summaryrefslogtreecommitdiffstats
path: root/block/iscsi.c
blob: 7d4b3b56d5c1b640fc6dfac384c5ffe84230161b (plain) (blame)
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
/*
 * QEMU Block driver for iSCSI images
 *
 * Copyright (c) 2010-2011 Ronnie Sahlberg <ronniesahlberg@gmail.com>
 * Copyright (c) 2012-2017 Peter Lieven <pl@kamp.de>
 *
 * 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 <poll.h>
#include <math.h>
#include <arpa/inet.h>
#include "qemu-common.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qemu/bitops.h"
#include "qemu/bitmap.h"
#include "block/block_int.h"
#include "block/qdict.h"
#include "scsi/constants.h"
#include "qemu/iov.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "qemu/uuid.h"
#include "sysemu/replay.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-machine.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qstring.h"
#include "crypto/secret.h"
#include "scsi/utils.h"
#include "trace.h"

/* Conflict between scsi/utils.h and libiscsi! :( */
#define SCSI_XFER_NONE ISCSI_XFER_NONE
#include <iscsi/iscsi.h>
#define inline __attribute__((gnu_inline))  /* required for libiscsi v1.9.0 */
#include <iscsi/scsi-lowlevel.h>
#undef inline
#undef SCSI_XFER_NONE
QEMU_BUILD_BUG_ON((int)SCSI_XFER_NONE != (int)ISCSI_XFER_NONE);

#ifdef __linux__
#include <scsi/sg.h>
#endif

typedef struct IscsiLun {
    struct iscsi_context *iscsi;
    AioContext *aio_context;
    int lun;
    enum scsi_inquiry_peripheral_device_type type;
    int block_size;
    uint64_t num_blocks;
    int events;
    QEMUTimer *nop_timer;
    QEMUTimer *event_timer;
    QemuMutex mutex;
    struct scsi_inquiry_logical_block_provisioning lbp;
    struct scsi_inquiry_block_limits bl;
    struct scsi_inquiry_device_designator *dd;
    unsigned char *zeroblock;
    /* The allocmap tracks which clusters (pages) on the iSCSI target are
     * allocated and which are not. In case a target returns zeros for
     * unallocated pages (iscsilun->lprz) we can directly return zeros instead
     * of reading zeros over the wire if a read request falls within an
     * unallocated block. As there are 3 possible states we need 2 bitmaps to
     * track. allocmap_valid keeps track if QEMU's information about a page is
     * valid. allocmap tracks if a page is allocated or not. In case QEMU has no
     * valid information about a page the corresponding allocmap entry should be
     * switched to unallocated as well to force a new lookup of the allocation
     * status as lookups are generally skipped if a page is suspect to be
     * allocated. If a iSCSI target is opened with cache.direct = on the
     * allocmap_valid does not exist turning all cached information invalid so
     * that a fresh lookup is made for any page even if allocmap entry returns
     * it's unallocated. */
    unsigned long *allocmap;
    unsigned long *allocmap_valid;
    long allocmap_size;
    int cluster_size;
    bool use_16_for_rw;
    bool write_protected;
    bool lbpme;
    bool lbprz;
    bool dpofua;
    bool has_write_same;
    bool request_timed_out;
} IscsiLun;

typedef struct IscsiTask {
    int status;
    int complete;
    int retries;
    int do_retry;
    struct scsi_task *task;
    Coroutine *co;
    IscsiLun *iscsilun;
    QEMUTimer retry_timer;
    int err_code;
    char *err_str;
} IscsiTask;

typedef struct IscsiAIOCB {
    BlockAIOCB common;
    QEMUBH *bh;
    IscsiLun *iscsilun;
    struct scsi_task *task;
    int status;
    int64_t sector_num;
    int nb_sectors;
    int ret;
#ifdef __linux__
    sg_io_hdr_t *ioh;
#endif
    bool cancelled;
} IscsiAIOCB;

/* libiscsi uses time_t so its enough to process events every second */
#define EVENT_INTERVAL 1000
#define NOP_INTERVAL 5000
#define MAX_NOP_FAILURES 3
#define ISCSI_CMD_RETRIES ARRAY_SIZE(iscsi_retry_times)
static const unsigned iscsi_retry_times[] = {8, 32, 128, 512, 2048, 8192, 32768};

/* this threshold is a trade-off knob to choose between
 * the potential additional overhead of an extra GET_LBA_STATUS request
 * vs. unnecessarily reading a lot of zero sectors over the wire.
 * If a read request is greater or equal than ISCSI_CHECKALLOC_THRES
 * sectors we check the allocation status of the area covered by the
 * request first if the allocationmap indicates that the area might be
 * unallocated. */
#define ISCSI_CHECKALLOC_THRES 64

#ifdef __linux__

static void
iscsi_bh_cb(void *p)
{
    IscsiAIOCB *acb = p;

    qemu_bh_delete(acb->bh);

    acb->common.cb(acb->common.opaque, acb->status);

    if (acb->task != NULL) {
        scsi_free_scsi_task(acb->task);
        acb->task = NULL;
    }

    qemu_aio_unref(acb);
}

static void
iscsi_schedule_bh(IscsiAIOCB *acb)
{
    if (acb->bh) {
        return;
    }
    acb->bh = aio_bh_new(acb->iscsilun->aio_context, iscsi_bh_cb, acb);
    qemu_bh_schedule(acb->bh);
}

#endif

static void iscsi_co_generic_bh_cb(void *opaque)
{
    struct IscsiTask *iTask = opaque;

    iTask->complete = 1;
    aio_co_wake(iTask->co);
}

static void iscsi_retry_timer_expired(void *opaque)
{
    struct IscsiTask *iTask = opaque;
    iTask->complete = 1;
    if (iTask->co) {
        aio_co_wake(iTask->co);
    }
}

static inline unsigned exp_random(double mean)
{
    return -mean * log((double)rand() / RAND_MAX);
}

/* SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST was introduced in
 * libiscsi 1.10.0, together with other constants we need.  Use it as
 * a hint that we have to define them ourselves if needed, to keep the
 * minimum required libiscsi version at 1.9.0.  We use an ASCQ macro for
 * the test because SCSI_STATUS_* is an enum.
 *
 * To guard against future changes where SCSI_SENSE_ASCQ_* also becomes
 * an enum, check against the LIBISCSI_API_VERSION macro, which was
 * introduced in 1.11.0.  If it is present, there is no need to define
 * anything.
 */
#if !defined(SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST) && \
    !defined(LIBISCSI_API_VERSION)
#define SCSI_STATUS_TASK_SET_FULL                          0x28
#define SCSI_STATUS_TIMEOUT                                0x0f000002
#define SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST    0x2600
#define SCSI_SENSE_ASCQ_PARAMETER_LIST_LENGTH_ERROR        0x1a00
#endif

#ifndef LIBISCSI_API_VERSION
#define LIBISCSI_API_VERSION 20130701
#endif

static int iscsi_translate_sense(struct scsi_sense *sense)
{
    return scsi_sense_to_errno(sense->key,
                               (sense->ascq & 0xFF00) >> 8,
                               sense->ascq & 0xFF);
}

/* Called (via iscsi_service) with QemuMutex held.  */
static void
iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
                        void *command_data, void *opaque)
{
    struct IscsiTask *iTask = opaque;
    struct scsi_task *task = command_data;

    iTask->status = status;
    iTask->do_retry = 0;
    iTask->err_code = 0;
    iTask->task = task;

    if (status != SCSI_STATUS_GOOD) {
        iTask->err_code = -EIO;
        if (iTask->retries++ < ISCSI_CMD_RETRIES) {
            if (status == SCSI_STATUS_BUSY ||
                status == SCSI_STATUS_TIMEOUT ||
                status == SCSI_STATUS_TASK_SET_FULL) {
                unsigned retry_time =
                    exp_random(iscsi_retry_times[iTask->retries - 1]);
                if (status == SCSI_STATUS_TIMEOUT) {
                    /* make sure the request is rescheduled AFTER the
                     * reconnect is initiated */
                    retry_time = EVENT_INTERVAL * 2;
                    iTask->iscsilun->request_timed_out = true;
                }
                error_report("iSCSI Busy/TaskSetFull/TimeOut"
                             " (retry #%u in %u ms): %s",
                             iTask->retries, retry_time,
                             iscsi_get_error(iscsi));
                aio_timer_init(iTask->iscsilun->aio_context,
                               &iTask->retry_timer, QEMU_CLOCK_REALTIME,
                               SCALE_MS, iscsi_retry_timer_expired, iTask);
                timer_mod(&iTask->retry_timer,
                          qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + retry_time);
                iTask->do_retry = 1;
            } else if (status == SCSI_STATUS_CHECK_CONDITION) {
                int error = iscsi_translate_sense(&task->sense);
                if (error == EAGAIN) {
                    error_report("iSCSI CheckCondition: %s",
                                 iscsi_get_error(iscsi));
                    iTask->do_retry = 1;
                } else {
                    iTask->err_code = -error;
                    iTask->err_str = g_strdup(iscsi_get_error(iscsi));
                }
            }
        }
    }

    if (iTask->co) {
        replay_bh_schedule_oneshot_event(iTask->iscsilun->aio_context,
                                         iscsi_co_generic_bh_cb, iTask);
    } else {
        iTask->complete = 1;
    }
}

static void iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask)
{
    *iTask = (struct IscsiTask) {
        .co         = qemu_coroutine_self(),
        .iscsilun   = iscsilun,
    };
}

#ifdef __linux__

/* Called (via iscsi_service) with QemuMutex held. */
static void
iscsi_abort_task_cb(struct iscsi_context *iscsi, int status, void *command_data,
                    void *private_data)
{
    IscsiAIOCB *acb = private_data;

    /* If the command callback hasn't been called yet, drop the task */
    if (!acb->bh) {
        /* Call iscsi_aio_ioctl_cb() with SCSI_STATUS_CANCELLED */
        iscsi_scsi_cancel_task(iscsi, acb->task);
    }

    qemu_aio_unref(acb); /* acquired in iscsi_aio_cancel() */
}

static void
iscsi_aio_cancel(BlockAIOCB *blockacb)
{
    IscsiAIOCB *acb = (IscsiAIOCB *)blockacb;
    IscsiLun *iscsilun = acb->iscsilun;

    WITH_QEMU_LOCK_GUARD(&iscsilun->mutex) {

        /* If it was cancelled or completed already, our work is done here */
        if (acb->cancelled || acb->status != -EINPROGRESS) {
            return;
        }

        acb->cancelled = true;

        qemu_aio_ref(acb); /* released in iscsi_abort_task_cb() */

        /* send a task mgmt call to the target to cancel the task on the target */
        if (iscsi_task_mgmt_abort_task_async(iscsilun->iscsi, acb->task,
                                             iscsi_abort_task_cb, acb) < 0) {
            qemu_aio_unref(acb); /* since iscsi_abort_task_cb() won't be called */
        }
    }
}

static const AIOCBInfo iscsi_aiocb_info = {
    .aiocb_size         = sizeof(IscsiAIOCB),
    .cancel_async       = iscsi_aio_cancel,
};

