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
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
|
/*
* fs/f2fs/recovery.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
/*
* Roll forward recovery scenarios.
*
* [Term] F: fsync_mark, D: dentry_mark
*
* 1. inode(x) | CP | inode(x) | dnode(F)
* -> Update the latest inode(x).
*
* 2. inode(x) | CP | inode(F) | dnode(F)
* -> No problem.
*
* 3. inode(x) | CP | dnode(F) | inode(x)
* -> Recover to the latest dnode(F), and drop the last inode(x)
*
* 4. inode(x) | CP | dnode(F) | inode(F)
* -> No problem.
*
* 5. CP | inode(x) | dnode(F)
* -> The inode(DF) was missing. Should drop this dnode(F).
*
* 6. CP | inode(DF) | dnode(F)
* -> No problem.
*
* 7. CP | dnode(F) | inode(DF)
* -> If f2fs_iget fails, then goto next to find inode(DF).
*
* 8. CP | dnode(F) | inode(x)
* -> If f2fs_iget fails, then goto next to find inode(DF).
* But it will fail due to no inode(DF).
*/
static struct kmem_cache *fsync_entry_slab;
bool space_for_roll_forward(struct f2fs_sb_info *sbi)
{
s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
if (sbi->last_valid_block_count + nalloc > sbi->user_block_count)
return false;
return true;
}
static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
nid_t ino)
{
struct fsync_inode_entry *entry;
list_for_each_entry(entry, head, list)
if (entry->inode->i_ino == ino)
return entry;
return NULL;
}
static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
struct list_head *head, nid_t ino, bool quota_inode)
{
struct inode *inode;
struct fsync_inode_entry *entry;
int err;
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
err = dquot_initialize(inode);
if (err)
goto err_out;
if (quota_inode) {
err = dquot_alloc_inode(inode);
if (err)
goto err_out;
}
entry = f2fs_kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
entry->inode = inode;
list_add_tail(&entry->list, head);
return entry;
err_out:
iput(inode);
return ERR_PTR(err);
}
static void del_fsync_inode(struct fsync_inode_entry *entry)
{
iput(entry->inode);
list_del(&entry->list);
kmem_cache_free(fsync_entry_slab, entry);
}
static int recover_dentry(struct inode *inode, struct page *ipage,
struct list_head *dir_list)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
struct f2fs_dir_entry *de;
struct fscrypt_name fname;
struct page *page;
struct inode *dir, *einode;
struct fsync_inode_entry *entry;
int err = 0;
char *name;
entry = get_fsync_inode(dir_list, pino);
if (!entry) {
entry = add_fsync_inode(F2FS_I_SB(inode), dir_list,
pino, false);
if (IS_ERR(entry)) {
dir = ERR_CAST(entry);
err = PTR_ERR(entry);
goto out;
}
}
dir = entry->inode;
memset(&fname, 0, sizeof(struct fscrypt_name));
fname.disk_name.len = le32_to_cpu(raw_inode->i_namelen);
fname.disk_name.name = raw_inode->i_name;
if (unlikely(fname.disk_name.len > F2FS_NAME_LEN)) {
WARN_ON(1);
err = -ENAMETOOLONG;
goto out;
}
retry:
de = __f2fs_find_entry(dir, &fname, &page);
if (de && inode->i_ino == le32_to_cpu(de->ino))
goto out_unmap_put;
if (de) {
einode = f2fs_iget_retry(inode->i_sb, le32_to_cpu(de->ino));
if (IS_ERR(einode)) {
WARN_ON(1);
err = PTR_ERR(einode);
if (err == -ENOENT)
err = -EEXIST;
goto out_unmap_put;
}
err = dquot_initialize(einode);
if (err) {
iput(einode);
goto out_unmap_put;
}
err = acquire_orphan_inode(F2FS_I_SB(inode));
if (err) {
iput(einode);
goto out_unmap_put;
}
f2fs_delete_entry(de, page, dir, einode);
iput(einode);
goto retry;
} else if (IS_ERR(page)) {
err = PTR_ERR(page);
} else {
err = __f2fs_do_add_link(dir, &fname, inode,
inode->i_ino, inode->i_mode);
}
if (err == -ENOMEM)
goto retry;
goto out;
out_unmap_put:
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
out:
if (file_enc_name(inode))
name = "<encrypted>";
else
name = raw_inode->i_name;
f2fs_msg(inode->i_sb, KERN_NOTICE,
"%s: ino = %x, name = %s, dir = %lx, err = %d",
__func__, ino_of_node(ipage), name,
IS_ERR(dir) ? 0 : dir->i_ino, err);
return err;
}
static void recover_inode(struct inode *inode, struct page *page)
{
struct f2fs_inode *raw = F2FS_INODE(page);
char *name;
inode->i_mode = le16_to_cpu(raw->i_mode);
f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime);
inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
inode->i_atime.tv_nsec = le32_to_cpu(raw->i_atime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
F2FS_I(inode)->i_advise = raw->i_advise;
F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags);
if (file_enc_name(inode))
name = "<encrypted>";
else
name = F2FS_INODE(page)->i_name;
f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
ino_of_node(page), name);
}
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
bool check_only)
{
struct curseg_info *curseg;
struct page *page = NULL;
block_t blkaddr;
int err = 0;
/* get node pages in the current segment */
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
struct fsync_inode_entry *entry;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
page = get_tmp_page(sbi, blkaddr);
if (!is_recoverable_dnode(page))
break;
if (!is_fsync_dnode(page))
goto next;
entry = get_fsync_inode(head, ino_of_node(page));
if (!entry) {
bool quota_inode = false;
