aboutsummaryrefslogtreecommitdiff
path: root/block/io.c
blob: 7d30e61edc6ca0faa2c0d73a3e57044eaab42fd4 (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
/*
 * Block layer I/O functions
 *
 * 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 "trace.h"
#include "sysemu/block-backend.h"
#include "block/aio-wait.h"
#include "block/blockjob.h"
#include "block/blockjob_int.h"
#include "block/block_int.h"
#include "qemu/cutils.h"
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "sysemu/replay.h"

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

/* Maximum bounce buffer for copy-on-read and write zeroes, in bytes */
#define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS)

static void bdrv_parent_cb_resize(BlockDriverState *bs);
static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
    int64_t offset, int bytes, BdrvRequestFlags flags);

static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore,
                                      bool ignore_bds_parents)
{
    BdrvChild *c, *next;

    QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) {
        if (c == ignore || (ignore_bds_parents && c->role->parent_is_bds)) {
            continue;
        }
        bdrv_parent_drained_begin_single(c, false);
    }
}

static void bdrv_parent_drained_end_single_no_poll(BdrvChild *c,
                                                   int *drained_end_counter)
{
    assert(c->parent_quiesce_counter > 0);
    c->parent_quiesce_counter--;
    if (c->role->drained_end) {
        c->role->drained_end(c, drained_end_counter);
    }
}

void bdrv_parent_drained_end_single(BdrvChild *c)
{
    int drained_end_counter = 0;
    bdrv_parent_drained_end_single_no_poll(c, &drained_end_counter);
    BDRV_POLL_WHILE(c->bs, atomic_read(&drained_end_counter) > 0);
}

static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore,
                                    bool ignore_bds_parents,
                                    int *drained_end_counter)
{
    BdrvChild *c;

    QLIST_FOREACH(c, &bs->parents, next_parent) {
        if (c == ignore || (ignore_bds_parents && c->role->parent_is_bds)) {
            continue;
        }
        bdrv_parent_drained_end_single_no_poll(c, drained_end_counter);
    }
}

static bool bdrv_parent_drained_poll_single(BdrvChild *c)
{
    if (c->role->drained_poll) {
        return c->role->drained_poll(c);
    }
    return false;
}

static bool bdrv_parent_drained_poll(BlockDriverState *bs, BdrvChild *ignore,
                                     bool ignore_bds_parents)
{
    BdrvChild *c, *next;
    bool busy = false;

    QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) {
        if (c == ignore || (ignore_bds_parents && c->role->parent_is_bds)) {
            continue;
        }
        busy |= bdrv_parent_drained_poll_single(c);
    }

    return busy;
}

void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll)
{
    c->parent_quiesce_counter++;
    if (c->role->drained_begin) {
        c->role->drained_begin(c);
    }
    if (poll) {
        BDRV_POLL_WHILE(c->bs, bdrv_parent_drained_poll_single(c));
    }
}

static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
{
    dst->opt_transfer = MAX(dst->opt_transfer, src->opt_transfer);
    dst->max_transfer = MIN_NON_ZERO(dst->max_transfer, src->max_transfer);
    dst->opt_mem_alignment = MAX(dst->opt_mem_alignment,
                                 src->opt_mem_alignment);
    dst->min_mem_alignment = MAX(dst->min_mem_alignment,
                                 src->min_mem_alignment);
    dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov);
}

void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
{
    BlockDriver *drv = bs->drv;
    Error *local_err = NULL;

    memset(&bs->bl, 0, sizeof(bs->bl));

    if (!drv) {
        return;
    }

    /* Default alignment based on whether driver has byte interface */
    bs->bl.request_alignment = (drv->bdrv_co_preadv ||
                                drv->bdrv_aio_preadv ||
                                drv->bdrv_co_preadv_part) ? 1 : 512;

    /* Take some limits from the children as a default */
    if (bs->file) {
        bdrv_refresh_limits(bs->file->bs, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            return;
        }
        bdrv_merge_limits(&bs->bl, &bs->file->bs->bl);
    } else {
        bs->bl.min_mem_alignment = 512;
        bs->bl.opt_mem_alignment = qemu_real_host_page_size;

        /* Safe default since most protocols use readv()/writev()/etc */
        bs->bl.max_iov = IOV_MAX;
    }

    if (bs->backing) {
        bdrv_refresh_limits(bs->backing->bs, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            return;
        }
        bdrv_merge_limits(&bs->bl, &bs->backing->bs->bl);
    }

    /* Then let the driver override it */
    if (drv->bdrv_refresh_limits) {
        drv->bdrv_refresh_limits(bs, errp);
    }
}

/**
 * The copy-on-read flag is actually a reference count so multiple users may
 * use the feature without worrying about clobbering its previous state.
 * Copy-on-read stays enabled until all users have called to disable it.
 */
void bdrv_enable_copy_on_read(BlockDriverState *bs)
{
    atomic_inc(&bs->copy_on_read);
}

void bdrv_disable_copy_on_read(BlockDriverState *bs)
{
    int old = atomic_fetch_dec(&bs->copy_on_read);
    assert(old >= 1);
}

typedef struct {
    Coroutine *co;
    BlockDriverState *bs;
    bool done;
    bool begin;
    bool recursive;
    bool poll;
    BdrvChild *parent;
    bool ignore_bds_parents;
    int *drained_end_counter;
} BdrvCoDrainData;

static void coroutine_fn bdrv_drain_invoke_entry(void *opaque)
{
    BdrvCoDrainData *data = opaque;
    BlockDriverState *bs = data->bs;

    if (data->begin) {
        bs->drv->bdrv_co_drain_begin(bs);
    } else {
        bs->drv->bdrv_co_drain_end(bs);
    }

    /* Set data->done and decrement drained_end_counter before bdrv_wakeup() */
    atomic_mb_set(&data->done, true);
    if (!data->begin) {
        atomic_dec(data->drained_end_counter);
    }
    bdrv_dec_in_flight(bs);

    g_free(data);
}

/* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */
static void bdrv_drain_invoke(BlockDriverState *bs, bool begin,
                              int *drained_end_counter)
{
    BdrvCoDrainData *data;

    if (!bs->drv || (begin && !bs->drv->bdrv_co_drain_begin) ||
            (!begin && !bs->drv->bdrv_co_drain_end)) {
        return;
    }

    data = g_new(BdrvCoDrainData, 1);
    *data = (BdrvCoDrainData) {
        .bs = bs,
        .done = false,
        .begin = begin,
        .drained_end_counter = drained_end_counter,
    };

    if (!begin) {
        atomic_inc(drained_end_counter);
    }

    /* Make sure the driver callback completes during the polling phase for
     * drain_begin. */
    bdrv_inc_in_flight(bs);
    data->co = qemu_coroutine_create(bdrv_drain_invoke_entry, data);
    aio_co_schedule(bdrv_get_aio_context(bs), data->co);
}

/* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */
bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
                     BdrvChild *ignore_parent, bool ignore_bds_parents)
{
    BdrvChild *child, *next;

    if (bdrv_parent_drained_poll(bs, ignore_parent, ignore_bds_parents)) {
        return true;
    }

    if (atomic_read(&bs->in_flight)) {
        return true;
    }

    if (recursive) {
        assert(!ignore_bds_parents);
        QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
            if (bdrv_drain_poll(child->bs, recursive, child, false)) {
                return true;
            }
        }
    }

    return false;
}

static bool bdrv_drain_poll_top_level(BlockDriverState *bs, bool recursive,
                                      BdrvChild *ignore_parent)
{
    return bdrv_drain_poll(bs, recursive, ignore_parent, false);
}

static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
                                  BdrvChild *parent, bool ignore_bds_parents,
                                  bool poll);
static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
                                BdrvChild *parent, bool ignore_bds_parents,
                                int *drained_end_counter);

static void bdrv_co_drain_bh_cb(void *opaque)
{
    BdrvCoDrainData *data = opaque;
    Coroutine *co = data->co;
    BlockDriverState *bs = data->bs;

    if (bs) {
        AioContext *ctx = bdrv_get_aio_context(bs);
        AioContext *co_ctx = qemu_coroutine_get_aio_context(co);

        /*
         * When the coroutine yielded, the lock for its home context was
         * released, so we need to re-acquire it here. If it explicitly
         * acquired a different context, the lock is still held and we don't
         * want to lock it a second time (or AIO_WAIT_WHILE() would hang).
         */
        if (ctx == co_ctx) {
            aio_context_acquire(ctx);
        }
        bdrv_dec_in_flight(bs);
        if (data->begin) {
            assert(!data->drained_end_counter);
            bdrv_do_drained_begin(bs, data->recursive, data->parent,
                                  data->ignore_bds_parents, data->poll);
        } else {
            assert(!data->poll);
            bdrv_do_drained_end(bs, data->recursive, data->parent,
                                data->ignore_bds_parents,
                                data->drained_end_counter);
        }
        if (ctx == co_ctx) {
            aio_context_release(ctx);
        }
    } else {
        assert(data->begin);
        bdrv_drain_all_begin();
    }

    data->done = true;
    aio_co_wake(co);
}

static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
                                                bool begin, bool recursive,
                                                BdrvChild *parent,
                                                bool ignore_bds_parents,
                                                bool poll,
                                                int *drained_end_counter)
{
    BdrvCoDrainData data;

    /* Calling bdrv_drain() from a BH ensures the current coroutine yields and
     * other coroutines run if they were queued by aio_co_enter(). */

    assert(qemu_in_coroutine());
    data = (BdrvCoDrainData) {
        .co = qemu_coroutine_self(),
        .bs = bs,
        .done = false,
        .begin = begin,
        .recursive = recursive,
        .parent = parent,
        .ignore_bds_parents = ignore_bds_parents,
        .poll = poll,
        .drained_end_counter = drained_end_counter,
    };

    if (bs) {
        bdrv_inc_in_flight(bs);
    }
    replay_bh_schedule_oneshot_event(bdrv_get_aio_context(bs),
                                     bdrv_co_drain_bh_cb, &data);

    qemu_coroutine_yield();
    /* If we are resumed from some other event (such as an aio completion or a
     * timer callback), it is a bug in the caller that should be fixed. */
    assert(data.done);
}

void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
                                   BdrvChild *parent, bool ignore_bds_parents)
{
    assert(!qemu_in_coroutine());

    /* Stop things in parent-to-child order */
    if (atomic_fetch_inc(&bs->quiesce_counter) == 0) {
        aio_disable_external(bdrv_get_aio_context(bs));
    }

    bdrv_parent_drained_begin(bs, parent, ignore_bds_parents);
    bdrv_drain_invoke(bs, true, NULL);
}

static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
                                  BdrvChild *parent, bool ignore_bds_parents,
                                  bool poll)
{
    BdrvChild *child, *next;

    if (qemu_in_coroutine()) {
        bdrv_co_yield_to_drain(bs, true, recursive, parent, ignore_bds_parents,
                               poll, NULL);
        return;
    }

    bdrv_do_drained_begin_quiesce(bs, parent, ignore_bds_parents);

    if (recursive) {
        assert(!ignore_bds_parents);
        bs->recursive_quiesce_counter++;
        QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
            bdrv_do_drained_begin(child->bs, true, child, ignore_bds_parents,
                                  false);
        }
    }

    /*
     * Wait for drained requests to finish.
     *
     * Calling BDRV_POLL_WHILE() only once for the top-level node is okay: The
     * call is needed so things in this AioContext can make progress even
     * though we don't return to the main AioContext loop - this automatically
     * includes other nodes in the same AioContext and therefore all child
     * nodes.
     */
    if (poll) {
        assert(!ignore_bds_parents);
        BDRV_POLL_WHILE(bs, bdrv_drain_poll_top_level(bs, recursive, parent));
    }
}

void bdrv_drained_begin(BlockDriverState *bs)
{
    bdrv_do_drained_begin(bs, false, NULL, false, true);
}

void bdrv_subtree_drained_begin(BlockDriverState *bs)
{
    bdrv_do_drained_begin(bs, true, NULL, false, true);
}

/**
 * This function does not poll, nor must any of its recursively called
 * functions.  The *drained_end_counter pointee will be incremented
 * once for every background operation scheduled, and decremented once
 * the operation settles.  Therefore, the pointer must remain valid
 * until the pointee reaches 0.  That implies that whoever sets up the
 * pointee has to poll until it is 0.
 *
 * We use atomic operations to access *drained_end_counter, because
 * (1) when called from bdrv_set_aio_context_ignore(), the subgraph of
 *     @bs may contain nodes in different AioContexts,
 * (2) bdrv_drain_all_end() uses the same counter for all nodes,
 *     regardless of which AioContext they are in.
 */
static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
                                BdrvChild *parent, bool ignore_bds_parents,
                                int *drained_end_counter)
{
    BdrvChild *child;
    int old_quiesce_counter;

    assert(drained_end_counter != NULL);

    if (qemu_in_coroutine()) {
        bdrv_co_yield_to_drain(bs, false, recursive, parent, ignore_bds_parents,
                               false, drained_end_counter);
        return;
    }
    assert(bs->quiesce_counter > 0);