#endif

static void iscsi_process_read(void *arg);
static void iscsi_process_write(void *arg);

/* Called with QemuMutex held.  */
static void
iscsi_set_events(IscsiLun *iscsilun)
{
    struct iscsi_context *iscsi = iscsilun->iscsi;
    int ev = iscsi_which_events(iscsi);

    if (ev != iscsilun->events) {
        aio_set_fd_handler(iscsilun->aio_context, iscsi_get_fd(iscsi),
                           false,
                           (ev & POLLIN) ? iscsi_process_read : NULL,
                           (ev & POLLOUT) ? iscsi_process_write : NULL,
                           NULL,
                           iscsilun);
        iscsilun->events = ev;
    }
}

static void iscsi_timed_check_events(void *opaque)
{
    IscsiLun *iscsilun = opaque;

    WITH_QEMU_LOCK_GUARD(&iscsilun->mutex) {
        /* check for timed out requests */
        iscsi_service(iscsilun->iscsi, 0);

        if (iscsilun->request_timed_out) {
            iscsilun->request_timed_out = false;
            iscsi_reconnect(iscsilun->iscsi);
        }

        /*
         * newer versions of libiscsi may return zero events. Ensure we are
         * able to return to service once this situation changes.
         */
        iscsi_set_events(iscsilun);
    }

    timer_mod(iscsilun->event_timer,
              qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + EVENT_INTERVAL);
}

static void
iscsi_process_read(void *arg)
{
    IscsiLun *iscsilun = arg;
    struct iscsi_context *iscsi = iscsilun->iscsi;

    qemu_mutex_lock(&iscsilun->mutex);
    iscsi_service(iscsi, POLLIN);
    iscsi_set_events(iscsilun);
    qemu_mutex_unlock(&iscsilun->mutex);
}

static void
iscsi_process_write(void *arg)
{
    IscsiLun *iscsilun = arg;
    struct iscsi_context *iscsi = iscsilun->iscsi;

    qemu_mutex_lock(&iscsilun->mutex);
    iscsi_service(iscsi, POLLOUT);
    iscsi_set_events(iscsilun);
    qemu_mutex_unlock(&iscsilun->mutex);
}

static int64_t sector_lun2qemu(int64_t sector, IscsiLun *iscsilun)
{
    return sector * iscsilun->block_size / BDRV_SECTOR_SIZE;
}

static int64_t sector_qemu2lun(int64_t sector, IscsiLun *iscsilun)
{
    return sector * BDRV_SECTOR_SIZE / iscsilun->block_size;
}

static bool is_byte_request_lun_aligned(int64_t offset, int count,
                                        IscsiLun *iscsilun)
{
    if (offset % iscsilun->block_size || count % iscsilun->block_size) {
        error_report("iSCSI misaligned request: "
                     "iscsilun->block_size %u, offset %" PRIi64
                     ", count %d",
                     iscsilun->block_size, offset, count);
        return false;
    }
    return true;
}

static bool is_sector_request_lun_aligned(int64_t sector_num, int nb_sectors,
                                          IscsiLun *iscsilun)
{
    assert(nb_sectors <= BDRV_REQUEST_MAX_SECTORS);
    return is_byte_request_lun_aligned(sector_num << BDRV_SECTOR_BITS,
                                       nb_sectors << BDRV_SECTOR_BITS,
                                       iscsilun);
}

static void iscsi_allocmap_free(IscsiLun *iscsilun)
{
    g_free(iscsilun->allocmap);
    g_free(iscsilun->allocmap_valid);
    iscsilun->allocmap = NULL;
    iscsilun->allocmap_valid = NULL;
}


static int iscsi_allocmap_init(IscsiLun *iscsilun, int open_flags)
{
    iscsi_allocmap_free(iscsilun);

    assert(iscsilun->cluster_size);
    iscsilun->allocmap_size =
        DIV_ROUND_UP(iscsilun->num_blocks * iscsilun->block_size,
                     iscsilun->cluster_size);

    iscsilun->allocmap = bitmap_try_new(iscsilun->allocmap_size);
    if (!iscsilun->allocmap) {
        return -ENOMEM;
    }

    if (open_flags & BDRV_O_NOCACHE) {
        /* when cache.direct = on all allocmap entries are
         * treated as invalid to force a relookup of the block
         * status on every read request */
        return 0;
    }

    iscsilun->allocmap_valid = bitmap_try_new(iscsilun->allocmap_size);
    if (!iscsilun->allocmap_valid) {
        /* if we are under memory pressure free the allocmap as well */
        iscsi_allocmap_free(iscsilun);
        return -ENOMEM;
    }

    return 0;
}

static void
iscsi_allocmap_update(IscsiLun *iscsilun, int64_t offset,
                      int64_t bytes, bool allocated, bool valid)
{
    int64_t cl_num_expanded, nb_cls_expanded, cl_num_shrunk, nb_cls_shrunk;

    if (iscsilun->allocmap == NULL) {
        return;
    }
    /* expand to entirely contain all affected clusters */
    assert(iscsilun->cluster_size);
    cl_num_expanded = offset / iscsilun->cluster_size;
    nb_cls_expanded = DIV_ROUND_UP(offset + bytes,
                                   iscsilun->cluster_size) - cl_num_expanded;
    /* shrink to touch only completely contained clusters */
    cl_num_shrunk = DIV_ROUND_UP(offset, iscsilun->cluster_size);
    nb_cls_shrunk = (offset + bytes) / iscsilun->cluster_size - cl_num_shrunk;
    if (allocated) {
        bitmap_set(iscsilun->allocmap, cl_num_expanded, nb_cls_expanded);
    } else {
        if (nb_cls_shrunk > 0) {
            bitmap_clear(iscsilun->allocmap, cl_num_shrunk, nb_cls_shrunk);
        }
    }

    if (iscsilun->allocmap_valid == NULL) {
        return;
    }
    if (valid) {
        if (nb_cls_shrunk > 0) {
            bitmap_set(iscsilun->allocmap_valid, cl_num_shrunk, nb_cls_shrunk);
        }
    } else {
        bitmap_clear(iscsilun->allocmap_valid, cl_num_expanded,
                     nb_cls_expanded);
    }
}

static void
iscsi_allocmap_set_allocated(IscsiLun *iscsilun, int64_t offset,
                             int64_t bytes)
{
    iscsi_allocmap_update(iscsilun, offset, bytes, true, true);
}

static void
iscsi_allocmap_set_unallocated(IscsiLun *iscsilun, int64_t offset,
                               int64_t bytes)
{
    /* Note: if cache.direct=on the fifth argument to iscsi_allocmap_update
     * is ignored, so this will in effect be an iscsi_allocmap_set_invalid.
     */
    iscsi_allocmap_update(iscsilun, offset, bytes, false, true);
}

static void iscsi_allocmap_set_invalid(IscsiLun *iscsilun, int64_t offset,
                                       int64_t bytes)
{
    iscsi_allocmap_update(iscsilun, offset, bytes, false, false);
}

static void iscsi_allocmap_invalidate(IscsiLun *iscsilun)
{
    if (iscsilun->allocmap) {
        bitmap_zero(iscsilun->allocmap, iscsilun->allocmap_size);
    }
    if (iscsilun->allocmap_valid) {
        bitmap_zero(iscsilun->allocmap_valid, iscsilun->allocmap_size);
    }
}

static inline bool
iscsi_allocmap_is_allocated(IscsiLun *iscsilun, int64_t offset,
                            int64_t bytes)
{
    unsigned long size;
    if (iscsilun->allocmap == NULL) {
        return true;
    }
    assert(iscsilun->cluster_size);
    size = DIV_ROUND_UP(offset + bytes, iscsilun->cluster_size);
    return !(find_next_bit(iscsilun->allocmap, size,
                           offset / iscsilun->cluster_size) == size);
}

static inline bool iscsi_allocmap_is_valid(IscsiLun *iscsilun,
                                           int64_t offset, int64_t bytes)
{
    unsigned long size;
    if (iscsilun->allocmap_valid == NULL) {
        return false;
    }
    assert(iscsilun->cluster_size);
    size = DIV_ROUND_UP(offset + bytes, iscsilun->cluster_size);
    return (find_next_zero_bit(iscsilun->allocmap_valid, size,
                               offset / iscsilun->cluster_size) == size);
}

static void coroutine_fn iscsi_co_wait_for_task(IscsiTask *iTask,
                                                IscsiLun *iscsilun)
{
    while (!iTask->complete) {
        iscsi_set_events(iscsilun);
        qemu_mutex_unlock(&iscsilun->mutex);
        qemu_coroutine_yield();
        qemu_mutex_lock(&iscsilun->mutex);
    }
}

static int coroutine_fn
iscsi_co_writev(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
                QEMUIOVector *iov, int flags)
{
    IscsiLun *iscsilun = bs->opaque;
    struct IscsiTask iTask;
    uint64_t lba;
    uint32_t num_sectors;
    bool fua = flags & BDRV_REQ_FUA;
    int r = 0;

    if (fua) {
        assert(iscsilun->dpofua);
    }
    if (!is_sector_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
        return -EINVAL;
    }

    if (bs->bl.max_transfer) {
        assert(nb_sectors << BDRV_SECTOR_BITS <= bs->bl.max_transfer);
    }

    lba = sector_qemu2lun(sector_num, iscsilun);
    num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
    iscsi_co_init_iscsitask(iscsilun, &iTask);
    qemu_mutex_lock(&iscsilun->mutex);
retry:
    if (iscsilun->use_16_for_rw) {
#if LIBISCSI_API_VERSION >= (20160603)
        iTask.task = iscsi_write16_iov_task(iscsilun->iscsi, iscsilun->lun, lba,
                                            NULL, num_sectors * iscsilun->block_size,
                                            iscsilun->block_size, 0, 0, fua, 0, 0,
                                            iscsi_co_generic_cb, &iTask,
                                            (struct scsi_iovec *)iov->iov, iov->niov);
    } else {
        iTask.task = iscsi_write10_iov_task(iscsilun->iscsi, iscsilun->lun, lba,
                                            NULL, num_sectors * iscsilun->block_size,
                                            iscsilun->block_size, 0, 0, fua, 0, 0,
                                            iscsi_co_generic_cb, &iTask,
                                            (struct scsi_iovec *)iov->iov, iov->niov);
    }
#else
        iTask.task = iscsi_write16_task(iscsilun->iscsi, iscsilun->lun, lba,
                                        NULL, num_sectors * iscsilun->block_size,
                                        iscsilun->block_size, 0, 0, fua, 0, 0,
                                        iscsi_co_generic_cb, &iTask);
    } else {
        iTask.task = iscsi_write10_task(iscsilun->iscsi, iscsilun->lun, lba,
                                        NULL, num_sectors * iscsilun->block_size,
                                        iscsilun->block_size, 0, 0, fua, 0, 0,
                                        iscsi_co_generic_cb, &iTask);
    }
#endif
    if (iTask.task == NULL) {
        qemu_mutex_unlock(&iscsilun->mutex);
        return -ENOMEM;
    }
#if LIBISCSI_API_VERSION < (20160603)
    scsi_task_set_iov_out(iTask.task, (struct scsi_iovec *) iov->iov,
                          iov->niov);
#endif
    iscsi_co_wait_for_task(&iTask, iscsilun);