if (!check_only &&
IS_INODE(page) && is_dent_dnode(page)) {
err = recover_inode_page(sbi, page);
if (err)
break;
quota_inode = true;
}
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
entry = add_fsync_inode(sbi, head, ino_of_node(page),
quota_inode);
if (IS_ERR(entry)) {
err = PTR_ERR(entry);
if (err == -ENOENT) {
err = 0;
goto next;
}
break;
}
}
entry->blkaddr = blkaddr;
if (IS_INODE(page) && is_dent_dnode(page))
entry->last_dentry = blkaddr;
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
ra_meta_pages_cond(sbi, blkaddr);
}
f2fs_put_page(page, 1);
return err;
}
static void destroy_fsync_dnodes(struct list_head *head)
{
struct fsync_inode_entry *entry, *tmp;
list_for_each_entry_safe(entry, tmp, head, list)
del_fsync_inode(entry);
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
block_t blkaddr, struct dnode_of_data *dn)
{
struct seg_entry *sentry;
unsigned int segno = GET_SEGNO(sbi, blkaddr);
unsigned short blkoff = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
struct f2fs_summary_block *sum_node;
struct f2fs_summary sum;
struct page *sum_page, *node_page;
struct dnode_of_data tdn = *dn;
nid_t ino, nid;
struct inode *inode;
unsigned int offset;
block_t bidx;
int i;
sentry = get_seg_entry(sbi, segno);
if (!f2fs_test_bit(blkoff, sentry->cur_valid_map))
return 0;
/* Get the previous summary */
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
struct curseg_info *curseg = CURSEG_I(sbi, i);
if (curseg->segno == segno) {
sum = curseg->sum_blk->entries[blkoff];
goto got_it;
}
}
sum_page = get_sum_page(sbi, segno);
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
sum = sum_node->entries[blkoff];
f2fs_put_page(sum_page, 1);
got_it:
/* Use the locked dnode page and inode */
nid = le32_to_cpu(sum.nid);
if (dn->inode->i_ino == nid) {
tdn.nid = nid;
if (!dn->inode_page_locked)
lock_page(dn->inode_page);
tdn.node_page = dn->inode_page;
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
goto truncate_out;
} else if (dn->nid == nid) {
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
goto truncate_out;
}
/* Get the node page */
node_page = get_node_page(sbi, nid);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
offset = ofs_of_node(node_page);
ino = ino_of_node(node_page);
f2fs_put_page(node_page, 1);
if (ino != dn->inode->i_ino) {
int ret;
/* Deallocate previous index in the node page */
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return PTR_ERR(inode);
ret = dquot_initialize(inode);
if (ret) {
iput(inode);
return ret;
}
} else {
inode = dn->inode;
}
bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
/*
* if inode page is locked, unlock temporarily, but its reference
* count keeps alive.
*/
if (ino == dn->inode->i_ino && dn->inode_page_locked)
unlock_page(dn->inode_page);
set_new_dnode(&tdn, inode, NULL, NULL, 0);
if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
goto out;
if (tdn.data_blkaddr == blkaddr)
truncate_data_blocks_range(&tdn, 1);
f2fs_put_dnode(&tdn);
out:
if (ino != dn->inode->i_ino)
iput(inode);
else if (dn->inode_page_locked)
lock_page(dn->inode_page);
return 0;
truncate_out:
if (datablock_addr(tdn.inode, tdn.node_page,
tdn.ofs_in_node) == blkaddr)
truncate_data_blocks_range(&tdn, 1);
if (dn->inode->i_ino == nid && !dn->inode_page_locked)
unlock_page(dn->inode_page);
return 0;
}
static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
struct page *page, block_t blkaddr)
{
struct dnode_of_data dn;
struct node_info ni;
unsigned int start, end;
int err = 0, recovered = 0;
/* step 1: recover xattr */
if (IS_INODE(page)) {
recover_inline_xattr(inode, page);
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
err = recover_xattr_data(inode, page, blkaddr);
if (!err)
recovered++;
goto out;
}
/* step 2: recover inline data */
if (recover_inline_data(inode, page))
goto out;
/* step 3: recover data indices */
start = start_bidx_of_node(ofs_of_node(page), inode);
end = start + ADDRS_PER_PAGE(page, inode);
set_new_dnode(&dn, inode, NULL, NULL, 0);
retry_dn:
err = get_dnode_of_data(&dn, start, ALLOC_NODE);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_dn;
}
goto out;
}
f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
get_node_info(sbi, dn.nid, &ni);
f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
if (ofs_of_node(dn.node_page) != ofs_of_node(page)) {
f2fs_msg(sbi->sb, KERN_WARNING,
"Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u",
inode->i_ino, ofs_of_node(dn.node_page),
ofs_of_node(page));
err = -EFSCORRUPTED;
goto err;
}
for (; start < end; start++, dn.ofs_in_node++) {
block_t src, dest;
src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
dest = datablock_addr(dn.inode, page, dn.ofs_in_node);
/* skip recovering if dest is the same as src */
if (src == dest)
continue;
/* dest is invalid, just invalidate src block */
if (dest == NULL_ADDR) {
truncate_data_blocks_range(&dn, 1);
continue;
}
if (!file_keep_isize(inode) &&
(i_size_read(inode) <= ((loff_t)start << PAGE_SHIFT)))
f2fs_i_size_write(inode,
(loff_t)(start + 1) << PAGE_SHIFT);
/*
* dest is reserved block, invalidate src block
* and then reserve one new block in dnode page.
