summaryrefslogtreecommitdiff
path: root/block-qcow2.c
blob: 9a49777ed15ccbd97d1b2d6948235d65336fe290 (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
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
/*
 * 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 <zlib.h>
#include "aes.h"
#include <assert.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.
*/

//#define DEBUG_ALLOC
//#define DEBUG_ALLOC2
//#define DEBUG_EXT

#define QCOW_MAGIC (('Q' << 24) | ('F' << 16) | ('I' << 8) | 0xfb)
#define QCOW_VERSION 2

#define QCOW_CRYPT_NONE 0
#define QCOW_CRYPT_AES  1

#define QCOW_MAX_CRYPT_CLUSTERS 32

/* indicate that the refcount of the referenced cluster is exactly one. */
#define QCOW_OFLAG_COPIED     (1LL << 63)
/* indicate that the cluster is compressed (they never have the copied flag) */
#define QCOW_OFLAG_COMPRESSED (1LL << 62)

#define REFCOUNT_SHIFT 1 /* refcount size is 2 bytes */

typedef struct QCowHeader {
    uint32_t magic;
    uint32_t version;
    uint64_t backing_file_offset;
    uint32_t backing_file_size;
    uint32_t cluster_bits;
    uint64_t size; /* in bytes */
    uint32_t crypt_method;
    uint32_t l1_size; /* XXX: save number of clusters instead ? */
    uint64_t l1_table_offset;
    uint64_t refcount_table_offset;
    uint32_t refcount_table_clusters;
    uint32_t nb_snapshots;
    uint64_t snapshots_offset;
} QCowHeader;


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


typedef struct __attribute__((packed)) QCowSnapshotHeader {
    /* header is 8 byte aligned */
    uint64_t l1_table_offset;

    uint32_t l1_size;
    uint16_t id_str_size;
    uint16_t name_size;

    uint32_t date_sec;
    uint32_t date_nsec;

    uint64_t vm_clock_nsec;

    uint32_t vm_state_size;
    uint32_t extra_data_size; /* for extension */
    /* extra data follows */
    /* id_str follows */
    /* name follows  */
} QCowSnapshotHeader;

#define L2_CACHE_SIZE 16

typedef struct QCowSnapshot {
    uint64_t l1_table_offset;
    uint32_t l1_size;
    char *id_str;
    char *name;
    uint32_t vm_state_size;
    uint32_t date_sec;
    uint32_t date_nsec;
    uint64_t vm_clock_nsec;
} QCowSnapshot;

typedef struct BDRVQcowState {
    BlockDriverState *hd;
    int cluster_bits;
    int cluster_size;
    int cluster_sectors;
    int l2_bits;
    int l2_size;
    int l1_size;
    int l1_vm_state_index;
    int csize_shift;
    int csize_mask;
    uint64_t cluster_offset_mask;
    uint64_t l1_table_offset;
    uint64_t *l1_table;
    uint64_t *l2_cache;
    uint64_t l2_cache_offsets[L2_CACHE_SIZE];
    uint32_t l2_cache_counts[L2_CACHE_SIZE];
    uint8_t *cluster_cache;
    uint8_t *cluster_data;
    uint64_t cluster_cache_offset;

    uint64_t *refcount_table;
    uint64_t refcount_table_offset;
    uint32_t refcount_table_size;
    uint64_t refcount_block_cache_offset;
    uint16_t *refcount_block_cache;
    int64_t free_cluster_index;
    int64_t free_byte_offset;

    uint32_t crypt_method; /* current crypt method, 0 if no key yet */
    uint32_t crypt_method_header;
    AES_KEY aes_encrypt_key;
    AES_KEY aes_decrypt_key;
    uint64_t snapshots_offset;
    int snapshots_size;
    int nb_snapshots;
    QCowSnapshot *snapshots;
} BDRVQcowState;

static int decompress_cluster(BDRVQcowState *s, uint64_t cluster_offset);
static int qcow_read(BlockDriverState *bs, int64_t sector_num,
                     uint8_t *buf, int nb_sectors);
static int qcow_read_snapshots(BlockDriverState *bs);
static void qcow_free_snapshots(BlockDriverState *bs);
static int refcount_init(BlockDriverState *bs);
static void refcount_close(BlockDriverState *bs);
static int get_refcount(BlockDriverState *bs, int64_t cluster_index);
static int update_cluster_refcount(BlockDriverState *bs,
                                   int64_t cluster_index,
                                   int addend);
static void update_refcount(BlockDriverState *bs,
                            int64_t offset, int64_t length,
                            int addend);
static int64_t alloc_clusters(BlockDriverState *bs, int64_t size);
static int64_t alloc_bytes(BlockDriverState *bs, int size);
static void free_clusters(BlockDriverState *bs,
                          int64_t offset, int64_t size);
static int check_refcounts(BlockDriverState *bs);

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 += ((ext.len + 7) & ~7);
            break;

        default:
            /* unknown magic -- just skip it */
            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;

    /* Performance is terrible right now with cache=writethrough due mainly
     * to reference count updates.  If the user does not explicitly specify
     * a caching type, force to writeback caching.
     */
    if ((flags & BDRV_O_CACHE_DEF)) {
        flags |= BDRV_O_CACHE_WB;
        flags &= ~BDRV_O_CACHE_DEF;
    }
    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.size <= 1 ||
        header.cluster_bits < 9 ||
        header.cluster_bits > 16)
        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;
    s->l1_table = qemu_malloc(s->l1_size * sizeof(uint64_t));
    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 (refcount_init(bs) < 0)
        goto fail;

    /* 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 (qcow_read_snapshots(bs) < 0)
        goto fail;

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

 fail:
    qcow_free_snapshots(bs);
    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;
}

/* The crypt function is compatible with the linux cryptoloop
   algorithm for < 4 GB images. NOTE: out_buf == in_buf is
   supported */
static void encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
                            uint8_t *out_buf, const uint8_t *in_buf,
                            int nb_sectors, int enc,
                            const AES_KEY *key)
{
    union {
        uint64_t ll[2];
        uint8_t b[16];
    } ivec;
    int i;

    for(i = 0; i < nb_sectors; i++) {
        ivec.ll[0] = cpu_to_le64(sector_num);
        ivec.ll[1] = 0;
        AES_cbc_encrypt(in_buf, out_buf, 512, key,
                        ivec.b, enc);
        sector_num++;
        in_buf += 512;
        out_buf += 512;
    }
}

static int copy_sectors(BlockDriverState *bs, uint64_t start_sect,
                        uint64_t cluster_offset, int n_start, int n_end)
{
    BDRVQcowState *s = bs->opaque;
    int n, ret;

    n = n_end - n_start;
    if (n <= 0)
        return 0;
    ret = qcow_read(bs, start_sect + n_start, s->cluster_data, n);
    if (ret < 0)
        return ret;
    if (s->crypt_method) {
        encrypt_sectors(s, start_sect + n_start,
                        s->cluster_data,
                        s->cluster_data, n, 1,
                        &s->aes_encrypt_key);
    }
    ret = bdrv_write(s->hd, (cluster_offset >> 9) + n_start,
                     s->cluster_data, n);
    if (ret < 0)
        return ret;
    return 0;
}

static void l2_cache_reset(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;

    memset(s->l2_cache, 0, s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
    memset(s->l2_cache_offsets, 0, L2_CACHE_SIZE * sizeof(uint64_t));
    memset(s->l2_cache_counts, 0, L2_CACHE_SIZE * sizeof(uint32_t));
}

static inline int l2_cache_new_entry(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    uint32_t min_count;
    int min_index, i;

    /* find a new entry in the least used one */
    min_index = 0;
    min_count = 0xffffffff;
    for(i = 0; i < L2_CACHE_SIZE; i++) {
        if (s->l2_cache_counts[i] < min_count) {
            min_count = s->l2_cache_counts[i];
            min_index = i;
        }
    }
    return min_index;
}

static int64_t align_offset(int64_t offset, int n)
{
    offset = (offset + n - 1) & ~(n - 1);
    return offset;
}

static int grow_l1_table(BlockDriverState *bs, int min_size)
{
    BDRVQcowState *s = bs->opaque;
    int new_l1_size, new_l1_size2, ret, i;
    uint64_t *new_l1_table;
    uint64_t new_l1_table_offset;
    uint8_t data[12];

    new_l1_size = s->l1_size;
    if (min_size <= new_l1_size)
        return 0;
    while (min_size > new_l1_size) {
        new_l1_size = (new_l1_size * 3 + 1) / 2;
    }
#ifdef DEBUG_ALLOC2
    printf("grow l1_table from %d to %d\n", s->l1_size, new_l1_size);
#endif

    new_l1_size2 = sizeof(uint64_t) * new_l1_size;
    new_l1_table = qemu_mallocz(new_l1_size2);
    memcpy(new_l1_table, s->l1_table, s->l1_size * sizeof(uint64_t));

