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
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
|
// 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"
#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 page 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 page boundary, thus it's possible to
* have at most 3 padding zeros at the end of the page.
*
* 2.2 Data Payload
* Variable size. Size up limit should be lzo1x_worst_compress(PAGE_SIZE)
* which is 4419 for a 4KiB page.
*
* Example:
* 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 ... |
*/
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;
static void lzo_init_workspace_manager(void)
{
btrfs_init_workspace_manager(&wsm, &btrfs_lzo_compress);
}
static void lzo_cleanup_workspace_manager(void)
{
btrfs_cleanup_workspace_manager(&wsm);
}
static struct list_head *lzo_get_workspace(unsigned int level)
{
return btrfs_get_workspace(&wsm, level);
}
static void lzo_put_workspace(struct list_head *ws)
{
btrfs_put_workspace(&wsm, ws);
}
static 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);
}
static 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(lzo1x_worst_compress(PAGE_SIZE), GFP_KERNEL);
workspace->cbuf = kvmalloc(lzo1x_worst_compress(PAGE_SIZE), 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);
}
static 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);
int ret = 0;
char *data_in;
char *cpage_out;
int nr_pages = 0;
struct page *in_page = NULL;
struct page *out_page = NULL;
unsigned long bytes_left;
unsigned long len = *total_out;
unsigned long nr_dest_pages = *out_pages;
const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
size_t in_len;
size_t out_len;
char *buf;
unsigned long tot_in = 0;
unsigned long tot_out = 0;
unsigned long pg_bytes_left;
unsigned long out_offset;
unsigned long bytes;
*out_pages = 0;
*total_out = 0;
*total_in = 0;
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
data_in = kmap(in_page);
/*
* store the size of all chunks of compressed data in
* the first 4 bytes
*/
out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
if (out_page == NULL) {
ret = -ENOMEM;
goto out;
}
cpage_out = kmap(out_page);
out_offset = LZO_LEN;
tot_out = LZO_LEN;
pages[0] = out_page;
nr_pages = 1;
pg_bytes_left = PAGE_SIZE - LZO_LEN;
/* compress at most one page of data each time */
in_len = min(len, PAGE_SIZE);
while (tot_in < len) {
ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf,
&out_len, workspace->mem);
if (ret != LZO_E_OK) {
pr_debug("BTRFS: lzo in loop returned %d\n",
ret);
ret = -EIO;
goto out;
}
/* store the size of this chunk of compressed data */
write_compress_length(cpage_out + out_offset, out_len);
tot_out += LZO_LEN;
out_offset += LZO_LEN;
pg_bytes_left -= LZO_LEN;
tot_in += in_len;
tot_out += out_len;
/* copy bytes from the working buffer into the pages */
buf = workspace->cbuf;
while (out_len) {
bytes = min_t(unsigned long, pg_bytes_left, out_len);
memcpy(cpage_out + out_offset, buf, bytes);
out_len -= bytes;
pg_bytes_left -= bytes;
buf += bytes;
out_offset += bytes;
/*
* we need another page for writing out.
*
* Note if there's less than 4 bytes left, we just
* skip to a new page.
*/
if ((out_len == 0 && pg_bytes_left < LZO_LEN) ||
pg_bytes_left == 0) {
if (pg_bytes_left) {
memset(cpage_out + out_offset, 0,
pg_bytes_left);
tot_out += pg_bytes_left;
}
/* we're done, don't allocate new page */
if (out_len == 0 && tot_in >= len)
break;
kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
goto out;
}
out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
if (out_page == NULL) {
ret = -ENOMEM;
goto out;
}
cpage_out = kmap(out_page);
pages[nr_pages++] = out_page;
pg_bytes_left = PAGE_SIZE;
out_offset = 0;
}
}
/* we're making it bigger, give up */
if (tot_in > 8192 && tot_in < tot_out) {
ret = -E2BIG;
goto out;
}
/* we're all done */
if (tot_in >= len)
break;
if (tot_out > max_out)
break;
bytes_left = len - tot_in;
kunmap(in_page);
put_page(in_page);
start += PAGE_SIZE;
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
data_in = kmap(in_page);
in_len = min(bytes_left, PAGE_SIZE);
}
if (tot_out >= tot_in) {
ret = -E2BIG;
goto out;
}
/* store the size of all chunks of compressed data */
cpage_out = kmap(pages[0]);
write_compress_length(cpage_out, tot_out);
kunmap(pages[0]);
ret = 0;
*total_out = tot_out;
*total_in = tot_in;
out:
*out_pages = nr_pages;
if (out_page)
kunmap(out_page);
if (in_page) {
kunmap(in_page);
put_page(in_page);
}
return ret;
}
static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0, ret2;
char *data_in;
unsigned long page_in_index = 0;
size_t srclen = cb->compressed_len;
unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
unsigned long buf_start;
unsigned long buf_offset = 0;
unsigned long bytes;
unsigned long working_bytes;
size_t in_len;
size_t out_len;
const size_t max_segment_len = lzo1x_worst_compress(PAGE_SIZE);
unsigned long in_offset;
unsigned long in_page_bytes_left;
unsigned long tot_in;
unsigned long tot_out;
unsigned long tot_len;
char *buf;
bool may_late_unmap, need_unmap;
struct page **pages_in = cb->compressed_pages;
u64 disk_start = cb->start;
struct bio *orig_bio = cb->orig_bio;
data_in = kmap(pages_in[0]);
tot_len = read_compress_length(data_in);
/*
* Compressed data header check.
