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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2008 Oracle. All rights reserved.
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/pagemap.h>
#include <linux/bio.h>
#include <linux/lzo.h>
#include <linux/refcount.h>
#include "compression.h"
#include "ctree.h"
#define LZO_LEN 4
/*
* Btrfs LZO compression format
*
* Regular and inlined LZO compressed data extents consist of:
*
* 1. Header
* Fixed size. LZO_LEN (4) bytes long, LE32.
* Records the total size (including the header) of compressed data.
*
* 2. Segment(s)
* Variable size. Each segment includes one segment header, followed by data
* payload.
* One regular LZO compressed extent can have one or more segments.
* For inlined LZO compressed extent, only one segment is allowed.
* One segment represents at most one sector of uncompressed data.
*
* 2.1 Segment header
* Fixed size. LZO_LEN (4) bytes long, LE32.
* Records the total size of the segment (not including the header).
* Segment header never crosses sector boundary, thus it's possible to
* have at most 3 padding zeros at the end of the sector.
*
* 2.2 Data Payload
* Variable size. Size up limit should be lzo1x_worst_compress(sectorsize)
* which is 4419 for a 4KiB sectorsize.
*
* Example with 4K sectorsize:
* Page 1:
* 0 0x2 0x4 0x6 0x8 0xa 0xc 0xe 0x10
* 0x0000 | Header | SegHdr 01 | Data payload 01 ... |
* ...
* 0x0ff0 | SegHdr N | Data payload N ... |00|
* ^^ padding zeros
* Page 2:
* 0x1000 | SegHdr N+1| Data payload N+1 ... |
*/
#define WORKSPACE_BUF_LENGTH (lzo1x_worst_compress(PAGE_SIZE))
#define WORKSPACE_CBUF_LENGTH (lzo1x_worst_compress(PAGE_SIZE))
struct workspace {
void *mem;
void *buf; /* where decompressed data goes */
void *cbuf; /* where compressed data goes */
struct list_head list;
};
static struct workspace_manager wsm;
void lzo_free_workspace(struct list_head *ws)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
kvfree(workspace->buf);
kvfree(workspace->cbuf);
kvfree(workspace->mem);
kfree(workspace);
}
struct list_head *lzo_alloc_workspace(unsigned int level)
{
struct workspace *workspace;
workspace = kzalloc(sizeof(*workspace), GFP_KERNEL);
if (!workspace)
return ERR_PTR(-ENOMEM);
workspace->mem = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
workspace->buf = kvmalloc(WORKSPACE_BUF_LENGTH, GFP_KERNEL);
workspace->cbuf = kvmalloc(WORKSPACE_CBUF_LENGTH, GFP_KERNEL);
if (!workspace->mem || !workspace->buf || !workspace->cbuf)
goto fail;
INIT_LIST_HEAD(&workspace->list);
return &workspace->list;
fail:
lzo_free_workspace(&workspace->list);
return ERR_PTR(-ENOMEM);
}
static inline void write_compress_length(char *buf, size_t len)
{
__le32 dlen;
dlen = cpu_to_le32(len);
memcpy(buf, &dlen, LZO_LEN);
}
static inline size_t read_compress_length(const char *buf)
{
__le32 dlen;
memcpy(&dlen, buf, LZO_LEN);
return le32_to_cpu(dlen);
}
/*
* Will do:
*
* - Write a segment header into the destination
* - Copy the compressed buffer into the destination
* - Make sure we have enough space in the last sector to fit a segment header
* If not, we will pad at most (LZO_LEN (4)) - 1 bytes of zeros.
*
* Will allocate new pages when needed.
*/
static int copy_compressed_data_to_page(char *compressed_data,
size_t compressed_size,
struct page **out_pages,
unsigned long max_nr_page,
u32 *cur_out,
const u32 sectorsize)
{
u32 sector_bytes_left;
u32 orig_out;
struct page *cur_page;
char *kaddr;
if ((*cur_out / PAGE_SIZE) >= max_nr_page)
return -E2BIG;
/*
* We never allow a segment header crossing sector boundary, previous
* run should ensure we have enough space left inside the sector.