    /* write new table (align to cluster) */
    new_l1_table_offset = alloc_clusters(bs, new_l1_size2);

    for(i = 0; i < s->l1_size; i++)
        new_l1_table[i] = cpu_to_be64(new_l1_table[i]);
    ret = bdrv_pwrite(s->hd, new_l1_table_offset, new_l1_table, new_l1_size2);
    if (ret != new_l1_size2)
        goto fail;
    for(i = 0; i < s->l1_size; i++)
        new_l1_table[i] = be64_to_cpu(new_l1_table[i]);

    /* set new table */
    cpu_to_be32w((uint32_t*)data, new_l1_size);
    cpu_to_be64w((uint64_t*)(data + 4), new_l1_table_offset);
    if (bdrv_pwrite(s->hd, offsetof(QCowHeader, l1_size), data,
                sizeof(data)) != sizeof(data))
        goto fail;
    qemu_free(s->l1_table);
    free_clusters(bs, s->l1_table_offset, s->l1_size * sizeof(uint64_t));
    s->l1_table_offset = new_l1_table_offset;
    s->l1_table = new_l1_table;
    s->l1_size = new_l1_size;
    return 0;
 fail:
    qemu_free(s->l1_table);
    return -EIO;
}

/*
 * seek_l2_table
 *
 * seek l2_offset in the l2_cache table
 * if not found, return NULL,
 * if found,
 *   increments the l2 cache hit count of the entry,
 *   if counter overflow, divide by two all counters
 *   return the pointer to the l2 cache entry
 *
 */

static uint64_t *seek_l2_table(BDRVQcowState *s, uint64_t l2_offset)
{
    int i, j;

    for(i = 0; i < L2_CACHE_SIZE; i++) {
        if (l2_offset == s->l2_cache_offsets[i]) {
            /* increment the hit count */
            if (++s->l2_cache_counts[i] == 0xffffffff) {
                for(j = 0; j < L2_CACHE_SIZE; j++) {
                    s->l2_cache_counts[j] >>= 1;
                }
            }
            return s->l2_cache + (i << s->l2_bits);
        }
    }
    return NULL;
}

/*
 * l2_load
 *
 * Loads a L2 table into memory. If the table is in the cache, the cache
 * is used; otherwise the L2 table is loaded from the image file.
 *
 * Returns a pointer to the L2 table on success, or NULL if the read from
 * the image file failed.
 */

static uint64_t *l2_load(BlockDriverState *bs, uint64_t l2_offset)
{
    BDRVQcowState *s = bs->opaque;
    int min_index;
    uint64_t *l2_table;

    /* seek if the table for the given offset is in the cache */

    l2_table = seek_l2_table(s, l2_offset);
    if (l2_table != NULL)
        return l2_table;

    /* not found: load a new entry in the least used one */

    min_index = l2_cache_new_entry(bs);
    l2_table = s->l2_cache + (min_index << s->l2_bits);
    if (bdrv_pread(s->hd, l2_offset, l2_table, s->l2_size * sizeof(uint64_t)) !=
        s->l2_size * sizeof(uint64_t))
        return NULL;
    s->l2_cache_offsets[min_index] = l2_offset;
    s->l2_cache_counts[min_index] = 1;

    return l2_table;
}

/*
 * l2_allocate
 *
 * Allocate a new l2 entry in the file. If l1_index points to an already
 * used entry in the L2 table (i.e. we are doing a copy on write for the L2
 * table) copy the contents of the old L2 table into the newly allocated one.
 * Otherwise the new table is initialized with zeros.
 *
 */

static uint64_t *l2_allocate(BlockDriverState *bs, int l1_index)
{
    BDRVQcowState *s = bs->opaque;
    int min_index;
    uint64_t old_l2_offset, tmp;
    uint64_t *l2_table, l2_offset;

    old_l2_offset = s->l1_table[l1_index];

    /* allocate a new l2 entry */

    l2_offset = alloc_clusters(bs, s->l2_size * sizeof(uint64_t));

    /* update the L1 entry */

    s->l1_table[l1_index] = l2_offset | QCOW_OFLAG_COPIED;

    tmp = cpu_to_be64(l2_offset | QCOW_OFLAG_COPIED);
    if (bdrv_pwrite(s->hd, s->l1_table_offset + l1_index * sizeof(tmp),
                    &tmp, sizeof(tmp)) != sizeof(tmp))
        return NULL;

    /* allocate a new entry in the l2 cache */

    min_index = l2_cache_new_entry(bs);
    l2_table = s->l2_cache + (min_index << s->l2_bits);

    if (old_l2_offset == 0) {
        /* if there was no old l2 table, clear the new table */
        memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
    } else {
        /* if there was an old l2 table, read it from the disk */
        if (bdrv_pread(s->hd, old_l2_offset,
                       l2_table, s->l2_size * sizeof(uint64_t)) !=
            s->l2_size * sizeof(uint64_t))
            return NULL;
    }
    /* write the l2 table to the file */
    if (bdrv_pwrite(s->hd, l2_offset,
                    l2_table, s->l2_size * sizeof(uint64_t)) !=
        s->l2_size * sizeof(uint64_t))
        return NULL;

    /* update the l2 cache entry */

    s->l2_cache_offsets[min_index] = l2_offset;
    s->l2_cache_counts[min_index] = 1;

    return l2_table;
}

static int size_to_clusters(BDRVQcowState *s, int64_t size)
{
    return (size + (s->cluster_size - 1)) >> s->cluster_bits;
}

static int count_contiguous_clusters(uint64_t nb_clusters, int cluster_size,
        uint64_t *l2_table, uint64_t start, uint64_t mask)
{
    int i;
    uint64_t offset = be64_to_cpu(l2_table[0]) & ~mask;

    if (!offset)
        return 0;

    for (i = start; i < start + nb_clusters; i++)
        if (offset + i * cluster_size != (be64_to_cpu(l2_table[i]) & ~mask))
            break;

	return (i - start);
}

static int count_contiguous_free_clusters(uint64_t nb_clusters, uint64_t *l2_table)
{
    int i = 0;

    while(nb_clusters-- && l2_table[i] == 0)
        i++;

    return i;
}

/*
 * get_cluster_offset
 *
 * For a given offset of the disk image, return cluster offset in
 * qcow2 file.
 *
 * on entry, *num is the number of contiguous clusters we'd like to
 * access following offset.
 *
 * on exit, *num is the number of contiguous clusters we can read.
 *
 * Return 1, if the offset is found
 * Return 0, otherwise.
 *
 */

static uint64_t get_cluster_offset(BlockDriverState *bs,
                                   uint64_t offset, int *num)
{
    BDRVQcowState *s = bs->opaque;
    int l1_index, l2_index;
    uint64_t l2_offset, *l2_table, cluster_offset;
    int l1_bits, c;
    int index_in_cluster, nb_available, nb_needed, nb_clusters;

    index_in_cluster = (offset >> 9) & (s->cluster_sectors - 1);
    nb_needed = *num + index_in_cluster;

    l1_bits = s->l2_bits + s->cluster_bits;

    /* compute how many bytes there are between the offset and
     * the end of the l1 entry
     */

    nb_available = (1 << l1_bits) - (offset & ((1 << l1_bits) - 1));

    /* compute the number of available sectors */

    nb_available = (nb_available >> 9) + index_in_cluster;

    if (nb_needed > nb_available) {
        nb_needed = nb_available;
    }

    cluster_offset = 0;

    /* seek the the l2 offset in the l1 table */

    l1_index = offset >> l1_bits;
    if (l1_index >= s->l1_size)
        goto out;

    l2_offset = s->l1_table[l1_index];

    /* seek the l2 table of the given l2 offset */

    if (!l2_offset)
        goto out;

    /* load the l2 table in memory */

    l2_offset &= ~QCOW_OFLAG_COPIED;
    l2_table = l2_load(bs, l2_offset);
    if (l2_table == NULL)
        return 0;

    /* find the cluster offset for the given disk offset */

    l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
    cluster_offset = be64_to_cpu(l2_table[l2_index]);
    nb_clusters = size_to_clusters(s, nb_needed << 9);

    if (!cluster_offset) {
        /* how many empty clusters ? */
        c = count_contiguous_free_clusters(nb_clusters, &l2_table[l2_index]);
    } else {
        /* how many allocated clusters ? */
        c = count_contiguous_clusters(nb_clusters, s->cluster_size,
                &l2_table[l2_index], 0, QCOW_OFLAG_COPIED);
    }

   nb_available = (c * s->cluster_sectors);
out:
    if (nb_available > nb_needed)
        nb_available = nb_needed;

    *num = nb_available - index_in_cluster;

    return cluster_offset & ~QCOW_OFLAG_COPIED;
}

/*
 * free_any_clusters
 *
 * free clusters according to its type: compressed or not
 *
 */

static void free_any_clusters(BlockDriverState *bs,
                              uint64_t cluster_offset, int nb_clusters)
{
    BDRVQcowState *s = bs->opaque;

