aboutsummaryrefslogtreecommitdiff
path: root/block/qcow2.c
blob: 4f9ef91715778cf078dd6e2e429c617391015f06 (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
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
/*
 * Block driver for the QCOW version 2 format
 *
 * Copyright (c) 2004-2006 Fabrice Bellard
 *
 * 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"
#include "module.h"
#include <zlib.h>
#include "aes.h"
#include "block/qcow2.h"

/*
  Differences with QCOW:

  - Support for multiple incremental snapshots.
  - Memory management by reference counts.
  - Clusters which have a reference count of one have the bit
    QCOW_OFLAG_COPIED to optimize write performance.
  - Size of compressed clusters is stored in sectors to reduce bit usage
    in the cluster offsets.
  - Support for storing additional data (such as the VM state) in the
    snapshots.
  - If a backing store is used, the cluster size is not constrained
    (could be backported to QCOW).
  - L2 tables have always a size of one cluster.
*/


typedef struct {
    uint32_t magic;
    uint32_t len;
} QCowExtension;
#define  QCOW_EXT_MAGIC_END 0
#define  QCOW_EXT_MAGIC_BACKING_FORMAT 0xE2792ACA



static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename)
{
    const QCowHeader *cow_header = (const void *)buf;

    if (buf_size >= sizeof(QCowHeader) &&
        be32_to_cpu(cow_header->magic) == QCOW_MAGIC &&
        be32_to_cpu(cow_header->version) == QCOW_VERSION)
        return 100;
    else
        return 0;
}


/* 
 * read qcow2 extension and fill bs
 * start reading from start_offset
 * finish reading upon magic of value 0 or when end_offset reached
 * unknown magic is skipped (future extension this version knows nothing about)
 * return 0 upon success, non-0 otherwise
 */
static int qcow_read_extensions(BlockDriverState *bs, uint64_t start_offset,
                                uint64_t end_offset)
{
    BDRVQcowState *s = bs->opaque;
    QCowExtension ext;
    uint64_t offset;

#ifdef DEBUG_EXT
    printf("qcow_read_extensions: start=%ld end=%ld\n", start_offset, end_offset);
#endif
    offset = start_offset;
    while (offset < end_offset) {

#ifdef DEBUG_EXT
        /* Sanity check */
        if (offset > s->cluster_size)
            printf("qcow_handle_extension: suspicious offset %lu\n", offset);

        printf("attemting to read extended header in offset %lu\n", offset);
#endif

        if (bdrv_pread(s->hd, offset, &ext, sizeof(ext)) != sizeof(ext)) {
            fprintf(stderr, "qcow_handle_extension: ERROR: pread fail from offset %llu\n",
                    (unsigned long long)offset);
            return 1;
        }
        be32_to_cpus(&ext.magic);
        be32_to_cpus(&ext.len);
        offset += sizeof(ext);
#ifdef DEBUG_EXT
        printf("ext.magic = 0x%x\n", ext.magic);
#endif
        switch (ext.magic) {
        case QCOW_EXT_MAGIC_END:
            return 0;

        case QCOW_EXT_MAGIC_BACKING_FORMAT:
            if (ext.len >= sizeof(bs->backing_format)) {
                fprintf(stderr, "ERROR: ext_backing_format: len=%u too large"
                        " (>=%zu)\n",
                        ext.len, sizeof(bs->backing_format));
                return 2;
            }
            if (bdrv_pread(s->hd, offset , bs->backing_format,
                           ext.len) != ext.len)
                return 3;
            bs->backing_format[ext.len] = '\0';
#ifdef DEBUG_EXT
            printf("Qcow2: Got format extension %s\n", bs->backing_format);
#endif
            offset = ((offset + ext.len + 7) & ~7);
            break;

        default:
            /* unknown magic -- just skip it */
            offset = ((offset + ext.len + 7) & ~7);
            break;
        }
    }

    return 0;
}


static int qcow_open(BlockDriverState *bs, const char *filename, int flags)
{
    BDRVQcowState *s = bs->opaque;
    int len, i, shift, ret;
    QCowHeader header;
    uint64_t ext_end;

    ret = bdrv_file_open(&s->hd, filename, flags);
    if (ret < 0)
        return ret;
    if (bdrv_pread(s->hd, 0, &header, sizeof(header)) != sizeof(header))
        goto fail;
    be32_to_cpus(&header.magic);
    be32_to_cpus(&header.version);
    be64_to_cpus(&header.backing_file_offset);
    be32_to_cpus(&header.backing_file_size);
    be64_to_cpus(&header.size);
    be32_to_cpus(&header.cluster_bits);
    be32_to_cpus(&header.crypt_method);
    be64_to_cpus(&header.l1_table_offset);
    be32_to_cpus(&header.l1_size);
    be64_to_cpus(&header.refcount_table_offset);
    be32_to_cpus(&header.refcount_table_clusters);
    be64_to_cpus(&header.snapshots_offset);
    be32_to_cpus(&header.nb_snapshots);

