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
|
/*
* fs/f2fs/node.h
*
* 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.
*/
/* start node id of a node block dedicated to the given node id */
#define START_NID(nid) ((nid / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
/* node block offset on the NAT area dedicated to the given start node id */
#define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
/* # of pages to perform readahead before building free nids */
#define FREE_NID_PAGES 4
/* maximum readahead size for node during getting data blocks */
#define MAX_RA_NODE 128
/* maximum cached nat entries to manage memory footprint */
#define NM_WOUT_THRESHOLD (64 * NAT_ENTRY_PER_BLOCK)
/* control the memory footprint threshold (10MB per 1GB ram) */
#define DEF_RAM_THRESHOLD 10
/* vector size for gang look-up from nat cache that consists of radix tree */
#define NATVEC_SIZE 64
/* return value for read_node_page */
#define LOCKED_PAGE 1
/*
* For node information
*/
struct node_info {
nid_t nid; /* node id */
nid_t ino; /* inode number of the node's owner */
block_t blk_addr; /* block address of the node */
unsigned char version; /* version of the node */
};
struct nat_entry {
struct list_head list; /* for clean or dirty nat list */
bool checkpointed; /* whether it is checkpointed or not */
struct node_info ni; /* in-memory node information */
};
#define nat_get_nid(nat) (nat->ni.nid)
#define nat_set_nid(nat, n) (nat->ni.nid = n)
#define nat_get_blkaddr(nat) (nat->ni.blk_addr)
#define nat_set_blkaddr(nat, b) (nat->ni.blk_addr = b)
#define nat_get_ino(nat) (nat->ni.ino)
#define nat_set_ino(nat, i) (nat->ni.ino = i)
#define nat_get_version(nat) (nat->ni.version)
#define nat_set_version(nat, v) (nat->ni.version = v)
#define __set_nat_cache_dirty(nm_i, ne) \
do { \
ne->checkpointed = false; \
list_move_tail(&ne->list, &nm_i->dirty_nat_entries); \
} while (0);
#define __clear_nat_cache_dirty(nm_i, ne) \
do { \
ne->checkpointed = true; \
list_move_tail(&ne->list, &nm_i->nat_entries); \
} while (0);
#define inc_node_version(version) (++version)
static inline void node_info_from_raw_nat(struct node_info *ni,
struct f2fs_nat_entry *raw_ne)
{
ni->ino = le32_to_cpu(raw_ne->ino);
ni->blk_addr = le32_to_cpu(raw_ne->block_addr);
ni->version = raw_ne->version;
}
enum nid_type {
FREE_NIDS, /* indicates the free nid list */
NAT_ENTRIES /* indicates the cached nat entry */
};
/*
* For free nid mangement
*/
enum nid_state {
NID_NEW, /* newly added to free nid list */
NID_ALLOC /* it is allocated */
};
struct free_nid {
struct list_head list; /* for free node id list */
nid_t nid; /* node id */
int state; /* in use or not: NID_NEW or NID_ALLOC */
};
static inline int next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *fnid;
if (nm_i->fcnt <= 0)
return -1;
spin_lock(&nm_i->free_nid_list_lock);
fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
*nid = fnid->nid;
spin_unlock(&nm_i->free_nid_list_lock);
return 0;
}
/*
* inline functions
*/
static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
}
static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
pgoff_t block_off;
pgoff_t block_addr;
int seg_off;
block_off = NAT_BLOCK_OFFSET(start);
seg_off = block_off >> sbi->log_blocks_per_seg;
block_addr = (pgoff_t)(nm_i->nat_blkaddr +
(seg_off << sbi->log_blocks_per_seg << 1) +
(block_off & ((1 << sbi->log_blocks_per_seg) - 1)));
if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
block_addr += sbi->blocks_per_seg;
return block_addr;
}
static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi,
pgoff_t block_addr)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
block_addr -= nm_i->nat_blkaddr;
if ((block_addr >> sbi->log_blocks_per_seg) % 2)
block_addr -= sbi->blocks_per_seg;
else
block_addr += sbi->blocks_per_seg;
return block_addr + nm_i->nat_blkaddr;
}
static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
{
unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
f2fs_clear_bit(block_off, nm_i->nat_bitmap);
else
f2fs_set_bit(block_off, nm_i->nat_bitmap);
}
static inline void fill_node_footer(struct page *page, nid_t nid,
nid_t ino, unsigned int ofs, bool reset)
{
struct f2fs_node *rn = F2FS_NODE(page);
if (reset)
memset(rn, 0, sizeof(*rn));
rn->footer.nid = cpu_to_le32(nid);
rn->footer.ino = cpu_to_le32(ino);
rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
}
static inline void copy_node_footer(struct page *dst, struct page *src)
{
struct f2fs_node *src_rn = F2FS_NODE(src);
struct f2fs_node *dst_rn = F2FS_NODE(dst);
memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
}
static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
{
struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct f2fs_node *rn = F2FS_NODE(page);
rn->footer.cp_ver = ckpt->checkpoint_ver;
rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
}
static inline nid_t ino_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
return le32_to_cpu(rn->footer.ino);
}
static inline nid_t nid_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
return le32_to_cpu(rn->footer.nid);
}
static inline unsigned int ofs_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
unsigned flag = le32_to_cpu(rn->footer.flag);
return flag >> OFFSET_BIT_SHIFT;
}
static inline unsigned long long cpver_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
return le64_to_cpu(rn->footer.cp_ver);
}
static inline block_t next_blkaddr_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
return le32_to_cpu(rn->footer.next_blkaddr);
}
/*
* f2fs assigns the following node offsets described as (num).
