aboutsummaryrefslogtreecommitdiff
path: root/block/vhdx.c
blob: 2c921cff4e8c510c6146b21e180e6fad537893f3 (plain)
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
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
/*
 * Block driver for Hyper-V VHDX Images
 *
 * Copyright (c) 2013 Red Hat, Inc.,
 *
 * Authors:
 *  Jeff Cody <jcody@redhat.com>
 *
 *  This is based on the "VHDX Format Specification v1.00", published 8/25/2012
 *  by Microsoft:
 *      https://www.microsoft.com/en-us/download/details.aspx?id=34750
 *
 * This work is licensed under the terms of the GNU LGPL, version 2 or later.
 * See the COPYING.LIB file in the top-level directory.
 *
 */

#include "qemu-common.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "qemu/crc32c.h"
#include "block/vhdx.h"
#include "migration/migration.h"

#include <uuid/uuid.h>

/* Several metadata and region table data entries are identified by
 * guids in  a MS-specific GUID format. */


/* ------- Known Region Table GUIDs ---------------------- */
static const MSGUID bat_guid =      { .data1 = 0x2dc27766,
                                      .data2 = 0xf623,
                                      .data3 = 0x4200,
                                      .data4 = { 0x9d, 0x64, 0x11, 0x5e,
                                                 0x9b, 0xfd, 0x4a, 0x08} };

static const MSGUID metadata_guid = { .data1 = 0x8b7ca206,
                                      .data2 = 0x4790,
                                      .data3 = 0x4b9a,
                                      .data4 = { 0xb8, 0xfe, 0x57, 0x5f,
                                                 0x05, 0x0f, 0x88, 0x6e} };



/* ------- Known Metadata Entry GUIDs ---------------------- */
static const MSGUID file_param_guid =   { .data1 = 0xcaa16737,
                                          .data2 = 0xfa36,
                                          .data3 = 0x4d43,
                                          .data4 = { 0xb3, 0xb6, 0x33, 0xf0,
                                                     0xaa, 0x44, 0xe7, 0x6b} };

static const MSGUID virtual_size_guid = { .data1 = 0x2FA54224,
                                          .data2 = 0xcd1b,
                                          .data3 = 0x4876,
                                          .data4 = { 0xb2, 0x11, 0x5d, 0xbe,
                                                     0xd8, 0x3b, 0xf4, 0xb8} };

static const MSGUID page83_guid =       { .data1 = 0xbeca12ab,
                                          .data2 = 0xb2e6,
                                          .data3 = 0x4523,
                                          .data4 = { 0x93, 0xef, 0xc3, 0x09,
                                                     0xe0, 0x00, 0xc7, 0x46} };


static const MSGUID phys_sector_guid =  { .data1 = 0xcda348c7,
                                          .data2 = 0x445d,
                                          .data3 = 0x4471,
                                          .data4 = { 0x9c, 0xc9, 0xe9, 0x88,
                                                     0x52, 0x51, 0xc5, 0x56} };

static const MSGUID parent_locator_guid = { .data1 = 0xa8d35f2d,
                                            .data2 = 0xb30b,
                                            .data3 = 0x454d,
                                            .data4 = { 0xab, 0xf7, 0xd3,
                                                       0xd8, 0x48, 0x34,
                                                       0xab, 0x0c} };

static const MSGUID logical_sector_guid = { .data1 = 0x8141bf1d,
                                            .data2 = 0xa96f,
                                            .data3 = 0x4709,
                                            .data4 = { 0xba, 0x47, 0xf2,
                                                       0x33, 0xa8, 0xfa,
                                                       0xab, 0x5f} };

/* Each parent type must have a valid GUID; this is for parent images
 * of type 'VHDX'.  If we were to allow e.g. a QCOW2 parent, we would
 * need to make up our own QCOW2 GUID type */
static const MSGUID parent_vhdx_guid = { .data1 = 0xb04aefb7,
                                         .data2 = 0xd19e,
                                         .data3 = 0x4a81,
                                         .data4 = { 0xb7, 0x89, 0x25, 0xb8,
                                                    0xe9, 0x44, 0x59, 0x13} };


#define META_FILE_PARAMETER_PRESENT      0x01
#define META_VIRTUAL_DISK_SIZE_PRESENT   0x02
#define META_PAGE_83_PRESENT             0x04
#define META_LOGICAL_SECTOR_SIZE_PRESENT 0x08
#define META_PHYS_SECTOR_SIZE_PRESENT    0x10
#define META_PARENT_LOCATOR_PRESENT      0x20

