forked from xenserver/qemu-xen-4.2
-
Notifications
You must be signed in to change notification settings - Fork 1
/
block-vpc.c
593 lines (470 loc) · 16.5 KB
/
block-vpc.c
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
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
/*
* Block driver for Conectix/Microsoft Virtual PC images
*
* Copyright (c) 2005 Alex Beregszaszi
* Copyright (c) 2009 Kevin Wolf <[email protected]>
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
/**************************************************************/
#define HEADER_SIZE 512
//#define CACHE
enum vhd_type {
VHD_FIXED = 2,
VHD_DYNAMIC = 3,
VHD_DIFFERENCING = 4,
};
// Seconds since Jan 1, 2000 0:00:00 (UTC)
#define VHD_TIMESTAMP_BASE 946684800
// always big-endian
struct vhd_footer {
char creator[8]; // "conectix"
uint32_t features;
uint32_t version;
// Offset of next header structure, 0xFFFFFFFF if none
uint64_t data_offset;
// Seconds since Jan 1, 2000 0:00:00 (UTC)
uint32_t timestamp;
char creator_app[4]; // "vpc "
uint16_t major;
uint16_t minor;
char creator_os[4]; // "Wi2k"
uint64_t orig_size;
uint64_t size;
uint16_t cyls;
uint8_t heads;
uint8_t secs_per_cyl;
uint32_t type;
// Checksum of the Hard Disk Footer ("one's complement of the sum of all
// the bytes in the footer without the checksum field")
uint32_t checksum;
// UUID used to identify a parent hard disk (backing file)
uint8_t uuid[16];
uint8_t in_saved_state;
};
struct vhd_dyndisk_header {
char magic[8]; // "cxsparse"
// Offset of next header structure, 0xFFFFFFFF if none
uint64_t data_offset;
// Offset of the Block Allocation Table (BAT)
uint64_t table_offset;
uint32_t version;
uint32_t max_table_entries; // 32bit/entry
// 2 MB by default, must be a power of two
uint32_t block_size;
uint32_t checksum;
uint8_t parent_uuid[16];
uint32_t parent_timestamp;
uint32_t reserved;
// Backing file name (in UTF-16)
uint8_t parent_name[512];
struct {
uint32_t platform;
uint32_t data_space;
uint32_t data_length;
uint32_t reserved;
uint64_t data_offset;
} parent_locator[8];
};
typedef struct BDRVVPCState {
BlockDriverState *hd;
uint8_t footer_buf[HEADER_SIZE];
uint64_t free_data_block_offset;
int max_table_entries;
uint32_t *pagetable;
uint64_t bat_offset;
uint64_t last_bitmap_offset;
uint32_t block_size;
uint32_t bitmap_size;
#ifdef CACHE
uint8_t *pageentry_u8;
uint32_t *pageentry_u32;
uint16_t *pageentry_u16;
uint64_t last_bitmap;
#endif
} BDRVVPCState;
static uint32_t vpc_checksum(uint8_t* buf, size_t size)
{
uint32_t res = 0;
int i;
for (i = 0; i < size; i++)
res += buf[i];
return ~res;
}
static int vpc_probe(const uint8_t *buf, int buf_size, const char *filename)
{
if (buf_size >= 8 && !strncmp((char *)buf, "conectix", 8))
return 100;
return 0;
}
static int vpc_open(BlockDriverState *bs, const char *filename, int flags)
{
BDRVVPCState *s = bs->opaque;
int ret, i;
struct vhd_footer* footer;
struct vhd_dyndisk_header* dyndisk_header;
uint8_t buf[HEADER_SIZE];
uint32_t checksum;
ret = bdrv_file_open(&s->hd, filename, flags);
if (ret < 0)
return ret;
if (bdrv_pread(s->hd, 0, s->footer_buf, HEADER_SIZE) != HEADER_SIZE)
goto fail;
footer = (struct vhd_footer*) s->footer_buf;
if (strncmp(footer->creator, "conectix", 8))
goto fail;
checksum = be32_to_cpu(footer->checksum);
footer->checksum = 0;
if (vpc_checksum(s->footer_buf, HEADER_SIZE) != checksum)
fprintf(stderr, "block-vpc: The header checksum of '%s' is "
"incorrect.\n", filename);
// The visible size of a image in Virtual PC depends on the geometry