    /* Re-enable things in child-to-parent order */
    bdrv_drain_invoke(bs, false, drained_end_counter);
    bdrv_parent_drained_end(bs, parent, ignore_bds_parents,
                            drained_end_counter);

    old_quiesce_counter = atomic_fetch_dec(&bs->quiesce_counter);
    if (old_quiesce_counter == 1) {
        aio_enable_external(bdrv_get_aio_context(bs));
    }

    if (recursive) {
        assert(!ignore_bds_parents);
        bs->recursive_quiesce_counter--;
        QLIST_FOREACH(child, &bs->children, next) {
            bdrv_do_drained_end(child->bs, true, child, ignore_bds_parents,
                                drained_end_counter);
        }
    }
}

void bdrv_drained_end(BlockDriverState *bs)
{
    int drained_end_counter = 0;
    bdrv_do_drained_end(bs, false, NULL, false, &drained_end_counter);
    BDRV_POLL_WHILE(bs, atomic_read(&drained_end_counter) > 0);
}

void bdrv_drained_end_no_poll(BlockDriverState *bs, int *drained_end_counter)
{
    bdrv_do_drained_end(bs, false, NULL, false, drained_end_counter);
}

void bdrv_subtree_drained_end(BlockDriverState *bs)
{
    int drained_end_counter = 0;
    bdrv_do_drained_end(bs, true, NULL, false, &drained_end_counter);
    BDRV_POLL_WHILE(bs, atomic_read(&drained_end_counter) > 0);
}

void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent)
{
    int i;

    for (i = 0; i < new_parent->recursive_quiesce_counter; i++) {
        bdrv_do_drained_begin(child->bs, true, child, false, true);
    }
}

void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent)
{
    int drained_end_counter = 0;
    int i;

    for (i = 0; i < old_parent->recursive_quiesce_counter; i++) {
        bdrv_do_drained_end(child->bs, true, child, false,
                            &drained_end_counter);
    }

    BDRV_POLL_WHILE(child->bs, atomic_read(&drained_end_counter) > 0);
}

/*
 * Wait for pending requests to complete on a single BlockDriverState subtree,
 * and suspend block driver's internal I/O until next request arrives.
 *
 * Note that unlike bdrv_drain_all(), the caller must hold the BlockDriverState
 * AioContext.
 */
void coroutine_fn bdrv_co_drain(BlockDriverState *bs)
{
    assert(qemu_in_coroutine());
    bdrv_drained_begin(bs);
    bdrv_drained_end(bs);
}

void bdrv_drain(BlockDriverState *bs)
{
    bdrv_drained_begin(bs);
    bdrv_drained_end(bs);
}

static void bdrv_drain_assert_idle(BlockDriverState *bs)
{
    BdrvChild *child, *next;

    assert(atomic_read(&bs->in_flight) == 0);
    QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
        bdrv_drain_assert_idle(child->bs);
    }
}

unsigned int bdrv_drain_all_count = 0;

static bool bdrv_drain_all_poll(void)
{
    BlockDriverState *bs = NULL;
    bool result = false;

    /* bdrv_drain_poll() can't make changes to the graph and we are holding the
     * main AioContext lock, so iterating bdrv_next_all_states() is safe. */
    while ((bs = bdrv_next_all_states(bs))) {
        AioContext *aio_context = bdrv_get_aio_context(bs);
        aio_context_acquire(aio_context);
        result |= bdrv_drain_poll(bs, false, NULL, true);
        aio_context_release(aio_context);
    }

    return result;
}

/*
 * Wait for pending requests to complete across all BlockDriverStates
 *
 * This function does not flush data to disk, use bdrv_flush_all() for that
 * after calling this function.
 *
 * This pauses all block jobs and disables external clients. It must
 * be paired with bdrv_drain_all_end().
 *
 * NOTE: no new block jobs or BlockDriverStates can be created between
 * the bdrv_drain_all_begin() and bdrv_drain_all_end() calls.
 */
void bdrv_drain_all_begin(void)
{
    BlockDriverState *bs = NULL;

    if (qemu_in_coroutine()) {
        bdrv_co_yield_to_drain(NULL, true, false, NULL, true, true, NULL);
        return;
    }

    /*
     * bdrv queue is managed by record/replay,
     * waiting for finishing the I/O requests may
     * be infinite
     */
    if (replay_events_enabled()) {
        return;
    }

    /* AIO_WAIT_WHILE() with a NULL context can only be called from the main
     * loop AioContext, so make sure we're in the main context. */
    assert(qemu_get_current_aio_context() == qemu_get_aio_context());
    assert(bdrv_drain_all_count < INT_MAX);
    bdrv_drain_all_count++;

    /* Quiesce all nodes, without polling in-flight requests yet. The graph
     * cannot change during this loop. */
    while ((bs = bdrv_next_all_states(bs))) {
        AioContext *aio_context = bdrv_get_aio_context(bs);

        aio_context_acquire(aio_context);
        bdrv_do_drained_begin(bs, false, NULL, true, false);
        aio_context_release(aio_context);
    }

    /* Now poll the in-flight requests */
    AIO_WAIT_WHILE(NULL, bdrv_drain_all_poll());

    while ((bs = bdrv_next_all_states(bs))) {
        bdrv_drain_assert_idle(bs);
    }
}

void bdrv_drain_all_end(void)
{
    BlockDriverState *bs = NULL;
    int drained_end_counter = 0;

    /*
     * bdrv queue is managed by record/replay,
     * waiting for finishing the I/O requests may
     * be endless
     */
    if (replay_events_enabled()) {
        return;
    }

    while ((bs = bdrv_next_all_states(bs))) {
        AioContext *aio_context = bdrv_get_aio_context(bs);

        aio_context_acquire(aio_context);
        bdrv_do_drained_end(bs, false, NULL, true, &drained_end_counter);
        aio_context_release(aio_context);
    }

    assert(qemu_get_current_aio_context() == qemu_get_aio_context());
    AIO_WAIT_WHILE(NULL, atomic_read(&drained_end_counter) > 0);

    assert(bdrv_drain_all_count > 0);
    bdrv_drain_all_count--;
}

void bdrv_drain_all(void)
{
    bdrv_drain_all_begin();
    bdrv_drain_all_end();
}

/**
 * Remove an active request from the tracked requests list
 *
 * This function should be called when a tracked request is completing.
 */
static void tracked_request_end(BdrvTrackedRequest *req)
{
    if (req->serialising) {
        atomic_dec(&req->bs->serialising_in_flight);
    }

    qemu_co_mutex_lock(&req->bs->reqs_lock);
    QLIST_REMOVE(req, list);
    qemu_co_queue_restart_all(&req->wait_queue);
    qemu_co_mutex_unlock(&req->bs->reqs_lock);
}

/**
 * Add an active request to the tracked requests list
 */
static void tracked_request_begin(BdrvTrackedRequest *req,
                                  BlockDriverState *bs,
                                  int64_t offset,
                                  uint64_t bytes,
                                  enum BdrvTrackedRequestType type)
{
    assert(bytes <= INT64_MAX && offset <= INT64_MAX - bytes);

    *req = (BdrvTrackedRequest){
        .bs = bs,
        .offset         = offset,
        .bytes          = bytes,
        .type           = type,
        .co             = qemu_coroutine_self(),
        .serialising    = false,
        .overlap_offset = offset,
        .overlap_bytes  = bytes,
    };

    qemu_co_queue_init(&req->wait_queue);

    qemu_co_mutex_lock(&bs->reqs_lock);
    QLIST_INSERT_HEAD(&bs->tracked_requests, req, list);
    qemu_co_mutex_unlock(&bs->reqs_lock);
}

static bool tracked_request_overlaps(BdrvTrackedRequest *req,
                                     int64_t offset, uint64_t bytes)
{
    /*        aaaa   bbbb */
    if (offset >= req->overlap_offset + req->overlap_bytes) {
        return false;
    }
    /* bbbb   aaaa        */
    if (req->overlap_offset >= offset + bytes) {
        return false;
    }
    return true;
}

static bool coroutine_fn
bdrv_wait_serialising_requests_locked(BlockDriverState *bs,
                                      BdrvTrackedRequest *self)
{
    BdrvTrackedRequest *req;
    bool retry;
    bool waited = false;

    do {
        retry = false;
        QLIST_FOREACH(req, &bs->tracked_requests, list) {
            if (req == self || (!req->serialising && !self->serialising)) {
                continue;
            }
            if (tracked_request_overlaps(req, self->overlap_offset,
                                         self->overlap_bytes))
            {
                /* Hitting this means there was a reentrant request, for
                 * example, a block driver issuing nested requests.  This must
                 * never happen since it means deadlock.
                 */
                assert(qemu_coroutine_self() != req->co);

                /* If the request is already (indirectly) waiting for us, or
                 * will wait for us as soon as it wakes up, then just go on
                 * (instead of producing a deadlock in the former case). */
                if (!req->waiting_for) {
                    self->waiting_for = req;
                    qemu_co_queue_wait(&req->wait_queue, &bs->reqs_lock);
                    self->waiting_for = NULL;
                    retry = true;
                    waited = true;
                    break;
                }
            }
        }
    } while (retry);
    return waited;
}

bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
{
    BlockDriverState *bs = req->bs;
    int64_t overlap_offset = req->offset & ~(align - 1);
    uint64_t overlap_bytes = ROUND_UP(req->offset + req->bytes, align)
                               - overlap_offset;
    bool waited;

    qemu_co_mutex_lock(&bs->reqs_lock);
    if (!req->serialising) {
        atomic_inc(&req->bs->serialising_in_flight);
        req->serialising = true;
    }

    req->overlap_offset = MIN(req->overlap_offset, overlap_offset);
    req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes);
    waited = bdrv_wait_serialising_requests_locked(bs, req);
    qemu_co_mutex_unlock(&bs->reqs_lock);
    return waited;
}

/**
 * Return the tracked request on @bs for the current coroutine, or
 * NULL if there is none.
 */
BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs)
{
    BdrvTrackedRequest *req;
    Coroutine *self = qemu_coroutine_self();

    QLIST_FOREACH(req, &bs->tracked_requests, list) {
        if (req->co == self) {
            return req;
        }
    }

    return NULL;
}

/**
 * Round a region to cluster boundaries
 */
void bdrv_round_to_clusters(BlockDriverState *bs,
                            int64_t offset, int64_t bytes,
                            int64_t *cluster_offset,
                            int64_t *cluster_bytes)
{
    BlockDriverInfo bdi;

    if (bdrv_get_info(bs, &bdi) < 0 || bdi.cluster_size == 0) {
        *cluster_offset = offset;
        *cluster_bytes = bytes;
    } else {
        int64_t c = bdi.cluster_size;
        *cluster_offset = QEMU_ALIGN_DOWN(offset, c);
        *cluster_bytes = QEMU_ALIGN_UP(offset - *cluster_offset + bytes, c);
    }
}

static int bdrv_get_cluster_size(BlockDriverState *bs)
{
    BlockDriverInfo bdi;
    int ret;

    ret = bdrv_get_info(bs, &bdi);
    if (ret < 0 || bdi.cluster_size == 0) {
        return bs->bl.request_alignment;
    } else {
        return bdi.cluster_size;
    }
}

void bdrv_inc_in_flight(BlockDriverState *bs)
{
    atomic_inc(&bs->in_flight);
}

void bdrv_wakeup(BlockDriverState *bs)
{
    aio_wait_kick();
}

void bdrv_dec_in_flight(BlockDriverState *bs)
{
    atomic_dec(&bs->in_flight);
    bdrv_wakeup(bs);
}

static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self)
{
    BlockDriverState *bs = self->bs;
    bool waited = false;

    if (!atomic_read(&bs->serialising_in_flight)) {
        return false;
    }

    qemu_co_mutex_lock(&bs->reqs_lock);
    waited = bdrv_wait_serialising_requests_locked(bs, self);
    qemu_co_mutex_unlock(&bs->reqs_lock);

    return waited;
}

static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
                                   size_t size)
{
    if (size > BDRV_REQUEST_MAX_BYTES) {
        return -EIO;
    }

    if (!bdrv_is_inserted(bs)) {
        return -ENOMEDIUM;
    }

    if (offset < 0) {
        return -EIO;
    }

    return 0;
}

typedef struct RwCo {
    BdrvChild *child;
    int64_t offset;
    QEMUIOVector *qiov;
    bool is_write;
    int ret;
    BdrvRequestFlags flags;
} RwCo;

static void coroutine_fn bdrv_rw_co_entry(void *opaque)
{
    RwCo *rwco = opaque;

    if (!rwco->is_write) {
        rwco->ret = bdrv_co_preadv(rwco->child, rwco->offset,
                                   rwco->qiov->size, rwco->qiov,
                                   rwco->flags);
    } else {
        rwco->ret = bdrv_co_pwritev(rwco->child, rwco->offset,
                                    rwco->qiov->size, rwco->qiov,
                                    rwco->flags);
    }
    aio_wait_kick();
}

