aboutsummaryrefslogtreecommitdiff
path: root/block.c
blob: 6dbcb7e083eab8de30690c06269c3033d41b2e83 (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
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
/*
 * QEMU System Emulator block driver
 *
 * Copyright (c) 2003 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/osdep.h"
#include "block/trace.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "block/nbd.h"
#include "block/qdict.h"
#include "qemu/error-report.h"
#include "module_block.h"
#include "qemu/main-loop.h"
#include "qemu/module.h"
#include "qapi/error.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qjson.h"
#include "qapi/qmp/qnull.h"
#include "qapi/qmp/qstring.h"
#include "qapi/qobject-output-visitor.h"
#include "qapi/qapi-visit-block-core.h"
#include "sysemu/block-backend.h"
#include "sysemu/sysemu.h"
#include "qemu/notify.h"
#include "qemu/option.h"
#include "qemu/coroutine.h"
#include "block/qapi.h"
#include "qemu/timer.h"
#include "qemu/cutils.h"
#include "qemu/id.h"

#ifdef CONFIG_BSD
#include <sys/ioctl.h>
#include <sys/queue.h>
#ifndef __DragonFly__
#include <sys/disk.h>
#endif
#endif

#ifdef _WIN32
#include <windows.h>
#endif

#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */

static QTAILQ_HEAD(, BlockDriverState) graph_bdrv_states =
    QTAILQ_HEAD_INITIALIZER(graph_bdrv_states);

static QTAILQ_HEAD(, BlockDriverState) all_bdrv_states =
    QTAILQ_HEAD_INITIALIZER(all_bdrv_states);

static QLIST_HEAD(, BlockDriver) bdrv_drivers =
    QLIST_HEAD_INITIALIZER(bdrv_drivers);

static BlockDriverState *bdrv_open_inherit(const char *filename,
                                           const char *reference,
                                           QDict *options, int flags,
                                           BlockDriverState *parent,
                                           const BdrvChildClass *child_class,
                                           BdrvChildRole child_role,
                                           Error **errp);

/* If non-zero, use only whitelisted block drivers */
static int use_bdrv_whitelist;

#ifdef _WIN32
static int is_windows_drive_prefix(const char *filename)
{
    return (((filename[0] >= 'a' && filename[0] <= 'z') ||
             (filename[0] >= 'A' && filename[0] <= 'Z')) &&
            filename[1] == ':');
}

int is_windows_drive(const char *filename)
{
    if (is_windows_drive_prefix(filename) &&
        filename[2] == '\0')
        return 1;
    if (strstart(filename, "\\\\.\\", NULL) ||
        strstart(filename, "//./", NULL))
        return 1;
    return 0;
}
#endif

size_t bdrv_opt_mem_align(BlockDriverState *bs)
{
    if (!bs || !bs->drv) {
        /* page size or 4k (hdd sector size) should be on the safe side */
        return MAX(4096, qemu_real_host_page_size);
    }

    return bs->bl.opt_mem_alignment;
}

size_t bdrv_min_mem_align(BlockDriverState *bs)
{
    if (!bs || !bs->drv) {
        /* page size or 4k (hdd sector size) should be on the safe side */
        return MAX(4096, qemu_real_host_page_size);
    }

    return bs->bl.min_mem_alignment;
}

/* check if the path starts with "<protocol>:" */
int path_has_protocol(const char *path)
{
    const char *p;

#ifdef _WIN32
    if (is_windows_drive(path) ||
        is_windows_drive_prefix(path)) {
        return 0;
    }
    p = path + strcspn(path, ":/\\");
#else
    p = path + strcspn(path, ":/");
#endif

    return *p == ':';
}

int path_is_absolute(const char *path)
{
#ifdef _WIN32
    /* specific case for names like: "\\.\d:" */
    if (is_windows_drive(path) || is_windows_drive_prefix(path)) {
        return 1;
    }
    return (*path == '/' || *path == '\\');
#else
    return (*path == '/');
#endif
}

/* if filename is absolute, just return its duplicate. Otherwise, build a
   path to it by considering it is relative to base_path. URL are
   supported. */
char *path_combine(const char *base_path, const char *filename)
{
    const char *protocol_stripped = NULL;
    const char *p, *p1;
    char *result;
    int len;

    if (path_is_absolute(filename)) {
        return g_strdup(filename);
    }

    if (path_has_protocol(base_path)) {
        protocol_stripped = strchr(base_path, ':');
        if (protocol_stripped) {
            protocol_stripped++;
        }
    }
    p = protocol_stripped ?: base_path;

    p1 = strrchr(base_path, '/');
#ifdef _WIN32
    {
        const char *p2;
        p2 = strrchr(base_path, '\\');
        if (!p1 || p2 > p1) {
            p1 = p2;
        }
    }
#endif
    if (p1) {
        p1++;
    } else {
        p1 = base_path;
    }
    if (p1 > p) {
        p = p1;
    }
    len = p - base_path;

    result = g_malloc(len + strlen(filename) + 1);
    memcpy(result, base_path, len);
    strcpy(result + len, filename);

    return result;
}

/*
 * Helper function for bdrv_parse_filename() implementations to remove optional
 * protocol prefixes (especially "file:") from a filename and for putting the
 * stripped filename into the options QDict if there is such a prefix.
 */
void bdrv_parse_filename_strip_prefix(const char *filename, const char *prefix,
                                      QDict *options)
{
    if (strstart(filename, prefix, &filename)) {
        /* Stripping the explicit protocol prefix may result in a protocol
         * prefix being (wrongly) detected (if the filename contains a colon) */
        if (path_has_protocol(filename)) {
            QString *fat_filename;

            /* This means there is some colon before the first slash; therefore,
             * this cannot be an absolute path */
            assert(!path_is_absolute(filename));

            /* And we can thus fix the protocol detection issue by prefixing it
             * by "./" */
            fat_filename = qstring_from_str("./");
            qstring_append(fat_filename, filename);

            assert(!path_has_protocol(qstring_get_str(fat_filename)));

            qdict_put(options, "filename", fat_filename);
        } else {
            /* If no protocol prefix was detected, we can use the shortened
             * filename as-is */
            qdict_put_str(options, "filename", filename);
        }
    }
}


/* Returns whether the image file is opened as read-only. Note that this can
 * return false and writing to the image file is still not possible because the
 * image is inactivated. */
bool bdrv_is_read_only(BlockDriverState *bs)
{
    return bs->read_only;
}

int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only,
                           bool ignore_allow_rdw, Error **errp)
{
    /* Do not set read_only if copy_on_read is enabled */
    if (bs->copy_on_read && read_only) {
        error_setg(errp, "Can't set node '%s' to r/o with copy-on-read enabled",
                   bdrv_get_device_or_node_name(bs));
        return -EINVAL;
    }

    /* Do not clear read_only if it is prohibited */
    if (!read_only && !(bs->open_flags & BDRV_O_ALLOW_RDWR) &&
        !ignore_allow_rdw)
    {
        error_setg(errp, "Node '%s' is read only",
                   bdrv_get_device_or_node_name(bs));
        return -EPERM;
    }

    return 0;
}

/*
 * Called by a driver that can only provide a read-only image.
 *
 * Returns 0 if the node is already read-only or it could switch the node to
 * read-only because BDRV_O_AUTO_RDONLY is set.
 *
 * Returns -EACCES if the node is read-write and BDRV_O_AUTO_RDONLY is not set
 * or bdrv_can_set_read_only() forbids making the node read-only. If @errmsg
 * is not NULL, it is used as the error message for the Error object.
 */
int bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg,
                              Error **errp)
{
    int ret = 0;

    if (!(bs->open_flags & BDRV_O_RDWR)) {
        return 0;
    }
    if (!(bs->open_flags & BDRV_O_AUTO_RDONLY)) {
        goto fail;
    }

    ret = bdrv_can_set_read_only(bs, true, false, NULL);
    if (ret < 0) {
        goto fail;
    }

    bs->read_only = true;
    bs->open_flags &= ~BDRV_O_RDWR;

    return 0;

fail:
    error_setg(errp, "%s", errmsg ?: "Image is read-only");
    return -EACCES;
}

/*
 * If @backing is empty, this function returns NULL without setting
 * @errp.  In all other cases, NULL will only be returned with @errp
 * set.
 *
 * Therefore, a return value of NULL without @errp set means that
 * there is no backing file; if @errp is set, there is one but its
 * absolute filename cannot be generated.
 */
char *bdrv_get_full_backing_filename_from_filename(const char *backed,
                                                   const char *backing,
                                                   Error **errp)
{
    if (backing[0] == '\0') {
        return NULL;
    } else if (path_has_protocol(backing) || path_is_absolute(backing)) {
        return g_strdup(backing);
    } else if (backed[0] == '\0' || strstart(backed, "json:", NULL)) {
        error_setg(errp, "Cannot use relative backing file names for '%s'",
                   backed);
        return NULL;
    } else {
        return path_combine(backed, backing);
    }
}

/*
 * If @filename is empty or NULL, this function returns NULL without
 * setting @errp.  In all other cases, NULL will only be returned with
 * @errp set.
 */
static char *bdrv_make_absolute_filename(BlockDriverState *relative_to,
                                         const char *filename, Error **errp)
{
    char *dir, *full_name;

    if (!filename || filename[0] == '\0') {
        return NULL;
    } else if (path_has_protocol(filename) || path_is_absolute(filename)) {
        return g_strdup(filename);
    }

    dir = bdrv_dirname(relative_to, errp);
    if (!dir) {
        return NULL;
    }

    full_name = g_strconcat(dir, filename, NULL);
    g_free(dir);
    return full_name;
}

char *bdrv_get_full_backing_filename(BlockDriverState *bs, Error **errp)
{
    return bdrv_make_absolute_filename(bs, bs->backing_file, errp);
}

void bdrv_register(BlockDriver *bdrv)
{
    assert(bdrv->format_name);
    QLIST_INSERT_HEAD(&bdrv_drivers, bdrv, list);
}

BlockDriverState *bdrv_new(void)
{
    BlockDriverState *bs;
    int i;

    bs = g_new0(BlockDriverState, 1);
    QLIST_INIT(&bs->dirty_bitmaps);
    for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
        QLIST_INIT(&bs->op_blockers[i]);
    }
    notifier_with_return_list_init(&bs->before_write_notifiers);
    qemu_co_mutex_init(&bs->reqs_lock);
    qemu_mutex_init(&bs->dirty_bitmap_mutex);
    bs->refcnt = 1;
    bs->aio_context = qemu_get_aio_context();

    qemu_co_queue_init(&bs->flush_queue);

    for (i = 0; i < bdrv_drain_all_count; i++) {
        bdrv_drained_begin(bs);
    }

    QTAILQ_INSERT_TAIL(&all_bdrv_states, bs, bs_list);

    return bs;
}

static BlockDriver *bdrv_do_find_format(const char *format_name)
{
    BlockDriver *drv1;

    QLIST_FOREACH(drv1, &bdrv_drivers, list) {
        if (!strcmp(drv1->format_name, format_name)) {
            return drv1;
        }
    }

    return NULL;
}

BlockDriver *bdrv_find_format(const char *format_name)
{
    BlockDriver *drv1;
    int i;

    drv1 = bdrv_do_find_format(format_name);
    if (drv1) {
        return drv1;
    }

    /* The driver isn't registered, maybe we need to load a module */
    for (i = 0; i < (int)ARRAY_SIZE(block_driver_modules); ++i) {
        if (!strcmp(block_driver_modules[i].format_name, format_name)) {
            block_module_load_one(block_driver_modules[i].library_name);
            break;
        }
    }

    return bdrv_do_find_format(format_name);
}

static int bdrv_format_is_whitelisted(const char *format_name, bool read_only)
{
    static const char *whitelist_rw[] = {
        CONFIG_BDRV_RW_WHITELIST
    };
    static const char *whitelist_ro[] = {
        CONFIG_BDRV_RO_WHITELIST
    };
    const char **p;

    if (!whitelist_rw[0] && !whitelist_ro[0]) {
        return 1;               /* no whitelist, anything goes */
    }

    for (p = whitelist_rw; *p; p++) {
        if (!strcmp(format_name, *p)) {
            return 1;
        }
    }
    if (read_only) {
        for (p = whitelist_ro; *p; p++) {
            if (!strcmp(format_name, *p)) {
                return 1;
            }
        }
    }
    return 0;
}

int bdrv_is_whitelisted(BlockDriver *drv, bool read_only)
{
    return bdrv_format_is_whitelisted(drv->format_name, read_only);
}

bool bdrv_uses_whitelist(void)
{
    return use_bdrv_whitelist;
}

typedef struct CreateCo {
    BlockDriver *drv;
    char *filename;
    QemuOpts *opts;
    int ret;
    Error *err;
} CreateCo;

static void coroutine_fn bdrv_create_co_entry(void *opaque)
{
    Error *local_err = NULL;
    int ret;

    CreateCo *cco = opaque;
    assert(cco->drv);

    ret = cco->drv->bdrv_co_create_opts(cco->drv,
                                        cco->filename, cco->opts, &local_err);
    error_propagate(&cco->err, local_err);
    cco->ret = ret;
}

int bdrv_create(BlockDriver *drv, const char* filename,
                QemuOpts *opts, Error **errp)
{
    int ret;

    Coroutine *co;
    CreateCo cco = {
        .drv = drv,
        .filename = g_strdup(filename),
        .opts = opts,
        .ret = NOT_DONE,
        .err = NULL,
    };

    if (!drv->bdrv_co_create_opts) {
        error_setg(errp, "Driver '%s' does not support image creation", drv->format_name);
        ret = -ENOTSUP;
        goto out;
    }

    if (qemu_in_coroutine()) {
        /* Fast-path if already in coroutine context */
        bdrv_create_co_entry(&cco);
    } else {
        co = qemu_coroutine_create(bdrv_create_co_entry, &cco);
        qemu_coroutine_enter(co);
        while (cco.ret == NOT_DONE) {
            aio_poll(qemu_get_aio_context(), true);
        }
    }

    ret = cco.ret;
    if (ret < 0) {
        if (cco.err) {
            error_propagate(errp, cco.err);
        } else {
            error_setg_errno(errp, -ret, "Could not create image");
        }
    }

out:
    g_free(cco.filename);
    return ret;
}

/**
 * Helper function for bdrv_create_file_fallback(): Resize @blk to at
 * least the given @minimum_size.
 *
 * On success, return @blk's actual length.
 * Otherwise, return -errno.
 */
static int64_t create_file_fallback_truncate(BlockBackend *blk,
                                             int64_t minimum_size, Error **errp)
{
    Error *local_err = NULL;
    int64_t size;
    int ret;

    ret = blk_truncate(blk, minimum_size, false, PREALLOC_MODE_OFF, 0,
                       &local_err);
    if (ret < 0 && ret != -ENOTSUP) {
        error_propagate(errp, local_err);
        return ret;
    }

    size = blk_getlength(blk);
    if (size < 0) {
        error_free(local_err);
        error_setg_errno(errp, -size,
                         "Failed to inquire the new image file's length");
        return size;
    }

    if (size < minimum_size) {
        /* Need to grow the image, but we failed to do that */
        error_propagate(errp, local_err);
        return -ENOTSUP;
    }

    error_free(local_err);
    local_err = NULL;

    return size;
}

/**
 * Helper function for bdrv_create_file_fallback(): Zero the first
 * sector to remove any potentially pre-existing image header.
 */
static int create_file_fallback_zero_first_sector(BlockBackend *blk,
                                                  int64_t current_size,
                                                  Error **errp)
{
    int64_t bytes_to_clear;
    int ret;

    bytes_to_clear = MIN(current_size, BDRV_SECTOR_SIZE);
    if (bytes_to_clear) {
        ret = blk_pwrite_zeroes(blk, 0, bytes_to_clear, BDRV_REQ_MAY_UNMAP);
        if (ret < 0) {
            error_setg_errno(errp, -ret,
                             "Failed to clear the new image's first sector");
            return ret;
        }
    }

    return 0;
}

/**
 * Simple implementation of bdrv_co_create_opts for protocol drivers
 * which only support creation via opening a file
 * (usually existing raw storage device)
 */
int coroutine_fn bdrv_co_create_opts_simple(BlockDriver *drv,
                                            const char *filename,
                                            QemuOpts *opts,
                                            Error **errp)
{
    BlockBackend *blk;
    QDict *options;
    int64_t size = 0;
    char *buf = NULL;
    PreallocMode prealloc;
    Error *local_err = NULL;
    int ret;

    size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
    buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
    prealloc = qapi_enum_parse(&PreallocMode_lookup, buf,
                               PREALLOC_MODE_OFF, &local_err);
    g_free(buf);
    if (local_err) {
        error_propagate(errp, local_err);
        return -EINVAL;
    }

    if (prealloc != PREALLOC_MODE_OFF) {
        error_setg(errp, "Unsupported preallocation mode '%s'",
                   PreallocMode_str(prealloc));
        return -ENOTSUP;
    }

    options = qdict_new();
    qdict_put_str(options, "driver", drv->format_name);

    blk = blk_new_open(filename, NULL, options,
                       BDRV_O_RDWR | BDRV_O_RESIZE, errp);
    if (!blk) {
        error_prepend(errp, "Protocol driver '%s' does not support image "
                      "creation, and opening the image failed: ",
                      drv->format_name);
        return -EINVAL;
    }

    size = create_file_fallback_truncate(blk, size, errp);
    if (size < 0) {
        ret = size;
        goto out;
    }

    ret = create_file_fallback_zero_first_sector(blk, size, errp);
    if (ret < 0) {
        goto out;
    }

    ret = 0;
out:
    blk_unref(blk);
    return ret;
}

int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp)
{
    BlockDriver *drv;

    drv = bdrv_find_protocol(filename, true, errp);
    if (drv == NULL) {
        return -ENOENT;
    }

    return bdrv_create(drv, filename, opts, errp);
}

int coroutine_fn bdrv_co_delete_file(BlockDriverState *bs, Error **errp)
{
    Error *local_err = NULL;
    int ret;

    assert(bs != NULL);

    if (!bs->drv) {
        error_setg(errp, "Block node '%s' is not opened", bs->filename);
        return -ENOMEDIUM;
    }

    if (!bs->drv->bdrv_co_delete_file) {
        error_setg(errp, "Driver '%s' does not support image deletion",
                   bs->drv->format_name);
        return -ENOTSUP;
    }

    ret = bs->drv->bdrv_co_delete_file(bs, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
    }

    return ret;
}

/**
 * Try to get @bs's logical and physical block size.
 * On success, store them in @bsz struct and return 0.
 * On failure return -errno.
 * @bs must not be empty.
 */
int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
{
    BlockDriver *drv = bs->drv;

    if (drv && drv->bdrv_probe_blocksizes) {
        return drv->bdrv_probe_blocksizes(bs, bsz);
    } else if (drv && drv->is_filter && bs->file) {
        return bdrv_probe_blocksizes(bs->file->bs, bsz);
    }

    return -ENOTSUP;
}

/**
 * Try to get @bs's geometry (cyls, heads, sectors).
 * On success, store them in @geo struct and return 0.
 * On failure return -errno.
 * @bs must not be empty.
 */
int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
{
    BlockDriver *drv = bs->drv;

    if (drv && drv->bdrv_probe_geometry) {
        return drv->bdrv_probe_geometry(bs, geo);
    } else if (drv && drv->is_filter && bs->file) {
        return bdrv_probe_geometry(bs->file->bs, geo);
    }

    return -ENOTSUP;
}

/*
 * Create a uniquely-named empty temporary file.
 * Return 0 upon success, otherwise a negative errno value.
 */
int get_tmp_filename(char *filename, int size)
{
#ifdef _WIN32
    char temp_dir[MAX_PATH];
    /* GetTempFileName requires that its output buffer (4th param)
       have length MAX_PATH or greater.  */
    assert(size >= MAX_PATH);
    return (GetTempPath(MAX_PATH, temp_dir)
            && GetTempFileName(temp_dir, "qem", 0, filename)
            ? 0 : -GetLastError());
#else
    int fd;
    const char *tmpdir;
    tmpdir = getenv("TMPDIR");
    if (!tmpdir) {
        tmpdir = "/var/tmp";
    }
    if (snprintf(filename, size, "%s/vl.XXXXXX", tmpdir) >= size) {
        return -EOVERFLOW;
    }
    fd = mkstemp(filename);
    if (fd < 0) {
        return -errno;
    }
    if (close(fd) != 0) {
        unlink(filename);
        return -errno;
    }
    return 0;
#endif
}

/*
 * Detect host devices. By convention, /dev/cdrom[N] is always
 * recognized as a host CDROM.
 */
static BlockDriver *find_hdev_driver(const char *filename)
{
    int score_max = 0, score;
    BlockDriver *drv = NULL, *d;

    QLIST_FOREACH(d, &bdrv_drivers, list) {
        if (d->bdrv_probe_device) {
            score = d->bdrv_probe_device(filename);
            if (score > score_max) {
                score_max = score;
                drv = d;
            }
        }
    }

    return drv;
}

static BlockDriver *bdrv_do_find_protocol(const char *protocol)
{
    BlockDriver *drv1;

    QLIST_FOREACH(drv1, &bdrv_drivers, list) {
        if (drv1->protocol_name && !strcmp(drv1->protocol_name, protocol)) {
            return drv1;
        }
    }

    return NULL;
}

BlockDriver *bdrv_find_protocol(const char *filename,
                                bool allow_protocol_prefix,
                                Error **errp)
{
    BlockDriver *drv1;
    char protocol[128];
    int len;
    const char *p;
    int i;

    /* TODO Drivers without bdrv_file_open must be specified explicitly */

    /*
     * XXX(hch): we really should not let host device detection
     * override an explicit protocol specification, but moving this
     * later breaks access to device names with colons in them.
     * Thanks to the brain-dead persistent naming schemes on udev-
     * based Linux systems those actually are quite common.
     */
    drv1 = find_hdev_driver(filename);
    if (drv1) {
        return drv1;
    }

    if (!path_has_protocol(filename) || !allow_protocol_prefix) {
        return &bdrv_file;
    }

    p = strchr(filename, ':');
    assert(p != NULL);
    len = p - filename;
    if (len > sizeof(protocol) - 1)
        len = sizeof(protocol) - 1;
    memcpy(protocol, filename, len);
    protocol[len] = '\0';

    drv1 = bdrv_do_find_protocol(protocol);
    if (drv1) {
        return drv1;
    }

    for (i = 0; i < (int)ARRAY_SIZE(block_driver_modules); ++i) {
        if (block_driver_modules[i].protocol_name &&
            !strcmp(block_driver_modules[i].protocol_name, protocol)) {
            block_module_load_one(block_driver_modules[i].library_name);
            break;
        }
    }

    drv1 = bdrv_do_find_protocol(protocol);
    if (!drv1) {
        error_setg(errp, "Unknown protocol '%s'", protocol);
    }
    return drv1;
}

/*
 * Guess image format by probing its contents.
 * This is not a good idea when your image is raw (CVE-2008-2004), but
 * we do it anyway for backward compatibility.
 *
 * @buf         contains the image's first @buf_size bytes.
 * @buf_size    is the buffer size in bytes (generally BLOCK_PROBE_BUF_SIZE,
 *              but can be smaller if the image file is smaller)
 * @filename    is its filename.
 *
 * For all block drivers, call the bdrv_probe() method to get its
 * probing score.
 * Return the first block driver with the highest probing score.
 */
BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
                            const char *filename)
{
    int score_max = 0, score;
    BlockDriver *drv = NULL, *d;

    QLIST_FOREACH(d, &bdrv_drivers, list) {
        if (d->bdrv_probe) {
            score = d->bdrv_probe(buf, buf_size, filename);
            if (score > score_max) {
                score_max = score;
                drv = d;
            }
        }
    }

    return drv;
}

static int find_image_format(BlockBackend *file, const char *filename,
                             BlockDriver **pdrv, Error **errp)
{
    BlockDriver *drv;
    uint8_t buf[BLOCK_PROBE_BUF_SIZE];
    int ret = 0;

    /* Return the raw BlockDriver * to scsi-generic devices or empty drives */
    if (blk_is_sg(file) || !blk_is_inserted(file) || blk_getlength(file) == 0) {
        *pdrv = &bdrv_raw;
        return ret;
    }

    ret = blk_pread(file, 0, buf, sizeof(buf));
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Could not read image for determining its "
                         "format");
        *pdrv = NULL;
        return ret;
    }

    drv = bdrv_probe_all(buf, ret, filename);
    if (!drv) {
        error_setg(errp, "Could not determine image format: No compatible "
                   "driver found");
        ret = -ENOENT;
    }
    *pdrv = drv;
    return ret;
}

/**
 * Set the current 'total_sectors' value
 * Return 0 on success, -errno on error.
 */
int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
{
    BlockDriver *drv = bs->drv;

    if (!drv) {
        return -ENOMEDIUM;
    }

    /* Do not attempt drv->bdrv_getlength() on scsi-generic devices */
    if (bdrv_is_sg(bs))
        return 0;