    /* free the cluster */

    if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
        int nb_csectors;
        nb_csectors = ((cluster_offset >> s->csize_shift) &
                       s->csize_mask) + 1;
        free_clusters(bs, (cluster_offset & s->cluster_offset_mask) & ~511,
                      nb_csectors * 512);
        return;
    }

    free_clusters(bs, cluster_offset, nb_clusters << s->cluster_bits);

    return;
}

/*
 * get_cluster_table
 *
 * for a given disk offset, load (and allocate if needed)
 * the l2 table.
 *
 * the l2 table offset in the qcow2 file and the cluster index
 * in the l2 table are given to the caller.
 *
 */

static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
                             uint64_t **new_l2_table,
                             uint64_t *new_l2_offset,
                             int *new_l2_index)
{
    BDRVQcowState *s = bs->opaque;
    int l1_index, l2_index, ret;
    uint64_t l2_offset, *l2_table;

    /* seek the the l2 offset in the l1 table */

    l1_index = offset >> (s->l2_bits + s->cluster_bits);
    if (l1_index >= s->l1_size) {
        ret = grow_l1_table(bs, l1_index + 1);
        if (ret < 0)
            return 0;
    }
    l2_offset = s->l1_table[l1_index];

    /* seek the l2 table of the given l2 offset */

    if (l2_offset & QCOW_OFLAG_COPIED) {
        /* load the l2 table in memory */
        l2_offset &= ~QCOW_OFLAG_COPIED;
        l2_table = l2_load(bs, l2_offset);
        if (l2_table == NULL)
            return 0;
    } else {
        if (l2_offset)
            free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t));
        l2_table = l2_allocate(bs, l1_index);
        if (l2_table == NULL)
            return 0;
        l2_offset = s->l1_table[l1_index] & ~QCOW_OFLAG_COPIED;
    }

    /* find the cluster offset for the given disk offset */

    l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);

    *new_l2_table = l2_table;
    *new_l2_offset = l2_offset;
    *new_l2_index = l2_index;

    return 1;
}

/*
 * alloc_compressed_cluster_offset
 *
 * For a given offset of the disk image, return cluster offset in
 * qcow2 file.
 *
 * If the offset is not found, allocate a new compressed cluster.
 *
 * Return the cluster offset if successful,
 * Return 0, otherwise.
 *
 */

static uint64_t alloc_compressed_cluster_offset(BlockDriverState *bs,
                                                uint64_t offset,
                                                int compressed_size)
{
    BDRVQcowState *s = bs->opaque;
    int l2_index, ret;
    uint64_t l2_offset, *l2_table, cluster_offset;
    int nb_csectors;

    ret = get_cluster_table(bs, offset, &l2_table, &l2_offset, &l2_index);
    if (ret == 0)
        return 0;

    cluster_offset = be64_to_cpu(l2_table[l2_index]);
    if (cluster_offset & QCOW_OFLAG_COPIED)
        return cluster_offset & ~QCOW_OFLAG_COPIED;

    if (cluster_offset)
        free_any_clusters(bs, cluster_offset, 1);

    cluster_offset = alloc_bytes(bs, compressed_size);
    nb_csectors = ((cluster_offset + compressed_size - 1) >> 9) -
                  (cluster_offset >> 9);

    cluster_offset |= QCOW_OFLAG_COMPRESSED |
                      ((uint64_t)nb_csectors << s->csize_shift);

    /* update L2 table */

    /* compressed clusters never have the copied flag */

    l2_table[l2_index] = cpu_to_be64(cluster_offset);
    if (bdrv_pwrite(s->hd,
                    l2_offset + l2_index * sizeof(uint64_t),
                    l2_table + l2_index,
                    sizeof(uint64_t)) != sizeof(uint64_t))
        return 0;

    return cluster_offset;
}

typedef struct QCowL2Meta
{
    uint64_t offset;
    int n_start;
    int nb_available;
    int nb_clusters;
} QCowL2Meta;

static int alloc_cluster_link_l2(BlockDriverState *bs, uint64_t cluster_offset,
        QCowL2Meta *m)
{
    BDRVQcowState *s = bs->opaque;
    int i, j = 0, l2_index, ret;
    uint64_t *old_cluster, start_sect, l2_offset, *l2_table;

    if (m->nb_clusters == 0)
        return 0;

    old_cluster = qemu_malloc(m->nb_clusters * sizeof(uint64_t));

    /* copy content of unmodified sectors */
    start_sect = (m->offset & ~(s->cluster_size - 1)) >> 9;
    if (m->n_start) {
        ret = copy_sectors(bs, start_sect, cluster_offset, 0, m->n_start);
        if (ret < 0)
            goto err;
    }

    if (m->nb_available & (s->cluster_sectors - 1)) {
        uint64_t end = m->nb_available & ~(uint64_t)(s->cluster_sectors - 1);
        ret = copy_sectors(bs, start_sect + end, cluster_offset + (end << 9),
                m->nb_available - end, s->cluster_sectors);
        if (ret < 0)
            goto err;
    }

    ret = -EIO;
    /* update L2 table */
    if (!get_cluster_table(bs, m->offset, &l2_table, &l2_offset, &l2_index))
        goto err;

    for (i = 0; i < m->nb_clusters; i++) {
        /* if two concurrent writes happen to the same unallocated cluster
	 * each write allocates separate cluster and writes data concurrently.
	 * The first one to complete updates l2 table with pointer to its
	 * cluster the second one has to do RMW (which is done above by
	 * copy_sectors()), update l2 table with its cluster pointer and free
	 * old cluster. This is what this loop does */
        if(l2_table[l2_index + i] != 0)
            old_cluster[j++] = l2_table[l2_index + i];

        l2_table[l2_index + i] = cpu_to_be64((cluster_offset +
                    (i << s->cluster_bits)) | QCOW_OFLAG_COPIED);
     }

    if (bdrv_pwrite(s->hd, l2_offset + l2_index * sizeof(uint64_t),
                l2_table + l2_index, m->nb_clusters * sizeof(uint64_t)) !=
            m->nb_clusters * sizeof(uint64_t))
        goto err;

    for (i = 0; i < j; i++)
        free_any_clusters(bs, be64_to_cpu(old_cluster[i]) & ~QCOW_OFLAG_COPIED,
                          1);

    ret = 0;
err:
    qemu_free(old_cluster);
    return ret;
 }

/*
 * alloc_cluster_offset
 *
 * For a given offset of the disk image, return cluster offset in
 * qcow2 file.
 *
 * If the offset is not found, allocate a new cluster.
 *
 * Return the cluster offset if successful,
 * Return 0, otherwise.
 *
 */

static uint64_t alloc_cluster_offset(BlockDriverState *bs,
                                     uint64_t offset,
                                     int n_start, int n_end,
                                     int *num, QCowL2Meta *m)
{
    BDRVQcowState *s = bs->opaque;
    int l2_index, ret;
    uint64_t l2_offset, *l2_table, cluster_offset;
    int nb_clusters, i = 0;

    ret = get_cluster_table(bs, offset, &l2_table, &l2_offset, &l2_index);
    if (ret == 0)
        return 0;

    nb_clusters = size_to_clusters(s, n_end << 9);

    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);

    cluster_offset = be64_to_cpu(l2_table[l2_index]);

    /* We keep all QCOW_OFLAG_COPIED clusters */

    if (cluster_offset & QCOW_OFLAG_COPIED) {
        nb_clusters = count_contiguous_clusters(nb_clusters, s->cluster_size,
                &l2_table[l2_index], 0, 0);

        cluster_offset &= ~QCOW_OFLAG_COPIED;
        m->nb_clusters = 0;

        goto out;
    }

    /* for the moment, multiple compressed clusters are not managed */

    if (cluster_offset & QCOW_OFLAG_COMPRESSED)
        nb_clusters = 1;

    /* how many available clusters ? */

    while (i < nb_clusters) {
        i += count_contiguous_clusters(nb_clusters - i, s->cluster_size,
                &l2_table[l2_index], i, 0);

        if(be64_to_cpu(l2_table[l2_index + i]))
            break;

        i += count_contiguous_free_clusters(nb_clusters - i,
                &l2_table[l2_index + i]);

        cluster_offset = be64_to_cpu(l2_table[l2_index + i]);

        if ((cluster_offset & QCOW_OFLAG_COPIED) ||
                (cluster_offset & QCOW_OFLAG_COMPRESSED))
            break;
    }
    nb_clusters = i;

    /* allocate a new cluster */

    cluster_offset = alloc_clusters(bs, nb_clusters * s->cluster_size);

    /* save info needed for meta data update */
    m->offset = offset;
    m->n_start = n_start;
    m->nb_clusters = nb_clusters;

out:
    m->nb_available = MIN(nb_clusters << (s->cluster_bits - 9), n_end);