#define META_ALL_PRESENT    \
    (META_FILE_PARAMETER_PRESENT | META_VIRTUAL_DISK_SIZE_PRESENT | \
     META_PAGE_83_PRESENT | META_LOGICAL_SECTOR_SIZE_PRESENT | \
     META_PHYS_SECTOR_SIZE_PRESENT)


typedef struct VHDXSectorInfo {
    uint32_t bat_idx;       /* BAT entry index */
    uint32_t sectors_avail; /* sectors available in payload block */
    uint32_t bytes_left;    /* bytes left in the block after data to r/w */
    uint32_t bytes_avail;   /* bytes available in payload block */
    uint64_t file_offset;   /* absolute offset in bytes, in file */
    uint64_t block_offset;  /* block offset, in bytes */
} VHDXSectorInfo;

/* Calculates new checksum.
 *
 * Zero is substituted during crc calculation for the original crc field
 * crc_offset: byte offset in buf of the buffer crc
 * buf: buffer pointer
 * size: size of buffer (must be > crc_offset+4)
 *
 * Note: The resulting checksum is in the CPU endianness, not necessarily
 *       in the file format endianness (LE).  Any header export to disk should
 *       make sure that vhdx_header_le_export() is used to convert to the
 *       correct endianness
 */
uint32_t vhdx_update_checksum(uint8_t *buf, size_t size, int crc_offset)
{
    uint32_t crc;

    assert(buf != NULL);
    assert(size > (crc_offset + sizeof(crc)));

    memset(buf + crc_offset, 0, sizeof(crc));
    crc =  crc32c(0xffffffff, buf, size);
    memcpy(buf + crc_offset, &crc, sizeof(crc));

    return crc;
}

uint32_t vhdx_checksum_calc(uint32_t crc, uint8_t *buf, size_t size,
                            int crc_offset)
{
    uint32_t crc_new;
    uint32_t crc_orig;
    assert(buf != NULL);

    if (crc_offset > 0) {
        memcpy(&crc_orig, buf + crc_offset, sizeof(crc_orig));
        memset(buf + crc_offset, 0, sizeof(crc_orig));
    }

    crc_new = crc32c(crc, buf, size);
    if (crc_offset > 0) {
        memcpy(buf + crc_offset, &crc_orig, sizeof(crc_orig));
    }

    return crc_new;
}

/* Validates the checksum of the buffer, with an in-place CRC.
 *
 * Zero is substituted during crc calculation for the original crc field,
 * and the crc field is restored afterwards.  But the buffer will be modifed
 * during the calculation, so this may not be not suitable for multi-threaded
 * use.
 *
 * crc_offset: byte offset in buf of the buffer crc
 * buf: buffer pointer
 * size: size of buffer (must be > crc_offset+4)
 *
 * returns true if checksum is valid, false otherwise
 */
bool vhdx_checksum_is_valid(uint8_t *buf, size_t size, int crc_offset)
{
    uint32_t crc_orig;
    uint32_t crc;

    assert(buf != NULL);
    assert(size > (crc_offset + 4));

    memcpy(&crc_orig, buf + crc_offset, sizeof(crc_orig));
    crc_orig = le32_to_cpu(crc_orig);

    crc = vhdx_checksum_calc(0xffffffff, buf, size, crc_offset);

    return crc == crc_orig;
}


/*
 * This generates a UUID that is compliant with the MS GUIDs used
 * in the VHDX spec (and elsewhere).
 */
void vhdx_guid_generate(MSGUID *guid)
{
    uuid_t uuid;
    assert(guid != NULL);

    uuid_generate(uuid);
    memcpy(guid, uuid, sizeof(MSGUID));
}

/*
 * Per the MS VHDX Specification, for every VHDX file:
 *      - The header section is fixed size - 1 MB
 *      - The header section is always the first "object"
 *      - The first 64KB of the header is the File Identifier
 *      - The first uint64 (8 bytes) is the VHDX Signature ("vhdxfile")
 *      - The following 512 bytes constitute a UTF-16 string identifiying the
 *        software that created the file, and is optional and diagnostic only.
 *
 *  Therefore, we probe by looking for the vhdxfile signature "vhdxfile"
 */
static int vhdx_probe(const uint8_t *buf, int buf_size, const char *filename)
{
    if (buf_size >= 8 && !memcmp(buf, "vhdxfile", 8)) {
        return 100;
    }
    return 0;
}

/* All VHDX structures on disk are little endian */
static void vhdx_header_le_import(VHDXHeader *h)
{
    assert(h != NULL);

    le32_to_cpus(&h->signature);
    le32_to_cpus(&h->checksum);
    le64_to_cpus(&h->sequence_number);

    leguid_to_cpus(&h->file_write_guid);
    leguid_to_cpus(&h->data_write_guid);
    leguid_to_cpus(&h->log_guid);

    le16_to_cpus(&h->log_version);
    le16_to_cpus(&h->version);
    le32_to_cpus(&h->log_length);
    le64_to_cpus(&h->log_offset);
}

