aboutsummaryrefslogtreecommitdiff
path: root/block/block-backend.c
blob: edad02a0f2a3a0b18bbe174fc7f8ec33aa7ed988 (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
/*
 * QEMU Block backends
 *
 * Copyright (C) 2014-2016 Red Hat, Inc.
 *
 * Authors:
 *  Markus Armbruster <armbru@redhat.com>,
 *
 * This work is licensed under the terms of the GNU LGPL, version 2.1
 * or later.  See the COPYING.LIB file in the top-level directory.
 */

#include "qemu/osdep.h"
#include "sysemu/block-backend.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "block/throttle-groups.h"
#include "sysemu/blockdev.h"
#include "sysemu/sysemu.h"
#include "qapi/error.h"
#include "qapi/qapi-events-block.h"
#include "qemu/id.h"
#include "qemu/option.h"
#include "trace.h"
#include "migration/misc.h"

/* Number of coroutines to reserve per attached device model */
#define COROUTINE_POOL_RESERVATION 64

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

static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb);

typedef struct BlockBackendAioNotifier {
    void (*attached_aio_context)(AioContext *new_context, void *opaque);
    void (*detach_aio_context)(void *opaque);
    void *opaque;
    QLIST_ENTRY(BlockBackendAioNotifier) list;
} BlockBackendAioNotifier;

struct BlockBackend {
    char *name;
    int refcnt;
    BdrvChild *root;
    DriveInfo *legacy_dinfo;    /* null unless created by drive_new() */
    QTAILQ_ENTRY(BlockBackend) link;         /* for block_backends */
    QTAILQ_ENTRY(BlockBackend) monitor_link; /* for monitor_block_backends */
    BlockBackendPublic public;

    DeviceState *dev;           /* attached device model, if any */
    const BlockDevOps *dev_ops;
    void *dev_opaque;

    /* the block size for which the guest device expects atomicity */
    int guest_block_size;

    /* If the BDS tree is removed, some of its options are stored here (which
     * can be used to restore those options in the new BDS on insert) */
    BlockBackendRootState root_state;

    bool enable_write_cache;

    /* I/O stats (display with "info blockstats"). */
    BlockAcctStats stats;

    BlockdevOnError on_read_error, on_write_error;
    bool iostatus_enabled;
    BlockDeviceIoStatus iostatus;

    uint64_t perm;
    uint64_t shared_perm;
    bool disable_perm;

    bool allow_write_beyond_eof;

    NotifierList remove_bs_notifiers, insert_bs_notifiers;
    QLIST_HEAD(, BlockBackendAioNotifier) aio_notifiers;

    int quiesce_counter;
    VMChangeStateEntry *vmsh;
    bool force_allow_inactivate;

    /* Number of in-flight aio requests.  BlockDriverState also counts
     * in-flight requests but aio requests can exist even when blk->root is
     * NULL, so we cannot rely on its counter for that case.
     * Accessed with atomic ops.
     */
    unsigned int in_flight;
};

typedef struct BlockBackendAIOCB {
    BlockAIOCB common;
    BlockBackend *blk;
    int ret;
} BlockBackendAIOCB;

static const AIOCBInfo block_backend_aiocb_info = {
    .get_aio_context = blk_aiocb_get_aio_context,
    .aiocb_size = sizeof(BlockBackendAIOCB),
};

static void drive_info_del(DriveInfo *dinfo);
static BlockBackend *bdrv_first_blk(BlockDriverState *bs);

/* All BlockBackends */
static QTAILQ_HEAD(, BlockBackend) block_backends =
    QTAILQ_HEAD_INITIALIZER(block_backends);

/* All BlockBackends referenced by the monitor and which are iterated through by
 * blk_next() */
static QTAILQ_HEAD(, BlockBackend) monitor_block_backends =
    QTAILQ_HEAD_INITIALIZER(monitor_block_backends);

static void blk_root_inherit_options(int *child_flags, QDict *child_options,
                                     int parent_flags, QDict *parent_options)
{
    /* We're not supposed to call this function for root nodes */
    abort();
}
static void blk_root_drained_begin(BdrvChild *child);
static bool blk_root_drained_poll(BdrvChild *child);
static void blk_root_drained_end(BdrvChild *child);

static void blk_root_change_media(BdrvChild *child, bool load);
static void blk_root_resize(BdrvChild *child);

static char *blk_root_get_parent_desc(BdrvChild *child)
{
    BlockBackend *blk = child->opaque;
    char *dev_id;

    if (blk->name) {
        return g_strdup(blk->name);
    }

    dev_id = blk_get_attached_dev_id(blk);
    if (*dev_id) {
        return dev_id;
    } else {
        /* TODO Callback into the BB owner for something more detailed */
        g_free(dev_id);
        return g_strdup("a block device");
    }
}

static const char *blk_root_get_name(BdrvChild *child)
{
    return blk_name(child->opaque);
}

static void blk_vm_state_changed(void *opaque, int running, RunState state)
{
    Error *local_err = NULL;
    BlockBackend *blk = opaque;

    if (state == RUN_STATE_INMIGRATE) {
        return;
    }

    qemu_del_vm_change_state_handler(blk->vmsh);
    blk->vmsh = NULL;
    blk_set_perm(blk, blk->perm, blk->shared_perm, &local_err);
    if (local_err) {
        error_report_err(local_err);
    }
}

/*
 * Notifies the user of the BlockBackend that migration has completed. qdev
 * devices can tighten their permissions in response (specifically revoke
 * shared write permissions that we needed for storage migration).
 *
 * If an error is returned, the VM cannot be allowed to be resumed.
 */
static void blk_root_activate(BdrvChild *child, Error **errp)
{
    BlockBackend *blk = child->opaque;
    Error *local_err = NULL;

    if (!blk->disable_perm) {
        return;
    }

    blk->disable_perm = false;

    blk_set_perm(blk, blk->perm, BLK_PERM_ALL, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        blk->disable_perm = true;
        return;
    }

    if (runstate_check(RUN_STATE_INMIGRATE)) {
        /* Activation can happen when migration process is still active, for
         * example when nbd_server_add is called during non-shared storage
         * migration. Defer the shared_perm update to migration completion. */
        if (!blk->vmsh) {
            blk->vmsh = qemu_add_vm_change_state_handler(blk_vm_state_changed,
                                                         blk);
        }
        return;
    }

    blk_set_perm(blk, blk->perm, blk->shared_perm, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        blk->disable_perm = true;
        return;
    }
}

void blk_set_force_allow_inactivate(BlockBackend *blk)
{
    blk->force_allow_inactivate = true;
}

static bool blk_can_inactivate(BlockBackend *blk)
{
    /* If it is a guest device, inactivate is ok. */
    if (blk->dev || blk_name(blk)[0]) {
        return true;
    }

    /* Inactivating means no more writes to the image can be done,
     * even if those writes would be changes invisible to the
     * guest.  For block job BBs that satisfy this, we can just allow
     * it.  This is the case for mirror job source, which is required
     * by libvirt non-shared block migration. */
    if (!(blk->perm & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED))) {
        return true;
    }

    return blk->force_allow_inactivate;
}

static int blk_root_inactivate(BdrvChild *child)
{
    BlockBackend *blk = child->opaque;

    if (blk->disable_perm) {
        return 0;
    }

    if (!blk_can_inactivate(blk)) {
        return -EPERM;
    }

    blk->disable_perm = true;
    if (blk->root) {
        bdrv_child_try_set_perm(blk->root, 0, BLK_PERM_ALL, &error_abort);
    }

    return 0;
}

static void blk_root_attach(BdrvChild *child)
{
    BlockBackend *blk = child->opaque;
    BlockBackendAioNotifier *notifier;

    trace_blk_root_attach(child, blk, child->bs);

