Linux preempt-rt

Check our new training course

Real-Time Linux with PREEMPT_RT

Check our new training course
with Creative Commons CC-BY-SA
lecture and lab materials

Bootlin logo

Elixir Cross Referencer

   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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2009, Microsoft Corporation.
 *
 * Authors:
 *   Haiyang Zhang <haiyangz@microsoft.com>
 *   Hank Janssen  <hjanssen@microsoft.com>
 *   K. Y. Srinivasan <kys@microsoft.com>
 */

#include <linux/kernel.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <linux/completion.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/hyperv.h>
#include <linux/blkdev.h>
#include <linux/dma-mapping.h>

#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_tcq.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_devinfo.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_transport_fc.h>
#include <scsi/scsi_transport.h>

/*
 * All wire protocol details (storage protocol between the guest and the host)
 * are consolidated here.
 *
 * Begin protocol definitions.
 */

/*
 * Version history:
 * V1 Beta: 0.1
 * V1 RC < 2008/1/31: 1.0
 * V1 RC > 2008/1/31:  2.0
 * Win7: 4.2
 * Win8: 5.1
 * Win8.1: 6.0
 * Win10: 6.2
 */

#define VMSTOR_PROTO_VERSION(MAJOR_, MINOR_)	((((MAJOR_) & 0xff) << 8) | \
						(((MINOR_) & 0xff)))

#define VMSTOR_PROTO_VERSION_WIN6	VMSTOR_PROTO_VERSION(2, 0)
#define VMSTOR_PROTO_VERSION_WIN7	VMSTOR_PROTO_VERSION(4, 2)
#define VMSTOR_PROTO_VERSION_WIN8	VMSTOR_PROTO_VERSION(5, 1)
#define VMSTOR_PROTO_VERSION_WIN8_1	VMSTOR_PROTO_VERSION(6, 0)
#define VMSTOR_PROTO_VERSION_WIN10	VMSTOR_PROTO_VERSION(6, 2)

/*  Packet structure describing virtual storage requests. */
enum vstor_packet_operation {
	VSTOR_OPERATION_COMPLETE_IO		= 1,
	VSTOR_OPERATION_REMOVE_DEVICE		= 2,
	VSTOR_OPERATION_EXECUTE_SRB		= 3,
	VSTOR_OPERATION_RESET_LUN		= 4,
	VSTOR_OPERATION_RESET_ADAPTER		= 5,
	VSTOR_OPERATION_RESET_BUS		= 6,
	VSTOR_OPERATION_BEGIN_INITIALIZATION	= 7,
	VSTOR_OPERATION_END_INITIALIZATION	= 8,
	VSTOR_OPERATION_QUERY_PROTOCOL_VERSION	= 9,
	VSTOR_OPERATION_QUERY_PROPERTIES	= 10,
	VSTOR_OPERATION_ENUMERATE_BUS		= 11,
	VSTOR_OPERATION_FCHBA_DATA              = 12,
	VSTOR_OPERATION_CREATE_SUB_CHANNELS     = 13,
	VSTOR_OPERATION_MAXIMUM                 = 13
};

/*
 * WWN packet for Fibre Channel HBA
 */

struct hv_fc_wwn_packet {
	u8	primary_active;
	u8	reserved1[3];
	u8	primary_port_wwn[8];
	u8	primary_node_wwn[8];
	u8	secondary_port_wwn[8];
	u8	secondary_node_wwn[8];
};



/*
 * SRB Flag Bits
 */

#define SRB_FLAGS_QUEUE_ACTION_ENABLE		0x00000002
#define SRB_FLAGS_DISABLE_DISCONNECT		0x00000004
#define SRB_FLAGS_DISABLE_SYNCH_TRANSFER	0x00000008
#define SRB_FLAGS_BYPASS_FROZEN_QUEUE		0x00000010
#define SRB_FLAGS_DISABLE_AUTOSENSE		0x00000020
#define SRB_FLAGS_DATA_IN			0x00000040
#define SRB_FLAGS_DATA_OUT			0x00000080
#define SRB_FLAGS_NO_DATA_TRANSFER		0x00000000
#define SRB_FLAGS_UNSPECIFIED_DIRECTION	(SRB_FLAGS_DATA_IN | SRB_FLAGS_DATA_OUT)
#define SRB_FLAGS_NO_QUEUE_FREEZE		0x00000100
#define SRB_FLAGS_ADAPTER_CACHE_ENABLE		0x00000200
#define SRB_FLAGS_FREE_SENSE_BUFFER		0x00000400

/*
 * This flag indicates the request is part of the workflow for processing a D3.
 */
#define SRB_FLAGS_D3_PROCESSING			0x00000800
#define SRB_FLAGS_IS_ACTIVE			0x00010000
#define SRB_FLAGS_ALLOCATED_FROM_ZONE		0x00020000
#define SRB_FLAGS_SGLIST_FROM_POOL		0x00040000
#define SRB_FLAGS_BYPASS_LOCKED_QUEUE		0x00080000
#define SRB_FLAGS_NO_KEEP_AWAKE			0x00100000
#define SRB_FLAGS_PORT_DRIVER_ALLOCSENSE	0x00200000
#define SRB_FLAGS_PORT_DRIVER_SENSEHASPORT	0x00400000
#define SRB_FLAGS_DONT_START_NEXT_PACKET	0x00800000
#define SRB_FLAGS_PORT_DRIVER_RESERVED		0x0F000000
#define SRB_FLAGS_CLASS_DRIVER_RESERVED		0xF0000000

#define SP_UNTAGGED			((unsigned char) ~0)
#define SRB_SIMPLE_TAG_REQUEST		0x20

/*
 * Platform neutral description of a scsi request -
 * this remains the same across the write regardless of 32/64 bit
 * note: it's patterned off the SCSI_PASS_THROUGH structure
 */
#define STORVSC_MAX_CMD_LEN			0x10

#define POST_WIN7_STORVSC_SENSE_BUFFER_SIZE	0x14
#define PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE	0x12

#define STORVSC_SENSE_BUFFER_SIZE		0x14
#define STORVSC_MAX_BUF_LEN_WITH_PADDING	0x14

/*
 * Sense buffer size changed in win8; have a run-time
 * variable to track the size we should use.  This value will
 * likely change during protocol negotiation but it is valid
 * to start by assuming pre-Win8.
 */
static int sense_buffer_size = PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE;

/*
 * The storage protocol version is determined during the
 * initial exchange with the host.  It will indicate which
 * storage functionality is available in the host.
*/
static int vmstor_proto_version;

#define STORVSC_LOGGING_NONE	0
#define STORVSC_LOGGING_ERROR	1
#define STORVSC_LOGGING_WARN	2

static int logging_level = STORVSC_LOGGING_ERROR;
module_param(logging_level, int, S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(logging_level,
	"Logging level, 0 - None, 1 - Error (default), 2 - Warning.");

static inline bool do_logging(int level)
{
	return logging_level >= level;
}

#define storvsc_log(dev, level, fmt, ...)			\
do {								\
	if (do_logging(level))					\
		dev_warn(&(dev)->device, fmt, ##__VA_ARGS__);	\
} while (0)

struct vmscsi_win8_extension {
	/*
	 * The following were added in Windows 8
	 */
	u16 reserve;
	u8  queue_tag;
	u8  queue_action;
	u32 srb_flags;
	u32 time_out_value;
	u32 queue_sort_ey;
} __packed;

struct vmscsi_request {
	u16 length;
	u8 srb_status;
	u8 scsi_status;

	u8  port_number;
	u8  path_id;
	u8  target_id;
	u8  lun;

	u8  cdb_length;
	u8  sense_info_length;
	u8  data_in;
	u8  reserved;

	u32 data_transfer_length;

	union {
		u8 cdb[STORVSC_MAX_CMD_LEN];
		u8 sense_data[STORVSC_SENSE_BUFFER_SIZE];
		u8 reserved_array[STORVSC_MAX_BUF_LEN_WITH_PADDING];
	};
	/*
	 * The following was added in win8.
	 */
	struct vmscsi_win8_extension win8_extension;

} __attribute((packed));

/*
 * The list of storage protocols in order of preference.
 */
struct vmstor_protocol {
	int protocol_version;
	int sense_buffer_size;
	int vmscsi_size_delta;
};


static const struct vmstor_protocol vmstor_protocols[] = {
	{
		VMSTOR_PROTO_VERSION_WIN10,
		POST_WIN7_STORVSC_SENSE_BUFFER_SIZE,
		0
	},
	{
		VMSTOR_PROTO_VERSION_WIN8_1,
		POST_WIN7_STORVSC_SENSE_BUFFER_SIZE,
		0
	},
	{
		VMSTOR_PROTO_VERSION_WIN8,
		POST_WIN7_STORVSC_SENSE_BUFFER_SIZE,
		0
	},
	{
		VMSTOR_PROTO_VERSION_WIN7,
		PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE,
		sizeof(struct vmscsi_win8_extension),
	},
	{
		VMSTOR_PROTO_VERSION_WIN6,
		PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE,
		sizeof(struct vmscsi_win8_extension),
	}
};


/*
 * This structure is sent during the initialization phase to get the different
 * properties of the channel.
 */