*/
ASSERT((*cur_out / sectorsize) == (*cur_out + LZO_LEN - 1) / sectorsize);
cur_page = out_pages[*cur_out / PAGE_SIZE];
/* Allocate a new page */
if (!cur_page) {
cur_page = alloc_page(GFP_NOFS);
if (!cur_page)
return -ENOMEM;
out_pages[*cur_out / PAGE_SIZE] = cur_page;
}
kaddr = kmap(cur_page);
write_compress_length(kaddr + offset_in_page(*cur_out),
compressed_size);
*cur_out += LZO_LEN;
orig_out = *cur_out;
/* Copy compressed data */
while (*cur_out - orig_out < compressed_size) {
u32 copy_len = min_t(u32, sectorsize - *cur_out % sectorsize,
orig_out + compressed_size - *cur_out);
kunmap(cur_page);
if ((*cur_out / PAGE_SIZE) >= max_nr_page)
return -E2BIG;
cur_page = out_pages[*cur_out / PAGE_SIZE];
/* Allocate a new page */
if (!cur_page) {
cur_page = alloc_page(GFP_NOFS);
if (!cur_page)
return -ENOMEM;
out_pages[*cur_out / PAGE_SIZE] = cur_page;
}
kaddr = kmap(cur_page);
memcpy(kaddr + offset_in_page(*cur_out),
compressed_data + *cur_out - orig_out, copy_len);
*cur_out += copy_len;
}
/*
* Check if we can fit the next segment header into the remaining space
* of the sector.
*/
sector_bytes_left = round_up(*cur_out, sectorsize) - *cur_out;
if (sector_bytes_left >= LZO_LEN || sector_bytes_left == 0)
goto out;
/* The remaining size is not enough, pad it with zeros */
memset(kaddr + offset_in_page(*cur_out), 0,
sector_bytes_left);
*cur_out += sector_bytes_left;
out:
kunmap(cur_page);
return 0;
}
int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
u64 start, struct page **pages, unsigned long *out_pages,
unsigned long *total_in, unsigned long *total_out)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
const u32 sectorsize = btrfs_sb(mapping->host->i_sb)->sectorsize;
struct page *page_in = NULL;
char *sizes_ptr;
const unsigned long max_nr_page = *out_pages;
int ret = 0;
/* Points to the file offset of input data */
u64 cur_in = start;
/* Points to the current output byte */
u32 cur_out = 0;
u32 len = *total_out;
ASSERT(max_nr_page > 0);
*out_pages = 0;
*total_out = 0;
*total_in = 0;
/*
* Skip the header for now, we will later come back and write the total
* compressed size
*/
cur_out += LZO_LEN;
while (cur_in < start + len) {
char *data_in;
const u32 sectorsize_mask = sectorsize - 1;
u32 sector_off = (cur_in - start) & sectorsize_mask;
u32 in_len;
size_t out_len;
/* Get the input page first */
if (!page_in) {
page_in = find_get_page(mapping, cur_in >> PAGE_SHIFT);
ASSERT(page_in);
}
/* Compress at most one sector of data each time */
in_len = min_t(u32, start + len - cur_in, sectorsize - sector_off);
ASSERT(in_len);
data_in = kmap(page_in);
ret = lzo1x_1_compress(data_in +
offset_in_page(cur_in), in_len,
workspace->cbuf, &out_len,
workspace->mem);
kunmap(page_in);
if (ret < 0) {
pr_debug("BTRFS: lzo in loop returned %d\n", ret);
ret = -EIO;
goto out;
}
ret = copy_compressed_data_to_page(workspace->cbuf, out_len,
pages, max_nr_page,
&cur_out, sectorsize);
if (ret < 0)
goto out;
cur_in += in_len;
/*
* Check if we're making it bigger after two sectors. And if
* it is so, give up.
*/
if (cur_in - start > sectorsize * 2 && cur_in - start < cur_out) {
ret = -E2BIG;
goto out;
}
/* Check if we have reached page boundary */
if (IS_ALIGNED(cur_in, PAGE_SIZE)) {
put_page(page_in);
page_in = NULL;
}
}
/* Store the size of all chunks of compressed data */
sizes_ptr = kmap_local_page(pages[0]);
write_compress_length(sizes_ptr, cur_out);
kunmap_local(sizes_ptr);
ret = 0;
*total_out = cur_out;
*total_in = cur_in - start;
out:
if (page_in)
put_page(page_in);
*out_pages = DIV_ROUND_UP(cur_out, PAGE_SIZE);
return ret;
}
/*
* Copy the compressed segment payload into @dest.
*
* For the payload there will be no padding, just need to do page switching.
*/
static void copy_compressed_segment(struct compressed_bio *cb,
char *dest, u32 len, u32 *cur_in)
{
u32 orig_in = *cur_in;
while (*cur_in < orig_in + len) {
char *kaddr;
struct page *cur_page;
u32 copy_len = min_t(u32, PAGE_SIZE - offset_in_page(*cur_in),
orig_in + len - *cur_in);
ASSERT(copy_len);
cur_page = cb->compressed_pages[*cur_in / PAGE_SIZE];
kaddr = kmap(cur_page);
memcpy(dest + *cur_in - orig_in,
kaddr + offset_in_page(*cur_in),
copy_len);
kunmap(cur_page);
*cur_in += copy_len;
}
}
int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
const struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
const u32 sectorsize = fs_info->sectorsize;
char *kaddr;
int ret;
/* Compressed data length, can be unaligned */
u32 len_in;
/* Offset inside the compressed data */
u32 cur_in = 0;
/* Bytes decompressed so far */
u32 cur_out = 0;
kaddr = kmap(cb->compressed_pages[0]);
len_in = read_compress_length(kaddr);
kunmap(cb->compressed_pages[0]);
cur_in += LZO_LEN;
/*
* LZO header length check
*
* The total length should not exceed the maximum extent length,
* and all sectors should be used.