    if (iTask.task != NULL) {
        scsi_free_scsi_task(iTask.task);
        iTask.task = NULL;
    }

    if (iTask.do_retry) {
        iTask.complete = 0;
        goto retry;
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
        iscsi_allocmap_set_invalid(iscsilun, sector_num * BDRV_SECTOR_SIZE,
                                   nb_sectors * BDRV_SECTOR_SIZE);
        error_report("iSCSI WRITE10/16 failed at lba %" PRIu64 ": %s", lba,
                     iTask.err_str);
        r = iTask.err_code;
        goto out_unlock;
    }

    iscsi_allocmap_set_allocated(iscsilun, sector_num * BDRV_SECTOR_SIZE,
                                 nb_sectors * BDRV_SECTOR_SIZE);

out_unlock:
    qemu_mutex_unlock(&iscsilun->mutex);
    g_free(iTask.err_str);
    return r;
}



static int coroutine_fn iscsi_co_block_status(BlockDriverState *bs,
                                              bool want_zero, int64_t offset,
                                              int64_t bytes, int64_t *pnum,
                                              int64_t *map,
                                              BlockDriverState **file)
{
    IscsiLun *iscsilun = bs->opaque;
    struct scsi_get_lba_status *lbas = NULL;
    struct scsi_lba_status_descriptor *lbasd = NULL;
    struct IscsiTask iTask;
    uint64_t lba, max_bytes;
    int ret;

    iscsi_co_init_iscsitask(iscsilun, &iTask);

    assert(QEMU_IS_ALIGNED(offset | bytes, iscsilun->block_size));

    /* default to all sectors allocated */
    ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
    if (map) {
        *map = offset;
    }
    *pnum = bytes;

    /* LUN does not support logical block provisioning */
    if (!iscsilun->lbpme) {
        goto out;
    }

    lba = offset / iscsilun->block_size;
    max_bytes = (iscsilun->num_blocks - lba) * iscsilun->block_size;

    qemu_mutex_lock(&iscsilun->mutex);
retry:
    if (iscsi_get_lba_status_task(iscsilun->iscsi, iscsilun->lun,
                                  lba, 8 + 16, iscsi_co_generic_cb,
                                  &iTask) == NULL) {
        ret = -ENOMEM;
        goto out_unlock;
    }
    iscsi_co_wait_for_task(&iTask, iscsilun);

    if (iTask.do_retry) {
        if (iTask.task != NULL) {
            scsi_free_scsi_task(iTask.task);
            iTask.task = NULL;
        }
        iTask.complete = 0;
        goto retry;
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
        /* in case the get_lba_status_callout fails (i.e.
         * because the device is busy or the cmd is not
         * supported) we pretend all blocks are allocated
         * for backwards compatibility */
        error_report("iSCSI GET_LBA_STATUS failed at lba %" PRIu64 ": %s",
                     lba, iTask.err_str);
        goto out_unlock;
    }

    lbas = scsi_datain_unmarshall(iTask.task);
    if (lbas == NULL || lbas->num_descriptors == 0) {
        ret = -EIO;
        goto out_unlock;
    }

    lbasd = &lbas->descriptors[0];

    if (lba != lbasd->lba) {
        ret = -EIO;
        goto out_unlock;
    }

    *pnum = MIN((int64_t) lbasd->num_blocks * iscsilun->block_size, max_bytes);

    if (lbasd->provisioning == SCSI_PROVISIONING_TYPE_DEALLOCATED ||
        lbasd->provisioning == SCSI_PROVISIONING_TYPE_ANCHORED) {
        ret &= ~BDRV_BLOCK_DATA;
        if (iscsilun->lbprz) {
            ret |= BDRV_BLOCK_ZERO;
        }
    }

    if (ret & BDRV_BLOCK_ZERO) {
        iscsi_allocmap_set_unallocated(iscsilun, offset, *pnum);
    } else {
        iscsi_allocmap_set_allocated(iscsilun, offset, *pnum);
    }

    if (*pnum > bytes) {
        *pnum = bytes;
    }
out_unlock:
    qemu_mutex_unlock(&iscsilun->mutex);
    g_free(iTask.err_str);
out:
    if (iTask.task != NULL) {
        scsi_free_scsi_task(iTask.task);
    }
    if (ret > 0 && ret & BDRV_BLOCK_OFFSET_VALID && file) {
        *file = bs;
    }
    return ret;
}

static int coroutine_fn iscsi_co_readv(BlockDriverState *bs,
                                       int64_t sector_num, int nb_sectors,
                                       QEMUIOVector *iov)
{
    IscsiLun *iscsilun = bs->opaque;
    struct IscsiTask iTask;
    uint64_t lba;
    uint32_t num_sectors;
    int r = 0;

    if (!is_sector_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
        return -EINVAL;
    }

    if (bs->bl.max_transfer) {
        assert(nb_sectors << BDRV_SECTOR_BITS <= bs->bl.max_transfer);
    }

    /* if cache.direct is off and we have a valid entry in our allocation map
     * we can skip checking the block status and directly return zeroes if
     * the request falls within an unallocated area */
    if (iscsi_allocmap_is_valid(iscsilun, sector_num * BDRV_SECTOR_SIZE,
                                nb_sectors * BDRV_SECTOR_SIZE) &&
        !iscsi_allocmap_is_allocated(iscsilun, sector_num * BDRV_SECTOR_SIZE,
                                     nb_sectors * BDRV_SECTOR_SIZE)) {
            qemu_iovec_memset(iov, 0, 0x00, iov->size);
            return 0;
    }

    if (nb_sectors >= ISCSI_CHECKALLOC_THRES &&
        !iscsi_allocmap_is_valid(iscsilun, sector_num * BDRV_SECTOR_SIZE,
                                 nb_sectors * BDRV_SECTOR_SIZE) &&
        !iscsi_allocmap_is_allocated(iscsilun, sector_num * BDRV_SECTOR_SIZE,
                                     nb_sectors * BDRV_SECTOR_SIZE)) {
        int64_t pnum;
        /* check the block status from the beginning of the cluster
         * containing the start sector */
        int64_t head;
        int ret;

        assert(iscsilun->cluster_size);
        head = (sector_num * BDRV_SECTOR_SIZE) % iscsilun->cluster_size;
        ret = iscsi_co_block_status(bs, true,
                                    sector_num * BDRV_SECTOR_SIZE - head,
                                    BDRV_REQUEST_MAX_BYTES, &pnum, NULL, NULL);
        if (ret < 0) {
            return ret;
        }
        /* if the whole request falls into an unallocated area we can avoid
         * reading and directly return zeroes instead */
        if (ret & BDRV_BLOCK_ZERO &&
            pnum >= nb_sectors * BDRV_SECTOR_SIZE + head) {
            qemu_iovec_memset(iov, 0, 0x00, iov->size);
            return 0;
        }
    }

    lba = sector_qemu2lun(sector_num, iscsilun);
    num_sectors = sector_qemu2lun(nb_sectors, iscsilun);

    iscsi_co_init_iscsitask(iscsilun, &iTask);
    qemu_mutex_lock(&iscsilun->mutex);
retry:
    if (iscsilun->use_16_for_rw) {
#if LIBISCSI_API_VERSION >= (20160603)
        iTask.task = iscsi_read16_iov_task(iscsilun->iscsi, iscsilun->lun, lba,
                                           num_sectors * iscsilun->block_size,
                                           iscsilun->block_size, 0, 0, 0, 0, 0,
                                           iscsi_co_generic_cb, &iTask,
                                           (struct scsi_iovec *)iov->iov, iov->niov);
    } else {
        iTask.task = iscsi_read10_iov_task(iscsilun->iscsi, iscsilun->lun, lba,
                                           num_sectors * iscsilun->block_size,
                                           iscsilun->block_size,
                                           0, 0, 0, 0, 0,
                                           iscsi_co_generic_cb, &iTask,
                                           (struct scsi_iovec *)iov->iov, iov->niov);
    }
#else
        iTask.task = iscsi_read16_task(iscsilun->iscsi, iscsilun->lun, lba,
                                       num_sectors * iscsilun->block_size,
                                       iscsilun->block_size, 0, 0, 0, 0, 0,
                                       iscsi_co_generic_cb, &iTask);
    } else {
        iTask.task = iscsi_read10_task(iscsilun->iscsi, iscsilun->lun, lba,
                                       num_sectors * iscsilun->block_size,
                                       iscsilun->block_size,
                                       0, 0, 0, 0, 0,
                                       iscsi_co_generic_cb, &iTask);
    }
#endif
    if (iTask.task == NULL) {
        qemu_mutex_unlock(&iscsilun->mutex);
        return -ENOMEM;
    }
#if LIBISCSI_API_VERSION < (20160603)
    scsi_task_set_iov_in(iTask.task, (struct scsi_iovec *) iov->iov, iov->niov);
#endif

    iscsi_co_wait_for_task(&iTask, iscsilun);
    if (iTask.task != NULL) {
        scsi_free_scsi_task(iTask.task);
        iTask.task = NULL;
    }

    if (iTask.do_retry) {
        iTask.complete = 0;
        goto retry;
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
        error_report("iSCSI READ10/16 failed at lba %" PRIu64 ": %s",
                     lba, iTask.err_str);
        r = iTask.err_code;
    }

    qemu_mutex_unlock(&iscsilun->mutex);
    g_free(iTask.err_str);
    return r;
}

static int coroutine_fn iscsi_co_flush(BlockDriverState *bs)
{
    IscsiLun *iscsilun = bs->opaque;
    struct IscsiTask iTask;
    int r = 0;

    iscsi_co_init_iscsitask(iscsilun, &iTask);
    qemu_mutex_lock(&iscsilun->mutex);
retry:
    if (iscsi_synchronizecache10_task(iscsilun->iscsi, iscsilun->lun, 0, 0, 0,
                                      0, iscsi_co_generic_cb, &iTask) == NULL) {
        qemu_mutex_unlock(&iscsilun->mutex);
        return -ENOMEM;
    }

    iscsi_co_wait_for_task(&iTask, iscsilun);

    if (iTask.task != NULL) {
        scsi_free_scsi_task(iTask.task);
        iTask.task = NULL;
    }

    if (iTask.do_retry) {
        iTask.complete = 0;
        goto retry;
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
        error_report("iSCSI SYNCHRONIZECACHE10 failed: %s", iTask.err_str);
        r = iTask.err_code;
    }

    qemu_mutex_unlock(&iscsilun->mutex);
    g_free(iTask.err_str);
    return r;
}

#ifdef __linux__
/* Called (via iscsi_service) with QemuMutex held.  */
static void
iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
                     void *command_data, void *opaque)
{
    IscsiAIOCB *acb = opaque;

    if (status == SCSI_STATUS_CANCELLED) {
        if (!acb->bh) {
            acb->status = -ECANCELED;
            iscsi_schedule_bh(acb);
        }
        return;
    }

    acb->status = 0;
    if (status < 0) {
        error_report("Failed to ioctl(SG_IO) to iSCSI lun. %s",
                     iscsi_get_error(iscsi));
        acb->status = -iscsi_translate_sense(&acb->task->sense);
    }

    acb->ioh->driver_status = 0;
    acb->ioh->host_status   = 0;
    acb->ioh->resid         = 0;
    acb->ioh->status        = status;