    if (header.magic != QCOW_MAGIC || header.version != QCOW_VERSION)
        goto fail;
    if (header.cluster_bits < MIN_CLUSTER_BITS ||
        header.cluster_bits > MAX_CLUSTER_BITS)
        goto fail;
    if (header.crypt_method > QCOW_CRYPT_AES)
        goto fail;
    s->crypt_method_header = header.crypt_method;
    if (s->crypt_method_header)
        bs->encrypted = 1;
    s->cluster_bits = header.cluster_bits;
    s->cluster_size = 1 << s->cluster_bits;
    s->cluster_sectors = 1 << (s->cluster_bits - 9);
    s->l2_bits = s->cluster_bits - 3; /* L2 is always one cluster */
    s->l2_size = 1 << s->l2_bits;
    bs->total_sectors = header.size / 512;
    s->csize_shift = (62 - (s->cluster_bits - 8));
    s->csize_mask = (1 << (s->cluster_bits - 8)) - 1;
    s->cluster_offset_mask = (1LL << s->csize_shift) - 1;
    s->refcount_table_offset = header.refcount_table_offset;
    s->refcount_table_size =
        header.refcount_table_clusters << (s->cluster_bits - 3);

    s->snapshots_offset = header.snapshots_offset;
    s->nb_snapshots = header.nb_snapshots;

    /* read the level 1 table */
    s->l1_size = header.l1_size;
    shift = s->cluster_bits + s->l2_bits;
    s->l1_vm_state_index = (header.size + (1LL << shift) - 1) >> shift;
    /* the L1 table must contain at least enough entries to put
       header.size bytes */
    if (s->l1_size < s->l1_vm_state_index)
        goto fail;
    s->l1_table_offset = header.l1_table_offset;
    if (s->l1_size > 0) {
        s->l1_table = qemu_mallocz(
            align_offset(s->l1_size * sizeof(uint64_t), 512));
        if (bdrv_pread(s->hd, s->l1_table_offset, s->l1_table, s->l1_size * sizeof(uint64_t)) !=
            s->l1_size * sizeof(uint64_t))
            goto fail;
        for(i = 0;i < s->l1_size; i++) {
            be64_to_cpus(&s->l1_table[i]);
        }
    }
    /* alloc L2 cache */
    s->l2_cache = qemu_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
    s->cluster_cache = qemu_malloc(s->cluster_size);
    /* one more sector for decompressed data alignment */
    s->cluster_data = qemu_malloc(QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size
                                  + 512);
    s->cluster_cache_offset = -1;

    if (qcow2_refcount_init(bs) < 0)
        goto fail;

    QLIST_INIT(&s->cluster_allocs);

    /* read qcow2 extensions */
    if (header.backing_file_offset)
        ext_end = header.backing_file_offset;
    else
        ext_end = s->cluster_size;
    if (qcow_read_extensions(bs, sizeof(header), ext_end))
        goto fail;

    /* read the backing file name */
    if (header.backing_file_offset != 0) {
        len = header.backing_file_size;
        if (len > 1023)
            len = 1023;
        if (bdrv_pread(s->hd, header.backing_file_offset, bs->backing_file, len) != len)
            goto fail;
        bs->backing_file[len] = '\0';
    }
    if (qcow2_read_snapshots(bs) < 0)
        goto fail;

#ifdef DEBUG_ALLOC
    qcow2_check_refcounts(bs);
#endif
    return 0;

 fail:
    qcow2_free_snapshots(bs);
    qcow2_refcount_close(bs);
    qemu_free(s->l1_table);
    qemu_free(s->l2_cache);
    qemu_free(s->cluster_cache);
    qemu_free(s->cluster_data);
    bdrv_delete(s->hd);
    return -1;
}

static int qcow_set_key(BlockDriverState *bs, const char *key)
{
    BDRVQcowState *s = bs->opaque;
    uint8_t keybuf[16];
    int len, i;

    memset(keybuf, 0, 16);
    len = strlen(key);
    if (len > 16)
        len = 16;
    /* XXX: we could compress the chars to 7 bits to increase
       entropy */
    for(i = 0;i < len;i++) {
        keybuf[i] = key[i];
    }
    s->crypt_method = s->crypt_method_header;

    if (AES_set_encrypt_key(keybuf, 128, &s->aes_encrypt_key) != 0)
        return -1;
    if (AES_set_decrypt_key(keybuf, 128, &s->aes_decrypt_key) != 0)
        return -1;
#if 0
    /* test */
    {
        uint8_t in[16];
        uint8_t out[16];
        uint8_t tmp[16];
        for(i=0;i<16;i++)
            in[i] = i;
        AES_encrypt(in, tmp, &s->aes_encrypt_key);
        AES_decrypt(tmp, out, &s->aes_decrypt_key);
        for(i = 0; i < 16; i++)
            printf(" %02x", tmp[i]);
        printf("\n");
        for(i = 0; i < 16; i++)
            printf(" %02x", out[i]);
        printf("\n");
    }
#endif
    return 0;
}

static int qcow_is_allocated(BlockDriverState *bs, int64_t sector_num,
                             int nb_sectors, int *pnum)
{
    uint64_t cluster_offset;