* If this happens, it means the compressed extent is corrupted.
*/
if (len_in > min_t(size_t, BTRFS_MAX_COMPRESSED, cb->compressed_len) ||
round_up(len_in, sectorsize) < cb->compressed_len) {
btrfs_err(fs_info,
"invalid lzo header, lzo len %u compressed len %u",
len_in, cb->compressed_len);
return -EUCLEAN;
}
/* Go through each lzo segment */
while (cur_in < len_in) {
struct page *cur_page;
/* Length of the compressed segment */
u32 seg_len;
u32 sector_bytes_left;
size_t out_len = lzo1x_worst_compress(sectorsize);
/*
* We should always have enough space for one segment header
* inside current sector.
*/
ASSERT(cur_in / sectorsize ==
(cur_in + LZO_LEN - 1) / sectorsize);
cur_page = cb->compressed_pages[cur_in / PAGE_SIZE];
ASSERT(cur_page);
kaddr = kmap(cur_page);
seg_len = read_compress_length(kaddr + offset_in_page(cur_in));
kunmap(cur_page);
cur_in += LZO_LEN;
if (seg_len > WORKSPACE_CBUF_LENGTH) {
/*
* seg_len shouldn't be larger than we have allocated
* for workspace->cbuf
*/
btrfs_err(fs_info, "unexpectedly large lzo segment len %u",
seg_len);
ret = -EIO;
goto out;
}
/* Copy the compressed segment payload into workspace */
copy_compressed_segment(cb, workspace->cbuf, seg_len, &cur_in);
/* Decompress the data */
ret = lzo1x_decompress_safe(workspace->cbuf, seg_len,
workspace->buf, &out_len);
if (ret != LZO_E_OK) {
btrfs_err(fs_info, "failed to decompress");
ret = -EIO;
goto out;
}
/* Copy the data into inode pages */
ret = btrfs_decompress_buf2page(workspace->buf, out_len, cb, cur_out);
cur_out += out_len;
/* All data read, exit */
if (ret == 0)
goto out;
ret = 0;
/* Check if the sector has enough space for a segment header */
sector_bytes_left = sectorsize - (cur_in % sectorsize);
if (sector_bytes_left >= LZO_LEN)
continue;
/* Skip the padding zeros */
cur_in += sector_bytes_left;
}
out:
if (!ret)
zero_fill_bio(cb->orig_bio);
return ret;
}
int lzo_decompress(struct list_head *ws, unsigned char *data_in,
struct page *dest_page, unsigned long start_byte, size_t srclen,
size_t destlen)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
size_t in_len;
size_t out_len;
size_t max_segment_len = WORKSPACE_BUF_LENGTH;
int ret = 0;
char *kaddr;
unsigned long bytes;
if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
return -EUCLEAN;
in_len = read_compress_length(data_in);
if (in_len != srclen)
return -EUCLEAN;
data_in += LZO_LEN;
in_len = read_compress_length(data_in);
if (in_len != srclen - LZO_LEN * 2) {
ret = -EUCLEAN;
goto out;
}
data_in += LZO_LEN;
out_len = PAGE_SIZE;
ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
if (ret != LZO_E_OK) {
pr_warn("BTRFS: decompress failed!\n");
ret = -EIO;
goto out;
}
if (out_len < start_byte) {
ret = -EIO;
goto out;
}
/*
* the caller is already checking against PAGE_SIZE, but lets
* move this check closer to the memcpy/memset
*/
destlen = min_t(unsigned long, destlen, PAGE_SIZE);
bytes = min_t(unsigned long, destlen, out_len - start_byte);
kaddr = kmap_local_page(dest_page);
memcpy(kaddr, workspace->buf + start_byte, bytes);
/*
* btrfs_getblock is doing a zero on the tail of the page too,
* but this will cover anything missing from the decompressed
* data.
*/
if (bytes < destlen)
memset(kaddr+bytes, 0, destlen-bytes);
kunmap_local(kaddr);
out:
return ret;
}
const struct btrfs_compress_op btrfs_lzo_compress = {
.workspace_manager = &wsm,
.max_level = 1,
.default_level = 1,
};
|