    /* query actual device if possible, otherwise just trust the hint */
    if (drv->bdrv_getlength) {
        int64_t length = drv->bdrv_getlength(bs);
        if (length < 0) {
            return length;
        }
        hint = DIV_ROUND_UP(length, BDRV_SECTOR_SIZE);
    }

    bs->total_sectors = hint;
    return 0;
}

/**
 * Combines a QDict of new block driver @options with any missing options taken
 * from @old_options, so that leaving out an option defaults to its old value.
 */
static void bdrv_join_options(BlockDriverState *bs, QDict *options,
                              QDict *old_options)
{
    if (bs->drv && bs->drv->bdrv_join_options) {
        bs->drv->bdrv_join_options(options, old_options);
    } else {
        qdict_join(options, old_options, false);
    }
}

static BlockdevDetectZeroesOptions bdrv_parse_detect_zeroes(QemuOpts *opts,
                                                            int open_flags,
                                                            Error **errp)
{
    Error *local_err = NULL;
    char *value = qemu_opt_get_del(opts, "detect-zeroes");
    BlockdevDetectZeroesOptions detect_zeroes =
        qapi_enum_parse(&BlockdevDetectZeroesOptions_lookup, value,
                        BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF, &local_err);
    g_free(value);
    if (local_err) {
        error_propagate(errp, local_err);
        return detect_zeroes;
    }

    if (detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP &&
        !(open_flags & BDRV_O_UNMAP))
    {
        error_setg(errp, "setting detect-zeroes to unmap is not allowed "
                   "without setting discard operation to unmap");
    }

    return detect_zeroes;
}

/**
 * Set open flags for aio engine
 *
 * Return 0 on success, -1 if the engine specified is invalid
 */
int bdrv_parse_aio(const char *mode, int *flags)
{
    if (!strcmp(mode, "threads")) {
        /* do nothing, default */
    } else if (!strcmp(mode, "native")) {
        *flags |= BDRV_O_NATIVE_AIO;
#ifdef CONFIG_LINUX_IO_URING
    } else if (!strcmp(mode, "io_uring")) {
        *flags |= BDRV_O_IO_URING;
#endif
    } else {
        return -1;
    }

    return 0;
}

/**
 * Set open flags for a given discard mode
 *
 * Return 0 on success, -1 if the discard mode was invalid.
 */
int bdrv_parse_discard_flags(const char *mode, int *flags)
{
    *flags &= ~BDRV_O_UNMAP;

    if (!strcmp(mode, "off") || !strcmp(mode, "ignore")) {
        /* do nothing */
    } else if (!strcmp(mode, "on") || !strcmp(mode, "unmap")) {
        *flags |= BDRV_O_UNMAP;
    } else {
        return -1;
    }

    return 0;
}

/**
 * Set open flags for a given cache mode
 *
 * Return 0 on success, -1 if the cache mode was invalid.
 */
int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough)
{
    *flags &= ~BDRV_O_CACHE_MASK;

    if (!strcmp(mode, "off") || !strcmp(mode, "none")) {
        *writethrough = false;
        *flags |= BDRV_O_NOCACHE;
    } else if (!strcmp(mode, "directsync")) {
        *writethrough = true;
        *flags |= BDRV_O_NOCACHE;
    } else if (!strcmp(mode, "writeback")) {
        *writethrough = false;
    } else if (!strcmp(mode, "unsafe")) {
        *writethrough = false;
        *flags |= BDRV_O_NO_FLUSH;
    } else if (!strcmp(mode, "writethrough")) {
        *writethrough = true;
    } else {
        return -1;
    }

    return 0;
}

static char *bdrv_child_get_parent_desc(BdrvChild *c)
{
    BlockDriverState *parent = c->opaque;
    return g_strdup(bdrv_get_device_or_node_name(parent));
}

static void bdrv_child_cb_drained_begin(BdrvChild *child)
{
    BlockDriverState *bs = child->opaque;
    bdrv_do_drained_begin_quiesce(bs, NULL, false);
}

static bool bdrv_child_cb_drained_poll(BdrvChild *child)
{
    BlockDriverState *bs = child->opaque;
    return bdrv_drain_poll(bs, false, NULL, false);
}

static void bdrv_child_cb_drained_end(BdrvChild *child,
                                      int *drained_end_counter)
{
    BlockDriverState *bs = child->opaque;
    bdrv_drained_end_no_poll(bs, drained_end_counter);
}

static int bdrv_child_cb_inactivate(BdrvChild *child)
{
    BlockDriverState *bs = child->opaque;
    assert(bs->open_flags & BDRV_O_INACTIVE);
    return 0;
}

static bool bdrv_child_cb_can_set_aio_ctx(BdrvChild *child, AioContext *ctx,
                                          GSList **ignore, Error **errp)
{
    BlockDriverState *bs = child->opaque;
    return bdrv_can_set_aio_context(bs, ctx, ignore, errp);
}

static void bdrv_child_cb_set_aio_ctx(BdrvChild *child, AioContext *ctx,
                                      GSList **ignore)
{
    BlockDriverState *bs = child->opaque;
    return bdrv_set_aio_context_ignore(bs, ctx, ignore);
}

/*
 * Returns the options and flags that a temporary snapshot should get, based on
 * the originally requested flags (the originally requested image will have
 * flags like a backing file)
 */
static void bdrv_temp_snapshot_options(int *child_flags, QDict *child_options,
                                       int parent_flags, QDict *parent_options)
{
    *child_flags = (parent_flags & ~BDRV_O_SNAPSHOT) | BDRV_O_TEMPORARY;

    /* For temporary files, unconditional cache=unsafe is fine */
    qdict_set_default_str(child_options, BDRV_OPT_CACHE_DIRECT, "off");
    qdict_set_default_str(child_options, BDRV_OPT_CACHE_NO_FLUSH, "on");

    /* Copy the read-only and discard options from the parent */
    qdict_copy_default(child_options, parent_options, BDRV_OPT_READ_ONLY);
    qdict_copy_default(child_options, parent_options, BDRV_OPT_DISCARD);

    /* aio=native doesn't work for cache.direct=off, so disable it for the
     * temporary snapshot */
    *child_flags &= ~BDRV_O_NATIVE_AIO;
}

static void bdrv_backing_attach(BdrvChild *c)
{
    BlockDriverState *parent = c->opaque;
    BlockDriverState *backing_hd = c->bs;

    assert(!parent->backing_blocker);
    error_setg(&parent->backing_blocker,
               "node is used as backing hd of '%s'",
               bdrv_get_device_or_node_name(parent));

    bdrv_refresh_filename(backing_hd);

    parent->open_flags &= ~BDRV_O_NO_BACKING;
    pstrcpy(parent->backing_file, sizeof(parent->backing_file),
            backing_hd->filename);
    pstrcpy(parent->backing_format, sizeof(parent->backing_format),
            backing_hd->drv ? backing_hd->drv->format_name : "");

    bdrv_op_block_all(backing_hd, parent->backing_blocker);
    /* Otherwise we won't be able to commit or stream */
    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_COMMIT_TARGET,
                    parent->backing_blocker);
    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_STREAM,
                    parent->backing_blocker);
    /*
     * We do backup in 3 ways:
     * 1. drive backup
     *    The target bs is new opened, and the source is top BDS
     * 2. blockdev backup
     *    Both the source and the target are top BDSes.
     * 3. internal backup(used for block replication)
     *    Both the source and the target are backing file
     *
     * In case 1 and 2, neither the source nor the target is the backing file.
     * In case 3, we will block the top BDS, so there is only one block job
     * for the top BDS and its backing chain.
     */
    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_SOURCE,
                    parent->backing_blocker);
    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET,
                    parent->backing_blocker);
}

static void bdrv_backing_detach(BdrvChild *c)
{
    BlockDriverState *parent = c->opaque;

    assert(parent->backing_blocker);
    bdrv_op_unblock_all(c->bs, parent->backing_blocker);
    error_free(parent->backing_blocker);
    parent->backing_blocker = NULL;
}

static int bdrv_backing_update_filename(BdrvChild *c, BlockDriverState *base,
                                        const char *filename, Error **errp)
{
    BlockDriverState *parent = c->opaque;
    bool read_only = bdrv_is_read_only(parent);
    int ret;

    if (read_only) {
        ret = bdrv_reopen_set_read_only(parent, false, errp);
        if (ret < 0) {
            return ret;
        }
    }

    ret = bdrv_change_backing_file(parent, filename,
                                   base->drv ? base->drv->format_name : "");
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Could not update backing file link");
    }

    if (read_only) {
        bdrv_reopen_set_read_only(parent, true, NULL);
    }

    return ret;
}

/*
 * Returns the options and flags that a generic child of a BDS should
 * get, based on the given options and flags for the parent BDS.
 */
static void bdrv_inherited_options(BdrvChildRole role, bool parent_is_format,
                                   int *child_flags, QDict *child_options,
                                   int parent_flags, QDict *parent_options)
{
    int flags = parent_flags;

    /*
     * First, decide whether to set, clear, or leave BDRV_O_PROTOCOL.
     * Generally, the question to answer is: Should this child be
     * format-probed by default?
     */

    /*
     * Pure and non-filtered data children of non-format nodes should
     * be probed by default (even when the node itself has BDRV_O_PROTOCOL
     * set).  This only affects a very limited set of drivers (namely
     * quorum and blkverify when this comment was written).
     * Force-clear BDRV_O_PROTOCOL then.
     */
    if (!parent_is_format &&
        (role & BDRV_CHILD_DATA) &&
        !(role & (BDRV_CHILD_METADATA | BDRV_CHILD_FILTERED)))
    {
        flags &= ~BDRV_O_PROTOCOL;
    }

    /*
     * All children of format nodes (except for COW children) and all
     * metadata children in general should never be format-probed.
     * Force-set BDRV_O_PROTOCOL then.
     */
    if ((parent_is_format && !(role & BDRV_CHILD_COW)) ||
        (role & BDRV_CHILD_METADATA))
    {
        flags |= BDRV_O_PROTOCOL;
    }

    /*
     * If the cache mode isn't explicitly set, inherit direct and no-flush from
     * the parent.
     */
    qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_DIRECT);
    qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_NO_FLUSH);
    qdict_copy_default(child_options, parent_options, BDRV_OPT_FORCE_SHARE);

    if (role & BDRV_CHILD_COW) {
        /* backing files are opened read-only by default */
        qdict_set_default_str(child_options, BDRV_OPT_READ_ONLY, "on");
        qdict_set_default_str(child_options, BDRV_OPT_AUTO_READ_ONLY, "off");
    } else {
        /* Inherit the read-only option from the parent if it's not set */
        qdict_copy_default(child_options, parent_options, BDRV_OPT_READ_ONLY);
        qdict_copy_default(child_options, parent_options,
                           BDRV_OPT_AUTO_READ_ONLY);
    }

    /*
     * bdrv_co_pdiscard() respects unmap policy for the parent, so we
     * can default to enable it on lower layers regardless of the
     * parent option.
     */
    qdict_set_default_str(child_options, BDRV_OPT_DISCARD, "unmap");

    /* Clear flags that only apply to the top layer */
    flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_COPY_ON_READ);

    if (role & BDRV_CHILD_METADATA) {
        flags &= ~BDRV_O_NO_IO;
    }
    if (role & BDRV_CHILD_COW) {
        flags &= ~BDRV_O_TEMPORARY;
    }

    *child_flags = flags;
}

static void bdrv_child_cb_attach(BdrvChild *child)
{
    BlockDriverState *bs = child->opaque;

    if (child->role & BDRV_CHILD_COW) {
        bdrv_backing_attach(child);
    }

    bdrv_apply_subtree_drain(child, bs);
}

static void bdrv_child_cb_detach(BdrvChild *child)
{
    BlockDriverState *bs = child->opaque;

    if (child->role & BDRV_CHILD_COW) {
        bdrv_backing_detach(child);
    }

    bdrv_unapply_subtree_drain(child, bs);
}

static int bdrv_child_cb_update_filename(BdrvChild *c, BlockDriverState *base,
                                         const char *filename, Error **errp)
{
    if (c->role & BDRV_CHILD_COW) {
        return bdrv_backing_update_filename(c, base, filename, errp);
    }
    return 0;
}

const BdrvChildClass child_of_bds = {
    .parent_is_bds   = true,
    .get_parent_desc = bdrv_child_get_parent_desc,
    .inherit_options = bdrv_inherited_options,
    .drained_begin   = bdrv_child_cb_drained_begin,
    .drained_poll    = bdrv_child_cb_drained_poll,
    .drained_end     = bdrv_child_cb_drained_end,
    .attach          = bdrv_child_cb_attach,
    .detach          = bdrv_child_cb_detach,
    .inactivate      = bdrv_child_cb_inactivate,
    .can_set_aio_ctx = bdrv_child_cb_can_set_aio_ctx,
    .set_aio_ctx     = bdrv_child_cb_set_aio_ctx,
    .update_filename = bdrv_child_cb_update_filename,
};

static int bdrv_open_flags(BlockDriverState *bs, int flags)
{
    int open_flags = flags;

    /*
     * Clear flags that are internal to the block layer before opening the
     * image.
     */
    open_flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_PROTOCOL);

    return open_flags;
}

static void update_flags_from_options(int *flags, QemuOpts *opts)
{
    *flags &= ~(BDRV_O_CACHE_MASK | BDRV_O_RDWR | BDRV_O_AUTO_RDONLY);

    if (qemu_opt_get_bool_del(opts, BDRV_OPT_CACHE_NO_FLUSH, false)) {
        *flags |= BDRV_O_NO_FLUSH;
    }

    if (qemu_opt_get_bool_del(opts, BDRV_OPT_CACHE_DIRECT, false)) {
        *flags |= BDRV_O_NOCACHE;
    }

    if (!qemu_opt_get_bool_del(opts, BDRV_OPT_READ_ONLY, false)) {
        *flags |= BDRV_O_RDWR;
    }

    if (qemu_opt_get_bool_del(opts, BDRV_OPT_AUTO_READ_ONLY, false)) {
        *flags |= BDRV_O_AUTO_RDONLY;
    }
}

static void update_options_from_flags(QDict *options, int flags)
{
    if (!qdict_haskey(options, BDRV_OPT_CACHE_DIRECT)) {
        qdict_put_bool(options, BDRV_OPT_CACHE_DIRECT, flags & BDRV_O_NOCACHE);
    }
    if (!qdict_haskey(options, BDRV_OPT_CACHE_NO_FLUSH)) {
        qdict_put_bool(options, BDRV_OPT_CACHE_NO_FLUSH,
                       flags & BDRV_O_NO_FLUSH);
    }
    if (!qdict_haskey(options, BDRV_OPT_READ_ONLY)) {
        qdict_put_bool(options, BDRV_OPT_READ_ONLY, !(flags & BDRV_O_RDWR));
    }
    if (!qdict_haskey(options, BDRV_OPT_AUTO_READ_ONLY)) {
        qdict_put_bool(options, BDRV_OPT_AUTO_READ_ONLY,
                       flags & BDRV_O_AUTO_RDONLY);
    }
}

static void bdrv_assign_node_name(BlockDriverState *bs,
                                  const char *node_name,
                                  Error **errp)
{
    char *gen_node_name = NULL;

    if (!node_name) {
        node_name = gen_node_name = id_generate(ID_BLOCK);
    } else if (!id_wellformed(node_name)) {
        /*
         * Check for empty string or invalid characters, but not if it is
         * generated (generated names use characters not available to the user)
         */
        error_setg(errp, "Invalid node name");
        return;
    }

    /* takes care of avoiding namespaces collisions */
    if (blk_by_name(node_name)) {
        error_setg(errp, "node-name=%s is conflicting with a device id",
                   node_name);
        goto out;
    }

    /* takes care of avoiding duplicates node names */
    if (bdrv_find_node(node_name)) {
        error_setg(errp, "Duplicate node name");
        goto out;
    }

    /* Make sure that the node name isn't truncated */
    if (strlen(node_name) >= sizeof(bs->node_name)) {
        error_setg(errp, "Node name too long");
        goto out;
    }

    /* copy node name into the bs and insert it into the graph list */
    pstrcpy(bs->node_name, sizeof(bs->node_name), node_name);
    QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs, node_list);
out:
    g_free(gen_node_name);
}

static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
                            const char *node_name, QDict *options,
                            int open_flags, Error **errp)
{
    Error *local_err = NULL;
    int i, ret;

    bdrv_assign_node_name(bs, node_name, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return -EINVAL;
    }

    bs->drv = drv;
    bs->read_only = !(bs->open_flags & BDRV_O_RDWR);
    bs->opaque = g_malloc0(drv->instance_size);

    if (drv->bdrv_file_open) {
        assert(!drv->bdrv_needs_filename || bs->filename[0]);
        ret = drv->bdrv_file_open(bs, options, open_flags, &local_err);
    } else if (drv->bdrv_open) {
        ret = drv->bdrv_open(bs, options, open_flags, &local_err);
    } else {
        ret = 0;
    }

    if (ret < 0) {
        if (local_err) {
            error_propagate(errp, local_err);
        } else if (bs->filename[0]) {
            error_setg_errno(errp, -ret, "Could not open '%s'", bs->filename);
        } else {
            error_setg_errno(errp, -ret, "Could not open image");
        }
        goto open_failed;
    }

    ret = refresh_total_sectors(bs, bs->total_sectors);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Could not refresh total sector count");
        return ret;
    }

    bdrv_refresh_limits(bs, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return -EINVAL;
    }

    assert(bdrv_opt_mem_align(bs) != 0);
    assert(bdrv_min_mem_align(bs) != 0);
    assert(is_power_of_2(bs->bl.request_alignment));

    for (i = 0; i < bs->quiesce_counter; i++) {
        if (drv->bdrv_co_drain_begin) {
            drv->bdrv_co_drain_begin(bs);
        }
    }

    return 0;
open_failed:
    bs->drv = NULL;
    if (bs->file != NULL) {
        bdrv_unref_child(bs, bs->file);
        bs->file = NULL;
    }
    g_free(bs->opaque);
    bs->opaque = NULL;
    return ret;
}

BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
                                       int flags, Error **errp)
{
    BlockDriverState *bs;
    int ret;

    bs = bdrv_new();
    bs->open_flags = flags;
    bs->explicit_options = qdict_new();
    bs->options = qdict_new();
    bs->opaque = NULL;

    update_options_from_flags(bs->options, flags);

    ret = bdrv_open_driver(bs, drv, node_name, bs->options, flags, errp);
    if (ret < 0) {
        qobject_unref(bs->explicit_options);
        bs->explicit_options = NULL;
        qobject_unref(bs->options);
        bs->options = NULL;
        bdrv_unref(bs);
        return NULL;
    }

    return bs;
}

QemuOptsList bdrv_runtime_opts = {
    .name = "bdrv_common",
    .head = QTAILQ_HEAD_INITIALIZER(bdrv_runtime_opts.head),
    .desc = {
        {
            .name = "node-name",
            .type = QEMU_OPT_STRING,
            .help = "Node name of the block device node",
        },
        {
            .name = "driver",
            .type = QEMU_OPT_STRING,
            .help = "Block driver to use for the node",
        },
        {
            .name = BDRV_OPT_CACHE_DIRECT,
            .type = QEMU_OPT_BOOL,
            .help = "Bypass software writeback cache on the host",
        },
        {
            .name = BDRV_OPT_CACHE_NO_FLUSH,
            .type = QEMU_OPT_BOOL,
            .help = "Ignore flush requests",
        },
        {
            .name = BDRV_OPT_READ_ONLY,
            .type = QEMU_OPT_BOOL,
            .help = "Node is opened in read-only mode",
        },
        {
            .name = BDRV_OPT_AUTO_READ_ONLY,
            .type = QEMU_OPT_BOOL,
            .help = "Node can become read-only if opening read-write fails",
        },
        {
            .name = "detect-zeroes",
            .type = QEMU_OPT_STRING,
            .help = "try to optimize zero writes (off, on, unmap)",
        },
        {
            .name = BDRV_OPT_DISCARD,
            .type = QEMU_OPT_STRING,
            .help = "discard operation (ignore/off, unmap/on)",
        },
        {
            .name = BDRV_OPT_FORCE_SHARE,
            .type = QEMU_OPT_BOOL,
            .help = "always accept other writers (default: off)",
        },
        { /* end of list */ }
    },
};

QemuOptsList bdrv_create_opts_simple = {
    .name = "simple-create-opts",
    .head = QTAILQ_HEAD_INITIALIZER(bdrv_create_opts_simple.head),
    .desc = {
        {
            .name = BLOCK_OPT_SIZE,
            .type = QEMU_OPT_SIZE,
            .help = "Virtual disk size"
        },
        {
            .name = BLOCK_OPT_PREALLOC,
            .type = QEMU_OPT_STRING,
            .help = "Preallocation mode (allowed values: off)"
        },
        { /* end of list */ }
    }
};

/*
 * Common part for opening disk images and files
 *
 * Removes all processed options from *options.
 */
static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
                            QDict *options, Error **errp)
{
    int ret, open_flags;
    const char *filename;
    const char *driver_name = NULL;
    const char *node_name = NULL;
    const char *discard;
    QemuOpts *opts;
    BlockDriver *drv;
    Error *local_err = NULL;

    assert(bs->file == NULL);
    assert(options != NULL && bs->options != options);

    opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
    qemu_opts_absorb_qdict(opts, options, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto fail_opts;
    }

    update_flags_from_options(&bs->open_flags, opts);

    driver_name = qemu_opt_get(opts, "driver");
    drv = bdrv_find_format(driver_name);
    assert(drv != NULL);

    bs->force_share = qemu_opt_get_bool(opts, BDRV_OPT_FORCE_SHARE, false);

    if (bs->force_share && (bs->open_flags & BDRV_O_RDWR)) {
        error_setg(errp,
                   BDRV_OPT_FORCE_SHARE
                   "=on can only be used with read-only images");
        ret = -EINVAL;
        goto fail_opts;
    }

    if (file != NULL) {
        bdrv_refresh_filename(blk_bs(file));
        filename = blk_bs(file)->filename;
    } else {
        /*
         * Caution: while qdict_get_try_str() is fine, getting
         * non-string types would require more care.  When @options
         * come from -blockdev or blockdev_add, its members are typed
         * according to the QAPI schema, but when they come from
         * -drive, they're all QString.
         */
        filename = qdict_get_try_str(options, "filename");
    }

    if (drv->bdrv_needs_filename && (!filename || !filename[0])) {
        error_setg(errp, "The '%s' block driver requires a file name",
                   drv->format_name);
        ret = -EINVAL;
        goto fail_opts;
    }

    trace_bdrv_open_common(bs, filename ?: "", bs->open_flags,
                           drv->format_name);

    bs->read_only = !(bs->open_flags & BDRV_O_RDWR);

    if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
        if (!bs->read_only && bdrv_is_whitelisted(drv, true)) {
            ret = bdrv_apply_auto_read_only(bs, NULL, NULL);
        } else {
            ret = -ENOTSUP;
        }
        if (ret < 0) {
            error_setg(errp,
                       !bs->read_only && bdrv_is_whitelisted(drv, true)
                       ? "Driver '%s' can only be used for read-only devices"
                       : "Driver '%s' is not whitelisted",
                       drv->format_name);
            goto fail_opts;
        }
    }

    /* bdrv_new() and bdrv_close() make it so */
    assert(atomic_read(&bs->copy_on_read) == 0);

    if (bs->open_flags & BDRV_O_COPY_ON_READ) {
        if (!bs->read_only) {
            bdrv_enable_copy_on_read(bs);
        } else {
            error_setg(errp, "Can't use copy-on-read on read-only device");
            ret = -EINVAL;
            goto fail_opts;
        }
    }

    discard = qemu_opt_get(opts, BDRV_OPT_DISCARD);
    if (discard != NULL) {
        if (bdrv_parse_discard_flags(discard, &bs->open_flags) != 0) {
            error_setg(errp, "Invalid discard option");
            ret = -EINVAL;
            goto fail_opts;
        }
    }

    bs->detect_zeroes =
        bdrv_parse_detect_zeroes(opts, bs->open_flags, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto fail_opts;
    }

    if (filename != NULL) {
        pstrcpy(bs->filename, sizeof(bs->filename), filename);
    } else {
        bs->filename[0] = '\0';
    }
    pstrcpy(bs->exact_filename, sizeof(bs->exact_filename), bs->filename);

    /* Open the image, either directly or using a protocol */
    open_flags = bdrv_open_flags(bs, bs->open_flags);
    node_name = qemu_opt_get(opts, "node-name");

    assert(!drv->bdrv_file_open || file == NULL);
    ret = bdrv_open_driver(bs, drv, node_name, options, open_flags, errp);
    if (ret < 0) {
        goto fail_opts;
    }

    qemu_opts_del(opts);
    return 0;

fail_opts:
    qemu_opts_del(opts);
    return ret;
}

static QDict *parse_json_filename(const char *filename, Error **errp)
{
    QObject *options_obj;
    QDict *options;
    int ret;

    ret = strstart(filename, "json:", &filename);
    assert(ret);

    options_obj = qobject_from_json(filename, errp);
    if (!options_obj) {
        error_prepend(errp, "Could not parse the JSON options: ");
        return NULL;
    }

    options = qobject_to(QDict, options_obj);
    if (!options) {
        qobject_unref(options_obj);
        error_setg(errp, "Invalid JSON object given");
        return NULL;
    }

    qdict_flatten(options);

    return options;
}

static void parse_json_protocol(QDict *options, const char **pfilename,
                                Error **errp)
{
    QDict *json_options;
    Error *local_err = NULL;

    /* Parse json: pseudo-protocol */
    if (!*pfilename || !g_str_has_prefix(*pfilename, "json:")) {
        return;
    }

    json_options = parse_json_filename(*pfilename, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    /* Options given in the filename have lower priority than options
     * specified directly */
    qdict_join(options, json_options, false);
    qobject_unref(json_options);
    *pfilename = NULL;
}

