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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017-2018 HUAWEI, Inc.
* http://www.huawei.com/
* Created by Gao Xiang <gaoxiang25@huawei.com>
*/
#include "internal.h"
#include <linux/prefetch.h>
#include <trace/events/erofs.h>
static inline void read_endio(struct bio *bio)
{
struct super_block *const sb = bio->bi_private;
struct bio_vec *bvec;
blk_status_t err = bio->bi_status;
struct bvec_iter_all iter_all;
if (time_to_inject(EROFS_SB(sb), FAULT_READ_IO)) {
erofs_show_injection_info(FAULT_READ_IO);
err = BLK_STS_IOERR;
}
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
/* page is already locked */
DBG_BUGON(PageUptodate(page));
if (err)
SetPageError(page);
else
SetPageUptodate(page);
unlock_page(page);
/* page could be reclaimed now */
}
bio_put(bio);
}
static struct bio *erofs_grab_raw_bio(struct super_block *sb,
erofs_blk_t blkaddr,
unsigned int nr_pages)
{
struct bio *bio = bio_alloc(GFP_NOIO, nr_pages);
bio->bi_end_io = read_endio;
bio_set_dev(bio, sb->s_bdev);
bio->bi_iter.bi_sector = (sector_t)blkaddr << LOG_SECTORS_PER_BLOCK;
bio->bi_private = sb;
return bio;
}
/* prio -- true is used for dir */
struct page *__erofs_get_meta_page(struct super_block *sb,
erofs_blk_t blkaddr, bool prio, bool nofail)
{
struct inode *const bd_inode = sb->s_bdev->bd_inode;
struct address_space *const mapping = bd_inode->i_mapping;
/* prefer retrying in the allocator to blindly looping below */
const gfp_t gfp = mapping_gfp_constraint(mapping, ~__GFP_FS) |
(nofail ? __GFP_NOFAIL : 0);
unsigned int io_retries = nofail ? EROFS_IO_MAX_RETRIES_NOFAIL : 0;
struct page *page;
int err;
repeat:
page = find_or_create_page(mapping, blkaddr, gfp);
if (!page) {
DBG_BUGON(nofail);
return ERR_PTR(-ENOMEM);
}
DBG_BUGON(!PageLocked(page));
if (!PageUptodate(page)) {
struct bio *bio;
bio = erofs_grab_raw_bio(sb, blkaddr, 1);
if (bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE) {
err = -EFAULT;
goto err_out;
}
__submit_bio(bio, REQ_OP_READ,
REQ_META | (prio ? REQ_PRIO : 0));
lock_page(page);
/* this page has been truncated by others */
if (page->mapping != mapping) {
unlock_repeat:
unlock_page(page);
put_page(page);
goto repeat;
}
/* more likely a read error */
if (!PageUptodate(page)) {
if (io_retries) {
--io_retries;
goto unlock_repeat;
}
err = -EIO;
goto err_out;
}
}
return page;
err_out:
unlock_page(page);
put_page(page);
return ERR_PTR(err);
}
static int erofs_map_blocks_flatmode(struct inode *inode,
struct erofs_map_blocks *map,
int flags)
{
int err = 0;
erofs_blk_t nblocks, lastblk;
u64 offset = map->m_la;
struct erofs_inode *vi = EROFS_I(inode);
bool tailendpacking = (vi->datalayout == EROFS_INODE_FLAT_INLINE);
trace_erofs_map_blocks_flatmode_enter(inode, map, flags);
nblocks = DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
lastblk = nblocks - tailendpacking;
if (offset >= inode->i_size) {
/* leave out-of-bound access unmapped */
map->m_flags = 0;
map->m_plen = 0;
goto out;
}
/* there is no hole in flatmode */
map->m_flags = EROFS_MAP_MAPPED;
if (offset < blknr_to_addr(lastblk)) {
map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la;
map->m_plen = blknr_to_addr(lastblk) - offset;
} else if (tailendpacking) {
/* 2 - inode inline B: inode, [xattrs], inline last blk... */
struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
map->m_pa = iloc(sbi, vi->nid) + vi->inode_isize +
vi->xattr_isize + erofs_blkoff(map->m_la);
map->m_plen = inode->i_size - offset;
/* inline data should be located in one meta block */
if (erofs_blkoff(map->m_pa) + map->m_plen > PAGE_SIZE) {
errln("inline data cross block boundary @ nid %llu",
vi->nid);
DBG_BUGON(1);
err = -EFSCORRUPTED;
goto err_out;
}
map->m_flags |= EROFS_MAP_META;
} else {
errln("internal error @ nid: %llu (size %llu), m_la 0x%llx",
vi->nid, inode->i_size, map->m_la);
DBG_BUGON(1);
err = -EIO;
goto err_out;
}
out:
map->m_llen = map->m_plen;
err_out:
trace_erofs_map_blocks_flatmode_exit(inode, map, flags, 0);
return err;
}
int erofs_map_blocks(struct inode *inode,
struct erofs_map_blocks *map, int flags)
{
if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) {
int err = z_erofs_map_blocks_iter(inode, map, flags);
if (map->mpage) {
put_page(map->mpage);
map->mpage = NULL;
}
return err;
}
return erofs_map_blocks_flatmode(inode, map, flags);
}
static inline struct bio *erofs_read_raw_page(struct bio *bio,
struct address_space *mapping,
struct page *page,
erofs_off_t *last_block,
unsigned int nblocks,
bool ra)
{
struct inode *const inode = mapping->host;
struct super_block *const sb = inode->i_sb;
erofs_off_t current_block = (erofs_off_t)page->index;
int err;
DBG_BUGON(!nblocks);