    *num = m->nb_available - n_start;

    return cluster_offset;
}

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 = get_cluster_offset(bs, sector_num << 9, pnum);

    return (cluster_offset != 0);
}

static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
                             const uint8_t *buf, int buf_size)
{
    z_stream strm1, *strm = &strm1;
    int ret, out_len;

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

    strm->next_in = (uint8_t *)buf;
    strm->avail_in = buf_size;
    strm->next_out = out_buf;
    strm->avail_out = out_buf_size;

    ret = inflateInit2(strm, -12);
    if (ret != Z_OK)
        return -1;
    ret = inflate(strm, Z_FINISH);
    out_len = strm->next_out - out_buf;
    if ((ret != Z_STREAM_END && ret != Z_BUF_ERROR) ||
        out_len != out_buf_size) {
        inflateEnd(strm);
        return -1;
    }
    inflateEnd(strm);
    return 0;
}

static int decompress_cluster(BDRVQcowState *s, uint64_t cluster_offset)
{
    int ret, csize, nb_csectors, sector_offset;
    uint64_t coffset;

    coffset = cluster_offset & s->cluster_offset_mask;
    if (s->cluster_cache_offset != coffset) {
        nb_csectors = ((cluster_offset >> s->csize_shift) & s->csize_mask) + 1;
        sector_offset = coffset & 511;
        csize = nb_csectors * 512 - sector_offset;
        ret = bdrv_read(s->hd, coffset >> 9, s->cluster_data, nb_csectors);
        if (ret < 0) {
            return -1;
        }
        if (decompress_buffer(s->cluster_cache, s->cluster_size,
                              s->cluster_data + sector_offset, csize) < 0) {
            return -1;
        }
        s->cluster_cache_offset = coffset;
    }
    return 0;
}

/* handle reading after the end of the backing file */
static int 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;
}

static int qcow_read(BlockDriverState *bs, int64_t sector_num,
                     uint8_t *buf, int nb_sectors)
{
    BDRVQcowState *s = bs->opaque;
    int ret, index_in_cluster, n, n1;
    uint64_t cluster_offset;

    while (nb_sectors > 0) {
        n = nb_sectors;
        cluster_offset = get_cluster_offset(bs, sector_num << 9, &n);
        index_in_cluster = sector_num & (s->cluster_sectors - 1);
        if (!cluster_offset) {
            if (bs->backing_hd) {
                /* read from the base image */
                n1 = backing_read1(bs->backing_hd, sector_num, buf, n);
                if (n1 > 0) {
                    ret = bdrv_read(bs->backing_hd, sector_num, buf, n1);
                    if (ret < 0)
                        return -1;
                }
            } else {
                memset(buf, 0, 512 * n);
            }
        } else if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
            if (decompress_cluster(s, cluster_offset) < 0)
                return -1;
            memcpy(buf, s->cluster_cache + index_in_cluster * 512, 512 * n);
        } else {
            ret = bdrv_pread(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512);
            if (ret != n * 512)
                return -1;
            if (s->crypt_method) {
                encrypt_sectors(s, sector_num, buf, buf, n, 0,
                                &s->aes_decrypt_key);
            }
        }
        nb_sectors -= n;
        sector_num += n;
        buf += n * 512;
    }
    return 0;
}

static int qcow_write(BlockDriverState *bs, int64_t sector_num,
                     const uint8_t *buf, int nb_sectors)
{
    BDRVQcowState *s = bs->opaque;
    int ret, index_in_cluster, n;
    uint64_t cluster_offset;
    int n_end;
    QCowL2Meta l2meta;

    while (nb_sectors > 0) {
        index_in_cluster = sector_num & (s->cluster_sectors - 1);
        n_end = index_in_cluster + nb_sectors;
        if (s->crypt_method &&
            n_end > QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors)
            n_end = QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors;
        cluster_offset = alloc_cluster_offset(bs, sector_num << 9,
                                              index_in_cluster,
                                              n_end, &n, &l2meta);
        if (!cluster_offset)
            return -1;
        if (s->crypt_method) {
            encrypt_sectors(s, sector_num, s->cluster_data, buf, n, 1,
                            &s->aes_encrypt_key);
            ret = bdrv_pwrite(s->hd, cluster_offset + index_in_cluster * 512,
                              s->cluster_data, n * 512);
        } else {
            ret = bdrv_pwrite(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512);
        }
        if (ret != n * 512 || alloc_cluster_link_l2(bs, cluster_offset, &l2meta) < 0) {
            free_any_clusters(bs, cluster_offset, l2meta.nb_clusters);
            return -1;
        }
        nb_sectors -= n;
        sector_num += n;
        buf += n * 512;
    }
    s->cluster_cache_offset = -1; /* disable compressed cache */
    return 0;
}

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;
} QCowAIOCB;

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) {
            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 = 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 = 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 (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(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;
    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)
{
    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)
        goto done;

    if (alloc_cluster_link_l2(bs, acb->cluster_offset, &acb->l2meta) < 0) {
        free_any_clusters(bs, acb->cluster_offset, acb->l2meta.nb_clusters);
        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 = alloc_cluster_offset(bs, acb->sector_num << 9,
                                          index_in_cluster,
                                          n_end, &acb->n, &acb->l2meta);
    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);
        }
        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_aio_cancel(BlockDriverAIOCB *blockacb)
{
    QCowAIOCB *acb = (QCowAIOCB *)blockacb;
    if (acb->hd_aiocb)
        bdrv_aio_cancel(acb->hd_aiocb);
    qemu_aio_release(acb);
}

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);
    refcount_close(bs);
    bdrv_delete(s->hd);
}

/* XXX: use std qcow open function ? */
typedef struct QCowCreateState {
    int cluster_size;
    int cluster_bits;
    uint16_t *refcount_block;
    uint64_t *refcount_table;
    int64_t l1_table_offset;
    int64_t refcount_table_offset;
    int64_t refcount_block_offset;
} QCowCreateState;

static void create_refcount_update(QCowCreateState *s,
                                   int64_t offset, int64_t size)
{
    int refcount;
    int64_t start, last, cluster_offset;
    uint16_t *p;

    start = offset & ~(s->cluster_size - 1);
    last = (offset + size - 1)  & ~(s->cluster_size - 1);
    for(cluster_offset = start; cluster_offset <= last;
        cluster_offset += s->cluster_size) {
        p = &s->refcount_block[cluster_offset >> s->cluster_bits];
        refcount = be16_to_cpu(*p);
        refcount++;
        *p = cpu_to_be16(refcount);
    }
}

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

    int fd, header_size, backing_filename_len, l1_size, i, shift, l2_bits;
    int ref_clusters, backing_format_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 + 7) & ~7;
            header_size += ((sizeof(ext_bf) + ext_bf.len + 7) & ~7);
        }
        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;
    }
    s->cluster_bits = 12;  /* 4 KB clusters */
    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 */
    create_refcount_update(s, 0, header_size);
    create_refcount_update(s, s->l1_table_offset, l1_size * sizeof(uint64_t));
    create_refcount_update(s, s->refcount_table_offset, s->cluster_size);
    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 d = ext_bf.len - backing_format_len;

            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 (d>0) {
                write(fd, zero, d);
            }
        }
        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);
    return 0;
}

static int qcow_create(const char *filename, int64_t total_size,
                       const char *backing_file, int flags)
{
    return qcow_create2(filename, total_size, backing_file, NULL, flags);
}

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 */
        qcow_write(bs, sector_num, buf, s->cluster_sectors);
    } else {
        cluster_offset = 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 int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
    BDRVQcowState *s = bs->opaque;
    bdi->cluster_size = s->cluster_size;
    bdi->vm_state_offset = (int64_t)s->l1_vm_state_index <<
        (s->cluster_bits + s->l2_bits);
    return 0;
}

/*********************************************************/
/* snapshot support */