    QLIST_FOREACH(notifier, &blk->aio_notifiers, list) {
        bdrv_add_aio_context_notifier(child->bs,
                notifier->attached_aio_context,
                notifier->detach_aio_context,
                notifier->opaque);
    }
}

static void blk_root_detach(BdrvChild *child)
{
    BlockBackend *blk = child->opaque;
    BlockBackendAioNotifier *notifier;

    trace_blk_root_detach(child, blk, child->bs);

    QLIST_FOREACH(notifier, &blk->aio_notifiers, list) {
        bdrv_remove_aio_context_notifier(child->bs,
                notifier->attached_aio_context,
                notifier->detach_aio_context,
                notifier->opaque);
    }
}

static const BdrvChildRole child_root = {
    .inherit_options    = blk_root_inherit_options,

    .change_media       = blk_root_change_media,
    .resize             = blk_root_resize,
    .get_name           = blk_root_get_name,
    .get_parent_desc    = blk_root_get_parent_desc,

    .drained_begin      = blk_root_drained_begin,
    .drained_poll       = blk_root_drained_poll,
    .drained_end        = blk_root_drained_end,

    .activate           = blk_root_activate,
    .inactivate         = blk_root_inactivate,

    .attach             = blk_root_attach,
    .detach             = blk_root_detach,
};

/*
 * Create a new BlockBackend with a reference count of one.
 *
 * @perm is a bitmasks of BLK_PERM_* constants which describes the permissions
 * to request for a block driver node that is attached to this BlockBackend.
 * @shared_perm is a bitmask which describes which permissions may be granted
 * to other users of the attached node.
 * Both sets of permissions can be changed later using blk_set_perm().
 *
 * Return the new BlockBackend on success, null on failure.
 */
BlockBackend *blk_new(uint64_t perm, uint64_t shared_perm)
{
    BlockBackend *blk;

    blk = g_new0(BlockBackend, 1);
    blk->refcnt = 1;
    blk->perm = perm;
    blk->shared_perm = shared_perm;
    blk_set_enable_write_cache(blk, true);

    blk->on_read_error = BLOCKDEV_ON_ERROR_REPORT;
    blk->on_write_error = BLOCKDEV_ON_ERROR_ENOSPC;

    block_acct_init(&blk->stats);

    notifier_list_init(&blk->remove_bs_notifiers);
    notifier_list_init(&blk->insert_bs_notifiers);
    QLIST_INIT(&blk->aio_notifiers);

    QTAILQ_INSERT_TAIL(&block_backends, blk, link);
    return blk;
}

/*
 * Creates a new BlockBackend, opens a new BlockDriverState, and connects both.
 *
 * Just as with bdrv_open(), after having called this function the reference to
 * @options belongs to the block layer (even on failure).
 *
 * TODO: Remove @filename and @flags; it should be possible to specify a whole
 * BDS tree just by specifying the @options QDict (or @reference,
 * alternatively). At the time of adding this function, this is not possible,
 * though, so callers of this function have to be able to specify @filename and
 * @flags.
 */
BlockBackend *blk_new_open(const char *filename, const char *reference,
                           QDict *options, int flags, Error **errp)
{
    BlockBackend *blk;
    BlockDriverState *bs;
    uint64_t perm = 0;

    /* blk_new_open() is mainly used in .bdrv_create implementations and the
     * tools where sharing isn't a concern because the BDS stays private, so we
     * just request permission according to the flags.
     *
     * The exceptions are xen_disk and blockdev_init(); in these cases, the
     * caller of blk_new_open() doesn't make use of the permissions, but they
     * shouldn't hurt either. We can still share everything here because the
     * guest devices will add their own blockers if they can't share. */
    if ((flags & BDRV_O_NO_IO) == 0) {
        perm |= BLK_PERM_CONSISTENT_READ;
        if (flags & BDRV_O_RDWR) {
            perm |= BLK_PERM_WRITE;
        }
    }
    if (flags & BDRV_O_RESIZE) {
        perm |= BLK_PERM_RESIZE;
    }

    blk = blk_new(perm, BLK_PERM_ALL);
    bs = bdrv_open(filename, reference, options, flags, errp);
    if (!bs) {
        blk_unref(blk);
        return NULL;
    }

    blk->root = bdrv_root_attach_child(bs, "root", &child_root,
                                       perm, BLK_PERM_ALL, blk, errp);
    if (!blk->root) {
        bdrv_unref(bs);
        blk_unref(blk);
        return NULL;
    }

    return blk;
}

static void blk_delete(BlockBackend *blk)
{
    assert(!blk->refcnt);
    assert(!blk->name);
    assert(!blk->dev);
    if (blk->public.throttle_group_member.throttle_state) {
        blk_io_limits_disable(blk);
    }
    if (blk->root) {
        blk_remove_bs(blk);
    }
    if (blk->vmsh) {
        qemu_del_vm_change_state_handler(blk->vmsh);
        blk->vmsh = NULL;
    }
    assert(QLIST_EMPTY(&blk->remove_bs_notifiers.notifiers));
    assert(QLIST_EMPTY(&blk->insert_bs_notifiers.notifiers));
    assert(QLIST_EMPTY(&blk->aio_notifiers));
    QTAILQ_REMOVE(&block_backends, blk, link);
    drive_info_del(blk->legacy_dinfo);
    block_acct_cleanup(&blk->stats);
    g_free(blk);
}

static void drive_info_del(DriveInfo *dinfo)
{
    if (!dinfo) {
        return;
    }
    qemu_opts_del(dinfo->opts);
    g_free(dinfo);
}

int blk_get_refcnt(BlockBackend *blk)
{
    return blk ? blk->refcnt : 0;
}

/*
 * Increment @blk's reference count.
 * @blk must not be null.
 */
void blk_ref(BlockBackend *blk)
{
    assert(blk->refcnt > 0);
    blk->refcnt++;
}

/*
 * Decrement @blk's reference count.
 * If this drops it to zero, destroy @blk.
 * For convenience, do nothing if @blk is null.
 */
void blk_unref(BlockBackend *blk)
{
    if (blk) {
        assert(blk->refcnt > 0);
        if (blk->refcnt > 1) {
            blk->refcnt--;
        } else {
            blk_drain(blk);
            /* blk_drain() cannot resurrect blk, nobody held a reference */
            assert(blk->refcnt == 1);
            blk->refcnt = 0;
            blk_delete(blk);
        }
    }
}

/*
 * Behaves similarly to blk_next() but iterates over all BlockBackends, even the
 * ones which are hidden (i.e. are not referenced by the monitor).
 */
BlockBackend *blk_all_next(BlockBackend *blk)
{
    return blk ? QTAILQ_NEXT(blk, link)
               : QTAILQ_FIRST(&block_backends);
}

void blk_remove_all_bs(void)
{
    BlockBackend *blk = NULL;

    while ((blk = blk_all_next(blk)) != NULL) {
        AioContext *ctx = blk_get_aio_context(blk);

        aio_context_acquire(ctx);
        if (blk->root) {
            blk_remove_bs(blk);
        }
        aio_context_release(ctx);
    }
}

/*
 * Return the monitor-owned BlockBackend after @blk.
 * If @blk is null, return the first one.
 * Else, return @blk's next sibling, which may be null.
 *
 * To iterate over all BlockBackends, do
 * for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
 *     ...
 * }
 */
BlockBackend *blk_next(BlockBackend *blk)
{
    return blk ? QTAILQ_NEXT(blk, monitor_link)
               : QTAILQ_FIRST(&monitor_block_backends);
}