#define STORAGE_CHANNEL_SUPPORTS_MULTI_CHANNEL		0x1

struct vmstorage_channel_properties {
	u32 reserved;
	u16 max_channel_cnt;
	u16 reserved1;

	u32 flags;
	u32   max_transfer_bytes;

	u64  reserved2;
} __packed;

/*  This structure is sent during the storage protocol negotiations. */
struct vmstorage_protocol_version {
	/* Major (MSW) and minor (LSW) version numbers. */
	u16 major_minor;

	/*
	 * Revision number is auto-incremented whenever this file is changed
	 * (See FILL_VMSTOR_REVISION macro above).  Mismatch does not
	 * definitely indicate incompatibility--but it does indicate mismatched
	 * builds.
	 * This is only used on the windows side. Just set it to 0.
	 */
	u16 revision;
} __packed;

/* Channel Property Flags */
#define STORAGE_CHANNEL_REMOVABLE_FLAG		0x1
#define STORAGE_CHANNEL_EMULATED_IDE_FLAG	0x2

struct vstor_packet {
	/* Requested operation type */
	enum vstor_packet_operation operation;

	/*  Flags - see below for values */
	u32 flags;

	/* Status of the request returned from the server side. */
	u32 status;

	/* Data payload area */
	union {
		/*
		 * Structure used to forward SCSI commands from the
		 * client to the server.
		 */
		struct vmscsi_request vm_srb;

		/* Structure used to query channel properties. */
		struct vmstorage_channel_properties storage_channel_properties;

		/* Used during version negotiations. */
		struct vmstorage_protocol_version version;

		/* Fibre channel address packet */
		struct hv_fc_wwn_packet wwn_packet;

		/* Number of sub-channels to create */
		u16 sub_channel_count;

		/* This will be the maximum of the union members */
		u8  buffer[0x34];
	};
} __packed;

/*
 * Packet Flags:
 *
 * This flag indicates that the server should send back a completion for this
 * packet.
 */

#define REQUEST_COMPLETION_FLAG	0x1

/* Matches Windows-end */
enum storvsc_request_type {
	WRITE_TYPE = 0,
	READ_TYPE,
	UNKNOWN_TYPE,
};

/*
 * SRB status codes and masks; a subset of the codes used here.
 */

#define SRB_STATUS_AUTOSENSE_VALID	0x80
#define SRB_STATUS_QUEUE_FROZEN		0x40
#define SRB_STATUS_INVALID_LUN	0x20
#define SRB_STATUS_SUCCESS	0x01
#define SRB_STATUS_ABORTED	0x02
#define SRB_STATUS_ERROR	0x04
#define SRB_STATUS_DATA_OVERRUN	0x12

#define SRB_STATUS(status) \
	(status & ~(SRB_STATUS_AUTOSENSE_VALID | SRB_STATUS_QUEUE_FROZEN))
/*
 * This is the end of Protocol specific defines.
 */

static int storvsc_ringbuffer_size = (128 * 1024);
static u32 max_outstanding_req_per_channel;
static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth);

static int storvsc_vcpus_per_sub_channel = 4;
static unsigned int storvsc_max_hw_queues;

module_param(storvsc_ringbuffer_size, int, S_IRUGO);
MODULE_PARM_DESC(storvsc_ringbuffer_size, "Ring buffer size (bytes)");

module_param(storvsc_max_hw_queues, uint, 0644);
MODULE_PARM_DESC(storvsc_max_hw_queues, "Maximum number of hardware queues");

module_param(storvsc_vcpus_per_sub_channel, int, S_IRUGO);
MODULE_PARM_DESC(storvsc_vcpus_per_sub_channel, "Ratio of VCPUs to subchannels");

static int ring_avail_percent_lowater = 10;
module_param(ring_avail_percent_lowater, int, S_IRUGO);
MODULE_PARM_DESC(ring_avail_percent_lowater,
		"Select a channel if available ring size > this in percent");

/*
 * Timeout in seconds for all devices managed by this driver.
 */
static int storvsc_timeout = 180;

#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
static struct scsi_transport_template *fc_transport_template;
#endif

static struct scsi_host_template scsi_driver;
static void storvsc_on_channel_callback(void *context);

#define STORVSC_MAX_LUNS_PER_TARGET			255
#define STORVSC_MAX_TARGETS				2
#define STORVSC_MAX_CHANNELS				8

#define STORVSC_FC_MAX_LUNS_PER_TARGET			255
#define STORVSC_FC_MAX_TARGETS				128
#define STORVSC_FC_MAX_CHANNELS				8

#define STORVSC_IDE_MAX_LUNS_PER_TARGET			64
#define STORVSC_IDE_MAX_TARGETS				1
#define STORVSC_IDE_MAX_CHANNELS			1

/*
 * Upper bound on the size of a storvsc packet. vmscsi_size_delta is not
 * included in the calculation because it is set after STORVSC_MAX_PKT_SIZE
 * is used in storvsc_connect_to_vsp
 */
#define STORVSC_MAX_PKT_SIZE (sizeof(struct vmpacket_descriptor) +\
			      sizeof(struct vstor_packet))

struct storvsc_cmd_request {
	struct scsi_cmnd *cmd;

	struct hv_device *device;

	/* Synchronize the request/response if needed */
	struct completion wait_event;

	struct vmbus_channel_packet_multipage_buffer mpb;
	struct vmbus_packet_mpb_array *payload;
	u32 payload_sz;

	struct vstor_packet vstor_packet;
};


/* A storvsc device is a device object that contains a vmbus channel */
struct storvsc_device {
	struct hv_device *device;

	bool	 destroy;
	bool	 drain_notify;
	atomic_t num_outstanding_req;
	struct Scsi_Host *host;

	wait_queue_head_t waiting_to_drain;

	/*
	 * Each unique Port/Path/Target represents 1 channel ie scsi
	 * controller. In reality, the pathid, targetid is always 0
	 * and the port is set by us
	 */
	unsigned int port_number;
	unsigned char path_id;
	unsigned char target_id;

	/*
	 * The size of the vmscsi_request has changed in win8. The
	 * additional size is because of new elements added to the
	 * structure. These elements are valid only when we are talking
	 * to a win8 host.
	 * Track the correction to size we need to apply. This value
	 * will likely change during protocol negotiation but it is
	 * valid to start by assuming pre-Win8.
	 */
	int vmscsi_size_delta;

	/*
	 * Max I/O, the device can support.
	 */
	u32   max_transfer_bytes;
	/*
	 * Number of sub-channels we will open.
	 */
	u16 num_sc;
	struct vmbus_channel **stor_chns;
	/*
	 * Mask of CPUs bound to subchannels.
	 */
	struct cpumask alloced_cpus;
	/*
	 * Serializes modifications of stor_chns[] from storvsc_do_io()
	 * and storvsc_change_target_cpu().
	 */
	spinlock_t lock;
	/* Used for vsc/vsp channel reset process */
	struct storvsc_cmd_request init_request;
	struct storvsc_cmd_request reset_request;
	/*
	 * Currently active port and node names for FC devices.
	 */
	u64 node_name;
	u64 port_name;
#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
	struct fc_rport *rport;
#endif
};

struct hv_host_device {
	struct hv_device *dev;
	unsigned int port;
	unsigned char path;
	unsigned char target;
	struct workqueue_struct *handle_error_wq;
	struct work_struct host_scan_work;
	struct Scsi_Host *host;
};

struct storvsc_scan_work {
	struct work_struct work;
	struct Scsi_Host *host;
	u8 lun;
	u8 tgt_id;
};

static void storvsc_device_scan(struct work_struct *work)
{
	struct storvsc_scan_work *wrk;
	struct scsi_device *sdev;

	wrk = container_of(work, struct storvsc_scan_work, work);

	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);
	if (!sdev)
		goto done;
	scsi_rescan_device(&sdev->sdev_gendev);
	scsi_device_put(sdev);

done:
	kfree(wrk);
}

static void storvsc_host_scan(struct work_struct *work)
{
	struct Scsi_Host *host;
	struct scsi_device *sdev;
	struct hv_host_device *host_device =
		container_of(work, struct hv_host_device, host_scan_work);

	host = host_device->host;
	/*
	 * Before scanning the host, first check to see if any of the
	 * currrently known devices have been hot removed. We issue a
	 * "unit ready" command against all currently known devices.
	 * This I/O will result in an error for devices that have been
	 * removed. As part of handling the I/O error, we remove the device.
	 *
	 * When a LUN is added or removed, the host sends us a signal to
	 * scan the host. Thus we are forced to discover the LUNs that
	 * may have been removed this way.
	 */
	mutex_lock(&host->scan_mutex);
	shost_for_each_device(sdev, host)
		scsi_test_unit_ready(sdev, 1, 1, NULL);
	mutex_unlock(&host->scan_mutex);
	/*
	 * Now scan the host to discover LUNs that may have been added.
	 */
	scsi_scan_host(host);
}

static void storvsc_remove_lun(struct work_struct *work)
{
	struct storvsc_scan_work *wrk;
	struct scsi_device *sdev;

	wrk = container_of(work, struct storvsc_scan_work, work);
	if (!scsi_host_get(wrk->host))
		goto done;