/*
 * Process a vectored synchronous request using coroutines
 */
static int bdrv_prwv_co(BdrvChild *child, int64_t offset,
                        QEMUIOVector *qiov, bool is_write,
                        BdrvRequestFlags flags)
{
    Coroutine *co;
    RwCo rwco = {
        .child = child,
        .offset = offset,
        .qiov = qiov,
        .is_write = is_write,
        .ret = NOT_DONE,
        .flags = flags,
    };

    if (qemu_in_coroutine()) {
        /* Fast-path if already in coroutine context */
        bdrv_rw_co_entry(&rwco);
    } else {
        co = qemu_coroutine_create(bdrv_rw_co_entry, &rwco);
        bdrv_coroutine_enter(child->bs, co);
        BDRV_POLL_WHILE(child->bs, rwco.ret == NOT_DONE);
    }
    return rwco.ret;
}

int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset,
                       int bytes, BdrvRequestFlags flags)
{
    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, NULL, bytes);

    return bdrv_prwv_co(child, offset, &qiov, true,
                        BDRV_REQ_ZERO_WRITE | flags);
}

/*
 * Completely zero out a block device with the help of bdrv_pwrite_zeroes.
 * The operation is sped up by checking the block status and only writing
 * zeroes to the device if they currently do not return zeroes. Optional
 * flags are passed through to bdrv_pwrite_zeroes (e.g. BDRV_REQ_MAY_UNMAP,
 * BDRV_REQ_FUA).
 *
 * Returns < 0 on error, 0 on success. For error codes see bdrv_pwrite().
 */
int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags)
{
    int ret;
    int64_t target_size, bytes, offset = 0;
    BlockDriverState *bs = child->bs;

    target_size = bdrv_getlength(bs);
    if (target_size < 0) {
        return target_size;
    }

    for (;;) {
        bytes = MIN(target_size - offset, BDRV_REQUEST_MAX_BYTES);
        if (bytes <= 0) {
            return 0;
        }
        ret = bdrv_block_status(bs, offset, bytes, &bytes, NULL, NULL);
        if (ret < 0) {
            return ret;
        }
        if (ret & BDRV_BLOCK_ZERO) {
            offset += bytes;
            continue;
        }
        ret = bdrv_pwrite_zeroes(child, offset, bytes, flags);
        if (ret < 0) {
            return ret;
        }
        offset += bytes;
    }
}

/* return < 0 if error. See bdrv_pwrite() for the return codes */
int bdrv_preadv(BdrvChild *child, int64_t offset, QEMUIOVector *qiov)
{
    int ret;

    ret = bdrv_prwv_co(child, offset, qiov, false, 0);
    if (ret < 0) {
        return ret;
    }

    return qiov->size;
}

/* See bdrv_pwrite() for the return codes */
int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int bytes)
{
    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);

    if (bytes < 0) {
        return -EINVAL;
    }

    return bdrv_preadv(child, offset, &qiov);
}

int bdrv_pwritev(BdrvChild *child, int64_t offset, QEMUIOVector *qiov)
{
    int ret;

    ret = bdrv_prwv_co(child, offset, qiov, true, 0);
    if (ret < 0) {
        return ret;
    }

    return qiov->size;
}

/* Return no. of bytes on success or < 0 on error. Important errors are:
  -EIO         generic I/O error (may happen for all errors)
  -ENOMEDIUM   No media inserted.
  -EINVAL      Invalid offset or number of bytes
  -EACCES      Trying to write a read-only device
*/
int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, int bytes)
{
    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);

    if (bytes < 0) {
        return -EINVAL;
    }

    return bdrv_pwritev(child, offset, &qiov);
}

/*
 * Writes to the file and ensures that no writes are reordered across this
 * request (acts as a barrier)
 *
 * Returns 0 on success, -errno in error cases.
 */
int bdrv_pwrite_sync(BdrvChild *child, int64_t offset,
                     const void *buf, int count)
{
    int ret;

    ret = bdrv_pwrite(child, offset, buf, count);
    if (ret < 0) {
        return ret;
    }

    ret = bdrv_flush(child->bs);
    if (ret < 0) {
        return ret;
    }

    return 0;
}

typedef struct CoroutineIOCompletion {
    Coroutine *coroutine;
    int ret;
} CoroutineIOCompletion;

static void bdrv_co_io_em_complete(void *opaque, int ret)
{
    CoroutineIOCompletion *co = opaque;

    co->ret = ret;
    aio_co_wake(co->coroutine);
}

static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs,
                                           uint64_t offset, uint64_t bytes,
                                           QEMUIOVector *qiov,
                                           size_t qiov_offset, int flags)
{
    BlockDriver *drv = bs->drv;
    int64_t sector_num;
    unsigned int nb_sectors;
    QEMUIOVector local_qiov;
    int ret;

    assert(!(flags & ~BDRV_REQ_MASK));
    assert(!(flags & BDRV_REQ_NO_FALLBACK));

    if (!drv) {
        return -ENOMEDIUM;
    }

    if (drv->bdrv_co_preadv_part) {
        return drv->bdrv_co_preadv_part(bs, offset, bytes, qiov, qiov_offset,
                                        flags);
    }

    if (qiov_offset > 0 || bytes != qiov->size) {
        qemu_iovec_init_slice(&local_qiov, qiov, qiov_offset, bytes);
        qiov = &local_qiov;
    }

    if (drv->bdrv_co_preadv) {
        ret = drv->bdrv_co_preadv(bs, offset, bytes, qiov, flags);
        goto out;
    }

    if (drv->bdrv_aio_preadv) {
        BlockAIOCB *acb;
        CoroutineIOCompletion co = {
            .coroutine = qemu_coroutine_self(),
        };

        acb = drv->bdrv_aio_preadv(bs, offset, bytes, qiov, flags,
                                   bdrv_co_io_em_complete, &co);
        if (acb == NULL) {
            ret = -EIO;
            goto out;
        } else {
            qemu_coroutine_yield();
            ret = co.ret;
            goto out;
        }
    }

    sector_num = offset >> BDRV_SECTOR_BITS;
    nb_sectors = bytes >> BDRV_SECTOR_BITS;

    assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE));
    assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE));
    assert(bytes <= BDRV_REQUEST_MAX_BYTES);
    assert(drv->bdrv_co_readv);

    ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);

out:
    if (qiov == &local_qiov) {
        qemu_iovec_destroy(&local_qiov);
    }

    return ret;
}

static int coroutine_fn bdrv_driver_pwritev(BlockDriverState *bs,
                                            uint64_t offset, uint64_t bytes,
                                            QEMUIOVector *qiov,
                                            size_t qiov_offset, int flags)
{
    BlockDriver *drv = bs->drv;
    int64_t sector_num;
    unsigned int nb_sectors;
    QEMUIOVector local_qiov;
    int ret;

    assert(!(flags & ~BDRV_REQ_MASK));
    assert(!(flags & BDRV_REQ_NO_FALLBACK));

    if (!drv) {
        return -ENOMEDIUM;
    }

    if (drv->bdrv_co_pwritev_part) {
        ret = drv->bdrv_co_pwritev_part(bs, offset, bytes, qiov, qiov_offset,
                                        flags & bs->supported_write_flags);
        flags &= ~bs->supported_write_flags;
        goto emulate_flags;
    }

    if (qiov_offset > 0 || bytes != qiov->size) {
        qemu_iovec_init_slice(&local_qiov, qiov, qiov_offset, bytes);
        qiov = &local_qiov;
    }

    if (drv->bdrv_co_pwritev) {
        ret = drv->bdrv_co_pwritev(bs, offset, bytes, qiov,
                                   flags & bs->supported_write_flags);
        flags &= ~bs->supported_write_flags;
        goto emulate_flags;
    }

    if (drv->bdrv_aio_pwritev) {
        BlockAIOCB *acb;
        CoroutineIOCompletion co = {
            .coroutine = qemu_coroutine_self(),
        };

        acb = drv->bdrv_aio_pwritev(bs, offset, bytes, qiov,
                                    flags & bs->supported_write_flags,
                                    bdrv_co_io_em_complete, &co);
        flags &= ~bs->supported_write_flags;
        if (acb == NULL) {
            ret = -EIO;
        } else {
            qemu_coroutine_yield();
            ret = co.ret;
        }
        goto emulate_flags;
    }

    sector_num = offset >> BDRV_SECTOR_BITS;
    nb_sectors = bytes >> BDRV_SECTOR_BITS;

    assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE));
    assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE));
    assert(bytes <= BDRV_REQUEST_MAX_BYTES);

    assert(drv->bdrv_co_writev);
    ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov,
                              flags & bs->supported_write_flags);
    flags &= ~bs->supported_write_flags;

emulate_flags:
    if (ret == 0 && (flags & BDRV_REQ_FUA)) {
        ret = bdrv_co_flush(bs);
    }

    if (qiov == &local_qiov) {
        qemu_iovec_destroy(&local_qiov);
    }

    return ret;
}

static int coroutine_fn
bdrv_driver_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
                               uint64_t bytes, QEMUIOVector *qiov,
                               size_t qiov_offset)
{
    BlockDriver *drv = bs->drv;
    QEMUIOVector local_qiov;
    int ret;

    if (!drv) {
        return -ENOMEDIUM;
    }

    if (!block_driver_can_compress(drv)) {
        return -ENOTSUP;
    }

    if (drv->bdrv_co_pwritev_compressed_part) {
        return drv->bdrv_co_pwritev_compressed_part(bs, offset, bytes,
                                                    qiov, qiov_offset);
    }

    if (qiov_offset == 0) {
        return drv->bdrv_co_pwritev_compressed(bs, offset, bytes, qiov);
    }

    qemu_iovec_init_slice(&local_qiov, qiov, qiov_offset, bytes);
    ret = drv->bdrv_co_pwritev_compressed(bs, offset, bytes, &local_qiov);
    qemu_iovec_destroy(&local_qiov);

    return ret;
}

static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child,
        int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
        size_t qiov_offset, int flags)
{
    BlockDriverState *bs = child->bs;

    /* Perform I/O through a temporary buffer so that users who scribble over
     * their read buffer while the operation is in progress do not end up
     * modifying the image file.  This is critical for zero-copy guest I/O
     * where anything might happen inside guest memory.
     */
    void *bounce_buffer = NULL;

    BlockDriver *drv = bs->drv;
    int64_t cluster_offset;
    int64_t cluster_bytes;
    size_t skip_bytes;
    int ret;
    int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer,
                                    BDRV_REQUEST_MAX_BYTES);
    unsigned int progress = 0;
    bool skip_write;

    if (!drv) {
        return -ENOMEDIUM;
    }

    /*
     * Do not write anything when the BDS is inactive.  That is not
     * allowed, and it would not help.
     */
    skip_write = (bs->open_flags & BDRV_O_INACTIVE);

    /* FIXME We cannot require callers to have write permissions when all they
     * are doing is a read request. If we did things right, write permissions
     * would be obtained anyway, but internally by the copy-on-read code. As
     * long as it is implemented here rather than in a separate filter driver,
     * the copy-on-read code doesn't have its own BdrvChild, however, for which
     * it could request permissions. Therefore we have to bypass the permission
     * system for the moment. */
    // assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));

    /* Cover entire cluster so no additional backing file I/O is required when
     * allocating cluster in the image file.  Note that this value may exceed
     * BDRV_REQUEST_MAX_BYTES (even when the original read did not), which
     * is one reason we loop rather than doing it all at once.
     */
    bdrv_round_to_clusters(bs, offset, bytes, &cluster_offset, &cluster_bytes);
    skip_bytes = offset - cluster_offset;

    trace_bdrv_co_do_copy_on_readv(bs, offset, bytes,
                                   cluster_offset, cluster_bytes);

    while (cluster_bytes) {
        int64_t pnum;

        if (skip_write) {
            ret = 1; /* "already allocated", so nothing will be copied */
            pnum = MIN(cluster_bytes, max_transfer);
        } else {
            ret = bdrv_is_allocated(bs, cluster_offset,
                                    MIN(cluster_bytes, max_transfer), &pnum);
            if (ret < 0) {
                /*
                 * Safe to treat errors in querying allocation as if
                 * unallocated; we'll probably fail again soon on the
                 * read, but at least that will set a decent errno.
                 */
                pnum = MIN(cluster_bytes, max_transfer);
            }

            /* Stop at EOF if the image ends in the middle of the cluster */
            if (ret == 0 && pnum == 0) {
                assert(progress >= bytes);
                break;
            }

            assert(skip_bytes < pnum);
        }

        if (ret <= 0) {
            QEMUIOVector local_qiov;