*/
if (dest == NEW_ADDR) {
truncate_data_blocks_range(&dn, 1);
reserve_new_block(&dn);
continue;
}
/* dest is valid block, try to recover from src to dest */
if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
err = reserve_new_block(&dn);
#ifdef CONFIG_F2FS_FAULT_INJECTION
while (err)
err = reserve_new_block(&dn);
#endif
/* We should not get -ENOSPC */
f2fs_bug_on(sbi, err);
if (err)
goto err;
}
retry_prev:
/* Check the previous node page having this index */
err = check_index_in_prev_nodes(sbi, dest, &dn);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_prev;
}
goto err;
}
/* write dummy data page */
f2fs_replace_block(sbi, &dn, src, dest,
ni.version, false, false);
recovered++;
}
}
copy_node_footer(dn.node_page, page);
fill_node_footer(dn.node_page, dn.nid, ni.ino,
ofs_of_node(page), false);
set_page_dirty(dn.node_page);
err:
f2fs_put_dnode(&dn);
out:
f2fs_msg(sbi->sb, KERN_NOTICE,
"recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d",
inode->i_ino,
file_keep_isize(inode) ? "keep" : "recover",
recovered, err);
return err;
}
static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
struct list_head *dir_list)
{
struct curseg_info *curseg;
struct page *page = NULL;
int err = 0;
block_t blkaddr;
/* get node pages in the current segment */
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
struct fsync_inode_entry *entry;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
break;
ra_meta_pages_cond(sbi, blkaddr);
page = get_tmp_page(sbi, blkaddr);
if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
break;
}
entry = get_fsync_inode(inode_list, ino_of_node(page));
if (!entry)
goto next;
/*
* inode(x) | CP | inode(x) | dnode(F)
* In this case, we can lose the latest inode(x).
* So, call recover_inode for the inode update.
*/
if (IS_INODE(page))
recover_inode(entry->inode, page);
if (entry->last_dentry == blkaddr) {
err = recover_dentry(entry->inode, page, dir_list);
if (err) {
f2fs_put_page(page, 1);
break;
}
}
err = do_recover_data(sbi, entry->inode, page, blkaddr);
if (err) {
f2fs_put_page(page, 1);
break;
}
if (entry->blkaddr == blkaddr)
del_fsync_inode(entry);
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
}
if (!err)
allocate_new_segments(sbi);
return err;
}
int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
struct list_head inode_list;
struct list_head dir_list;
int err;
int ret = 0;
unsigned long s_flags = sbi->sb->s_flags;
bool need_writecp = false;
if (s_flags & MS_RDONLY) {
f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
sbi->sb->s_flags &= ~MS_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
sbi->sb->s_flags |= MS_ACTIVE;
/* Turn on quotas so that they are updated correctly */
f2fs_enable_quota_files(sbi);
#endif
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
sizeof(struct fsync_inode_entry));
if (!fsync_entry_slab) {
err = -ENOMEM;
goto out;
}
INIT_LIST_HEAD(&inode_list);
INIT_LIST_HEAD(&dir_list);
/* prevent checkpoint */
mutex_lock(&sbi->cp_mutex);
/* step #1: find fsynced inode numbers */
err = find_fsync_dnodes(sbi, &inode_list, check_only);
if (err || list_empty(&inode_list))
goto skip;
if (check_only) {
ret = 1;
goto skip;
}
need_writecp = true;
/* step #2: recover data */
err = recover_data(sbi, &inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
skip:
destroy_fsync_dnodes(&inode_list);
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
(loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1);
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
truncate_inode_pages_final(META_MAPPING(sbi));
}
clear_sbi_flag(sbi, SBI_POR_DOING);
mutex_unlock(&sbi->cp_mutex);
/* let's drop all the directory inodes for clean checkpoint */
destroy_fsync_dnodes(&dir_list);
if (!err && need_writecp) {
struct cp_control cpc = {
.reason = CP_RECOVERY,
};
err = write_checkpoint(sbi, &cpc);
}
kmem_cache_destroy(fsync_entry_slab);
out:
#ifdef CONFIG_QUOTA
/* Turn quotas off */
f2fs_quota_off_umount(sbi->sb);
#endif
sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
return ret ? ret: err;
}
|