	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);

	if (sdev) {
		scsi_remove_device(sdev);
		scsi_device_put(sdev);
	}
	scsi_host_put(wrk->host);

done:
	kfree(wrk);
}


/*
 * We can get incoming messages from the host that are not in response to
 * messages that we have sent out. An example of this would be messages
 * received by the guest to notify dynamic addition/removal of LUNs. To
 * deal with potential race conditions where the driver may be in the
 * midst of being unloaded when we might receive an unsolicited message
 * from the host, we have implemented a mechanism to gurantee sequential
 * consistency:
 *
 * 1) Once the device is marked as being destroyed, we will fail all
 *    outgoing messages.
 * 2) We permit incoming messages when the device is being destroyed,
 *    only to properly account for messages already sent out.
 */

static inline struct storvsc_device *get_out_stor_device(
					struct hv_device *device)
{
	struct storvsc_device *stor_device;

	stor_device = hv_get_drvdata(device);

	if (stor_device && stor_device->destroy)
		stor_device = NULL;

	return stor_device;
}


static inline void storvsc_wait_to_drain(struct storvsc_device *dev)
{
	dev->drain_notify = true;
	wait_event(dev->waiting_to_drain,
		   atomic_read(&dev->num_outstanding_req) == 0);
	dev->drain_notify = false;
}

static inline struct storvsc_device *get_in_stor_device(
					struct hv_device *device)
{
	struct storvsc_device *stor_device;

	stor_device = hv_get_drvdata(device);

	if (!stor_device)
		goto get_in_err;

	/*
	 * If the device is being destroyed; allow incoming
	 * traffic only to cleanup outstanding requests.
	 */

	if (stor_device->destroy  &&
		(atomic_read(&stor_device->num_outstanding_req) == 0))
		stor_device = NULL;

get_in_err:
	return stor_device;

}

static void storvsc_change_target_cpu(struct vmbus_channel *channel, u32 old,
				      u32 new)
{
	struct storvsc_device *stor_device;
	struct vmbus_channel *cur_chn;
	bool old_is_alloced = false;
	struct hv_device *device;
	unsigned long flags;
	int cpu;

	device = channel->primary_channel ?
			channel->primary_channel->device_obj
				: channel->device_obj;
	stor_device = get_out_stor_device(device);
	if (!stor_device)
		return;

	/* See storvsc_do_io() -> get_og_chn(). */
	spin_lock_irqsave(&stor_device->lock, flags);

	/*
	 * Determines if the storvsc device has other channels assigned to
	 * the "old" CPU to update the alloced_cpus mask and the stor_chns
	 * array.
	 */
	if (device->channel != channel && device->channel->target_cpu == old) {
		cur_chn = device->channel;
		old_is_alloced = true;
		goto old_is_alloced;
	}
	list_for_each_entry(cur_chn, &device->channel->sc_list, sc_list) {
		if (cur_chn == channel)
			continue;
		if (cur_chn->target_cpu == old) {
			old_is_alloced = true;
			goto old_is_alloced;
		}
	}

old_is_alloced:
	if (old_is_alloced)
		WRITE_ONCE(stor_device->stor_chns[old], cur_chn);
	else
		cpumask_clear_cpu(old, &stor_device->alloced_cpus);

	/* "Flush" the stor_chns array. */
	for_each_possible_cpu(cpu) {
		if (stor_device->stor_chns[cpu] && !cpumask_test_cpu(
					cpu, &stor_device->alloced_cpus))
			WRITE_ONCE(stor_device->stor_chns[cpu], NULL);
	}

	WRITE_ONCE(stor_device->stor_chns[new], channel);
	cpumask_set_cpu(new, &stor_device->alloced_cpus);

	spin_unlock_irqrestore(&stor_device->lock, flags);
}

static u64 storvsc_next_request_id(struct vmbus_channel *channel, u64 rqst_addr)
{
	struct storvsc_cmd_request *request =
		(struct storvsc_cmd_request *)(unsigned long)rqst_addr;

	if (rqst_addr == VMBUS_RQST_INIT)
		return VMBUS_RQST_INIT;
	if (rqst_addr == VMBUS_RQST_RESET)
		return VMBUS_RQST_RESET;

	/*
	 * Cannot return an ID of 0, which is reserved for an unsolicited
	 * message from Hyper-V.
	 */
	return (u64)blk_mq_unique_tag(scsi_cmd_to_rq(request->cmd)) + 1;
}

static void handle_sc_creation(struct vmbus_channel *new_sc)
{
	struct hv_device *device = new_sc->primary_channel->device_obj;
	struct device *dev = &device->device;
	struct storvsc_device *stor_device;
	struct vmstorage_channel_properties props;
	int ret;

	stor_device = get_out_stor_device(device);
	if (!stor_device)
		return;

	memset(&props, 0, sizeof(struct vmstorage_channel_properties));
	new_sc->max_pkt_size = STORVSC_MAX_PKT_SIZE;

	new_sc->next_request_id_callback = storvsc_next_request_id;

	ret = vmbus_open(new_sc,
			 storvsc_ringbuffer_size,
			 storvsc_ringbuffer_size,
			 (void *)&props,
			 sizeof(struct vmstorage_channel_properties),
			 storvsc_on_channel_callback, new_sc);

	/* In case vmbus_open() fails, we don't use the sub-channel. */
	if (ret != 0) {
		dev_err(dev, "Failed to open sub-channel: err=%d\n", ret);
		return;
	}

	new_sc->change_target_cpu_callback = storvsc_change_target_cpu;

	/* Add the sub-channel to the array of available channels. */
	stor_device->stor_chns[new_sc->target_cpu] = new_sc;
	cpumask_set_cpu(new_sc->target_cpu, &stor_device->alloced_cpus);
}

static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
{
	struct device *dev = &device->device;
	struct storvsc_device *stor_device;
	int num_sc;
	struct storvsc_cmd_request *request;
	struct vstor_packet *vstor_packet;
	int ret, t;

	/*
	 * If the number of CPUs is artificially restricted, such as
	 * with maxcpus=1 on the kernel boot line, Hyper-V could offer
	 * sub-channels >= the number of CPUs. These sub-channels
	 * should not be created. The primary channel is already created
	 * and assigned to one CPU, so check against # CPUs - 1.
	 */
	num_sc = min((int)(num_online_cpus() - 1), max_chns);
	if (!num_sc)
		return;

	stor_device = get_out_stor_device(device);
	if (!stor_device)
		return;

	stor_device->num_sc = num_sc;
	request = &stor_device->init_request;
	vstor_packet = &request->vstor_packet;

	/*
	 * Establish a handler for dealing with subchannels.
	 */
	vmbus_set_sc_create_callback(device->channel, handle_sc_creation);

	/*
	 * Request the host to create sub-channels.
	 */
	memset(request, 0, sizeof(struct storvsc_cmd_request));
	init_completion(&request->wait_event);
	vstor_packet->operation = VSTOR_OPERATION_CREATE_SUB_CHANNELS;
	vstor_packet->flags = REQUEST_COMPLETION_FLAG;
	vstor_packet->sub_channel_count = num_sc;

	ret = vmbus_sendpacket(device->channel, vstor_packet,
			       (sizeof(struct vstor_packet) -
			       stor_device->vmscsi_size_delta),
			       VMBUS_RQST_INIT,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);

	if (ret != 0) {
		dev_err(dev, "Failed to create sub-channel: err=%d\n", ret);
		return;
	}

	t = wait_for_completion_timeout(&request->wait_event, 10*HZ);
	if (t == 0) {
		dev_err(dev, "Failed to create sub-channel: timed out\n");
		return;
	}

	if (vstor_packet->operation != VSTOR_OPERATION_COMPLETE_IO ||
	    vstor_packet->status != 0) {
		dev_err(dev, "Failed to create sub-channel: op=%d, sts=%d\n",
			vstor_packet->operation, vstor_packet->status);
		return;
	}

	/*
	 * We need to do nothing here, because vmbus_process_offer()
	 * invokes channel->sc_creation_callback, which will open and use
	 * the sub-channel(s).
	 */
}

static void cache_wwn(struct storvsc_device *stor_device,
		      struct vstor_packet *vstor_packet)
{
	/*
	 * Cache the currently active port and node ww names.
	 */
	if (vstor_packet->wwn_packet.primary_active) {
		stor_device->node_name =
			wwn_to_u64(vstor_packet->wwn_packet.primary_node_wwn);
		stor_device->port_name =
			wwn_to_u64(vstor_packet->wwn_packet.primary_port_wwn);
	} else {
		stor_device->node_name =
			wwn_to_u64(vstor_packet->wwn_packet.secondary_node_wwn);
		stor_device->port_name =
			wwn_to_u64(vstor_packet->wwn_packet.secondary_port_wwn);
	}
}


static int storvsc_execute_vstor_op(struct hv_device *device,
				    struct storvsc_cmd_request *request,
				    bool status_check)
{
	struct storvsc_device *stor_device;
	struct vstor_packet *vstor_packet;
	int ret, t;

	stor_device = get_out_stor_device(device);
	if (!stor_device)
		return -ENODEV;

	vstor_packet = &request->vstor_packet;

	init_completion(&request->wait_event);
	vstor_packet->flags = REQUEST_COMPLETION_FLAG;

	ret = vmbus_sendpacket(device->channel, vstor_packet,
			       (sizeof(struct vstor_packet) -
			       stor_device->vmscsi_size_delta),
			       VMBUS_RQST_INIT,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret != 0)
		return ret;