            /* Must copy-on-read; use the bounce buffer */
            pnum = MIN(pnum, MAX_BOUNCE_BUFFER);
            if (!bounce_buffer) {
                int64_t max_we_need = MAX(pnum, cluster_bytes - pnum);
                int64_t max_allowed = MIN(max_transfer, MAX_BOUNCE_BUFFER);
                int64_t bounce_buffer_len = MIN(max_we_need, max_allowed);

                bounce_buffer = qemu_try_blockalign(bs, bounce_buffer_len);
                if (!bounce_buffer) {
                    ret = -ENOMEM;
                    goto err;
                }
            }
            qemu_iovec_init_buf(&local_qiov, bounce_buffer, pnum);

            ret = bdrv_driver_preadv(bs, cluster_offset, pnum,
                                     &local_qiov, 0, 0);
            if (ret < 0) {
                goto err;
            }

            bdrv_debug_event(bs, BLKDBG_COR_WRITE);
            if (drv->bdrv_co_pwrite_zeroes &&
                buffer_is_zero(bounce_buffer, pnum)) {
                /* FIXME: Should we (perhaps conditionally) be setting
                 * BDRV_REQ_MAY_UNMAP, if it will allow for a sparser copy
                 * that still correctly reads as zero? */
                ret = bdrv_co_do_pwrite_zeroes(bs, cluster_offset, pnum,
                                               BDRV_REQ_WRITE_UNCHANGED);
            } else {
                /* This does not change the data on the disk, it is not
                 * necessary to flush even in cache=writethrough mode.
                 */
                ret = bdrv_driver_pwritev(bs, cluster_offset, pnum,
                                          &local_qiov, 0,
                                          BDRV_REQ_WRITE_UNCHANGED);
            }

            if (ret < 0) {
                /* It might be okay to ignore write errors for guest
                 * requests.  If this is a deliberate copy-on-read
                 * then we don't want to ignore the error.  Simply
                 * report it in all cases.
                 */
                goto err;
            }

            if (!(flags & BDRV_REQ_PREFETCH)) {
                qemu_iovec_from_buf(qiov, qiov_offset + progress,
                                    bounce_buffer + skip_bytes,
                                    MIN(pnum - skip_bytes, bytes - progress));
            }
        } else if (!(flags & BDRV_REQ_PREFETCH)) {
            /* Read directly into the destination */
            ret = bdrv_driver_preadv(bs, offset + progress,
                                     MIN(pnum - skip_bytes, bytes - progress),
                                     qiov, qiov_offset + progress, 0);
            if (ret < 0) {
                goto err;
            }
        }

        cluster_offset += pnum;
        cluster_bytes -= pnum;
        progress += pnum - skip_bytes;
        skip_bytes = 0;
    }
    ret = 0;

err:
    qemu_vfree(bounce_buffer);
    return ret;
}

/*
 * Forwards an already correctly aligned request to the BlockDriver. This
 * handles copy on read, zeroing after EOF, and fragmentation of large
 * reads; any other features must be implemented by the caller.
 */
static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
    BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
    int64_t align, QEMUIOVector *qiov, size_t qiov_offset, int flags)
{
    BlockDriverState *bs = child->bs;
    int64_t total_bytes, max_bytes;
    int ret = 0;
    uint64_t bytes_remaining = bytes;
    int max_transfer;

    assert(is_power_of_2(align));
    assert((offset & (align - 1)) == 0);
    assert((bytes & (align - 1)) == 0);
    assert((bs->open_flags & BDRV_O_NO_IO) == 0);
    max_transfer = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_transfer, INT_MAX),
                                   align);

    /* TODO: We would need a per-BDS .supported_read_flags and
     * potential fallback support, if we ever implement any read flags
     * to pass through to drivers.  For now, there aren't any
     * passthrough flags.  */
    assert(!(flags & ~(BDRV_REQ_COPY_ON_READ | BDRV_REQ_PREFETCH)));

    /* Handle Copy on Read and associated serialisation */
    if (flags & BDRV_REQ_COPY_ON_READ) {
        /* If we touch the same cluster it counts as an overlap.  This
         * guarantees that allocating writes will be serialized and not race
         * with each other for the same cluster.  For example, in copy-on-read
         * it ensures that the CoR read and write operations are atomic and
         * guest writes cannot interleave between them. */
        bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
    } else {
        bdrv_wait_serialising_requests(req);
    }

    if (flags & BDRV_REQ_COPY_ON_READ) {
        int64_t pnum;

        ret = bdrv_is_allocated(bs, offset, bytes, &pnum);
        if (ret < 0) {
            goto out;
        }

        if (!ret || pnum != bytes) {
            ret = bdrv_co_do_copy_on_readv(child, offset, bytes,
                                           qiov, qiov_offset, flags);
            goto out;
        } else if (flags & BDRV_REQ_PREFETCH) {
            goto out;
        }
    }

    /* Forward the request to the BlockDriver, possibly fragmenting it */
    total_bytes = bdrv_getlength(bs);
    if (total_bytes < 0) {
        ret = total_bytes;
        goto out;
    }

    max_bytes = ROUND_UP(MAX(0, total_bytes - offset), align);
    if (bytes <= max_bytes && bytes <= max_transfer) {
        ret = bdrv_driver_preadv(bs, offset, bytes, qiov, qiov_offset, 0);
        goto out;
    }

    while (bytes_remaining) {
        int num;

        if (max_bytes) {
            num = MIN(bytes_remaining, MIN(max_bytes, max_transfer));
            assert(num);

            ret = bdrv_driver_preadv(bs, offset + bytes - bytes_remaining,
                                     num, qiov, bytes - bytes_remaining, 0);
            max_bytes -= num;
        } else {
            num = bytes_remaining;
            ret = qemu_iovec_memset(qiov, bytes - bytes_remaining, 0,
                                    bytes_remaining);
        }
        if (ret < 0) {
            goto out;
        }
        bytes_remaining -= num;
    }

out:
    return ret < 0 ? ret : 0;
}

/*
 * Request padding
 *
 *  |<---- align ----->|                     |<----- align ---->|
 *  |<- head ->|<------------- bytes ------------->|<-- tail -->|
 *  |          |       |                     |     |            |
 * -*----------$-------*-------- ... --------*-----$------------*---
 *  |          |       |                     |     |            |
 *  |          offset  |                     |     end          |
 *  ALIGN_DOWN(offset) ALIGN_UP(offset)      ALIGN_DOWN(end)   ALIGN_UP(end)
 *  [buf   ... )                             [tail_buf          )
 *
 * @buf is an aligned allocation needed to store @head and @tail paddings. @head
 * is placed at the beginning of @buf and @tail at the @end.
 *
 * @tail_buf is a pointer to sub-buffer, corresponding to align-sized chunk
 * around tail, if tail exists.
 *
 * @merge_reads is true for small requests,
 * if @buf_len == @head + bytes + @tail. In this case it is possible that both
 * head and tail exist but @buf_len == align and @tail_buf == @buf.
 */
typedef struct BdrvRequestPadding {
    uint8_t *buf;
    size_t buf_len;
    uint8_t *tail_buf;
    size_t head;
    size_t tail;
    bool merge_reads;
    QEMUIOVector local_qiov;
} BdrvRequestPadding;

static bool bdrv_init_padding(BlockDriverState *bs,
                              int64_t offset, int64_t bytes,
                              BdrvRequestPadding *pad)
{
    uint64_t align = bs->bl.request_alignment;
    size_t sum;

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

    pad->head = offset & (align - 1);
    pad->tail = ((offset + bytes) & (align - 1));
    if (pad->tail) {
        pad->tail = align - pad->tail;
    }

    if (!pad->head && !pad->tail) {
        return false;
    }

    assert(bytes); /* Nothing good in aligning zero-length requests */

    sum = pad->head + bytes + pad->tail;
    pad->buf_len = (sum > align && pad->head && pad->tail) ? 2 * align : align;
    pad->buf = qemu_blockalign(bs, pad->buf_len);
    pad->merge_reads = sum == pad->buf_len;
    if (pad->tail) {
        pad->tail_buf = pad->buf + pad->buf_len - align;
    }

    return true;
}

static int bdrv_padding_rmw_read(BdrvChild *child,
                                 BdrvTrackedRequest *req,
                                 BdrvRequestPadding *pad,
                                 bool zero_middle)
{
    QEMUIOVector local_qiov;
    BlockDriverState *bs = child->bs;
    uint64_t align = bs->bl.request_alignment;
    int ret;

    assert(req->serialising && pad->buf);

    if (pad->head || pad->merge_reads) {
        uint64_t bytes = pad->merge_reads ? pad->buf_len : align;

        qemu_iovec_init_buf(&local_qiov, pad->buf, bytes);

        if (pad->head) {
            bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
        }
        if (pad->merge_reads && pad->tail) {
            bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
        }
        ret = bdrv_aligned_preadv(child, req, req->overlap_offset, bytes,
                                  align, &local_qiov, 0, 0);
        if (ret < 0) {
            return ret;
        }
        if (pad->head) {
            bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_HEAD);
        }
        if (pad->merge_reads && pad->tail) {
            bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL);
        }

        if (pad->merge_reads) {
            goto zero_mem;
        }
    }

    if (pad->tail) {
        qemu_iovec_init_buf(&local_qiov, pad->tail_buf, align);

        bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
        ret = bdrv_aligned_preadv(
                child, req,
                req->overlap_offset + req->overlap_bytes - align,
                align, align, &local_qiov, 0, 0);
        if (ret < 0) {
            return ret;
        }
        bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL);
    }

zero_mem:
    if (zero_middle) {
        memset(pad->buf + pad->head, 0, pad->buf_len - pad->head - pad->tail);
    }

    return 0;
}

static void bdrv_padding_destroy(BdrvRequestPadding *pad)
{
    if (pad->buf) {
        qemu_vfree(pad->buf);
        qemu_iovec_destroy(&pad->local_qiov);
    }
}

/*
 * bdrv_pad_request
 *
 * Exchange request parameters with padded request if needed. Don't include RMW
 * read of padding, bdrv_padding_rmw_read() should be called separately if
 * needed.
 *
 * All parameters except @bs are in-out: they represent original request at
 * function call and padded (if padding needed) at function finish.
 *
 * Function always succeeds.
 */
static bool bdrv_pad_request(BlockDriverState *bs,
                             QEMUIOVector **qiov, size_t *qiov_offset,
                             int64_t *offset, unsigned int *bytes,
                             BdrvRequestPadding *pad)
{
    if (!bdrv_init_padding(bs, *offset, *bytes, pad)) {
        return false;
    }

    qemu_iovec_init_extended(&pad->local_qiov, pad->buf, pad->head,
                             *qiov, *qiov_offset, *bytes,
                             pad->buf + pad->buf_len - pad->tail, pad->tail);
    *bytes += pad->head + pad->tail;
    *offset -= pad->head;
    *qiov = &pad->local_qiov;
    *qiov_offset = 0;

    return true;
}

int coroutine_fn bdrv_co_preadv(BdrvChild *child,
    int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
    BdrvRequestFlags flags)
{
    return bdrv_co_preadv_part(child, offset, bytes, qiov, 0, flags);
}

int coroutine_fn bdrv_co_preadv_part(BdrvChild *child,
    int64_t offset, unsigned int bytes,
    QEMUIOVector *qiov, size_t qiov_offset,
    BdrvRequestFlags flags)
{
    BlockDriverState *bs = child->bs;
    BdrvTrackedRequest req;
    BdrvRequestPadding pad;
    int ret;

    trace_bdrv_co_preadv(bs, offset, bytes, flags);

    ret = bdrv_check_byte_request(bs, offset, bytes);
    if (ret < 0) {
        return ret;
    }

    if (bytes == 0 && !QEMU_IS_ALIGNED(offset, bs->bl.request_alignment)) {
        /*
         * Aligning zero request is nonsense. Even if driver has special meaning
         * of zero-length (like qcow2_co_pwritev_compressed_part), we can't pass
         * it to driver due to request_alignment.
         *
         * Still, no reason to return an error if someone do unaligned
         * zero-length read occasionally.
         */
        return 0;
    }

    bdrv_inc_in_flight(bs);

    /* Don't do copy-on-read if we read data before write operation */
    if (atomic_read(&bs->copy_on_read)) {
        flags |= BDRV_REQ_COPY_ON_READ;
    }

    bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad);

    tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_READ);
    ret = bdrv_aligned_preadv(child, &req, offset, bytes,
                              bs->bl.request_alignment,
                              qiov, qiov_offset, flags);
    tracked_request_end(&req);
    bdrv_dec_in_flight(bs);

    bdrv_padding_destroy(&pad);

    return ret;
}

static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
    int64_t offset, int bytes, BdrvRequestFlags flags)
{
    BlockDriver *drv = bs->drv;
    QEMUIOVector qiov;
    void *buf = NULL;
    int ret = 0;
    bool need_flush = false;
    int head = 0;
    int tail = 0;

    int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_pwrite_zeroes, INT_MAX);
    int alignment = MAX(bs->bl.pwrite_zeroes_alignment,
                        bs->bl.request_alignment);
    int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, MAX_BOUNCE_BUFFER);

    if (!drv) {
        return -ENOMEDIUM;
    }

    if ((flags & ~bs->supported_zero_flags) & BDRV_REQ_NO_FALLBACK) {
        return -ENOTSUP;
    }

    assert(alignment % bs->bl.request_alignment == 0);
    head = offset % alignment;
    tail = (offset + bytes) % alignment;
    max_write_zeroes = QEMU_ALIGN_DOWN(max_write_zeroes, alignment);
    assert(max_write_zeroes >= bs->bl.request_alignment);

    while (bytes > 0 && !ret) {
        int num = bytes;