/* Iterates over all top-level BlockDriverStates, i.e. BDSs that are owned by
 * the monitor or attached to a BlockBackend */
BlockDriverState *bdrv_next(BdrvNextIterator *it)
{
    BlockDriverState *bs, *old_bs;

    /* Must be called from the main loop */
    assert(qemu_get_current_aio_context() == qemu_get_aio_context());

    /* First, return all root nodes of BlockBackends. In order to avoid
     * returning a BDS twice when multiple BBs refer to it, we only return it
     * if the BB is the first one in the parent list of the BDS. */
    if (it->phase == BDRV_NEXT_BACKEND_ROOTS) {
        BlockBackend *old_blk = it->blk;

        old_bs = old_blk ? blk_bs(old_blk) : NULL;

        do {
            it->blk = blk_all_next(it->blk);
            bs = it->blk ? blk_bs(it->blk) : NULL;
        } while (it->blk && (bs == NULL || bdrv_first_blk(bs) != it->blk));

        if (it->blk) {
            blk_ref(it->blk);
        }
        blk_unref(old_blk);

        if (bs) {
            bdrv_ref(bs);
            bdrv_unref(old_bs);
            return bs;
        }
        it->phase = BDRV_NEXT_MONITOR_OWNED;
    } else {
        old_bs = it->bs;
    }

    /* Then return the monitor-owned BDSes without a BB attached. Ignore all
     * BDSes that are attached to a BlockBackend here; they have been handled
     * by the above block already */
    do {
        it->bs = bdrv_next_monitor_owned(it->bs);
        bs = it->bs;
    } while (bs && bdrv_has_blk(bs));

    if (bs) {
        bdrv_ref(bs);
    }
    bdrv_unref(old_bs);

    return bs;
}

static void bdrv_next_reset(BdrvNextIterator *it)
{
    *it = (BdrvNextIterator) {
        .phase = BDRV_NEXT_BACKEND_ROOTS,
    };
}

BlockDriverState *bdrv_first(BdrvNextIterator *it)
{
    bdrv_next_reset(it);
    return bdrv_next(it);
}

/* Must be called when aborting a bdrv_next() iteration before
 * bdrv_next() returns NULL */
void bdrv_next_cleanup(BdrvNextIterator *it)
{
    /* Must be called from the main loop */
    assert(qemu_get_current_aio_context() == qemu_get_aio_context());

    if (it->phase == BDRV_NEXT_BACKEND_ROOTS) {
        if (it->blk) {
            bdrv_unref(blk_bs(it->blk));
            blk_unref(it->blk);
        }
    } else {
        bdrv_unref(it->bs);
    }

    bdrv_next_reset(it);
}

/*
 * Add a BlockBackend into the list of backends referenced by the monitor, with
 * the given @name acting as the handle for the monitor.
 * Strictly for use by blockdev.c.
 *
 * @name must not be null or empty.
 *
 * Returns true on success and false on failure. In the latter case, an Error
 * object is returned through @errp.
 */
bool monitor_add_blk(BlockBackend *blk, const char *name, Error **errp)
{
    assert(!blk->name);
    assert(name && name[0]);

    if (!id_wellformed(name)) {
        error_setg(errp, "Invalid device name");
        return false;
    }
    if (blk_by_name(name)) {
        error_setg(errp, "Device with id '%s' already exists", name);
        return false;
    }
    if (bdrv_find_node(name)) {
        error_setg(errp,
                   "Device name '%s' conflicts with an existing node name",
                   name);
        return false;
    }

    blk->name = g_strdup(name);
    QTAILQ_INSERT_TAIL(&monitor_block_backends, blk, monitor_link);
    return true;
}

/*
 * Remove a BlockBackend from the list of backends referenced by the monitor.
 * Strictly for use by blockdev.c.
 */
void monitor_remove_blk(BlockBackend *blk)
{
    if (!blk->name) {
        return;
    }

    QTAILQ_REMOVE(&monitor_block_backends, blk, monitor_link);
    g_free(blk->name);
    blk->name = NULL;
}

/*
 * Return @blk's name, a non-null string.
 * Returns an empty string iff @blk is not referenced by the monitor.
 */
const char *blk_name(const BlockBackend *blk)
{
    return blk->name ?: "";
}

/*
 * Return the BlockBackend with name @name if it exists, else null.
 * @name must not be null.
 */
BlockBackend *blk_by_name(const char *name)
{
    BlockBackend *blk = NULL;

    assert(name);
    while ((blk = blk_next(blk)) != NULL) {
        if (!strcmp(name, blk->name)) {
            return blk;
        }
    }
    return NULL;
}

/*
 * Return the BlockDriverState attached to @blk if any, else null.
 */
BlockDriverState *blk_bs(BlockBackend *blk)
{
    return blk->root ? blk->root->bs : NULL;
}

static BlockBackend *bdrv_first_blk(BlockDriverState *bs)
{
    BdrvChild *child;
    QLIST_FOREACH(child, &bs->parents, next_parent) {
        if (child->role == &child_root) {
            return child->opaque;
        }
    }

    return NULL;
}

/*
 * Returns true if @bs has an associated BlockBackend.
 */
bool bdrv_has_blk(BlockDriverState *bs)
{
    return bdrv_first_blk(bs) != NULL;
}

/*
 * Returns true if @bs has only BlockBackends as parents.
 */
bool bdrv_is_root_node(BlockDriverState *bs)
{
    BdrvChild *c;

    QLIST_FOREACH(c, &bs->parents, next_parent) {
        if (c->role != &child_root) {
            return false;
        }
    }

    return true;
}

/*
 * Return @blk's DriveInfo if any, else null.
 */
DriveInfo *blk_legacy_dinfo(BlockBackend *blk)
{
    return blk->legacy_dinfo;
}

/*
 * Set @blk's DriveInfo to @dinfo, and return it.
 * @blk must not have a DriveInfo set already.
 * No other BlockBackend may have the same DriveInfo set.
 */
DriveInfo *blk_set_legacy_dinfo(BlockBackend *blk, DriveInfo *dinfo)
{
    assert(!blk->legacy_dinfo);
    return blk->legacy_dinfo = dinfo;
}

/*
 * Return the BlockBackend with DriveInfo @dinfo.
 * It must exist.
 */
BlockBackend *blk_by_legacy_dinfo(DriveInfo *dinfo)
{
    BlockBackend *blk = NULL;

    while ((blk = blk_next(blk)) != NULL) {
        if (blk->legacy_dinfo == dinfo) {
            return blk;
        }
    }
    abort();
}

/*
 * Returns a pointer to the publicly accessible fields of @blk.
 */
BlockBackendPublic *blk_get_public(BlockBackend *blk)
{
    return &blk->public;
}

/*
 * Returns a BlockBackend given the associated @public fields.
 */
BlockBackend *blk_by_public(BlockBackendPublic *public)
{
    return container_of(public, BlockBackend, public);
}

/*
 * Disassociates the currently associated BlockDriverState from @blk.
 */
void blk_remove_bs(BlockBackend *blk)
{
    ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
    BlockDriverState *bs;

    notifier_list_notify(&blk->remove_bs_notifiers, blk);
    if (tgm->throttle_state) {
        bs = blk_bs(blk);
        bdrv_drained_begin(bs);
        throttle_group_detach_aio_context(tgm);
        throttle_group_attach_aio_context(tgm, qemu_get_aio_context());
        bdrv_drained_end(bs);
    }

    blk_update_root_state(blk);