/* All VHDX structures on disk are little endian */
static void vhdx_header_le_export(VHDXHeader *orig_h, VHDXHeader *new_h)
{
    assert(orig_h != NULL);
    assert(new_h != NULL);

    new_h->signature       = cpu_to_le32(orig_h->signature);
    new_h->checksum        = cpu_to_le32(orig_h->checksum);
    new_h->sequence_number = cpu_to_le64(orig_h->sequence_number);

    new_h->file_write_guid = orig_h->file_write_guid;
    new_h->data_write_guid = orig_h->data_write_guid;
    new_h->log_guid        = orig_h->log_guid;

    cpu_to_leguids(&new_h->file_write_guid);
    cpu_to_leguids(&new_h->data_write_guid);
    cpu_to_leguids(&new_h->log_guid);

    new_h->log_version     = cpu_to_le16(orig_h->log_version);
    new_h->version         = cpu_to_le16(orig_h->version);
    new_h->log_length      = cpu_to_le32(orig_h->log_length);
    new_h->log_offset      = cpu_to_le64(orig_h->log_offset);
}

/* Update the VHDX headers
 *
 * This follows the VHDX spec procedures for header updates.
 *
 *  - non-current header is updated with largest sequence number
 */
static int vhdx_update_header(BlockDriverState *bs, BDRVVHDXState *s,
                              bool generate_data_write_guid)
{
    int ret = 0;
    int hdr_idx = 0;
    uint64_t header_offset = VHDX_HEADER1_OFFSET;

    VHDXHeader *active_header;
    VHDXHeader *inactive_header;
    VHDXHeader header_le;
    uint8_t *buffer;

    /* operate on the non-current header */
    if (s->curr_header == 0) {
        hdr_idx = 1;
        header_offset = VHDX_HEADER2_OFFSET;
    }

    active_header   = s->headers[s->curr_header];
    inactive_header = s->headers[hdr_idx];

    inactive_header->sequence_number = active_header->sequence_number + 1;

    /* a new file guid must be generated before any file write, including
     * headers */
    inactive_header->file_write_guid = s->session_guid;

    /* a new data guid only needs to be generated before any guest-visible
     * writes (i.e. something observable via virtual disk read) */
    if (generate_data_write_guid) {
        vhdx_guid_generate(&inactive_header->data_write_guid);
    }

    /* the header checksum is not over just the packed size of VHDXHeader,
     * but rather over the entire 'reserved' range for the header, which is
     * 4KB (VHDX_HEADER_SIZE). */

    buffer = qemu_blockalign(bs, VHDX_HEADER_SIZE);
    /* we can't assume the extra reserved bytes are 0 */
    ret = bdrv_pread(bs->file, header_offset, buffer, VHDX_HEADER_SIZE);
    if (ret < 0) {
        goto exit;
    }
    /* overwrite the actual VHDXHeader portion */
    memcpy(buffer, inactive_header, sizeof(VHDXHeader));
    inactive_header->checksum =
                        vhdx_update_checksum(buffer, VHDX_HEADER_SIZE,
                                             offsetof(VHDXHeader, checksum));
    vhdx_header_le_export(inactive_header, &header_le);
    ret = bdrv_pwrite_sync(bs->file, header_offset, &header_le,
                           sizeof(VHDXHeader));
    if (ret < 0) {
        goto exit;
    }
    s->curr_header = hdr_idx;

exit:
    qemu_vfree(buffer);
    return ret;
}

/*
 * The VHDX spec calls for header updates to be performed twice, so that both
 * the current and non-current header have valid info
 */
static int vhdx_update_headers(BlockDriverState *bs, BDRVVHDXState *s,
                               bool generate_data_write_guid)
{
    int ret;

    ret = vhdx_update_header(bs, s, generate_data_write_guid);
    if (ret < 0) {
        return ret;
    }
    ret = vhdx_update_header(bs, s, generate_data_write_guid);
    return ret;
}

/* opens the specified header block from the VHDX file header section */
static int vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s)
{
    int ret = 0;
    VHDXHeader *header1;
    VHDXHeader *header2;
    bool h1_valid = false;
    bool h2_valid = false;
    uint64_t h1_seq = 0;
    uint64_t h2_seq = 0;
    uint8_t *buffer;

    /* header1 & header2 are freed in vhdx_close() */
    header1 = qemu_blockalign(bs, sizeof(VHDXHeader));
    header2 = qemu_blockalign(bs, sizeof(VHDXHeader));

    buffer = qemu_blockalign(bs, VHDX_HEADER_SIZE);

    s->headers[0] = header1;
    s->headers[1] = header2;