        /* Align request.  Block drivers can expect the "bulk" of the request
         * to be aligned, and that unaligned requests do not cross cluster
         * boundaries.
         */
        if (head) {
            /* Make a small request up to the first aligned sector. For
             * convenience, limit this request to max_transfer even if
             * we don't need to fall back to writes.  */
            num = MIN(MIN(bytes, max_transfer), alignment - head);
            head = (head + num) % alignment;
            assert(num < max_write_zeroes);
        } else if (tail && num > alignment) {
            /* Shorten the request to the last aligned sector.  */
            num -= tail;
        }

        /* limit request size */
        if (num > max_write_zeroes) {
            num = max_write_zeroes;
        }

        ret = -ENOTSUP;
        /* First try the efficient write zeroes operation */
        if (drv->bdrv_co_pwrite_zeroes) {
            ret = drv->bdrv_co_pwrite_zeroes(bs, offset, num,
                                             flags & bs->supported_zero_flags);
            if (ret != -ENOTSUP && (flags & BDRV_REQ_FUA) &&
                !(bs->supported_zero_flags & BDRV_REQ_FUA)) {
                need_flush = true;
            }
        } else {
            assert(!bs->supported_zero_flags);
        }

        if (ret == -ENOTSUP && !(flags & BDRV_REQ_NO_FALLBACK)) {
            /* Fall back to bounce buffer if write zeroes is unsupported */
            BdrvRequestFlags write_flags = flags & ~BDRV_REQ_ZERO_WRITE;

            if ((flags & BDRV_REQ_FUA) &&
                !(bs->supported_write_flags & BDRV_REQ_FUA)) {
                /* No need for bdrv_driver_pwrite() to do a fallback
                 * flush on each chunk; use just one at the end */
                write_flags &= ~BDRV_REQ_FUA;
                need_flush = true;
            }
            num = MIN(num, max_transfer);
            if (buf == NULL) {
                buf = qemu_try_blockalign0(bs, num);
                if (buf == NULL) {
                    ret = -ENOMEM;
                    goto fail;
                }
            }
            qemu_iovec_init_buf(&qiov, buf, num);

            ret = bdrv_driver_pwritev(bs, offset, num, &qiov, 0, write_flags);

            /* Keep bounce buffer around if it is big enough for all
             * all future requests.
             */
            if (num < max_transfer) {
                qemu_vfree(buf);
                buf = NULL;
            }
        }

        offset += num;
        bytes -= num;
    }

fail:
    if (ret == 0 && need_flush) {
        ret = bdrv_co_flush(bs);
    }
    qemu_vfree(buf);
    return ret;
}

static inline int coroutine_fn
bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes,
                          BdrvTrackedRequest *req, int flags)
{
    BlockDriverState *bs = child->bs;
    bool waited;
    int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);

    if (bs->read_only) {
        return -EPERM;
    }

    assert(!(bs->open_flags & BDRV_O_INACTIVE));
    assert((bs->open_flags & BDRV_O_NO_IO) == 0);
    assert(!(flags & ~BDRV_REQ_MASK));

    if (flags & BDRV_REQ_SERIALISING) {
        waited = bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
        /*
         * For a misaligned request we should have already waited earlier,
         * because we come after bdrv_padding_rmw_read which must be called
         * with the request already marked as serialising.
         */
        assert(!waited ||
               (req->offset == req->overlap_offset &&
                req->bytes == req->overlap_bytes));
    } else {
        bdrv_wait_serialising_requests(req);
    }

    assert(req->overlap_offset <= offset);
    assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
    assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE);

    switch (req->type) {
    case BDRV_TRACKED_WRITE:
    case BDRV_TRACKED_DISCARD:
        if (flags & BDRV_REQ_WRITE_UNCHANGED) {
            assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));
        } else {
            assert(child->perm & BLK_PERM_WRITE);
        }
        return notifier_with_return_list_notify(&bs->before_write_notifiers,
                                                req);
    case BDRV_TRACKED_TRUNCATE:
        assert(child->perm & BLK_PERM_RESIZE);
        return 0;
    default:
        abort();
    }
}

static inline void coroutine_fn
bdrv_co_write_req_finish(BdrvChild *child, int64_t offset, uint64_t bytes,
                         BdrvTrackedRequest *req, int ret)
{
    int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
    BlockDriverState *bs = child->bs;

    atomic_inc(&bs->write_gen);

    /*
     * Discard cannot extend the image, but in error handling cases, such as
     * when reverting a qcow2 cluster allocation, the discarded range can pass
     * the end of image file, so we cannot assert about BDRV_TRACKED_DISCARD
     * here. Instead, just skip it, since semantically a discard request
     * beyond EOF cannot expand the image anyway.
     */
    if (ret == 0 &&
        (req->type == BDRV_TRACKED_TRUNCATE ||
         end_sector > bs->total_sectors) &&
        req->type != BDRV_TRACKED_DISCARD) {
        bs->total_sectors = end_sector;
        bdrv_parent_cb_resize(bs);
        bdrv_dirty_bitmap_truncate(bs, end_sector << BDRV_SECTOR_BITS);
    }
    if (req->bytes) {
        switch (req->type) {
        case BDRV_TRACKED_WRITE:
            stat64_max(&bs->wr_highest_offset, offset + bytes);
            /* fall through, to set dirty bits */
        case BDRV_TRACKED_DISCARD:
            bdrv_set_dirty(bs, offset, bytes);
            break;
        default:
            break;
        }
    }
}

/*
 * Forwards an already correctly aligned write request to the BlockDriver,
 * after possibly fragmenting it.
 */
static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child,
    BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
    int64_t align, QEMUIOVector *qiov, size_t qiov_offset, int flags)
{
    BlockDriverState *bs = child->bs;
    BlockDriver *drv = bs->drv;
    int ret;

    uint64_t bytes_remaining = bytes;
    int max_transfer;

    if (!drv) {
        return -ENOMEDIUM;
    }

    if (bdrv_has_readonly_bitmaps(bs)) {
        return -EPERM;
    }

    assert(is_power_of_2(align));
    assert((offset & (align - 1)) == 0);
    assert((bytes & (align - 1)) == 0);
    assert(!qiov || qiov_offset + bytes <= qiov->size);
    max_transfer = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_transfer, INT_MAX),
                                   align);

    ret = bdrv_co_write_req_prepare(child, offset, bytes, req, flags);

    if (!ret && bs->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF &&
        !(flags & BDRV_REQ_ZERO_WRITE) && drv->bdrv_co_pwrite_zeroes &&
        qemu_iovec_is_zero(qiov, qiov_offset, bytes)) {
        flags |= BDRV_REQ_ZERO_WRITE;
        if (bs->detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP) {
            flags |= BDRV_REQ_MAY_UNMAP;
        }
    }

    if (ret < 0) {
        /* Do nothing, write notifier decided to fail this request */
    } else if (flags & BDRV_REQ_ZERO_WRITE) {
        bdrv_debug_event(bs, BLKDBG_PWRITEV_ZERO);
        ret = bdrv_co_do_pwrite_zeroes(bs, offset, bytes, flags);
    } else if (flags & BDRV_REQ_WRITE_COMPRESSED) {
        ret = bdrv_driver_pwritev_compressed(bs, offset, bytes,
                                             qiov, qiov_offset);
    } else if (bytes <= max_transfer) {
        bdrv_debug_event(bs, BLKDBG_PWRITEV);
        ret = bdrv_driver_pwritev(bs, offset, bytes, qiov, qiov_offset, flags);
    } else {
        bdrv_debug_event(bs, BLKDBG_PWRITEV);
        while (bytes_remaining) {
            int num = MIN(bytes_remaining, max_transfer);
            int local_flags = flags;

            assert(num);
            if (num < bytes_remaining && (flags & BDRV_REQ_FUA) &&
                !(bs->supported_write_flags & BDRV_REQ_FUA)) {
                /* If FUA is going to be emulated by flush, we only
                 * need to flush on the last iteration */
                local_flags &= ~BDRV_REQ_FUA;
            }

            ret = bdrv_driver_pwritev(bs, offset + bytes - bytes_remaining,
                                      num, qiov, bytes - bytes_remaining,
                                      local_flags);
            if (ret < 0) {
                break;
            }
            bytes_remaining -= num;
        }
    }
    bdrv_debug_event(bs, BLKDBG_PWRITEV_DONE);

    if (ret >= 0) {
        ret = 0;
    }
    bdrv_co_write_req_finish(child, offset, bytes, req, ret);

    return ret;
}

static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
                                                int64_t offset,
                                                unsigned int bytes,
                                                BdrvRequestFlags flags,
                                                BdrvTrackedRequest *req)
{
    BlockDriverState *bs = child->bs;
    QEMUIOVector local_qiov;
    uint64_t align = bs->bl.request_alignment;
    int ret = 0;
    bool padding;
    BdrvRequestPadding pad;

    padding = bdrv_init_padding(bs, offset, bytes, &pad);
    if (padding) {
        bdrv_mark_request_serialising(req, align);

        bdrv_padding_rmw_read(child, req, &pad, true);

        if (pad.head || pad.merge_reads) {
            int64_t aligned_offset = offset & ~(align - 1);
            int64_t write_bytes = pad.merge_reads ? pad.buf_len : align;

            qemu_iovec_init_buf(&local_qiov, pad.buf, write_bytes);
            ret = bdrv_aligned_pwritev(child, req, aligned_offset, write_bytes,
                                       align, &local_qiov, 0,
                                       flags & ~BDRV_REQ_ZERO_WRITE);
            if (ret < 0 || pad.merge_reads) {
                /* Error or all work is done */
                goto out;
            }
            offset += write_bytes - pad.head;
            bytes -= write_bytes - pad.head;
        }
    }

    assert(!bytes || (offset & (align - 1)) == 0);
    if (bytes >= align) {
        /* Write the aligned part in the middle. */
        uint64_t aligned_bytes = bytes & ~(align - 1);
        ret = bdrv_aligned_pwritev(child, req, offset, aligned_bytes, align,
                                   NULL, 0, flags);
        if (ret < 0) {
            goto out;
        }
        bytes -= aligned_bytes;
        offset += aligned_bytes;
    }

    assert(!bytes || (offset & (align - 1)) == 0);
    if (bytes) {
        assert(align == pad.tail + bytes);

        qemu_iovec_init_buf(&local_qiov, pad.tail_buf, align);
        ret = bdrv_aligned_pwritev(child, req, offset, align, align,
                                   &local_qiov, 0,
                                   flags & ~BDRV_REQ_ZERO_WRITE);
    }

out:
    bdrv_padding_destroy(&pad);

    return ret;
}

/*
 * Handle a write request in coroutine context
 */
int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
    int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
    BdrvRequestFlags flags)
{
    return bdrv_co_pwritev_part(child, offset, bytes, qiov, 0, flags);
}

int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
    int64_t offset, unsigned int bytes, QEMUIOVector *qiov, size_t qiov_offset,
    BdrvRequestFlags flags)
{
    BlockDriverState *bs = child->bs;
    BdrvTrackedRequest req;
    uint64_t align = bs->bl.request_alignment;
    BdrvRequestPadding pad;
    int ret;

    trace_bdrv_co_pwritev(child->bs, offset, bytes, flags);

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

    ret = bdrv_check_byte_request(bs, offset, bytes);
    if (ret < 0) {
        return ret;
    }

    /* If the request is misaligned then we can't make it efficient */
    if ((flags & BDRV_REQ_NO_FALLBACK) &&
        !QEMU_IS_ALIGNED(offset | bytes, align))
    {
        return -ENOTSUP;
    }

    if (bytes == 0 && !QEMU_IS_ALIGNED(offset, bs->bl.request_alignment)) {
        /*
         * Aligning zero request is nonsense. Even if driver has special meaning
         * of zero-length (like qcow2_co_pwritev_compressed_part), we can't pass
         * it to driver due to request_alignment.
         *
         * Still, no reason to return an error if someone do unaligned
         * zero-length write occasionally.
         */
        return 0;
    }

    bdrv_inc_in_flight(bs);
    /*
     * Align write if necessary by performing a read-modify-write cycle.
     * Pad qiov with the read parts and be sure to have a tracked request not
     * only for bdrv_aligned_pwritev, but also for the reads of the RMW cycle.
     */
    tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_WRITE);

    if (flags & BDRV_REQ_ZERO_WRITE) {
        ret = bdrv_co_do_zero_pwritev(child, offset, bytes, flags, &req);
        goto out;
    }

    if (bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad)) {
        bdrv_mark_request_serialising(&req, align);
        bdrv_padding_rmw_read(child, &req, &pad, false);
    }

    ret = bdrv_aligned_pwritev(child, &req, offset, bytes, align,
                               qiov, qiov_offset, flags);

    bdrv_padding_destroy(&pad);

out:
    tracked_request_end(&req);
    bdrv_dec_in_flight(bs);

    return ret;
}

int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild *child, int64_t offset,
                                       int bytes, BdrvRequestFlags flags)
{
    trace_bdrv_co_pwrite_zeroes(child->bs, offset, bytes, flags);

    if (!(child->bs->open_flags & BDRV_O_UNMAP)) {
        flags &= ~BDRV_REQ_MAY_UNMAP;
    }

    return bdrv_co_pwritev(child, offset, bytes, NULL,
                           BDRV_REQ_ZERO_WRITE | flags);
}