    /* bdrv_root_unref_child() will cause blk->root to become stale and may
     * switch to a completion coroutine later on. Let's drain all I/O here
     * to avoid that and a potential QEMU crash.
     */
    blk_drain(blk);
    bdrv_root_unref_child(blk->root);
    blk->root = NULL;
}

/*
 * Associates a new BlockDriverState with @blk.
 */
int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
{
    ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
    blk->root = bdrv_root_attach_child(bs, "root", &child_root,
                                       blk->perm, blk->shared_perm, blk, errp);
    if (blk->root == NULL) {
        return -EPERM;
    }
    bdrv_ref(bs);

    notifier_list_notify(&blk->insert_bs_notifiers, blk);
    if (tgm->throttle_state) {
        throttle_group_detach_aio_context(tgm);
        throttle_group_attach_aio_context(tgm, bdrv_get_aio_context(bs));
    }

    return 0;
}

/*
 * Sets the permission bitmasks that the user of the BlockBackend needs.
 */
int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
                 Error **errp)
{
    int ret;

    if (blk->root && !blk->disable_perm) {
        ret = bdrv_child_try_set_perm(blk->root, perm, shared_perm, errp);
        if (ret < 0) {
            return ret;
        }
    }

    blk->perm = perm;
    blk->shared_perm = shared_perm;

    return 0;
}

void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm)
{
    *perm = blk->perm;
    *shared_perm = blk->shared_perm;
}

/*
 * Attach device model @dev to @blk.
 * Return 0 on success, -EBUSY when a device model is attached already.
 */
int blk_attach_dev(BlockBackend *blk, DeviceState *dev)
{
    if (blk->dev) {
        return -EBUSY;
    }

    /* While migration is still incoming, we don't need to apply the
     * permissions of guest device BlockBackends. We might still have a block
     * job or NBD server writing to the image for storage migration. */
    if (runstate_check(RUN_STATE_INMIGRATE)) {
        blk->disable_perm = true;
    }

    blk_ref(blk);
    blk->dev = dev;
    blk_iostatus_reset(blk);

    return 0;
}

/*
 * Detach device model @dev from @blk.
 * @dev must be currently attached to @blk.
 */
void blk_detach_dev(BlockBackend *blk, DeviceState *dev)
{
    assert(blk->dev == dev);
    blk->dev = NULL;
    blk->dev_ops = NULL;
    blk->dev_opaque = NULL;
    blk->guest_block_size = 512;
    blk_set_perm(blk, 0, BLK_PERM_ALL, &error_abort);
    blk_unref(blk);
}

/*
 * Return the device model attached to @blk if any, else null.
 */
DeviceState *blk_get_attached_dev(BlockBackend *blk)
{
    return blk->dev;
}

/* Return the qdev ID, or if no ID is assigned the QOM path, of the block
 * device attached to the BlockBackend. */
char *blk_get_attached_dev_id(BlockBackend *blk)
{
    DeviceState *dev = blk->dev;

    if (!dev) {
        return g_strdup("");
    } else if (dev->id) {
        return g_strdup(dev->id);
    }

    return object_get_canonical_path(OBJECT(dev)) ?: g_strdup("");
}

/*
 * Return the BlockBackend which has the device model @dev attached if it
 * exists, else null.
 *
 * @dev must not be null.
 */
BlockBackend *blk_by_dev(void *dev)
{
    BlockBackend *blk = NULL;

    assert(dev != NULL);
    while ((blk = blk_all_next(blk)) != NULL) {
        if (blk->dev == dev) {
            return blk;
        }
    }
    return NULL;
}

/*
 * Set @blk's device model callbacks to @ops.
 * @opaque is the opaque argument to pass to the callbacks.
 * This is for use by device models.
 */
void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops,
                     void *opaque)
{
    blk->dev_ops = ops;
    blk->dev_opaque = opaque;

    /* Are we currently quiesced? Should we enforce this right now? */
    if (blk->quiesce_counter && ops->drained_begin) {
        ops->drained_begin(opaque);
    }
}

/*
 * Notify @blk's attached device model of media change.
 *
 * If @load is true, notify of media load. This action can fail, meaning that
 * the medium cannot be loaded. @errp is set then.
 *
 * If @load is false, notify of media eject. This can never fail.
 *
 * Also send DEVICE_TRAY_MOVED events as appropriate.
 */
void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp)
{
    if (blk->dev_ops && blk->dev_ops->change_media_cb) {
        bool tray_was_open, tray_is_open;
        Error *local_err = NULL;

        tray_was_open = blk_dev_is_tray_open(blk);
        blk->dev_ops->change_media_cb(blk->dev_opaque, load, &local_err);
        if (local_err) {
            assert(load == true);
            error_propagate(errp, local_err);
            return;
        }
        tray_is_open = blk_dev_is_tray_open(blk);

        if (tray_was_open != tray_is_open) {
            char *id = blk_get_attached_dev_id(blk);
            qapi_event_send_device_tray_moved(blk_name(blk), id, tray_is_open);
            g_free(id);
        }
    }
}

static void blk_root_change_media(BdrvChild *child, bool load)
{
    blk_dev_change_media_cb(child->opaque, load, NULL);
}

/*
 * Does @blk's attached device model have removable media?
 * %true if no device model is attached.
 */
bool blk_dev_has_removable_media(BlockBackend *blk)
{
    return !blk->dev || (blk->dev_ops && blk->dev_ops->change_media_cb);
}

/*
 * Does @blk's attached device model have a tray?
 */
bool blk_dev_has_tray(BlockBackend *blk)
{
    return blk->dev_ops && blk->dev_ops->is_tray_open;
}

/*
 * Notify @blk's attached device model of a media eject request.
 * If @force is true, the medium is about to be yanked out forcefully.
 */
void blk_dev_eject_request(BlockBackend *blk, bool force)
{
    if (blk->dev_ops && blk->dev_ops->eject_request_cb) {
        blk->dev_ops->eject_request_cb(blk->dev_opaque, force);
    }
}

/*
 * Does @blk's attached device model have a tray, and is it open?
 */
bool blk_dev_is_tray_open(BlockBackend *blk)
{
    if (blk_dev_has_tray(blk)) {
        return blk->dev_ops->is_tray_open(blk->dev_opaque);
    }
    return false;
}

/*
 * Does @blk's attached device model have the medium locked?
 * %false if the device model has no such lock.
 */
bool blk_dev_is_medium_locked(BlockBackend *blk)
{
    if (blk->dev_ops && blk->dev_ops->is_medium_locked) {
        return blk->dev_ops->is_medium_locked(blk->dev_opaque);
    }
    return false;
}

/*
 * Notify @blk's attached device model of a backend size change.
 */
static void blk_root_resize(BdrvChild *child)
{
    BlockBackend *blk = child->opaque;

    if (blk->dev_ops && blk->dev_ops->resize_cb) {
        blk->dev_ops->resize_cb(blk->dev_opaque);
    }
}

void blk_iostatus_enable(BlockBackend *blk)
{
    blk->iostatus_enabled = true;
    blk->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
}

/* The I/O status is only enabled if the drive explicitly
 * enables it _and_ the VM is configured to stop on errors */
bool blk_iostatus_is_enabled(const BlockBackend *blk)
{
    return (blk->iostatus_enabled &&
           (blk->on_write_error == BLOCKDEV_ON_ERROR_ENOSPC ||
            blk->on_write_error == BLOCKDEV_ON_ERROR_STOP   ||
            blk->on_read_error == BLOCKDEV_ON_ERROR_STOP));
}