    *pnum = nb_sectors;
    cluster_offset = qcow2_get_cluster_offset(bs, sector_num << 9, pnum);

    return (cluster_offset != 0);
}

/* handle reading after the end of the backing file */
int qcow2_backing_read1(BlockDriverState *bs,
                  int64_t sector_num, uint8_t *buf, int nb_sectors)
{
    int n1;
    if ((sector_num + nb_sectors) <= bs->total_sectors)
        return nb_sectors;
    if (sector_num >= bs->total_sectors)
        n1 = 0;
    else
        n1 = bs->total_sectors - sector_num;
    memset(buf + n1 * 512, 0, 512 * (nb_sectors - n1));
    return n1;
}

typedef struct QCowAIOCB {
    BlockDriverAIOCB common;
    int64_t sector_num;
    QEMUIOVector *qiov;
    uint8_t *buf;
    void *orig_buf;
    int nb_sectors;
    int n;
    uint64_t cluster_offset;
    uint8_t *cluster_data;
    BlockDriverAIOCB *hd_aiocb;
    struct iovec hd_iov;
    QEMUIOVector hd_qiov;
    QEMUBH *bh;
    QCowL2Meta l2meta;
    QLIST_ENTRY(QCowAIOCB) next_depend;
} QCowAIOCB;

static void qcow_aio_cancel(BlockDriverAIOCB *blockacb)
{
    QCowAIOCB *acb = (QCowAIOCB *)blockacb;
    if (acb->hd_aiocb)
        bdrv_aio_cancel(acb->hd_aiocb);
    qemu_aio_release(acb);
}

static AIOPool qcow_aio_pool = {
    .aiocb_size         = sizeof(QCowAIOCB),
    .cancel             = qcow_aio_cancel,
};

static void qcow_aio_read_cb(void *opaque, int ret);
static void qcow_aio_read_bh(void *opaque)
{
    QCowAIOCB *acb = opaque;
    qemu_bh_delete(acb->bh);
    acb->bh = NULL;
    qcow_aio_read_cb(opaque, 0);
}

static int qcow_schedule_bh(QEMUBHFunc *cb, QCowAIOCB *acb)
{
    if (acb->bh)
        return -EIO;

    acb->bh = qemu_bh_new(cb, acb);
    if (!acb->bh)
        return -EIO;

    qemu_bh_schedule(acb->bh);

    return 0;
}

static void qcow_aio_read_cb(void *opaque, int ret)
{
    QCowAIOCB *acb = opaque;
    BlockDriverState *bs = acb->common.bs;
    BDRVQcowState *s = bs->opaque;
    int index_in_cluster, n1;

    acb->hd_aiocb = NULL;
    if (ret < 0)
        goto done;

    /* post process the read buffer */
    if (!acb->cluster_offset) {
        /* nothing to do */
    } else if (acb->cluster_offset & QCOW_OFLAG_COMPRESSED) {
        /* nothing to do */
    } else {
        if (s->crypt_method) {
            qcow2_encrypt_sectors(s, acb->sector_num, acb->buf, acb->buf,
                            acb->n, 0,
                            &s->aes_decrypt_key);
        }
    }

    acb->nb_sectors -= acb->n;
    acb->sector_num += acb->n;
    acb->buf += acb->n * 512;

    if (acb->nb_sectors == 0) {
        /* request completed */
        ret = 0;
        goto done;
    }

    /* prepare next AIO request */
    acb->n = acb->nb_sectors;
    acb->cluster_offset =
        qcow2_get_cluster_offset(bs, acb->sector_num << 9, &acb->n);
    index_in_cluster = acb->sector_num & (s->cluster_sectors - 1);

    if (!acb->cluster_offset) {
        if (bs->backing_hd) {
            /* read from the base image */
            n1 = qcow2_backing_read1(bs->backing_hd, acb->sector_num,
                               acb->buf, acb->n);
            if (n1 > 0) {
                acb->hd_iov.iov_base = (void *)acb->buf;
                acb->hd_iov.iov_len = acb->n * 512;
                qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
                acb->hd_aiocb = bdrv_aio_readv(bs->backing_hd, acb->sector_num,
                                    &acb->hd_qiov, acb->n,
				    qcow_aio_read_cb, acb);
                if (acb->hd_aiocb == NULL)
                    goto done;
            } else {
                ret = qcow_schedule_bh(qcow_aio_read_bh, acb);
                if (ret < 0)
                    goto done;
            }
        } else {
            /* Note: in this case, no need to wait */
            memset(acb->buf, 0, 512 * acb->n);
            ret = qcow_schedule_bh(qcow_aio_read_bh, acb);
            if (ret < 0)
                goto done;
        }
    } else if (acb->cluster_offset & QCOW_OFLAG_COMPRESSED) {
        /* add AIO support for compressed blocks ? */
        if (qcow2_decompress_cluster(s, acb->cluster_offset) < 0)
            goto done;
        memcpy(acb->buf,
               s->cluster_cache + index_in_cluster * 512, 512 * acb->n);
        ret = qcow_schedule_bh(qcow_aio_read_bh, acb);
        if (ret < 0)
            goto done;
    } else {
        if ((acb->cluster_offset & 511) != 0) {
            ret = -EIO;
            goto done;
        }

