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
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/slab.h>
#include "ctree.h"
#include "subpage.h"
int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
struct page *page, enum btrfs_subpage_type type)
{
struct btrfs_subpage *subpage = NULL;
int ret;
/*
* We have cases like a dummy extent buffer page, which is not mappped
* and doesn't need to be locked.
*/
if (page->mapping)
ASSERT(PageLocked(page));
/* Either not subpage, or the page already has private attached */
if (fs_info->sectorsize == PAGE_SIZE || PagePrivate(page))
return 0;
ret = btrfs_alloc_subpage(fs_info, &subpage, type);
if (ret < 0)
return ret;
attach_page_private(page, subpage);
return 0;
}
void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info,
struct page *page)
{
struct btrfs_subpage *subpage;
/* Either not subpage, or already detached */
if (fs_info->sectorsize == PAGE_SIZE || !PagePrivate(page))
return;
subpage = (struct btrfs_subpage *)detach_page_private(page);
ASSERT(subpage);
btrfs_free_subpage(subpage);
}
int btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info,
struct btrfs_subpage **ret,
enum btrfs_subpage_type type)
{
if (fs_info->sectorsize == PAGE_SIZE)
return 0;
*ret = kzalloc(sizeof(struct btrfs_subpage), GFP_NOFS);
if (!*ret)
return -ENOMEM;
spin_lock_init(&(*ret)->lock);
if (type == BTRFS_SUBPAGE_METADATA)
atomic_set(&(*ret)->eb_refs, 0);
else
atomic_set(&(*ret)->readers, 0);
return 0;
}
void btrfs_free_subpage(struct btrfs_subpage *subpage)
{
kfree(subpage);
}
/*
* Increase the eb_refs of current subpage.
*
* This is important for eb allocation, to prevent race with last eb freeing
* of the same page.
* With the eb_refs increased before the eb inserted into radix tree,
* detach_extent_buffer_page() won't detach the page private while we're still
* allocating the extent buffer.
*/
void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info,
struct page *page)
{
struct btrfs_subpage *subpage;
if (fs_info->sectorsize == PAGE_SIZE)
return;
ASSERT(PagePrivate(page) && page->mapping);
lockdep_assert_held(&page->mapping->private_lock);
subpage = (struct btrfs_subpage *)page->private;
atomic_inc(&subpage->eb_refs);
}
void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info,
struct page *page)
{
struct btrfs_subpage *subpage;
if (fs_info->sectorsize == PAGE_SIZE)
return;
ASSERT(PagePrivate(page) && page->mapping);
lockdep_assert_held(&page->mapping->private_lock);
subpage = (struct btrfs_subpage *)page->private;
ASSERT(atomic_read(&subpage->eb_refs));
atomic_dec(&subpage->eb_refs);
}
static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
/* Basic checks */
ASSERT(PagePrivate(page) && page->private);
ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
IS_ALIGNED(len, fs_info->sectorsize));
/*
* The range check only works for mapped page, we can still have
* unmapped page like dummy extent buffer pages.
*/
if (page->mapping)
ASSERT(page_offset(page) <= start &&
start + len <= page_offset(page) + PAGE_SIZE);
}
void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
const int nbits = len >> fs_info->sectorsize_bits;
int ret;
btrfs_subpage_assert(fs_info, page, start, len);
ret = atomic_add_return(nbits, &subpage->readers);
ASSERT(ret == nbits);
}
void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
const int nbits = len >> fs_info->sectorsize_bits;
btrfs_subpage_assert(fs_info, page, start, len);
ASSERT(atomic_read(&subpage->readers) >= nbits);
if (atomic_sub_and_test(nbits, &subpage->readers))
unlock_page(page);
}
/*
* Convert the [start, start + len) range into a u16 bitmap
*
* For example: if start == page_offset() + 16K, len = 16K, we get 0x00f0.
*/
static u16 btrfs_subpage_calc_bitmap(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
const int bit_start = offset_in_page(start) >> fs_info->sectorsize_bits;
const int nbits = len >> fs_info->sectorsize_bits;
btrfs_subpage_assert(fs_info, page, start, len);
/*
* Here nbits can be 16, thus can go beyond u16 range. We make the
* first left shift to be calculate in unsigned long (at least u32),
* then truncate the result to u16.