BlockDeviceIoStatus blk_iostatus(const BlockBackend *blk)
{
    return blk->iostatus;
}

void blk_iostatus_disable(BlockBackend *blk)
{
    blk->iostatus_enabled = false;
}

void blk_iostatus_reset(BlockBackend *blk)
{
    if (blk_iostatus_is_enabled(blk)) {
        BlockDriverState *bs = blk_bs(blk);
        blk->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
        if (bs && bs->job) {
            block_job_iostatus_reset(bs->job);
        }
    }
}

void blk_iostatus_set_err(BlockBackend *blk, int error)
{
    assert(blk_iostatus_is_enabled(blk));
    if (blk->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
        blk->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
                                          BLOCK_DEVICE_IO_STATUS_FAILED;
    }
}

void blk_set_allow_write_beyond_eof(BlockBackend *blk, bool allow)
{
    blk->allow_write_beyond_eof = allow;
}

static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
                                  size_t size)
{
    int64_t len;

    if (size > INT_MAX) {
        return -EIO;
    }

    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

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

    if (!blk->allow_write_beyond_eof) {
        len = blk_getlength(blk);
        if (len < 0) {
            return len;
        }

        if (offset > len || len - offset < size) {
            return -EIO;
        }
    }

    return 0;
}

int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
                               unsigned int bytes, QEMUIOVector *qiov,
                               BdrvRequestFlags flags)
{
    int ret;
    BlockDriverState *bs = blk_bs(blk);

    trace_blk_co_preadv(blk, bs, offset, bytes, flags);

    ret = blk_check_byte_request(blk, offset, bytes);
    if (ret < 0) {
        return ret;
    }

    bdrv_inc_in_flight(bs);

    /* throttling disk I/O */
    if (blk->public.throttle_group_member.throttle_state) {
        throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
                bytes, false);
    }

    ret = bdrv_co_preadv(blk->root, offset, bytes, qiov, flags);
    bdrv_dec_in_flight(bs);
    return ret;
}

int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
                                unsigned int bytes, QEMUIOVector *qiov,
                                BdrvRequestFlags flags)
{
    int ret;
    BlockDriverState *bs = blk_bs(blk);

    trace_blk_co_pwritev(blk, bs, offset, bytes, flags);

    ret = blk_check_byte_request(blk, offset, bytes);
    if (ret < 0) {
        return ret;
    }

    bdrv_inc_in_flight(bs);
    /* throttling disk I/O */
    if (blk->public.throttle_group_member.throttle_state) {
        throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
                bytes, true);
    }

    if (!blk->enable_write_cache) {
        flags |= BDRV_REQ_FUA;
    }

    ret = bdrv_co_pwritev(blk->root, offset, bytes, qiov, flags);
    bdrv_dec_in_flight(bs);
    return ret;
}

typedef struct BlkRwCo {
    BlockBackend *blk;
    int64_t offset;
    void *iobuf;
    int ret;
    BdrvRequestFlags flags;
} BlkRwCo;

static void blk_read_entry(void *opaque)
{
    BlkRwCo *rwco = opaque;
    QEMUIOVector *qiov = rwco->iobuf;

    rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, qiov->size,
                              qiov, rwco->flags);
    aio_wait_kick();
}

static void blk_write_entry(void *opaque)
{
    BlkRwCo *rwco = opaque;
    QEMUIOVector *qiov = rwco->iobuf;

    rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, qiov->size,
                               qiov, rwco->flags);
    aio_wait_kick();
}

static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
                   int64_t bytes, CoroutineEntry co_entry,
                   BdrvRequestFlags flags)
{
    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
    BlkRwCo rwco = {
        .blk    = blk,
        .offset = offset,
        .iobuf  = &qiov,
        .flags  = flags,
        .ret    = NOT_DONE,
    };

    if (qemu_in_coroutine()) {
        /* Fast-path if already in coroutine context */
        co_entry(&rwco);
    } else {
        Coroutine *co = qemu_coroutine_create(co_entry, &rwco);
        bdrv_coroutine_enter(blk_bs(blk), co);
        BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE);
    }

    return rwco.ret;
}

int blk_pread_unthrottled(BlockBackend *blk, int64_t offset, uint8_t *buf,
                          int count)
{
    int ret;

    ret = blk_check_byte_request(blk, offset, count);
    if (ret < 0) {
        return ret;
    }

    blk_root_drained_begin(blk->root);
    ret = blk_pread(blk, offset, buf, count);
    blk_root_drained_end(blk->root);
    return ret;
}

int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
                      int bytes, BdrvRequestFlags flags)
{
    return blk_prw(blk, offset, NULL, bytes, blk_write_entry,
                   flags | BDRV_REQ_ZERO_WRITE);
}

int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags)
{
    return bdrv_make_zero(blk->root, flags);
}

void blk_inc_in_flight(BlockBackend *blk)
{
    atomic_inc(&blk->in_flight);
}

void blk_dec_in_flight(BlockBackend *blk)
{
    atomic_dec(&blk->in_flight);
    aio_wait_kick();
}

static void error_callback_bh(void *opaque)
{
    struct BlockBackendAIOCB *acb = opaque;

    blk_dec_in_flight(acb->blk);
    acb->common.cb(acb->common.opaque, acb->ret);
    qemu_aio_unref(acb);
}

BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
                                  BlockCompletionFunc *cb,
                                  void *opaque, int ret)
{
    struct BlockBackendAIOCB *acb;

    blk_inc_in_flight(blk);
    acb = blk_aio_get(&block_backend_aiocb_info, blk, cb, opaque);
    acb->blk = blk;
    acb->ret = ret;

    aio_bh_schedule_oneshot(blk_get_aio_context(blk), error_callback_bh, acb);
    return &acb->common;
}

typedef struct BlkAioEmAIOCB {
    BlockAIOCB common;
    BlkRwCo rwco;
    int bytes;
    bool has_returned;
} BlkAioEmAIOCB;

static const AIOCBInfo blk_aio_em_aiocb_info = {
    .aiocb_size         = sizeof(BlkAioEmAIOCB),
};

static void blk_aio_complete(BlkAioEmAIOCB *acb)
{
    if (acb->has_returned) {
        acb->common.cb(acb->common.opaque, acb->rwco.ret);
        blk_dec_in_flight(acb->rwco.blk);
        qemu_aio_unref(acb);
    }
}

static void blk_aio_complete_bh(void *opaque)
{
    BlkAioEmAIOCB *acb = opaque;
    assert(acb->has_returned);
    blk_aio_complete(acb);
}

static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
                                void *iobuf, CoroutineEntry co_entry,
                                BdrvRequestFlags flags,
                                BlockCompletionFunc *cb, void *opaque)
{
    BlkAioEmAIOCB *acb;
    Coroutine *co;

    blk_inc_in_flight(blk);
    acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque);
    acb->rwco = (BlkRwCo) {
        .blk    = blk,
        .offset = offset,
        .iobuf  = iobuf,
        .flags  = flags,
        .ret    = NOT_DONE,
    };
    acb->bytes = bytes;
    acb->has_returned = false;

    co = qemu_coroutine_create(co_entry, acb);
    bdrv_coroutine_enter(blk_bs(blk), co);

    acb->has_returned = true;
    if (acb->rwco.ret != NOT_DONE) {
        aio_bh_schedule_oneshot(blk_get_aio_context(blk),
                                blk_aio_complete_bh, acb);
    }

    return &acb->common;
}

static void blk_aio_read_entry(void *opaque)
{
    BlkAioEmAIOCB *acb = opaque;
    BlkRwCo *rwco = &acb->rwco;
    QEMUIOVector *qiov = rwco->iobuf;

    assert(qiov->size == acb->bytes);
    rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, acb->bytes,
                              qiov, rwco->flags);
    blk_aio_complete(acb);
}

static void blk_aio_write_entry(void *opaque)
{
    BlkAioEmAIOCB *acb = opaque;
    BlkRwCo *rwco = &acb->rwco;
    QEMUIOVector *qiov = rwco->iobuf;

    assert(!qiov || qiov->size == acb->bytes);
    rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, acb->bytes,
                               qiov, rwco->flags);
    blk_aio_complete(acb);
}

BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset,
                                  int count, BdrvRequestFlags flags,
                                  BlockCompletionFunc *cb, void *opaque)
{
    return blk_aio_prwv(blk, offset, count, NULL, blk_aio_write_entry,
                        flags | BDRV_REQ_ZERO_WRITE, cb, opaque);
}

int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int count)
{
    int ret = blk_prw(blk, offset, buf, count, blk_read_entry, 0);
    if (ret < 0) {
        return ret;
    }
    return count;
}

int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int count,
               BdrvRequestFlags flags)
{
    int ret = blk_prw(blk, offset, (void *) buf, count, blk_write_entry,
                      flags);
    if (ret < 0) {
        return ret;
    }
    return count;
}

int64_t blk_getlength(BlockBackend *blk)
{
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

    return bdrv_getlength(blk_bs(blk));
}

void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr)
{
    if (!blk_bs(blk)) {
        *nb_sectors_ptr = 0;
    } else {
        bdrv_get_geometry(blk_bs(blk), nb_sectors_ptr);
    }
}

int64_t blk_nb_sectors(BlockBackend *blk)
{
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

    return bdrv_nb_sectors(blk_bs(blk));
}

BlockAIOCB *blk_aio_preadv(BlockBackend *blk, int64_t offset,
                           QEMUIOVector *qiov, BdrvRequestFlags flags,
                           BlockCompletionFunc *cb, void *opaque)
{
    return blk_aio_prwv(blk, offset, qiov->size, qiov,
                        blk_aio_read_entry, flags, cb, opaque);
}

BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
                            QEMUIOVector *qiov, BdrvRequestFlags flags,
                            BlockCompletionFunc *cb, void *opaque)
{
    return blk_aio_prwv(blk, offset, qiov->size, qiov,
                        blk_aio_write_entry, flags, cb, opaque);
}

static void blk_aio_flush_entry(void *opaque)
{
    BlkAioEmAIOCB *acb = opaque;
    BlkRwCo *rwco = &acb->rwco;

    rwco->ret = blk_co_flush(rwco->blk);
    blk_aio_complete(acb);
}

BlockAIOCB *blk_aio_flush(BlockBackend *blk,
                          BlockCompletionFunc *cb, void *opaque)
{
    return blk_aio_prwv(blk, 0, 0, NULL, blk_aio_flush_entry, 0, cb, opaque);
}

static void blk_aio_pdiscard_entry(void *opaque)
{
    BlkAioEmAIOCB *acb = opaque;
    BlkRwCo *rwco = &acb->rwco;

    rwco->ret = blk_co_pdiscard(rwco->blk, rwco->offset, acb->bytes);
    blk_aio_complete(acb);
}

BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk,
                             int64_t offset, int bytes,
                             BlockCompletionFunc *cb, void *opaque)
{
    return blk_aio_prwv(blk, offset, bytes, NULL, blk_aio_pdiscard_entry, 0,
                        cb, opaque);
}

void blk_aio_cancel(BlockAIOCB *acb)
{
    bdrv_aio_cancel(acb);
}

void blk_aio_cancel_async(BlockAIOCB *acb)
{
    bdrv_aio_cancel_async(acb);
}

int blk_co_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
{
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

    return bdrv_co_ioctl(blk_bs(blk), req, buf);
}

static void blk_ioctl_entry(void *opaque)
{
    BlkRwCo *rwco = opaque;
    QEMUIOVector *qiov = rwco->iobuf;

    rwco->ret = blk_co_ioctl(rwco->blk, rwco->offset,
                             qiov->iov[0].iov_base);
    aio_wait_kick();
}

int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
{
    return blk_prw(blk, req, buf, 0, blk_ioctl_entry, 0);
}

static void blk_aio_ioctl_entry(void *opaque)
{
    BlkAioEmAIOCB *acb = opaque;
    BlkRwCo *rwco = &acb->rwco;

    rwco->ret = blk_co_ioctl(rwco->blk, rwco->offset, rwco->iobuf);

    blk_aio_complete(acb);
}

BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
                          BlockCompletionFunc *cb, void *opaque)
{
    return blk_aio_prwv(blk, req, 0, buf, blk_aio_ioctl_entry, 0, cb, opaque);
}

int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
{
    int ret = blk_check_byte_request(blk, offset, bytes);
    if (ret < 0) {
        return ret;
    }

    return bdrv_co_pdiscard(blk->root, offset, bytes);
}

int blk_co_flush(BlockBackend *blk)
{
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

    return bdrv_co_flush(blk_bs(blk));
}

static void blk_flush_entry(void *opaque)
{
    BlkRwCo *rwco = opaque;
    rwco->ret = blk_co_flush(rwco->blk);
    aio_wait_kick();
}

int blk_flush(BlockBackend *blk)
{
    return blk_prw(blk, 0, NULL, 0, blk_flush_entry, 0);
}

void blk_drain(BlockBackend *blk)
{
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        bdrv_drained_begin(bs);
    }

    /* We may have -ENOMEDIUM completions in flight */
    AIO_WAIT_WHILE(blk_get_aio_context(blk),
                   atomic_mb_read(&blk->in_flight) > 0);

    if (bs) {
        bdrv_drained_end(bs);
    }
}

void blk_drain_all(void)
{
    BlockBackend *blk = NULL;

    bdrv_drain_all_begin();

    while ((blk = blk_all_next(blk)) != NULL) {
        AioContext *ctx = blk_get_aio_context(blk);

        aio_context_acquire(ctx);

        /* We may have -ENOMEDIUM completions in flight */
        AIO_WAIT_WHILE(ctx, atomic_mb_read(&blk->in_flight) > 0);

        aio_context_release(ctx);
    }

    bdrv_drain_all_end();
}

void blk_set_on_error(BlockBackend *blk, BlockdevOnError on_read_error,
                      BlockdevOnError on_write_error)
{
    blk->on_read_error = on_read_error;
    blk->on_write_error = on_write_error;
}

BlockdevOnError blk_get_on_error(BlockBackend *blk, bool is_read)
{
    return is_read ? blk->on_read_error : blk->on_write_error;
}

BlockErrorAction blk_get_error_action(BlockBackend *blk, bool is_read,
                                      int error)
{
    BlockdevOnError on_err = blk_get_on_error(blk, is_read);

    switch (on_err) {
    case BLOCKDEV_ON_ERROR_ENOSPC:
        return (error == ENOSPC) ?
               BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
    case BLOCKDEV_ON_ERROR_STOP:
        return BLOCK_ERROR_ACTION_STOP;
    case BLOCKDEV_ON_ERROR_REPORT:
        return BLOCK_ERROR_ACTION_REPORT;
    case BLOCKDEV_ON_ERROR_IGNORE:
        return BLOCK_ERROR_ACTION_IGNORE;
    case BLOCKDEV_ON_ERROR_AUTO:
    default:
        abort();
    }
}

static void send_qmp_error_event(BlockBackend *blk,
                                 BlockErrorAction action,
                                 bool is_read, int error)
{
    IoOperationType optype;
    BlockDriverState *bs = blk_bs(blk);

    optype = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
    qapi_event_send_block_io_error(blk_name(blk), !!bs,
                                   bs ? bdrv_get_node_name(bs) : NULL, optype,
                                   action, blk_iostatus_is_enabled(blk),
                                   error == ENOSPC, strerror(error));
}