/*
 * Fills in default options for opening images and converts the legacy
 * filename/flags pair to option QDict entries.
 * The BDRV_O_PROTOCOL flag in *flags will be set or cleared accordingly if a
 * block driver has been specified explicitly.
 */
static int bdrv_fill_options(QDict **options, const char *filename,
                             int *flags, Error **errp)
{
    const char *drvname;
    bool protocol = *flags & BDRV_O_PROTOCOL;
    bool parse_filename = false;
    BlockDriver *drv = NULL;
    Error *local_err = NULL;

    /*
     * Caution: while qdict_get_try_str() is fine, getting non-string
     * types would require more care.  When @options come from
     * -blockdev or blockdev_add, its members are typed according to
     * the QAPI schema, but when they come from -drive, they're all
     * QString.
     */
    drvname = qdict_get_try_str(*options, "driver");
    if (drvname) {
        drv = bdrv_find_format(drvname);
        if (!drv) {
            error_setg(errp, "Unknown driver '%s'", drvname);
            return -ENOENT;
        }
        /* If the user has explicitly specified the driver, this choice should
         * override the BDRV_O_PROTOCOL flag */
        protocol = drv->bdrv_file_open;
    }

    if (protocol) {
        *flags |= BDRV_O_PROTOCOL;
    } else {
        *flags &= ~BDRV_O_PROTOCOL;
    }

    /* Translate cache options from flags into options */
    update_options_from_flags(*options, *flags);

    /* Fetch the file name from the options QDict if necessary */
    if (protocol && filename) {
        if (!qdict_haskey(*options, "filename")) {
            qdict_put_str(*options, "filename", filename);
            parse_filename = true;
        } else {
            error_setg(errp, "Can't specify 'file' and 'filename' options at "
                             "the same time");
            return -EINVAL;
        }
    }

    /* Find the right block driver */
    /* See cautionary note on accessing @options above */
    filename = qdict_get_try_str(*options, "filename");

    if (!drvname && protocol) {
        if (filename) {
            drv = bdrv_find_protocol(filename, parse_filename, errp);
            if (!drv) {
                return -EINVAL;
            }

            drvname = drv->format_name;
            qdict_put_str(*options, "driver", drvname);
        } else {
            error_setg(errp, "Must specify either driver or file");
            return -EINVAL;
        }
    }

    assert(drv || !protocol);

    /* Driver-specific filename parsing */
    if (drv && drv->bdrv_parse_filename && parse_filename) {
        drv->bdrv_parse_filename(filename, *options, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            return -EINVAL;
        }

        if (!drv->bdrv_needs_filename) {
            qdict_del(*options, "filename");
        }
    }

    return 0;
}

static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q,
                                 uint64_t perm, uint64_t shared,
                                 GSList *ignore_children,
                                 bool *tighten_restrictions, Error **errp);
static void bdrv_child_abort_perm_update(BdrvChild *c);
static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared);

typedef struct BlockReopenQueueEntry {
     bool prepared;
     bool perms_checked;
     BDRVReopenState state;
     QTAILQ_ENTRY(BlockReopenQueueEntry) entry;
} BlockReopenQueueEntry;

/*
 * Return the flags that @bs will have after the reopens in @q have
 * successfully completed. If @q is NULL (or @bs is not contained in @q),
 * return the current flags.
 */
static int bdrv_reopen_get_flags(BlockReopenQueue *q, BlockDriverState *bs)
{
    BlockReopenQueueEntry *entry;

    if (q != NULL) {
        QTAILQ_FOREACH(entry, q, entry) {
            if (entry->state.bs == bs) {
                return entry->state.flags;
            }
        }
    }

    return bs->open_flags;
}

/* Returns whether the image file can be written to after the reopen queue @q
 * has been successfully applied, or right now if @q is NULL. */
static bool bdrv_is_writable_after_reopen(BlockDriverState *bs,
                                          BlockReopenQueue *q)
{
    int flags = bdrv_reopen_get_flags(q, bs);

    return (flags & (BDRV_O_RDWR | BDRV_O_INACTIVE)) == BDRV_O_RDWR;
}

/*
 * Return whether the BDS can be written to.  This is not necessarily
 * the same as !bdrv_is_read_only(bs), as inactivated images may not
 * be written to but do not count as read-only images.
 */
bool bdrv_is_writable(BlockDriverState *bs)
{
    return bdrv_is_writable_after_reopen(bs, NULL);
}

static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs,
                            BdrvChild *c, BdrvChildRole role,
                            BlockReopenQueue *reopen_queue,
                            uint64_t parent_perm, uint64_t parent_shared,
                            uint64_t *nperm, uint64_t *nshared)
{
    assert(bs->drv && bs->drv->bdrv_child_perm);
    bs->drv->bdrv_child_perm(bs, c, role, reopen_queue,
                             parent_perm, parent_shared,
                             nperm, nshared);
    /* TODO Take force_share from reopen_queue */
    if (child_bs && child_bs->force_share) {
        *nshared = BLK_PERM_ALL;
    }
}

/*
 * Check whether permissions on this node can be changed in a way that
 * @cumulative_perms and @cumulative_shared_perms are the new cumulative
 * permissions of all its parents. This involves checking whether all necessary
 * permission changes to child nodes can be performed.
 *
 * Will set *tighten_restrictions to true if and only if new permissions have to
 * be taken or currently shared permissions are to be unshared.  Otherwise,
 * errors are not fatal as long as the caller accepts that the restrictions
 * remain tighter than they need to be.  The caller still has to abort the
 * transaction.
 * @tighten_restrictions cannot be used together with @q: When reopening, we may
 * encounter fatal errors even though no restrictions are to be tightened.  For
 * example, changing a node from RW to RO will fail if the WRITE permission is
 * to be kept.
 *
 * A call to this function must always be followed by a call to bdrv_set_perm()
 * or bdrv_abort_perm_update().
 */
static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
                           uint64_t cumulative_perms,
                           uint64_t cumulative_shared_perms,
                           GSList *ignore_children,
                           bool *tighten_restrictions, Error **errp)
{
    BlockDriver *drv = bs->drv;
    BdrvChild *c;
    int ret;

    assert(!q || !tighten_restrictions);

    if (tighten_restrictions) {
        uint64_t current_perms, current_shared;
        uint64_t added_perms, removed_shared_perms;

        bdrv_get_cumulative_perm(bs, &current_perms, &current_shared);

        added_perms = cumulative_perms & ~current_perms;
        removed_shared_perms = current_shared & ~cumulative_shared_perms;

        *tighten_restrictions = added_perms || removed_shared_perms;
    }

    /* Write permissions never work with read-only images */
    if ((cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) &&
        !bdrv_is_writable_after_reopen(bs, q))
    {
        if (!bdrv_is_writable_after_reopen(bs, NULL)) {
            error_setg(errp, "Block node is read-only");
        } else {
            uint64_t current_perms, current_shared;
            bdrv_get_cumulative_perm(bs, &current_perms, &current_shared);
            if (current_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) {
                error_setg(errp, "Cannot make block node read-only, there is "
                           "a writer on it");
            } else {
                error_setg(errp, "Cannot make block node read-only and create "
                           "a writer on it");
            }
        }

        return -EPERM;
    }

    /* Check this node */
    if (!drv) {
        return 0;
    }

    if (drv->bdrv_check_perm) {
        return drv->bdrv_check_perm(bs, cumulative_perms,
                                    cumulative_shared_perms, errp);
    }

    /* Drivers that never have children can omit .bdrv_child_perm() */
    if (!drv->bdrv_child_perm) {
        assert(QLIST_EMPTY(&bs->children));
        return 0;
    }

    /* Check all children */
    QLIST_FOREACH(c, &bs->children, next) {
        uint64_t cur_perm, cur_shared;
        bool child_tighten_restr;

        bdrv_child_perm(bs, c->bs, c, c->role, q,
                        cumulative_perms, cumulative_shared_perms,
                        &cur_perm, &cur_shared);
        ret = bdrv_child_check_perm(c, q, cur_perm, cur_shared, ignore_children,
                                    tighten_restrictions ? &child_tighten_restr
                                                         : NULL,
                                    errp);
        if (tighten_restrictions) {
            *tighten_restrictions |= child_tighten_restr;
        }
        if (ret < 0) {
            return ret;
        }
    }

    return 0;
}

/*
 * Notifies drivers that after a previous bdrv_check_perm() call, the
 * permission update is not performed and any preparations made for it (e.g.
 * taken file locks) need to be undone.
 *
 * This function recursively notifies all child nodes.
 */
static void bdrv_abort_perm_update(BlockDriverState *bs)
{
    BlockDriver *drv = bs->drv;
    BdrvChild *c;

    if (!drv) {
        return;
    }

    if (drv->bdrv_abort_perm_update) {
        drv->bdrv_abort_perm_update(bs);
    }

    QLIST_FOREACH(c, &bs->children, next) {
        bdrv_child_abort_perm_update(c);
    }
}

static void bdrv_set_perm(BlockDriverState *bs, uint64_t cumulative_perms,
                          uint64_t cumulative_shared_perms)
{
    BlockDriver *drv = bs->drv;
    BdrvChild *c;

    if (!drv) {
        return;
    }

    /* Update this node */
    if (drv->bdrv_set_perm) {
        drv->bdrv_set_perm(bs, cumulative_perms, cumulative_shared_perms);
    }

    /* Drivers that never have children can omit .bdrv_child_perm() */
    if (!drv->bdrv_child_perm) {
        assert(QLIST_EMPTY(&bs->children));
        return;
    }

    /* Update all children */
    QLIST_FOREACH(c, &bs->children, next) {
        uint64_t cur_perm, cur_shared;
        bdrv_child_perm(bs, c->bs, c, c->role, NULL,
                        cumulative_perms, cumulative_shared_perms,
                        &cur_perm, &cur_shared);
        bdrv_child_set_perm(c, cur_perm, cur_shared);
    }
}

void bdrv_get_cumulative_perm(BlockDriverState *bs, uint64_t *perm,
                              uint64_t *shared_perm)
{
    BdrvChild *c;
    uint64_t cumulative_perms = 0;
    uint64_t cumulative_shared_perms = BLK_PERM_ALL;

    QLIST_FOREACH(c, &bs->parents, next_parent) {
        cumulative_perms |= c->perm;
        cumulative_shared_perms &= c->shared_perm;
    }

    *perm = cumulative_perms;
    *shared_perm = cumulative_shared_perms;
}

static char *bdrv_child_user_desc(BdrvChild *c)
{
    if (c->klass->get_parent_desc) {
        return c->klass->get_parent_desc(c);
    }

    return g_strdup("another user");
}

char *bdrv_perm_names(uint64_t perm)
{
    struct perm_name {
        uint64_t perm;
        const char *name;
    } permissions[] = {
        { BLK_PERM_CONSISTENT_READ, "consistent read" },
        { BLK_PERM_WRITE,           "write" },
        { BLK_PERM_WRITE_UNCHANGED, "write unchanged" },
        { BLK_PERM_RESIZE,          "resize" },
        { BLK_PERM_GRAPH_MOD,       "change children" },
        { 0, NULL }
    };

    GString *result = g_string_sized_new(30);
    struct perm_name *p;

    for (p = permissions; p->name; p++) {
        if (perm & p->perm) {
            if (result->len > 0) {
                g_string_append(result, ", ");
            }
            g_string_append(result, p->name);
        }
    }

    return g_string_free(result, FALSE);
}

/*
 * Checks whether a new reference to @bs can be added if the new user requires
 * @new_used_perm/@new_shared_perm as its permissions. If @ignore_children is
 * set, the BdrvChild objects in this list are ignored in the calculations;
 * this allows checking permission updates for an existing reference.
 *
 * See bdrv_check_perm() for the semantics of @tighten_restrictions.
 *
 * Needs to be followed by a call to either bdrv_set_perm() or
 * bdrv_abort_perm_update(). */
static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q,
                                  uint64_t new_used_perm,
                                  uint64_t new_shared_perm,
                                  GSList *ignore_children,
                                  bool *tighten_restrictions,
                                  Error **errp)
{
    BdrvChild *c;
    uint64_t cumulative_perms = new_used_perm;
    uint64_t cumulative_shared_perms = new_shared_perm;

    assert(!q || !tighten_restrictions);

    /* There is no reason why anyone couldn't tolerate write_unchanged */
    assert(new_shared_perm & BLK_PERM_WRITE_UNCHANGED);

    QLIST_FOREACH(c, &bs->parents, next_parent) {
        if (g_slist_find(ignore_children, c)) {
            continue;
        }

        if ((new_used_perm & c->shared_perm) != new_used_perm) {
            char *user = bdrv_child_user_desc(c);
            char *perm_names = bdrv_perm_names(new_used_perm & ~c->shared_perm);

            if (tighten_restrictions) {
                *tighten_restrictions = true;
            }

            error_setg(errp, "Conflicts with use by %s as '%s', which does not "
                             "allow '%s' on %s",
                       user, c->name, perm_names, bdrv_get_node_name(c->bs));
            g_free(user);
            g_free(perm_names);
            return -EPERM;
        }

        if ((c->perm & new_shared_perm) != c->perm) {
            char *user = bdrv_child_user_desc(c);
            char *perm_names = bdrv_perm_names(c->perm & ~new_shared_perm);

            if (tighten_restrictions) {
                *tighten_restrictions = true;
            }

            error_setg(errp, "Conflicts with use by %s as '%s', which uses "
                             "'%s' on %s",
                       user, c->name, perm_names, bdrv_get_node_name(c->bs));
            g_free(user);
            g_free(perm_names);
            return -EPERM;
        }

        cumulative_perms |= c->perm;
        cumulative_shared_perms &= c->shared_perm;
    }

    return bdrv_check_perm(bs, q, cumulative_perms, cumulative_shared_perms,
                           ignore_children, tighten_restrictions, errp);
}

/* Needs to be followed by a call to either bdrv_child_set_perm() or
 * bdrv_child_abort_perm_update(). */
static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q,
                                 uint64_t perm, uint64_t shared,
                                 GSList *ignore_children,
                                 bool *tighten_restrictions, Error **errp)
{
    int ret;

    ignore_children = g_slist_prepend(g_slist_copy(ignore_children), c);
    ret = bdrv_check_update_perm(c->bs, q, perm, shared, ignore_children,
                                 tighten_restrictions, errp);
    g_slist_free(ignore_children);

    if (ret < 0) {
        return ret;
    }

    if (!c->has_backup_perm) {
        c->has_backup_perm = true;
        c->backup_perm = c->perm;
        c->backup_shared_perm = c->shared_perm;
    }
    /*
     * Note: it's OK if c->has_backup_perm was already set, as we can find the
     * same child twice during check_perm procedure
     */

    c->perm = perm;
    c->shared_perm = shared;

    return 0;
}

static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared)
{
    uint64_t cumulative_perms, cumulative_shared_perms;

    c->has_backup_perm = false;

    c->perm = perm;
    c->shared_perm = shared;

    bdrv_get_cumulative_perm(c->bs, &cumulative_perms,
                             &cumulative_shared_perms);
    bdrv_set_perm(c->bs, cumulative_perms, cumulative_shared_perms);
}

static void bdrv_child_abort_perm_update(BdrvChild *c)
{
    if (c->has_backup_perm) {
        c->perm = c->backup_perm;
        c->shared_perm = c->backup_shared_perm;
        c->has_backup_perm = false;
    }

    bdrv_abort_perm_update(c->bs);
}

int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
                            Error **errp)
{
    Error *local_err = NULL;
    int ret;
    bool tighten_restrictions;

    ret = bdrv_child_check_perm(c, NULL, perm, shared, NULL,
                                &tighten_restrictions, &local_err);
    if (ret < 0) {
        bdrv_child_abort_perm_update(c);
        if (tighten_restrictions) {
            error_propagate(errp, local_err);
        } else {
            /*
             * Our caller may intend to only loosen restrictions and
             * does not expect this function to fail.  Errors are not
             * fatal in such a case, so we can just hide them from our
             * caller.
             */
            error_free(local_err);
            ret = 0;
        }
        return ret;
    }

    bdrv_child_set_perm(c, perm, shared);

    return 0;
}

int bdrv_child_refresh_perms(BlockDriverState *bs, BdrvChild *c, Error **errp)
{
    uint64_t parent_perms, parent_shared;
    uint64_t perms, shared;

    bdrv_get_cumulative_perm(bs, &parent_perms, &parent_shared);
    bdrv_child_perm(bs, c->bs, c, c->role, NULL,
                    parent_perms, parent_shared, &perms, &shared);

    return bdrv_child_try_set_perm(c, perms, shared, errp);
}

/*
 * Default implementation for .bdrv_child_perm() for block filters:
 * Forward CONSISTENT_READ, WRITE, WRITE_UNCHANGED, and RESIZE to the
 * filtered child.
 */
static void bdrv_filter_default_perms(BlockDriverState *bs, BdrvChild *c,
                                      BdrvChildRole role,
                                      BlockReopenQueue *reopen_queue,
                                      uint64_t perm, uint64_t shared,
                                      uint64_t *nperm, uint64_t *nshared)
{
    *nperm = perm & DEFAULT_PERM_PASSTHROUGH;
    *nshared = (shared & DEFAULT_PERM_PASSTHROUGH) | DEFAULT_PERM_UNCHANGED;
}

static void bdrv_default_perms_for_cow(BlockDriverState *bs, BdrvChild *c,
                                       BdrvChildRole role,
                                       BlockReopenQueue *reopen_queue,
                                       uint64_t perm, uint64_t shared,
                                       uint64_t *nperm, uint64_t *nshared)
{
    assert(role & BDRV_CHILD_COW);

    /*
     * We want consistent read from backing files if the parent needs it.
     * No other operations are performed on backing files.
     */
    perm &= BLK_PERM_CONSISTENT_READ;

    /*
     * If the parent can deal with changing data, we're okay with a
     * writable and resizable backing file.
     * TODO Require !(perm & BLK_PERM_CONSISTENT_READ), too?
     */
    if (shared & BLK_PERM_WRITE) {
        shared = BLK_PERM_WRITE | BLK_PERM_RESIZE;
    } else {
        shared = 0;
    }

    shared |= BLK_PERM_CONSISTENT_READ | BLK_PERM_GRAPH_MOD |
              BLK_PERM_WRITE_UNCHANGED;

    if (bs->open_flags & BDRV_O_INACTIVE) {
        shared |= BLK_PERM_WRITE | BLK_PERM_RESIZE;
    }

    *nperm = perm;
    *nshared = shared;
}

static void bdrv_default_perms_for_storage(BlockDriverState *bs, BdrvChild *c,
                                           BdrvChildRole role,
                                           BlockReopenQueue *reopen_queue,
                                           uint64_t perm, uint64_t shared,
                                           uint64_t *nperm, uint64_t *nshared)
{
    int flags;

    assert(role & (BDRV_CHILD_METADATA | BDRV_CHILD_DATA));

    flags = bdrv_reopen_get_flags(reopen_queue, bs);

    /*
     * Apart from the modifications below, the same permissions are
     * forwarded and left alone as for filters
     */
    bdrv_filter_default_perms(bs, c, role, reopen_queue,
                              perm, shared, &perm, &shared);

    if (role & BDRV_CHILD_METADATA) {
        /* Format drivers may touch metadata even if the guest doesn't write */
        if (bdrv_is_writable_after_reopen(bs, reopen_queue)) {
            perm |= BLK_PERM_WRITE | BLK_PERM_RESIZE;
        }

        /*
         * bs->file always needs to be consistent because of the
         * metadata. We can never allow other users to resize or write
         * to it.
         */
        if (!(flags & BDRV_O_NO_IO)) {
            perm |= BLK_PERM_CONSISTENT_READ;
        }
        shared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
    }

    if (role & BDRV_CHILD_DATA) {
        /*
         * Technically, everything in this block is a subset of the
         * BDRV_CHILD_METADATA path taken above, and so this could
         * be an "else if" branch.  However, that is not obvious, and
         * this function is not performance critical, therefore we let
         * this be an independent "if".
         */

        /*
         * We cannot allow other users to resize the file because the
         * format driver might have some assumptions about the size
         * (e.g. because it is stored in metadata, or because the file
         * is split into fixed-size data files).
         */
        shared &= ~BLK_PERM_RESIZE;

        /*
         * WRITE_UNCHANGED often cannot be performed as such on the
         * data file.  For example, the qcow2 driver may still need to
         * write copied clusters on copy-on-read.
         */
        if (perm & BLK_PERM_WRITE_UNCHANGED) {
            perm |= BLK_PERM_WRITE;
        }

        /*
         * If the data file is written to, the format driver may
         * expect to be able to resize it by writing beyond the EOF.
         */
        if (perm & BLK_PERM_WRITE) {
            perm |= BLK_PERM_RESIZE;
        }
    }

    if (bs->open_flags & BDRV_O_INACTIVE) {
        shared |= BLK_PERM_WRITE | BLK_PERM_RESIZE;
    }

    *nperm = perm;
    *nshared = shared;
}

void bdrv_default_perms(BlockDriverState *bs, BdrvChild *c,
                        BdrvChildRole role, BlockReopenQueue *reopen_queue,
                        uint64_t perm, uint64_t shared,
                        uint64_t *nperm, uint64_t *nshared)
{
    if (role & BDRV_CHILD_FILTERED) {
        assert(!(role & (BDRV_CHILD_DATA | BDRV_CHILD_METADATA |
                         BDRV_CHILD_COW)));
        bdrv_filter_default_perms(bs, c, role, reopen_queue,
                                  perm, shared, nperm, nshared);
    } else if (role & BDRV_CHILD_COW) {
        assert(!(role & (BDRV_CHILD_DATA | BDRV_CHILD_METADATA)));
        bdrv_default_perms_for_cow(bs, c, role, reopen_queue,
                                   perm, shared, nperm, nshared);
    } else if (role & (BDRV_CHILD_METADATA | BDRV_CHILD_DATA)) {
        bdrv_default_perms_for_storage(bs, c, role, reopen_queue,
                                       perm, shared, nperm, nshared);
    } else {
        g_assert_not_reached();
    }
}

uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm)
{
    static const uint64_t permissions[] = {
        [BLOCK_PERMISSION_CONSISTENT_READ]  = BLK_PERM_CONSISTENT_READ,
        [BLOCK_PERMISSION_WRITE]            = BLK_PERM_WRITE,
        [BLOCK_PERMISSION_WRITE_UNCHANGED]  = BLK_PERM_WRITE_UNCHANGED,
        [BLOCK_PERMISSION_RESIZE]           = BLK_PERM_RESIZE,
        [BLOCK_PERMISSION_GRAPH_MOD]        = BLK_PERM_GRAPH_MOD,
    };

    QEMU_BUILD_BUG_ON(ARRAY_SIZE(permissions) != BLOCK_PERMISSION__MAX);
    QEMU_BUILD_BUG_ON(1UL << ARRAY_SIZE(permissions) != BLK_PERM_ALL + 1);

    assert(qapi_perm < BLOCK_PERMISSION__MAX);

    return permissions[qapi_perm];
}

static void bdrv_replace_child_noperm(BdrvChild *child,
                                      BlockDriverState *new_bs)
{
    BlockDriverState *old_bs = child->bs;
    int new_bs_quiesce_counter;
    int drain_saldo;

    assert(!child->frozen);

    if (old_bs && new_bs) {
        assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
    }

    new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
    drain_saldo = new_bs_quiesce_counter - child->parent_quiesce_counter;

    /*
     * If the new child node is drained but the old one was not, flush
     * all outstanding requests to the old child node.
     */
    while (drain_saldo > 0 && child->klass->drained_begin) {
        bdrv_parent_drained_begin_single(child, true);
        drain_saldo--;
    }

    if (old_bs) {
        /* Detach first so that the recursive drain sections coming from @child
         * are already gone and we only end the drain sections that came from
         * elsewhere. */
        if (child->klass->detach) {
            child->klass->detach(child);
        }
        QLIST_REMOVE(child, next_parent);
    }

    child->bs = new_bs;

    if (new_bs) {
        QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);

        /*
         * Detaching the old node may have led to the new node's
         * quiesce_counter having been decreased.  Not a problem, we
         * just need to recognize this here and then invoke
         * drained_end appropriately more often.
         */
        assert(new_bs->quiesce_counter <= new_bs_quiesce_counter);
        drain_saldo += new_bs->quiesce_counter - new_bs_quiesce_counter;

        /* Attach only after starting new drained sections, so that recursive
         * drain sections coming from @child don't get an extra .drained_begin
         * callback. */
        if (child->klass->attach) {
            child->klass->attach(child);
        }
    }

    /*
     * If the old child node was drained but the new one is not, allow
     * requests to come in only after the new node has been attached.
     */
    while (drain_saldo < 0 && child->klass->drained_end) {
        bdrv_parent_drained_end_single(child);
        drain_saldo++;
    }
}

/*
 * Updates @child to change its reference to point to @new_bs, including
 * checking and applying the necessary permisson updates both to the old node
 * and to @new_bs.
 *
 * NULL is passed as @new_bs for removing the reference before freeing @child.
 *
 * If @new_bs is not NULL, bdrv_check_perm() must be called beforehand, as this
 * function uses bdrv_set_perm() to update the permissions according to the new
 * reference that @new_bs gets.
 */
static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
{
    BlockDriverState *old_bs = child->bs;
    uint64_t perm, shared_perm;

    bdrv_replace_child_noperm(child, new_bs);