#define SG_ERR_DRIVER_SENSE    0x08

    if (status == SCSI_STATUS_CHECK_CONDITION && acb->task->datain.size >= 2) {
        int ss;

        acb->ioh->driver_status |= SG_ERR_DRIVER_SENSE;

        acb->ioh->sb_len_wr = acb->task->datain.size - 2;
        ss = MIN(acb->ioh->mx_sb_len, acb->ioh->sb_len_wr);
        memcpy(acb->ioh->sbp, &acb->task->datain.data[2], ss);
    }

    iscsi_schedule_bh(acb);
}

static void iscsi_ioctl_bh_completion(void *opaque)
{
    IscsiAIOCB *acb = opaque;

    qemu_bh_delete(acb->bh);
    acb->common.cb(acb->common.opaque, acb->ret);
    qemu_aio_unref(acb);
}

static void iscsi_ioctl_handle_emulated(IscsiAIOCB *acb, int req, void *buf)
{
    BlockDriverState *bs = acb->common.bs;
    IscsiLun *iscsilun = bs->opaque;
    int ret = 0;

    switch (req) {
    case SG_GET_VERSION_NUM:
        *(int *)buf = 30000;
        break;
    case SG_GET_SCSI_ID:
        ((struct sg_scsi_id *)buf)->scsi_type = iscsilun->type;
        break;
    default:
        ret = -EINVAL;
    }
    assert(!acb->bh);
    acb->bh = aio_bh_new(bdrv_get_aio_context(bs),
                         iscsi_ioctl_bh_completion, acb);
    acb->ret = ret;
    qemu_bh_schedule(acb->bh);
}

static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
        unsigned long int req, void *buf,
        BlockCompletionFunc *cb, void *opaque)
{
    IscsiLun *iscsilun = bs->opaque;
    struct iscsi_context *iscsi = iscsilun->iscsi;
    struct iscsi_data data;
    IscsiAIOCB *acb;

    acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);

    acb->iscsilun = iscsilun;
    acb->bh          = NULL;
    acb->status      = -EINPROGRESS;
    acb->ioh         = buf;
    acb->cancelled   = false;

    if (req != SG_IO) {
        iscsi_ioctl_handle_emulated(acb, req, buf);
        return &acb->common;
    }

    if (acb->ioh->cmd_len > SCSI_CDB_MAX_SIZE) {
        error_report("iSCSI: ioctl error CDB exceeds max size (%d > %d)",
                     acb->ioh->cmd_len, SCSI_CDB_MAX_SIZE);
        qemu_aio_unref(acb);
        return NULL;
    }

    acb->task = malloc(sizeof(struct scsi_task));
    if (acb->task == NULL) {
        error_report("iSCSI: Failed to allocate task for scsi command. %s",
                     iscsi_get_error(iscsi));
        qemu_aio_unref(acb);
        return NULL;
    }
    memset(acb->task, 0, sizeof(struct scsi_task));

    switch (acb->ioh->dxfer_direction) {
    case SG_DXFER_TO_DEV:
        acb->task->xfer_dir = SCSI_XFER_WRITE;
        break;
    case SG_DXFER_FROM_DEV:
        acb->task->xfer_dir = SCSI_XFER_READ;
        break;
    default:
        acb->task->xfer_dir = SCSI_XFER_NONE;
        break;
    }

    acb->task->cdb_size = acb->ioh->cmd_len;
    memcpy(&acb->task->cdb[0], acb->ioh->cmdp, acb->ioh->cmd_len);
    acb->task->expxferlen = acb->ioh->dxfer_len;

    data.size = 0;
    qemu_mutex_lock(&iscsilun->mutex);
    if (acb->task->xfer_dir == SCSI_XFER_WRITE) {
        if (acb->ioh->iovec_count == 0) {
            data.data = acb->ioh->dxferp;
            data.size = acb->ioh->dxfer_len;
        } else {
            scsi_task_set_iov_out(acb->task,
                                 (struct scsi_iovec *) acb->ioh->dxferp,
                                 acb->ioh->iovec_count);
        }
    }

    if (iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
                                 iscsi_aio_ioctl_cb,
                                 (data.size > 0) ? &data : NULL,
                                 acb) != 0) {
        qemu_mutex_unlock(&iscsilun->mutex);
        scsi_free_scsi_task(acb->task);
        qemu_aio_unref(acb);
        return NULL;
    }

    /* tell libiscsi to read straight into the buffer we got from ioctl */
    if (acb->task->xfer_dir == SCSI_XFER_READ) {
        if (acb->ioh->iovec_count == 0) {
            scsi_task_add_data_in_buffer(acb->task,
                                         acb->ioh->dxfer_len,
                                         acb->ioh->dxferp);
        } else {
            scsi_task_set_iov_in(acb->task,
                                 (struct scsi_iovec *) acb->ioh->dxferp,
                                 acb->ioh->iovec_count);
        }
    }

    iscsi_set_events(iscsilun);
    qemu_mutex_unlock(&iscsilun->mutex);

    return &acb->common;
}

#endif

static int64_t
iscsi_getlength(BlockDriverState *bs)
{
    IscsiLun *iscsilun = bs->opaque;
    int64_t len;

    len  = iscsilun->num_blocks;
    len *= iscsilun->block_size;

    return len;
}

static int
coroutine_fn iscsi_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes)
{
    IscsiLun *iscsilun = bs->opaque;
    struct IscsiTask iTask;
    struct unmap_list list;
    int r = 0;

    if (!is_byte_request_lun_aligned(offset, bytes, iscsilun)) {
        return -ENOTSUP;
    }

    if (!iscsilun->lbp.lbpu) {
        /* UNMAP is not supported by the target */
        return 0;
    }

    list.lba = offset / iscsilun->block_size;
    list.num = bytes / iscsilun->block_size;

    iscsi_co_init_iscsitask(iscsilun, &iTask);
    qemu_mutex_lock(&iscsilun->mutex);
retry:
    if (iscsi_unmap_task(iscsilun->iscsi, iscsilun->lun, 0, 0, &list, 1,
                         iscsi_co_generic_cb, &iTask) == NULL) {
        r = -ENOMEM;
        goto out_unlock;
    }

    iscsi_co_wait_for_task(&iTask, iscsilun);

    if (iTask.task != NULL) {
        scsi_free_scsi_task(iTask.task);
        iTask.task = NULL;
    }

    if (iTask.do_retry) {
        iTask.complete = 0;
        goto retry;
    }

    iscsi_allocmap_set_invalid(iscsilun, offset, bytes);

    if (iTask.status == SCSI_STATUS_CHECK_CONDITION) {
        /* the target might fail with a check condition if it
           is not happy with the alignment of the UNMAP request
           we silently fail in this case */
        goto out_unlock;
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
        error_report("iSCSI UNMAP failed at lba %" PRIu64 ": %s",
                     list.lba, iTask.err_str);
        r = iTask.err_code;
        goto out_unlock;
    }

out_unlock:
    qemu_mutex_unlock(&iscsilun->mutex);
    g_free(iTask.err_str);
    return r;
}

static int
coroutine_fn iscsi_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
                                    int bytes, BdrvRequestFlags flags)
{
    IscsiLun *iscsilun = bs->opaque;
    struct IscsiTask iTask;
    uint64_t lba;
    uint32_t nb_blocks;
    bool use_16_for_ws = iscsilun->use_16_for_rw;
    int r = 0;

    if (!is_byte_request_lun_aligned(offset, bytes, iscsilun)) {
        return -ENOTSUP;
    }

    if (flags & BDRV_REQ_MAY_UNMAP) {
        if (!use_16_for_ws && !iscsilun->lbp.lbpws10) {
            /* WRITESAME10 with UNMAP is unsupported try WRITESAME16 */
            use_16_for_ws = true;
        }
        if (use_16_for_ws && !iscsilun->lbp.lbpws) {
            /* WRITESAME16 with UNMAP is not supported by the target,
             * fall back and try WRITESAME10/16 without UNMAP */
            flags &= ~BDRV_REQ_MAY_UNMAP;
            use_16_for_ws = iscsilun->use_16_for_rw;
        }
    }

    if (!(flags & BDRV_REQ_MAY_UNMAP) && !iscsilun->has_write_same) {
        /* WRITESAME without UNMAP is not supported by the target */
        return -ENOTSUP;
    }

    lba = offset / iscsilun->block_size;
    nb_blocks = bytes / iscsilun->block_size;

    if (iscsilun->zeroblock == NULL) {
        iscsilun->zeroblock = g_try_malloc0(iscsilun->block_size);
        if (iscsilun->zeroblock == NULL) {
            return -ENOMEM;
        }
    }

    qemu_mutex_lock(&iscsilun->mutex);
    iscsi_co_init_iscsitask(iscsilun, &iTask);
retry:
    if (use_16_for_ws) {
        iTask.task = iscsi_writesame16_task(iscsilun->iscsi, iscsilun->lun, lba,
                                            iscsilun->zeroblock, iscsilun->block_size,
                                            nb_blocks, 0, !!(flags & BDRV_REQ_MAY_UNMAP),
                                            0, 0, iscsi_co_generic_cb, &iTask);
    } else {
        iTask.task = iscsi_writesame10_task(iscsilun->iscsi, iscsilun->lun, lba,
                                            iscsilun->zeroblock, iscsilun->block_size,
                                            nb_blocks, 0, !!(flags & BDRV_REQ_MAY_UNMAP),
                                            0, 0, iscsi_co_generic_cb, &iTask);
    }
    if (iTask.task == NULL) {
        qemu_mutex_unlock(&iscsilun->mutex);
        return -ENOMEM;
    }