	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
	if (t == 0)
		return -ETIMEDOUT;

	if (!status_check)
		return ret;

	if (vstor_packet->operation != VSTOR_OPERATION_COMPLETE_IO ||
	    vstor_packet->status != 0)
		return -EINVAL;

	return ret;
}

static int storvsc_channel_init(struct hv_device *device, bool is_fc)
{
	struct storvsc_device *stor_device;
	struct storvsc_cmd_request *request;
	struct vstor_packet *vstor_packet;
	int ret, i;
	int max_chns;
	bool process_sub_channels = false;

	stor_device = get_out_stor_device(device);
	if (!stor_device)
		return -ENODEV;

	request = &stor_device->init_request;
	vstor_packet = &request->vstor_packet;

	/*
	 * Now, initiate the vsc/vsp initialization protocol on the open
	 * channel
	 */
	memset(request, 0, sizeof(struct storvsc_cmd_request));
	vstor_packet->operation = VSTOR_OPERATION_BEGIN_INITIALIZATION;
	ret = storvsc_execute_vstor_op(device, request, true);
	if (ret)
		return ret;
	/*
	 * Query host supported protocol version.
	 */

	for (i = 0; i < ARRAY_SIZE(vmstor_protocols); i++) {
		/* reuse the packet for version range supported */
		memset(vstor_packet, 0, sizeof(struct vstor_packet));
		vstor_packet->operation =
			VSTOR_OPERATION_QUERY_PROTOCOL_VERSION;

		vstor_packet->version.major_minor =
			vmstor_protocols[i].protocol_version;

		/*
		 * The revision number is only used in Windows; set it to 0.
		 */
		vstor_packet->version.revision = 0;
		ret = storvsc_execute_vstor_op(device, request, false);
		if (ret != 0)
			return ret;

		if (vstor_packet->operation != VSTOR_OPERATION_COMPLETE_IO)
			return -EINVAL;

		if (vstor_packet->status == 0) {
			vmstor_proto_version =
				vmstor_protocols[i].protocol_version;

			sense_buffer_size =
				vmstor_protocols[i].sense_buffer_size;

			stor_device->vmscsi_size_delta =
				vmstor_protocols[i].vmscsi_size_delta;

			break;
		}
	}

	if (vstor_packet->status != 0)
		return -EINVAL;


	memset(vstor_packet, 0, sizeof(struct vstor_packet));
	vstor_packet->operation = VSTOR_OPERATION_QUERY_PROPERTIES;
	ret = storvsc_execute_vstor_op(device, request, true);
	if (ret != 0)
		return ret;

	/*
	 * Check to see if multi-channel support is there.
	 * Hosts that implement protocol version of 5.1 and above
	 * support multi-channel.
	 */
	max_chns = vstor_packet->storage_channel_properties.max_channel_cnt;

	/*
	 * Allocate state to manage the sub-channels.
	 * We allocate an array based on the numbers of possible CPUs
	 * (Hyper-V does not support cpu online/offline).
	 * This Array will be sparseley populated with unique
	 * channels - primary + sub-channels.
	 * We will however populate all the slots to evenly distribute
	 * the load.
	 */
	stor_device->stor_chns = kcalloc(num_possible_cpus(), sizeof(void *),
					 GFP_KERNEL);
	if (stor_device->stor_chns == NULL)
		return -ENOMEM;

	device->channel->change_target_cpu_callback = storvsc_change_target_cpu;

	stor_device->stor_chns[device->channel->target_cpu] = device->channel;
	cpumask_set_cpu(device->channel->target_cpu,
			&stor_device->alloced_cpus);

	if (vmstor_proto_version >= VMSTOR_PROTO_VERSION_WIN8) {
		if (vstor_packet->storage_channel_properties.flags &
		    STORAGE_CHANNEL_SUPPORTS_MULTI_CHANNEL)
			process_sub_channels = true;
	}
	stor_device->max_transfer_bytes =
		vstor_packet->storage_channel_properties.max_transfer_bytes;

	if (!is_fc)
		goto done;

	/*
	 * For FC devices retrieve FC HBA data.
	 */
	memset(vstor_packet, 0, sizeof(struct vstor_packet));
	vstor_packet->operation = VSTOR_OPERATION_FCHBA_DATA;
	ret = storvsc_execute_vstor_op(device, request, true);
	if (ret != 0)
		return ret;

	/*
	 * Cache the currently active port and node ww names.
	 */
	cache_wwn(stor_device, vstor_packet);

done:

	memset(vstor_packet, 0, sizeof(struct vstor_packet));
	vstor_packet->operation = VSTOR_OPERATION_END_INITIALIZATION;
	ret = storvsc_execute_vstor_op(device, request, true);
	if (ret != 0)
		return ret;

	if (process_sub_channels)
		handle_multichannel_storage(device, max_chns);

	return ret;
}

static void storvsc_handle_error(struct vmscsi_request *vm_srb,
				struct scsi_cmnd *scmnd,
				struct Scsi_Host *host,
				u8 asc, u8 ascq)
{
	struct storvsc_scan_work *wrk;
	void (*process_err_fn)(struct work_struct *work);
	struct hv_host_device *host_dev = shost_priv(host);

	/*
	 * In some situations, Hyper-V sets multiple bits in the
	 * srb_status, such as ABORTED and ERROR. So process them
	 * individually, with the most specific bits first.
	 */

	if (vm_srb->srb_status & SRB_STATUS_INVALID_LUN) {
		set_host_byte(scmnd, DID_NO_CONNECT);
		process_err_fn = storvsc_remove_lun;
		goto do_work;
	}

	if (vm_srb->srb_status & SRB_STATUS_ABORTED) {
		if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID &&
		    /* Capacity data has changed */
		    (asc == 0x2a) && (ascq == 0x9)) {
			process_err_fn = storvsc_device_scan;
			/*
			 * Retry the I/O that triggered this.
			 */
			set_host_byte(scmnd, DID_REQUEUE);
			goto do_work;
		}
	}

	if (vm_srb->srb_status & SRB_STATUS_ERROR) {
		/*
		 * Let upper layer deal with error when
		 * sense message is present.
		 */
		if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID)
			return;

		/*
		 * If there is an error; offline the device since all
		 * error recovery strategies would have already been
		 * deployed on the host side. However, if the command
		 * were a pass-through command deal with it appropriately.
		 */
		switch (scmnd->cmnd[0]) {
		case ATA_16:
		case ATA_12:
			set_host_byte(scmnd, DID_PASSTHROUGH);
			break;
		/*
		 * On some Hyper-V hosts TEST_UNIT_READY command can
		 * return SRB_STATUS_ERROR. Let the upper level code
		 * deal with it based on the sense information.
		 */
		case TEST_UNIT_READY:
			break;
		default:
			set_host_byte(scmnd, DID_ERROR);
		}
	}
	return;

do_work:
	/*
	 * We need to schedule work to process this error; schedule it.
	 */
	wrk = kmalloc(sizeof(struct storvsc_scan_work), GFP_ATOMIC);
	if (!wrk) {
		set_host_byte(scmnd, DID_TARGET_FAILURE);
		return;
	}

	wrk->host = host;
	wrk->lun = vm_srb->lun;
	wrk->tgt_id = vm_srb->target_id;
	INIT_WORK(&wrk->work, process_err_fn);
	queue_work(host_dev->handle_error_wq, &wrk->work);
}


static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request,
				       struct storvsc_device *stor_dev)
{
	struct scsi_cmnd *scmnd = cmd_request->cmd;
	struct scsi_sense_hdr sense_hdr;
	struct vmscsi_request *vm_srb;
	u32 data_transfer_length;
	struct Scsi_Host *host;
	u32 payload_sz = cmd_request->payload_sz;
	void *payload = cmd_request->payload;
	bool sense_ok;

	host = stor_dev->host;

	vm_srb = &cmd_request->vstor_packet.vm_srb;
	data_transfer_length = vm_srb->data_transfer_length;

	scmnd->result = vm_srb->scsi_status;

	if (scmnd->result) {
		sense_ok = scsi_normalize_sense(scmnd->sense_buffer,
				SCSI_SENSE_BUFFERSIZE, &sense_hdr);

		if (sense_ok && do_logging(STORVSC_LOGGING_WARN))
			scsi_print_sense_hdr(scmnd->device, "storvsc",
					     &sense_hdr);
	}

	if (vm_srb->srb_status != SRB_STATUS_SUCCESS) {
		storvsc_handle_error(vm_srb, scmnd, host, sense_hdr.asc,
					 sense_hdr.ascq);
		/*
		 * The Windows driver set data_transfer_length on
		 * SRB_STATUS_DATA_OVERRUN. On other errors, this value
		 * is untouched.  In these cases we set it to 0.
		 */
		if (vm_srb->srb_status != SRB_STATUS_DATA_OVERRUN)
			data_transfer_length = 0;
	}