        acb->hd_iov.iov_base = (void *)acb->buf;
        acb->hd_iov.iov_len = acb->n * 512;
        qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
        acb->hd_aiocb = bdrv_aio_readv(s->hd,
                            (acb->cluster_offset >> 9) + index_in_cluster,
                            &acb->hd_qiov, acb->n, qcow_aio_read_cb, acb);
        if (acb->hd_aiocb == NULL)
            goto done;
    }

    return;
done:
    if (acb->qiov->niov > 1) {
        qemu_iovec_from_buffer(acb->qiov, acb->orig_buf, acb->qiov->size);
        qemu_vfree(acb->orig_buf);
    }
    acb->common.cb(acb->common.opaque, ret);
    qemu_aio_release(acb);
}

static QCowAIOCB *qcow_aio_setup(BlockDriverState *bs,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque, int is_write)
{
    QCowAIOCB *acb;

    acb = qemu_aio_get(&qcow_aio_pool, bs, cb, opaque);
    if (!acb)
        return NULL;
    acb->hd_aiocb = NULL;
    acb->sector_num = sector_num;
    acb->qiov = qiov;
    if (qiov->niov > 1) {
        acb->buf = acb->orig_buf = qemu_blockalign(bs, qiov->size);
        if (is_write)
            qemu_iovec_to_buffer(qiov, acb->buf);
    } else {
        acb->buf = (uint8_t *)qiov->iov->iov_base;
    }
    acb->nb_sectors = nb_sectors;
    acb->n = 0;
    acb->cluster_offset = 0;
    acb->l2meta.nb_clusters = 0;
    QLIST_INIT(&acb->l2meta.dependent_requests);
    return acb;
}

static BlockDriverAIOCB *qcow_aio_readv(BlockDriverState *bs,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque)
{
    QCowAIOCB *acb;

    acb = qcow_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
    if (!acb)
        return NULL;

    qcow_aio_read_cb(acb, 0);
    return &acb->common;
}

static void qcow_aio_write_cb(void *opaque, int ret);

static void run_dependent_requests(QCowL2Meta *m)
{
    QCowAIOCB *req;
    QCowAIOCB *next;

    /* Take the request off the list of running requests */
    if (m->nb_clusters != 0) {
        QLIST_REMOVE(m, next_in_flight);
    }

    /*
     * Restart all dependent requests.
     * Can't use QLIST_FOREACH here - the next link might not be the same
     * any more after the callback  (request could depend on a different
     * request now)
     */
    for (req = m->dependent_requests.lh_first; req != NULL; req = next) {
        next = req->next_depend.le_next;
        qcow_aio_write_cb(req, 0);
    }

    /* Empty the list for the next part of the request */
    QLIST_INIT(&m->dependent_requests);
}

static void qcow_aio_write_cb(void *opaque, int ret)
{
    QCowAIOCB *acb = opaque;
    BlockDriverState *bs = acb->common.bs;
    BDRVQcowState *s = bs->opaque;
    int index_in_cluster;
    const uint8_t *src_buf;
    int n_end;

    acb->hd_aiocb = NULL;

    if (ret >= 0) {
        ret = qcow2_alloc_cluster_link_l2(bs, acb->cluster_offset, &acb->l2meta);
    }

    run_dependent_requests(&acb->l2meta);

    if (ret < 0)
        goto done;

    acb->nb_sectors -= acb->n;
    acb->sector_num += acb->n;
    acb->buf += acb->n * 512;

    if (acb->nb_sectors == 0) {
        /* request completed */
        ret = 0;
        goto done;
    }

    index_in_cluster = acb->sector_num & (s->cluster_sectors - 1);
    n_end = index_in_cluster + acb->nb_sectors;
    if (s->crypt_method &&
        n_end > QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors)
        n_end = QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors;

    acb->cluster_offset = qcow2_alloc_cluster_offset(bs, acb->sector_num << 9,
                                          index_in_cluster,
                                          n_end, &acb->n, &acb->l2meta);

    /* Need to wait for another request? If so, we are done for now. */
    if (!acb->cluster_offset && acb->l2meta.depends_on != NULL) {
        QLIST_INSERT_HEAD(&acb->l2meta.depends_on->dependent_requests,
            acb, next_depend);
        return;
    }

    if (!acb->cluster_offset || (acb->cluster_offset & 511) != 0) {
        ret = -EIO;
        goto done;
    }
    if (s->crypt_method) {
        if (!acb->cluster_data) {
            acb->cluster_data = qemu_mallocz(QCOW_MAX_CRYPT_CLUSTERS *
                                             s->cluster_size);
        }
        qcow2_encrypt_sectors(s, acb->sector_num, acb->cluster_data, acb->buf,
                        acb->n, 1, &s->aes_encrypt_key);
        src_buf = acb->cluster_data;
    } else {
        src_buf = acb->buf;
    }
    acb->hd_iov.iov_base = (void *)src_buf;
    acb->hd_iov.iov_len = acb->n * 512;
    qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
    acb->hd_aiocb = bdrv_aio_writev(s->hd,
                                    (acb->cluster_offset >> 9) + index_in_cluster,
                                    &acb->hd_qiov, acb->n,
                                    qcow_aio_write_cb, acb);
    if (acb->hd_aiocb == NULL)
        goto done;