/*
 * Flush ALL BDSes regardless of if they are reachable via a BlkBackend or not.
 */
int bdrv_flush_all(void)
{
    BdrvNextIterator it;
    BlockDriverState *bs = NULL;
    int result = 0;

    /*
     * bdrv queue is managed by record/replay,
     * creating new flush request for stopping
     * the VM may break the determinism
     */
    if (replay_events_enabled()) {
        return result;
    }

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

        aio_context_acquire(aio_context);
        ret = bdrv_flush(bs);
        if (ret < 0 && !result) {
            result = ret;
        }
        aio_context_release(aio_context);
    }

    return result;
}


typedef struct BdrvCoBlockStatusData {
    BlockDriverState *bs;
    BlockDriverState *base;
    bool want_zero;
    int64_t offset;
    int64_t bytes;
    int64_t *pnum;
    int64_t *map;
    BlockDriverState **file;
    int ret;
    bool done;
} BdrvCoBlockStatusData;

int coroutine_fn bdrv_co_block_status_from_file(BlockDriverState *bs,
                                                bool want_zero,
                                                int64_t offset,
                                                int64_t bytes,
                                                int64_t *pnum,
                                                int64_t *map,
                                                BlockDriverState **file)
{
    assert(bs->file && bs->file->bs);
    *pnum = bytes;
    *map = offset;
    *file = bs->file->bs;
    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
}

int coroutine_fn bdrv_co_block_status_from_backing(BlockDriverState *bs,
                                                   bool want_zero,
                                                   int64_t offset,
                                                   int64_t bytes,
                                                   int64_t *pnum,
                                                   int64_t *map,
                                                   BlockDriverState **file)
{
    assert(bs->backing && bs->backing->bs);
    *pnum = bytes;
    *map = offset;
    *file = bs->backing->bs;
    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID;
}

/*
 * Returns the allocation status of the specified sectors.
 * Drivers not implementing the functionality are assumed to not support
 * backing files, hence all their sectors are reported as allocated.
 *
 * If 'want_zero' is true, the caller is querying for mapping
 * purposes, with a focus on valid BDRV_BLOCK_OFFSET_VALID, _DATA, and
 * _ZERO where possible; otherwise, the result favors larger 'pnum',
 * with a focus on accurate BDRV_BLOCK_ALLOCATED.
 *
 * If 'offset' is beyond the end of the disk image the return value is
 * BDRV_BLOCK_EOF and 'pnum' is set to 0.
 *
 * 'bytes' is the max value 'pnum' should be set to.  If bytes goes
 * beyond the end of the disk image it will be clamped; if 'pnum' is set to
 * the end of the image, then the returned value will include BDRV_BLOCK_EOF.
 *
 * 'pnum' is set to the number of bytes (including and immediately
 * following the specified offset) that are easily known to be in the
 * same allocated/unallocated state.  Note that a second call starting
 * at the original offset plus returned pnum may have the same status.
 * The returned value is non-zero on success except at end-of-file.
 *
 * Returns negative errno on failure.  Otherwise, if the
 * BDRV_BLOCK_OFFSET_VALID bit is set, 'map' and 'file' (if non-NULL) are
 * set to the host mapping and BDS corresponding to the guest offset.
 */
static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
                                             bool want_zero,
                                             int64_t offset, int64_t bytes,
                                             int64_t *pnum, int64_t *map,
                                             BlockDriverState **file)
{
    int64_t total_size;
    int64_t n; /* bytes */
    int ret;
    int64_t local_map = 0;
    BlockDriverState *local_file = NULL;
    int64_t aligned_offset, aligned_bytes;
    uint32_t align;

    assert(pnum);
    *pnum = 0;
    total_size = bdrv_getlength(bs);
    if (total_size < 0) {
        ret = total_size;
        goto early_out;
    }

    if (offset >= total_size) {
        ret = BDRV_BLOCK_EOF;
        goto early_out;
    }
    if (!bytes) {
        ret = 0;
        goto early_out;
    }

    n = total_size - offset;
    if (n < bytes) {
        bytes = n;
    }

    /* Must be non-NULL or bdrv_getlength() would have failed */
    assert(bs->drv);
    if (!bs->drv->bdrv_co_block_status) {
        *pnum = bytes;
        ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED;
        if (offset + bytes == total_size) {
            ret |= BDRV_BLOCK_EOF;
        }
        if (bs->drv->protocol_name) {
            ret |= BDRV_BLOCK_OFFSET_VALID;
            local_map = offset;
            local_file = bs;
        }
        goto early_out;
    }

    bdrv_inc_in_flight(bs);

    /* Round out to request_alignment boundaries */
    align = bs->bl.request_alignment;
    aligned_offset = QEMU_ALIGN_DOWN(offset, align);
    aligned_bytes = ROUND_UP(offset + bytes, align) - aligned_offset;

    ret = bs->drv->bdrv_co_block_status(bs, want_zero, aligned_offset,
                                        aligned_bytes, pnum, &local_map,
                                        &local_file);
    if (ret < 0) {
        *pnum = 0;
        goto out;
    }

    /*
     * The driver's result must be a non-zero multiple of request_alignment.
     * Clamp pnum and adjust map to original request.
     */
    assert(*pnum && QEMU_IS_ALIGNED(*pnum, align) &&
           align > offset - aligned_offset);
    if (ret & BDRV_BLOCK_RECURSE) {
        assert(ret & BDRV_BLOCK_DATA);
        assert(ret & BDRV_BLOCK_OFFSET_VALID);
        assert(!(ret & BDRV_BLOCK_ZERO));
    }

    *pnum -= offset - aligned_offset;
    if (*pnum > bytes) {
        *pnum = bytes;
    }
    if (ret & BDRV_BLOCK_OFFSET_VALID) {
        local_map += offset - aligned_offset;
    }

    if (ret & BDRV_BLOCK_RAW) {
        assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file);
        ret = bdrv_co_block_status(local_file, want_zero, local_map,
                                   *pnum, pnum, &local_map, &local_file);
        goto out;
    }

    if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
        ret |= BDRV_BLOCK_ALLOCATED;
    } else if (want_zero) {
        if (bdrv_unallocated_blocks_are_zero(bs)) {
            ret |= BDRV_BLOCK_ZERO;
        } else if (bs->backing) {
            BlockDriverState *bs2 = bs->backing->bs;
            int64_t size2 = bdrv_getlength(bs2);

            if (size2 >= 0 && offset >= size2) {
                ret |= BDRV_BLOCK_ZERO;
            }
        }
    }

    if (want_zero && ret & BDRV_BLOCK_RECURSE &&
        local_file && local_file != bs &&
        (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) &&
        (ret & BDRV_BLOCK_OFFSET_VALID)) {
        int64_t file_pnum;
        int ret2;

        ret2 = bdrv_co_block_status(local_file, want_zero, local_map,
                                    *pnum, &file_pnum, NULL, NULL);
        if (ret2 >= 0) {
            /* Ignore errors.  This is just providing extra information, it
             * is useful but not necessary.
             */
            if (ret2 & BDRV_BLOCK_EOF &&
                (!file_pnum || ret2 & BDRV_BLOCK_ZERO)) {
                /*
                 * It is valid for the format block driver to read
                 * beyond the end of the underlying file's current
                 * size; such areas read as zero.
                 */
                ret |= BDRV_BLOCK_ZERO;
            } else {
                /* Limit request to the range reported by the protocol driver */
                *pnum = file_pnum;
                ret |= (ret2 & BDRV_BLOCK_ZERO);
            }
        }
    }

out:
    bdrv_dec_in_flight(bs);
    if (ret >= 0 && offset + *pnum == total_size) {
        ret |= BDRV_BLOCK_EOF;
    }
early_out:
    if (file) {
        *file = local_file;
    }
    if (map) {
        *map = local_map;
    }
    return ret;
}

static int coroutine_fn bdrv_co_block_status_above(BlockDriverState *bs,
                                                   BlockDriverState *base,
                                                   bool want_zero,
                                                   int64_t offset,
                                                   int64_t bytes,
                                                   int64_t *pnum,
                                                   int64_t *map,
                                                   BlockDriverState **file)
{
    BlockDriverState *p;
    int ret = 0;
    bool first = true;

    assert(bs != base);
    for (p = bs; p != base; p = backing_bs(p)) {
        ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map,
                                   file);
        if (ret < 0) {
            break;
        }
        if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) {
            /*
             * Reading beyond the end of the file continues to read
             * zeroes, but we can only widen the result to the
             * unallocated length we learned from an earlier
             * iteration.
             */
            *pnum = bytes;
        }
        if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) {
            break;
        }
        /* [offset, pnum] unallocated on this layer, which could be only
         * the first part of [offset, bytes].  */
        bytes = MIN(bytes, *pnum);
        first = false;
    }
    return ret;
}

/* Coroutine wrapper for bdrv_block_status_above() */
static void coroutine_fn bdrv_block_status_above_co_entry(void *opaque)
{
    BdrvCoBlockStatusData *data = opaque;

    data->ret = bdrv_co_block_status_above(data->bs, data->base,
                                           data->want_zero,
                                           data->offset, data->bytes,
                                           data->pnum, data->map, data->file);
    data->done = true;
    aio_wait_kick();
}

/*
 * Synchronous wrapper around bdrv_co_block_status_above().
 *
 * See bdrv_co_block_status_above() for details.
 */
static int bdrv_common_block_status_above(BlockDriverState *bs,
                                          BlockDriverState *base,
                                          bool want_zero, int64_t offset,
                                          int64_t bytes, int64_t *pnum,
                                          int64_t *map,
                                          BlockDriverState **file)
{
    Coroutine *co;
    BdrvCoBlockStatusData data = {
        .bs = bs,
        .base = base,
        .want_zero = want_zero,
        .offset = offset,
        .bytes = bytes,
        .pnum = pnum,
        .map = map,
        .file = file,
        .done = false,
    };

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

int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base,
                            int64_t offset, int64_t bytes, int64_t *pnum,
                            int64_t *map, BlockDriverState **file)
{
    return bdrv_common_block_status_above(bs, base, true, offset, bytes,
                                          pnum, map, file);
}

int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes,
                      int64_t *pnum, int64_t *map, BlockDriverState **file)
{
    return bdrv_block_status_above(bs, backing_bs(bs),
                                   offset, bytes, pnum, map, file);
}

int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset,
                                   int64_t bytes, int64_t *pnum)
{
    int ret;
    int64_t dummy;

    ret = bdrv_common_block_status_above(bs, backing_bs(bs), false, offset,
                                         bytes, pnum ? pnum : &dummy, NULL,
                                         NULL);
    if (ret < 0) {
        return ret;
    }
    return !!(ret & BDRV_BLOCK_ALLOCATED);
}