	/* Validate data_transfer_length (from Hyper-V) */
	if (data_transfer_length > cmd_request->payload->range.len)
		data_transfer_length = cmd_request->payload->range.len;

	scsi_set_resid(scmnd,
		cmd_request->payload->range.len - data_transfer_length);

	scsi_done(scmnd);

	if (payload_sz >
		sizeof(struct vmbus_channel_packet_multipage_buffer))
		kfree(payload);
}

static void storvsc_on_io_completion(struct storvsc_device *stor_device,
				  struct vstor_packet *vstor_packet,
				  struct storvsc_cmd_request *request)
{
	struct vstor_packet *stor_pkt;
	struct hv_device *device = stor_device->device;

	stor_pkt = &request->vstor_packet;

	/*
	 * The current SCSI handling on the host side does
	 * not correctly handle:
	 * INQUIRY command with page code parameter set to 0x80
	 * MODE_SENSE command with cmd[2] == 0x1c
	 *
	 * Setup srb and scsi status so this won't be fatal.
	 * We do this so we can distinguish truly fatal failues
	 * (srb status == 0x4) and off-line the device in that case.
	 */

	if ((stor_pkt->vm_srb.cdb[0] == INQUIRY) ||
	   (stor_pkt->vm_srb.cdb[0] == MODE_SENSE)) {
		vstor_packet->vm_srb.scsi_status = 0;
		vstor_packet->vm_srb.srb_status = SRB_STATUS_SUCCESS;
	}

	/* Copy over the status...etc */
	stor_pkt->vm_srb.scsi_status = vstor_packet->vm_srb.scsi_status;
	stor_pkt->vm_srb.srb_status = vstor_packet->vm_srb.srb_status;

	/*
	 * Copy over the sense_info_length, but limit to the known max
	 * size if Hyper-V returns a bad value.
	 */
	stor_pkt->vm_srb.sense_info_length = min_t(u8, sense_buffer_size,
		vstor_packet->vm_srb.sense_info_length);

	if (vstor_packet->vm_srb.scsi_status != 0 ||
	    vstor_packet->vm_srb.srb_status != SRB_STATUS_SUCCESS) {

		/*
		 * Log TEST_UNIT_READY errors only as warnings. Hyper-V can
		 * return errors when detecting devices using TEST_UNIT_READY,
		 * and logging these as errors produces unhelpful noise.
		 */
		int loglevel = (stor_pkt->vm_srb.cdb[0] == TEST_UNIT_READY) ?
			STORVSC_LOGGING_WARN : STORVSC_LOGGING_ERROR;

		storvsc_log(device, loglevel,
			"tag#%d cmd 0x%x status: scsi 0x%x srb 0x%x hv 0x%x\n",
			scsi_cmd_to_rq(request->cmd)->tag,
			stor_pkt->vm_srb.cdb[0],
			vstor_packet->vm_srb.scsi_status,
			vstor_packet->vm_srb.srb_status,
			vstor_packet->status);
	}

	if (vstor_packet->vm_srb.scsi_status == SAM_STAT_CHECK_CONDITION &&
	    (vstor_packet->vm_srb.srb_status & SRB_STATUS_AUTOSENSE_VALID))
		memcpy(request->cmd->sense_buffer,
		       vstor_packet->vm_srb.sense_data,
		       stor_pkt->vm_srb.sense_info_length);

	stor_pkt->vm_srb.data_transfer_length =
		vstor_packet->vm_srb.data_transfer_length;

	storvsc_command_completion(request, stor_device);

	if (atomic_dec_and_test(&stor_device->num_outstanding_req) &&
		stor_device->drain_notify)
		wake_up(&stor_device->waiting_to_drain);
}

static void storvsc_on_receive(struct storvsc_device *stor_device,
			     struct vstor_packet *vstor_packet,
			     struct storvsc_cmd_request *request)
{
	struct hv_host_device *host_dev;
	switch (vstor_packet->operation) {
	case VSTOR_OPERATION_COMPLETE_IO:
		storvsc_on_io_completion(stor_device, vstor_packet, request);
		break;

	case VSTOR_OPERATION_REMOVE_DEVICE:
	case VSTOR_OPERATION_ENUMERATE_BUS:
		host_dev = shost_priv(stor_device->host);
		queue_work(
			host_dev->handle_error_wq, &host_dev->host_scan_work);
		break;

	case VSTOR_OPERATION_FCHBA_DATA:
		cache_wwn(stor_device, vstor_packet);
#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
		fc_host_node_name(stor_device->host) = stor_device->node_name;
		fc_host_port_name(stor_device->host) = stor_device->port_name;
#endif
		break;
	default:
		break;
	}
}

static void storvsc_on_channel_callback(void *context)
{
	struct vmbus_channel *channel = (struct vmbus_channel *)context;
	const struct vmpacket_descriptor *desc;
	struct hv_device *device;
	struct storvsc_device *stor_device;
	struct Scsi_Host *shost;

	if (channel->primary_channel != NULL)
		device = channel->primary_channel->device_obj;
	else
		device = channel->device_obj;

	stor_device = get_in_stor_device(device);
	if (!stor_device)
		return;

	shost = stor_device->host;

	foreach_vmbus_pkt(desc, channel) {
		struct vstor_packet *packet = hv_pkt_data(desc);
		struct storvsc_cmd_request *request = NULL;
		u32 pktlen = hv_pkt_datalen(desc);
		u64 rqst_id = desc->trans_id;
		u32 minlen = rqst_id ? sizeof(struct vstor_packet) -
			stor_device->vmscsi_size_delta : sizeof(enum vstor_packet_operation);

		if (pktlen < minlen) {
			dev_err(&device->device,
				"Invalid pkt: id=%llu, len=%u, minlen=%u\n",
				rqst_id, pktlen, minlen);
			continue;
		}

		if (rqst_id == VMBUS_RQST_INIT) {
			request = &stor_device->init_request;
		} else if (rqst_id == VMBUS_RQST_RESET) {
			request = &stor_device->reset_request;
		} else {
			/* Hyper-V can send an unsolicited message with ID of 0 */
			if (rqst_id == 0) {
				/*
				 * storvsc_on_receive() looks at the vstor_packet in the message
				 * from the ring buffer.
				 *
				 * - If the operation in the vstor_packet is COMPLETE_IO, then
				 *   we call storvsc_on_io_completion(), and dereference the
				 *   guest memory address.  Make sure we don't call
				 *   storvsc_on_io_completion() with a guest memory address
				 *   that is zero if Hyper-V were to construct and send such
				 *   a bogus packet.
				 *
				 * - If the operation in the vstor_packet is FCHBA_DATA, then
				 *   we call cache_wwn(), and access the data payload area of
				 *   the packet (wwn_packet); however, there is no guarantee
				 *   that the packet is big enough to contain such area.
				 *   Future-proof the code by rejecting such a bogus packet.
				 */
				if (packet->operation == VSTOR_OPERATION_COMPLETE_IO ||
				    packet->operation == VSTOR_OPERATION_FCHBA_DATA) {
					dev_err(&device->device, "Invalid packet with ID of 0\n");
					continue;
				}
			} else {
				struct scsi_cmnd *scmnd;

				/* Transaction 'rqst_id' corresponds to tag 'rqst_id - 1' */
				scmnd = scsi_host_find_tag(shost, rqst_id - 1);
				if (scmnd == NULL) {
					dev_err(&device->device, "Incorrect transaction ID\n");
					continue;
				}
				request = (struct storvsc_cmd_request *)scsi_cmd_priv(scmnd);
				scsi_dma_unmap(scmnd);
			}

			storvsc_on_receive(stor_device, packet, request);
			continue;
		}

		memcpy(&request->vstor_packet, packet,
		       (sizeof(struct vstor_packet) - stor_device->vmscsi_size_delta));
		complete(&request->wait_event);
	}
}

static int storvsc_connect_to_vsp(struct hv_device *device, u32 ring_size,
				  bool is_fc)
{
	struct vmstorage_channel_properties props;
	int ret;

	memset(&props, 0, sizeof(struct vmstorage_channel_properties));

	device->channel->max_pkt_size = STORVSC_MAX_PKT_SIZE;
	device->channel->next_request_id_callback = storvsc_next_request_id;

	ret = vmbus_open(device->channel,
			 ring_size,
			 ring_size,
			 (void *)&props,
			 sizeof(struct vmstorage_channel_properties),
			 storvsc_on_channel_callback, device->channel);

	if (ret != 0)
		return ret;

	ret = storvsc_channel_init(device, is_fc);

	return ret;
}

static int storvsc_dev_remove(struct hv_device *device)
{
	struct storvsc_device *stor_device;

	stor_device = hv_get_drvdata(device);

	stor_device->destroy = true;

	/* Make sure flag is set before waiting */
	wmb();

	/*
	 * At this point, all outbound traffic should be disable. We
	 * only allow inbound traffic (responses) to proceed so that
	 * outstanding requests can be completed.
	 */

	storvsc_wait_to_drain(stor_device);