    iscsi_co_wait_for_task(&iTask, iscsilun);

    if (iTask.status == SCSI_STATUS_CHECK_CONDITION &&
        iTask.task->sense.key == SCSI_SENSE_ILLEGAL_REQUEST &&
        (iTask.task->sense.ascq == SCSI_SENSE_ASCQ_INVALID_OPERATION_CODE ||
         iTask.task->sense.ascq == SCSI_SENSE_ASCQ_INVALID_FIELD_IN_CDB)) {
        /* WRITE SAME is not supported by the target */
        iscsilun->has_write_same = false;
        scsi_free_scsi_task(iTask.task);
        r = -ENOTSUP;
        goto out_unlock;
    }

    if (iTask.task != NULL) {
        scsi_free_scsi_task(iTask.task);
        iTask.task = NULL;
    }

    if (iTask.do_retry) {
        iTask.complete = 0;
        goto retry;
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
        iscsi_allocmap_set_invalid(iscsilun, offset, bytes);
        error_report("iSCSI WRITESAME10/16 failed at lba %" PRIu64 ": %s",
                     lba, iTask.err_str);
        r = iTask.err_code;
        goto out_unlock;
    }

    if (flags & BDRV_REQ_MAY_UNMAP) {
        iscsi_allocmap_set_invalid(iscsilun, offset, bytes);
    } else {
        iscsi_allocmap_set_allocated(iscsilun, offset, bytes);
    }

out_unlock:
    qemu_mutex_unlock(&iscsilun->mutex);
    g_free(iTask.err_str);
    return r;
}

static void apply_chap(struct iscsi_context *iscsi, QemuOpts *opts,
                       Error **errp)
{
    const char *user = NULL;
    const char *password = NULL;
    const char *secretid;
    char *secret = NULL;

    user = qemu_opt_get(opts, "user");
    if (!user) {
        return;
    }

    secretid = qemu_opt_get(opts, "password-secret");
    password = qemu_opt_get(opts, "password");
    if (secretid && password) {
        error_setg(errp, "'password' and 'password-secret' properties are "
                   "mutually exclusive");
        return;
    }
    if (secretid) {
        secret = qcrypto_secret_lookup_as_utf8(secretid, errp);
        if (!secret) {
            return;
        }
        password = secret;
    } else if (!password) {
        error_setg(errp, "CHAP username specified but no password was given");
        return;
    }

    if (iscsi_set_initiator_username_pwd(iscsi, user, password)) {
        error_setg(errp, "Failed to set initiator username and password");
    }

    g_free(secret);
}

static void apply_header_digest(struct iscsi_context *iscsi, QemuOpts *opts,
                                Error **errp)
{
    const char *digest = NULL;

    digest = qemu_opt_get(opts, "header-digest");
    if (!digest) {
        iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
    } else if (!strcmp(digest, "crc32c")) {
        iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_CRC32C);
    } else if (!strcmp(digest, "none")) {
        iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE);
    } else if (!strcmp(digest, "crc32c-none")) {
        iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_CRC32C_NONE);
    } else if (!strcmp(digest, "none-crc32c")) {
        iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
    } else {
        error_setg(errp, "Invalid header-digest setting : %s", digest);
    }
}

static char *get_initiator_name(QemuOpts *opts)
{
    const char *name;
    char *iscsi_name;
    UuidInfo *uuid_info;

    name = qemu_opt_get(opts, "initiator-name");
    if (name) {
        return g_strdup(name);
    }

    uuid_info = qmp_query_uuid(NULL);
    if (strcmp(uuid_info->UUID, UUID_NONE) == 0) {
        name = qemu_get_vm_name();
    } else {
        name = uuid_info->UUID;
    }
    iscsi_name = g_strdup_printf("iqn.2008-11.org.linux-kvm%s%s",
                                 name ? ":" : "", name ? name : "");
    qapi_free_UuidInfo(uuid_info);
    return iscsi_name;
}

static void iscsi_nop_timed_event(void *opaque)
{
    IscsiLun *iscsilun = opaque;

    QEMU_LOCK_GUARD(&iscsilun->mutex);
    if (iscsi_get_nops_in_flight(iscsilun->iscsi) >= MAX_NOP_FAILURES) {
        error_report("iSCSI: NOP timeout. Reconnecting...");
        iscsilun->request_timed_out = true;
    } else if (iscsi_nop_out_async(iscsilun->iscsi, NULL, NULL, 0, NULL) != 0) {
        error_report("iSCSI: failed to sent NOP-Out. Disabling NOP messages.");
        return;
    }

    timer_mod(iscsilun->nop_timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);
    iscsi_set_events(iscsilun);
}

static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
{
    struct scsi_task *task = NULL;
    struct scsi_readcapacity10 *rc10 = NULL;
    struct scsi_readcapacity16 *rc16 = NULL;
    int retries = ISCSI_CMD_RETRIES; 

    do {
        if (task != NULL) {
            scsi_free_scsi_task(task);
            task = NULL;
        }

        switch (iscsilun->type) {
        case TYPE_DISK:
            task = iscsi_readcapacity16_sync(iscsilun->iscsi, iscsilun->lun);
            if (task != NULL && task->status == SCSI_STATUS_GOOD) {
                rc16 = scsi_datain_unmarshall(task);
                if (rc16 == NULL) {
                    error_setg(errp, "iSCSI: Failed to unmarshall readcapacity16 data.");
                } else {
                    iscsilun->block_size = rc16->block_length;
                    iscsilun->num_blocks = rc16->returned_lba + 1;
                    iscsilun->lbpme = !!rc16->lbpme;
                    iscsilun->lbprz = !!rc16->lbprz;
                    iscsilun->use_16_for_rw = (rc16->returned_lba > 0xffffffff);
                }
                break;
            }
            if (task != NULL && task->status == SCSI_STATUS_CHECK_CONDITION
                && task->sense.key == SCSI_SENSE_UNIT_ATTENTION) {
                break;
            }
            /* Fall through and try READ CAPACITY(10) instead.  */
        case TYPE_ROM:
            task = iscsi_readcapacity10_sync(iscsilun->iscsi, iscsilun->lun, 0, 0);
            if (task != NULL && task->status == SCSI_STATUS_GOOD) {
                rc10 = scsi_datain_unmarshall(task);
                if (rc10 == NULL) {
                    error_setg(errp, "iSCSI: Failed to unmarshall readcapacity10 data.");
                } else {
                    iscsilun->block_size = rc10->block_size;
                    if (rc10->lba == 0) {
                        /* blank disk loaded */
                        iscsilun->num_blocks = 0;
                    } else {
                        iscsilun->num_blocks = rc10->lba + 1;
                    }
                }
            }
            break;
        default:
            return;
        }
    } while (task != NULL && task->status == SCSI_STATUS_CHECK_CONDITION
             && task->sense.key == SCSI_SENSE_UNIT_ATTENTION
             && retries-- > 0);

    if (task == NULL || task->status != SCSI_STATUS_GOOD) {
        error_setg(errp, "iSCSI: failed to send readcapacity10/16 command");
    } else if (!iscsilun->block_size ||
               iscsilun->block_size % BDRV_SECTOR_SIZE) {
        error_setg(errp, "iSCSI: the target returned an invalid "
                   "block size of %d.", iscsilun->block_size);
    }
    if (task) {
        scsi_free_scsi_task(task);
    }
}

static struct scsi_task *iscsi_do_inquiry(struct iscsi_context *iscsi, int lun,
                                          int evpd, int pc, void **inq, Error **errp)
{
    int full_size;
    struct scsi_task *task = NULL;
    task = iscsi_inquiry_sync(iscsi, lun, evpd, pc, 64);
    if (task == NULL || task->status != SCSI_STATUS_GOOD) {
        goto fail;
    }
    full_size = scsi_datain_getfullsize(task);
    if (full_size > task->datain.size) {
        scsi_free_scsi_task(task);

        /* we need more data for the full list */
        task = iscsi_inquiry_sync(iscsi, lun, evpd, pc, full_size);
        if (task == NULL || task->status != SCSI_STATUS_GOOD) {
            goto fail;
        }
    }

    *inq = scsi_datain_unmarshall(task);
    if (*inq == NULL) {
        error_setg(errp, "iSCSI: failed to unmarshall inquiry datain blob");
        goto fail_with_err;
    }

    return task;

fail:
    error_setg(errp, "iSCSI: Inquiry command failed : %s",
               iscsi_get_error(iscsi));
fail_with_err:
    if (task != NULL) {
        scsi_free_scsi_task(task);
    }
    return NULL;
}

static void iscsi_detach_aio_context(BlockDriverState *bs)
{
    IscsiLun *iscsilun = bs->opaque;

    aio_set_fd_handler(iscsilun->aio_context, iscsi_get_fd(iscsilun->iscsi),
                       false, NULL, NULL, NULL, NULL);
    iscsilun->events = 0;

    if (iscsilun->nop_timer) {
        timer_del(iscsilun->nop_timer);
        timer_free(iscsilun->nop_timer);
        iscsilun->nop_timer = NULL;
    }
    if (iscsilun->event_timer) {
        timer_del(iscsilun->event_timer);
        timer_free(iscsilun->event_timer);
        iscsilun->event_timer = NULL;
    }
}

static void iscsi_attach_aio_context(BlockDriverState *bs,
                                     AioContext *new_context)
{
    IscsiLun *iscsilun = bs->opaque;

    iscsilun->aio_context = new_context;
    iscsi_set_events(iscsilun);

    /* Set up a timer for sending out iSCSI NOPs */
    iscsilun->nop_timer = aio_timer_new(iscsilun->aio_context,
                                        QEMU_CLOCK_REALTIME, SCALE_MS,
                                        iscsi_nop_timed_event, iscsilun);
    timer_mod(iscsilun->nop_timer,
              qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);