/* This is done by device models because, while the block layer knows
 * about the error, it does not know whether an operation comes from
 * the device or the block layer (from a job, for example).
 */
void blk_error_action(BlockBackend *blk, BlockErrorAction action,
                      bool is_read, int error)
{
    assert(error >= 0);

    if (action == BLOCK_ERROR_ACTION_STOP) {
        /* First set the iostatus, so that "info block" returns an iostatus
         * that matches the events raised so far (an additional error iostatus
         * is fine, but not a lost one).
         */
        blk_iostatus_set_err(blk, error);

        /* Then raise the request to stop the VM and the event.
         * qemu_system_vmstop_request_prepare has two effects.  First,
         * it ensures that the STOP event always comes after the
         * BLOCK_IO_ERROR event.  Second, it ensures that even if management
         * can observe the STOP event and do a "cont" before the STOP
         * event is issued, the VM will not stop.  In this case, vm_start()
         * also ensures that the STOP/RESUME pair of events is emitted.
         */
        qemu_system_vmstop_request_prepare();
        send_qmp_error_event(blk, action, is_read, error);
        qemu_system_vmstop_request(RUN_STATE_IO_ERROR);
    } else {
        send_qmp_error_event(blk, action, is_read, error);
    }
}

bool blk_is_read_only(BlockBackend *blk)
{
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        return bdrv_is_read_only(bs);
    } else {
        return blk->root_state.read_only;
    }
}

bool blk_is_sg(BlockBackend *blk)
{
    BlockDriverState *bs = blk_bs(blk);

    if (!bs) {
        return false;
    }

    return bdrv_is_sg(bs);
}

bool blk_enable_write_cache(BlockBackend *blk)
{
    return blk->enable_write_cache;
}

void blk_set_enable_write_cache(BlockBackend *blk, bool wce)
{
    blk->enable_write_cache = wce;
}

void blk_invalidate_cache(BlockBackend *blk, Error **errp)
{
    BlockDriverState *bs = blk_bs(blk);

    if (!bs) {
        error_setg(errp, "Device '%s' has no medium", blk->name);
        return;
    }

    bdrv_invalidate_cache(bs, errp);
}

bool blk_is_inserted(BlockBackend *blk)
{
    BlockDriverState *bs = blk_bs(blk);

    return bs && bdrv_is_inserted(bs);
}

bool blk_is_available(BlockBackend *blk)
{
    return blk_is_inserted(blk) && !blk_dev_is_tray_open(blk);
}

void blk_lock_medium(BlockBackend *blk, bool locked)
{
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        bdrv_lock_medium(bs, locked);
    }
}

void blk_eject(BlockBackend *blk, bool eject_flag)
{
    BlockDriverState *bs = blk_bs(blk);
    char *id;

    if (bs) {
        bdrv_eject(bs, eject_flag);
    }

    /* Whether or not we ejected on the backend,
     * the frontend experienced a tray event. */
    id = blk_get_attached_dev_id(blk);
    qapi_event_send_device_tray_moved(blk_name(blk), id,
                                      eject_flag);
    g_free(id);
}

int blk_get_flags(BlockBackend *blk)
{
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        return bdrv_get_flags(bs);
    } else {
        return blk->root_state.open_flags;
    }
}

/* Returns the maximum transfer length, in bytes; guaranteed nonzero */
uint32_t blk_get_max_transfer(BlockBackend *blk)
{
    BlockDriverState *bs = blk_bs(blk);
    uint32_t max = 0;

    if (bs) {
        max = bs->bl.max_transfer;
    }
    return MIN_NON_ZERO(max, INT_MAX);
}

int blk_get_max_iov(BlockBackend *blk)
{
    return blk->root->bs->bl.max_iov;
}

void blk_set_guest_block_size(BlockBackend *blk, int align)
{
    blk->guest_block_size = align;
}

void *blk_try_blockalign(BlockBackend *blk, size_t size)
{
    return qemu_try_blockalign(blk ? blk_bs(blk) : NULL, size);
}

void *blk_blockalign(BlockBackend *blk, size_t size)
{
    return qemu_blockalign(blk ? blk_bs(blk) : NULL, size);
}

bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp)
{
    BlockDriverState *bs = blk_bs(blk);

    if (!bs) {
        return false;
    }

    return bdrv_op_is_blocked(bs, op, errp);
}

void blk_op_unblock(BlockBackend *blk, BlockOpType op, Error *reason)
{
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        bdrv_op_unblock(bs, op, reason);
    }
}

void blk_op_block_all(BlockBackend *blk, Error *reason)
{
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        bdrv_op_block_all(bs, reason);
    }
}

void blk_op_unblock_all(BlockBackend *blk, Error *reason)
{
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        bdrv_op_unblock_all(bs, reason);
    }
}

AioContext *blk_get_aio_context(BlockBackend *blk)
{
    return bdrv_get_aio_context(blk_bs(blk));
}

static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb)
{
    BlockBackendAIOCB *blk_acb = DO_UPCAST(BlockBackendAIOCB, common, acb);
    return blk_get_aio_context(blk_acb->blk);
}

void blk_set_aio_context(BlockBackend *blk, AioContext *new_context)
{
    BlockDriverState *bs = blk_bs(blk);
    ThrottleGroupMember *tgm = &blk->public.throttle_group_member;

    if (bs) {
        if (tgm->throttle_state) {
            bdrv_drained_begin(bs);
            throttle_group_detach_aio_context(tgm);
            throttle_group_attach_aio_context(tgm, new_context);
            bdrv_drained_end(bs);
        }
        bdrv_set_aio_context(bs, new_context);
    }
}

void blk_add_aio_context_notifier(BlockBackend *blk,
        void (*attached_aio_context)(AioContext *new_context, void *opaque),
        void (*detach_aio_context)(void *opaque), void *opaque)
{
    BlockBackendAioNotifier *notifier;
    BlockDriverState *bs = blk_bs(blk);

    notifier = g_new(BlockBackendAioNotifier, 1);
    notifier->attached_aio_context = attached_aio_context;
    notifier->detach_aio_context = detach_aio_context;
    notifier->opaque = opaque;
    QLIST_INSERT_HEAD(&blk->aio_notifiers, notifier, list);

    if (bs) {
        bdrv_add_aio_context_notifier(bs, attached_aio_context,
                                      detach_aio_context, opaque);
    }
}

void blk_remove_aio_context_notifier(BlockBackend *blk,
                                     void (*attached_aio_context)(AioContext *,
                                                                  void *),
                                     void (*detach_aio_context)(void *),
                                     void *opaque)
{
    BlockBackendAioNotifier *notifier;
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        bdrv_remove_aio_context_notifier(bs, attached_aio_context,
                                         detach_aio_context, opaque);
    }