*
* The real compressed size can't exceed the maximum extent length, and
* all pages should be used (whole unused page with just the segment
* header is not possible). If this happens it means the compressed
* extent is corrupted.
*/
if (tot_len > min_t(size_t, BTRFS_MAX_COMPRESSED, srclen) ||
tot_len < srclen - PAGE_SIZE) {
ret = -EUCLEAN;
goto done;
}
tot_in = LZO_LEN;
in_offset = LZO_LEN;
in_page_bytes_left = PAGE_SIZE - LZO_LEN;
tot_out = 0;
while (tot_in < tot_len) {
in_len = read_compress_length(data_in + in_offset);
in_page_bytes_left -= LZO_LEN;
in_offset += LZO_LEN;
tot_in += LZO_LEN;
/*
* Segment header check.
*
* The segment length must not exceed the maximum LZO
* compression size, nor the total compressed size.
*/
if (in_len > max_segment_len || tot_in + in_len > tot_len) {
ret = -EUCLEAN;
goto done;
}
tot_in += in_len;
working_bytes = in_len;
may_late_unmap = need_unmap = false;
/* fast path: avoid using the working buffer */
if (in_page_bytes_left >= in_len) {
buf = data_in + in_offset;
bytes = in_len;
may_late_unmap = true;
goto cont;
}
/* copy bytes from the pages into the working buffer */
buf = workspace->cbuf;
buf_offset = 0;
while (working_bytes) {
bytes = min(working_bytes, in_page_bytes_left);
memcpy(buf + buf_offset, data_in + in_offset, bytes);
buf_offset += bytes;
cont:
working_bytes -= bytes;
in_page_bytes_left -= bytes;
in_offset += bytes;
/* check if we need to pick another page */
if ((working_bytes == 0 && in_page_bytes_left < LZO_LEN)
|| in_page_bytes_left == 0) {
tot_in += in_page_bytes_left;
if (working_bytes == 0 && tot_in >= tot_len)
break;
if (page_in_index + 1 >= total_pages_in) {
ret = -EIO;
goto done;
}
if (may_late_unmap)
need_unmap = true;
else
kunmap(pages_in[page_in_index]);
data_in = kmap(pages_in[++page_in_index]);
in_page_bytes_left = PAGE_SIZE;
in_offset = 0;
}
}
out_len = max_segment_len;
ret = lzo1x_decompress_safe(buf, in_len, workspace->buf,
&out_len);
if (need_unmap)
kunmap(pages_in[page_in_index - 1]);
if (ret != LZO_E_OK) {
pr_warn("BTRFS: decompress failed\n");
ret = -EIO;
break;
}
buf_start = tot_out;
tot_out += out_len;
ret2 = btrfs_decompress_buf2page(workspace->buf, buf_start,
tot_out, disk_start, orig_bio);
if (ret2 == 0)
break;
}
done:
kunmap(pages_in[page_in_index]);
if (!ret)
zero_fill_bio(orig_bio);
return ret;
}
static 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 = lzo1x_worst_compress(PAGE_SIZE);
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_atomic(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_atomic(kaddr);
out:
return ret;
}
const struct btrfs_compress_op btrfs_lzo_compress = {
.init_workspace_manager = lzo_init_workspace_manager,
.cleanup_workspace_manager = lzo_cleanup_workspace_manager,
.get_workspace = lzo_get_workspace,
.put_workspace = lzo_put_workspace,
.alloc_workspace = lzo_alloc_workspace,
.free_workspace = lzo_free_workspace,
.compress_pages = lzo_compress_pages,
.decompress_bio = lzo_decompress_bio,
.decompress = lzo_decompress,
.max_level = 1,
.default_level = 1,
};
|