/* update the refcounts of snapshots and the copied flag */
static int update_snapshot_refcount(BlockDriverState *bs,
                                    int64_t l1_table_offset,
                                    int l1_size,
                                    int addend)
{
    BDRVQcowState *s = bs->opaque;
    uint64_t *l1_table, *l2_table, l2_offset, offset, l1_size2, l1_allocated;
    int64_t old_offset, old_l2_offset;
    int l2_size, i, j, l1_modified, l2_modified, nb_csectors, refcount;

    l2_cache_reset(bs);

    l2_table = NULL;
    l1_table = NULL;
    l1_size2 = l1_size * sizeof(uint64_t);
    l1_allocated = 0;
    if (l1_table_offset != s->l1_table_offset) {
        l1_table = qemu_malloc(l1_size2);
        l1_allocated = 1;
        if (bdrv_pread(s->hd, l1_table_offset,
                       l1_table, l1_size2) != l1_size2)
            goto fail;
        for(i = 0;i < l1_size; i++)
            be64_to_cpus(&l1_table[i]);
    } else {
        assert(l1_size == s->l1_size);
        l1_table = s->l1_table;
        l1_allocated = 0;
    }

    l2_size = s->l2_size * sizeof(uint64_t);
    l2_table = qemu_malloc(l2_size);
    l1_modified = 0;
    for(i = 0; i < l1_size; i++) {
        l2_offset = l1_table[i];
        if (l2_offset) {
            old_l2_offset = l2_offset;
            l2_offset &= ~QCOW_OFLAG_COPIED;
            l2_modified = 0;
            if (bdrv_pread(s->hd, l2_offset, l2_table, l2_size) != l2_size)
                goto fail;
            for(j = 0; j < s->l2_size; j++) {
                offset = be64_to_cpu(l2_table[j]);
                if (offset != 0) {
                    old_offset = offset;
                    offset &= ~QCOW_OFLAG_COPIED;
                    if (offset & QCOW_OFLAG_COMPRESSED) {
                        nb_csectors = ((offset >> s->csize_shift) &
                                       s->csize_mask) + 1;
                        if (addend != 0)
                            update_refcount(bs, (offset & s->cluster_offset_mask) & ~511,
                                            nb_csectors * 512, addend);
                        /* compressed clusters are never modified */
                        refcount = 2;
                    } else {
                        if (addend != 0) {
                            refcount = update_cluster_refcount(bs, offset >> s->cluster_bits, addend);
                        } else {
                            refcount = get_refcount(bs, offset >> s->cluster_bits);
                        }
                    }

                    if (refcount == 1) {
                        offset |= QCOW_OFLAG_COPIED;
                    }
                    if (offset != old_offset) {
                        l2_table[j] = cpu_to_be64(offset);
                        l2_modified = 1;
                    }
                }
            }
            if (l2_modified) {
                if (bdrv_pwrite(s->hd,
                                l2_offset, l2_table, l2_size) != l2_size)
                    goto fail;
            }

            if (addend != 0) {
                refcount = update_cluster_refcount(bs, l2_offset >> s->cluster_bits, addend);
            } else {
                refcount = get_refcount(bs, l2_offset >> s->cluster_bits);
            }
            if (refcount == 1) {
                l2_offset |= QCOW_OFLAG_COPIED;
            }
            if (l2_offset != old_l2_offset) {
                l1_table[i] = l2_offset;
                l1_modified = 1;
            }
        }
    }
    if (l1_modified) {
        for(i = 0; i < l1_size; i++)
            cpu_to_be64s(&l1_table[i]);
        if (bdrv_pwrite(s->hd, l1_table_offset, l1_table,
                        l1_size2) != l1_size2)
            goto fail;
        for(i = 0; i < l1_size; i++)
            be64_to_cpus(&l1_table[i]);
    }
    if (l1_allocated)
        qemu_free(l1_table);
    qemu_free(l2_table);
    return 0;
 fail:
    if (l1_allocated)
        qemu_free(l1_table);
    qemu_free(l2_table);
    return -EIO;
}

static void qcow_free_snapshots(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    int i;

    for(i = 0; i < s->nb_snapshots; i++) {
        qemu_free(s->snapshots[i].name);
        qemu_free(s->snapshots[i].id_str);
    }
    qemu_free(s->snapshots);
    s->snapshots = NULL;
    s->nb_snapshots = 0;
}

static int qcow_read_snapshots(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    QCowSnapshotHeader h;
    QCowSnapshot *sn;
    int i, id_str_size, name_size;
    int64_t offset;
    uint32_t extra_data_size;

    if (!s->nb_snapshots) {
        s->snapshots = NULL;
        s->snapshots_size = 0;
        return 0;
    }

    offset = s->snapshots_offset;
    s->snapshots = qemu_mallocz(s->nb_snapshots * sizeof(QCowSnapshot));
    for(i = 0; i < s->nb_snapshots; i++) {
        offset = align_offset(offset, 8);
        if (bdrv_pread(s->hd, offset, &h, sizeof(h)) != sizeof(h))
            goto fail;
        offset += sizeof(h);
        sn = s->snapshots + i;
        sn->l1_table_offset = be64_to_cpu(h.l1_table_offset);
        sn->l1_size = be32_to_cpu(h.l1_size);
        sn->vm_state_size = be32_to_cpu(h.vm_state_size);
        sn->date_sec = be32_to_cpu(h.date_sec);
        sn->date_nsec = be32_to_cpu(h.date_nsec);
        sn->vm_clock_nsec = be64_to_cpu(h.vm_clock_nsec);
        extra_data_size = be32_to_cpu(h.extra_data_size);

        id_str_size = be16_to_cpu(h.id_str_size);
        name_size = be16_to_cpu(h.name_size);

        offset += extra_data_size;

        sn->id_str = qemu_malloc(id_str_size + 1);
        if (bdrv_pread(s->hd, offset, sn->id_str, id_str_size) != id_str_size)
            goto fail;
        offset += id_str_size;
        sn->id_str[id_str_size] = '\0';

        sn->name = qemu_malloc(name_size + 1);
        if (bdrv_pread(s->hd, offset, sn->name, name_size) != name_size)
            goto fail;
        offset += name_size;
        sn->name[name_size] = '\0';
    }
    s->snapshots_size = offset - s->snapshots_offset;
    return 0;
 fail:
    qcow_free_snapshots(bs);
    return -1;
}

/* add at the end of the file a new list of snapshots */
static int qcow_write_snapshots(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *sn;
    QCowSnapshotHeader h;
    int i, name_size, id_str_size, snapshots_size;
    uint64_t data64;
    uint32_t data32;
    int64_t offset, snapshots_offset;

    /* compute the size of the snapshots */
    offset = 0;
    for(i = 0; i < s->nb_snapshots; i++) {
        sn = s->snapshots + i;
        offset = align_offset(offset, 8);
        offset += sizeof(h);
        offset += strlen(sn->id_str);
        offset += strlen(sn->name);
    }
    snapshots_size = offset;

    snapshots_offset = alloc_clusters(bs, snapshots_size);
    offset = snapshots_offset;

    for(i = 0; i < s->nb_snapshots; i++) {
        sn = s->snapshots + i;
        memset(&h, 0, sizeof(h));
        h.l1_table_offset = cpu_to_be64(sn->l1_table_offset);
        h.l1_size = cpu_to_be32(sn->l1_size);
        h.vm_state_size = cpu_to_be32(sn->vm_state_size);
        h.date_sec = cpu_to_be32(sn->date_sec);
        h.date_nsec = cpu_to_be32(sn->date_nsec);
        h.vm_clock_nsec = cpu_to_be64(sn->vm_clock_nsec);

        id_str_size = strlen(sn->id_str);
        name_size = strlen(sn->name);
        h.id_str_size = cpu_to_be16(id_str_size);
        h.name_size = cpu_to_be16(name_size);
        offset = align_offset(offset, 8);
        if (bdrv_pwrite(s->hd, offset, &h, sizeof(h)) != sizeof(h))
            goto fail;
        offset += sizeof(h);
        if (bdrv_pwrite(s->hd, offset, sn->id_str, id_str_size) != id_str_size)
            goto fail;
        offset += id_str_size;
        if (bdrv_pwrite(s->hd, offset, sn->name, name_size) != name_size)
            goto fail;
        offset += name_size;
    }

    /* update the various header fields */
    data64 = cpu_to_be64(snapshots_offset);
    if (bdrv_pwrite(s->hd, offsetof(QCowHeader, snapshots_offset),
                    &data64, sizeof(data64)) != sizeof(data64))
        goto fail;
    data32 = cpu_to_be32(s->nb_snapshots);
    if (bdrv_pwrite(s->hd, offsetof(QCowHeader, nb_snapshots),
                    &data32, sizeof(data32)) != sizeof(data32))
        goto fail;

    /* free the old snapshot table */
    free_clusters(bs, s->snapshots_offset, s->snapshots_size);
    s->snapshots_offset = snapshots_offset;
    s->snapshots_size = snapshots_size;
    return 0;
 fail:
    return -1;
}

static void find_new_snapshot_id(BlockDriverState *bs,
                                 char *id_str, int id_str_size)
{
    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *sn;
    int i, id, id_max = 0;

    for(i = 0; i < s->nb_snapshots; i++) {
        sn = s->snapshots + i;
        id = strtoul(sn->id_str, NULL, 10);
        if (id > id_max)
            id_max = id;
    }
    snprintf(id_str, id_str_size, "%d", id_max + 1);
}

static int find_snapshot_by_id(BlockDriverState *bs, const char *id_str)
{
    BDRVQcowState *s = bs->opaque;
    int i;

    for(i = 0; i < s->nb_snapshots; i++) {
        if (!strcmp(s->snapshots[i].id_str, id_str))
            return i;
    }
    return -1;
}

static int find_snapshot_by_id_or_name(BlockDriverState *bs, const char *name)
{
    BDRVQcowState *s = bs->opaque;
    int i, ret;

    ret = find_snapshot_by_id(bs, name);
    if (ret >= 0)
        return ret;
    for(i = 0; i < s->nb_snapshots; i++) {
        if (!strcmp(s->snapshots[i].name, name))
            return i;
    }
    return -1;
}