    /* We have to read the whole VHDX_HEADER_SIZE instead of
     * sizeof(VHDXHeader), because the checksum is over the whole
     * region */
    ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, buffer, VHDX_HEADER_SIZE);
    if (ret < 0) {
        goto fail;
    }
    /* copy over just the relevant portion that we need */
    memcpy(header1, buffer, sizeof(VHDXHeader));
    vhdx_header_le_import(header1);

    if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4) &&
        !memcmp(&header1->signature, "head", 4)             &&
        header1->version == 1) {
        h1_seq = header1->sequence_number;
        h1_valid = true;
    }

    ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer, VHDX_HEADER_SIZE);
    if (ret < 0) {
        goto fail;
    }
    /* copy over just the relevant portion that we need */
    memcpy(header2, buffer, sizeof(VHDXHeader));
    vhdx_header_le_import(header2);

    if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4) &&
        !memcmp(&header2->signature, "head", 4)             &&
        header2->version == 1) {
        h2_seq = header2->sequence_number;
        h2_valid = true;
    }

    /* If there is only 1 valid header (or no valid headers), we
     * don't care what the sequence numbers are */
    if (h1_valid && !h2_valid) {
        s->curr_header = 0;
    } else if (!h1_valid && h2_valid) {
        s->curr_header = 1;
    } else if (!h1_valid && !h2_valid) {
        ret = -EINVAL;
        goto fail;
    } else {
        /* If both headers are valid, then we choose the active one by the
         * highest sequence number.  If the sequence numbers are equal, that is
         * invalid */
        if (h1_seq > h2_seq) {
            s->curr_header = 0;
        } else if (h2_seq > h1_seq) {
            s->curr_header = 1;
        } else {
            ret = -EINVAL;
            goto fail;
        }
    }

    ret = 0;

    goto exit;

fail:
    qerror_report(ERROR_CLASS_GENERIC_ERROR, "No valid VHDX header found");
    qemu_vfree(header1);
    qemu_vfree(header2);
    s->headers[0] = NULL;
    s->headers[1] = NULL;
exit:
    qemu_vfree(buffer);
    return ret;
}


static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s)
{
    int ret = 0;
    uint8_t *buffer;
    int offset = 0;
    VHDXRegionTableEntry rt_entry;
    uint32_t i;
    bool bat_rt_found = false;
    bool metadata_rt_found = false;

    /* We have to read the whole 64KB block, because the crc32 is over the
     * whole block */
    buffer = qemu_blockalign(bs, VHDX_HEADER_BLOCK_SIZE);

    ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, buffer,
                     VHDX_HEADER_BLOCK_SIZE);
    if (ret < 0) {
        goto fail;
    }
    memcpy(&s->rt, buffer, sizeof(s->rt));
    le32_to_cpus(&s->rt.signature);
    le32_to_cpus(&s->rt.checksum);
    le32_to_cpus(&s->rt.entry_count);
    le32_to_cpus(&s->rt.reserved);
    offset += sizeof(s->rt);

    if (!vhdx_checksum_is_valid(buffer, VHDX_HEADER_BLOCK_SIZE, 4) ||
        memcmp(&s->rt.signature, "regi", 4)) {
        ret = -EINVAL;
        goto fail;
    }

    /* Per spec, maximum region table entry count is 2047 */
    if (s->rt.entry_count > 2047) {
        ret = -EINVAL;
        goto fail;
    }

    for (i = 0; i < s->rt.entry_count; i++) {
        memcpy(&rt_entry, buffer + offset, sizeof(rt_entry));
        offset += sizeof(rt_entry);

        leguid_to_cpus(&rt_entry.guid);
        le64_to_cpus(&rt_entry.file_offset);
        le32_to_cpus(&rt_entry.length);
        le32_to_cpus(&rt_entry.data_bits);

        /* see if we recognize the entry */
        if (guid_eq(rt_entry.guid, bat_guid)) {
            /* must be unique; if we have already found it this is invalid */
            if (bat_rt_found) {
                ret = -EINVAL;
                goto fail;
            }
            bat_rt_found = true;
            s->bat_rt = rt_entry;
            continue;
        }

        if (guid_eq(rt_entry.guid, metadata_guid)) {
            /* must be unique; if we have already found it this is invalid */
            if (metadata_rt_found) {
                ret = -EINVAL;
                goto fail;
            }
            metadata_rt_found = true;
            s->metadata_rt = rt_entry;
            continue;
        }

        if (rt_entry.data_bits & VHDX_REGION_ENTRY_REQUIRED) {
            /* cannot read vhdx file - required region table entry that
             * we do not understand.  per spec, we must fail to open */
            ret = -ENOTSUP;
            goto fail;
        }
    }
    ret = 0;