    /*
     * Start with the new node's permissions.  If @new_bs is a (direct
     * or indirect) child of @old_bs, we must complete the permission
     * update on @new_bs before we loosen the restrictions on @old_bs.
     * Otherwise, bdrv_check_perm() on @old_bs would re-initiate
     * updating the permissions of @new_bs, and thus not purely loosen
     * restrictions.
     */
    if (new_bs) {
        bdrv_get_cumulative_perm(new_bs, &perm, &shared_perm);
        bdrv_set_perm(new_bs, perm, shared_perm);
    }

    if (old_bs) {
        /* Update permissions for old node. This is guaranteed to succeed
         * because we're just taking a parent away, so we're loosening
         * restrictions. */
        bool tighten_restrictions;
        int ret;

        bdrv_get_cumulative_perm(old_bs, &perm, &shared_perm);
        ret = bdrv_check_perm(old_bs, NULL, perm, shared_perm, NULL,
                              &tighten_restrictions, NULL);
        assert(tighten_restrictions == false);
        if (ret < 0) {
            /* We only tried to loosen restrictions, so errors are not fatal */
            bdrv_abort_perm_update(old_bs);
        } else {
            bdrv_set_perm(old_bs, perm, shared_perm);
        }

        /* When the parent requiring a non-default AioContext is removed, the
         * node moves back to the main AioContext */
        bdrv_try_set_aio_context(old_bs, qemu_get_aio_context(), NULL);
    }
}

/*
 * This function steals the reference to child_bs from the caller.
 * That reference is later dropped by bdrv_root_unref_child().
 *
 * On failure NULL is returned, errp is set and the reference to
 * child_bs is also dropped.
 *
 * The caller must hold the AioContext lock @child_bs, but not that of @ctx
 * (unless @child_bs is already in @ctx).
 */
BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
                                  const char *child_name,
                                  const BdrvChildClass *child_class,
                                  BdrvChildRole child_role,
                                  AioContext *ctx,
                                  uint64_t perm, uint64_t shared_perm,
                                  void *opaque, Error **errp)
{
    BdrvChild *child;
    Error *local_err = NULL;
    int ret;

    ret = bdrv_check_update_perm(child_bs, NULL, perm, shared_perm, NULL, NULL,
                                 errp);
    if (ret < 0) {
        bdrv_abort_perm_update(child_bs);
        bdrv_unref(child_bs);
        return NULL;
    }

    child = g_new(BdrvChild, 1);
    *child = (BdrvChild) {
        .bs             = NULL,
        .name           = g_strdup(child_name),
        .klass          = child_class,
        .role           = child_role,
        .perm           = perm,
        .shared_perm    = shared_perm,
        .opaque         = opaque,
    };

    /* If the AioContexts don't match, first try to move the subtree of
     * child_bs into the AioContext of the new parent. If this doesn't work,
     * try moving the parent into the AioContext of child_bs instead. */
    if (bdrv_get_aio_context(child_bs) != ctx) {
        ret = bdrv_try_set_aio_context(child_bs, ctx, &local_err);
        if (ret < 0 && child_class->can_set_aio_ctx) {
            GSList *ignore = g_slist_prepend(NULL, child);
            ctx = bdrv_get_aio_context(child_bs);
            if (child_class->can_set_aio_ctx(child, ctx, &ignore, NULL)) {
                error_free(local_err);
                ret = 0;
                g_slist_free(ignore);
                ignore = g_slist_prepend(NULL, child);
                child_class->set_aio_ctx(child, ctx, &ignore);
            }
            g_slist_free(ignore);
        }
        if (ret < 0) {
            error_propagate(errp, local_err);
            g_free(child);
            bdrv_abort_perm_update(child_bs);
            bdrv_unref(child_bs);
            return NULL;
        }
    }

    /* This performs the matching bdrv_set_perm() for the above check. */
    bdrv_replace_child(child, child_bs);

    return child;
}

/*
 * This function transfers the reference to child_bs from the caller
 * to parent_bs. That reference is later dropped by parent_bs on
 * bdrv_close() or if someone calls bdrv_unref_child().
 *
 * On failure NULL is returned, errp is set and the reference to
 * child_bs is also dropped.
 *
 * If @parent_bs and @child_bs are in different AioContexts, the caller must
 * hold the AioContext lock for @child_bs, but not for @parent_bs.
 */
BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
                             BlockDriverState *child_bs,
                             const char *child_name,
                             const BdrvChildClass *child_class,
                             BdrvChildRole child_role,
                             Error **errp)
{
    BdrvChild *child;
    uint64_t perm, shared_perm;

    bdrv_get_cumulative_perm(parent_bs, &perm, &shared_perm);

    assert(parent_bs->drv);
    bdrv_child_perm(parent_bs, child_bs, NULL, child_role, NULL,
                    perm, shared_perm, &perm, &shared_perm);

    child = bdrv_root_attach_child(child_bs, child_name, child_class,
                                   child_role, bdrv_get_aio_context(parent_bs),
                                   perm, shared_perm, parent_bs, errp);
    if (child == NULL) {
        return NULL;
    }

    QLIST_INSERT_HEAD(&parent_bs->children, child, next);
    return child;
}

static void bdrv_detach_child(BdrvChild *child)
{
    QLIST_SAFE_REMOVE(child, next);

    bdrv_replace_child(child, NULL);

    g_free(child->name);
    g_free(child);
}

void bdrv_root_unref_child(BdrvChild *child)
{
    BlockDriverState *child_bs;

    child_bs = child->bs;
    bdrv_detach_child(child);
    bdrv_unref(child_bs);
}

/**
 * Clear all inherits_from pointers from children and grandchildren of
 * @root that point to @root, where necessary.
 */
static void bdrv_unset_inherits_from(BlockDriverState *root, BdrvChild *child)
{
    BdrvChild *c;

    if (child->bs->inherits_from == root) {
        /*
         * Remove inherits_from only when the last reference between root and
         * child->bs goes away.
         */
        QLIST_FOREACH(c, &root->children, next) {
            if (c != child && c->bs == child->bs) {
                break;
            }
        }
        if (c == NULL) {
            child->bs->inherits_from = NULL;
        }
    }

    QLIST_FOREACH(c, &child->bs->children, next) {
        bdrv_unset_inherits_from(root, c);
    }
}

void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
{
    if (child == NULL) {
        return;
    }

    bdrv_unset_inherits_from(parent, child);
    bdrv_root_unref_child(child);
}


static void bdrv_parent_cb_change_media(BlockDriverState *bs, bool load)
{
    BdrvChild *c;
    QLIST_FOREACH(c, &bs->parents, next_parent) {
        if (c->klass->change_media) {
            c->klass->change_media(c, load);
        }
    }
}

/* Return true if you can reach parent going through child->inherits_from
 * recursively. If parent or child are NULL, return false */
static bool bdrv_inherits_from_recursive(BlockDriverState *child,
                                         BlockDriverState *parent)
{
    while (child && child != parent) {
        child = child->inherits_from;
    }

    return child != NULL;
}

/*
 * Return the BdrvChildRole for @bs's backing child.  bs->backing is
 * mostly used for COW backing children (role = COW), but also for
 * filtered children (role = FILTERED | PRIMARY).
 */
static BdrvChildRole bdrv_backing_role(BlockDriverState *bs)
{
    if (bs->drv && bs->drv->is_filter) {
        return BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY;
    } else {
        return BDRV_CHILD_COW;
    }
}

/*
 * Sets the backing file link of a BDS. A new reference is created; callers
 * which don't need their own reference any more must call bdrv_unref().
 */
void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
                         Error **errp)
{
    bool update_inherits_from = bdrv_chain_contains(bs, backing_hd) &&
        bdrv_inherits_from_recursive(backing_hd, bs);

    if (bdrv_is_backing_chain_frozen(bs, backing_bs(bs), errp)) {
        return;
    }

    if (backing_hd) {
        bdrv_ref(backing_hd);
    }

    if (bs->backing) {
        bdrv_unref_child(bs, bs->backing);
        bs->backing = NULL;
    }

    if (!backing_hd) {
        goto out;
    }

    bs->backing = bdrv_attach_child(bs, backing_hd, "backing", &child_of_bds,
                                    bdrv_backing_role(bs), errp);
    /* If backing_hd was already part of bs's backing chain, and
     * inherits_from pointed recursively to bs then let's update it to
     * point directly to bs (else it will become NULL). */
    if (bs->backing && update_inherits_from) {
        backing_hd->inherits_from = bs;
    }

out:
    bdrv_refresh_limits(bs, NULL);
}

/*
 * Opens the backing file for a BlockDriverState if not yet open
 *
 * bdref_key specifies the key for the image's BlockdevRef in the options QDict.
 * That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
 * itself, all options starting with "${bdref_key}." are considered part of the
 * BlockdevRef.
 *
 * TODO Can this be unified with bdrv_open_image()?
 */
int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
                           const char *bdref_key, Error **errp)
{
    char *backing_filename = NULL;
    char *bdref_key_dot;
    const char *reference = NULL;
    int ret = 0;
    bool implicit_backing = false;
    BlockDriverState *backing_hd;
    QDict *options;
    QDict *tmp_parent_options = NULL;
    Error *local_err = NULL;

    if (bs->backing != NULL) {
        goto free_exit;
    }

    /* NULL means an empty set of options */
    if (parent_options == NULL) {
        tmp_parent_options = qdict_new();
        parent_options = tmp_parent_options;
    }

    bs->open_flags &= ~BDRV_O_NO_BACKING;

    bdref_key_dot = g_strdup_printf("%s.", bdref_key);
    qdict_extract_subqdict(parent_options, &options, bdref_key_dot);
    g_free(bdref_key_dot);

    /*
     * Caution: while qdict_get_try_str() is fine, getting non-string
     * types would require more care.  When @parent_options come from
     * -blockdev or blockdev_add, its members are typed according to
     * the QAPI schema, but when they come from -drive, they're all
     * QString.
     */
    reference = qdict_get_try_str(parent_options, bdref_key);
    if (reference || qdict_haskey(options, "file.filename")) {
        /* keep backing_filename NULL */
    } else if (bs->backing_file[0] == '\0' && qdict_size(options) == 0) {
        qobject_unref(options);
        goto free_exit;
    } else {
        if (qdict_size(options) == 0) {
            /* If the user specifies options that do not modify the
             * backing file's behavior, we might still consider it the
             * implicit backing file.  But it's easier this way, and
             * just specifying some of the backing BDS's options is
             * only possible with -drive anyway (otherwise the QAPI
             * schema forces the user to specify everything). */
            implicit_backing = !strcmp(bs->auto_backing_file, bs->backing_file);
        }

        backing_filename = bdrv_get_full_backing_filename(bs, &local_err);
        if (local_err) {
            ret = -EINVAL;
            error_propagate(errp, local_err);
            qobject_unref(options);
            goto free_exit;
        }
    }

    if (!bs->drv || !bs->drv->supports_backing) {
        ret = -EINVAL;
        error_setg(errp, "Driver doesn't support backing files");
        qobject_unref(options);
        goto free_exit;
    }

    if (!reference &&
        bs->backing_format[0] != '\0' && !qdict_haskey(options, "driver")) {
        qdict_put_str(options, "driver", bs->backing_format);
    }

    backing_hd = bdrv_open_inherit(backing_filename, reference, options, 0, bs,
                                   &child_of_bds, bdrv_backing_role(bs), errp);
    if (!backing_hd) {
        bs->open_flags |= BDRV_O_NO_BACKING;
        error_prepend(errp, "Could not open backing file: ");
        ret = -EINVAL;
        goto free_exit;
    }

    if (implicit_backing) {
        bdrv_refresh_filename(backing_hd);
        pstrcpy(bs->auto_backing_file, sizeof(bs->auto_backing_file),
                backing_hd->filename);
    }

    /* Hook up the backing file link; drop our reference, bs owns the
     * backing_hd reference now */
    bdrv_set_backing_hd(bs, backing_hd, &local_err);
    bdrv_unref(backing_hd);
    if (local_err) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto free_exit;
    }

    qdict_del(parent_options, bdref_key);

free_exit:
    g_free(backing_filename);
    qobject_unref(tmp_parent_options);
    return ret;
}

static BlockDriverState *
bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key,
                   BlockDriverState *parent, const BdrvChildClass *child_class,
                   BdrvChildRole child_role, bool allow_none, Error **errp)
{
    BlockDriverState *bs = NULL;
    QDict *image_options;
    char *bdref_key_dot;
    const char *reference;

    assert(child_class != NULL);

    bdref_key_dot = g_strdup_printf("%s.", bdref_key);
    qdict_extract_subqdict(options, &image_options, bdref_key_dot);
    g_free(bdref_key_dot);

    /*
     * Caution: while qdict_get_try_str() is fine, getting non-string
     * types would require more care.  When @options come from
     * -blockdev or blockdev_add, its members are typed according to
     * the QAPI schema, but when they come from -drive, they're all
     * QString.
     */
    reference = qdict_get_try_str(options, bdref_key);
    if (!filename && !reference && !qdict_size(image_options)) {
        if (!allow_none) {
            error_setg(errp, "A block device must be specified for \"%s\"",
                       bdref_key);
        }
        qobject_unref(image_options);
        goto done;
    }

    bs = bdrv_open_inherit(filename, reference, image_options, 0,
                           parent, child_class, child_role, errp);
    if (!bs) {
        goto done;
    }

done:
    qdict_del(options, bdref_key);
    return bs;
}

/*
 * Opens a disk image whose options are given as BlockdevRef in another block
 * device's options.
 *
 * If allow_none is true, no image will be opened if filename is false and no
 * BlockdevRef is given. NULL will be returned, but errp remains unset.
 *
 * bdrev_key specifies the key for the image's BlockdevRef in the options QDict.
 * That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
 * itself, all options starting with "${bdref_key}." are considered part of the
 * BlockdevRef.
 *
 * The BlockdevRef will be removed from the options QDict.
 */
BdrvChild *bdrv_open_child(const char *filename,
                           QDict *options, const char *bdref_key,
                           BlockDriverState *parent,
                           const BdrvChildClass *child_class,
                           BdrvChildRole child_role,
                           bool allow_none, Error **errp)
{
    BlockDriverState *bs;

    bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_class,
                            child_role, allow_none, errp);
    if (bs == NULL) {
        return NULL;
    }

    return bdrv_attach_child(parent, bs, bdref_key, child_class, child_role,
                             errp);
}

/*
 * TODO Future callers may need to specify parent/child_class in order for
 * option inheritance to work. Existing callers use it for the root node.
 */
BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp)
{
    BlockDriverState *bs = NULL;
    QObject *obj = NULL;
    QDict *qdict = NULL;
    const char *reference = NULL;
    Visitor *v = NULL;

    if (ref->type == QTYPE_QSTRING) {
        reference = ref->u.reference;
    } else {
        BlockdevOptions *options = &ref->u.definition;
        assert(ref->type == QTYPE_QDICT);

        v = qobject_output_visitor_new(&obj);
        visit_type_BlockdevOptions(v, NULL, &options, &error_abort);
        visit_complete(v, &obj);

        qdict = qobject_to(QDict, obj);
        qdict_flatten(qdict);

        /* bdrv_open_inherit() defaults to the values in bdrv_flags (for
         * compatibility with other callers) rather than what we want as the
         * real defaults. Apply the defaults here instead. */
        qdict_set_default_str(qdict, BDRV_OPT_CACHE_DIRECT, "off");
        qdict_set_default_str(qdict, BDRV_OPT_CACHE_NO_FLUSH, "off");
        qdict_set_default_str(qdict, BDRV_OPT_READ_ONLY, "off");
        qdict_set_default_str(qdict, BDRV_OPT_AUTO_READ_ONLY, "off");

    }

    bs = bdrv_open_inherit(NULL, reference, qdict, 0, NULL, NULL, 0, errp);
    obj = NULL;
    qobject_unref(obj);
    visit_free(v);
    return bs;
}

static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
                                                   int flags,
                                                   QDict *snapshot_options,
                                                   Error **errp)
{
    /* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
    char *tmp_filename = g_malloc0(PATH_MAX + 1);
    int64_t total_size;
    QemuOpts *opts = NULL;
    BlockDriverState *bs_snapshot = NULL;
    Error *local_err = NULL;
    int ret;

    /* if snapshot, we create a temporary backing file and open it
       instead of opening 'filename' directly */

    /* Get the required size from the image */
    total_size = bdrv_getlength(bs);
    if (total_size < 0) {
        error_setg_errno(errp, -total_size, "Could not get image size");
        goto out;
    }

    /* Create the temporary image */
    ret = get_tmp_filename(tmp_filename, PATH_MAX + 1);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Could not get temporary filename");
        goto out;
    }

    opts = qemu_opts_create(bdrv_qcow2.create_opts, NULL, 0,
                            &error_abort);
    qemu_opt_set_number(opts, BLOCK_OPT_SIZE, total_size, &error_abort);
    ret = bdrv_create(&bdrv_qcow2, tmp_filename, opts, errp);
    qemu_opts_del(opts);
    if (ret < 0) {
        error_prepend(errp, "Could not create temporary overlay '%s': ",
                      tmp_filename);
        goto out;
    }

    /* Prepare options QDict for the temporary file */
    qdict_put_str(snapshot_options, "file.driver", "file");
    qdict_put_str(snapshot_options, "file.filename", tmp_filename);
    qdict_put_str(snapshot_options, "driver", "qcow2");

    bs_snapshot = bdrv_open(NULL, NULL, snapshot_options, flags, errp);
    snapshot_options = NULL;
    if (!bs_snapshot) {
        goto out;
    }

    /* bdrv_append() consumes a strong reference to bs_snapshot
     * (i.e. it will call bdrv_unref() on it) even on error, so in
     * order to be able to return one, we have to increase
     * bs_snapshot's refcount here */
    bdrv_ref(bs_snapshot);
    bdrv_append(bs_snapshot, bs, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        bs_snapshot = NULL;
        goto out;
    }

out:
    qobject_unref(snapshot_options);
    g_free(tmp_filename);
    return bs_snapshot;
}

/*
 * Opens a disk image (raw, qcow2, vmdk, ...)
 *
 * options is a QDict of options to pass to the block drivers, or NULL for an
 * empty set of options. The reference to the QDict belongs to the block layer
 * after the call (even on failure), so if the caller intends to reuse the
 * dictionary, it needs to use qobject_ref() before calling bdrv_open.
 *
 * If *pbs is NULL, a new BDS will be created with a pointer to it stored there.
 * If it is not NULL, the referenced BDS will be reused.
 *
 * The reference parameter may be used to specify an existing block device which
 * should be opened. If specified, neither options nor a filename may be given,
 * nor can an existing BDS be reused (that is, *pbs has to be NULL).
 */
static BlockDriverState *bdrv_open_inherit(const char *filename,
                                           const char *reference,
                                           QDict *options, int flags,
                                           BlockDriverState *parent,
                                           const BdrvChildClass *child_class,
                                           BdrvChildRole child_role,
                                           Error **errp)
{
    int ret;
    BlockBackend *file = NULL;
    BlockDriverState *bs;
    BlockDriver *drv = NULL;
    BdrvChild *child;
    const char *drvname;
    const char *backing;
    Error *local_err = NULL;
    QDict *snapshot_options = NULL;
    int snapshot_flags = 0;

    assert(!child_class || !flags);
    assert(!child_class == !parent);

    if (reference) {
        bool options_non_empty = options ? qdict_size(options) : false;
        qobject_unref(options);

        if (filename || options_non_empty) {
            error_setg(errp, "Cannot reference an existing block device with "
                       "additional options or a new filename");
            return NULL;
        }

        bs = bdrv_lookup_bs(reference, reference, errp);
        if (!bs) {
            return NULL;
        }

        bdrv_ref(bs);
        return bs;
    }

    bs = bdrv_new();

    /* NULL means an empty set of options */
    if (options == NULL) {
        options = qdict_new();
    }

    /* json: syntax counts as explicit options, as if in the QDict */
    parse_json_protocol(options, &filename, &local_err);
    if (local_err) {
        goto fail;
    }

    bs->explicit_options = qdict_clone_shallow(options);

    if (child_class) {
        bool parent_is_format;

        if (parent->drv) {
            parent_is_format = parent->drv->is_format;
        } else {
            /*
             * parent->drv is not set yet because this node is opened for
             * (potential) format probing.  That means that @parent is going
             * to be a format node.
             */
            parent_is_format = true;
        }

        bs->inherits_from = parent;
        child_class->inherit_options(child_role, parent_is_format,
                                     &flags, options,
                                     parent->open_flags, parent->options);
    }

    ret = bdrv_fill_options(&options, filename, &flags, &local_err);
    if (ret < 0) {
        goto fail;
    }

    /*
     * Set the BDRV_O_RDWR and BDRV_O_ALLOW_RDWR flags.
     * Caution: getting a boolean member of @options requires care.
     * When @options come from -blockdev or blockdev_add, members are
     * typed according to the QAPI schema, but when they come from
     * -drive, they're all QString.
     */
    if (g_strcmp0(qdict_get_try_str(options, BDRV_OPT_READ_ONLY), "on") &&
        !qdict_get_try_bool(options, BDRV_OPT_READ_ONLY, false)) {
        flags |= (BDRV_O_RDWR | BDRV_O_ALLOW_RDWR);
    } else {
        flags &= ~BDRV_O_RDWR;
    }

    if (flags & BDRV_O_SNAPSHOT) {
        snapshot_options = qdict_new();
        bdrv_temp_snapshot_options(&snapshot_flags, snapshot_options,
                                   flags, options);
        /* Let bdrv_backing_options() override "read-only" */
        qdict_del(options, BDRV_OPT_READ_ONLY);
        bdrv_inherited_options(BDRV_CHILD_COW, true,
                               &flags, options, flags, options);
    }

    bs->open_flags = flags;
    bs->options = options;
    options = qdict_clone_shallow(options);

    /* Find the right image format driver */
    /* See cautionary note on accessing @options above */
    drvname = qdict_get_try_str(options, "driver");
    if (drvname) {
        drv = bdrv_find_format(drvname);
        if (!drv) {
            error_setg(errp, "Unknown driver: '%s'", drvname);
            goto fail;
        }
    }

    assert(drvname || !(flags & BDRV_O_PROTOCOL));

    /* See cautionary note on accessing @options above */
    backing = qdict_get_try_str(options, "backing");
    if (qobject_to(QNull, qdict_get(options, "backing")) != NULL ||
        (backing && *backing == '\0'))
    {
        if (backing) {
            warn_report("Use of \"backing\": \"\" is deprecated; "
                        "use \"backing\": null instead");
        }
        flags |= BDRV_O_NO_BACKING;
        qdict_del(bs->explicit_options, "backing");
        qdict_del(bs->options, "backing");
        qdict_del(options, "backing");
    }

    /* Open image file without format layer. This BlockBackend is only used for
     * probing, the block drivers will do their own bdrv_open_child() for the
     * same BDS, which is why we put the node name back into options. */
    if ((flags & BDRV_O_PROTOCOL) == 0) {
        BlockDriverState *file_bs;

        file_bs = bdrv_open_child_bs(filename, options, "file", bs,
                                     &child_of_bds, BDRV_CHILD_IMAGE,
                                     true, &local_err);
        if (local_err) {
            goto fail;
        }
        if (file_bs != NULL) {
            /* Not requesting BLK_PERM_CONSISTENT_READ because we're only
             * looking at the header to guess the image format. This works even
             * in cases where a guest would not see a consistent state. */
            file = blk_new(bdrv_get_aio_context(file_bs), 0, BLK_PERM_ALL);
            blk_insert_bs(file, file_bs, &local_err);
            bdrv_unref(file_bs);
            if (local_err) {
                goto fail;
            }

            qdict_put_str(options, "file", bdrv_get_node_name(file_bs));
        }
    }

    /* Image format probing */
    bs->probed = !drv;
    if (!drv && file) {
        ret = find_image_format(file, filename, &drv, &local_err);
        if (ret < 0) {
            goto fail;
        }
        /*
         * This option update would logically belong in bdrv_fill_options(),
         * but we first need to open bs->file for the probing to work, while
         * opening bs->file already requires the (mostly) final set of options
         * so that cache mode etc. can be inherited.
         *
         * Adding the driver later is somewhat ugly, but it's not an option
         * that would ever be inherited, so it's correct. We just need to make
         * sure to update both bs->options (which has the full effective
         * options for bs) and options (which has file.* already removed).
         */
        qdict_put_str(bs->options, "driver", drv->format_name);
        qdict_put_str(options, "driver", drv->format_name);
    } else if (!drv) {
        error_setg(errp, "Must specify either driver or file");
        goto fail;
    }

    /* BDRV_O_PROTOCOL must be set iff a protocol BDS is about to be created */
    assert(!!(flags & BDRV_O_PROTOCOL) == !!drv->bdrv_file_open);
    /* file must be NULL if a protocol BDS is about to be created
     * (the inverse results in an error message from bdrv_open_common()) */
    assert(!(flags & BDRV_O_PROTOCOL) || !file);

    /* Open the image */
    ret = bdrv_open_common(bs, file, options, &local_err);
    if (ret < 0) {
        goto fail;
    }

    if (file) {
        blk_unref(file);
        file = NULL;
    }

    /* If there is a backing file, use it */
    if ((flags & BDRV_O_NO_BACKING) == 0) {
        ret = bdrv_open_backing_file(bs, options, "backing", &local_err);
        if (ret < 0) {
            goto close_and_fail;
        }
    }

    /* Remove all children options and references
     * from bs->options and bs->explicit_options */
    QLIST_FOREACH(child, &bs->children, next) {
        char *child_key_dot;
        child_key_dot = g_strdup_printf("%s.", child->name);
        qdict_extract_subqdict(bs->explicit_options, NULL, child_key_dot);
        qdict_extract_subqdict(bs->options, NULL, child_key_dot);
        qdict_del(bs->explicit_options, child->name);
        qdict_del(bs->options, child->name);
        g_free(child_key_dot);
    }