// rather than on the size stored in the footer (the size in the footer
// is too large usually)
bs->total_sectors = (int64_t)
be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;
if (bdrv_pread(s->hd, be64_to_cpu(footer->data_offset), buf, HEADER_SIZE)
!= HEADER_SIZE)
goto fail;
dyndisk_header = (struct vhd_dyndisk_header*) buf;
if (strncmp(dyndisk_header->magic, "cxsparse", 8))
goto fail;
s->block_size = be32_to_cpu(dyndisk_header->block_size);
s->bitmap_size = ((s->block_size / (8 * 512)) + 511) & ~511;
s->max_table_entries = be32_to_cpu(dyndisk_header->max_table_entries);
s->pagetable = qemu_malloc(s->max_table_entries * 4);
s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
if (bdrv_pread(s->hd, s->bat_offset, s->pagetable,
s->max_table_entries * 4) != s->max_table_entries * 4)
goto fail;
s->free_data_block_offset =
(s->bat_offset + (s->max_table_entries * 4) + 511) & ~511;
for (i = 0; i < s->max_table_entries; i++) {
be32_to_cpus(&s->pagetable[i]);
if (s->pagetable[i] != 0xFFFFFFFF) {
int64_t next = (512 * (int64_t) s->pagetable[i]) +
s->bitmap_size + s->block_size;
if (next> s->free_data_block_offset)
s->free_data_block_offset = next;
}
}
s->last_bitmap_offset = (int64_t) -1;
#ifdef CACHE
s->pageentry_u8 = qemu_malloc(512);
s->pageentry_u32 = s->pageentry_u8;
s->pageentry_u16 = s->pageentry_u8;
s->last_pagetable = -1;
#endif
return 0;
fail:
bdrv_delete(s->hd);
return -1;
}
/*
* Returns the absolute byte offset of the given sector in the image file.
* If the sector is not allocated, -1 is returned instead.
*
* The parameter write must be 1 if the offset will be used for a write
* operation (the block bitmaps is updated then), 0 otherwise.
*/
static inline int64_t get_sector_offset(BlockDriverState *bs,
int64_t sector_num, int write)
{
BDRVVPCState *s = bs->opaque;
uint64_t offset = sector_num * 512;
uint64_t bitmap_offset, block_offset;
uint32_t pagetable_index, pageentry_index;
pagetable_index = offset / s->block_size;
pageentry_index = (offset % s->block_size) / 512;
if (pagetable_index >= s->max_table_entries || s->pagetable[pagetable_index] == 0xffffffff)
return -1; // not allocated
bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
block_offset = bitmap_offset + s->bitmap_size + (512 * pageentry_index);
// We must ensure that we don't write to any sectors which are marked as
// unused in the bitmap. We get away with setting all bits in the block
// bitmap each time we write to a new block. This might cause Virtual PC to
// miss sparse read optimization, but it's not a problem in terms of
// correctness.
if (write && (s->last_bitmap_offset != bitmap_offset)) {
uint8_t bitmap[s->bitmap_size];
s->last_bitmap_offset = bitmap_offset;
memset(bitmap, 0xff, s->bitmap_size);
bdrv_pwrite(s->hd, bitmap_offset, bitmap, s->bitmap_size);
}
// printf("sector: %" PRIx64 ", index: %x, offset: %x, bioff: %" PRIx64 ", bloff: %" PRIx64 "\n",
// sector_num, pagetable_index, pageentry_index,
// bitmap_offset, block_offset);
// disabled by reason
#if 0
#ifdef CACHE
if (bitmap_offset != s->last_bitmap)
{
lseek(s->fd, bitmap_offset, SEEK_SET);
s->last_bitmap = bitmap_offset;
// Scary! Bitmap is stored as big endian 32bit entries,
// while we used to look it up byte by byte
read(s->fd, s->pageentry_u8, 512); // no error handling ?!
for (i = 0; i < 128; i++)
be32_to_cpus(&s->pageentry_u32[i]);
}
if ((s->pageentry_u8[pageentry_index / 8] >> (pageentry_index % 8)) & 1)
return -1;
#else
lseek(s->fd, bitmap_offset + (pageentry_index / 8), SEEK_SET);
read(s->fd, &bitmap_entry, 1); // no error handling ?!