/*
 * Given an image chain: ... -> [BASE] -> [INTER1] -> [INTER2] -> [TOP]
 *
 * Return 1 if (a prefix of) the given range is allocated in any image
 * between BASE and TOP (BASE is only included if include_base is set).
 * BASE can be NULL to check if the given offset is allocated in any
 * image of the chain.  Return 0 otherwise, or negative errno on
 * failure.
 *
 * 'pnum' is set to the number of bytes (including and immediately
 * following the specified offset) that are known to be in the same
 * allocated/unallocated state.  Note that a subsequent call starting
 * at 'offset + *pnum' may return the same allocation status (in other
 * words, the result is not necessarily the maximum possible range);
 * but 'pnum' will only be 0 when end of file is reached.
 *
 */
int bdrv_is_allocated_above(BlockDriverState *top,
                            BlockDriverState *base,
                            bool include_base, int64_t offset,
                            int64_t bytes, int64_t *pnum)
{
    BlockDriverState *intermediate;
    int ret;
    int64_t n = bytes;

    assert(base || !include_base);

    intermediate = top;
    while (include_base || intermediate != base) {
        int64_t pnum_inter;
        int64_t size_inter;

        assert(intermediate);
        ret = bdrv_is_allocated(intermediate, offset, bytes, &pnum_inter);
        if (ret < 0) {
            return ret;
        }
        if (ret) {
            *pnum = pnum_inter;
            return 1;
        }

        size_inter = bdrv_getlength(intermediate);
        if (size_inter < 0) {
            return size_inter;
        }
        if (n > pnum_inter &&
            (intermediate == top || offset + pnum_inter < size_inter)) {
            n = pnum_inter;
        }

        if (intermediate == base) {
            break;
        }

        intermediate = backing_bs(intermediate);
    }

    *pnum = n;
    return 0;
}

typedef struct BdrvVmstateCo {
    BlockDriverState    *bs;
    QEMUIOVector        *qiov;
    int64_t             pos;
    bool                is_read;
    int                 ret;
} BdrvVmstateCo;

static int coroutine_fn
bdrv_co_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos,
                   bool is_read)
{
    BlockDriver *drv = bs->drv;
    int ret = -ENOTSUP;

    bdrv_inc_in_flight(bs);

    if (!drv) {
        ret = -ENOMEDIUM;
    } else if (drv->bdrv_load_vmstate) {
        if (is_read) {
            ret = drv->bdrv_load_vmstate(bs, qiov, pos);
        } else {
            ret = drv->bdrv_save_vmstate(bs, qiov, pos);
        }
    } else if (bs->file) {
        ret = bdrv_co_rw_vmstate(bs->file->bs, qiov, pos, is_read);
    }

    bdrv_dec_in_flight(bs);
    return ret;
}

static void coroutine_fn bdrv_co_rw_vmstate_entry(void *opaque)
{
    BdrvVmstateCo *co = opaque;
    co->ret = bdrv_co_rw_vmstate(co->bs, co->qiov, co->pos, co->is_read);
    aio_wait_kick();
}

static inline int
bdrv_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos,
                bool is_read)
{
    if (qemu_in_coroutine()) {
        return bdrv_co_rw_vmstate(bs, qiov, pos, is_read);
    } else {
        BdrvVmstateCo data = {
            .bs         = bs,
            .qiov       = qiov,
            .pos        = pos,
            .is_read    = is_read,
            .ret        = -EINPROGRESS,
        };
        Coroutine *co = qemu_coroutine_create(bdrv_co_rw_vmstate_entry, &data);

        bdrv_coroutine_enter(bs, co);
        BDRV_POLL_WHILE(bs, data.ret == -EINPROGRESS);
        return data.ret;
    }
}

int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
                      int64_t pos, int size)
{
    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size);
    int ret;

    ret = bdrv_writev_vmstate(bs, &qiov, pos);
    if (ret < 0) {
        return ret;
    }

    return size;
}

int bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos)
{
    return bdrv_rw_vmstate(bs, qiov, pos, false);
}

int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
                      int64_t pos, int size)
{
    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size);
    int ret;

    ret = bdrv_readv_vmstate(bs, &qiov, pos);
    if (ret < 0) {
        return ret;
    }

    return size;
}

int bdrv_readv_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos)
{
    return bdrv_rw_vmstate(bs, qiov, pos, true);
}

/**************************************************************/
/* async I/Os */

void bdrv_aio_cancel(BlockAIOCB *acb)
{
    qemu_aio_ref(acb);
    bdrv_aio_cancel_async(acb);
    while (acb->refcnt > 1) {
        if (acb->aiocb_info->get_aio_context) {
            aio_poll(acb->aiocb_info->get_aio_context(acb), true);
        } else if (acb->bs) {
            /* qemu_aio_ref and qemu_aio_unref are not thread-safe, so
             * assert that we're not using an I/O thread.  Thread-safe
             * code should use bdrv_aio_cancel_async exclusively.
             */
            assert(bdrv_get_aio_context(acb->bs) == qemu_get_aio_context());
            aio_poll(bdrv_get_aio_context(acb->bs), true);
        } else {
            abort();
        }
    }
    qemu_aio_unref(acb);
}

/* Async version of aio cancel. The caller is not blocked if the acb implements
 * cancel_async, otherwise we do nothing and let the request normally complete.
 * In either case the completion callback must be called. */
void bdrv_aio_cancel_async(BlockAIOCB *acb)
{
    if (acb->aiocb_info->cancel_async) {
        acb->aiocb_info->cancel_async(acb);
    }
}

/**************************************************************/
/* Coroutine block device emulation */

typedef struct FlushCo {
    BlockDriverState *bs;
    int ret;
} FlushCo;


static void coroutine_fn bdrv_flush_co_entry(void *opaque)
{
    FlushCo *rwco = opaque;

    rwco->ret = bdrv_co_flush(rwco->bs);
    aio_wait_kick();
}

int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
{
    int current_gen;
    int ret = 0;

    bdrv_inc_in_flight(bs);

    if (!bdrv_is_inserted(bs) || bdrv_is_read_only(bs) ||
        bdrv_is_sg(bs)) {
        goto early_exit;
    }

    qemu_co_mutex_lock(&bs->reqs_lock);
    current_gen = atomic_read(&bs->write_gen);

    /* Wait until any previous flushes are completed */
    while (bs->active_flush_req) {
        qemu_co_queue_wait(&bs->flush_queue, &bs->reqs_lock);
    }

    /* Flushes reach this point in nondecreasing current_gen order.  */
    bs->active_flush_req = true;
    qemu_co_mutex_unlock(&bs->reqs_lock);

    /* Write back all layers by calling one driver function */
    if (bs->drv->bdrv_co_flush) {
        ret = bs->drv->bdrv_co_flush(bs);
        goto out;
    }

    /* Write back cached data to the OS even with cache=unsafe */
    BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_OS);
    if (bs->drv->bdrv_co_flush_to_os) {
        ret = bs->drv->bdrv_co_flush_to_os(bs);
        if (ret < 0) {
            goto out;
        }
    }

    /* But don't actually force it to the disk with cache=unsafe */
    if (bs->open_flags & BDRV_O_NO_FLUSH) {
        goto flush_parent;
    }

    /* Check if we really need to flush anything */
    if (bs->flushed_gen == current_gen) {
        goto flush_parent;
    }

    BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_DISK);
    if (!bs->drv) {
        /* bs->drv->bdrv_co_flush() might have ejected the BDS
         * (even in case of apparent success) */
        ret = -ENOMEDIUM;
        goto out;
    }
    if (bs->drv->bdrv_co_flush_to_disk) {
        ret = bs->drv->bdrv_co_flush_to_disk(bs);
    } else if (bs->drv->bdrv_aio_flush) {
        BlockAIOCB *acb;
        CoroutineIOCompletion co = {
            .coroutine = qemu_coroutine_self(),
        };

        acb = bs->drv->bdrv_aio_flush(bs, bdrv_co_io_em_complete, &co);
        if (acb == NULL) {
            ret = -EIO;
        } else {
            qemu_coroutine_yield();
            ret = co.ret;
        }
    } else {
        /*
         * Some block drivers always operate in either writethrough or unsafe
         * mode and don't support bdrv_flush therefore. Usually qemu doesn't
         * know how the server works (because the behaviour is hardcoded or
         * depends on server-side configuration), so we can't ensure that
         * everything is safe on disk. Returning an error doesn't work because
         * that would break guests even if the server operates in writethrough
         * mode.
         *
         * Let's hope the user knows what he's doing.
         */
        ret = 0;
    }

    if (ret < 0) {
        goto out;
    }

    /* Now flush the underlying protocol.  It will also have BDRV_O_NO_FLUSH
     * in the case of cache=unsafe, so there are no useless flushes.
     */
flush_parent:
    ret = bs->file ? bdrv_co_flush(bs->file->bs) : 0;
out:
    /* Notify any pending flushes that we have completed */
    if (ret == 0) {
        bs->flushed_gen = current_gen;
    }

    qemu_co_mutex_lock(&bs->reqs_lock);
    bs->active_flush_req = false;
    /* Return value is ignored - it's ok if wait queue is empty */
    qemu_co_queue_next(&bs->flush_queue);
    qemu_co_mutex_unlock(&bs->reqs_lock);

early_exit:
    bdrv_dec_in_flight(bs);
    return ret;
}

int bdrv_flush(BlockDriverState *bs)
{
    Coroutine *co;
    FlushCo flush_co = {
        .bs = bs,
        .ret = NOT_DONE,
    };

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

    return flush_co.ret;
}

typedef struct DiscardCo {
    BdrvChild *child;
    int64_t offset;
    int64_t bytes;
    int ret;
} DiscardCo;
static void coroutine_fn bdrv_pdiscard_co_entry(void *opaque)
{
    DiscardCo *rwco = opaque;

    rwco->ret = bdrv_co_pdiscard(rwco->child, rwco->offset, rwco->bytes);
    aio_wait_kick();
}

int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset,
                                  int64_t bytes)
{
    BdrvTrackedRequest req;
    int max_pdiscard, ret;
    int head, tail, align;
    BlockDriverState *bs = child->bs;

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

    if (bdrv_has_readonly_bitmaps(bs)) {
        return -EPERM;
    }

    if (offset < 0 || bytes < 0 || bytes > INT64_MAX - offset) {
        return -EIO;
    }

    /* Do nothing if disabled.  */
    if (!(bs->open_flags & BDRV_O_UNMAP)) {
        return 0;
    }

    if (!bs->drv->bdrv_co_pdiscard && !bs->drv->bdrv_aio_pdiscard) {
        return 0;
    }

    /* Discard is advisory, but some devices track and coalesce
     * unaligned requests, so we must pass everything down rather than
     * round here.  Still, most devices will just silently ignore
     * unaligned requests (by returning -ENOTSUP), so we must fragment
     * the request accordingly.  */
    align = MAX(bs->bl.pdiscard_alignment, bs->bl.request_alignment);
    assert(align % bs->bl.request_alignment == 0);
    head = offset % align;
    tail = (offset + bytes) % align;

    bdrv_inc_in_flight(bs);
    tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_DISCARD);

    ret = bdrv_co_write_req_prepare(child, offset, bytes, &req, 0);
    if (ret < 0) {
        goto out;
    }

    max_pdiscard = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_pdiscard, INT_MAX),
                                   align);
    assert(max_pdiscard >= bs->bl.request_alignment);

    while (bytes > 0) {
        int64_t num = bytes;

        if (head) {
            /* Make small requests to get to alignment boundaries. */
            num = MIN(bytes, align - head);
            if (!QEMU_IS_ALIGNED(num, bs->bl.request_alignment)) {
                num %= bs->bl.request_alignment;
            }
            head = (head + num) % align;
            assert(num < max_pdiscard);
        } else if (tail) {
            if (num > align) {
                /* Shorten the request to the last aligned cluster.  */
                num -= tail;
            } else if (!QEMU_IS_ALIGNED(tail, bs->bl.request_alignment) &&
                       tail > bs->bl.request_alignment) {
                tail %= bs->bl.request_alignment;
                num -= tail;
            }
        }
        /* limit request size */
        if (num > max_pdiscard) {
            num = max_pdiscard;
        }

        if (!bs->drv) {
            ret = -ENOMEDIUM;
            goto out;
        }
        if (bs->drv->bdrv_co_pdiscard) {
            ret = bs->drv->bdrv_co_pdiscard(bs, offset, num);
        } else {
            BlockAIOCB *acb;
            CoroutineIOCompletion co = {
                .coroutine = qemu_coroutine_self(),
            };

            acb = bs->drv->bdrv_aio_pdiscard(bs, offset, num,
                                             bdrv_co_io_em_complete, &co);
            if (acb == NULL) {
                ret = -EIO;
                goto out;
            } else {
                qemu_coroutine_yield();
                ret = co.ret;
            }
        }
        if (ret && ret != -ENOTSUP) {
            goto out;
        }

        offset += num;
        bytes -= num;
    }
    ret = 0;
out:
    bdrv_co_write_req_finish(child, req.offset, req.bytes, &req, ret);
    tracked_request_end(&req);
    bdrv_dec_in_flight(bs);
    return ret;
}

int bdrv_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes)
{
    Coroutine *co;
    DiscardCo rwco = {
        .child = child,
        .offset = offset,
        .bytes = bytes,
        .ret = NOT_DONE,
    };

    if (qemu_in_coroutine()) {
        /* Fast-path if already in coroutine context */
        bdrv_pdiscard_co_entry(&rwco);
    } else {
        co = qemu_coroutine_create(bdrv_pdiscard_co_entry, &rwco);
        bdrv_coroutine_enter(child->bs, co);
        BDRV_POLL_WHILE(child->bs, rwco.ret == NOT_DONE);
    }

    return rwco.ret;
}

int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf)
{
    BlockDriver *drv = bs->drv;
    CoroutineIOCompletion co = {
        .coroutine = qemu_coroutine_self(),
    };
    BlockAIOCB *acb;

    bdrv_inc_in_flight(bs);
    if (!drv || (!drv->bdrv_aio_ioctl && !drv->bdrv_co_ioctl)) {
        co.ret = -ENOTSUP;
        goto out;
    }

    if (drv->bdrv_co_ioctl) {
        co.ret = drv->bdrv_co_ioctl(bs, req, buf);
    } else {
        acb = drv->bdrv_aio_ioctl(bs, req, buf, bdrv_co_io_em_complete, &co);
        if (!acb) {
            co.ret = -ENOTSUP;
            goto out;
        }
        qemu_coroutine_yield();
    }
out:
    bdrv_dec_in_flight(bs);
    return co.ret;
}

void *qemu_blockalign(BlockDriverState *bs, size_t size)
{
    return qemu_memalign(bdrv_opt_mem_align(bs), size);
}

void *qemu_blockalign0(BlockDriverState *bs, size_t size)
{
    return memset(qemu_blockalign(bs, size), 0, size);
}

void *qemu_try_blockalign(BlockDriverState *bs, size_t size)
{
    size_t align = bdrv_opt_mem_align(bs);