    /* Check if any unknown options were used */
    if (qdict_size(options) != 0) {
        const QDictEntry *entry = qdict_first(options);
        if (flags & BDRV_O_PROTOCOL) {
            error_setg(errp, "Block protocol '%s' doesn't support the option "
                       "'%s'", drv->format_name, entry->key);
        } else {
            error_setg(errp,
                       "Block format '%s' does not support the option '%s'",
                       drv->format_name, entry->key);
        }

        goto close_and_fail;
    }

    bdrv_parent_cb_change_media(bs, true);

    qobject_unref(options);
    options = NULL;

    /* For snapshot=on, create a temporary qcow2 overlay. bs points to the
     * temporary snapshot afterwards. */
    if (snapshot_flags) {
        BlockDriverState *snapshot_bs;
        snapshot_bs = bdrv_append_temp_snapshot(bs, snapshot_flags,
                                                snapshot_options, &local_err);
        snapshot_options = NULL;
        if (local_err) {
            goto close_and_fail;
        }
        /* We are not going to return bs but the overlay on top of it
         * (snapshot_bs); thus, we have to drop the strong reference to bs
         * (which we obtained by calling bdrv_new()). bs will not be deleted,
         * though, because the overlay still has a reference to it. */
        bdrv_unref(bs);
        bs = snapshot_bs;
    }

    return bs;

fail:
    blk_unref(file);
    qobject_unref(snapshot_options);
    qobject_unref(bs->explicit_options);
    qobject_unref(bs->options);
    qobject_unref(options);
    bs->options = NULL;
    bs->explicit_options = NULL;
    bdrv_unref(bs);
    error_propagate(errp, local_err);
    return NULL;

close_and_fail:
    bdrv_unref(bs);
    qobject_unref(snapshot_options);
    qobject_unref(options);
    error_propagate(errp, local_err);
    return NULL;
}

BlockDriverState *bdrv_open(const char *filename, const char *reference,
                            QDict *options, int flags, Error **errp)
{
    return bdrv_open_inherit(filename, reference, options, flags, NULL,
                             NULL, 0, errp);
}

/* Return true if the NULL-terminated @list contains @str */
static bool is_str_in_list(const char *str, const char *const *list)
{
    if (str && list) {
        int i;
        for (i = 0; list[i] != NULL; i++) {
            if (!strcmp(str, list[i])) {
                return true;
            }
        }
    }
    return false;
}

/*
 * Check that every option set in @bs->options is also set in
 * @new_opts.
 *
 * Options listed in the common_options list and in
 * @bs->drv->mutable_opts are skipped.
 *
 * Return 0 on success, otherwise return -EINVAL and set @errp.
 */
static int bdrv_reset_options_allowed(BlockDriverState *bs,
                                      const QDict *new_opts, Error **errp)
{
    const QDictEntry *e;
    /* These options are common to all block drivers and are handled
     * in bdrv_reopen_prepare() so they can be left out of @new_opts */
    const char *const common_options[] = {
        "node-name", "discard", "cache.direct", "cache.no-flush",
        "read-only", "auto-read-only", "detect-zeroes", NULL
    };

    for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
        if (!qdict_haskey(new_opts, e->key) &&
            !is_str_in_list(e->key, common_options) &&
            !is_str_in_list(e->key, bs->drv->mutable_opts)) {
            error_setg(errp, "Option '%s' cannot be reset "
                       "to its default value", e->key);
            return -EINVAL;
        }
    }

    return 0;
}

/*
 * Returns true if @child can be reached recursively from @bs
 */
static bool bdrv_recurse_has_child(BlockDriverState *bs,
                                   BlockDriverState *child)
{
    BdrvChild *c;

    if (bs == child) {
        return true;
    }

    QLIST_FOREACH(c, &bs->children, next) {
        if (bdrv_recurse_has_child(c->bs, child)) {
            return true;
        }
    }

    return false;
}

/*
 * Adds a BlockDriverState to a simple queue for an atomic, transactional
 * reopen of multiple devices.
 *
 * bs_queue can either be an existing BlockReopenQueue that has had QTAILQ_INIT
 * already performed, or alternatively may be NULL a new BlockReopenQueue will
 * be created and initialized. This newly created BlockReopenQueue should be
 * passed back in for subsequent calls that are intended to be of the same
 * atomic 'set'.
 *
 * bs is the BlockDriverState to add to the reopen queue.
 *
 * options contains the changed options for the associated bs
 * (the BlockReopenQueue takes ownership)
 *
 * flags contains the open flags for the associated bs
 *
 * returns a pointer to bs_queue, which is either the newly allocated
 * bs_queue, or the existing bs_queue being used.
 *
 * bs must be drained between bdrv_reopen_queue() and bdrv_reopen_multiple().
 */
static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
                                                 BlockDriverState *bs,
                                                 QDict *options,
                                                 const BdrvChildClass *klass,
                                                 BdrvChildRole role,
                                                 bool parent_is_format,
                                                 QDict *parent_options,
                                                 int parent_flags,
                                                 bool keep_old_opts)
{
    assert(bs != NULL);

    BlockReopenQueueEntry *bs_entry;
    BdrvChild *child;
    QDict *old_options, *explicit_options, *options_copy;
    int flags;
    QemuOpts *opts;

    /* Make sure that the caller remembered to use a drained section. This is
     * important to avoid graph changes between the recursive queuing here and
     * bdrv_reopen_multiple(). */
    assert(bs->quiesce_counter > 0);

    if (bs_queue == NULL) {
        bs_queue = g_new0(BlockReopenQueue, 1);
        QTAILQ_INIT(bs_queue);
    }

    if (!options) {
        options = qdict_new();
    }

    /* Check if this BlockDriverState is already in the queue */
    QTAILQ_FOREACH(bs_entry, bs_queue, entry) {
        if (bs == bs_entry->state.bs) {
            break;
        }
    }

    /*
     * Precedence of options:
     * 1. Explicitly passed in options (highest)
     * 2. Retained from explicitly set options of bs
     * 3. Inherited from parent node
     * 4. Retained from effective options of bs
     */

    /* Old explicitly set values (don't overwrite by inherited value) */
    if (bs_entry || keep_old_opts) {
        old_options = qdict_clone_shallow(bs_entry ?
                                          bs_entry->state.explicit_options :
                                          bs->explicit_options);
        bdrv_join_options(bs, options, old_options);
        qobject_unref(old_options);
    }

    explicit_options = qdict_clone_shallow(options);

    /* Inherit from parent node */
    if (parent_options) {
        flags = 0;
        klass->inherit_options(role, parent_is_format, &flags, options,
                               parent_flags, parent_options);
    } else {
        flags = bdrv_get_flags(bs);
    }

    if (keep_old_opts) {
        /* Old values are used for options that aren't set yet */
        old_options = qdict_clone_shallow(bs->options);
        bdrv_join_options(bs, options, old_options);
        qobject_unref(old_options);
    }

    /* We have the final set of options so let's update the flags */
    options_copy = qdict_clone_shallow(options);
    opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
    qemu_opts_absorb_qdict(opts, options_copy, NULL);
    update_flags_from_options(&flags, opts);
    qemu_opts_del(opts);
    qobject_unref(options_copy);

    /* bdrv_open_inherit() sets and clears some additional flags internally */
    flags &= ~BDRV_O_PROTOCOL;
    if (flags & BDRV_O_RDWR) {
        flags |= BDRV_O_ALLOW_RDWR;
    }

    if (!bs_entry) {
        bs_entry = g_new0(BlockReopenQueueEntry, 1);
        QTAILQ_INSERT_TAIL(bs_queue, bs_entry, entry);
    } else {
        qobject_unref(bs_entry->state.options);
        qobject_unref(bs_entry->state.explicit_options);
    }

    bs_entry->state.bs = bs;
    bs_entry->state.options = options;
    bs_entry->state.explicit_options = explicit_options;
    bs_entry->state.flags = flags;

    /* This needs to be overwritten in bdrv_reopen_prepare() */
    bs_entry->state.perm = UINT64_MAX;
    bs_entry->state.shared_perm = 0;

    /*
     * If keep_old_opts is false then it means that unspecified
     * options must be reset to their original value. We don't allow
     * resetting 'backing' but we need to know if the option is
     * missing in order to decide if we have to return an error.
     */
    if (!keep_old_opts) {
        bs_entry->state.backing_missing =
            !qdict_haskey(options, "backing") &&
            !qdict_haskey(options, "backing.driver");
    }

    QLIST_FOREACH(child, &bs->children, next) {
        QDict *new_child_options = NULL;
        bool child_keep_old = keep_old_opts;

        /* reopen can only change the options of block devices that were
         * implicitly created and inherited options. For other (referenced)
         * block devices, a syntax like "backing.foo" results in an error. */
        if (child->bs->inherits_from != bs) {
            continue;
        }

        /* Check if the options contain a child reference */
        if (qdict_haskey(options, child->name)) {
            const char *childref = qdict_get_try_str(options, child->name);
            /*
             * The current child must not be reopened if the child
             * reference is null or points to a different node.
             */
            if (g_strcmp0(childref, child->bs->node_name)) {
                continue;
            }
            /*
             * If the child reference points to the current child then
             * reopen it with its existing set of options (note that
             * it can still inherit new options from the parent).
             */
            child_keep_old = true;
        } else {
            /* Extract child options ("child-name.*") */
            char *child_key_dot = g_strdup_printf("%s.", child->name);
            qdict_extract_subqdict(explicit_options, NULL, child_key_dot);
            qdict_extract_subqdict(options, &new_child_options, child_key_dot);
            g_free(child_key_dot);
        }

        bdrv_reopen_queue_child(bs_queue, child->bs, new_child_options,
                                child->klass, child->role, bs->drv->is_format,
                                options, flags, child_keep_old);
    }

    return bs_queue;
}

BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
                                    BlockDriverState *bs,
                                    QDict *options, bool keep_old_opts)
{
    return bdrv_reopen_queue_child(bs_queue, bs, options, NULL, 0, false,
                                   NULL, 0, keep_old_opts);
}

/*
 * Reopen multiple BlockDriverStates atomically & transactionally.
 *
 * The queue passed in (bs_queue) must have been built up previous
 * via bdrv_reopen_queue().
 *
 * Reopens all BDS specified in the queue, with the appropriate
 * flags.  All devices are prepared for reopen, and failure of any
 * device will cause all device changes to be abandoned, and intermediate
 * data cleaned up.
 *
 * If all devices prepare successfully, then the changes are committed
 * to all devices.
 *
 * All affected nodes must be drained between bdrv_reopen_queue() and
 * bdrv_reopen_multiple().
 */
int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp)
{
    int ret = -1;
    BlockReopenQueueEntry *bs_entry, *next;

    assert(bs_queue != NULL);

    QTAILQ_FOREACH(bs_entry, bs_queue, entry) {
        assert(bs_entry->state.bs->quiesce_counter > 0);
        if (bdrv_reopen_prepare(&bs_entry->state, bs_queue, errp)) {
            goto cleanup;
        }
        bs_entry->prepared = true;
    }

    QTAILQ_FOREACH(bs_entry, bs_queue, entry) {
        BDRVReopenState *state = &bs_entry->state;
        ret = bdrv_check_perm(state->bs, bs_queue, state->perm,
                              state->shared_perm, NULL, NULL, errp);
        if (ret < 0) {
            goto cleanup_perm;
        }
        /* Check if new_backing_bs would accept the new permissions */
        if (state->replace_backing_bs && state->new_backing_bs) {
            uint64_t nperm, nshared;
            bdrv_child_perm(state->bs, state->new_backing_bs,
                            NULL, bdrv_backing_role(state->bs),
                            bs_queue, state->perm, state->shared_perm,
                            &nperm, &nshared);
            ret = bdrv_check_update_perm(state->new_backing_bs, NULL,
                                         nperm, nshared, NULL, NULL, errp);
            if (ret < 0) {
                goto cleanup_perm;
            }
        }
        bs_entry->perms_checked = true;
    }

    /*
     * If we reach this point, we have success and just need to apply the
     * changes.
     *
     * Reverse order is used to comfort qcow2 driver: on commit it need to write
     * IN_USE flag to the image, to mark bitmaps in the image as invalid. But
     * children are usually goes after parents in reopen-queue, so go from last
     * to first element.
     */
    QTAILQ_FOREACH_REVERSE(bs_entry, bs_queue, entry) {
        bdrv_reopen_commit(&bs_entry->state);
    }

    ret = 0;
cleanup_perm:
    QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
        BDRVReopenState *state = &bs_entry->state;

        if (!bs_entry->perms_checked) {
            continue;
        }

        if (ret == 0) {
            bdrv_set_perm(state->bs, state->perm, state->shared_perm);
        } else {
            bdrv_abort_perm_update(state->bs);
            if (state->replace_backing_bs && state->new_backing_bs) {
                bdrv_abort_perm_update(state->new_backing_bs);
            }
        }
    }

    if (ret == 0) {
        QTAILQ_FOREACH_REVERSE(bs_entry, bs_queue, entry) {
            BlockDriverState *bs = bs_entry->state.bs;

            if (bs->drv->bdrv_reopen_commit_post)
                bs->drv->bdrv_reopen_commit_post(&bs_entry->state);
        }
    }
cleanup:
    QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
        if (ret) {
            if (bs_entry->prepared) {
                bdrv_reopen_abort(&bs_entry->state);
            }
            qobject_unref(bs_entry->state.explicit_options);
            qobject_unref(bs_entry->state.options);
        }
        if (bs_entry->state.new_backing_bs) {
            bdrv_unref(bs_entry->state.new_backing_bs);
        }
        g_free(bs_entry);
    }
    g_free(bs_queue);

    return ret;
}

int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only,
                              Error **errp)
{
    int ret;
    BlockReopenQueue *queue;
    QDict *opts = qdict_new();

    qdict_put_bool(opts, BDRV_OPT_READ_ONLY, read_only);

    bdrv_subtree_drained_begin(bs);
    queue = bdrv_reopen_queue(NULL, bs, opts, true);
    ret = bdrv_reopen_multiple(queue, errp);
    bdrv_subtree_drained_end(bs);

    return ret;
}

static BlockReopenQueueEntry *find_parent_in_reopen_queue(BlockReopenQueue *q,
                                                          BdrvChild *c)
{
    BlockReopenQueueEntry *entry;

    QTAILQ_FOREACH(entry, q, entry) {
        BlockDriverState *bs = entry->state.bs;
        BdrvChild *child;

        QLIST_FOREACH(child, &bs->children, next) {
            if (child == c) {
                return entry;
            }
        }
    }

    return NULL;
}

static void bdrv_reopen_perm(BlockReopenQueue *q, BlockDriverState *bs,
                             uint64_t *perm, uint64_t *shared)
{
    BdrvChild *c;
    BlockReopenQueueEntry *parent;
    uint64_t cumulative_perms = 0;
    uint64_t cumulative_shared_perms = BLK_PERM_ALL;

    QLIST_FOREACH(c, &bs->parents, next_parent) {
        parent = find_parent_in_reopen_queue(q, c);
        if (!parent) {
            cumulative_perms |= c->perm;
            cumulative_shared_perms &= c->shared_perm;
        } else {
            uint64_t nperm, nshared;

            bdrv_child_perm(parent->state.bs, bs, c, c->role, q,
                            parent->state.perm, parent->state.shared_perm,
                            &nperm, &nshared);

            cumulative_perms |= nperm;
            cumulative_shared_perms &= nshared;
        }
    }
    *perm = cumulative_perms;
    *shared = cumulative_shared_perms;
}

static bool bdrv_reopen_can_attach(BlockDriverState *parent,
                                   BdrvChild *child,
                                   BlockDriverState *new_child,
                                   Error **errp)
{
    AioContext *parent_ctx = bdrv_get_aio_context(parent);
    AioContext *child_ctx = bdrv_get_aio_context(new_child);
    GSList *ignore;
    bool ret;

    ignore = g_slist_prepend(NULL, child);
    ret = bdrv_can_set_aio_context(new_child, parent_ctx, &ignore, NULL);
    g_slist_free(ignore);
    if (ret) {
        return ret;
    }

    ignore = g_slist_prepend(NULL, child);
    ret = bdrv_can_set_aio_context(parent, child_ctx, &ignore, errp);
    g_slist_free(ignore);
    return ret;
}

/*
 * Take a BDRVReopenState and check if the value of 'backing' in the
 * reopen_state->options QDict is valid or not.
 *
 * If 'backing' is missing from the QDict then return 0.
 *
 * If 'backing' contains the node name of the backing file of
 * reopen_state->bs then return 0.
 *
 * If 'backing' contains a different node name (or is null) then check
 * whether the current backing file can be replaced with the new one.
 * If that's the case then reopen_state->replace_backing_bs is set to
 * true and reopen_state->new_backing_bs contains a pointer to the new
 * backing BlockDriverState (or NULL).
 *
 * Return 0 on success, otherwise return < 0 and set @errp.
 */
static int bdrv_reopen_parse_backing(BDRVReopenState *reopen_state,
                                     Error **errp)
{
    BlockDriverState *bs = reopen_state->bs;
    BlockDriverState *overlay_bs, *new_backing_bs;
    QObject *value;
    const char *str;

    value = qdict_get(reopen_state->options, "backing");
    if (value == NULL) {
        return 0;
    }

    switch (qobject_type(value)) {
    case QTYPE_QNULL:
        new_backing_bs = NULL;
        break;
    case QTYPE_QSTRING:
        str = qobject_get_try_str(value);
        new_backing_bs = bdrv_lookup_bs(NULL, str, errp);
        if (new_backing_bs == NULL) {
            return -EINVAL;
        } else if (bdrv_recurse_has_child(new_backing_bs, bs)) {
            error_setg(errp, "Making '%s' a backing file of '%s' "
                       "would create a cycle", str, bs->node_name);
            return -EINVAL;
        }
        break;
    default:
        /* 'backing' does not allow any other data type */
        g_assert_not_reached();
    }

    /*
     * Check AioContext compatibility so that the bdrv_set_backing_hd() call in
     * bdrv_reopen_commit() won't fail.
     */
    if (new_backing_bs) {
        if (!bdrv_reopen_can_attach(bs, bs->backing, new_backing_bs, errp)) {
            return -EINVAL;
        }
    }

    /*
     * Find the "actual" backing file by skipping all links that point
     * to an implicit node, if any (e.g. a commit filter node).
     */
    overlay_bs = bs;
    while (backing_bs(overlay_bs) && backing_bs(overlay_bs)->implicit) {
        overlay_bs = backing_bs(overlay_bs);
    }

    /* If we want to replace the backing file we need some extra checks */
    if (new_backing_bs != backing_bs(overlay_bs)) {
        /* Check for implicit nodes between bs and its backing file */
        if (bs != overlay_bs) {
            error_setg(errp, "Cannot change backing link if '%s' has "
                       "an implicit backing file", bs->node_name);
            return -EPERM;
        }
        /* Check if the backing link that we want to replace is frozen */
        if (bdrv_is_backing_chain_frozen(overlay_bs, backing_bs(overlay_bs),
                                         errp)) {
            return -EPERM;
        }
        reopen_state->replace_backing_bs = true;
        if (new_backing_bs) {
            bdrv_ref(new_backing_bs);
            reopen_state->new_backing_bs = new_backing_bs;
        }
    }

    return 0;
}

/*
 * Prepares a BlockDriverState for reopen. All changes are staged in the
 * 'opaque' field of the BDRVReopenState, which is used and allocated by
 * the block driver layer .bdrv_reopen_prepare()
 *
 * bs is the BlockDriverState to reopen
 * flags are the new open flags
 * queue is the reopen queue
 *
 * Returns 0 on success, non-zero on error.  On error errp will be set
 * as well.
 *
 * On failure, bdrv_reopen_abort() will be called to clean up any data.
 * It is the responsibility of the caller to then call the abort() or
 * commit() for any other BDS that have been left in a prepare() state
 *
 */
int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
                        Error **errp)
{
    int ret = -1;
    int old_flags;
    Error *local_err = NULL;
    BlockDriver *drv;
    QemuOpts *opts;
    QDict *orig_reopen_opts;
    char *discard = NULL;
    bool read_only;
    bool drv_prepared = false;

    assert(reopen_state != NULL);
    assert(reopen_state->bs->drv != NULL);
    drv = reopen_state->bs->drv;

    /* This function and each driver's bdrv_reopen_prepare() remove
     * entries from reopen_state->options as they are processed, so
     * we need to make a copy of the original QDict. */
    orig_reopen_opts = qdict_clone_shallow(reopen_state->options);

    /* Process generic block layer options */
    opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
    qemu_opts_absorb_qdict(opts, reopen_state->options, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto error;
    }

    /* This was already called in bdrv_reopen_queue_child() so the flags
     * are up-to-date. This time we simply want to remove the options from
     * QemuOpts in order to indicate that they have been processed. */
    old_flags = reopen_state->flags;
    update_flags_from_options(&reopen_state->flags, opts);
    assert(old_flags == reopen_state->flags);

    discard = qemu_opt_get_del(opts, BDRV_OPT_DISCARD);
    if (discard != NULL) {
        if (bdrv_parse_discard_flags(discard, &reopen_state->flags) != 0) {
            error_setg(errp, "Invalid discard option");
            ret = -EINVAL;
            goto error;
        }
    }

    reopen_state->detect_zeroes =
        bdrv_parse_detect_zeroes(opts, reopen_state->flags, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto error;
    }

    /* All other options (including node-name and driver) must be unchanged.
     * Put them back into the QDict, so that they are checked at the end
     * of this function. */
    qemu_opts_to_qdict(opts, reopen_state->options);

    /* If we are to stay read-only, do not allow permission change
     * to r/w. Attempting to set to r/w may fail if either BDRV_O_ALLOW_RDWR is
     * not set, or if the BDS still has copy_on_read enabled */
    read_only = !(reopen_state->flags & BDRV_O_RDWR);
    ret = bdrv_can_set_read_only(reopen_state->bs, read_only, true, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        goto error;
    }

    /* Calculate required permissions after reopening */
    bdrv_reopen_perm(queue, reopen_state->bs,
                     &reopen_state->perm, &reopen_state->shared_perm);

    ret = bdrv_flush(reopen_state->bs);
    if (ret) {
        error_setg_errno(errp, -ret, "Error flushing drive");
        goto error;
    }

    if (drv->bdrv_reopen_prepare) {
        /*
         * If a driver-specific option is missing, it means that we
         * should reset it to its default value.
         * But not all options allow that, so we need to check it first.
         */
        ret = bdrv_reset_options_allowed(reopen_state->bs,
                                         reopen_state->options, errp);
        if (ret) {
            goto error;
        }

        ret = drv->bdrv_reopen_prepare(reopen_state, queue, &local_err);
        if (ret) {
            if (local_err != NULL) {
                error_propagate(errp, local_err);
            } else {
                bdrv_refresh_filename(reopen_state->bs);
                error_setg(errp, "failed while preparing to reopen image '%s'",
                           reopen_state->bs->filename);
            }
            goto error;
        }
    } else {
        /* It is currently mandatory to have a bdrv_reopen_prepare()
         * handler for each supported drv. */
        error_setg(errp, "Block format '%s' used by node '%s' "
                   "does not support reopening files", drv->format_name,
                   bdrv_get_device_or_node_name(reopen_state->bs));
        ret = -1;
        goto error;
    }

    drv_prepared = true;

    /*
     * We must provide the 'backing' option if the BDS has a backing
     * file or if the image file has a backing file name as part of
     * its metadata. Otherwise the 'backing' option can be omitted.
     */
    if (drv->supports_backing && reopen_state->backing_missing &&
        (backing_bs(reopen_state->bs) || reopen_state->bs->backing_file[0])) {
        error_setg(errp, "backing is missing for '%s'",
                   reopen_state->bs->node_name);
        ret = -EINVAL;
        goto error;
    }

    /*
     * Allow changing the 'backing' option. The new value can be
     * either a reference to an existing node (using its node name)
     * or NULL to simply detach the current backing file.
     */
    ret = bdrv_reopen_parse_backing(reopen_state, errp);
    if (ret < 0) {
        goto error;
    }
    qdict_del(reopen_state->options, "backing");

    /* Options that are not handled are only okay if they are unchanged
     * compared to the old state. It is expected that some options are only
     * used for the initial open, but not reopen (e.g. filename) */
    if (qdict_size(reopen_state->options)) {
        const QDictEntry *entry = qdict_first(reopen_state->options);

        do {
            QObject *new = entry->value;
            QObject *old = qdict_get(reopen_state->bs->options, entry->key);

            /* Allow child references (child_name=node_name) as long as they
             * point to the current child (i.e. everything stays the same). */
            if (qobject_type(new) == QTYPE_QSTRING) {
                BdrvChild *child;
                QLIST_FOREACH(child, &reopen_state->bs->children, next) {
                    if (!strcmp(child->name, entry->key)) {
                        break;
                    }
                }

                if (child) {
                    const char *str = qobject_get_try_str(new);
                    if (!strcmp(child->bs->node_name, str)) {
                        continue; /* Found child with this name, skip option */
                    }
                }
            }