	/*
	 * Since we have already drained, we don't need to busy wait
	 * as was done in final_release_stor_device()
	 * Note that we cannot set the ext pointer to NULL until
	 * we have drained - to drain the outgoing packets, we need to
	 * allow incoming packets.
	 */
	hv_set_drvdata(device, NULL);

	/* Close the channel */
	vmbus_close(device->channel);

	kfree(stor_device->stor_chns);
	kfree(stor_device);
	return 0;
}

static struct vmbus_channel *get_og_chn(struct storvsc_device *stor_device,
					u16 q_num)
{
	u16 slot = 0;
	u16 hash_qnum;
	const struct cpumask *node_mask;
	int num_channels, tgt_cpu;

	if (stor_device->num_sc == 0) {
		stor_device->stor_chns[q_num] = stor_device->device->channel;
		return stor_device->device->channel;
	}

	/*
	 * Our channel array is sparsley populated and we
	 * initiated I/O on a processor/hw-q that does not
	 * currently have a designated channel. Fix this.
	 * The strategy is simple:
	 * I. Ensure NUMA locality
	 * II. Distribute evenly (best effort)
	 */

	node_mask = cpumask_of_node(cpu_to_node(q_num));

	num_channels = 0;
	for_each_cpu(tgt_cpu, &stor_device->alloced_cpus) {
		if (cpumask_test_cpu(tgt_cpu, node_mask))
			num_channels++;
	}
	if (num_channels == 0) {
		stor_device->stor_chns[q_num] = stor_device->device->channel;
		return stor_device->device->channel;
	}

	hash_qnum = q_num;
	while (hash_qnum >= num_channels)
		hash_qnum -= num_channels;

	for_each_cpu(tgt_cpu, &stor_device->alloced_cpus) {
		if (!cpumask_test_cpu(tgt_cpu, node_mask))
			continue;
		if (slot == hash_qnum)
			break;
		slot++;
	}

	stor_device->stor_chns[q_num] = stor_device->stor_chns[tgt_cpu];

	return stor_device->stor_chns[q_num];
}


static int storvsc_do_io(struct hv_device *device,
			 struct storvsc_cmd_request *request, u16 q_num)
{
	struct storvsc_device *stor_device;
	struct vstor_packet *vstor_packet;
	struct vmbus_channel *outgoing_channel, *channel;
	unsigned long flags;
	int ret = 0;
	const struct cpumask *node_mask;
	int tgt_cpu;

	vstor_packet = &request->vstor_packet;
	stor_device = get_out_stor_device(device);

	if (!stor_device)
		return -ENODEV;


	request->device  = device;
	/*
	 * Select an appropriate channel to send the request out.
	 */
	/* See storvsc_change_target_cpu(). */
	outgoing_channel = READ_ONCE(stor_device->stor_chns[q_num]);
	if (outgoing_channel != NULL) {
		if (outgoing_channel->target_cpu == q_num) {
			/*
			 * Ideally, we want to pick a different channel if
			 * available on the same NUMA node.
			 */
			node_mask = cpumask_of_node(cpu_to_node(q_num));
			for_each_cpu_wrap(tgt_cpu,
				 &stor_device->alloced_cpus, q_num + 1) {
				if (!cpumask_test_cpu(tgt_cpu, node_mask))
					continue;
				if (tgt_cpu == q_num)
					continue;
				channel = READ_ONCE(
					stor_device->stor_chns[tgt_cpu]);
				if (channel == NULL)
					continue;
				if (hv_get_avail_to_write_percent(
							&channel->outbound)
						> ring_avail_percent_lowater) {
					outgoing_channel = channel;
					goto found_channel;
				}
			}

			/*
			 * All the other channels on the same NUMA node are
			 * busy. Try to use the channel on the current CPU
			 */
			if (hv_get_avail_to_write_percent(
						&outgoing_channel->outbound)
					> ring_avail_percent_lowater)
				goto found_channel;

			/*
			 * If we reach here, all the channels on the current
			 * NUMA node are busy. Try to find a channel in
			 * other NUMA nodes
			 */
			for_each_cpu(tgt_cpu, &stor_device->alloced_cpus) {
				if (cpumask_test_cpu(tgt_cpu, node_mask))
					continue;
				channel = READ_ONCE(
					stor_device->stor_chns[tgt_cpu]);
				if (channel == NULL)
					continue;
				if (hv_get_avail_to_write_percent(
							&channel->outbound)
						> ring_avail_percent_lowater) {
					outgoing_channel = channel;
					goto found_channel;
				}
			}
		}
	} else {
		spin_lock_irqsave(&stor_device->lock, flags);
		outgoing_channel = stor_device->stor_chns[q_num];
		if (outgoing_channel != NULL) {
			spin_unlock_irqrestore(&stor_device->lock, flags);
			goto found_channel;
		}
		outgoing_channel = get_og_chn(stor_device, q_num);
		spin_unlock_irqrestore(&stor_device->lock, flags);
	}

found_channel:
	vstor_packet->flags |= REQUEST_COMPLETION_FLAG;

	vstor_packet->vm_srb.length = (sizeof(struct vmscsi_request) -
					stor_device->vmscsi_size_delta);


	vstor_packet->vm_srb.sense_info_length = sense_buffer_size;


	vstor_packet->vm_srb.data_transfer_length =
	request->payload->range.len;

	vstor_packet->operation = VSTOR_OPERATION_EXECUTE_SRB;

	if (request->payload->range.len) {

		ret = vmbus_sendpacket_mpb_desc(outgoing_channel,
				request->payload, request->payload_sz,
				vstor_packet,
				(sizeof(struct vstor_packet) -
				stor_device->vmscsi_size_delta),
				(unsigned long)request);
	} else {
		ret = vmbus_sendpacket(outgoing_channel, vstor_packet,
			       (sizeof(struct vstor_packet) -
				stor_device->vmscsi_size_delta),
			       (unsigned long)request,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	}

	if (ret != 0)
		return ret;

	atomic_inc(&stor_device->num_outstanding_req);

	return ret;
}

static int storvsc_device_alloc(struct scsi_device *sdevice)
{
	/*
	 * Set blist flag to permit the reading of the VPD pages even when
	 * the target may claim SPC-2 compliance. MSFT targets currently
	 * claim SPC-2 compliance while they implement post SPC-2 features.
	 * With this flag we can correctly handle WRITE_SAME_16 issues.
	 *
	 * Hypervisor reports SCSI_UNKNOWN type for DVD ROM device but
	 * still supports REPORT LUN.
	 */
	sdevice->sdev_bflags = BLIST_REPORTLUN2 | BLIST_TRY_VPD_PAGES;

	return 0;
}

static int storvsc_device_configure(struct scsi_device *sdevice)
{
	blk_queue_rq_timeout(sdevice->request_queue, (storvsc_timeout * HZ));

	sdevice->no_write_same = 1;

	/*
	 * If the host is WIN8 or WIN8 R2, claim conformance to SPC-3
	 * if the device is a MSFT virtual device.  If the host is
	 * WIN10 or newer, allow write_same.
	 */
	if (!strncmp(sdevice->vendor, "Msft", 4)) {
		switch (vmstor_proto_version) {
		case VMSTOR_PROTO_VERSION_WIN8:
		case VMSTOR_PROTO_VERSION_WIN8_1:
			sdevice->scsi_level = SCSI_SPC_3;
			break;
		}

		if (vmstor_proto_version >= VMSTOR_PROTO_VERSION_WIN10)
			sdevice->no_write_same = 0;
	}

	return 0;
}

static int storvsc_get_chs(struct scsi_device *sdev, struct block_device * bdev,
			   sector_t capacity, int *info)
{
	sector_t nsect = capacity;
	sector_t cylinders = nsect;
	int heads, sectors_pt;

	/*
	 * We are making up these values; let us keep it simple.
	 */
	heads = 0xff;
	sectors_pt = 0x3f;      /* Sectors per track */
	sector_div(cylinders, heads * sectors_pt);
	if ((sector_t)(cylinders + 1) * heads * sectors_pt < nsect)
		cylinders = 0xffff;

	info[0] = heads;
	info[1] = sectors_pt;
	info[2] = (int)cylinders;

	return 0;
}

static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
{
	struct hv_host_device *host_dev = shost_priv(scmnd->device->host);
	struct hv_device *device = host_dev->dev;

	struct storvsc_device *stor_device;
	struct storvsc_cmd_request *request;
	struct vstor_packet *vstor_packet;
	int ret, t;

	stor_device = get_out_stor_device(device);
	if (!stor_device)
		return FAILED;

	request = &stor_device->reset_request;
	vstor_packet = &request->vstor_packet;
	memset(vstor_packet, 0, sizeof(struct vstor_packet));

	init_completion(&request->wait_event);

	vstor_packet->operation = VSTOR_OPERATION_RESET_BUS;
	vstor_packet->flags = REQUEST_COMPLETION_FLAG;
	vstor_packet->vm_srb.path_id = stor_device->path_id;

	ret = vmbus_sendpacket(device->channel, vstor_packet,
			       (sizeof(struct vstor_packet) -
				stor_device->vmscsi_size_delta),
			       VMBUS_RQST_RESET,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret != 0)
		return FAILED;