fail:
    qemu_vfree(buffer);
    return ret;
}



/* Metadata initial parser
 *
 * This loads all the metadata entry fields.  This may cause additional
 * fields to be processed (e.g. parent locator, etc..).
 *
 * There are 5 Metadata items that are always required:
 *      - File Parameters (block size, has a parent)
 *      - Virtual Disk Size (size, in bytes, of the virtual drive)
 *      - Page 83 Data (scsi page 83 guid)
 *      - Logical Sector Size (logical sector size in bytes, either 512 or
 *                             4096.  We only support 512 currently)
 *      - Physical Sector Size (512 or 4096)
 *
 * Also, if the File Parameters indicate this is a differencing file,
 * we must also look for the Parent Locator metadata item.
 */
static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
{
    int ret = 0;
    uint8_t *buffer;
    int offset = 0;
    uint32_t i = 0;
    VHDXMetadataTableEntry md_entry;

    buffer = qemu_blockalign(bs, VHDX_METADATA_TABLE_MAX_SIZE);

    ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, buffer,
                     VHDX_METADATA_TABLE_MAX_SIZE);
    if (ret < 0) {
        goto exit;
    }
    memcpy(&s->metadata_hdr, buffer, sizeof(s->metadata_hdr));
    offset += sizeof(s->metadata_hdr);

    le64_to_cpus(&s->metadata_hdr.signature);
    le16_to_cpus(&s->metadata_hdr.reserved);
    le16_to_cpus(&s->metadata_hdr.entry_count);

    if (memcmp(&s->metadata_hdr.signature, "metadata", 8)) {
        ret = -EINVAL;
        goto exit;
    }

    s->metadata_entries.present = 0;

    if ((s->metadata_hdr.entry_count * sizeof(md_entry)) >
        (VHDX_METADATA_TABLE_MAX_SIZE - offset)) {
        ret = -EINVAL;
        goto exit;
    }

    for (i = 0; i < s->metadata_hdr.entry_count; i++) {
        memcpy(&md_entry, buffer + offset, sizeof(md_entry));
        offset += sizeof(md_entry);

        leguid_to_cpus(&md_entry.item_id);
        le32_to_cpus(&md_entry.offset);
        le32_to_cpus(&md_entry.length);
        le32_to_cpus(&md_entry.data_bits);
        le32_to_cpus(&md_entry.reserved2);

        if (guid_eq(md_entry.item_id, file_param_guid)) {
            if (s->metadata_entries.present & META_FILE_PARAMETER_PRESENT) {
                ret = -EINVAL;
                goto exit;
            }
            s->metadata_entries.file_parameters_entry = md_entry;
            s->metadata_entries.present |= META_FILE_PARAMETER_PRESENT;
            continue;
        }

        if (guid_eq(md_entry.item_id, virtual_size_guid)) {
            if (s->metadata_entries.present & META_VIRTUAL_DISK_SIZE_PRESENT) {
                ret = -EINVAL;
                goto exit;
            }
            s->metadata_entries.virtual_disk_size_entry = md_entry;
            s->metadata_entries.present |= META_VIRTUAL_DISK_SIZE_PRESENT;
            continue;
        }

        if (guid_eq(md_entry.item_id, page83_guid)) {
            if (s->metadata_entries.present & META_PAGE_83_PRESENT) {
                ret = -EINVAL;
                goto exit;
            }
            s->metadata_entries.page83_data_entry = md_entry;
            s->metadata_entries.present |= META_PAGE_83_PRESENT;
            continue;
        }

        if (guid_eq(md_entry.item_id, logical_sector_guid)) {
            if (s->metadata_entries.present &
                META_LOGICAL_SECTOR_SIZE_PRESENT) {
                ret = -EINVAL;
                goto exit;
            }
            s->metadata_entries.logical_sector_size_entry = md_entry;
            s->metadata_entries.present |= META_LOGICAL_SECTOR_SIZE_PRESENT;
            continue;
        }

        if (guid_eq(md_entry.item_id, phys_sector_guid)) {
            if (s->metadata_entries.present & META_PHYS_SECTOR_SIZE_PRESENT) {
                ret = -EINVAL;
                goto exit;
            }
            s->metadata_entries.phys_sector_size_entry = md_entry;
            s->metadata_entries.present |= META_PHYS_SECTOR_SIZE_PRESENT;
            continue;
        }

        if (guid_eq(md_entry.item_id, parent_locator_guid)) {
            if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
                ret = -EINVAL;
                goto exit;
            }
            s->metadata_entries.parent_locator_entry = md_entry;
            s->metadata_entries.present |= META_PARENT_LOCATOR_PRESENT;
            continue;
        }