            /*
             * TODO: When using -drive to specify blockdev options, all values
             * will be strings; however, when using -blockdev, blockdev-add or
             * filenames using the json:{} pseudo-protocol, they will be
             * correctly typed.
             * In contrast, reopening options are (currently) always strings
             * (because you can only specify them through qemu-io; all other
             * callers do not specify any options).
             * Therefore, when using anything other than -drive to create a BDS,
             * this cannot detect non-string options as unchanged, because
             * qobject_is_equal() always returns false for objects of different
             * type.  In the future, this should be remedied by correctly typing
             * all options.  For now, this is not too big of an issue because
             * the user can simply omit options which cannot be changed anyway,
             * so they will stay unchanged.
             */
            if (!qobject_is_equal(new, old)) {
                error_setg(errp, "Cannot change the option '%s'", entry->key);
                ret = -EINVAL;
                goto error;
            }
        } while ((entry = qdict_next(reopen_state->options, entry)));
    }

    ret = 0;

    /* Restore the original reopen_state->options QDict */
    qobject_unref(reopen_state->options);
    reopen_state->options = qobject_ref(orig_reopen_opts);

error:
    if (ret < 0 && drv_prepared) {
        /* drv->bdrv_reopen_prepare() has succeeded, so we need to
         * call drv->bdrv_reopen_abort() before signaling an error
         * (bdrv_reopen_multiple() will not call bdrv_reopen_abort()
         * when the respective bdrv_reopen_prepare() has failed) */
        if (drv->bdrv_reopen_abort) {
            drv->bdrv_reopen_abort(reopen_state);
        }
    }
    qemu_opts_del(opts);
    qobject_unref(orig_reopen_opts);
    g_free(discard);
    return ret;
}

/*
 * Takes the staged changes for the reopen from bdrv_reopen_prepare(), and
 * makes them final by swapping the staging BlockDriverState contents into
 * the active BlockDriverState contents.
 */
void bdrv_reopen_commit(BDRVReopenState *reopen_state)
{
    BlockDriver *drv;
    BlockDriverState *bs;
    BdrvChild *child;

    assert(reopen_state != NULL);
    bs = reopen_state->bs;
    drv = bs->drv;
    assert(drv != NULL);

    /* If there are any driver level actions to take */
    if (drv->bdrv_reopen_commit) {
        drv->bdrv_reopen_commit(reopen_state);
    }

    /* set BDS specific flags now */
    qobject_unref(bs->explicit_options);
    qobject_unref(bs->options);

    bs->explicit_options   = reopen_state->explicit_options;
    bs->options            = reopen_state->options;
    bs->open_flags         = reopen_state->flags;
    bs->read_only = !(reopen_state->flags & BDRV_O_RDWR);
    bs->detect_zeroes      = reopen_state->detect_zeroes;

    if (reopen_state->replace_backing_bs) {
        qdict_del(bs->explicit_options, "backing");
        qdict_del(bs->options, "backing");
    }

    /* Remove child references from bs->options and bs->explicit_options.
     * Child options were already removed in bdrv_reopen_queue_child() */
    QLIST_FOREACH(child, &bs->children, next) {
        qdict_del(bs->explicit_options, child->name);
        qdict_del(bs->options, child->name);
    }

    /*
     * Change the backing file if a new one was specified. We do this
     * after updating bs->options, so bdrv_refresh_filename() (called
     * from bdrv_set_backing_hd()) has the new values.
     */
    if (reopen_state->replace_backing_bs) {
        BlockDriverState *old_backing_bs = backing_bs(bs);
        assert(!old_backing_bs || !old_backing_bs->implicit);
        /* Abort the permission update on the backing bs we're detaching */
        if (old_backing_bs) {
            bdrv_abort_perm_update(old_backing_bs);
        }
        bdrv_set_backing_hd(bs, reopen_state->new_backing_bs, &error_abort);
    }

    bdrv_refresh_limits(bs, NULL);
}

/*
 * Abort the reopen, and delete and free the staged changes in
 * reopen_state
 */
void bdrv_reopen_abort(BDRVReopenState *reopen_state)
{
    BlockDriver *drv;

    assert(reopen_state != NULL);
    drv = reopen_state->bs->drv;
    assert(drv != NULL);

    if (drv->bdrv_reopen_abort) {
        drv->bdrv_reopen_abort(reopen_state);
    }
}


static void bdrv_close(BlockDriverState *bs)
{
    BdrvAioNotifier *ban, *ban_next;
    BdrvChild *child, *next;

    assert(!bs->refcnt);

    bdrv_drained_begin(bs); /* complete I/O */
    bdrv_flush(bs);
    bdrv_drain(bs); /* in case flush left pending I/O */

    if (bs->drv) {
        if (bs->drv->bdrv_close) {
            bs->drv->bdrv_close(bs);
        }
        bs->drv = NULL;
    }

    QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
        bdrv_unref_child(bs, child);
    }

    bs->backing = NULL;
    bs->file = NULL;
    g_free(bs->opaque);
    bs->opaque = NULL;
    atomic_set(&bs->copy_on_read, 0);
    bs->backing_file[0] = '\0';
    bs->backing_format[0] = '\0';
    bs->total_sectors = 0;
    bs->encrypted = false;
    bs->sg = false;
    qobject_unref(bs->options);
    qobject_unref(bs->explicit_options);
    bs->options = NULL;
    bs->explicit_options = NULL;
    qobject_unref(bs->full_open_options);
    bs->full_open_options = NULL;

    bdrv_release_named_dirty_bitmaps(bs);
    assert(QLIST_EMPTY(&bs->dirty_bitmaps));

    QLIST_FOREACH_SAFE(ban, &bs->aio_notifiers, list, ban_next) {
        g_free(ban);
    }
    QLIST_INIT(&bs->aio_notifiers);
    bdrv_drained_end(bs);
}

void bdrv_close_all(void)
{
    assert(job_next(NULL) == NULL);
    nbd_export_close_all();

    /* Drop references from requests still in flight, such as canceled block
     * jobs whose AIO context has not been polled yet */
    bdrv_drain_all();

    blk_remove_all_bs();
    blockdev_close_all_bdrv_states();

    assert(QTAILQ_EMPTY(&all_bdrv_states));
}

static bool should_update_child(BdrvChild *c, BlockDriverState *to)
{
    GQueue *queue;
    GHashTable *found;
    bool ret;

    if (c->klass->stay_at_node) {
        return false;
    }

    /* If the child @c belongs to the BDS @to, replacing the current
     * c->bs by @to would mean to create a loop.
     *
     * Such a case occurs when appending a BDS to a backing chain.
     * For instance, imagine the following chain:
     *
     *   guest device -> node A -> further backing chain...
     *
     * Now we create a new BDS B which we want to put on top of this
     * chain, so we first attach A as its backing node:
     *
     *                   node B
     *                     |
     *                     v
     *   guest device -> node A -> further backing chain...
     *
     * Finally we want to replace A by B.  When doing that, we want to
     * replace all pointers to A by pointers to B -- except for the
     * pointer from B because (1) that would create a loop, and (2)
     * that pointer should simply stay intact:
     *
     *   guest device -> node B
     *                     |
     *                     v
     *                   node A -> further backing chain...
     *
     * In general, when replacing a node A (c->bs) by a node B (@to),
     * if A is a child of B, that means we cannot replace A by B there
     * because that would create a loop.  Silently detaching A from B
     * is also not really an option.  So overall just leaving A in
     * place there is the most sensible choice.
     *
     * We would also create a loop in any cases where @c is only
     * indirectly referenced by @to. Prevent this by returning false
     * if @c is found (by breadth-first search) anywhere in the whole
     * subtree of @to.
     */

    ret = true;
    found = g_hash_table_new(NULL, NULL);
    g_hash_table_add(found, to);
    queue = g_queue_new();
    g_queue_push_tail(queue, to);

    while (!g_queue_is_empty(queue)) {
        BlockDriverState *v = g_queue_pop_head(queue);
        BdrvChild *c2;

        QLIST_FOREACH(c2, &v->children, next) {
            if (c2 == c) {
                ret = false;
                break;
            }

            if (g_hash_table_contains(found, c2->bs)) {
                continue;
            }

            g_queue_push_tail(queue, c2->bs);
            g_hash_table_add(found, c2->bs);
        }
    }

    g_queue_free(queue);
    g_hash_table_destroy(found);

    return ret;
}

void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to,
                       Error **errp)
{
    BdrvChild *c, *next;
    GSList *list = NULL, *p;
    uint64_t perm = 0, shared = BLK_PERM_ALL;
    int ret;

    /* Make sure that @from doesn't go away until we have successfully attached
     * all of its parents to @to. */
    bdrv_ref(from);

    assert(qemu_get_current_aio_context() == qemu_get_aio_context());
    assert(bdrv_get_aio_context(from) == bdrv_get_aio_context(to));
    bdrv_drained_begin(from);

    /* Put all parents into @list and calculate their cumulative permissions */
    QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) {
        assert(c->bs == from);
        if (!should_update_child(c, to)) {
            continue;
        }
        if (c->frozen) {
            error_setg(errp, "Cannot change '%s' link to '%s'",
                       c->name, from->node_name);
            goto out;
        }
        list = g_slist_prepend(list, c);
        perm |= c->perm;
        shared &= c->shared_perm;
    }

    /* Check whether the required permissions can be granted on @to, ignoring
     * all BdrvChild in @list so that they can't block themselves. */
    ret = bdrv_check_update_perm(to, NULL, perm, shared, list, NULL, errp);
    if (ret < 0) {
        bdrv_abort_perm_update(to);
        goto out;
    }

    /* Now actually perform the change. We performed the permission check for
     * all elements of @list at once, so set the permissions all at once at the
     * very end. */
    for (p = list; p != NULL; p = p->next) {
        c = p->data;

        bdrv_ref(to);
        bdrv_replace_child_noperm(c, to);
        bdrv_unref(from);
    }

    bdrv_get_cumulative_perm(to, &perm, &shared);
    bdrv_set_perm(to, perm, shared);

out:
    g_slist_free(list);
    bdrv_drained_end(from);
    bdrv_unref(from);
}

/*
 * Add new bs contents at the top of an image chain while the chain is
 * live, while keeping required fields on the top layer.
 *
 * This will modify the BlockDriverState fields, and swap contents
 * between bs_new and bs_top. Both bs_new and bs_top are modified.
 *
 * bs_new must not be attached to a BlockBackend.
 *
 * This function does not create any image files.
 *
 * bdrv_append() takes ownership of a bs_new reference and unrefs it because
 * that's what the callers commonly need. bs_new will be referenced by the old
 * parents of bs_top after bdrv_append() returns. If the caller needs to keep a
 * reference of its own, it must call bdrv_ref().
 */
void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
                 Error **errp)
{
    Error *local_err = NULL;

    bdrv_set_backing_hd(bs_new, bs_top, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        goto out;
    }

    bdrv_replace_node(bs_top, bs_new, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        bdrv_set_backing_hd(bs_new, NULL, &error_abort);
        goto out;
    }

    /* bs_new is now referenced by its new parents, we don't need the
     * additional reference any more. */
out:
    bdrv_unref(bs_new);
}

static void bdrv_delete(BlockDriverState *bs)
{
    assert(bdrv_op_blocker_is_empty(bs));
    assert(!bs->refcnt);

    /* remove from list, if necessary */
    if (bs->node_name[0] != '\0') {
        QTAILQ_REMOVE(&graph_bdrv_states, bs, node_list);
    }
    QTAILQ_REMOVE(&all_bdrv_states, bs, bs_list);

    bdrv_close(bs);

    g_free(bs);
}

/*
 * Run consistency checks on an image
 *
 * Returns 0 if the check could be completed (it doesn't mean that the image is
 * free of errors) or -errno when an internal error occurred. The results of the
 * check are stored in res.
 */
static int coroutine_fn bdrv_co_check(BlockDriverState *bs,
                                      BdrvCheckResult *res, BdrvCheckMode fix)
{
    if (bs->drv == NULL) {
        return -ENOMEDIUM;
    }
    if (bs->drv->bdrv_co_check == NULL) {
        return -ENOTSUP;
    }

    memset(res, 0, sizeof(*res));
    return bs->drv->bdrv_co_check(bs, res, fix);
}

typedef struct CheckCo {
    BlockDriverState *bs;
    BdrvCheckResult *res;
    BdrvCheckMode fix;
    int ret;
} CheckCo;

static void coroutine_fn bdrv_check_co_entry(void *opaque)
{
    CheckCo *cco = opaque;
    cco->ret = bdrv_co_check(cco->bs, cco->res, cco->fix);
    aio_wait_kick();
}

int bdrv_check(BlockDriverState *bs,
               BdrvCheckResult *res, BdrvCheckMode fix)
{
    Coroutine *co;
    CheckCo cco = {
        .bs = bs,
        .res = res,
        .ret = -EINPROGRESS,
        .fix = fix,
    };

    if (qemu_in_coroutine()) {
        /* Fast-path if already in coroutine context */
        bdrv_check_co_entry(&cco);
    } else {
        co = qemu_coroutine_create(bdrv_check_co_entry, &cco);
        bdrv_coroutine_enter(bs, co);
        BDRV_POLL_WHILE(bs, cco.ret == -EINPROGRESS);
    }

    return cco.ret;
}

/*
 * Return values:
 * 0        - success
 * -EINVAL  - backing format specified, but no file
 * -ENOSPC  - can't update the backing file because no space is left in the
 *            image file header
 * -ENOTSUP - format driver doesn't support changing the backing file
 */
int bdrv_change_backing_file(BlockDriverState *bs,
    const char *backing_file, const char *backing_fmt)
{
    BlockDriver *drv = bs->drv;
    int ret;

    if (!drv) {
        return -ENOMEDIUM;
    }

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

    if (drv->bdrv_change_backing_file != NULL) {
        ret = drv->bdrv_change_backing_file(bs, backing_file, backing_fmt);
    } else {
        ret = -ENOTSUP;
    }

    if (ret == 0) {
        pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_file ?: "");
        pstrcpy(bs->backing_format, sizeof(bs->backing_format), backing_fmt ?: "");
        pstrcpy(bs->auto_backing_file, sizeof(bs->auto_backing_file),
                backing_file ?: "");
    }
    return ret;
}

/*
 * Finds the image layer in the chain that has 'bs' as its backing file.
 *
 * active is the current topmost image.
 *
 * Returns NULL if bs is not found in active's image chain,
 * or if active == bs.
 *
 * Returns the bottommost base image if bs == NULL.
 */
BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
                                    BlockDriverState *bs)
{
    while (active && bs != backing_bs(active)) {
        active = backing_bs(active);
    }

    return active;
}

/* Given a BDS, searches for the base layer. */
BlockDriverState *bdrv_find_base(BlockDriverState *bs)
{
    return bdrv_find_overlay(bs, NULL);
}

/*
 * Return true if at least one of the backing links between @bs and
 * @base is frozen. @errp is set if that's the case.
 * @base must be reachable from @bs, or NULL.
 */
bool bdrv_is_backing_chain_frozen(BlockDriverState *bs, BlockDriverState *base,
                                  Error **errp)
{
    BlockDriverState *i;

    for (i = bs; i != base; i = backing_bs(i)) {
        if (i->backing && i->backing->frozen) {
            error_setg(errp, "Cannot change '%s' link from '%s' to '%s'",
                       i->backing->name, i->node_name,
                       backing_bs(i)->node_name);
            return true;
        }
    }

    return false;
}

/*
 * Freeze all backing links between @bs and @base.
 * If any of the links is already frozen the operation is aborted and
 * none of the links are modified.
 * @base must be reachable from @bs, or NULL.
 * Returns 0 on success. On failure returns < 0 and sets @errp.
 */
int bdrv_freeze_backing_chain(BlockDriverState *bs, BlockDriverState *base,
                              Error **errp)
{
    BlockDriverState *i;

    if (bdrv_is_backing_chain_frozen(bs, base, errp)) {
        return -EPERM;
    }

    for (i = bs; i != base; i = backing_bs(i)) {
        if (i->backing && backing_bs(i)->never_freeze) {
            error_setg(errp, "Cannot freeze '%s' link to '%s'",
                       i->backing->name, backing_bs(i)->node_name);
            return -EPERM;
        }
    }

    for (i = bs; i != base; i = backing_bs(i)) {
        if (i->backing) {
            i->backing->frozen = true;
        }
    }

    return 0;
}

/*
 * Unfreeze all backing links between @bs and @base. The caller must
 * ensure that all links are frozen before using this function.
 * @base must be reachable from @bs, or NULL.
 */
void bdrv_unfreeze_backing_chain(BlockDriverState *bs, BlockDriverState *base)
{
    BlockDriverState *i;

    for (i = bs; i != base; i = backing_bs(i)) {
        if (i->backing) {
            assert(i->backing->frozen);
            i->backing->frozen = false;
        }
    }
}

/*
 * Drops images above 'base' up to and including 'top', and sets the image
 * above 'top' to have base as its backing file.
 *
 * Requires that the overlay to 'top' is opened r/w, so that the backing file
 * information in 'bs' can be properly updated.
 *
 * E.g., this will convert the following chain:
 * bottom <- base <- intermediate <- top <- active
 *
 * to
 *
 * bottom <- base <- active
 *
 * It is allowed for bottom==base, in which case it converts:
 *
 * base <- intermediate <- top <- active
 *
 * to
 *
 * base <- active
 *
 * If backing_file_str is non-NULL, it will be used when modifying top's
 * overlay image metadata.
 *
 * Error conditions:
 *  if active == top, that is considered an error
 *
 */
int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
                           const char *backing_file_str)
{
    BlockDriverState *explicit_top = top;
    bool update_inherits_from;
    BdrvChild *c, *next;
    Error *local_err = NULL;
    int ret = -EIO;

    bdrv_ref(top);
    bdrv_subtree_drained_begin(top);

    if (!top->drv || !base->drv) {
        goto exit;
    }

    /* Make sure that base is in the backing chain of top */
    if (!bdrv_chain_contains(top, base)) {
        goto exit;
    }

    /* This function changes all links that point to top and makes
     * them point to base. Check that none of them is frozen. */
    QLIST_FOREACH(c, &top->parents, next_parent) {
        if (c->frozen) {
            goto exit;
        }
    }

    /* If 'base' recursively inherits from 'top' then we should set
     * base->inherits_from to top->inherits_from after 'top' and all
     * other intermediate nodes have been dropped.
     * If 'top' is an implicit node (e.g. "commit_top") we should skip
     * it because no one inherits from it. We use explicit_top for that. */
    while (explicit_top && explicit_top->implicit) {
        explicit_top = backing_bs(explicit_top);
    }
    update_inherits_from = bdrv_inherits_from_recursive(base, explicit_top);

    /* success - we can delete the intermediate states, and link top->base */
    /* TODO Check graph modification op blockers (BLK_PERM_GRAPH_MOD) once
     * we've figured out how they should work. */
    if (!backing_file_str) {
        bdrv_refresh_filename(base);
        backing_file_str = base->filename;
    }

    QLIST_FOREACH_SAFE(c, &top->parents, next_parent, next) {
        /* Check whether we are allowed to switch c from top to base */
        GSList *ignore_children = g_slist_prepend(NULL, c);
        ret = bdrv_check_update_perm(base, NULL, c->perm, c->shared_perm,
                                     ignore_children, NULL, &local_err);
        g_slist_free(ignore_children);
        if (ret < 0) {
            error_report_err(local_err);
            goto exit;
        }

        /* If so, update the backing file path in the image file */
        if (c->klass->update_filename) {
            ret = c->klass->update_filename(c, base, backing_file_str,
                                            &local_err);
            if (ret < 0) {
                bdrv_abort_perm_update(base);
                error_report_err(local_err);
                goto exit;
            }
        }

        /* Do the actual switch in the in-memory graph.
         * Completes bdrv_check_update_perm() transaction internally. */
        bdrv_ref(base);
        bdrv_replace_child(c, base);
        bdrv_unref(top);
    }

    if (update_inherits_from) {
        base->inherits_from = explicit_top->inherits_from;
    }

    ret = 0;
exit:
    bdrv_subtree_drained_end(top);
    bdrv_unref(top);
    return ret;
}

/**
 * Length of a allocated file in bytes. Sparse files are counted by actual
 * allocated space. Return < 0 if error or unknown.
 */
int64_t bdrv_get_allocated_file_size(BlockDriverState *bs)
{
    BlockDriver *drv = bs->drv;
    if (!drv) {
        return -ENOMEDIUM;
    }
    if (drv->bdrv_get_allocated_file_size) {
        return drv->bdrv_get_allocated_file_size(bs);
    }
    if (bs->file) {
        return bdrv_get_allocated_file_size(bs->file->bs);
    }
    return -ENOTSUP;
}

/*
 * bdrv_measure:
 * @drv: Format driver
 * @opts: Creation options for new image
 * @in_bs: Existing image containing data for new image (may be NULL)
 * @errp: Error object
 * Returns: A #BlockMeasureInfo (free using qapi_free_BlockMeasureInfo())
 *          or NULL on error
 *
 * Calculate file size required to create a new image.
 *
 * If @in_bs is given then space for allocated clusters and zero clusters
 * from that image are included in the calculation.  If @opts contains a
 * backing file that is shared by @in_bs then backing clusters may be omitted
 * from the calculation.
 *
 * If @in_bs is NULL then the calculation includes no allocated clusters
 * unless a preallocation option is given in @opts.
 *
 * Note that @in_bs may use a different BlockDriver from @drv.
 *
 * If an error occurs the @errp pointer is set.
 */
BlockMeasureInfo *bdrv_measure(BlockDriver *drv, QemuOpts *opts,
                               BlockDriverState *in_bs, Error **errp)
{
    if (!drv->bdrv_measure) {
        error_setg(errp, "Block driver '%s' does not support size measurement",
                   drv->format_name);
        return NULL;
    }

    return drv->bdrv_measure(opts, in_bs, errp);
}

/**
 * Return number of sectors on success, -errno on error.
 */
int64_t bdrv_nb_sectors(BlockDriverState *bs)
{
    BlockDriver *drv = bs->drv;

    if (!drv)
        return -ENOMEDIUM;

    if (drv->has_variable_length) {
        int ret = refresh_total_sectors(bs, bs->total_sectors);
        if (ret < 0) {
            return ret;
        }
    }
    return bs->total_sectors;
}

/**
 * Return length in bytes on success, -errno on error.
 * The length is always a multiple of BDRV_SECTOR_SIZE.
 */
int64_t bdrv_getlength(BlockDriverState *bs)
{
    int64_t ret = bdrv_nb_sectors(bs);

    ret = ret > INT64_MAX / BDRV_SECTOR_SIZE ? -EFBIG : ret;
    return ret < 0 ? ret : ret * BDRV_SECTOR_SIZE;
}

/* return 0 as number of sectors if no device present or error */
void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr)
{
    int64_t nb_sectors = bdrv_nb_sectors(bs);

    *nb_sectors_ptr = nb_sectors < 0 ? 0 : nb_sectors;
}

bool bdrv_is_sg(BlockDriverState *bs)
{
    return bs->sg;
}

bool bdrv_is_encrypted(BlockDriverState *bs)
{
    if (bs->backing && bs->backing->bs->encrypted) {
        return true;
    }
    return bs->encrypted;
}

const char *bdrv_get_format_name(BlockDriverState *bs)
{
    return bs->drv ? bs->drv->format_name : NULL;
}

static int qsort_strcmp(const void *a, const void *b)
{
    return strcmp(*(char *const *)a, *(char *const *)b);
}

void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
                         void *opaque, bool read_only)
{
    BlockDriver *drv;
    int count = 0;
    int i;
    const char **formats = NULL;

    QLIST_FOREACH(drv, &bdrv_drivers, list) {
        if (drv->format_name) {
            bool found = false;
            int i = count;

            if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, read_only)) {
                continue;
            }

            while (formats && i && !found) {
                found = !strcmp(formats[--i], drv->format_name);
            }

            if (!found) {
                formats = g_renew(const char *, formats, count + 1);
                formats[count++] = drv->format_name;
            }
        }
    }

    for (i = 0; i < (int)ARRAY_SIZE(block_driver_modules); i++) {
        const char *format_name = block_driver_modules[i].format_name;

        if (format_name) {
            bool found = false;
            int j = count;

            if (use_bdrv_whitelist &&
                !bdrv_format_is_whitelisted(format_name, read_only)) {
                continue;
            }

            while (formats && j && !found) {
                found = !strcmp(formats[--j], format_name);
            }

            if (!found) {
                formats = g_renew(const char *, formats, count + 1);
                formats[count++] = format_name;
            }
        }
    }

    qsort(formats, count, sizeof(formats[0]), qsort_strcmp);

    for (i = 0; i < count; i++) {
        it(opaque, formats[i]);
    }

    g_free(formats);
}

/* This function is to find a node in the bs graph */
BlockDriverState *bdrv_find_node(const char *node_name)
{
    BlockDriverState *bs;

    assert(node_name);

    QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) {
        if (!strcmp(node_name, bs->node_name)) {
            return bs;
        }
    }
    return NULL;
}