	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
	if (t == 0)
		return TIMEOUT_ERROR;


	/*
	 * At this point, all outstanding requests in the adapter
	 * should have been flushed out and return to us
	 * There is a potential race here where the host may be in
	 * the process of responding when we return from here.
	 * Just wait for all in-transit packets to be accounted for
	 * before we return from here.
	 */
	storvsc_wait_to_drain(stor_device);

	return SUCCESS;
}

/*
 * The host guarantees to respond to each command, although I/O latencies might
 * be unbounded on Azure.  Reset the timer unconditionally to give the host a
 * chance to perform EH.
 */
static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
{
#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
	if (scmnd->device->host->transportt == fc_transport_template)
		return fc_eh_timed_out(scmnd);
#endif
	return BLK_EH_RESET_TIMER;
}

static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd)
{
	bool allowed = true;
	u8 scsi_op = scmnd->cmnd[0];

	switch (scsi_op) {
	/* the host does not handle WRITE_SAME, log accident usage */
	case WRITE_SAME:
	/*
	 * smartd sends this command and the host does not handle
	 * this. So, don't send it.
	 */
	case SET_WINDOW:
		set_host_byte(scmnd, DID_ERROR);
		allowed = false;
		break;
	default:
		break;
	}
	return allowed;
}

static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
{
	int ret;
	struct hv_host_device *host_dev = shost_priv(host);
	struct hv_device *dev = host_dev->dev;
	struct storvsc_cmd_request *cmd_request = scsi_cmd_priv(scmnd);
	struct scatterlist *sgl;
	struct vmscsi_request *vm_srb;
	struct vmbus_packet_mpb_array  *payload;
	u32 payload_sz;
	u32 length;

	if (vmstor_proto_version <= VMSTOR_PROTO_VERSION_WIN8) {
		/*
		 * On legacy hosts filter unimplemented commands.
		 * Future hosts are expected to correctly handle
		 * unsupported commands. Furthermore, it is
		 * possible that some of the currently
		 * unsupported commands maybe supported in
		 * future versions of the host.
		 */
		if (!storvsc_scsi_cmd_ok(scmnd)) {
			scsi_done(scmnd);
			return 0;
		}
	}

	/* Setup the cmd request */
	cmd_request->cmd = scmnd;

	memset(&cmd_request->vstor_packet, 0, sizeof(struct vstor_packet));
	vm_srb = &cmd_request->vstor_packet.vm_srb;
	vm_srb->win8_extension.time_out_value = 60;

	vm_srb->win8_extension.srb_flags |=
		SRB_FLAGS_DISABLE_SYNCH_TRANSFER;

	if (scmnd->device->tagged_supported) {
		vm_srb->win8_extension.srb_flags |=
		(SRB_FLAGS_QUEUE_ACTION_ENABLE | SRB_FLAGS_NO_QUEUE_FREEZE);
		vm_srb->win8_extension.queue_tag = SP_UNTAGGED;
		vm_srb->win8_extension.queue_action = SRB_SIMPLE_TAG_REQUEST;
	}

	/* Build the SRB */
	switch (scmnd->sc_data_direction) {
	case DMA_TO_DEVICE:
		vm_srb->data_in = WRITE_TYPE;
		vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_OUT;
		break;
	case DMA_FROM_DEVICE:
		vm_srb->data_in = READ_TYPE;
		vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_IN;
		break;
	case DMA_NONE:
		vm_srb->data_in = UNKNOWN_TYPE;
		vm_srb->win8_extension.srb_flags |= SRB_FLAGS_NO_DATA_TRANSFER;
		break;
	default:
		/*
		 * This is DMA_BIDIRECTIONAL or something else we are never
		 * supposed to see here.
		 */
		WARN(1, "Unexpected data direction: %d\n",
		     scmnd->sc_data_direction);
		return -EINVAL;
	}


	vm_srb->port_number = host_dev->port;
	vm_srb->path_id = scmnd->device->channel;
	vm_srb->target_id = scmnd->device->id;
	vm_srb->lun = scmnd->device->lun;

	vm_srb->cdb_length = scmnd->cmd_len;

	memcpy(vm_srb->cdb, scmnd->cmnd, vm_srb->cdb_length);

	sgl = (struct scatterlist *)scsi_sglist(scmnd);

	length = scsi_bufflen(scmnd);
	payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb;
	payload_sz = sizeof(cmd_request->mpb);

	if (scsi_sg_count(scmnd)) {
		unsigned long offset_in_hvpg = offset_in_hvpage(sgl->offset);
		unsigned int hvpg_count = HVPFN_UP(offset_in_hvpg + length);
		struct scatterlist *sg;
		unsigned long hvpfn, hvpfns_to_add;
		int j, i = 0, sg_count;

		if (hvpg_count > MAX_PAGE_BUFFER_COUNT) {

			payload_sz = (hvpg_count * sizeof(u64) +
				      sizeof(struct vmbus_packet_mpb_array));
			payload = kzalloc(payload_sz, GFP_ATOMIC);
			if (!payload)
				return SCSI_MLQUEUE_DEVICE_BUSY;
		}

		payload->range.len = length;
		payload->range.offset = offset_in_hvpg;

		sg_count = scsi_dma_map(scmnd);
		if (sg_count < 0) {
			ret = SCSI_MLQUEUE_DEVICE_BUSY;
			goto err_free_payload;
		}

		for_each_sg(sgl, sg, sg_count, j) {
			/*
			 * Init values for the current sgl entry. hvpfns_to_add
			 * is in units of Hyper-V size pages. Handling the
			 * PAGE_SIZE != HV_HYP_PAGE_SIZE case also handles
			 * values of sgl->offset that are larger than PAGE_SIZE.
			 * Such offsets are handled even on other than the first
			 * sgl entry, provided they are a multiple of PAGE_SIZE.
			 */
			hvpfn = HVPFN_DOWN(sg_dma_address(sg));
			hvpfns_to_add = HVPFN_UP(sg_dma_address(sg) +
						 sg_dma_len(sg)) - hvpfn;

			/*
			 * Fill the next portion of the PFN array with
			 * sequential Hyper-V PFNs for the continguous physical
			 * memory described by the sgl entry. The end of the
			 * last sgl should be reached at the same time that
			 * the PFN array is filled.
			 */
			while (hvpfns_to_add--)
				payload->range.pfn_array[i++] = hvpfn++;
		}
	}

	cmd_request->payload = payload;
	cmd_request->payload_sz = payload_sz;

	/* Invokes the vsc to start an IO */
	ret = storvsc_do_io(dev, cmd_request, get_cpu());
	put_cpu();

	if (ret == -EAGAIN) {
		/* no more space */
		ret = SCSI_MLQUEUE_DEVICE_BUSY;
		goto err_free_payload;
	}

	return 0;

err_free_payload:
	if (payload_sz > sizeof(cmd_request->mpb))
		kfree(payload);

	return ret;
}

static struct scsi_host_template scsi_driver = {
	.module	=		THIS_MODULE,
	.name =			"storvsc_host_t",
	.cmd_size =             sizeof(struct storvsc_cmd_request),
	.bios_param =		storvsc_get_chs,
	.queuecommand =		storvsc_queuecommand,
	.eh_host_reset_handler =	storvsc_host_reset_handler,
	.proc_name =		"storvsc_host",
	.eh_timed_out =		storvsc_eh_timed_out,
	.slave_alloc =		storvsc_device_alloc,
	.slave_configure =	storvsc_device_configure,
	.cmd_per_lun =		2048,
	.this_id =		-1,
	/* Ensure there are no gaps in presented sgls */
	.virt_boundary_mask =	PAGE_SIZE-1,
	.no_write_same =	1,
	.track_queue_depth =	1,
	.change_queue_depth =	storvsc_change_queue_depth,
};

enum {
	SCSI_GUID,
	IDE_GUID,
	SFC_GUID,
};

static const struct hv_vmbus_device_id id_table[] = {
	/* SCSI guid */
	{ HV_SCSI_GUID,
	  .driver_data = SCSI_GUID
	},
	/* IDE guid */
	{ HV_IDE_GUID,
	  .driver_data = IDE_GUID
	},
	/* Fibre Channel GUID */
	{
	  HV_SYNTHFC_GUID,
	  .driver_data = SFC_GUID
	},
	{ },
};

MODULE_DEVICE_TABLE(vmbus, id_table);

static const struct { guid_t guid; } fc_guid = { HV_SYNTHFC_GUID };

static bool hv_dev_is_fc(struct hv_device *hv_dev)
{
	return guid_equal(&fc_guid.guid, &hv_dev->dev_type);
}

static int storvsc_probe(struct hv_device *device,
			const struct hv_vmbus_device_id *dev_id)
{
	int ret;
	int num_cpus = num_online_cpus();
	int num_present_cpus = num_present_cpus();
	struct Scsi_Host *host;
	struct hv_host_device *host_dev;
	bool dev_is_ide = ((dev_id->driver_data == IDE_GUID) ? true : false);
	bool is_fc = ((dev_id->driver_data == SFC_GUID) ? true : false);
	int target = 0;
	struct storvsc_device *stor_device;
	int max_luns_per_target;
	int max_targets;
	int max_channels;
	int max_sub_channels = 0;