    /* Ensure that NULL is never returned on success */
    assert(align > 0);
    if (size == 0) {
        size = align;
    }

    return qemu_try_memalign(align, size);
}

void *qemu_try_blockalign0(BlockDriverState *bs, size_t size)
{
    void *mem = qemu_try_blockalign(bs, size);

    if (mem) {
        memset(mem, 0, size);
    }

    return mem;
}

/*
 * Check if all memory in this vector is sector aligned.
 */
bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
{
    int i;
    size_t alignment = bdrv_min_mem_align(bs);

    for (i = 0; i < qiov->niov; i++) {
        if ((uintptr_t) qiov->iov[i].iov_base % alignment) {
            return false;
        }
        if (qiov->iov[i].iov_len % alignment) {
            return false;
        }
    }

    return true;
}

void bdrv_add_before_write_notifier(BlockDriverState *bs,
                                    NotifierWithReturn *notifier)
{
    notifier_with_return_list_add(&bs->before_write_notifiers, notifier);
}

void bdrv_io_plug(BlockDriverState *bs)
{
    BdrvChild *child;

    QLIST_FOREACH(child, &bs->children, next) {
        bdrv_io_plug(child->bs);
    }

    if (atomic_fetch_inc(&bs->io_plugged) == 0) {
        BlockDriver *drv = bs->drv;
        if (drv && drv->bdrv_io_plug) {
            drv->bdrv_io_plug(bs);
        }
    }
}

void bdrv_io_unplug(BlockDriverState *bs)
{
    BdrvChild *child;

    assert(bs->io_plugged);
    if (atomic_fetch_dec(&bs->io_plugged) == 1) {
        BlockDriver *drv = bs->drv;
        if (drv && drv->bdrv_io_unplug) {
            drv->bdrv_io_unplug(bs);
        }
    }

    QLIST_FOREACH(child, &bs->children, next) {
        bdrv_io_unplug(child->bs);
    }
}

void bdrv_register_buf(BlockDriverState *bs, void *host, size_t size)
{
    BdrvChild *child;

    if (bs->drv && bs->drv->bdrv_register_buf) {
        bs->drv->bdrv_register_buf(bs, host, size);
    }
    QLIST_FOREACH(child, &bs->children, next) {
        bdrv_register_buf(child->bs, host, size);
    }
}

void bdrv_unregister_buf(BlockDriverState *bs, void *host)
{
    BdrvChild *child;

    if (bs->drv && bs->drv->bdrv_unregister_buf) {
        bs->drv->bdrv_unregister_buf(bs, host);
    }
    QLIST_FOREACH(child, &bs->children, next) {
        bdrv_unregister_buf(child->bs, host);
    }
}

static int coroutine_fn bdrv_co_copy_range_internal(
        BdrvChild *src, uint64_t src_offset, BdrvChild *dst,
        uint64_t dst_offset, uint64_t bytes,
        BdrvRequestFlags read_flags, BdrvRequestFlags write_flags,
        bool recurse_src)
{
    BdrvTrackedRequest req;
    int ret;

    /* TODO We can support BDRV_REQ_NO_FALLBACK here */
    assert(!(read_flags & BDRV_REQ_NO_FALLBACK));
    assert(!(write_flags & BDRV_REQ_NO_FALLBACK));

    if (!dst || !dst->bs) {
        return -ENOMEDIUM;
    }
    ret = bdrv_check_byte_request(dst->bs, dst_offset, bytes);
    if (ret) {
        return ret;
    }
    if (write_flags & BDRV_REQ_ZERO_WRITE) {
        return bdrv_co_pwrite_zeroes(dst, dst_offset, bytes, write_flags);
    }

    if (!src || !src->bs) {
        return -ENOMEDIUM;
    }
    ret = bdrv_check_byte_request(src->bs, src_offset, bytes);
    if (ret) {
        return ret;
    }

    if (!src->bs->drv->bdrv_co_copy_range_from
        || !dst->bs->drv->bdrv_co_copy_range_to
        || src->bs->encrypted || dst->bs->encrypted) {
        return -ENOTSUP;
    }

    if (recurse_src) {
        bdrv_inc_in_flight(src->bs);
        tracked_request_begin(&req, src->bs, src_offset, bytes,
                              BDRV_TRACKED_READ);

        /* BDRV_REQ_SERIALISING is only for write operation */
        assert(!(read_flags & BDRV_REQ_SERIALISING));
        bdrv_wait_serialising_requests(&req);

        ret = src->bs->drv->bdrv_co_copy_range_from(src->bs,
                                                    src, src_offset,
                                                    dst, dst_offset,
                                                    bytes,
                                                    read_flags, write_flags);

        tracked_request_end(&req);
        bdrv_dec_in_flight(src->bs);
    } else {
        bdrv_inc_in_flight(dst->bs);
        tracked_request_begin(&req, dst->bs, dst_offset, bytes,
                              BDRV_TRACKED_WRITE);
        ret = bdrv_co_write_req_prepare(dst, dst_offset, bytes, &req,
                                        write_flags);
        if (!ret) {
            ret = dst->bs->drv->bdrv_co_copy_range_to(dst->bs,
                                                      src, src_offset,
                                                      dst, dst_offset,
                                                      bytes,
                                                      read_flags, write_flags);
        }
        bdrv_co_write_req_finish(dst, dst_offset, bytes, &req, ret);
        tracked_request_end(&req);
        bdrv_dec_in_flight(dst->bs);
    }

    return ret;
}

/* Copy range from @src to @dst.
 *
 * See the comment of bdrv_co_copy_range for the parameter and return value
 * semantics. */
int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, uint64_t src_offset,
                                         BdrvChild *dst, uint64_t dst_offset,
                                         uint64_t bytes,
                                         BdrvRequestFlags read_flags,
                                         BdrvRequestFlags write_flags)
{
    trace_bdrv_co_copy_range_from(src, src_offset, dst, dst_offset, bytes,
                                  read_flags, write_flags);
    return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
                                       bytes, read_flags, write_flags, true);
}

/* Copy range from @src to @dst.
 *
 * See the comment of bdrv_co_copy_range for the parameter and return value
 * semantics. */
int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, uint64_t src_offset,
                                       BdrvChild *dst, uint64_t dst_offset,
                                       uint64_t bytes,
                                       BdrvRequestFlags read_flags,
                                       BdrvRequestFlags write_flags)
{
    trace_bdrv_co_copy_range_to(src, src_offset, dst, dst_offset, bytes,
                                read_flags, write_flags);
    return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
                                       bytes, read_flags, write_flags, false);
}

int coroutine_fn bdrv_co_copy_range(BdrvChild *src, uint64_t src_offset,
                                    BdrvChild *dst, uint64_t dst_offset,
                                    uint64_t bytes, BdrvRequestFlags read_flags,
                                    BdrvRequestFlags write_flags)
{
    return bdrv_co_copy_range_from(src, src_offset,
                                   dst, dst_offset,
                                   bytes, read_flags, write_flags);
}

static void bdrv_parent_cb_resize(BlockDriverState *bs)
{
    BdrvChild *c;
    QLIST_FOREACH(c, &bs->parents, next_parent) {
        if (c->role->resize) {
            c->role->resize(c);
        }
    }
}

/**
 * Truncate file to 'offset' bytes (needed only for file protocols)
 *
 * If 'exact' is true, the file must be resized to exactly the given
 * 'offset'.  Otherwise, it is sufficient for the node to be at least
 * 'offset' bytes in length.
 */
int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
                                  PreallocMode prealloc, BdrvRequestFlags flags,
                                  Error **errp)
{
    BlockDriverState *bs = child->bs;
    BlockDriver *drv = bs->drv;
    BdrvTrackedRequest req;
    int64_t old_size, new_bytes;
    int ret;


    /* if bs->drv == NULL, bs is closed, so there's nothing to do here */
    if (!drv) {
        error_setg(errp, "No medium inserted");
        return -ENOMEDIUM;
    }
    if (offset < 0) {
        error_setg(errp, "Image size cannot be negative");
        return -EINVAL;
    }

    old_size = bdrv_getlength(bs);
    if (old_size < 0) {
        error_setg_errno(errp, -old_size, "Failed to get old image size");
        return old_size;
    }

    if (offset > old_size) {
        new_bytes = offset - old_size;
    } else {
        new_bytes = 0;
    }

    bdrv_inc_in_flight(bs);
    tracked_request_begin(&req, bs, offset - new_bytes, new_bytes,
                          BDRV_TRACKED_TRUNCATE);

    /* If we are growing the image and potentially using preallocation for the
     * new area, we need to make sure that no write requests are made to it
     * concurrently or they might be overwritten by preallocation. */
    if (new_bytes) {
        bdrv_mark_request_serialising(&req, 1);
    }
    if (bs->read_only) {
        error_setg(errp, "Image is read-only");
        ret = -EACCES;
        goto out;
    }
    ret = bdrv_co_write_req_prepare(child, offset - new_bytes, new_bytes, &req,
                                    0);
    if (ret < 0) {
        error_setg_errno(errp, -ret,
                         "Failed to prepare request for truncation");
        goto out;
    }

    /*
     * If the image has a backing file that is large enough that it would
     * provide data for the new area, we cannot leave it unallocated because
     * then the backing file content would become visible. Instead, zero-fill
     * the new area.
     *
     * Note that if the image has a backing file, but was opened without the
     * backing file, taking care of keeping things consistent with that backing
     * file is the user's responsibility.
     */
    if (new_bytes && bs->backing) {
        int64_t backing_len;

        backing_len = bdrv_getlength(backing_bs(bs));
        if (backing_len < 0) {
            ret = backing_len;
            error_setg_errno(errp, -ret, "Could not get backing file size");
            goto out;
        }

        if (backing_len > old_size) {
            flags |= BDRV_REQ_ZERO_WRITE;
        }
    }

    if (drv->bdrv_co_truncate) {
        if (flags & ~bs->supported_truncate_flags) {
            error_setg(errp, "Block driver does not support requested flags");
            ret = -ENOTSUP;
            goto out;
        }
        ret = drv->bdrv_co_truncate(bs, offset, exact, prealloc, flags, errp);
    } else if (bs->file && drv->is_filter) {
        ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, flags, errp);
    } else {
        error_setg(errp, "Image format driver does not support resize");
        ret = -ENOTSUP;
        goto out;
    }
    if (ret < 0) {
        goto out;
    }

    ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Could not refresh total sector count");
    } else {
        offset = bs->total_sectors * BDRV_SECTOR_SIZE;
    }
    /* It's possible that truncation succeeded but refresh_total_sectors
     * failed, but the latter doesn't affect how we should finish the request.
     * Pass 0 as the last parameter so that dirty bitmaps etc. are handled. */
    bdrv_co_write_req_finish(child, offset - new_bytes, new_bytes, &req, 0);

out:
    tracked_request_end(&req);
    bdrv_dec_in_flight(bs);

    return ret;
}

typedef struct TruncateCo {
    BdrvChild *child;
    int64_t offset;
    bool exact;
    PreallocMode prealloc;
    BdrvRequestFlags flags;
    Error **errp;
    int ret;
} TruncateCo;

static void coroutine_fn bdrv_truncate_co_entry(void *opaque)
{
    TruncateCo *tco = opaque;
    tco->ret = bdrv_co_truncate(tco->child, tco->offset, tco->exact,
                                tco->prealloc, tco->flags, tco->errp);
    aio_wait_kick();
}

int bdrv_truncate(BdrvChild *child, int64_t offset, bool exact,
                  PreallocMode prealloc, BdrvRequestFlags flags, Error **errp)
{
    Coroutine *co;
    TruncateCo tco = {
        .child      = child,
        .offset     = offset,
        .exact      = exact,
        .prealloc   = prealloc,
        .flags      = flags,
        .errp       = errp,
        .ret        = NOT_DONE,
    };

    if (qemu_in_coroutine()) {
        /* Fast-path if already in coroutine context */
        bdrv_truncate_co_entry(&tco);
    } else {
        co = qemu_coroutine_create(bdrv_truncate_co_entry, &tco);
        bdrv_coroutine_enter(child->bs, co);
        BDRV_POLL_WHILE(child->bs, tco.ret == NOT_DONE);
    }

    return tco.ret;
}