    /* Set up a timer for periodic calls to iscsi_set_events and to
     * scan for command timeout */
    iscsilun->event_timer = aio_timer_new(iscsilun->aio_context,
                                          QEMU_CLOCK_REALTIME, SCALE_MS,
                                          iscsi_timed_check_events, iscsilun);
    timer_mod(iscsilun->event_timer,
              qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + EVENT_INTERVAL);
}

static void iscsi_modesense_sync(IscsiLun *iscsilun)
{
    struct scsi_task *task;
    struct scsi_mode_sense *ms = NULL;
    iscsilun->write_protected = false;
    iscsilun->dpofua = false;

    task = iscsi_modesense6_sync(iscsilun->iscsi, iscsilun->lun,
                                 1, SCSI_MODESENSE_PC_CURRENT,
                                 0x3F, 0, 255);
    if (task == NULL) {
        error_report("iSCSI: Failed to send MODE_SENSE(6) command: %s",
                     iscsi_get_error(iscsilun->iscsi));
        goto out;
    }

    if (task->status != SCSI_STATUS_GOOD) {
        error_report("iSCSI: Failed MODE_SENSE(6), LUN assumed writable");
        goto out;
    }
    ms = scsi_datain_unmarshall(task);
    if (!ms) {
        error_report("iSCSI: Failed to unmarshall MODE_SENSE(6) data: %s",
                     iscsi_get_error(iscsilun->iscsi));
        goto out;
    }
    iscsilun->write_protected = ms->device_specific_parameter & 0x80;
    iscsilun->dpofua          = ms->device_specific_parameter & 0x10;

out:
    if (task) {
        scsi_free_scsi_task(task);
    }
}

static void iscsi_parse_iscsi_option(const char *target, QDict *options)
{
    QemuOptsList *list;
    QemuOpts *opts;
    const char *user, *password, *password_secret, *initiator_name,
               *header_digest, *timeout;

    list = qemu_find_opts("iscsi");
    if (!list) {
        return;
    }

    opts = qemu_opts_find(list, target);
    if (opts == NULL) {
        opts = QTAILQ_FIRST(&list->head);
        if (!opts) {
            return;
        }
    }

    user = qemu_opt_get(opts, "user");
    if (user) {
        qdict_set_default_str(options, "user", user);
    }

    password = qemu_opt_get(opts, "password");
    if (password) {
        qdict_set_default_str(options, "password", password);
    }

    password_secret = qemu_opt_get(opts, "password-secret");
    if (password_secret) {
        qdict_set_default_str(options, "password-secret", password_secret);
    }

    initiator_name = qemu_opt_get(opts, "initiator-name");
    if (initiator_name) {
        qdict_set_default_str(options, "initiator-name", initiator_name);
    }

    header_digest = qemu_opt_get(opts, "header-digest");
    if (header_digest) {
        /* -iscsi takes upper case values, but QAPI only supports lower case
         * enum constant names, so we have to convert here. */
        char *qapi_value = g_ascii_strdown(header_digest, -1);
        qdict_set_default_str(options, "header-digest", qapi_value);
        g_free(qapi_value);
    }

    timeout = qemu_opt_get(opts, "timeout");
    if (timeout) {
        qdict_set_default_str(options, "timeout", timeout);
    }
}

/*
 * We support iscsi url's on the form
 * iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun>
 */
static void iscsi_parse_filename(const char *filename, QDict *options,
                                 Error **errp)
{
    struct iscsi_url *iscsi_url;
    const char *transport_name;
    char *lun_str;

    iscsi_url = iscsi_parse_full_url(NULL, filename);
    if (iscsi_url == NULL) {
        error_setg(errp, "Failed to parse URL : %s", filename);
        return;
    }

#if LIBISCSI_API_VERSION >= (20160603)
    switch (iscsi_url->transport) {
    case TCP_TRANSPORT:
        transport_name = "tcp";
        break;
    case ISER_TRANSPORT:
        transport_name = "iser";
        break;
    default:
        error_setg(errp, "Unknown transport type (%d)",
                   iscsi_url->transport);
        return;
    }
#else
    transport_name = "tcp";
#endif

    qdict_set_default_str(options, "transport", transport_name);
    qdict_set_default_str(options, "portal", iscsi_url->portal);
    qdict_set_default_str(options, "target", iscsi_url->target);

    lun_str = g_strdup_printf("%d", iscsi_url->lun);
    qdict_set_default_str(options, "lun", lun_str);
    g_free(lun_str);

    /* User/password from -iscsi take precedence over those from the URL */
    iscsi_parse_iscsi_option(iscsi_url->target, options);

    if (iscsi_url->user[0] != '\0') {
        qdict_set_default_str(options, "user", iscsi_url->user);
        qdict_set_default_str(options, "password", iscsi_url->passwd);
    }

    iscsi_destroy_url(iscsi_url);
}

static QemuOptsList runtime_opts = {
    .name = "iscsi",
    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
    .desc = {
        {
            .name = "transport",
            .type = QEMU_OPT_STRING,
        },
        {
            .name = "portal",
            .type = QEMU_OPT_STRING,
        },
        {
            .name = "target",
            .type = QEMU_OPT_STRING,
        },
        {
            .name = "user",
            .type = QEMU_OPT_STRING,
        },
        {
            .name = "password",
            .type = QEMU_OPT_STRING,
        },
        {
            .name = "password-secret",
            .type = QEMU_OPT_STRING,
        },
        {
            .name = "lun",
            .type = QEMU_OPT_NUMBER,
        },
        {
            .name = "initiator-name",
            .type = QEMU_OPT_STRING,
        },
        {
            .name = "header-digest",
            .type = QEMU_OPT_STRING,
        },
        {
            .name = "timeout",
            .type = QEMU_OPT_NUMBER,
        },
        { /* end of list */ }
    },
};

static void iscsi_save_designator(IscsiLun *lun,
                                  struct scsi_inquiry_device_identification *inq_di)
{
    struct scsi_inquiry_device_designator *desig, *copy = NULL;

    for (desig = inq_di->designators; desig; desig = desig->next) {
        if (desig->association ||
            desig->designator_type > SCSI_DESIGNATOR_TYPE_NAA) {
            continue;
        }
        /* NAA works better than T10 vendor ID based designator. */
        if (!copy || copy->designator_type < desig->designator_type) {
            copy = desig;
        }
    }
    if (copy) {
        lun->dd = g_new(struct scsi_inquiry_device_designator, 1);
        *lun->dd = *copy;
        lun->dd->next = NULL;
        lun->dd->designator = g_malloc(copy->designator_length);
        memcpy(lun->dd->designator, copy->designator, copy->designator_length);
    }
}

static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
{
    IscsiLun *iscsilun = bs->opaque;
    struct iscsi_context *iscsi = NULL;
    struct scsi_task *task = NULL;
    struct scsi_inquiry_standard *inq = NULL;
    struct scsi_inquiry_supported_pages *inq_vpd;
    char *initiator_name = NULL;
    QemuOpts *opts;
    Error *local_err = NULL;
    const char *transport_name, *portal, *target;
#if LIBISCSI_API_VERSION >= (20160603)
    enum iscsi_transport_type transport;
#endif
    int i, ret = 0, timeout = 0, lun;

    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
    if (!qemu_opts_absorb_qdict(opts, options, errp)) {
        ret = -EINVAL;
        goto out;
    }

    transport_name = qemu_opt_get(opts, "transport");
    portal = qemu_opt_get(opts, "portal");
    target = qemu_opt_get(opts, "target");
    lun = qemu_opt_get_number(opts, "lun", 0);

    if (!transport_name || !portal || !target) {
        error_setg(errp, "Need all of transport, portal and target options");
        ret = -EINVAL;
        goto out;
    }

    if (!strcmp(transport_name, "tcp")) {
#if LIBISCSI_API_VERSION >= (20160603)
        transport = TCP_TRANSPORT;
    } else if (!strcmp(transport_name, "iser")) {
        transport = ISER_TRANSPORT;
#else
        /* TCP is what older libiscsi versions always use */
#endif
    } else {
        error_setg(errp, "Unknown transport: %s", transport_name);
        ret = -EINVAL;
        goto out;
    }

    memset(iscsilun, 0, sizeof(IscsiLun));

    initiator_name = get_initiator_name(opts);

    iscsi = iscsi_create_context(initiator_name);
    if (iscsi == NULL) {
        error_setg(errp, "iSCSI: Failed to create iSCSI context.");
        ret = -ENOMEM;
        goto out;
    }
#if LIBISCSI_API_VERSION >= (20160603)
    if (iscsi_init_transport(iscsi, transport)) {
        error_setg(errp, ("Error initializing transport."));
        ret = -EINVAL;
        goto out;
    }
#endif
    if (iscsi_set_targetname(iscsi, target)) {
        error_setg(errp, "iSCSI: Failed to set target name.");
        ret = -EINVAL;
        goto out;
    }

    /* check if we got CHAP username/password via the options */
    apply_chap(iscsi, opts, &local_err);
    if (local_err != NULL) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto out;
    }

    if (iscsi_set_session_type(iscsi, ISCSI_SESSION_NORMAL) != 0) {
        error_setg(errp, "iSCSI: Failed to set session type to normal.");
        ret = -EINVAL;
        goto out;
    }

    /* check if we got HEADER_DIGEST via the options */
    apply_header_digest(iscsi, opts, &local_err);
    if (local_err != NULL) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto out;
    }

    /* timeout handling is broken in libiscsi before 1.15.0 */
    timeout = qemu_opt_get_number(opts, "timeout", 0);
#if LIBISCSI_API_VERSION >= 20150621
    iscsi_set_timeout(iscsi, timeout);
#else
    if (timeout) {
        warn_report("iSCSI: ignoring timeout value for libiscsi <1.15.0");
    }
#endif

    if (iscsi_full_connect_sync(iscsi, portal, lun) != 0) {
        error_setg(errp, "iSCSI: Failed to connect to LUN : %s",
            iscsi_get_error(iscsi));
        ret = -EINVAL;
        goto out;
    }

    iscsilun->iscsi = iscsi;
    iscsilun->aio_context = bdrv_get_aio_context(bs);
    iscsilun->lun = lun;
    iscsilun->has_write_same = true;

    task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 0, 0,
                            (void **) &inq, errp);
    if (task == NULL) {
        ret = -EINVAL;
        goto out;
    }
    iscsilun->type = inq->periperal_device_type;
    scsi_free_scsi_task(task);
    task = NULL;

    iscsi_modesense_sync(iscsilun);
    if (iscsilun->dpofua) {
        bs->supported_write_flags = BDRV_REQ_FUA;
    }

    /* Check the write protect flag of the LUN if we want to write */
    if (iscsilun->type == TYPE_DISK && (flags & BDRV_O_RDWR) &&
        iscsilun->write_protected) {
        ret = bdrv_apply_auto_read_only(bs, "LUN is write protected", errp);
        if (ret < 0) {
            goto out;
        }
        flags &= ~BDRV_O_RDWR;
    }

    iscsi_readcapacity_sync(iscsilun, &local_err);
    if (local_err != NULL) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto out;
    }
    bs->total_sectors = sector_lun2qemu(iscsilun->num_blocks, iscsilun);