    return;

done:
    if (acb->qiov->niov > 1)
        qemu_vfree(acb->orig_buf);
    acb->common.cb(acb->common.opaque, ret);
    qemu_aio_release(acb);
}

static BlockDriverAIOCB *qcow_aio_writev(BlockDriverState *bs,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque)
{
    BDRVQcowState *s = bs->opaque;
    QCowAIOCB *acb;

    s->cluster_cache_offset = -1; /* disable compressed cache */

    acb = qcow_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
    if (!acb)
        return NULL;

    qcow_aio_write_cb(acb, 0);
    return &acb->common;
}

static void qcow_close(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    qemu_free(s->l1_table);
    qemu_free(s->l2_cache);
    qemu_free(s->cluster_cache);
    qemu_free(s->cluster_data);
    qcow2_refcount_close(bs);
    bdrv_delete(s->hd);
}

/*
 * Updates the variable length parts of the qcow2 header, i.e. the backing file
 * name and all extensions. qcow2 was not designed to allow such changes, so if
 * we run out of space (we can only use the first cluster) this function may
 * fail.
 *
 * Returns 0 on success, -errno in error cases.
 */
static int qcow2_update_ext_header(BlockDriverState *bs,
    const char *backing_file, const char *backing_fmt)
{
    size_t backing_file_len = 0;
    size_t backing_fmt_len = 0;
    BDRVQcowState *s = bs->opaque;
    QCowExtension ext_backing_fmt = {0, 0};
    int ret;

    /* Backing file format doesn't make sense without a backing file */
    if (backing_fmt && !backing_file) {
        return -EINVAL;
    }

    /* Prepare the backing file format extension if needed */
    if (backing_fmt) {
        ext_backing_fmt.len = cpu_to_be32(strlen(backing_fmt));
        ext_backing_fmt.magic = cpu_to_be32(QCOW_EXT_MAGIC_BACKING_FORMAT);
        backing_fmt_len = ((sizeof(ext_backing_fmt)
            + strlen(backing_fmt) + 7) & ~7);
    }

    /* Check if we can fit the new header into the first cluster */
    if (backing_file) {
        backing_file_len = strlen(backing_file);
    }

    size_t header_size = sizeof(QCowHeader) + backing_file_len
        + backing_fmt_len;

    if (header_size > s->cluster_size) {
        return -ENOSPC;
    }

    /* Rewrite backing file name and qcow2 extensions */
    size_t ext_size = header_size - sizeof(QCowHeader);
    uint8_t buf[ext_size];
    size_t offset = 0;
    size_t backing_file_offset = 0;

    if (backing_file) {
        if (backing_fmt) {
            int padding = backing_fmt_len -
                (sizeof(ext_backing_fmt) + strlen(backing_fmt));

            memcpy(buf + offset, &ext_backing_fmt, sizeof(ext_backing_fmt));
            offset += sizeof(ext_backing_fmt);

            memcpy(buf + offset, backing_fmt, strlen(backing_fmt));
            offset += strlen(backing_fmt);

            memset(buf + offset, 0, padding);
            offset += padding;
        }

        memcpy(buf + offset, backing_file, backing_file_len);
        backing_file_offset = sizeof(QCowHeader) + offset;
    }

    ret = bdrv_pwrite(s->hd, sizeof(QCowHeader), buf, ext_size);
    if (ret < 0) {
        goto fail;
    }

    /* Update header fields */
    uint64_t be_backing_file_offset = cpu_to_be64(backing_file_offset);
    uint32_t be_backing_file_size = cpu_to_be32(backing_file_len);

    ret = bdrv_pwrite(s->hd, offsetof(QCowHeader, backing_file_offset),
        &be_backing_file_offset, sizeof(uint64_t));
    if (ret < 0) {
        goto fail;
    }

    ret = bdrv_pwrite(s->hd, offsetof(QCowHeader, backing_file_size),
        &be_backing_file_size, sizeof(uint32_t));
    if (ret < 0) {
        goto fail;
    }

    ret = 0;
fail:
    return ret;
}

static int qcow2_change_backing_file(BlockDriverState *bs,
    const char *backing_file, const char *backing_fmt)
{
    return qcow2_update_ext_header(bs, backing_file, backing_fmt);
}

static int get_bits_from_size(size_t size)
{
    int res = 0;

    if (size == 0) {
        return -1;
    }

    while (size != 1) {
        /* Not a power of two */
        if (size & 1) {
            return -1;
        }

        size >>= 1;
        res++;
    }

    return res;
}


static int preallocate(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    uint64_t cluster_offset = 0;
    uint64_t nb_sectors;
    uint64_t offset;
    int num;
    QCowL2Meta meta;

    nb_sectors = bdrv_getlength(bs) >> 9;
    offset = 0;
    QLIST_INIT(&meta.dependent_requests);

    while (nb_sectors) {
        num = MIN(nb_sectors, INT_MAX >> 9);
        cluster_offset = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num,
            &meta);

        if (cluster_offset == 0) {
            return -1;
        }

        if (qcow2_alloc_cluster_link_l2(bs, cluster_offset, &meta) < 0) {
            qcow2_free_any_clusters(bs, cluster_offset, meta.nb_clusters);
            return -1;
        }