*/
return (u16)(((1UL << nbits) - 1) << bit_start);
}
void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
unsigned long flags;
spin_lock_irqsave(&subpage->lock, flags);
subpage->uptodate_bitmap |= tmp;
if (subpage->uptodate_bitmap == U16_MAX)
SetPageUptodate(page);
spin_unlock_irqrestore(&subpage->lock, flags);
}
void btrfs_subpage_clear_uptodate(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
unsigned long flags;
spin_lock_irqsave(&subpage->lock, flags);
subpage->uptodate_bitmap &= ~tmp;
ClearPageUptodate(page);
spin_unlock_irqrestore(&subpage->lock, flags);
}
void btrfs_subpage_set_error(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
unsigned long flags;
spin_lock_irqsave(&subpage->lock, flags);
subpage->error_bitmap |= tmp;
SetPageError(page);
spin_unlock_irqrestore(&subpage->lock, flags);
}
void btrfs_subpage_clear_error(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
unsigned long flags;
spin_lock_irqsave(&subpage->lock, flags);
subpage->error_bitmap &= ~tmp;
if (subpage->error_bitmap == 0)
ClearPageError(page);
spin_unlock_irqrestore(&subpage->lock, flags);
}
void btrfs_subpage_set_dirty(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
unsigned long flags;
spin_lock_irqsave(&subpage->lock, flags);
subpage->dirty_bitmap |= tmp;
spin_unlock_irqrestore(&subpage->lock, flags);
set_page_dirty(page);
}
/*
* Extra clear_and_test function for subpage dirty bitmap.
*
* Return true if we're the last bits in the dirty_bitmap and clear the
* dirty_bitmap.
* Return false otherwise.
*
* NOTE: Callers should manually clear page dirty for true case, as we have
* extra handling for tree blocks.
*/
bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
unsigned long flags;
bool last = false;
spin_lock_irqsave(&subpage->lock, flags);
subpage->dirty_bitmap &= ~tmp;
if (subpage->dirty_bitmap == 0)
last = true;
spin_unlock_irqrestore(&subpage->lock, flags);
return last;
}
void btrfs_subpage_clear_dirty(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
{
bool last;
last = btrfs_subpage_clear_and_test_dirty(fs_info, page, start, len);
if (last)
clear_page_dirty_for_io(page);
}
/*
* Unlike set/clear which is dependent on each page status, for test all bits
* are tested in the same way.
*/
#define IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(name) \
bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \
struct page *page, u64 start, u32 len) \
{ \
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; \
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); \
unsigned long flags; \
bool ret; \
\
spin_lock_irqsave(&subpage->lock, flags); \
ret = ((subpage->name##_bitmap & tmp) == tmp); \
spin_unlock_irqrestore(&subpage->lock, flags); \
return ret; \
}
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(uptodate);
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(error);
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(dirty);
/*
* Note that, in selftests (extent-io-tests), we can have empty fs_info passed
* in. We only test sectorsize == PAGE_SIZE cases so far, thus we can fall
* back to regular sectorsize branch.
*/
#define IMPLEMENT_BTRFS_PAGE_OPS(name, set_page_func, clear_page_func, \
test_page_func) \
void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \
struct page *page, u64 start, u32 len) \
{ \
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \
set_page_func(page); \
return; \
} \
btrfs_subpage_set_##name(fs_info, page, start, len); \
} \
void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \
struct page *page, u64 start, u32 len) \
{ \
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \
clear_page_func(page); \
return; \
} \
btrfs_subpage_clear_##name(fs_info, page, start, len); \
} \
bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \
struct page *page, u64 start, u32 len) \
{ \
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) \
return test_page_func(page); \
return btrfs_subpage_test_##name(fs_info, page, start, len); \
}
IMPLEMENT_BTRFS_PAGE_OPS(uptodate, SetPageUptodate, ClearPageUptodate,
PageUptodate);
IMPLEMENT_BTRFS_PAGE_OPS(error, SetPageError, ClearPageError, PageError);
IMPLEMENT_BTRFS_PAGE_OPS(dirty, set_page_dirty, clear_page_dirty_for_io,
PageDirty);
|