        if (md_entry.data_bits & VHDX_META_FLAGS_IS_REQUIRED) {
            /* cannot read vhdx file - required region table entry that
             * we do not understand.  per spec, we must fail to open */
            ret = -ENOTSUP;
            goto exit;
        }
    }

    if (s->metadata_entries.present != META_ALL_PRESENT) {
        ret = -ENOTSUP;
        goto exit;
    }

    ret = bdrv_pread(bs->file,
                     s->metadata_entries.file_parameters_entry.offset
                                         + s->metadata_rt.file_offset,
                     &s->params,
                     sizeof(s->params));

    if (ret < 0) {
        goto exit;
    }

    le32_to_cpus(&s->params.block_size);
    le32_to_cpus(&s->params.data_bits);


    /* We now have the file parameters, so we can tell if this is a
     * differencing file (i.e.. has_parent), is dynamic or fixed
     * sized (leave_blocks_allocated), and the block size */

    /* The parent locator required iff the file parameters has_parent set */
    if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
        if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
            /* TODO: parse  parent locator fields */
            ret = -ENOTSUP; /* temp, until differencing files are supported */
            goto exit;
        } else {
            /* if has_parent is set, but there is not parent locator present,
             * then that is an invalid combination */
            ret = -EINVAL;
            goto exit;
        }
    }

    /* determine virtual disk size, logical sector size,
     * and phys sector size */

    ret = bdrv_pread(bs->file,
                     s->metadata_entries.virtual_disk_size_entry.offset
                                           + s->metadata_rt.file_offset,
                     &s->virtual_disk_size,
                     sizeof(uint64_t));
    if (ret < 0) {
        goto exit;
    }
    ret = bdrv_pread(bs->file,
                     s->metadata_entries.logical_sector_size_entry.offset
                                             + s->metadata_rt.file_offset,
                     &s->logical_sector_size,
                     sizeof(uint32_t));
    if (ret < 0) {
        goto exit;
    }
    ret = bdrv_pread(bs->file,
                     s->metadata_entries.phys_sector_size_entry.offset
                                          + s->metadata_rt.file_offset,
                     &s->physical_sector_size,
                     sizeof(uint32_t));
    if (ret < 0) {
        goto exit;
    }

    le64_to_cpus(&s->virtual_disk_size);
    le32_to_cpus(&s->logical_sector_size);
    le32_to_cpus(&s->physical_sector_size);

    if (s->logical_sector_size == 0 || s->params.block_size == 0) {
        ret = -EINVAL;
        goto exit;
    }

    /* both block_size and sector_size are guaranteed powers of 2 */
    s->sectors_per_block = s->params.block_size / s->logical_sector_size;
    s->chunk_ratio = (VHDX_MAX_SECTORS_PER_BLOCK) *
                     (uint64_t)s->logical_sector_size /
                     (uint64_t)s->params.block_size;

    /* These values are ones we will want to use for division / multiplication
     * later on, and they are all guaranteed (per the spec) to be powers of 2,
     * so we can take advantage of that for shift operations during
     * reads/writes */
    if (s->logical_sector_size & (s->logical_sector_size - 1)) {
        ret = -EINVAL;
        goto exit;
    }
    if (s->sectors_per_block & (s->sectors_per_block - 1)) {
        ret = -EINVAL;
        goto exit;
    }
    if (s->chunk_ratio & (s->chunk_ratio - 1)) {
        ret = -EINVAL;
        goto exit;
    }
    s->block_size = s->params.block_size;
    if (s->block_size & (s->block_size - 1)) {
        ret = -EINVAL;
        goto exit;
    }

    s->logical_sector_size_bits = 31 - clz32(s->logical_sector_size);
    s->sectors_per_block_bits =   31 - clz32(s->sectors_per_block);
    s->chunk_ratio_bits =         63 - clz64(s->chunk_ratio);
    s->block_size_bits =          31 - clz32(s->block_size);

    ret = 0;

exit:
    qemu_vfree(buffer);
    return ret;
}

/* Parse the replay log.  Per the VHDX spec, if the log is present
 * it must be replayed prior to opening the file, even read-only.
 *
 * If read-only, we must replay the log in RAM (or refuse to open
 * a dirty VHDX file read-only */
static int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s)
{
    int ret = 0;
    int i;
    VHDXHeader *hdr;

    hdr = s->headers[s->curr_header];

    /* either the log guid, or log length is zero,
     * then a replay log is present */
    for (i = 0; i < sizeof(hdr->log_guid.data4); i++) {
        ret |= hdr->log_guid.data4[i];
    }
    if (hdr->log_guid.data1 == 0 &&
        hdr->log_guid.data2 == 0 &&
        hdr->log_guid.data3 == 0 &&
        ret == 0) {
        goto exit;
    }