        /* There are no dependent requests, but we need to remove our request
         * from the list of in-flight requests */
        run_dependent_requests(&meta);

        /* TODO Preallocate data if requested */

        nb_sectors -= num;
        offset += num << 9;
    }

    /*
     * It is expected that the image file is large enough to actually contain
     * all of the allocated clusters (otherwise we get failing reads after
     * EOF). Extend the image to the last allocated sector.
     */
    if (cluster_offset != 0) {
        uint8_t buf[512];
        memset(buf, 0, 512);
        bdrv_write(s->hd, (cluster_offset >> 9) + num - 1, buf, 1);
    }

    return 0;
}

static int qcow_create2(const char *filename, int64_t total_size,
                        const char *backing_file, const char *backing_format,
                        int flags, size_t cluster_size, int prealloc)
{

    int fd, header_size, backing_filename_len, l1_size, i, shift, l2_bits;
    int ref_clusters, backing_format_len = 0;
    int rounded_ext_bf_len = 0;
    QCowHeader header;
    uint64_t tmp, offset;
    QCowCreateState s1, *s = &s1;
    QCowExtension ext_bf = {0, 0};


    memset(s, 0, sizeof(*s));

    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
    if (fd < 0)
        return -1;
    memset(&header, 0, sizeof(header));
    header.magic = cpu_to_be32(QCOW_MAGIC);
    header.version = cpu_to_be32(QCOW_VERSION);
    header.size = cpu_to_be64(total_size * 512);
    header_size = sizeof(header);
    backing_filename_len = 0;
    if (backing_file) {
        if (backing_format) {
            ext_bf.magic = QCOW_EXT_MAGIC_BACKING_FORMAT;
            backing_format_len = strlen(backing_format);
            ext_bf.len = backing_format_len;
            rounded_ext_bf_len = (sizeof(ext_bf) + ext_bf.len + 7) & ~7;
            header_size += rounded_ext_bf_len;
        }
        header.backing_file_offset = cpu_to_be64(header_size);
        backing_filename_len = strlen(backing_file);
        header.backing_file_size = cpu_to_be32(backing_filename_len);
        header_size += backing_filename_len;
    }

    /* Cluster size */
    s->cluster_bits = get_bits_from_size(cluster_size);
    if (s->cluster_bits < MIN_CLUSTER_BITS ||
        s->cluster_bits > MAX_CLUSTER_BITS)
    {
        fprintf(stderr, "Cluster size must be a power of two between "
            "%d and %dk\n",
            1 << MIN_CLUSTER_BITS,
            1 << (MAX_CLUSTER_BITS - 10));
        return -EINVAL;
    }
    s->cluster_size = 1 << s->cluster_bits;

    header.cluster_bits = cpu_to_be32(s->cluster_bits);
    header_size = (header_size + 7) & ~7;
    if (flags & BLOCK_FLAG_ENCRYPT) {
        header.crypt_method = cpu_to_be32(QCOW_CRYPT_AES);
    } else {
        header.crypt_method = cpu_to_be32(QCOW_CRYPT_NONE);
    }
    l2_bits = s->cluster_bits - 3;
    shift = s->cluster_bits + l2_bits;
    l1_size = (((total_size * 512) + (1LL << shift) - 1) >> shift);
    offset = align_offset(header_size, s->cluster_size);
    s->l1_table_offset = offset;
    header.l1_table_offset = cpu_to_be64(s->l1_table_offset);
    header.l1_size = cpu_to_be32(l1_size);
    offset += align_offset(l1_size * sizeof(uint64_t), s->cluster_size);

    s->refcount_table = qemu_mallocz(s->cluster_size);

    s->refcount_table_offset = offset;
    header.refcount_table_offset = cpu_to_be64(offset);
    header.refcount_table_clusters = cpu_to_be32(1);
    offset += s->cluster_size;
    s->refcount_block_offset = offset;

    /* count how many refcount blocks needed */
    tmp = offset >> s->cluster_bits;
    ref_clusters = (tmp >> (s->cluster_bits - REFCOUNT_SHIFT)) + 1;
    for (i=0; i < ref_clusters; i++) {
        s->refcount_table[i] = cpu_to_be64(offset);
        offset += s->cluster_size;
    }

    s->refcount_block = qemu_mallocz(ref_clusters * s->cluster_size);