    /* We don't have any emulation for devices other than disks and CD-ROMs, so
     * this must be sg ioctl compatible. We force it to be sg, otherwise qemu
     * will try to read from the device to guess the image format.
     */
    if (iscsilun->type != TYPE_DISK && iscsilun->type != TYPE_ROM) {
        bs->sg = true;
    }

    task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
                            SCSI_INQUIRY_PAGECODE_SUPPORTED_VPD_PAGES,
                            (void **) &inq_vpd, errp);
    if (task == NULL) {
        ret = -EINVAL;
        goto out;
    }
    for (i = 0; i < inq_vpd->num_pages; i++) {
        struct scsi_task *inq_task;
        struct scsi_inquiry_logical_block_provisioning *inq_lbp;
        struct scsi_inquiry_block_limits *inq_bl;
        struct scsi_inquiry_device_identification *inq_di;
        switch (inq_vpd->pages[i]) {
        case SCSI_INQUIRY_PAGECODE_LOGICAL_BLOCK_PROVISIONING:
            inq_task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
                                        SCSI_INQUIRY_PAGECODE_LOGICAL_BLOCK_PROVISIONING,
                                        (void **) &inq_lbp, errp);
            if (inq_task == NULL) {
                ret = -EINVAL;
                goto out;
            }
            memcpy(&iscsilun->lbp, inq_lbp,
                   sizeof(struct scsi_inquiry_logical_block_provisioning));
            scsi_free_scsi_task(inq_task);
            break;
        case SCSI_INQUIRY_PAGECODE_BLOCK_LIMITS:
            inq_task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
                                    SCSI_INQUIRY_PAGECODE_BLOCK_LIMITS,
                                    (void **) &inq_bl, errp);
            if (inq_task == NULL) {
                ret = -EINVAL;
                goto out;
            }
            memcpy(&iscsilun->bl, inq_bl,
                   sizeof(struct scsi_inquiry_block_limits));
            scsi_free_scsi_task(inq_task);
            break;
        case SCSI_INQUIRY_PAGECODE_DEVICE_IDENTIFICATION:
            inq_task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
                                    SCSI_INQUIRY_PAGECODE_DEVICE_IDENTIFICATION,
                                    (void **) &inq_di, errp);
            if (inq_task == NULL) {
                ret = -EINVAL;
                goto out;
            }
            iscsi_save_designator(iscsilun, inq_di);
            scsi_free_scsi_task(inq_task);
            break;
        default:
            break;
        }
    }
    scsi_free_scsi_task(task);
    task = NULL;

    qemu_mutex_init(&iscsilun->mutex);
    iscsi_attach_aio_context(bs, iscsilun->aio_context);

    /* Guess the internal cluster (page) size of the iscsi target by the means
     * of opt_unmap_gran. Transfer the unmap granularity only if it has a
     * reasonable size */
    if (iscsilun->bl.opt_unmap_gran * iscsilun->block_size >= 4 * 1024 &&
        iscsilun->bl.opt_unmap_gran * iscsilun->block_size <= 16 * 1024 * 1024) {
        iscsilun->cluster_size = iscsilun->bl.opt_unmap_gran *
            iscsilun->block_size;
        if (iscsilun->lbprz) {
            ret = iscsi_allocmap_init(iscsilun, flags);
        }
    }

    if (iscsilun->lbprz && iscsilun->lbp.lbpws) {
        bs->supported_zero_flags = BDRV_REQ_MAY_UNMAP;
    }

out:
    qemu_opts_del(opts);
    g_free(initiator_name);
    if (task != NULL) {
        scsi_free_scsi_task(task);
    }

    if (ret) {
        if (iscsi != NULL) {
            if (iscsi_is_logged_in(iscsi)) {
                iscsi_logout_sync(iscsi);
            }
            iscsi_destroy_context(iscsi);
        }
        memset(iscsilun, 0, sizeof(IscsiLun));
    }

    return ret;
}

static void iscsi_close(BlockDriverState *bs)
{
    IscsiLun *iscsilun = bs->opaque;
    struct iscsi_context *iscsi = iscsilun->iscsi;

    iscsi_detach_aio_context(bs);
    if (iscsi_is_logged_in(iscsi)) {
        iscsi_logout_sync(iscsi);
    }
    iscsi_destroy_context(iscsi);
    if (iscsilun->dd) {
        g_free(iscsilun->dd->designator);
        g_free(iscsilun->dd);
    }
    g_free(iscsilun->zeroblock);
    iscsi_allocmap_free(iscsilun);
    qemu_mutex_destroy(&iscsilun->mutex);
    memset(iscsilun, 0, sizeof(IscsiLun));
}

static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp)
{
    /* We don't actually refresh here, but just return data queried in
     * iscsi_open(): iscsi targets don't change their limits. */

    IscsiLun *iscsilun = bs->opaque;
    uint64_t max_xfer_len = iscsilun->use_16_for_rw ? 0xffffffff : 0xffff;
    unsigned int block_size = MAX(BDRV_SECTOR_SIZE, iscsilun->block_size);

    assert(iscsilun->block_size >= BDRV_SECTOR_SIZE || bs->sg);

    bs->bl.request_alignment = block_size;

    if (iscsilun->bl.max_xfer_len) {
        max_xfer_len = MIN(max_xfer_len, iscsilun->bl.max_xfer_len);
    }

    if (max_xfer_len * block_size < INT_MAX) {
        bs->bl.max_transfer = max_xfer_len * iscsilun->block_size;
    }

    if (iscsilun->lbp.lbpu) {
        if (iscsilun->bl.max_unmap < 0xffffffff / block_size) {
            bs->bl.max_pdiscard =
                iscsilun->bl.max_unmap * iscsilun->block_size;
        }
        bs->bl.pdiscard_alignment =
            iscsilun->bl.opt_unmap_gran * iscsilun->block_size;
    } else {
        bs->bl.pdiscard_alignment = iscsilun->block_size;
    }

    if (iscsilun->bl.max_ws_len < 0xffffffff / block_size) {
        bs->bl.max_pwrite_zeroes =
            iscsilun->bl.max_ws_len * iscsilun->block_size;
    }
    if (iscsilun->lbp.lbpws) {
        bs->bl.pwrite_zeroes_alignment =
            iscsilun->bl.opt_unmap_gran * iscsilun->block_size;
    } else {
        bs->bl.pwrite_zeroes_alignment = iscsilun->block_size;
    }
    if (iscsilun->bl.opt_xfer_len &&
        iscsilun->bl.opt_xfer_len < INT_MAX / block_size) {
        bs->bl.opt_transfer = pow2floor(iscsilun->bl.opt_xfer_len *
                                        iscsilun->block_size);
    }
}

/* Note that this will not re-establish a connection with an iSCSI target - it
 * is effectively a NOP.  */
static int iscsi_reopen_prepare(BDRVReopenState *state,
                                BlockReopenQueue *queue, Error **errp)
{
    IscsiLun *iscsilun = state->bs->opaque;

    if (state->flags & BDRV_O_RDWR && iscsilun->write_protected) {
        error_setg(errp, "Cannot open a write protected LUN as read-write");
        return -EACCES;
    }
    return 0;
}

static void iscsi_reopen_commit(BDRVReopenState *reopen_state)
{
    IscsiLun *iscsilun = reopen_state->bs->opaque;

    /* the cache.direct status might have changed */
    if (iscsilun->allocmap != NULL) {
        iscsi_allocmap_init(iscsilun, reopen_state->flags);
    }
}

static int coroutine_fn iscsi_co_truncate(BlockDriverState *bs, int64_t offset,
                                          bool exact, PreallocMode prealloc,
                                          BdrvRequestFlags flags, Error **errp)
{
    IscsiLun *iscsilun = bs->opaque;
    int64_t cur_length;
    Error *local_err = NULL;

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

    if (iscsilun->type != TYPE_DISK) {
        error_setg(errp, "Cannot resize non-disk iSCSI devices");
        return -ENOTSUP;
    }

    iscsi_readcapacity_sync(iscsilun, &local_err);
    if (local_err != NULL) {
        error_propagate(errp, local_err);
        return -EIO;
    }

    cur_length = iscsi_getlength(bs);
    if (offset != cur_length && exact) {
        error_setg(errp, "Cannot resize iSCSI devices");
        return -ENOTSUP;
    } else if (offset > cur_length) {
        error_setg(errp, "Cannot grow iSCSI devices");
        return -EINVAL;
    }

    if (iscsilun->allocmap != NULL) {
        iscsi_allocmap_init(iscsilun, bs->open_flags);
    }

    return 0;
}

static int iscsi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
    IscsiLun *iscsilun = bs->opaque;
    bdi->cluster_size = iscsilun->cluster_size;
    return 0;
}

static void coroutine_fn iscsi_co_invalidate_cache(BlockDriverState *bs,
                                                   Error **errp)
{
    IscsiLun *iscsilun = bs->opaque;
    iscsi_allocmap_invalidate(iscsilun);
}

static int coroutine_fn iscsi_co_copy_range_from(BlockDriverState *bs,
                                                 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_to(src, src_offset, dst, dst_offset, bytes,
                                 read_flags, write_flags);
}

static struct scsi_task *iscsi_xcopy_task(int param_len)
{
    struct scsi_task *task;

    task = g_new0(struct scsi_task, 1);

    task->cdb[0]     = EXTENDED_COPY;
    task->cdb[10]    = (param_len >> 24) & 0xFF;
    task->cdb[11]    = (param_len >> 16) & 0xFF;
    task->cdb[12]    = (param_len >> 8) & 0xFF;
    task->cdb[13]    = param_len & 0xFF;
    task->cdb_size   = 16;
    task->xfer_dir   = SCSI_XFER_WRITE;
    task->expxferlen = param_len;

    return task;
}

static void iscsi_populate_target_desc(unsigned char *desc, IscsiLun *lun)
{
    struct scsi_inquiry_device_designator *dd = lun->dd;

    memset(desc, 0, 32);
    desc[0] = 0xE4; /* IDENT_DESCR_TGT_DESCR */
    desc[4] = dd->code_set;
    desc[5] = (dd->designator_type & 0xF)
        | ((dd->association & 3) << 4);
    desc[7] = dd->designator_length;
    memcpy(desc + 8, dd->designator, MIN(dd->designator_length, 20));

    desc[28] = 0;
    desc[29] = (lun->block_size >> 16) & 0xFF;
    desc[30] = (lun->block_size >> 8) & 0xFF;
    desc[31] = lun->block_size & 0xFF;
}

static void iscsi_xcopy_desc_hdr(uint8_t *hdr, int dc, int cat, int src_index,
                                 int dst_index)
{
    hdr[0] = 0x02; /* BLK_TO_BLK_SEG_DESCR */
    hdr[1] = ((dc << 1) | cat) & 0xFF;
    hdr[2] = (XCOPY_BLK2BLK_SEG_DESC_SIZE >> 8) & 0xFF;
    /* don't account for the first 4 bytes in descriptor header*/
    hdr[3] = (XCOPY_BLK2BLK_SEG_DESC_SIZE - 4 /* SEG_DESC_SRC_INDEX_OFFSET */) & 0xFF;
    hdr[4] = (src_index >> 8) & 0xFF;
    hdr[5] = src_index & 0xFF;
    hdr[6] = (dst_index >> 8) & 0xFF;
    hdr[7] = dst_index & 0xFF;
}

static void iscsi_xcopy_populate_desc(uint8_t *desc, int dc, int cat,
                                      int src_index, int dst_index, int num_blks,
                                      uint64_t src_lba, uint64_t dst_lba)
{
    iscsi_xcopy_desc_hdr(desc, dc, cat, src_index, dst_index);

