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
|
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext4/block_validity.c
*
* Copyright (C) 2009
* Theodore Ts'o (tytso@mit.edu)
*
* Track which blocks in the filesystem are metadata blocks that
* should never be used as data blocks by files or directories.
*/
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include "ext4.h"
struct ext4_system_zone {
struct rb_node node;
ext4_fsblk_t start_blk;
unsigned int count;
u32 ino;
};
static struct kmem_cache *ext4_system_zone_cachep;
int __init ext4_init_system_zone(void)
{
ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, 0);
if (ext4_system_zone_cachep == NULL)
return -ENOMEM;
return 0;
}
void ext4_exit_system_zone(void)
{
rcu_barrier();
kmem_cache_destroy(ext4_system_zone_cachep);
}
static inline int can_merge(struct ext4_system_zone *entry1,
struct ext4_system_zone *entry2)
{
if ((entry1->start_blk + entry1->count) == entry2->start_blk &&
entry1->ino == entry2->ino)
return 1;
return 0;
}
static void release_system_zone(struct ext4_system_blocks *system_blks)
{
struct ext4_system_zone *entry, *n;
rbtree_postorder_for_each_entry_safe(entry, n,
&system_blks->root, node)
kmem_cache_free(ext4_system_zone_cachep, entry);
}
/*
* Mark a range of blocks as belonging to the "system zone" --- that
* is, filesystem metadata blocks which should never be used by
* inodes.
*/
static int add_system_zone(struct ext4_system_blocks *system_blks,
ext4_fsblk_t start_blk,
unsigned int count, u32 ino)
{
struct ext4_system_zone *new_entry, *entry;
struct rb_node **n = &system_blks->root.rb_node, *node;
struct rb_node *parent = NULL, *new_node = NULL;
while (*n) {
parent = *n;
entry = rb_entry(parent, struct ext4_system_zone, node);
if (start_blk < entry->start_blk)
n = &(*n)->rb_left;
else if (start_blk >= (entry->start_blk + entry->count))
n = &(*n)->rb_right;
else /* Unexpected overlap of system zones. */
return -EFSCORRUPTED;
}
new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
GFP_KERNEL);
if (!new_entry)
return -ENOMEM;
new_entry->start_blk = start_blk;
new_entry->count = count;
new_entry->ino = ino;
new_node = &new_entry->node;
rb_link_node(new_node, parent, n);
rb_insert_color(new_node, &system_blks->root);
/* Can we merge to the left? */
node = rb_prev(new_node);
if (node) {
entry = rb_entry(node, struct ext4_system_zone, node);
if (can_merge(entry, new_entry)) {
new_entry->start_blk = entry->start_blk;
new_entry->count += entry->count;
rb_erase(node, &system_blks->root);
kmem_cache_free(ext4_system_zone_cachep, entry);
}
}
/* Can we merge to the right? */
node = rb_next(new_node);
if (node) {
entry = rb_entry(node, struct ext4_system_zone, node);
if (can_merge(new_entry, entry)) {
new_entry->count += entry->count;
rb_erase(node, &system_blks->root);
kmem_cache_free(ext4_system_zone_cachep, entry);
}
}
return 0;
}
static void debug_print_tree(struct ext4_sb_info *sbi)
{
struct rb_node *node;
struct ext4_system_zone *entry;
struct ext4_system_blocks *system_blks;
int first = 1;
printk(KERN_INFO "System zones: ");
rcu_read_lock();
system_blks = rcu_dereference(sbi->system_blks);
node = rb_first(&system_blks->root);
while (node) {
entry = rb_entry(node, struct ext4_system_zone, node);
printk(KERN_CONT "%s%llu-%llu", first ? "" : ", ",
entry->start_blk, entry->start_blk + entry->count - 1);
first = 0;
node = rb_next(node);
}
rcu_read_unlock();
printk(KERN_CONT "\n");
}
/*
* Returns 1 if the passed-in block region (start_blk,
* start_blk+count) is valid; 0 if some part of the block region
* overlaps with filesystem metadata blocks.
*/
static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi,
struct ext4_system_blocks *system_blks,
ext4_fsblk_t start_blk,
unsigned int count, ino_t ino)
{
struct ext4_system_zone *entry;
struct rb_node *n;
if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
(start_blk + count < start_blk) ||
(start_blk + count > ext4_blocks_count(sbi->s_es)))
return 0;
if (system_blks == NULL)
return 1;
n = system_blks->root.rb_node;
while (n) {
entry = rb_entry(n, struct ext4_system_zone, node);
if (start_blk + count - 1 < entry->start_blk)
n = n->rb_left;
else if (start_blk >= (entry->start_blk + entry->count))
n = n->rb_right;
else
return entry->ino == ino;
}
return 1;
}
static int ext4_protect_reserved_inode(struct super_block *sb,
struct ext4_system_blocks *system_blks,
u32 ino)
{
struct inode *inode;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_map_blocks map;
u32 i = 0, num;
int err = 0, n;
if ((ino < EXT4_ROOT_INO) ||
(ino > le32_to_cpu(sbi->s_es->s_inodes_count)))
return -EINVAL;
inode = ext4_iget(sb, ino, EXT4_IGET_SPECIAL);
if (IS_ERR(inode))
return PTR_ERR(inode);
num = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
while (i < num) {
cond_resched();
map.m_lblk = i;
map.m_len = num - i;
n = ext4_map_blocks(NULL, inode, &map, 0);
if (n < 0) {
err = n;
break;
}
if (n == 0) {
i++;
} else {
err = add_system_zone(system_blks, map.m_pblk, n, ino);
if (err < 0) {
if (err == -EFSCORRUPTED) {
__ext4_error(sb, __func__, __LINE__,
-err, map.m_pblk,
"blocks %llu-%llu from inode %u overlap system zone",
map.m_pblk,
map.m_pblk + map.m_len - 1,
ino);
}
break;
}
i += n;
}
}
iput(inode);
return err;
}
static void ext4_destroy_system_zone(struct rcu_head *rcu)
{
struct ext4_system_blocks *system_blks;
system_blks = container_of(rcu, struct ext4_system_blocks, rcu);
release_system_zone(system_blks);
kfree(system_blks);
}
/*
* Build system zone rbtree which is used for block validity checking.
*
* The update of system_blks pointer in this function is protected by
* sb->s_umount semaphore. However we have to be careful as we can be
* racing with ext4_data_block_valid() calls reading system_blks rbtree
* protected only by RCU. That's why we first build the rbtree and then
* swap it in place.
*/
int ext4_setup_system_zone(struct super_block *sb)
{
ext4_group_t ngroups = ext4_get_groups_count(sb);
struct ext4_sb_info *sbi
|