* N = NIDS_PER_BLOCK
*
* Inode block (0)
* |- direct node (1)
* |- direct node (2)
* |- indirect node (3)
* | `- direct node (4 => 4 + N - 1)
* |- indirect node (4 + N)
* | `- direct node (5 + N => 5 + 2N - 1)
* `- double indirect node (5 + 2N)
* `- indirect node (6 + 2N)
* `- direct node
* ......
* `- indirect node ((6 + 2N) + x(N + 1))
* `- direct node
* ......
* `- indirect node ((6 + 2N) + (N - 1)(N + 1))
* `- direct node
*/
static inline bool IS_DNODE(struct page *node_page)
{
unsigned int ofs = ofs_of_node(node_page);
if (f2fs_has_xattr_block(ofs))
return false;
if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
ofs == 5 + 2 * NIDS_PER_BLOCK)
return false;
if (ofs >= 6 + 2 * NIDS_PER_BLOCK) {
ofs -= 6 + 2 * NIDS_PER_BLOCK;
if (!((long int)ofs % (NIDS_PER_BLOCK + 1)))
return false;
}
return true;
}
static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
{
struct f2fs_node *rn = F2FS_NODE(p);
wait_on_page_writeback(p);
if (i)
rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
else
rn->in.nid[off] = cpu_to_le32(nid);
set_page_dirty(p);
}
static inline nid_t get_nid(struct page *p, int off, bool i)
{
struct f2fs_node *rn = F2FS_NODE(p);
if (i)
return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]);
return le32_to_cpu(rn->in.nid[off]);
}
/*
* Coldness identification:
* - Mark cold files in f2fs_inode_info
* - Mark cold node blocks in their node footer
* - Mark cold data pages in page cache
*/
static inline int is_file(struct inode *inode, int type)
{
return F2FS_I(inode)->i_advise & type;
}
static inline void set_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise |= type;
}
static inline void clear_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise &= ~type;
}
#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT)
#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT)
#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT)
#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT)
#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT)
#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT)
static inline int is_cold_data(struct page *page)
{
return PageChecked(page);
}
static inline void set_cold_data(struct page *page)
{
SetPageChecked(page);
}
static inline void clear_cold_data(struct page *page)
{
ClearPageChecked(page);
}
static inline int is_node(struct page *page, int type)
{
struct f2fs_node *rn = F2FS_NODE(page);
return le32_to_cpu(rn->footer.flag) & (1 << type);
}
#define is_cold_node(page) is_node(page, COLD_BIT_SHIFT)
#define is_fsync_dnode(page) is_node(page, FSYNC_BIT_SHIFT)
#define is_dent_dnode(page) is_node(page, DENT_BIT_SHIFT)
static inline void set_cold_node(struct inode *inode, struct page *page)
{
struct f2fs_node *rn = F2FS_NODE(page);
unsigned int flag = le32_to_cpu(rn->footer.flag);
if (S_ISDIR(inode->i_mode))
flag &= ~(0x1 << COLD_BIT_SHIFT);
else
flag |= (0x1 << COLD_BIT_SHIFT);
rn->footer.flag = cpu_to_le32(flag);
}
static inline void set_mark(struct page *page, int mark, int type)
{
struct f2fs_node *rn = F2FS_NODE(page);
unsigned int flag = le32_to_cpu(rn->footer.flag);
if (mark)
flag |= (0x1 << type);
else
flag &= ~(0x1 << type);
rn->footer.flag = cpu_to_le32(flag);
}
#define set_dentry_mark(page, mark) set_mark(page, mark, DENT_BIT_SHIFT)
#define set_fsync_mark(page, mark) set_mark(page, mark, FSYNC_BIT_SHIFT)
|