/* Put this QMP function here so it can access the static graph_bdrv_states. */
BlockDeviceInfoList *bdrv_named_nodes_list(bool flat,
                                           Error **errp)
{
    BlockDeviceInfoList *list, *entry;
    BlockDriverState *bs;

    list = NULL;
    QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) {
        BlockDeviceInfo *info = bdrv_block_device_info(NULL, bs, flat, errp);
        if (!info) {
            qapi_free_BlockDeviceInfoList(list);
            return NULL;
        }
        entry = g_malloc0(sizeof(*entry));
        entry->value = info;
        entry->next = list;
        list = entry;
    }

    return list;
}

#define QAPI_LIST_ADD(list, element) do { \
    typeof(list) _tmp = g_new(typeof(*(list)), 1); \
    _tmp->value = (element); \
    _tmp->next = (list); \
    (list) = _tmp; \
} while (0)

typedef struct XDbgBlockGraphConstructor {
    XDbgBlockGraph *graph;
    GHashTable *graph_nodes;
} XDbgBlockGraphConstructor;

static XDbgBlockGraphConstructor *xdbg_graph_new(void)
{
    XDbgBlockGraphConstructor *gr = g_new(XDbgBlockGraphConstructor, 1);

    gr->graph = g_new0(XDbgBlockGraph, 1);
    gr->graph_nodes = g_hash_table_new(NULL, NULL);

    return gr;
}

static XDbgBlockGraph *xdbg_graph_finalize(XDbgBlockGraphConstructor *gr)
{
    XDbgBlockGraph *graph = gr->graph;

    g_hash_table_destroy(gr->graph_nodes);
    g_free(gr);

    return graph;
}

static uintptr_t xdbg_graph_node_num(XDbgBlockGraphConstructor *gr, void *node)
{
    uintptr_t ret = (uintptr_t)g_hash_table_lookup(gr->graph_nodes, node);

    if (ret != 0) {
        return ret;
    }

    /*
     * Start counting from 1, not 0, because 0 interferes with not-found (NULL)
     * answer of g_hash_table_lookup.
     */
    ret = g_hash_table_size(gr->graph_nodes) + 1;
    g_hash_table_insert(gr->graph_nodes, node, (void *)ret);

    return ret;
}

static void xdbg_graph_add_node(XDbgBlockGraphConstructor *gr, void *node,
                                XDbgBlockGraphNodeType type, const char *name)
{
    XDbgBlockGraphNode *n;

    n = g_new0(XDbgBlockGraphNode, 1);

    n->id = xdbg_graph_node_num(gr, node);
    n->type = type;
    n->name = g_strdup(name);

    QAPI_LIST_ADD(gr->graph->nodes, n);
}

static void xdbg_graph_add_edge(XDbgBlockGraphConstructor *gr, void *parent,
                                const BdrvChild *child)
{
    BlockPermission qapi_perm;
    XDbgBlockGraphEdge *edge;

    edge = g_new0(XDbgBlockGraphEdge, 1);

    edge->parent = xdbg_graph_node_num(gr, parent);
    edge->child = xdbg_graph_node_num(gr, child->bs);
    edge->name = g_strdup(child->name);

    for (qapi_perm = 0; qapi_perm < BLOCK_PERMISSION__MAX; qapi_perm++) {
        uint64_t flag = bdrv_qapi_perm_to_blk_perm(qapi_perm);

        if (flag & child->perm) {
            QAPI_LIST_ADD(edge->perm, qapi_perm);
        }
        if (flag & child->shared_perm) {
            QAPI_LIST_ADD(edge->shared_perm, qapi_perm);
        }
    }

    QAPI_LIST_ADD(gr->graph->edges, edge);
}


XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp)
{
    BlockBackend *blk;
    BlockJob *job;
    BlockDriverState *bs;
    BdrvChild *child;
    XDbgBlockGraphConstructor *gr = xdbg_graph_new();

    for (blk = blk_all_next(NULL); blk; blk = blk_all_next(blk)) {
        char *allocated_name = NULL;
        const char *name = blk_name(blk);

        if (!*name) {
            name = allocated_name = blk_get_attached_dev_id(blk);
        }
        xdbg_graph_add_node(gr, blk, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_BACKEND,
                           name);
        g_free(allocated_name);
        if (blk_root(blk)) {
            xdbg_graph_add_edge(gr, blk, blk_root(blk));
        }
    }

    for (job = block_job_next(NULL); job; job = block_job_next(job)) {
        GSList *el;

        xdbg_graph_add_node(gr, job, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_JOB,
                           job->job.id);
        for (el = job->nodes; el; el = el->next) {
            xdbg_graph_add_edge(gr, job, (BdrvChild *)el->data);
        }
    }

    QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) {
        xdbg_graph_add_node(gr, bs, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_DRIVER,
                           bs->node_name);
        QLIST_FOREACH(child, &bs->children, next) {
            xdbg_graph_add_edge(gr, bs, child);
        }
    }

    return xdbg_graph_finalize(gr);
}

BlockDriverState *bdrv_lookup_bs(const char *device,
                                 const char *node_name,
                                 Error **errp)
{
    BlockBackend *blk;
    BlockDriverState *bs;

    if (device) {
        blk = blk_by_name(device);

        if (blk) {
            bs = blk_bs(blk);
            if (!bs) {
                error_setg(errp, "Device '%s' has no medium", device);
            }

            return bs;
        }
    }

    if (node_name) {
        bs = bdrv_find_node(node_name);

        if (bs) {
            return bs;
        }
    }

    error_setg(errp, "Cannot find device=%s nor node_name=%s",
                     device ? device : "",
                     node_name ? node_name : "");
    return NULL;
}

/* If 'base' is in the same chain as 'top', return true. Otherwise,
 * return false.  If either argument is NULL, return false. */
bool bdrv_chain_contains(BlockDriverState *top, BlockDriverState *base)
{
    while (top && top != base) {
        top = backing_bs(top);
    }

    return top != NULL;
}

BlockDriverState *bdrv_next_node(BlockDriverState *bs)
{
    if (!bs) {
        return QTAILQ_FIRST(&graph_bdrv_states);
    }
    return QTAILQ_NEXT(bs, node_list);
}

BlockDriverState *bdrv_next_all_states(BlockDriverState *bs)
{
    if (!bs) {
        return QTAILQ_FIRST(&all_bdrv_states);
    }
    return QTAILQ_NEXT(bs, bs_list);
}

const char *bdrv_get_node_name(const BlockDriverState *bs)
{
    return bs->node_name;
}

const char *bdrv_get_parent_name(const BlockDriverState *bs)
{
    BdrvChild *c;
    const char *name;

    /* If multiple parents have a name, just pick the first one. */
    QLIST_FOREACH(c, &bs->parents, next_parent) {
        if (c->klass->get_name) {
            name = c->klass->get_name(c);
            if (name && *name) {
                return name;
            }
        }
    }

    return NULL;
}

/* TODO check what callers really want: bs->node_name or blk_name() */
const char *bdrv_get_device_name(const BlockDriverState *bs)
{
    return bdrv_get_parent_name(bs) ?: "";
}

/* This can be used to identify nodes that might not have a device
 * name associated. Since node and device names live in the same
 * namespace, the result is unambiguous. The exception is if both are
 * absent, then this returns an empty (non-null) string. */
const char *bdrv_get_device_or_node_name(const BlockDriverState *bs)
{
    return bdrv_get_parent_name(bs) ?: bs->node_name;
}

int bdrv_get_flags(BlockDriverState *bs)
{
    return bs->open_flags;
}

int bdrv_has_zero_init_1(BlockDriverState *bs)
{
    return 1;
}

int bdrv_has_zero_init(BlockDriverState *bs)
{
    if (!bs->drv) {
        return 0;
    }

    /* If BS is a copy on write image, it is initialized to
       the contents of the base image, which may not be zeroes.  */
    if (bs->backing) {
        return 0;
    }
    if (bs->drv->bdrv_has_zero_init) {
        return bs->drv->bdrv_has_zero_init(bs);
    }
    if (bs->file && bs->drv->is_filter) {
        return bdrv_has_zero_init(bs->file->bs);
    }

    /* safe default */
    return 0;
}

bool bdrv_unallocated_blocks_are_zero(BlockDriverState *bs)
{
    BlockDriverInfo bdi;

    if (bs->backing) {
        return false;
    }

    if (bdrv_get_info(bs, &bdi) == 0) {
        return bdi.unallocated_blocks_are_zero;
    }

    return false;
}

bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs)
{
    if (!(bs->open_flags & BDRV_O_UNMAP)) {
        return false;
    }

    return bs->supported_zero_flags & BDRV_REQ_MAY_UNMAP;
}

void bdrv_get_backing_filename(BlockDriverState *bs,
                               char *filename, int filename_size)
{
    pstrcpy(filename, filename_size, bs->backing_file);
}

int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
    BlockDriver *drv = bs->drv;
    /* if bs->drv == NULL, bs is closed, so there's nothing to do here */
    if (!drv) {
        return -ENOMEDIUM;
    }
    if (!drv->bdrv_get_info) {
        if (bs->file && drv->is_filter) {
            return bdrv_get_info(bs->file->bs, bdi);
        }
        return -ENOTSUP;
    }
    memset(bdi, 0, sizeof(*bdi));
    return drv->bdrv_get_info(bs, bdi);
}

ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs,
                                          Error **errp)
{
    BlockDriver *drv = bs->drv;
    if (drv && drv->bdrv_get_specific_info) {
        return drv->bdrv_get_specific_info(bs, errp);
    }
    return NULL;
}

BlockStatsSpecific *bdrv_get_specific_stats(BlockDriverState *bs)
{
    BlockDriver *drv = bs->drv;
    if (!drv || !drv->bdrv_get_specific_stats) {
        return NULL;
    }
    return drv->bdrv_get_specific_stats(bs);
}

void bdrv_debug_event(BlockDriverState *bs, BlkdebugEvent event)
{
    if (!bs || !bs->drv || !bs->drv->bdrv_debug_event) {
        return;
    }

    bs->drv->bdrv_debug_event(bs, event);
}

static BlockDriverState *bdrv_find_debug_node(BlockDriverState *bs)
{
    while (bs && bs->drv && !bs->drv->bdrv_debug_breakpoint) {
        if (bs->file) {
            bs = bs->file->bs;
            continue;
        }

        if (bs->drv->is_filter && bs->backing) {
            bs = bs->backing->bs;
            continue;
        }

        break;
    }

    if (bs && bs->drv && bs->drv->bdrv_debug_breakpoint) {
        assert(bs->drv->bdrv_debug_remove_breakpoint);
        return bs;
    }

    return NULL;
}

int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
                          const char *tag)
{
    bs = bdrv_find_debug_node(bs);
    if (bs) {
        return bs->drv->bdrv_debug_breakpoint(bs, event, tag);
    }

    return -ENOTSUP;
}

int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag)
{
    bs = bdrv_find_debug_node(bs);
    if (bs) {
        return bs->drv->bdrv_debug_remove_breakpoint(bs, tag);
    }

    return -ENOTSUP;
}

int bdrv_debug_resume(BlockDriverState *bs, const char *tag)
{
    while (bs && (!bs->drv || !bs->drv->bdrv_debug_resume)) {
        bs = bs->file ? bs->file->bs : NULL;
    }

    if (bs && bs->drv && bs->drv->bdrv_debug_resume) {
        return bs->drv->bdrv_debug_resume(bs, tag);
    }

    return -ENOTSUP;
}

bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag)
{
    while (bs && bs->drv && !bs->drv->bdrv_debug_is_suspended) {
        bs = bs->file ? bs->file->bs : NULL;
    }

    if (bs && bs->drv && bs->drv->bdrv_debug_is_suspended) {
        return bs->drv->bdrv_debug_is_suspended(bs, tag);
    }

    return false;
}

/* backing_file can either be relative, or absolute, or a protocol.  If it is
 * relative, it must be relative to the chain.  So, passing in bs->filename
 * from a BDS as backing_file should not be done, as that may be relative to
 * the CWD rather than the chain. */
BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
        const char *backing_file)
{
    char *filename_full = NULL;
    char *backing_file_full = NULL;
    char *filename_tmp = NULL;
    int is_protocol = 0;
    BlockDriverState *curr_bs = NULL;
    BlockDriverState *retval = NULL;

    if (!bs || !bs->drv || !backing_file) {
        return NULL;
    }

    filename_full     = g_malloc(PATH_MAX);
    backing_file_full = g_malloc(PATH_MAX);

    is_protocol = path_has_protocol(backing_file);

    for (curr_bs = bs; curr_bs->backing; curr_bs = curr_bs->backing->bs) {

        /* If either of the filename paths is actually a protocol, then
         * compare unmodified paths; otherwise make paths relative */
        if (is_protocol || path_has_protocol(curr_bs->backing_file)) {
            char *backing_file_full_ret;

            if (strcmp(backing_file, curr_bs->backing_file) == 0) {
                retval = curr_bs->backing->bs;
                break;
            }
            /* Also check against the full backing filename for the image */
            backing_file_full_ret = bdrv_get_full_backing_filename(curr_bs,
                                                                   NULL);
            if (backing_file_full_ret) {
                bool equal = strcmp(backing_file, backing_file_full_ret) == 0;
                g_free(backing_file_full_ret);
                if (equal) {
                    retval = curr_bs->backing->bs;
                    break;
                }
            }
        } else {
            /* If not an absolute filename path, make it relative to the current
             * image's filename path */
            filename_tmp = bdrv_make_absolute_filename(curr_bs, backing_file,
                                                       NULL);
            /* We are going to compare canonicalized absolute pathnames */
            if (!filename_tmp || !realpath(filename_tmp, filename_full)) {
                g_free(filename_tmp);
                continue;
            }
            g_free(filename_tmp);

            /* We need to make sure the backing filename we are comparing against
             * is relative to the current image filename (or absolute) */
            filename_tmp = bdrv_get_full_backing_filename(curr_bs, NULL);
            if (!filename_tmp || !realpath(filename_tmp, backing_file_full)) {
                g_free(filename_tmp);
                continue;
            }
            g_free(filename_tmp);

            if (strcmp(backing_file_full, filename_full) == 0) {
                retval = curr_bs->backing->bs;
                break;
            }
        }
    }

    g_free(filename_full);
    g_free(backing_file_full);
    return retval;
}

void bdrv_init(void)
{
    module_call_init(MODULE_INIT_BLOCK);
}

void bdrv_init_with_whitelist(void)
{
    use_bdrv_whitelist = 1;
    bdrv_init();
}

static void coroutine_fn bdrv_co_invalidate_cache(BlockDriverState *bs,
                                                  Error **errp)
{
    BdrvChild *child, *parent;
    uint64_t perm, shared_perm;
    Error *local_err = NULL;
    int ret;
    BdrvDirtyBitmap *bm;

    if (!bs->drv)  {
        return;
    }

    QLIST_FOREACH(child, &bs->children, next) {
        bdrv_co_invalidate_cache(child->bs, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            return;
        }
    }

    /*
     * Update permissions, they may differ for inactive nodes.
     *
     * Note that the required permissions of inactive images are always a
     * subset of the permissions required after activating the image. This
     * allows us to just get the permissions upfront without restricting
     * drv->bdrv_invalidate_cache().
     *
     * It also means that in error cases, we don't have to try and revert to
     * the old permissions (which is an operation that could fail, too). We can
     * just keep the extended permissions for the next time that an activation
     * of the image is tried.
     */
    if (bs->open_flags & BDRV_O_INACTIVE) {
        bs->open_flags &= ~BDRV_O_INACTIVE;
        bdrv_get_cumulative_perm(bs, &perm, &shared_perm);
        ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, NULL, &local_err);
        if (ret < 0) {
            bs->open_flags |= BDRV_O_INACTIVE;
            error_propagate(errp, local_err);
            return;
        }
        bdrv_set_perm(bs, perm, shared_perm);

        if (bs->drv->bdrv_co_invalidate_cache) {
            bs->drv->bdrv_co_invalidate_cache(bs, &local_err);
            if (local_err) {
                bs->open_flags |= BDRV_O_INACTIVE;
                error_propagate(errp, local_err);
                return;
            }
        }

        FOR_EACH_DIRTY_BITMAP(bs, bm) {
            bdrv_dirty_bitmap_skip_store(bm, false);
        }

        ret = refresh_total_sectors(bs, bs->total_sectors);
        if (ret < 0) {
            bs->open_flags |= BDRV_O_INACTIVE;
            error_setg_errno(errp, -ret, "Could not refresh total sector count");
            return;
        }
    }

    QLIST_FOREACH(parent, &bs->parents, next_parent) {
        if (parent->klass->activate) {
            parent->klass->activate(parent, &local_err);
            if (local_err) {
                bs->open_flags |= BDRV_O_INACTIVE;
                error_propagate(errp, local_err);
                return;
            }
        }
    }
}

typedef struct InvalidateCacheCo {
    BlockDriverState *bs;
    Error **errp;
    bool done;
} InvalidateCacheCo;

static void coroutine_fn bdrv_invalidate_cache_co_entry(void *opaque)
{
    InvalidateCacheCo *ico = opaque;
    bdrv_co_invalidate_cache(ico->bs, ico->errp);
    ico->done = true;
    aio_wait_kick();
}

void bdrv_invalidate_cache(BlockDriverState *bs, Error **errp)
{
    Coroutine *co;
    InvalidateCacheCo ico = {
        .bs = bs,
        .done = false,
        .errp = errp
    };

    if (qemu_in_coroutine()) {
        /* Fast-path if already in coroutine context */
        bdrv_invalidate_cache_co_entry(&ico);
    } else {
        co = qemu_coroutine_create(bdrv_invalidate_cache_co_entry, &ico);
        bdrv_coroutine_enter(bs, co);
        BDRV_POLL_WHILE(bs, !ico.done);
    }
}

void bdrv_invalidate_cache_all(Error **errp)
{
    BlockDriverState *bs;
    Error *local_err = NULL;
    BdrvNextIterator it;

    for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
        AioContext *aio_context = bdrv_get_aio_context(bs);

        aio_context_acquire(aio_context);
        bdrv_invalidate_cache(bs, &local_err);
        aio_context_release(aio_context);
        if (local_err) {
            error_propagate(errp, local_err);
            bdrv_next_cleanup(&it);
            return;
        }
    }
}

static bool bdrv_has_bds_parent(BlockDriverState *bs, bool only_active)
{
    BdrvChild *parent;

    QLIST_FOREACH(parent, &bs->parents, next_parent) {
        if (parent->klass->parent_is_bds) {
            BlockDriverState *parent_bs = parent->opaque;
            if (!only_active || !(parent_bs->open_flags & BDRV_O_INACTIVE)) {
                return true;
            }
        }
    }

    return false;
}

static int bdrv_inactivate_recurse(BlockDriverState *bs)
{
    BdrvChild *child, *parent;
    bool tighten_restrictions;
    uint64_t perm, shared_perm;
    int ret;

    if (!bs->drv) {
        return -ENOMEDIUM;
    }

    /* Make sure that we don't inactivate a child before its parent.
     * It will be covered by recursion from the yet active parent. */
    if (bdrv_has_bds_parent(bs, true)) {
        return 0;
    }

    assert(!(bs->open_flags & BDRV_O_INACTIVE));

    /* Inactivate this node */
    if (bs->drv->bdrv_inactivate) {
        ret = bs->drv->bdrv_inactivate(bs);
        if (ret < 0) {
            return ret;
        }
    }

    QLIST_FOREACH(parent, &bs->parents, next_parent) {
        if (parent->klass->inactivate) {
            ret = parent->klass->inactivate(parent);
            if (ret < 0) {
                return ret;
            }
        }
    }

    bs->open_flags |= BDRV_O_INACTIVE;

    /* Update permissions, they may differ for inactive nodes */
    bdrv_get_cumulative_perm(bs, &perm, &shared_perm);
    ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL,
                          &tighten_restrictions, NULL);
    assert(tighten_restrictions == false);
    if (ret < 0) {
        /* We only tried to loosen restrictions, so errors are not fatal */
        bdrv_abort_perm_update(bs);
    } else {
        bdrv_set_perm(bs, perm, shared_perm);
    }


    /* Recursively inactivate children */
    QLIST_FOREACH(child, &bs->children, next) {
        ret = bdrv_inactivate_recurse(child->bs);
        if (ret < 0) {
            return ret;
        }
    }

    return 0;
}

int bdrv_inactivate_all(void)
{
    BlockDriverState *bs = NULL;
    BdrvNextIterator it;
    int ret = 0;
    GSList *aio_ctxs = NULL, *ctx;

    for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
        AioContext *aio_context = bdrv_get_aio_context(bs);

        if (!g_slist_find(aio_ctxs, aio_context)) {
            aio_ctxs = g_slist_prepend(aio_ctxs, aio_context);
            aio_context_acquire(aio_context);
        }
    }

    for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
        /* Nodes with BDS parents are covered by recursion from the last
         * parent that gets inactivated. Don't inactivate them a second
         * time if that has already happened. */
        if (bdrv_has_bds_parent(bs, false)) {
            continue;
        }
        ret = bdrv_inactivate_recurse(bs);
        if (ret < 0) {
            bdrv_next_cleanup(&it);
            goto out;
        }
    }

out:
    for (ctx = aio_ctxs; ctx != NULL; ctx = ctx->next) {
        AioContext *aio_context = ctx->data;
        aio_context_release(aio_context);
    }
    g_slist_free(aio_ctxs);

    return ret;
}

/**************************************************************/
/* removable device support */

/**
 * Return TRUE if the media is present
 */
bool bdrv_is_inserted(BlockDriverState *bs)
{
    BlockDriver *drv = bs->drv;
    BdrvChild *child;

    if (!drv) {
        return false;
    }
    if (drv->bdrv_is_inserted) {
        return drv->bdrv_is_inserted(bs);
    }
    QLIST_FOREACH(child, &bs->children, next) {
        if (!bdrv_is_inserted(child->bs)) {
            return false;
        }
    }
    return true;
}

/**
 * If eject_flag is TRUE, eject the media. Otherwise, close the tray
 */
void bdrv_eject(BlockDriverState *bs, bool eject_flag)
{
    BlockDriver *drv = bs->drv;

    if (drv && drv->bdrv_eject) {
        drv->bdrv_eject(bs, eject_flag);
    }
}

/**
 * Lock or unlock the media (if it is locked, the user won't be able
 * to eject it manually).
 */
void bdrv_lock_medium(BlockDriverState *bs, bool locked)
{
    BlockDriver *drv = bs->drv;

    trace_bdrv_lock_medium(bs, locked);

    if (drv && drv->bdrv_lock_medium) {
        drv->bdrv_lock_medium(bs, locked);
    }
}

/* Get a reference to bs */
void bdrv_ref(BlockDriverState *bs)
{
    bs->refcnt++;
}

/* Release a previously grabbed reference to bs.
 * If after releasing, reference count is zero, the BlockDriverState is
 * deleted. */
void bdrv_unref(BlockDriverState *bs)
{
    if (!bs) {
        return;
    }
    assert(bs->refcnt > 0);
    if (--bs->refcnt == 0) {
        bdrv_delete(bs);
    }
}

struct BdrvOpBlocker {
    Error *reason;
    QLIST_ENTRY(BdrvOpBlocker) list;
};

bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp)
{
    BdrvOpBlocker *blocker;
    assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX);
    if (!QLIST_EMPTY(&bs->op_blockers[op])) {
        blocker = QLIST_FIRST(&bs->op_blockers[op]);
        error_propagate_prepend(errp, error_copy(blocker->reason),
                                "Node '%s' is busy: ",
                                bdrv_get_device_or_node_name(bs));
        return true;
    }
    return false;
}

void bdrv_op_block(BlockDriverState *bs, BlockOpType op, Error *reason)
{
    BdrvOpBlocker *blocker;
    assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX);

    blocker = g_new0(BdrvOpBlocker, 1);
    blocker->reason = reason;
    QLIST_INSERT_HEAD(&bs->op_blockers[op], blocker, list);
}

void bdrv_op_unblock(BlockDriverState *bs, BlockOpType op, Error *reason)
{
    BdrvOpBlocker *blocker, *next;
    assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX);
    QLIST_FOREACH_SAFE(blocker, &bs->op_blockers[op], list, next) {
        if (blocker->reason == reason) {
            QLIST_REMOVE(blocker, list);
            g_free(blocker);
        }
    }
}

void bdrv_op_block_all(BlockDriverState *bs, Error *reason)
{
    int i;
    for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
        bdrv_op_block(bs, i, reason);
    }
}

void bdrv_op_unblock_all(BlockDriverState *bs, Error *reason)
{
    int i;
    for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
        bdrv_op_unblock(bs, i, reason);
    }
}

bool bdrv_op_blocker_is_empty(BlockDriverState *bs)
{
    int i;

    for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
        if (!QLIST_EMPTY(&bs->op_blockers[i])) {
            return false;
        }
    }
    return true;
}

void bdrv_img_create(const char *filename, const char *fmt,
                     const char *base_filename, const char *base_fmt,
                     char *options, uint64_t img_size, int flags, bool quiet,
                     Error **errp)
{
    QemuOptsList *create_opts = NULL;
    QemuOpts *opts = NULL;
    const char *backing_fmt, *backing_file;
    int64_t size;
    BlockDriver *drv, *proto_drv;
    Error *local_err = NULL;
    int ret = 0;

    /* Find driver and parse its options */
    drv = bdrv_find_format(fmt);
    if (!drv) {
        error_setg(errp, "Unknown file format '%s'", fmt);
        return;
    }

    proto_drv = bdrv_find_protocol(filename, true, errp);
    if (!proto_drv) {
        return;
    }

    if (!drv->create_opts) {
        error_setg(errp, "Format driver '%s' does not support image creation",
                   drv->format_name);
        return;
    }

    if (!proto_drv->create_opts) {
        error_setg(errp, "Protocol driver '%s' does not support image creation",
                   proto_drv->format_name);
        return;
    }

    /* Create parameter list */
    create_opts = qemu_opts_append(create_opts, drv->create_opts);
    create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);

    opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);