    /* per spec, only log version of 0 is supported */
    if (hdr->log_version != 0) {
        ret = -EINVAL;
        goto exit;
    }

    if (hdr->log_length == 0) {
        goto exit;
    }

    /* We currently do not support images with logs to replay */
    ret = -ENOTSUP;

exit:
    return ret;
}


static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
{
    BDRVVHDXState *s = bs->opaque;
    int ret = 0;
    uint32_t i;
    uint64_t signature;
    uint32_t data_blocks_cnt, bitmap_blocks_cnt;


    s->bat = NULL;

    qemu_co_mutex_init(&s->lock);

    /* validate the file signature */
    ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t));
    if (ret < 0) {
        goto fail;
    }
    if (memcmp(&signature, "vhdxfile", 8)) {
        ret = -EINVAL;
        goto fail;
    }

    /* This is used for any header updates, for the file_write_guid.
     * The spec dictates that a new value should be used for the first
     * header update */
    vhdx_guid_generate(&s->session_guid);

    ret = vhdx_parse_header(bs, s);
    if (ret) {
        goto fail;
    }

    ret = vhdx_parse_log(bs, s);
    if (ret) {
        goto fail;
    }

    ret = vhdx_open_region_tables(bs, s);
    if (ret) {
        goto fail;
    }

    ret = vhdx_parse_metadata(bs, s);
    if (ret) {
        goto fail;
    }
    s->block_size = s->params.block_size;

    /* the VHDX spec dictates that virtual_disk_size is always a multiple of
     * logical_sector_size */
    bs->total_sectors = s->virtual_disk_size >> s->logical_sector_size_bits;

    data_blocks_cnt = s->virtual_disk_size >> s->block_size_bits;
    if (s->virtual_disk_size - (data_blocks_cnt << s->block_size_bits)) {
        data_blocks_cnt++;
    }
    bitmap_blocks_cnt = data_blocks_cnt >> s->chunk_ratio_bits;
    if (data_blocks_cnt - (bitmap_blocks_cnt << s->chunk_ratio_bits)) {
        bitmap_blocks_cnt++;
    }

    if (s->parent_entries) {
        s->bat_entries = bitmap_blocks_cnt * (s->chunk_ratio + 1);
    } else {
        s->bat_entries = data_blocks_cnt +
                         ((data_blocks_cnt - 1) >> s->chunk_ratio_bits);
    }

    s->bat_offset = s->bat_rt.file_offset;

    if (s->bat_entries > s->bat_rt.length / sizeof(VHDXBatEntry)) {
        /* BAT allocation is not large enough for all entries */
        ret = -EINVAL;
        goto fail;
    }

    /* s->bat is freed in vhdx_close() */
    s->bat = qemu_blockalign(bs, s->bat_rt.length);

    ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length);
    if (ret < 0) {
        goto fail;
    }

    for (i = 0; i < s->bat_entries; i++) {
        le64_to_cpus(&s->bat[i]);
    }

    if (flags & BDRV_O_RDWR) {
        ret = vhdx_update_headers(bs, s, false);
        if (ret < 0) {
            goto fail;
        }
    }

    /* TODO: differencing files, write */

    /* Disable migration when VHDX images are used */
    error_set(&s->migration_blocker,
            QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
            "vhdx", bs->device_name, "live migration");
    migrate_add_blocker(s->migration_blocker);

    return 0;
fail:
    qemu_vfree(s->headers[0]);
    qemu_vfree(s->headers[1]);
    qemu_vfree(s->bat);
    qemu_vfree(s->parent_entries);
    return ret;
}

static int vhdx_reopen_prepare(BDRVReopenState *state,
                               BlockReopenQueue *queue, Error **errp)
{
    return 0;
}


/*
 * Perform sector to block offset translations, to get various
 * sector and file offsets into the image.  See VHDXSectorInfo
 */
static void vhdx_block_translate(BDRVVHDXState *s, int64_t sector_num,
                                 int nb_sectors, VHDXSectorInfo *sinfo)
{
    uint32_t block_offset;

    sinfo->bat_idx = sector_num >> s->sectors_per_block_bits;
    /* effectively a modulo - this gives us the offset into the block
     * (in sector sizes) for our sector number */
    block_offset = sector_num - (sinfo->bat_idx << s->sectors_per_block_bits);
    /* the chunk ratio gives us the interleaving of the sector
     * bitmaps, so we need to advance our page block index by the
     * sector bitmaps entry number */
    sinfo->bat_idx += sinfo->bat_idx >> s->chunk_ratio_bits;