if ((bitmap_entry >> (pageentry_index % 8)) & 1)
return -1; // not allocated
#endif
#endif
return block_offset;
}
/*
* Writes the footer to the end of the image file. This is needed when the
* file grows as it overwrites the old footer
*
* Returns 0 on success and < 0 on error
*/
static int rewrite_footer(BlockDriverState* bs)
{
int ret;
BDRVVPCState *s = bs->opaque;
int64_t offset = s->free_data_block_offset;
ret = bdrv_pwrite(s->hd, offset, s->footer_buf, HEADER_SIZE);
if (ret < 0)
return ret;
return 0;
}
/*
* Allocates a new block. This involves writing a new footer and updating
* the Block Allocation Table to use the space at the old end of the image
* file (overwriting the old footer)
*
* Returns the sectors' offset in the image file on success and < 0 on error
*/
static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
{
BDRVVPCState *s = bs->opaque;
int64_t bat_offset;
uint32_t index, bat_value;
int ret;
uint8_t bitmap[s->bitmap_size];
// Check if sector_num is valid
if ((sector_num < 0) || (sector_num > bs->total_sectors))
return -1;
// Write entry into in-memory BAT
index = (sector_num * 512) / s->block_size;
if (s->pagetable[index] != 0xFFFFFFFF)
return -1;
s->pagetable[index] = s->free_data_block_offset / 512;
// Initialize the block's bitmap
memset(bitmap, 0xff, s->bitmap_size);
bdrv_pwrite(s->hd, s->free_data_block_offset, bitmap, s->bitmap_size);
// Write new footer (the old one will be overwritten)
s->free_data_block_offset += s->block_size + s->bitmap_size;
ret = rewrite_footer(bs);
if (ret < 0)
goto fail;
// Write BAT entry to disk
bat_offset = s->bat_offset + (4 * index);
bat_value = be32_to_cpu(s->pagetable[index]);
ret = bdrv_pwrite(s->hd, bat_offset, &bat_value, 4);
if (ret < 0)
goto fail;
return get_sector_offset(bs, sector_num, 0);
fail:
s->free_data_block_offset -= (s->block_size + s->bitmap_size);
return -1;
}
static int vpc_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
BDRVVPCState *s = bs->opaque;
int ret;
int64_t offset;
while (nb_sectors > 0) {
offset = get_sector_offset(bs, sector_num, 0);
if (offset == -1) {
memset(buf, 0, 512);
} else {
ret = bdrv_pread(s->hd, offset, buf, 512);
if (ret != 512)
return -1;
}
nb_sectors--;
sector_num++;
buf += 512;
}
return 0;
}
static int vpc_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
BDRVVPCState *s = bs->opaque;
int64_t offset;
int ret;
while (nb_sectors > 0) {
offset = get_sector_offset(bs, sector_num, 1);
if (offset == -1) {
offset = alloc_block(bs, sector_num);
if (offset < 0)
return -1;
}
ret = bdrv_pwrite(s->hd, offset, buf, 512);
if (ret != 512)
return -1;
nb_sectors--;
sector_num++;
buf += 512;
}
return 0;
}
/*
* Calculates the number of cylinders, heads and sectors per cylinder
* based on a given number of sectors. This is the algorithm described
* in the VHD specification.
*
* Note that the geometry doesn't always exactly match total_sectors but
* may round it down.