/* if no id is provided, a new one is constructed */
static int qcow_snapshot_create(BlockDriverState *bs,
                                QEMUSnapshotInfo *sn_info)
{
    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *snapshots1, sn1, *sn = &sn1;
    int i, ret;
    uint64_t *l1_table = NULL;

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

    if (sn_info->id_str[0] == '\0') {
        /* compute a new id */
        find_new_snapshot_id(bs, sn_info->id_str, sizeof(sn_info->id_str));
    }

    /* check that the ID is unique */
    if (find_snapshot_by_id(bs, sn_info->id_str) >= 0)
        return -ENOENT;

    sn->id_str = qemu_strdup(sn_info->id_str);
    if (!sn->id_str)
        goto fail;
    sn->name = qemu_strdup(sn_info->name);
    if (!sn->name)
        goto fail;
    sn->vm_state_size = sn_info->vm_state_size;
    sn->date_sec = sn_info->date_sec;
    sn->date_nsec = sn_info->date_nsec;
    sn->vm_clock_nsec = sn_info->vm_clock_nsec;

    ret = update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1);
    if (ret < 0)
        goto fail;

    /* create the L1 table of the snapshot */
    sn->l1_table_offset = alloc_clusters(bs, s->l1_size * sizeof(uint64_t));
    sn->l1_size = s->l1_size;

    l1_table = qemu_malloc(s->l1_size * sizeof(uint64_t));
    for(i = 0; i < s->l1_size; i++) {
        l1_table[i] = cpu_to_be64(s->l1_table[i]);
    }
    if (bdrv_pwrite(s->hd, sn->l1_table_offset,
                    l1_table, s->l1_size * sizeof(uint64_t)) !=
        (s->l1_size * sizeof(uint64_t)))
        goto fail;
    qemu_free(l1_table);
    l1_table = NULL;

    snapshots1 = qemu_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
    if (s->snapshots) {
        memcpy(snapshots1, s->snapshots, s->nb_snapshots * sizeof(QCowSnapshot));
        qemu_free(s->snapshots);
    }
    s->snapshots = snapshots1;
    s->snapshots[s->nb_snapshots++] = *sn;

    if (qcow_write_snapshots(bs) < 0)
        goto fail;
#ifdef DEBUG_ALLOC
    check_refcounts(bs);
#endif
    return 0;
 fail:
    qemu_free(sn->name);
    qemu_free(l1_table);
    return -1;
}

/* copy the snapshot 'snapshot_name' into the current disk image */
static int qcow_snapshot_goto(BlockDriverState *bs,
                              const char *snapshot_id)
{
    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *sn;
    int i, snapshot_index, l1_size2;

    snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
    if (snapshot_index < 0)
        return -ENOENT;
    sn = &s->snapshots[snapshot_index];

    if (update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, -1) < 0)
        goto fail;

    if (grow_l1_table(bs, sn->l1_size) < 0)
        goto fail;

    s->l1_size = sn->l1_size;
    l1_size2 = s->l1_size * sizeof(uint64_t);
    /* copy the snapshot l1 table to the current l1 table */
    if (bdrv_pread(s->hd, sn->l1_table_offset,
                   s->l1_table, l1_size2) != l1_size2)
        goto fail;
    if (bdrv_pwrite(s->hd, s->l1_table_offset,
                    s->l1_table, l1_size2) != l1_size2)
        goto fail;
    for(i = 0;i < s->l1_size; i++) {
        be64_to_cpus(&s->l1_table[i]);
    }

    if (update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1) < 0)
        goto fail;

#ifdef DEBUG_ALLOC
    check_refcounts(bs);
#endif
    return 0;
 fail:
    return -EIO;
}

static int qcow_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
{
    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *sn;
    int snapshot_index, ret;

    snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
    if (snapshot_index < 0)
        return -ENOENT;
    sn = &s->snapshots[snapshot_index];

    ret = update_snapshot_refcount(bs, sn->l1_table_offset, sn->l1_size, -1);
    if (ret < 0)
        return ret;
    /* must update the copied flag on the current cluster offsets */
    ret = update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
    if (ret < 0)
        return ret;
    free_clusters(bs, sn->l1_table_offset, sn->l1_size * sizeof(uint64_t));

    qemu_free(sn->id_str);
    qemu_free(sn->name);
    memmove(sn, sn + 1, (s->nb_snapshots - snapshot_index - 1) * sizeof(*sn));
    s->nb_snapshots--;
    ret = qcow_write_snapshots(bs);
    if (ret < 0) {
        /* XXX: restore snapshot if error ? */
        return ret;
    }
#ifdef DEBUG_ALLOC
    check_refcounts(bs);
#endif
    return 0;
}

static int qcow_snapshot_list(BlockDriverState *bs,
                              QEMUSnapshotInfo **psn_tab)
{
    BDRVQcowState *s = bs->opaque;
    QEMUSnapshotInfo *sn_tab, *sn_info;
    QCowSnapshot *sn;
    int i;

    sn_tab = qemu_mallocz(s->nb_snapshots * sizeof(QEMUSnapshotInfo));
    for(i = 0; i < s->nb_snapshots; i++) {
        sn_info = sn_tab + i;
        sn = s->snapshots + i;
        pstrcpy(sn_info->id_str, sizeof(sn_info->id_str),
                sn->id_str);
        pstrcpy(sn_info->name, sizeof(sn_info->name),
                sn->name);
        sn_info->vm_state_size = sn->vm_state_size;
        sn_info->date_sec = sn->date_sec;
        sn_info->date_nsec = sn->date_nsec;
        sn_info->vm_clock_nsec = sn->vm_clock_nsec;
    }
    *psn_tab = sn_tab;
    return s->nb_snapshots;
}

/*********************************************************/
/* refcount handling */

static int refcount_init(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    int ret, refcount_table_size2, i;

    s->refcount_block_cache = qemu_malloc(s->cluster_size);
    refcount_table_size2 = s->refcount_table_size * sizeof(uint64_t);
    s->refcount_table = qemu_malloc(refcount_table_size2);
    if (s->refcount_table_size > 0) {
        ret = bdrv_pread(s->hd, s->refcount_table_offset,
                         s->refcount_table, refcount_table_size2);
        if (ret != refcount_table_size2)
            goto fail;
        for(i = 0; i < s->refcount_table_size; i++)
            be64_to_cpus(&s->refcount_table[i]);
    }
    return 0;
 fail:
    return -ENOMEM;
}

static void refcount_close(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    qemu_free(s->refcount_block_cache);
    qemu_free(s->refcount_table);
}


static int load_refcount_block(BlockDriverState *bs,
                               int64_t refcount_block_offset)
{
    BDRVQcowState *s = bs->opaque;
    int ret;
    ret = bdrv_pread(s->hd, refcount_block_offset, s->refcount_block_cache,
                     s->cluster_size);
    if (ret != s->cluster_size)
        return -EIO;
    s->refcount_block_cache_offset = refcount_block_offset;
    return 0;
}

static int get_refcount(BlockDriverState *bs, int64_t cluster_index)
{
    BDRVQcowState *s = bs->opaque;
    int refcount_table_index, block_index;
    int64_t refcount_block_offset;

    refcount_table_index = cluster_index >> (s->cluster_bits - REFCOUNT_SHIFT);
    if (refcount_table_index >= s->refcount_table_size)
        return 0;
    refcount_block_offset = s->refcount_table[refcount_table_index];
    if (!refcount_block_offset)
        return 0;
    if (refcount_block_offset != s->refcount_block_cache_offset) {
        /* better than nothing: return allocated if read error */
        if (load_refcount_block(bs, refcount_block_offset) < 0)
            return 1;
    }
    block_index = cluster_index &
        ((1 << (s->cluster_bits - REFCOUNT_SHIFT)) - 1);
    return be16_to_cpu(s->refcount_block_cache[block_index]);
}

/* return < 0 if error */
static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size)
{
    BDRVQcowState *s = bs->opaque;
    int i, nb_clusters;

    nb_clusters = size_to_clusters(s, size);
retry:
    for(i = 0; i < nb_clusters; i++) {
        int64_t i = s->free_cluster_index++;
        if (get_refcount(bs, i) != 0)
            goto retry;
    }
#ifdef DEBUG_ALLOC2
    printf("alloc_clusters: size=%lld -> %lld\n",
            size,
            (s->free_cluster_index - nb_clusters) << s->cluster_bits);
#endif
    return (s->free_cluster_index - nb_clusters) << s->cluster_bits;
}

static int64_t alloc_clusters(BlockDriverState *bs, int64_t size)
{
    int64_t offset;

    offset = alloc_clusters_noref(bs, size);
    update_refcount(bs, offset, size, 1);
    return offset;
}