    /* Parse -o options */
    if (options) {
        qemu_opts_do_parse(opts, options, NULL, &local_err);
        if (local_err) {
            goto out;
        }
    }

    if (!qemu_opt_get(opts, BLOCK_OPT_SIZE)) {
        qemu_opt_set_number(opts, BLOCK_OPT_SIZE, img_size, &error_abort);
    } else if (img_size != UINT64_C(-1)) {
        error_setg(errp, "The image size must be specified only once");
        goto out;
    }

    if (base_filename) {
        qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, base_filename, &local_err);
        if (local_err) {
            error_setg(errp, "Backing file not supported for file format '%s'",
                       fmt);
            goto out;
        }
    }

    if (base_fmt) {
        qemu_opt_set(opts, BLOCK_OPT_BACKING_FMT, base_fmt, &local_err);
        if (local_err) {
            error_setg(errp, "Backing file format not supported for file "
                             "format '%s'", fmt);
            goto out;
        }
    }

    backing_file = qemu_opt_get(opts, BLOCK_OPT_BACKING_FILE);
    if (backing_file) {
        if (!strcmp(filename, backing_file)) {
            error_setg(errp, "Error: Trying to create an image with the "
                             "same filename as the backing file");
            goto out;
        }
    }

    backing_fmt = qemu_opt_get(opts, BLOCK_OPT_BACKING_FMT);

    /* The size for the image must always be specified, unless we have a backing
     * file and we have not been forbidden from opening it. */
    size = qemu_opt_get_size(opts, BLOCK_OPT_SIZE, img_size);
    if (backing_file && !(flags & BDRV_O_NO_BACKING)) {
        BlockDriverState *bs;
        char *full_backing;
        int back_flags;
        QDict *backing_options = NULL;

        full_backing =
            bdrv_get_full_backing_filename_from_filename(filename, backing_file,
                                                         &local_err);
        if (local_err) {
            goto out;
        }
        assert(full_backing);

        /* backing files always opened read-only */
        back_flags = flags;
        back_flags &= ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);

        backing_options = qdict_new();
        if (backing_fmt) {
            qdict_put_str(backing_options, "driver", backing_fmt);
        }
        qdict_put_bool(backing_options, BDRV_OPT_FORCE_SHARE, true);

        bs = bdrv_open(full_backing, NULL, backing_options, back_flags,
                       &local_err);
        g_free(full_backing);
        if (!bs && size != -1) {
            /* Couldn't open BS, but we have a size, so it's nonfatal */
            warn_reportf_err(local_err,
                            "Could not verify backing image. "
                            "This may become an error in future versions.\n");
            local_err = NULL;
        } else if (!bs) {
            /* Couldn't open bs, do not have size */
            error_append_hint(&local_err,
                              "Could not open backing image to determine size.\n");
            goto out;
        } else {
            if (size == -1) {
                /* Opened BS, have no size */
                size = bdrv_getlength(bs);
                if (size < 0) {
                    error_setg_errno(errp, -size, "Could not get size of '%s'",
                                     backing_file);
                    bdrv_unref(bs);
                    goto out;
                }
                qemu_opt_set_number(opts, BLOCK_OPT_SIZE, size, &error_abort);
            }
            bdrv_unref(bs);
        }
    } /* (backing_file && !(flags & BDRV_O_NO_BACKING)) */

    if (size == -1) {
        error_setg(errp, "Image creation needs a size parameter");
        goto out;
    }

    if (!quiet) {
        printf("Formatting '%s', fmt=%s ", filename, fmt);
        qemu_opts_print(opts, " ");
        puts("");
    }

    ret = bdrv_create(drv, filename, opts, &local_err);

    if (ret == -EFBIG) {
        /* This is generally a better message than whatever the driver would
         * deliver (especially because of the cluster_size_hint), since that
         * is most probably not much different from "image too large". */
        const char *cluster_size_hint = "";
        if (qemu_opt_get_size(opts, BLOCK_OPT_CLUSTER_SIZE, 0)) {
            cluster_size_hint = " (try using a larger cluster size)";
        }
        error_setg(errp, "The image size is too large for file format '%s'"
                   "%s", fmt, cluster_size_hint);
        error_free(local_err);
        local_err = NULL;
    }

out:
    qemu_opts_del(opts);
    qemu_opts_free(create_opts);
    error_propagate(errp, local_err);
}

AioContext *bdrv_get_aio_context(BlockDriverState *bs)
{
    return bs ? bs->aio_context : qemu_get_aio_context();
}

void bdrv_coroutine_enter(BlockDriverState *bs, Coroutine *co)
{
    aio_co_enter(bdrv_get_aio_context(bs), co);
}

static void bdrv_do_remove_aio_context_notifier(BdrvAioNotifier *ban)
{
    QLIST_REMOVE(ban, list);
    g_free(ban);
}

static void bdrv_detach_aio_context(BlockDriverState *bs)
{
    BdrvAioNotifier *baf, *baf_tmp;

    assert(!bs->walking_aio_notifiers);
    bs->walking_aio_notifiers = true;
    QLIST_FOREACH_SAFE(baf, &bs->aio_notifiers, list, baf_tmp) {
        if (baf->deleted) {
            bdrv_do_remove_aio_context_notifier(baf);
        } else {
            baf->detach_aio_context(baf->opaque);
        }
    }
    /* Never mind iterating again to check for ->deleted.  bdrv_close() will
     * remove remaining aio notifiers if we aren't called again.
     */
    bs->walking_aio_notifiers = false;

    if (bs->drv && bs->drv->bdrv_detach_aio_context) {
        bs->drv->bdrv_detach_aio_context(bs);
    }

    if (bs->quiesce_counter) {
        aio_enable_external(bs->aio_context);
    }
    bs->aio_context = NULL;
}

static void bdrv_attach_aio_context(BlockDriverState *bs,
                                    AioContext *new_context)
{
    BdrvAioNotifier *ban, *ban_tmp;

    if (bs->quiesce_counter) {
        aio_disable_external(new_context);
    }

    bs->aio_context = new_context;

    if (bs->drv && bs->drv->bdrv_attach_aio_context) {
        bs->drv->bdrv_attach_aio_context(bs, new_context);
    }

    assert(!bs->walking_aio_notifiers);
    bs->walking_aio_notifiers = true;
    QLIST_FOREACH_SAFE(ban, &bs->aio_notifiers, list, ban_tmp) {
        if (ban->deleted) {
            bdrv_do_remove_aio_context_notifier(ban);
        } else {
            ban->attached_aio_context(new_context, ban->opaque);
        }
    }
    bs->walking_aio_notifiers = false;
}

/*
 * Changes the AioContext used for fd handlers, timers, and BHs by this
 * BlockDriverState and all its children and parents.
 *
 * Must be called from the main AioContext.
 *
 * The caller must own the AioContext lock for the old AioContext of bs, but it
 * must not own the AioContext lock for new_context (unless new_context is the
 * same as the current context of bs).
 *
 * @ignore will accumulate all visited BdrvChild object. The caller is
 * responsible for freeing the list afterwards.
 */
void bdrv_set_aio_context_ignore(BlockDriverState *bs,
                                 AioContext *new_context, GSList **ignore)
{
    AioContext *old_context = bdrv_get_aio_context(bs);
    BdrvChild *child;

    g_assert(qemu_get_current_aio_context() == qemu_get_aio_context());

    if (old_context == new_context) {
        return;
    }

    bdrv_drained_begin(bs);

    QLIST_FOREACH(child, &bs->children, next) {
        if (g_slist_find(*ignore, child)) {
            continue;
        }
        *ignore = g_slist_prepend(*ignore, child);
        bdrv_set_aio_context_ignore(child->bs, new_context, ignore);
    }
    QLIST_FOREACH(child, &bs->parents, next_parent) {
        if (g_slist_find(*ignore, child)) {
            continue;
        }
        assert(child->klass->set_aio_ctx);
        *ignore = g_slist_prepend(*ignore, child);
        child->klass->set_aio_ctx(child, new_context, ignore);
    }

    bdrv_detach_aio_context(bs);

    /* Acquire the new context, if necessary */
    if (qemu_get_aio_context() != new_context) {
        aio_context_acquire(new_context);
    }

    bdrv_attach_aio_context(bs, new_context);

    /*
     * If this function was recursively called from
     * bdrv_set_aio_context_ignore(), there may be nodes in the
     * subtree that have not yet been moved to the new AioContext.
     * Release the old one so bdrv_drained_end() can poll them.
     */
    if (qemu_get_aio_context() != old_context) {
        aio_context_release(old_context);
    }

    bdrv_drained_end(bs);

    if (qemu_get_aio_context() != old_context) {
        aio_context_acquire(old_context);
    }
    if (qemu_get_aio_context() != new_context) {
        aio_context_release(new_context);
    }
}

static bool bdrv_parent_can_set_aio_context(BdrvChild *c, AioContext *ctx,
                                            GSList **ignore, Error **errp)
{
    if (g_slist_find(*ignore, c)) {
        return true;
    }
    *ignore = g_slist_prepend(*ignore, c);

    /*
     * A BdrvChildClass that doesn't handle AioContext changes cannot
     * tolerate any AioContext changes
     */
    if (!c->klass->can_set_aio_ctx) {
        char *user = bdrv_child_user_desc(c);
        error_setg(errp, "Changing iothreads is not supported by %s", user);
        g_free(user);
        return false;
    }
    if (!c->klass->can_set_aio_ctx(c, ctx, ignore, errp)) {
        assert(!errp || *errp);
        return false;
    }
    return true;
}

bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx,
                                    GSList **ignore, Error **errp)
{
    if (g_slist_find(*ignore, c)) {
        return true;
    }
    *ignore = g_slist_prepend(*ignore, c);
    return bdrv_can_set_aio_context(c->bs, ctx, ignore, errp);
}

/* @ignore will accumulate all visited BdrvChild object. The caller is
 * responsible for freeing the list afterwards. */
bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx,
                              GSList **ignore, Error **errp)
{
    BdrvChild *c;

    if (bdrv_get_aio_context(bs) == ctx) {
        return true;
    }

    QLIST_FOREACH(c, &bs->parents, next_parent) {
        if (!bdrv_parent_can_set_aio_context(c, ctx, ignore, errp)) {
            return false;
        }
    }
    QLIST_FOREACH(c, &bs->children, next) {
        if (!bdrv_child_can_set_aio_context(c, ctx, ignore, errp)) {
            return false;
        }
    }

    return true;
}

int bdrv_child_try_set_aio_context(BlockDriverState *bs, AioContext *ctx,
                                   BdrvChild *ignore_child, Error **errp)
{
    GSList *ignore;
    bool ret;

    ignore = ignore_child ? g_slist_prepend(NULL, ignore_child) : NULL;
    ret = bdrv_can_set_aio_context(bs, ctx, &ignore, errp);
    g_slist_free(ignore);

    if (!ret) {
        return -EPERM;
    }

    ignore = ignore_child ? g_slist_prepend(NULL, ignore_child) : NULL;
    bdrv_set_aio_context_ignore(bs, ctx, &ignore);
    g_slist_free(ignore);

    return 0;
}

int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx,
                             Error **errp)
{
    return bdrv_child_try_set_aio_context(bs, ctx, NULL, errp);
}

void bdrv_add_aio_context_notifier(BlockDriverState *bs,
        void (*attached_aio_context)(AioContext *new_context, void *opaque),
        void (*detach_aio_context)(void *opaque), void *opaque)
{
    BdrvAioNotifier *ban = g_new(BdrvAioNotifier, 1);
    *ban = (BdrvAioNotifier){
        .attached_aio_context = attached_aio_context,
        .detach_aio_context   = detach_aio_context,
        .opaque               = opaque
    };

    QLIST_INSERT_HEAD(&bs->aio_notifiers, ban, list);
}

void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
                                      void (*attached_aio_context)(AioContext *,
                                                                   void *),
                                      void (*detach_aio_context)(void *),
                                      void *opaque)
{
    BdrvAioNotifier *ban, *ban_next;

    QLIST_FOREACH_SAFE(ban, &bs->aio_notifiers, list, ban_next) {
        if (ban->attached_aio_context == attached_aio_context &&
            ban->detach_aio_context   == detach_aio_context   &&
            ban->opaque               == opaque               &&
            ban->deleted              == false)
        {
            if (bs->walking_aio_notifiers) {
                ban->deleted = true;
            } else {
                bdrv_do_remove_aio_context_notifier(ban);
            }
            return;
        }
    }

    abort();
}

int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts,
                       BlockDriverAmendStatusCB *status_cb, void *cb_opaque,
                       Error **errp)
{
    if (!bs->drv) {
        error_setg(errp, "Node is ejected");
        return -ENOMEDIUM;
    }
    if (!bs->drv->bdrv_amend_options) {
        error_setg(errp, "Block driver '%s' does not support option amendment",
                   bs->drv->format_name);
        return -ENOTSUP;
    }
    return bs->drv->bdrv_amend_options(bs, opts, status_cb, cb_opaque, errp);
}

/*
 * This function checks whether the given @to_replace is allowed to be
 * replaced by a node that always shows the same data as @bs.  This is
 * used for example to verify whether the mirror job can replace
 * @to_replace by the target mirrored from @bs.
 * To be replaceable, @bs and @to_replace may either be guaranteed to
 * always show the same data (because they are only connected through
 * filters), or some driver may allow replacing one of its children
 * because it can guarantee that this child's data is not visible at
 * all (for example, for dissenting quorum children that have no other
 * parents).
 */
bool bdrv_recurse_can_replace(BlockDriverState *bs,
                              BlockDriverState *to_replace)
{
    if (!bs || !bs->drv) {
        return false;
    }

    if (bs == to_replace) {
        return true;
    }

    /* See what the driver can do */
    if (bs->drv->bdrv_recurse_can_replace) {
        return bs->drv->bdrv_recurse_can_replace(bs, to_replace);
    }

    /* For filters without an own implementation, we can recurse on our own */
    if (bs->drv->is_filter) {
        BdrvChild *child = bs->file ?: bs->backing;
        return bdrv_recurse_can_replace(child->bs, to_replace);
    }

    /* Safe default */
    return false;
}

/*
 * Check whether the given @node_name can be replaced by a node that
 * has the same data as @parent_bs.  If so, return @node_name's BDS;
 * NULL otherwise.
 *
 * @node_name must be a (recursive) *child of @parent_bs (or this
 * function will return NULL).
 *
 * The result (whether the node can be replaced or not) is only valid
 * for as long as no graph or permission changes occur.
 */
BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs,
                                        const char *node_name, Error **errp)
{
    BlockDriverState *to_replace_bs = bdrv_find_node(node_name);
    AioContext *aio_context;

    if (!to_replace_bs) {
        error_setg(errp, "Node name '%s' not found", node_name);
        return NULL;
    }

    aio_context = bdrv_get_aio_context(to_replace_bs);
    aio_context_acquire(aio_context);

    if (bdrv_op_is_blocked(to_replace_bs, BLOCK_OP_TYPE_REPLACE, errp)) {
        to_replace_bs = NULL;
        goto out;
    }

    /* We don't want arbitrary node of the BDS chain to be replaced only the top
     * most non filter in order to prevent data corruption.
     * Another benefit is that this tests exclude backing files which are
     * blocked by the backing blockers.
     */
    if (!bdrv_recurse_can_replace(parent_bs, to_replace_bs)) {
        error_setg(errp, "Cannot replace '%s' by a node mirrored from '%s', "
                   "because it cannot be guaranteed that doing so would not "
                   "lead to an abrupt change of visible data",
                   node_name, parent_bs->node_name);
        to_replace_bs = NULL;
        goto out;
    }

out:
    aio_context_release(aio_context);
    return to_replace_bs;
}

/**
 * Iterates through the list of runtime option keys that are said to
 * be "strong" for a BDS.  An option is called "strong" if it changes
 * a BDS's data.  For example, the null block driver's "size" and
 * "read-zeroes" options are strong, but its "latency-ns" option is
 * not.
 *
 * If a key returned by this function ends with a dot, all options
 * starting with that prefix are strong.
 */
static const char *const *strong_options(BlockDriverState *bs,
                                         const char *const *curopt)
{
    static const char *const global_options[] = {
        "driver", "filename", NULL
    };

    if (!curopt) {
        return &global_options[0];
    }

    curopt++;
    if (curopt == &global_options[ARRAY_SIZE(global_options) - 1] && bs->drv) {
        curopt = bs->drv->strong_runtime_opts;
    }

    return (curopt && *curopt) ? curopt : NULL;
}

/**
 * Copies all strong runtime options from bs->options to the given
 * QDict.  The set of strong option keys is determined by invoking
 * strong_options().
 *
 * Returns true iff any strong option was present in bs->options (and
 * thus copied to the target QDict) with the exception of "filename"
 * and "driver".  The caller is expected to use this value to decide
 * whether the existence of strong options prevents the generation of
 * a plain filename.
 */
static bool append_strong_runtime_options(QDict *d, BlockDriverState *bs)
{
    bool found_any = false;
    const char *const *option_name = NULL;

    if (!bs->drv) {
        return false;
    }

    while ((option_name = strong_options(bs, option_name))) {
        bool option_given = false;

        assert(strlen(*option_name) > 0);
        if ((*option_name)[strlen(*option_name) - 1] != '.') {
            QObject *entry = qdict_get(bs->options, *option_name);
            if (!entry) {
                continue;
            }

            qdict_put_obj(d, *option_name, qobject_ref(entry));
            option_given = true;
        } else {
            const QDictEntry *entry;
            for (entry = qdict_first(bs->options); entry;
                 entry = qdict_next(bs->options, entry))
            {
                if (strstart(qdict_entry_key(entry), *option_name, NULL)) {
                    qdict_put_obj(d, qdict_entry_key(entry),
                                  qobject_ref(qdict_entry_value(entry)));
                    option_given = true;
                }
            }
        }

        /* While "driver" and "filename" need to be included in a JSON filename,
         * their existence does not prohibit generation of a plain filename. */
        if (!found_any && option_given &&
            strcmp(*option_name, "driver") && strcmp(*option_name, "filename"))
        {
            found_any = true;
        }
    }

    if (!qdict_haskey(d, "driver")) {
        /* Drivers created with bdrv_new_open_driver() may not have a
         * @driver option.  Add it here. */
        qdict_put_str(d, "driver", bs->drv->format_name);
    }

    return found_any;
}

/* Note: This function may return false positives; it may return true
 * even if opening the backing file specified by bs's image header
 * would result in exactly bs->backing. */
static bool bdrv_backing_overridden(BlockDriverState *bs)
{
    if (bs->backing) {
        return strcmp(bs->auto_backing_file,
                      bs->backing->bs->filename);
    } else {
        /* No backing BDS, so if the image header reports any backing
         * file, it must have been suppressed */
        return bs->auto_backing_file[0] != '\0';
    }
}

/* Updates the following BDS fields:
 *  - exact_filename: A filename which may be used for opening a block device
 *                    which (mostly) equals the given BDS (even without any
 *                    other options; so reading and writing must return the same
 *                    results, but caching etc. may be different)
 *  - full_open_options: Options which, when given when opening a block device
 *                       (without a filename), result in a BDS (mostly)
 *                       equalling the given one
 *  - filename: If exact_filename is set, it is copied here. Otherwise,
 *              full_open_options is converted to a JSON object, prefixed with
 *              "json:" (for use through the JSON pseudo protocol) and put here.
 */
void bdrv_refresh_filename(BlockDriverState *bs)
{
    BlockDriver *drv = bs->drv;
    BdrvChild *child;
    QDict *opts;
    bool backing_overridden;
    bool generate_json_filename; /* Whether our default implementation should
                                    fill exact_filename (false) or not (true) */

    if (!drv) {
        return;
    }

    /* This BDS's file name may depend on any of its children's file names, so
     * refresh those first */
    QLIST_FOREACH(child, &bs->children, next) {
        bdrv_refresh_filename(child->bs);
    }

    if (bs->implicit) {
        /* For implicit nodes, just copy everything from the single child */
        child = QLIST_FIRST(&bs->children);
        assert(QLIST_NEXT(child, next) == NULL);

        pstrcpy(bs->exact_filename, sizeof(bs->exact_filename),
                child->bs->exact_filename);
        pstrcpy(bs->filename, sizeof(bs->filename), child->bs->filename);

        qobject_unref(bs->full_open_options);
        bs->full_open_options = qobject_ref(child->bs->full_open_options);

        return;
    }

    backing_overridden = bdrv_backing_overridden(bs);

    if (bs->open_flags & BDRV_O_NO_IO) {
        /* Without I/O, the backing file does not change anything.
         * Therefore, in such a case (primarily qemu-img), we can
         * pretend the backing file has not been overridden even if
         * it technically has been. */
        backing_overridden = false;
    }

    /* Gather the options QDict */
    opts = qdict_new();
    generate_json_filename = append_strong_runtime_options(opts, bs);
    generate_json_filename |= backing_overridden;

    if (drv->bdrv_gather_child_options) {
        /* Some block drivers may not want to present all of their children's
         * options, or name them differently from BdrvChild.name */
        drv->bdrv_gather_child_options(bs, opts, backing_overridden);
    } else {
        QLIST_FOREACH(child, &bs->children, next) {
            if (child == bs->backing && !backing_overridden) {
                /* We can skip the backing BDS if it has not been overridden */
                continue;
            }

            qdict_put(opts, child->name,
                      qobject_ref(child->bs->full_open_options));
        }

        if (backing_overridden && !bs->backing) {
            /* Force no backing file */
            qdict_put_null(opts, "backing");
        }
    }

    qobject_unref(bs->full_open_options);
    bs->full_open_options = opts;

    if (drv->bdrv_refresh_filename) {
        /* Obsolete information is of no use here, so drop the old file name
         * information before refreshing it */
        bs->exact_filename[0] = '\0';

        drv->bdrv_refresh_filename(bs);
    } else if (bs->file) {
        /* Try to reconstruct valid information from the underlying file */

        bs->exact_filename[0] = '\0';

        /*
         * We can use the underlying file's filename if:
         * - it has a filename,
         * - the file is a protocol BDS, and
         * - opening that file (as this BDS's format) will automatically create
         *   the BDS tree we have right now, that is:
         *   - the user did not significantly change this BDS's behavior with
         *     some explicit (strong) options
         *   - no non-file child of this BDS has been overridden by the user
         *   Both of these conditions are represented by generate_json_filename.
         */
        if (bs->file->bs->exact_filename[0] &&
            bs->file->bs->drv->bdrv_file_open &&
            !generate_json_filename)
        {
            strcpy(bs->exact_filename, bs->file->bs->exact_filename);
        }
    }

    if (bs->exact_filename[0]) {
        pstrcpy(bs->filename, sizeof(bs->filename), bs->exact_filename);
    } else {
        QString *json = qobject_to_json(QOBJECT(bs->full_open_options));
        if (snprintf(bs->filename, sizeof(bs->filename), "json:%s",
                     qstring_get_str(json)) >= sizeof(bs->filename)) {
            /* Give user a hint if we truncated things. */
            strcpy(bs->filename + sizeof(bs->filename) - 4, "...");
        }
        qobject_unref(json);
    }
}

char *bdrv_dirname(BlockDriverState *bs, Error **errp)
{
    BlockDriver *drv = bs->drv;

    if (!drv) {
        error_setg(errp, "Node '%s' is ejected", bs->node_name);
        return NULL;
    }

    if (drv->bdrv_dirname) {
        return drv->bdrv_dirname(bs, errp);
    }

    if (bs->file) {
        return bdrv_dirname(bs->file->bs, errp);
    }

    bdrv_refresh_filename(bs);
    if (bs->exact_filename[0] != '\0') {
        return path_combine(bs->exact_filename, "");
    }

    error_setg(errp, "Cannot generate a base directory for %s nodes",
               drv->format_name);
    return NULL;
}

/*
 * Hot add/remove a BDS's child. So the user can take a child offline when
 * it is broken and take a new child online
 */
void bdrv_add_child(BlockDriverState *parent_bs, BlockDriverState *child_bs,
                    Error **errp)
{

    if (!parent_bs->drv || !parent_bs->drv->bdrv_add_child) {
        error_setg(errp, "The node %s does not support adding a child",
                   bdrv_get_device_or_node_name(parent_bs));
        return;
    }

    if (!QLIST_EMPTY(&child_bs->parents)) {
        error_setg(errp, "The node %s already has a parent",
                   child_bs->node_name);
        return;
    }

    parent_bs->drv->bdrv_add_child(parent_bs, child_bs, errp);
}

void bdrv_del_child(BlockDriverState *parent_bs, BdrvChild *child, Error **errp)
{
    BdrvChild *tmp;

    if (!parent_bs->drv || !parent_bs->drv->bdrv_del_child) {
        error_setg(errp, "The node %s does not support removing a child",
                   bdrv_get_device_or_node_name(parent_bs));
        return;
    }

    QLIST_FOREACH(tmp, &parent_bs->children, next) {
        if (tmp == child) {
            break;
        }
    }

    if (!tmp) {
        error_setg(errp, "The node %s does not have a child named %s",
                   bdrv_get_device_or_node_name(parent_bs),
                   bdrv_get_device_or_node_name(child->bs));
        return;
    }

    parent_bs->drv->bdrv_del_child(parent_bs, child, errp);
}

int bdrv_make_empty(BdrvChild *c, Error **errp)
{
    BlockDriver *drv = c->bs->drv;
    int ret;

    assert(c->perm & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED));

    if (!drv->bdrv_make_empty) {
        error_setg(errp, "%s does not support emptying nodes",
                   drv->format_name);
        return -ENOTSUP;
    }

    ret = drv->bdrv_make_empty(c->bs);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Failed to empty %s",
                         c->bs->filename);
        return ret;
    }

    return 0;
}