    /* the number of sectors we can read/write in this cycle */
    sinfo->sectors_avail = s->sectors_per_block - block_offset;

    sinfo->bytes_left = sinfo->sectors_avail << s->logical_sector_size_bits;

    if (sinfo->sectors_avail > nb_sectors) {
        sinfo->sectors_avail = nb_sectors;
    }

    sinfo->bytes_avail = sinfo->sectors_avail << s->logical_sector_size_bits;

    sinfo->file_offset = s->bat[sinfo->bat_idx] >> VHDX_BAT_FILE_OFF_BITS;

    sinfo->block_offset = block_offset << s->logical_sector_size_bits;

    /* The file offset must be past the header section, so must be > 0 */
    if (sinfo->file_offset == 0) {
        return;
    }

    /* block offset is the offset in vhdx logical sectors, in
     * the payload data block. Convert that to a byte offset
     * in the block, and add in the payload data block offset
     * in the file, in bytes, to get the final read address */

    sinfo->file_offset <<= 20;  /* now in bytes, rather than 1MB units */
    sinfo->file_offset += sinfo->block_offset;
}



static coroutine_fn int vhdx_co_readv(BlockDriverState *bs, int64_t sector_num,
                                      int nb_sectors, QEMUIOVector *qiov)
{
    BDRVVHDXState *s = bs->opaque;
    int ret = 0;
    VHDXSectorInfo sinfo;
    uint64_t bytes_done = 0;
    QEMUIOVector hd_qiov;

    qemu_iovec_init(&hd_qiov, qiov->niov);

    qemu_co_mutex_lock(&s->lock);

    while (nb_sectors > 0) {
        /* We are a differencing file, so we need to inspect the sector bitmap
         * to see if we have the data or not */
        if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
            /* not supported yet */
            ret = -ENOTSUP;
            goto exit;
        } else {
            vhdx_block_translate(s, sector_num, nb_sectors, &sinfo);

            qemu_iovec_reset(&hd_qiov);
            qemu_iovec_concat(&hd_qiov, qiov,  bytes_done, sinfo.bytes_avail);

            /* check the payload block state */
            switch (s->bat[sinfo.bat_idx] & VHDX_BAT_STATE_BIT_MASK) {
            case PAYLOAD_BLOCK_NOT_PRESENT: /* fall through */
            case PAYLOAD_BLOCK_UNDEFINED:   /* fall through */
            case PAYLOAD_BLOCK_UNMAPPED:    /* fall through */
            case PAYLOAD_BLOCK_ZERO:
                /* return zero */
                qemu_iovec_memset(&hd_qiov, 0, 0, sinfo.bytes_avail);
                break;
            case PAYLOAD_BLOCK_FULL_PRESENT:
                qemu_co_mutex_unlock(&s->lock);
                ret = bdrv_co_readv(bs->file,
                                    sinfo.file_offset >> BDRV_SECTOR_BITS,
                                    sinfo.sectors_avail, &hd_qiov);
                qemu_co_mutex_lock(&s->lock);
                if (ret < 0) {
                    goto exit;
                }
                break;
            case PAYLOAD_BLOCK_PARTIALLY_PRESENT:
                /* we don't yet support difference files, fall through
                 * to error */
            default:
                ret = -EIO;
                goto exit;
                break;
            }
            nb_sectors -= sinfo.sectors_avail;
            sector_num += sinfo.sectors_avail;
            bytes_done += sinfo.bytes_avail;
        }
    }
    ret = 0;
exit:
    qemu_co_mutex_unlock(&s->lock);
    qemu_iovec_destroy(&hd_qiov);
    return ret;
}



static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
                                      int nb_sectors, QEMUIOVector *qiov)
{
    return -ENOTSUP;
}


static void vhdx_close(BlockDriverState *bs)
{
    BDRVVHDXState *s = bs->opaque;
    qemu_vfree(s->headers[0]);
    qemu_vfree(s->headers[1]);
    qemu_vfree(s->bat);
    qemu_vfree(s->parent_entries);
    migrate_del_blocker(s->migration_blocker);
    error_free(s->migration_blocker);
}

static BlockDriver bdrv_vhdx = {
    .format_name            = "vhdx",
    .instance_size          = sizeof(BDRVVHDXState),
    .bdrv_probe             = vhdx_probe,
    .bdrv_open              = vhdx_open,
    .bdrv_close             = vhdx_close,
    .bdrv_reopen_prepare    = vhdx_reopen_prepare,
    .bdrv_co_readv          = vhdx_co_readv,
    .bdrv_co_writev         = vhdx_co_writev,
};

static void bdrv_vhdx_init(void)
{
    bdrv_register(&bdrv_vhdx);
}

block_init(bdrv_vhdx_init);