    /* update refcounts */
    qcow2_create_refcount_update(s, 0, header_size);
    qcow2_create_refcount_update(s, s->l1_table_offset,
        l1_size * sizeof(uint64_t));
    qcow2_create_refcount_update(s, s->refcount_table_offset, s->cluster_size);
    qcow2_create_refcount_update(s, s->refcount_block_offset,
        ref_clusters * s->cluster_size);

    /* write all the data */
    write(fd, &header, sizeof(header));
    if (backing_file) {
        if (backing_format_len) {
            char zero[16];
            int padding = rounded_ext_bf_len - (ext_bf.len + sizeof(ext_bf));

            memset(zero, 0, sizeof(zero));
            cpu_to_be32s(&ext_bf.magic);
            cpu_to_be32s(&ext_bf.len);
            write(fd, &ext_bf, sizeof(ext_bf));
            write(fd, backing_format, backing_format_len);
            if (padding > 0) {
                write(fd, zero, padding);
            }
        }
        write(fd, backing_file, backing_filename_len);
    }
    lseek(fd, s->l1_table_offset, SEEK_SET);
    tmp = 0;
    for(i = 0;i < l1_size; i++) {
        write(fd, &tmp, sizeof(tmp));
    }
    lseek(fd, s->refcount_table_offset, SEEK_SET);
    write(fd, s->refcount_table, s->cluster_size);

    lseek(fd, s->refcount_block_offset, SEEK_SET);
    write(fd, s->refcount_block, ref_clusters * s->cluster_size);

    qemu_free(s->refcount_table);
    qemu_free(s->refcount_block);
    close(fd);

    /* Preallocate metadata */
    if (prealloc) {
        BlockDriverState *bs;
        bs = bdrv_new("");
        bdrv_open(bs, filename, BDRV_O_CACHE_WB);
        preallocate(bs);
        bdrv_close(bs);
    }

    return 0;
}

static int qcow_create(const char *filename, QEMUOptionParameter *options)
{
    const char *backing_file = NULL;
    const char *backing_fmt = NULL;
    uint64_t sectors = 0;
    int flags = 0;
    size_t cluster_size = 65536;
    int prealloc = 0;

    /* Read out options */
    while (options && options->name) {
        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
            sectors = options->value.n / 512;
        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
            backing_file = options->value.s;
        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FMT)) {
            backing_fmt = options->value.s;
        } else if (!strcmp(options->name, BLOCK_OPT_ENCRYPT)) {
            flags |= options->value.n ? BLOCK_FLAG_ENCRYPT : 0;
        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
            if (options->value.n) {
                cluster_size = options->value.n;
            }
        } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
            if (!options->value.s || !strcmp(options->value.s, "off")) {
                prealloc = 0;
            } else if (!strcmp(options->value.s, "metadata")) {
                prealloc = 1;
            } else {
                fprintf(stderr, "Invalid preallocation mode: '%s'\n",
                    options->value.s);
                return -EINVAL;
            }
        }
        options++;
    }

    if (backing_file && prealloc) {
        fprintf(stderr, "Backing file and preallocation cannot be used at "
            "the same time\n");
        return -EINVAL;
    }

    return qcow_create2(filename, sectors, backing_file, backing_fmt, flags,
        cluster_size, prealloc);
}

static int qcow_make_empty(BlockDriverState *bs)
{
#if 0
    /* XXX: not correct */
    BDRVQcowState *s = bs->opaque;
    uint32_t l1_length = s->l1_size * sizeof(uint64_t);
    int ret;

    memset(s->l1_table, 0, l1_length);
    if (bdrv_pwrite(s->hd, s->l1_table_offset, s->l1_table, l1_length) < 0)
        return -1;
    ret = bdrv_truncate(s->hd, s->l1_table_offset + l1_length);
    if (ret < 0)
        return ret;

    l2_cache_reset(bs);
#endif
    return 0;
}

/* XXX: put compressed sectors first, then all the cluster aligned
   tables to avoid losing bytes in alignment */
static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
                                 const uint8_t *buf, int nb_sectors)
{
    BDRVQcowState *s = bs->opaque;
    z_stream strm;
    int ret, out_len;
    uint8_t *out_buf;
    uint64_t cluster_offset;

    if (nb_sectors == 0) {
        /* align end of file to a sector boundary to ease reading with
           sector based I/Os */
        cluster_offset = bdrv_getlength(s->hd);
        cluster_offset = (cluster_offset + 511) & ~511;
        bdrv_truncate(s->hd, cluster_offset);
        return 0;
    }

    if (nb_sectors != s->cluster_sectors)
        return -EINVAL;

    out_buf = qemu_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);