/* only used to allocate compressed sectors. We try to allocate
   contiguous sectors. size must be <= cluster_size */
static int64_t alloc_bytes(BlockDriverState *bs, int size)
{
    BDRVQcowState *s = bs->opaque;
    int64_t offset, cluster_offset;
    int free_in_cluster;

    assert(size > 0 && size <= s->cluster_size);
    if (s->free_byte_offset == 0) {
        s->free_byte_offset = alloc_clusters(bs, s->cluster_size);
    }
 redo:
    free_in_cluster = s->cluster_size -
        (s->free_byte_offset & (s->cluster_size - 1));
    if (size <= free_in_cluster) {
        /* enough space in current cluster */
        offset = s->free_byte_offset;
        s->free_byte_offset += size;
        free_in_cluster -= size;
        if (free_in_cluster == 0)
            s->free_byte_offset = 0;
        if ((offset & (s->cluster_size - 1)) != 0)
            update_cluster_refcount(bs, offset >> s->cluster_bits, 1);
    } else {
        offset = alloc_clusters(bs, s->cluster_size);
        cluster_offset = s->free_byte_offset & ~(s->cluster_size - 1);
        if ((cluster_offset + s->cluster_size) == offset) {
            /* we are lucky: contiguous data */
            offset = s->free_byte_offset;
            update_cluster_refcount(bs, offset >> s->cluster_bits, 1);
            s->free_byte_offset += size;
        } else {
            s->free_byte_offset = offset;
            goto redo;
        }
    }
    return offset;
}

static void free_clusters(BlockDriverState *bs,
                          int64_t offset, int64_t size)
{
    update_refcount(bs, offset, size, -1);
}

static int grow_refcount_table(BlockDriverState *bs, int min_size)
{
    BDRVQcowState *s = bs->opaque;
    int new_table_size, new_table_size2, refcount_table_clusters, i, ret;
    uint64_t *new_table;
    int64_t table_offset;
    uint8_t data[12];
    int old_table_size;
    int64_t old_table_offset;

    if (min_size <= s->refcount_table_size)
        return 0;
    /* compute new table size */
    refcount_table_clusters = s->refcount_table_size >> (s->cluster_bits - 3);
    for(;;) {
        if (refcount_table_clusters == 0) {
            refcount_table_clusters = 1;
        } else {
            refcount_table_clusters = (refcount_table_clusters * 3 + 1) / 2;
        }
        new_table_size = refcount_table_clusters << (s->cluster_bits - 3);
        if (min_size <= new_table_size)
            break;
    }
#ifdef DEBUG_ALLOC2
    printf("grow_refcount_table from %d to %d\n",
           s->refcount_table_size,
           new_table_size);
#endif
    new_table_size2 = new_table_size * sizeof(uint64_t);
    new_table = qemu_mallocz(new_table_size2);
    memcpy(new_table, s->refcount_table,
           s->refcount_table_size * sizeof(uint64_t));
    for(i = 0; i < s->refcount_table_size; i++)
        cpu_to_be64s(&new_table[i]);
    /* Note: we cannot update the refcount now to avoid recursion */
    table_offset = alloc_clusters_noref(bs, new_table_size2);
    ret = bdrv_pwrite(s->hd, table_offset, new_table, new_table_size2);
    if (ret != new_table_size2)
        goto fail;
    for(i = 0; i < s->refcount_table_size; i++)
        be64_to_cpus(&new_table[i]);

    cpu_to_be64w((uint64_t*)data, table_offset);
    cpu_to_be32w((uint32_t*)(data + 8), refcount_table_clusters);
    if (bdrv_pwrite(s->hd, offsetof(QCowHeader, refcount_table_offset),
                    data, sizeof(data)) != sizeof(data))
        goto fail;
    qemu_free(s->refcount_table);
    old_table_offset = s->refcount_table_offset;
    old_table_size = s->refcount_table_size;
    s->refcount_table = new_table;
    s->refcount_table_size = new_table_size;
    s->refcount_table_offset = table_offset;

    update_refcount(bs, table_offset, new_table_size2, 1);
    free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t));
    return 0;
 fail:
    free_clusters(bs, table_offset, new_table_size2);
    qemu_free(new_table);
    return -EIO;
}

/* addend must be 1 or -1 */
/* XXX: cache several refcount block clusters ? */
static int update_cluster_refcount(BlockDriverState *bs,
                                   int64_t cluster_index,
                                   int addend)
{
    BDRVQcowState *s = bs->opaque;
    int64_t offset, refcount_block_offset;
    int ret, refcount_table_index, block_index, refcount;
    uint64_t data64;

    refcount_table_index = cluster_index >> (s->cluster_bits - REFCOUNT_SHIFT);
    if (refcount_table_index >= s->refcount_table_size) {
        if (addend < 0)
            return -EINVAL;
        ret = grow_refcount_table(bs, refcount_table_index + 1);
        if (ret < 0)
            return ret;
    }
    refcount_block_offset = s->refcount_table[refcount_table_index];
    if (!refcount_block_offset) {
        if (addend < 0)
            return -EINVAL;
        /* create a new refcount block */
        /* Note: we cannot update the refcount now to avoid recursion */
        offset = alloc_clusters_noref(bs, s->cluster_size);
        memset(s->refcount_block_cache, 0, s->cluster_size);
        ret = bdrv_pwrite(s->hd, offset, s->refcount_block_cache, s->cluster_size);
        if (ret != s->cluster_size)
            return -EINVAL;
        s->refcount_table[refcount_table_index] = offset;
        data64 = cpu_to_be64(offset);
        ret = bdrv_pwrite(s->hd, s->refcount_table_offset +
                          refcount_table_index * sizeof(uint64_t),
                          &data64, sizeof(data64));
        if (ret != sizeof(data64))
            return -EINVAL;

        refcount_block_offset = offset;
        s->refcount_block_cache_offset = offset;
        update_refcount(bs, offset, s->cluster_size, 1);
    } else {
        if (refcount_block_offset != s->refcount_block_cache_offset) {
            if (load_refcount_block(bs, refcount_block_offset) < 0)
                return -EIO;
        }
    }
    /* we can update the count and save it */
    block_index = cluster_index &
        ((1 << (s->cluster_bits - REFCOUNT_SHIFT)) - 1);
    refcount = be16_to_cpu(s->refcount_block_cache[block_index]);
    refcount += addend;
    if (refcount < 0 || refcount > 0xffff)
        return -EINVAL;
    if (refcount == 0 && cluster_index < s->free_cluster_index) {
        s->free_cluster_index = cluster_index;
    }
    s->refcount_block_cache[block_index] = cpu_to_be16(refcount);
    if (bdrv_pwrite(s->hd,
                    refcount_block_offset + (block_index << REFCOUNT_SHIFT),
                    &s->refcount_block_cache[block_index], 2) != 2)
        return -EIO;
    return refcount;
}

static void update_refcount(BlockDriverState *bs,
                            int64_t offset, int64_t length,
                            int addend)
{
    BDRVQcowState *s = bs->opaque;
    int64_t start, last, cluster_offset;

#ifdef DEBUG_ALLOC2
    printf("update_refcount: offset=%lld size=%lld addend=%d\n",
           offset, length, addend);
#endif
    if (length <= 0)
        return;
    start = offset & ~(s->cluster_size - 1);
    last = (offset + length - 1) & ~(s->cluster_size - 1);
    for(cluster_offset = start; cluster_offset <= last;
        cluster_offset += s->cluster_size) {
        update_cluster_refcount(bs, cluster_offset >> s->cluster_bits, addend);
    }
}

/*
 * Increases the refcount for a range of clusters in a given refcount table.
 * This is used to construct a temporary refcount table out of L1 and L2 tables
 * which can be compared the the refcount table saved in the image.
 *
 * Returns the number of errors in the image that were found
 */
static int inc_refcounts(BlockDriverState *bs,
                          uint16_t *refcount_table,
                          int refcount_table_size,
                          int64_t offset, int64_t size)
{
    BDRVQcowState *s = bs->opaque;
    int64_t start, last, cluster_offset;
    int k;
    int errors = 0;

    if (size <= 0)
        return 0;

    start = offset & ~(s->cluster_size - 1);
    last = (offset + size - 1) & ~(s->cluster_size - 1);
    for(cluster_offset = start; cluster_offset <= last;
        cluster_offset += s->cluster_size) {
        k = cluster_offset >> s->cluster_bits;
        if (k < 0 || k >= refcount_table_size) {
            fprintf(stderr, "ERROR: invalid cluster offset=0x%" PRIx64 "\n",
                cluster_offset);
            errors++;
        } else {
            if (++refcount_table[k] == 0) {
                fprintf(stderr, "ERROR: overflow cluster offset=0x%" PRIx64
                    "\n", cluster_offset);
                errors++;
            }
        }
    }

    return errors;
}

/*
 * Increases the refcount in the given refcount table for the all clusters
 * referenced in the L2 table. While doing so, performs some checks on L2
 * entries.
 *
 * Returns the number of errors found by the checks or -errno if an internal
 * error occurred.
 */
static int check_refcounts_l2(BlockDriverState *bs,
    uint16_t *refcount_table, int refcount_table_size, int64_t l2_offset,
    int check_copied)
{
    BDRVQcowState *s = bs->opaque;
    uint64_t *l2_table, offset;
    int i, l2_size, nb_csectors, refcount;
    int errors = 0;

