree_super(struct btrfs_trans_handle *trans, struct btrfs_root
*root)
{
int ret;
struct extent_buffer *super = root->fs_info->sb_buffer;
struct inode *btree_inode = root->fs_info->btree_inode;
set_extent_buffer_dirty(&BTRFS_I(btree_inode)->extent_tree, super);
ret = sync_page_range_nolock(btree_inode, btree_inode->i_mapping,
super->start, super->len);
return ret;
}
int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
{
radix_tree_delete(&fs_info->fs_roots_radix,
(unsigned long)root->root_key.objectid);
btrfs_sysfs_del_root(root);
if (root->inode)
iput(root->inode);
if (root->node)
free_extent_buffer(root->node);
if (root->commit_root)
free_extent_buffer(root->commit_root);
if (root->name)
kfree(root->name);
kfree(root);
return 0;
}
static int del_fs_roots(struct btrfs_fs_info *fs_info)
{
int ret;
struct btrfs_root *gang[8];
int i;
while(1) {
ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
(void **)gang, 0,
ARRAY_SIZE(gang));
if (!ret)
break;
for (i = 0; i < ret; i++)
btrfs_free_fs_root(fs_info, gang[i]);
}
return 0;
}
int close_ctree(struct btrfs_root *root)
{
int ret;
struct btrfs_trans_handle *trans;
struct btrfs_fs_info *fs_info = root->fs_info;
fs_info->closing = 1;
btrfs_transaction_flush_work(root);
mutex_lock(&fs_info->fs_mutex);
btrfs_defrag_dirty_roots(root->fs_info);
trans = btrfs_start_transaction(root, 1);
ret = btrfs_commit_transaction(trans, root);
/* run commit again to drop the original snapshot */
trans = btrfs_start_transaction(root, 1);
btrfs_commit_transaction(trans, root);
ret = btrfs_write_and_wait_transaction(NULL, root);
BUG_ON(ret);
write_ctree_super(NULL, root);
mutex_unlock(&fs_info->fs_mutex);
if (fs_info->extent_root->node)
free_extent_buffer(fs_info->extent_root->node);
if (fs_info->tree_root->node)
free_extent_buffer(fs_info->tree_root->node);
free_extent_buffer(fs_info->sb_buffer);
truncate_inode_pages(fs_info->btree_inode->i_mapping, 0);
iput(fs_info->btree_inode);
btrfs_free_block_groups(root->fs_info);
del_fs_roots(fs_info);
kfree(fs_info->extent_root);
kfree(fs_info->tree_root);
return 0;
}
int btrfs_buffer_uptodate(struct extent_buffer *buf)
{
struct inode *btree_inode = buf->first_page->mapping->host;
return extent_buffer_uptodate(&BTRFS_I(btree_inode)->extent_tree, buf);
}
int btrfs_set_buffer_uptodate(struct extent_buffer *buf)
{
struct inode *btree_inode = buf->first_page->mapping->host;
return set_extent_buffer_uptodate(&BTRFS_I(btree_inode)->extent_tree,
buf);
}
void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
{
struct btrfs_root *root = BTRFS_I(buf->first_page->mapping->host)->root;
u64 transid = btrfs_header_generation(buf);
struct inode *btree_inode = root->fs_info->btree_inode;
if (transid != root->fs_info->generation) {
printk(KERN_CRIT "transid mismatch buffer %llu, found %Lu running %Lu\n",
(unsigned long long)extent_buffer_blocknr(buf),
transid, root->fs_info->generation);
WARN_ON(1);
}
set_extent_buffer_dirty(&BTRFS_I(btree_inode)->extent_tree, buf);
}
void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr)
{
balance_dirty_pages_ratelimited_nr(
root->fs_info->btree_inode->i_mapping, nr);
}
|