    QLIST_FOREACH(notifier, &blk->aio_notifiers, list) {
        if (notifier->attached_aio_context == attached_aio_context &&
            notifier->detach_aio_context == detach_aio_context &&
            notifier->opaque == opaque) {
            QLIST_REMOVE(notifier, list);
            g_free(notifier);
            return;
        }
    }

    abort();
}

void blk_add_remove_bs_notifier(BlockBackend *blk, Notifier *notify)
{
    notifier_list_add(&blk->remove_bs_notifiers, notify);
}

void blk_add_insert_bs_notifier(BlockBackend *blk, Notifier *notify)
{
    notifier_list_add(&blk->insert_bs_notifiers, notify);
}

void blk_io_plug(BlockBackend *blk)
{
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        bdrv_io_plug(bs);
    }
}

void blk_io_unplug(BlockBackend *blk)
{
    BlockDriverState *bs = blk_bs(blk);

    if (bs) {
        bdrv_io_unplug(bs);
    }
}

BlockAcctStats *blk_get_stats(BlockBackend *blk)
{
    return &blk->stats;
}

void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk,
                  BlockCompletionFunc *cb, void *opaque)
{
    return qemu_aio_get(aiocb_info, blk_bs(blk), cb, opaque);
}

int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset,
                                      int bytes, BdrvRequestFlags flags)
{
    return blk_co_pwritev(blk, offset, bytes, NULL,
                          flags | BDRV_REQ_ZERO_WRITE);
}

int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf,
                          int count)
{
    return blk_prw(blk, offset, (void *) buf, count, blk_write_entry,
                   BDRV_REQ_WRITE_COMPRESSED);
}

int blk_truncate(BlockBackend *blk, int64_t offset, PreallocMode prealloc,
                 Error **errp)
{
    if (!blk_is_available(blk)) {
        error_setg(errp, "No medium inserted");
        return -ENOMEDIUM;
    }

    return bdrv_truncate(blk->root, offset, prealloc, errp);
}

static void blk_pdiscard_entry(void *opaque)
{
    BlkRwCo *rwco = opaque;
    QEMUIOVector *qiov = rwco->iobuf;

    rwco->ret = blk_co_pdiscard(rwco->blk, rwco->offset, qiov->size);
    aio_wait_kick();
}

int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
{
    return blk_prw(blk, offset, NULL, bytes, blk_pdiscard_entry, 0);
}

int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
                     int64_t pos, int size)
{
    int ret;

    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

    ret = bdrv_save_vmstate(blk_bs(blk), buf, pos, size);
    if (ret < 0) {
        return ret;
    }

    if (ret == size && !blk->enable_write_cache) {
        ret = bdrv_flush(blk_bs(blk));
    }

    return ret < 0 ? ret : size;
}

int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size)
{
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

    return bdrv_load_vmstate(blk_bs(blk), buf, pos, size);
}

int blk_probe_blocksizes(BlockBackend *blk, BlockSizes *bsz)
{
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

    return bdrv_probe_blocksizes(blk_bs(blk), bsz);
}

int blk_probe_geometry(BlockBackend *blk, HDGeometry *geo)
{
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }

    return bdrv_probe_geometry(blk_bs(blk), geo);
}

/*
 * Updates the BlockBackendRootState object with data from the currently
 * attached BlockDriverState.
 */
void blk_update_root_state(BlockBackend *blk)
{
    assert(blk->root);

    blk->root_state.open_flags    = blk->root->bs->open_flags;
    blk->root_state.read_only     = blk->root->bs->read_only;
    blk->root_state.detect_zeroes = blk->root->bs->detect_zeroes;
}

/*
 * Returns the detect-zeroes setting to be used for bdrv_open() of a
 * BlockDriverState which is supposed to inherit the root state.
 */
bool blk_get_detect_zeroes_from_root_state(BlockBackend *blk)
{
    return blk->root_state.detect_zeroes;
}

/*
 * Returns the flags to be used for bdrv_open() of a BlockDriverState which is
 * supposed to inherit the root state.
 */
int blk_get_open_flags_from_root_state(BlockBackend *blk)
{
    int bs_flags;

    bs_flags = blk->root_state.read_only ? 0 : BDRV_O_RDWR;
    bs_flags |= blk->root_state.open_flags & ~BDRV_O_RDWR;

    return bs_flags;
}

BlockBackendRootState *blk_get_root_state(BlockBackend *blk)
{
    return &blk->root_state;
}

int blk_commit_all(void)
{
    BlockBackend *blk = NULL;

    while ((blk = blk_all_next(blk)) != NULL) {
        AioContext *aio_context = blk_get_aio_context(blk);

        aio_context_acquire(aio_context);
        if (blk_is_inserted(blk) && blk->root->bs->backing) {
            int ret = bdrv_commit(blk->root->bs);
            if (ret < 0) {
                aio_context_release(aio_context);
                return ret;
            }
        }
        aio_context_release(aio_context);
    }
    return 0;
}


/* throttling disk I/O limits */
void blk_set_io_limits(BlockBackend *blk, ThrottleConfig *cfg)
{
    throttle_group_config(&blk->public.throttle_group_member, cfg);
}

void blk_io_limits_disable(BlockBackend *blk)
{
    BlockDriverState *bs = blk_bs(blk);
    ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
    assert(tgm->throttle_state);
    if (bs) {
        bdrv_drained_begin(bs);
    }
    throttle_group_unregister_tgm(tgm);
    if (bs) {
        bdrv_drained_end(bs);
    }
}

/* should be called before blk_set_io_limits if a limit is set */
void blk_io_limits_enable(BlockBackend *blk, const char *group)
{
    assert(!blk->public.throttle_group_member.throttle_state);
    throttle_group_register_tgm(&blk->public.throttle_group_member,
                                group, blk_get_aio_context(blk));
}

void blk_io_limits_update_group(BlockBackend *blk, const char *group)
{
    /* this BB is not part of any group */
    if (!blk->public.throttle_group_member.throttle_state) {
        return;
    }

    /* this BB is a part of the same group than the one we want */
    if (!g_strcmp0(throttle_group_get_name(&blk->public.throttle_group_member),
                group)) {
        return;
    }

    /* need to change the group this bs belong to */
    blk_io_limits_disable(blk);
    blk_io_limits_enable(blk, group);
}

static void blk_root_drained_begin(BdrvChild *child)
{
    BlockBackend *blk = child->opaque;

    if (++blk->quiesce_counter == 1) {
        if (blk->dev_ops && blk->dev_ops->drained_begin) {
            blk->dev_ops->drained_begin(blk->dev_opaque);
        }
    }

    /* Note that blk->root may not be accessible here yet if we are just
     * attaching to a BlockDriverState that is drained. Use child instead. */

    if (atomic_fetch_inc(&blk->public.throttle_group_member.io_limits_disabled) == 0) {
        throttle_group_restart_tgm(&blk->public.throttle_group_member);
    }
}

static bool blk_root_drained_poll(BdrvChild *child)
{
    BlockBackend *blk = child->opaque;
    assert(blk->quiesce_counter);
    return !!blk->in_flight;
}

static void blk_root_drained_end(BdrvChild *child)
{
    BlockBackend *blk = child->opaque;
    assert(blk->quiesce_counter);

    assert(blk->public.throttle_group_member.io_limits_disabled);
    atomic_dec(&blk->public.throttle_group_member.io_limits_disabled);

    if (--blk->quiesce_counter == 0) {
        if (blk->dev_ops && blk->dev_ops->drained_end) {
            blk->dev_ops->drained_end(blk->dev_opaque);
        }
    }
}

void blk_register_buf(BlockBackend *blk, void *host, size_t size)
{
    bdrv_register_buf(blk_bs(blk), host, size);
}

void blk_unregister_buf(BlockBackend *blk, void *host)
{
    bdrv_unregister_buf(blk_bs(blk), host);
}

int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
                                   BlockBackend *blk_out, int64_t off_out,
                                   int bytes, BdrvRequestFlags read_flags,
                                   BdrvRequestFlags write_flags)
{
    int r;
    r = blk_check_byte_request(blk_in, off_in, bytes);
    if (r) {
        return r;
    }
    r = blk_check_byte_request(blk_out, off_out, bytes);
    if (r) {
        return r;
    }
    return bdrv_co_copy_range(blk_in->root, off_in,
                              blk_out->root, off_out,
                              bytes, read_flags, write_flags);
}

const BdrvChild *blk_root(BlockBackend *blk)
{
    return blk->root;
}