	/*
	 * Based on the windows host we are running on,
	 * set state to properly communicate with the host.
	 */

	if (vmbus_proto_version < VERSION_WIN8) {
		max_luns_per_target = STORVSC_IDE_MAX_LUNS_PER_TARGET;
		max_targets = STORVSC_IDE_MAX_TARGETS;
		max_channels = STORVSC_IDE_MAX_CHANNELS;
	} else {
		max_luns_per_target = STORVSC_MAX_LUNS_PER_TARGET;
		max_targets = STORVSC_MAX_TARGETS;
		max_channels = STORVSC_MAX_CHANNELS;
		/*
		 * On Windows8 and above, we support sub-channels for storage
		 * on SCSI and FC controllers.
		 * The number of sub-channels offerred is based on the number of
		 * VCPUs in the guest.
		 */
		if (!dev_is_ide)
			max_sub_channels =
				(num_cpus - 1) / storvsc_vcpus_per_sub_channel;
	}

	scsi_driver.can_queue = max_outstanding_req_per_channel *
				(max_sub_channels + 1) *
				(100 - ring_avail_percent_lowater) / 100;

	host = scsi_host_alloc(&scsi_driver,
			       sizeof(struct hv_host_device));
	if (!host)
		return -ENOMEM;

	host_dev = shost_priv(host);
	memset(host_dev, 0, sizeof(struct hv_host_device));

	host_dev->port = host->host_no;
	host_dev->dev = device;
	host_dev->host = host;


	stor_device = kzalloc(sizeof(struct storvsc_device), GFP_KERNEL);
	if (!stor_device) {
		ret = -ENOMEM;
		goto err_out0;
	}

	stor_device->destroy = false;
	init_waitqueue_head(&stor_device->waiting_to_drain);
	stor_device->device = device;
	stor_device->host = host;
	stor_device->vmscsi_size_delta = sizeof(struct vmscsi_win8_extension);
	spin_lock_init(&stor_device->lock);
	hv_set_drvdata(device, stor_device);
	dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1);

	stor_device->port_number = host->host_no;
	ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc);
	if (ret)
		goto err_out1;

	host_dev->path = stor_device->path_id;
	host_dev->target = stor_device->target_id;

	switch (dev_id->driver_data) {
	case SFC_GUID:
		host->max_lun = STORVSC_FC_MAX_LUNS_PER_TARGET;
		host->max_id = STORVSC_FC_MAX_TARGETS;
		host->max_channel = STORVSC_FC_MAX_CHANNELS - 1;
#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
		host->transportt = fc_transport_template;
#endif
		break;

	case SCSI_GUID:
		host->max_lun = max_luns_per_target;
		host->max_id = max_targets;
		host->max_channel = max_channels - 1;
		break;

	default:
		host->max_lun = STORVSC_IDE_MAX_LUNS_PER_TARGET;
		host->max_id = STORVSC_IDE_MAX_TARGETS;
		host->max_channel = STORVSC_IDE_MAX_CHANNELS - 1;
		break;
	}
	/* max cmd length */
	host->max_cmd_len = STORVSC_MAX_CMD_LEN;

	/*
	 * set the table size based on the info we got
	 * from the host.
	 */
	host->sg_tablesize = (stor_device->max_transfer_bytes >> PAGE_SHIFT);
	/*
	 * For non-IDE disks, the host supports multiple channels.
	 * Set the number of HW queues we are supporting.
	 */
	if (!dev_is_ide) {
		if (storvsc_max_hw_queues > num_present_cpus) {
			storvsc_max_hw_queues = 0;
			storvsc_log(device, STORVSC_LOGGING_WARN,
				"Resetting invalid storvsc_max_hw_queues value to default.\n");
		}
		if (storvsc_max_hw_queues)
			host->nr_hw_queues = storvsc_max_hw_queues;
		else
			host->nr_hw_queues = num_present_cpus;
	}

	/*
	 * Set the error handler work queue.
	 */
	host_dev->handle_error_wq =
			alloc_ordered_workqueue("storvsc_error_wq_%d",
						WQ_MEM_RECLAIM,
						host->host_no);
	if (!host_dev->handle_error_wq) {
		ret = -ENOMEM;
		goto err_out2;
	}
	INIT_WORK(&host_dev->host_scan_work, storvsc_host_scan);
	/* Register the HBA and start the scsi bus scan */
	ret = scsi_add_host(host, &device->device);
	if (ret != 0)
		goto err_out3;

	if (!dev_is_ide) {
		scsi_scan_host(host);
	} else {
		target = (device->dev_instance.b[5] << 8 |
			 device->dev_instance.b[4]);
		ret = scsi_add_device(host, 0, target, 0);
		if (ret)
			goto err_out4;
	}
#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
	if (host->transportt == fc_transport_template) {
		struct fc_rport_identifiers ids = {
			.roles = FC_PORT_ROLE_FCP_DUMMY_INITIATOR,
		};

		fc_host_node_name(host) = stor_device->node_name;
		fc_host_port_name(host) = stor_device->port_name;
		stor_device->rport = fc_remote_port_add(host, 0, &ids);
		if (!stor_device->rport) {
			ret = -ENOMEM;
			goto err_out4;
		}
	}
#endif
	return 0;

err_out4:
	scsi_remove_host(host);

err_out3:
	destroy_workqueue(host_dev->handle_error_wq);

err_out2:
	/*
	 * Once we have connected with the host, we would need to
	 * to invoke storvsc_dev_remove() to rollback this state and
	 * this call also frees up the stor_device; hence the jump around
	 * err_out1 label.
	 */
	storvsc_dev_remove(device);
	goto err_out0;

err_out1:
	kfree(stor_device->stor_chns);
	kfree(stor_device);

err_out0:
	scsi_host_put(host);
	return ret;
}

/* Change a scsi target's queue depth */
static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth)
{
	if (queue_depth > scsi_driver.can_queue)
		queue_depth = scsi_driver.can_queue;

	return scsi_change_queue_depth(sdev, queue_depth);
}

static int storvsc_remove(struct hv_device *dev)
{
	struct storvsc_device *stor_device = hv_get_drvdata(dev);
	struct Scsi_Host *host = stor_device->host;
	struct hv_host_device *host_dev = shost_priv(host);

#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
	if (host->transportt == fc_transport_template) {
		fc_remote_port_delete(stor_device->rport);
		fc_remove_host(host);
	}
#endif
	destroy_workqueue(host_dev->handle_error_wq);
	scsi_remove_host(host);
	storvsc_dev_remove(dev);
	scsi_host_put(host);

	return 0;
}

static int storvsc_suspend(struct hv_device *hv_dev)
{
	struct storvsc_device *stor_device = hv_get_drvdata(hv_dev);
	struct Scsi_Host *host = stor_device->host;
	struct hv_host_device *host_dev = shost_priv(host);

	storvsc_wait_to_drain(stor_device);

	drain_workqueue(host_dev->handle_error_wq);

	vmbus_close(hv_dev->channel);

	kfree(stor_device->stor_chns);
	stor_device->stor_chns = NULL;

	cpumask_clear(&stor_device->alloced_cpus);

	return 0;
}

static int storvsc_resume(struct hv_device *hv_dev)
{
	int ret;

	ret = storvsc_connect_to_vsp(hv_dev, storvsc_ringbuffer_size,
				     hv_dev_is_fc(hv_dev));
	return ret;
}

static struct hv_driver storvsc_drv = {
	.name = KBUILD_MODNAME,
	.id_table = id_table,
	.probe = storvsc_probe,
	.remove = storvsc_remove,
	.suspend = storvsc_suspend,
	.resume = storvsc_resume,
	.driver = {
		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
	},
};

#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
static struct fc_function_template fc_transport_functions = {
	.show_host_node_name = 1,
	.show_host_port_name = 1,
};
#endif

static int __init storvsc_drv_init(void)
{
	int ret;

	/*
	 * Divide the ring buffer data size (which is 1 page less
	 * than the ring buffer size since that page is reserved for
	 * the ring buffer indices) by the max request size (which is
	 * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64)
	 *
	 * The computation underestimates max_outstanding_req_per_channel
	 * for Win7 and older hosts because it does not take into account
	 * the vmscsi_size_delta correction to the max request size.
	 */
	max_outstanding_req_per_channel =
		((storvsc_ringbuffer_size - PAGE_SIZE) /
		ALIGN(MAX_MULTIPAGE_BUFFER_PACKET +
		sizeof(struct vstor_packet) + sizeof(u64),
		sizeof(u64)));

#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
	fc_transport_template = fc_attach_transport(&fc_transport_functions);
	if (!fc_transport_template)
		return -ENODEV;
#endif

	ret = vmbus_driver_register(&storvsc_drv);

#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
	if (ret)
		fc_release_transport(fc_transport_template);
#endif

	return ret;
}

static void __exit storvsc_drv_exit(void)
{
	vmbus_driver_unregister(&storvsc_drv);
#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
	fc_release_transport(fc_transport_template);
#endif
}

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Microsoft Hyper-V virtual storage driver");
module_init(storvsc_drv_init);
module_exit(storvsc_drv_exit);