*/
static void calculate_geometry(int64_t total_sectors, uint16_t* cyls,
uint8_t* heads, uint8_t* secs_per_cyl)
{
uint32_t cyls_times_heads;
if (total_sectors > 65535 * 16 * 255)
total_sectors = 65535 * 16 * 255;
if (total_sectors > 65535 * 16 * 63) {
*secs_per_cyl = 255;
*heads = 16;
cyls_times_heads = total_sectors / *secs_per_cyl;
} else {
*secs_per_cyl = 17;
cyls_times_heads = total_sectors / *secs_per_cyl;
*heads = (cyls_times_heads + 1023) / 1024;
if (*heads < 4)
*heads = 4;
if (cyls_times_heads >= (*heads * 1024) || *heads > 16) {
*secs_per_cyl = 31;
*heads = 16;
cyls_times_heads = total_sectors / *secs_per_cyl;
}
if (cyls_times_heads >= (*heads * 1024)) {
*secs_per_cyl = 63;
*heads = 16;
cyls_times_heads = total_sectors / *secs_per_cyl;
}
}
// Note: Rounding up deviates from the Virtual PC behaviour
// However, we need this to avoid truncating images in qemu-img convert
*cyls = (cyls_times_heads + *heads - 1) / *heads;
}
static int vpc_create(const char *filename, int64_t total_sectors,
const char *backing_file, int flags)
{
uint8_t buf[1024];
struct vhd_footer* footer = (struct vhd_footer*) buf;
struct vhd_dyndisk_header* dyndisk_header =
(struct vhd_dyndisk_header*) buf;
int fd, i;
uint16_t cyls;
uint8_t heads;
uint8_t secs_per_cyl;
size_t block_size, num_bat_entries;
if (backing_file != NULL)
return -ENOTSUP;
fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
if (fd < 0)
return -EIO;
// Calculate matching total_size and geometry
calculate_geometry(total_sectors, &cyls, &heads, &secs_per_cyl);
total_sectors = (int64_t) cyls * heads * secs_per_cyl;
// Prepare the Hard Disk Footer
memset(buf, 0, 1024);
strncpy(footer->creator, "conectix", 8);
// TODO Check if "qemu" creator_app is ok for VPC
strncpy(footer->creator_app, "qemu", 4);
strncpy(footer->creator_os, "Wi2k", 4);
footer->features = be32_to_cpu(0x02);
footer->version = be32_to_cpu(0x00010000);
footer->data_offset = be64_to_cpu(HEADER_SIZE);
footer->timestamp = be32_to_cpu(time(NULL) - VHD_TIMESTAMP_BASE);
// Version of Virtual PC 2007
footer->major = be16_to_cpu(0x0005);
footer->minor =be16_to_cpu(0x0003);
footer->orig_size = be64_to_cpu(total_sectors * 512);
footer->size = be64_to_cpu(total_sectors * 512);
footer->cyls = be16_to_cpu(cyls);
footer->heads = heads;
footer->secs_per_cyl = secs_per_cyl;
footer->type = be32_to_cpu(VHD_DYNAMIC);
// TODO uuid is missing
footer->checksum = be32_to_cpu(vpc_checksum(buf, HEADER_SIZE));
// Write the footer (twice: at the beginning and at the end)
block_size = 0x200000;
num_bat_entries = (total_sectors + block_size / 512) / (block_size / 512);
if (write(fd, buf, HEADER_SIZE) != HEADER_SIZE)
return -EIO;
if (lseek(fd, 1536 + ((num_bat_entries * 4 + 511) & ~511), SEEK_SET) < 0)
return -EIO;
if (write(fd, buf, HEADER_SIZE) != HEADER_SIZE)
return -EIO;
// Write the initial BAT
if (lseek(fd, 3 * 512, SEEK_SET) < 0)
return -EIO;
memset(buf, 0xFF, 512);
for (i = 0; i < (num_bat_entries * 4 + 511) / 512; i++)
if (write(fd, buf, 512) != 512)
return -EIO;
// Prepare the Dynamic Disk Header
memset(buf, 0, 1024);
strncpy(dyndisk_header->magic, "cxsparse", 8);
dyndisk_header->data_offset = be64_to_cpu(0xFFFFFFFF);
dyndisk_header->table_offset = be64_to_cpu(3 * 512);
dyndisk_header->version = be32_to_cpu(0x00010000);
dyndisk_header->block_size = be32_to_cpu(block_size);
dyndisk_header->max_table_entries = be32_to_cpu(num_bat_entries);
dyndisk_header->checksum = be32_to_cpu(vpc_checksum(buf, 1024));
// Write the header
if (lseek(fd, 512, SEEK_SET) < 0)
return -EIO;
if (write(fd, buf, 1024) != 1024)
return -EIO;
close(fd);
return 0;
}
static void vpc_close(BlockDriverState *bs)
{
BDRVVPCState *s = bs->opaque;
qemu_free(s->pagetable);
#ifdef CACHE
qemu_free(s->pageentry_u8);
#endif
bdrv_delete(s->hd);
}
BlockDriver bdrv_vpc = {
"vpc",
sizeof(BDRVVPCState),
vpc_probe,
vpc_open,
vpc_read,
vpc_write,
vpc_close,
vpc_create,
};