    /* The caller should verify the request size */
    assert(num_blks < 65536);
    desc[10] = (num_blks >> 8) & 0xFF;
    desc[11] = num_blks & 0xFF;
    desc[12] = (src_lba >> 56) & 0xFF;
    desc[13] = (src_lba >> 48) & 0xFF;
    desc[14] = (src_lba >> 40) & 0xFF;
    desc[15] = (src_lba >> 32) & 0xFF;
    desc[16] = (src_lba >> 24) & 0xFF;
    desc[17] = (src_lba >> 16) & 0xFF;
    desc[18] = (src_lba >> 8) & 0xFF;
    desc[19] = src_lba & 0xFF;
    desc[20] = (dst_lba >> 56) & 0xFF;
    desc[21] = (dst_lba >> 48) & 0xFF;
    desc[22] = (dst_lba >> 40) & 0xFF;
    desc[23] = (dst_lba >> 32) & 0xFF;
    desc[24] = (dst_lba >> 24) & 0xFF;
    desc[25] = (dst_lba >> 16) & 0xFF;
    desc[26] = (dst_lba >> 8) & 0xFF;
    desc[27] = dst_lba & 0xFF;
}

static void iscsi_xcopy_populate_header(unsigned char *buf, int list_id, int str,
                                        int list_id_usage, int prio,
                                        int tgt_desc_len,
                                        int seg_desc_len, int inline_data_len)
{
    buf[0] = list_id;
    buf[1] = ((str & 1) << 5) | ((list_id_usage & 3) << 3) | (prio & 7);
    buf[2] = (tgt_desc_len >> 8) & 0xFF;
    buf[3] = tgt_desc_len & 0xFF;
    buf[8] = (seg_desc_len >> 24) & 0xFF;
    buf[9] = (seg_desc_len >> 16) & 0xFF;
    buf[10] = (seg_desc_len >> 8) & 0xFF;
    buf[11] = seg_desc_len & 0xFF;
    buf[12] = (inline_data_len >> 24) & 0xFF;
    buf[13] = (inline_data_len >> 16) & 0xFF;
    buf[14] = (inline_data_len >> 8) & 0xFF;
    buf[15] = inline_data_len & 0xFF;
}

static void iscsi_xcopy_data(struct iscsi_data *data,
                             IscsiLun *src, int64_t src_lba,
                             IscsiLun *dst, int64_t dst_lba,
                             uint16_t num_blocks)
{
    uint8_t *buf;
    const int src_offset = XCOPY_DESC_OFFSET;
    const int dst_offset = XCOPY_DESC_OFFSET + IDENT_DESCR_TGT_DESCR_SIZE;
    const int seg_offset = dst_offset + IDENT_DESCR_TGT_DESCR_SIZE;

    data->size = XCOPY_DESC_OFFSET +
                 IDENT_DESCR_TGT_DESCR_SIZE * 2 +
                 XCOPY_BLK2BLK_SEG_DESC_SIZE;
    data->data = g_malloc0(data->size);
    buf = data->data;

    /* Initialise the parameter list header */
    iscsi_xcopy_populate_header(buf, 1, 0, 2 /* LIST_ID_USAGE_DISCARD */,
                                0, 2 * IDENT_DESCR_TGT_DESCR_SIZE,
                                XCOPY_BLK2BLK_SEG_DESC_SIZE,
                                0);

    /* Initialise CSCD list with one src + one dst descriptor */
    iscsi_populate_target_desc(&buf[src_offset], src);
    iscsi_populate_target_desc(&buf[dst_offset], dst);

    /* Initialise one segment descriptor */
    iscsi_xcopy_populate_desc(&buf[seg_offset], 0, 0, 0, 1, num_blocks,
                              src_lba, dst_lba);
}

static int coroutine_fn iscsi_co_copy_range_to(BlockDriverState *bs,
                                               BdrvChild *src,
                                               uint64_t src_offset,
                                               BdrvChild *dst,
                                               uint64_t dst_offset,
                                               uint64_t bytes,
                                               BdrvRequestFlags read_flags,
                                               BdrvRequestFlags write_flags)
{
    IscsiLun *dst_lun = dst->bs->opaque;
    IscsiLun *src_lun;
    struct IscsiTask iscsi_task;
    struct iscsi_data data;
    int r = 0;
    int block_size;

    if (src->bs->drv->bdrv_co_copy_range_to != iscsi_co_copy_range_to) {
        return -ENOTSUP;
    }
    src_lun = src->bs->opaque;

    if (!src_lun->dd || !dst_lun->dd) {
        return -ENOTSUP;
    }
    if (!is_byte_request_lun_aligned(dst_offset, bytes, dst_lun)) {
        return -ENOTSUP;
    }
    if (!is_byte_request_lun_aligned(src_offset, bytes, src_lun)) {
        return -ENOTSUP;
    }
    if (dst_lun->block_size != src_lun->block_size ||
        !dst_lun->block_size) {
        return -ENOTSUP;
    }

    block_size = dst_lun->block_size;
    if (bytes / block_size > 65535) {
        return -ENOTSUP;
    }

    iscsi_xcopy_data(&data,
                     src_lun, src_offset / block_size,
                     dst_lun, dst_offset / block_size,
                     bytes / block_size);

    iscsi_co_init_iscsitask(dst_lun, &iscsi_task);

    qemu_mutex_lock(&dst_lun->mutex);
    iscsi_task.task = iscsi_xcopy_task(data.size);
retry:
    if (iscsi_scsi_command_async(dst_lun->iscsi, dst_lun->lun,
                                 iscsi_task.task, iscsi_co_generic_cb,
                                 &data,
                                 &iscsi_task) != 0) {
        r = -EIO;
        goto out_unlock;
    }

    iscsi_co_wait_for_task(&iscsi_task, dst_lun);

    if (iscsi_task.do_retry) {
        iscsi_task.complete = 0;
        goto retry;
    }

    if (iscsi_task.status != SCSI_STATUS_GOOD) {
        r = iscsi_task.err_code;
        goto out_unlock;
    }

out_unlock:

    trace_iscsi_xcopy(src_lun, src_offset, dst_lun, dst_offset, bytes, r);
    g_free(iscsi_task.task);
    qemu_mutex_unlock(&dst_lun->mutex);
    g_free(iscsi_task.err_str);
    return r;
}


static const char *const iscsi_strong_runtime_opts[] = {
    "transport",
    "portal",
    "target",
    "user",
    "password",
    "password-secret",
    "lun",
    "initiator-name",
    "header-digest",

    NULL
};

static BlockDriver bdrv_iscsi = {
    .format_name     = "iscsi",
    .protocol_name   = "iscsi",

    .instance_size          = sizeof(IscsiLun),
    .bdrv_parse_filename    = iscsi_parse_filename,
    .bdrv_file_open         = iscsi_open,
    .bdrv_close             = iscsi_close,
    .bdrv_co_create_opts    = bdrv_co_create_opts_simple,
    .create_opts            = &bdrv_create_opts_simple,
    .bdrv_reopen_prepare    = iscsi_reopen_prepare,
    .bdrv_reopen_commit     = iscsi_reopen_commit,
    .bdrv_co_invalidate_cache = iscsi_co_invalidate_cache,

    .bdrv_getlength  = iscsi_getlength,
    .bdrv_get_info   = iscsi_get_info,
    .bdrv_co_truncate    = iscsi_co_truncate,
    .bdrv_refresh_limits = iscsi_refresh_limits,

    .bdrv_co_block_status  = iscsi_co_block_status,
    .bdrv_co_pdiscard      = iscsi_co_pdiscard,
    .bdrv_co_copy_range_from = iscsi_co_copy_range_from,
    .bdrv_co_copy_range_to  = iscsi_co_copy_range_to,
    .bdrv_co_pwrite_zeroes = iscsi_co_pwrite_zeroes,
    .bdrv_co_readv         = iscsi_co_readv,
    .bdrv_co_writev        = iscsi_co_writev,
    .bdrv_co_flush_to_disk = iscsi_co_flush,

#ifdef __linux__
    .bdrv_aio_ioctl   = iscsi_aio_ioctl,
#endif

    .bdrv_detach_aio_context = iscsi_detach_aio_context,
    .bdrv_attach_aio_context = iscsi_attach_aio_context,

    .strong_runtime_opts = iscsi_strong_runtime_opts,
};

#if LIBISCSI_API_VERSION >= (20160603)
static BlockDriver bdrv_iser = {
    .format_name     = "iser",
    .protocol_name   = "iser",

    .instance_size          = sizeof(IscsiLun),
    .bdrv_parse_filename    = iscsi_parse_filename,
    .bdrv_file_open         = iscsi_open,
    .bdrv_close             = iscsi_close,
    .bdrv_co_create_opts    = bdrv_co_create_opts_simple,
    .create_opts            = &bdrv_create_opts_simple,
    .bdrv_reopen_prepare    = iscsi_reopen_prepare,
    .bdrv_reopen_commit     = iscsi_reopen_commit,
    .bdrv_co_invalidate_cache  = iscsi_co_invalidate_cache,

    .bdrv_getlength  = iscsi_getlength,
    .bdrv_get_info   = iscsi_get_info,
    .bdrv_co_truncate    = iscsi_co_truncate,
    .bdrv_refresh_limits = iscsi_refresh_limits,

    .bdrv_co_block_status  = iscsi_co_block_status,
    .bdrv_co_pdiscard      = iscsi_co_pdiscard,
    .bdrv_co_copy_range_from = iscsi_co_copy_range_from,
    .bdrv_co_copy_range_to  = iscsi_co_copy_range_to,
    .bdrv_co_pwrite_zeroes = iscsi_co_pwrite_zeroes,
    .bdrv_co_readv         = iscsi_co_readv,
    .bdrv_co_writev        = iscsi_co_writev,
    .bdrv_co_flush_to_disk = iscsi_co_flush,

#ifdef __linux__
    .bdrv_aio_ioctl   = iscsi_aio_ioctl,
#endif

    .bdrv_detach_aio_context = iscsi_detach_aio_context,
    .bdrv_attach_aio_context = iscsi_attach_aio_context,

    .strong_runtime_opts = iscsi_strong_runtime_opts,
};
#endif

static void iscsi_block_init(void)
{
    bdrv_register(&bdrv_iscsi);
#if LIBISCSI_API_VERSION >= (20160603)
    bdrv_register(&bdrv_iser);
#endif
}

block_init(iscsi_block_init);