if (PageUptodate(page)) {
err = 0;
goto has_updated;
}
/* note that for readpage case, bio also equals to NULL */
if (bio &&
/* not continuous */
*last_block + 1 != current_block) {
submit_bio_retry:
__submit_bio(bio, REQ_OP_READ, 0);
bio = NULL;
}
if (!bio) {
struct erofs_map_blocks map = {
.m_la = blknr_to_addr(current_block),
};
erofs_blk_t blknr;
unsigned int blkoff;
err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
if (err)
goto err_out;
/* zero out the holed page */
if (!(map.m_flags & EROFS_MAP_MAPPED)) {
zero_user_segment(page, 0, PAGE_SIZE);
SetPageUptodate(page);
/* imply err = 0, see erofs_map_blocks */
goto has_updated;
}
/* for RAW access mode, m_plen must be equal to m_llen */
DBG_BUGON(map.m_plen != map.m_llen);
blknr = erofs_blknr(map.m_pa);
blkoff = erofs_blkoff(map.m_pa);
/* deal with inline page */
if (map.m_flags & EROFS_MAP_META) {
void *vsrc, *vto;
struct page *ipage;
DBG_BUGON(map.m_plen > PAGE_SIZE);
ipage = erofs_get_meta_page(inode->i_sb, blknr, 0);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto err_out;
}
vsrc = kmap_atomic(ipage);
vto = kmap_atomic(page);
memcpy(vto, vsrc + blkoff, map.m_plen);
memset(vto + map.m_plen, 0, PAGE_SIZE - map.m_plen);
kunmap_atomic(vto);
kunmap_atomic(vsrc);
flush_dcache_page(page);
SetPageUptodate(page);
/* TODO: could we unlock the page earlier? */
unlock_page(ipage);
put_page(ipage);
/* imply err = 0, see erofs_map_blocks */
goto has_updated;
}
/* pa must be block-aligned for raw reading */
DBG_BUGON(erofs_blkoff(map.m_pa));
/* max # of continuous pages */
if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
if (nblocks > BIO_MAX_PAGES)
nblocks = BIO_MAX_PAGES;
bio = erofs_grab_raw_bio(sb, blknr, nblocks);
}
err = bio_add_page(bio, page, PAGE_SIZE, 0);
/* out of the extent or bio is full */
if (err < PAGE_SIZE)
goto submit_bio_retry;
*last_block = current_block;
/* shift in advance in case of it followed by too many gaps */
if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
/* err should reassign to 0 after submitting */
err = 0;
goto submit_bio_out;
}
return bio;
err_out:
/* for sync reading, set page error immediately */
if (!ra) {
SetPageError(page);
ClearPageUptodate(page);
}
has_updated:
unlock_page(page);
/* if updated manually, continuous pages has a gap */
if (bio)
submit_bio_out:
__submit_bio(bio, REQ_OP_READ, 0);
return err ? ERR_PTR(err) : NULL;
}
/*
* since we dont have write or truncate flows, so no inode
* locking needs to be held at the moment.
*/
static int erofs_raw_access_readpage(struct file *file, struct page *page)
{
erofs_off_t last_block;
struct bio *bio;
trace_erofs_readpage(page, true);
bio = erofs_read_raw_page(NULL, page->mapping,
page, &last_block, 1, false);
if (IS_ERR(bio))
return PTR_ERR(bio);
DBG_BUGON(bio); /* since we have only one bio -- must be NULL */
return 0;
}
static int erofs_raw_access_readpages(struct file *filp,
struct address_space *mapping,
struct list_head *pages,
unsigned int nr_pages)
{
erofs_off_t last_block;
struct bio *bio = NULL;
gfp_t gfp = readahead_gfp_mask(mapping);
struct page *page = list_last_entry(pages, struct page, lru);
trace_erofs_readpages(mapping->host, page, nr_pages, true);
for (; nr_pages; --nr_pages) {
page = list_entry(pages->prev, struct page, lru);
prefetchw(&page->flags);
list_del(&page->lru);
if (!add_to_page_cache_lru(page, mapping, page->index, gfp)) {
bio = erofs_read_raw_page(bio, mapping, page,
&last_block, nr_pages, true);
/* all the page errors are ignored when readahead */
if (IS_ERR(bio)) {
pr_err("%s, readahead error at page %lu of nid %llu\n",
__func__, page->index,
EROFS_I(mapping->host)->nid);
bio = NULL;
}
}
/* pages could still be locked */
put_page(page);
}
DBG_BUGON(!list_empty(pages));
/* the rare case (end in gaps) */
if (bio)
__submit_bio(bio, REQ_OP_READ, 0);
return 0;
}
static int erofs_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
struct erofs_map_blocks map = {
.m_la = iblock << 9,
};
int err;
err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
if (err)
return err;
if (map.m_flags & EROFS_MAP_MAPPED)
bh->b_blocknr = erofs_blknr(map.m_pa);
return err;
}
static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
if (EROFS_I(inode)->datalayout == EROFS_INODE_FLAT_INLINE) {
erofs_blk_t blks = i_size_read(inode) >> LOG_BLOCK_SIZE;
if (block >> LOG_SECTORS_PER_BLOCK >= blks)
return 0;
}
return generic_block_bmap(mapping, block, erofs_get_block);
}
/* for uncompressed (aligned) files and raw access for other files */
const struct address_space_operations erofs_raw_access_aops = {
.readpage = erofs_raw_access_readpage,
.readpages = erofs_raw_access_readpages,
.bmap = erofs_bmap,
};
|