    /* best compression, small window, no zlib header */
    memset(&strm, 0, sizeof(strm));
    ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION,
                       Z_DEFLATED, -12,
                       9, Z_DEFAULT_STRATEGY);
    if (ret != 0) {
        qemu_free(out_buf);
        return -1;
    }

    strm.avail_in = s->cluster_size;
    strm.next_in = (uint8_t *)buf;
    strm.avail_out = s->cluster_size;
    strm.next_out = out_buf;

    ret = deflate(&strm, Z_FINISH);
    if (ret != Z_STREAM_END && ret != Z_OK) {
        qemu_free(out_buf);
        deflateEnd(&strm);
        return -1;
    }
    out_len = strm.next_out - out_buf;

    deflateEnd(&strm);

    if (ret != Z_STREAM_END || out_len >= s->cluster_size) {
        /* could not compress: write normal cluster */
        bdrv_write(bs, sector_num, buf, s->cluster_sectors);
    } else {
        cluster_offset = qcow2_alloc_compressed_cluster_offset(bs,
            sector_num << 9, out_len);
        if (!cluster_offset)
            return -1;
        cluster_offset &= s->cluster_offset_mask;
        if (bdrv_pwrite(s->hd, cluster_offset, out_buf, out_len) != out_len) {
            qemu_free(out_buf);
            return -1;
        }
    }

    qemu_free(out_buf);
    return 0;
}

static void qcow_flush(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    bdrv_flush(s->hd);
}

static int64_t qcow_vm_state_offset(BDRVQcowState *s)
{
	return (int64_t)s->l1_vm_state_index << (s->cluster_bits + s->l2_bits);
}

static int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
    BDRVQcowState *s = bs->opaque;
    bdi->cluster_size = s->cluster_size;
    bdi->vm_state_offset = qcow_vm_state_offset(s);
    return 0;
}


static int qcow_check(BlockDriverState *bs)
{
    return qcow2_check_refcounts(bs);
}

#if 0
static void dump_refcounts(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    int64_t nb_clusters, k, k1, size;
    int refcount;

    size = bdrv_getlength(s->hd);
    nb_clusters = size_to_clusters(s, size);
    for(k = 0; k < nb_clusters;) {
        k1 = k;
        refcount = get_refcount(bs, k);
        k++;
        while (k < nb_clusters && get_refcount(bs, k) == refcount)
            k++;
        printf("%lld: refcount=%d nb=%lld\n", k, refcount, k - k1);
    }
}
#endif

static int qcow_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
                           int64_t pos, int size)
{
    BDRVQcowState *s = bs->opaque;
    int growable = bs->growable;

    bs->growable = 1;
    bdrv_pwrite(bs, qcow_vm_state_offset(s) + pos, buf, size);
    bs->growable = growable;

    return size;
}

static int qcow_load_vmstate(BlockDriverState *bs, uint8_t *buf,
                           int64_t pos, int size)
{
    BDRVQcowState *s = bs->opaque;
    int growable = bs->growable;
    int ret;

    bs->growable = 1;
    ret = bdrv_pread(bs, qcow_vm_state_offset(s) + pos, buf, size);
    bs->growable = growable;

    return ret;
}

static QEMUOptionParameter qcow_create_options[] = {
    {
        .name = BLOCK_OPT_SIZE,
        .type = OPT_SIZE,
        .help = "Virtual disk size"
    },
    {
        .name = BLOCK_OPT_BACKING_FILE,
        .type = OPT_STRING,
        .help = "File name of a base image"
    },
    {
        .name = BLOCK_OPT_BACKING_FMT,
        .type = OPT_STRING,
        .help = "Image format of the base image"
    },
    {
        .name = BLOCK_OPT_ENCRYPT,
        .type = OPT_FLAG,
        .help = "Encrypt the image"
    },
    {
        .name = BLOCK_OPT_CLUSTER_SIZE,
        .type = OPT_SIZE,
        .help = "qcow2 cluster size"
    },
    {
        .name = BLOCK_OPT_PREALLOC,
        .type = OPT_STRING,
        .help = "Preallocation mode (allowed values: off, metadata)"
    },
    { NULL }
};

static BlockDriver bdrv_qcow2 = {
    .format_name	= "qcow2",
    .instance_size	= sizeof(BDRVQcowState),
    .bdrv_probe		= qcow_probe,
    .bdrv_open		= qcow_open,
    .bdrv_close		= qcow_close,
    .bdrv_create	= qcow_create,
    .bdrv_flush		= qcow_flush,
    .bdrv_is_allocated	= qcow_is_allocated,
    .bdrv_set_key	= qcow_set_key,
    .bdrv_make_empty	= qcow_make_empty,

    .bdrv_aio_readv	= qcow_aio_readv,
    .bdrv_aio_writev	= qcow_aio_writev,
    .bdrv_write_compressed = qcow_write_compressed,

    .bdrv_snapshot_create   = qcow2_snapshot_create,
    .bdrv_snapshot_goto     = qcow2_snapshot_goto,
    .bdrv_snapshot_delete   = qcow2_snapshot_delete,
    .bdrv_snapshot_list     = qcow2_snapshot_list,
    .bdrv_get_info	= qcow_get_info,

    .bdrv_save_vmstate    = qcow_save_vmstate,
    .bdrv_load_vmstate    = qcow_load_vmstate,

    .bdrv_change_backing_file   = qcow2_change_backing_file,

    .create_options = qcow_create_options,
    .bdrv_check = qcow_check,
};

static void bdrv_qcow2_init(void)
{
    bdrv_register(&bdrv_qcow2);
}

block_init(bdrv_qcow2_init);