    /* Read L2 table from disk */
    l2_size = s->l2_size * sizeof(uint64_t);
    l2_table = qemu_malloc(l2_size);

    if (bdrv_pread(s->hd, l2_offset, l2_table, l2_size) != l2_size)
        goto fail;

    /* Do the actual checks */
    for(i = 0; i < s->l2_size; i++) {
        offset = be64_to_cpu(l2_table[i]);
        if (offset != 0) {
            if (offset & QCOW_OFLAG_COMPRESSED) {
                /* Compressed clusters don't have QCOW_OFLAG_COPIED */
                if (offset & QCOW_OFLAG_COPIED) {
                    fprintf(stderr, "ERROR: cluster %" PRId64 ": "
                        "copied flag must never be set for compressed "
                        "clusters\n", offset >> s->cluster_bits);
                    offset &= ~QCOW_OFLAG_COPIED;
                    errors++;
                }

                /* Mark cluster as used */
                nb_csectors = ((offset >> s->csize_shift) &
                               s->csize_mask) + 1;
                offset &= s->cluster_offset_mask;
                errors += inc_refcounts(bs, refcount_table,
                              refcount_table_size,
                              offset & ~511, nb_csectors * 512);
            } else {
                /* QCOW_OFLAG_COPIED must be set iff refcount == 1 */
                if (check_copied) {
                    uint64_t entry = offset;
                    offset &= ~QCOW_OFLAG_COPIED;
                    refcount = get_refcount(bs, offset >> s->cluster_bits);
                    if ((refcount == 1) != ((entry & QCOW_OFLAG_COPIED) != 0)) {
                        fprintf(stderr, "ERROR OFLAG_COPIED: offset=%"
                            PRIx64 " refcount=%d\n", entry, refcount);
                        errors++;
                    }
                }

                /* Mark cluster as used */
                offset &= ~QCOW_OFLAG_COPIED;
                errors += inc_refcounts(bs, refcount_table,
                              refcount_table_size,
                              offset, s->cluster_size);

                /* Correct offsets are cluster aligned */
                if (offset & (s->cluster_size - 1)) {
                    fprintf(stderr, "ERROR offset=%" PRIx64 ": Cluster is not "
                        "properly aligned; L2 entry corrupted.\n", offset);
                    errors++;
                }
            }
        }
    }

    qemu_free(l2_table);
    return errors;

fail:
    fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n");
    qemu_free(l2_table);
    return -EIO;
}

/*
 * Increases the refcount for the L1 table, its L2 tables and all referenced
 * clusters in the given refcount table. While doing so, performs some checks
 * on L1 and L2 entries.
 *
 * Returns the number of errors found by the checks or -errno if an internal
 * error occurred.
 */
static int check_refcounts_l1(BlockDriverState *bs,
                              uint16_t *refcount_table,
                              int refcount_table_size,
                              int64_t l1_table_offset, int l1_size,
                              int check_copied)
{
    BDRVQcowState *s = bs->opaque;
    uint64_t *l1_table, l2_offset, l1_size2;
    int i, refcount, ret;
    int errors = 0;

    l1_size2 = l1_size * sizeof(uint64_t);

    /* Mark L1 table as used */
    errors += inc_refcounts(bs, refcount_table, refcount_table_size,
                  l1_table_offset, l1_size2);

    /* Read L1 table entries from disk */
    l1_table = qemu_malloc(l1_size2);
    if (bdrv_pread(s->hd, l1_table_offset,
                   l1_table, l1_size2) != l1_size2)
        goto fail;
    for(i = 0;i < l1_size; i++)
        be64_to_cpus(&l1_table[i]);

    /* Do the actual checks */
    for(i = 0; i < l1_size; i++) {
        l2_offset = l1_table[i];
        if (l2_offset) {
            /* QCOW_OFLAG_COPIED must be set iff refcount == 1 */
            if (check_copied) {
                refcount = get_refcount(bs, (l2_offset & ~QCOW_OFLAG_COPIED)
                    >> s->cluster_bits);
                if ((refcount == 1) != ((l2_offset & QCOW_OFLAG_COPIED) != 0)) {
                    fprintf(stderr, "ERROR OFLAG_COPIED: l2_offset=%" PRIx64
                        " refcount=%d\n", l2_offset, refcount);
                    errors++;
                }
            }

            /* Mark L2 table as used */
            l2_offset &= ~QCOW_OFLAG_COPIED;
            errors += inc_refcounts(bs, refcount_table,
                          refcount_table_size,
                          l2_offset,
                          s->cluster_size);

            /* L2 tables are cluster aligned */
            if (l2_offset & (s->cluster_size - 1)) {
                fprintf(stderr, "ERROR l2_offset=%" PRIx64 ": Table is not "
                    "cluster aligned; L1 entry corrupted\n", l2_offset);
                errors++;
            }

            /* Process and check L2 entries */
            ret = check_refcounts_l2(bs, refcount_table, refcount_table_size,
                l2_offset, check_copied);
            if (ret < 0) {
                goto fail;
            }
            errors += ret;
        }
    }
    qemu_free(l1_table);
    return errors;

fail:
    fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n");
    qemu_free(l1_table);
    return -EIO;
}

/*
 * Checks an image for refcount consistency.
 *
 * Returns 0 if no errors are found, the number of errors in case the image is
 * detected as corrupted, and -errno when an internal error occured.
 */
static int check_refcounts(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    int64_t size;
    int nb_clusters, refcount1, refcount2, i;
    QCowSnapshot *sn;
    uint16_t *refcount_table;
    int ret, errors = 0;

    size = bdrv_getlength(s->hd);
    nb_clusters = size_to_clusters(s, size);
    refcount_table = qemu_mallocz(nb_clusters * sizeof(uint16_t));

    /* header */
    errors += inc_refcounts(bs, refcount_table, nb_clusters,
                  0, s->cluster_size);

    /* current L1 table */
    ret = check_refcounts_l1(bs, refcount_table, nb_clusters,
                       s->l1_table_offset, s->l1_size, 1);
    if (ret < 0) {
        return ret;
    }
    errors += ret;

    /* snapshots */
    for(i = 0; i < s->nb_snapshots; i++) {
        sn = s->snapshots + i;
        check_refcounts_l1(bs, refcount_table, nb_clusters,
                           sn->l1_table_offset, sn->l1_size, 0);
    }
    errors += inc_refcounts(bs, refcount_table, nb_clusters,
                  s->snapshots_offset, s->snapshots_size);

    /* refcount data */
    errors += inc_refcounts(bs, refcount_table, nb_clusters,
                  s->refcount_table_offset,
                  s->refcount_table_size * sizeof(uint64_t));
    for(i = 0; i < s->refcount_table_size; i++) {
        int64_t offset;
        offset = s->refcount_table[i];
        if (offset != 0) {
            errors += inc_refcounts(bs, refcount_table, nb_clusters,
                          offset, s->cluster_size);
        }
    }

    /* compare ref counts */
    for(i = 0; i < nb_clusters; i++) {
        refcount1 = get_refcount(bs, i);
        refcount2 = refcount_table[i];
        if (refcount1 != refcount2) {
            fprintf(stderr, "ERROR cluster %d refcount=%d reference=%d\n",
                   i, refcount1, refcount2);
            errors++;
        }
    }

    qemu_free(refcount_table);

    return errors;
}

static int qcow_check(BlockDriverState *bs)
{
    return 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_put_buffer(BlockDriverState *bs, const uint8_t *buf,
                           int64_t pos, int size)
{
    int growable = bs->growable;

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

    return size;
}

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

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

    return ret;
}

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_aio_cancel	= qcow_aio_cancel,
    .aiocb_size		= sizeof(QCowAIOCB),
    .bdrv_write_compressed = qcow_write_compressed,

    .bdrv_snapshot_create = qcow_snapshot_create,
    .bdrv_snapshot_goto	= qcow_snapshot_goto,
    .bdrv_snapshot_delete = qcow_snapshot_delete,
    .bdrv_snapshot_list	= qcow_snapshot_list,
    .bdrv_get_info	= qcow_get_info,

    .bdrv_put_buffer    = qcow_put_buffer,
    .bdrv_get_buffer    = qcow_get_buffer,

    .bdrv_create2 = qcow_create2,
    .bdrv_check = qcow_check,
};