scsi.c 58.2 KB
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
/*******************************************************************************
 * Vhost kernel TCM fabric driver for virtio SCSI initiators
 *
 * (C) Copyright 2010-2013 Datera, Inc.
 * (C) Copyright 2010-2012 IBM Corp.
 *
 * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
 *
 * Authors: Nicholas A. Bellinger <nab@daterainc.com>
 *          Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 ****************************************************************************/

#include <linux/module.h>
#include <linux/moduleparam.h>
#include <generated/utsrelease.h>
#include <linux/utsname.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/kthread.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/configfs.h>
#include <linux/ctype.h>
#include <linux/compat.h>
#include <linux/eventfd.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <linux/miscdevice.h>
#include <asm/unaligned.h>
#include <scsi/scsi_common.h>
#include <scsi/scsi_proto.h>
#include <target/target_core_base.h>
#include <target/target_core_fabric.h>
#include <linux/vhost.h>
#include <linux/virtio_scsi.h>
#include <linux/llist.h>
#include <linux/bitmap.h>
#include <linux/percpu_ida.h>

#include "vhost.h"

#define VHOST_SCSI_VERSION  "v0.1"
#define VHOST_SCSI_NAMELEN 256
#define VHOST_SCSI_MAX_CDB_SIZE 32
#define VHOST_SCSI_DEFAULT_TAGS 256
#define VHOST_SCSI_PREALLOC_SGLS 2048
#define VHOST_SCSI_PREALLOC_UPAGES 2048
#define VHOST_SCSI_PREALLOC_PROT_SGLS 512

struct vhost_scsi_inflight {
	/* Wait for the flush operation to finish */
	struct completion comp;
	/* Refcount for the inflight reqs */
	struct kref kref;
};

struct vhost_scsi_cmd {
	/* Descriptor from vhost_get_vq_desc() for virt_queue segment */
	int tvc_vq_desc;
	/* virtio-scsi initiator task attribute */
	int tvc_task_attr;
	/* virtio-scsi response incoming iovecs */
	int tvc_in_iovs;
	/* virtio-scsi initiator data direction */
	enum dma_data_direction tvc_data_direction;
	/* Expected data transfer length from virtio-scsi header */
	u32 tvc_exp_data_len;
	/* The Tag from include/linux/virtio_scsi.h:struct virtio_scsi_cmd_req */
	u64 tvc_tag;
	/* The number of scatterlists associated with this cmd */
	u32 tvc_sgl_count;
	u32 tvc_prot_sgl_count;
	/* Saved unpacked SCSI LUN for vhost_scsi_submission_work() */
	u32 tvc_lun;
	/* Pointer to the SGL formatted memory from virtio-scsi */
	struct scatterlist *tvc_sgl;
	struct scatterlist *tvc_prot_sgl;
	struct page **tvc_upages;
	/* Pointer to response header iovec */
	struct iovec tvc_resp_iov;
	/* Pointer to vhost_scsi for our device */
	struct vhost_scsi *tvc_vhost;
	/* Pointer to vhost_virtqueue for the cmd */
	struct vhost_virtqueue *tvc_vq;
	/* Pointer to vhost nexus memory */
	struct vhost_scsi_nexus *tvc_nexus;
	/* The TCM I/O descriptor that is accessed via container_of() */
	struct se_cmd tvc_se_cmd;
	/* work item used for cmwq dispatch to vhost_scsi_submission_work() */
	struct work_struct work;
	/* Copy of the incoming SCSI command descriptor block (CDB) */
	unsigned char tvc_cdb[VHOST_SCSI_MAX_CDB_SIZE];
	/* Sense buffer that will be mapped into outgoing status */
	unsigned char tvc_sense_buf[TRANSPORT_SENSE_BUFFER];
	/* Completed commands list, serviced from vhost worker thread */
	struct llist_node tvc_completion_list;
	/* Used to track inflight cmd */
	struct vhost_scsi_inflight *inflight;
};

struct vhost_scsi_nexus {
	/* Pointer to TCM session for I_T Nexus */
	struct se_session *tvn_se_sess;
};

struct vhost_scsi_tpg {
	/* Vhost port target portal group tag for TCM */
	u16 tport_tpgt;
	/* Used to track number of TPG Port/Lun Links wrt to explict I_T Nexus shutdown */
	int tv_tpg_port_count;
	/* Used for vhost_scsi device reference to tpg_nexus, protected by tv_tpg_mutex */
	int tv_tpg_vhost_count;
	/* Used for enabling T10-PI with legacy devices */
	int tv_fabric_prot_type;
	/* list for vhost_scsi_list */
	struct list_head tv_tpg_list;
	/* Used to protect access for tpg_nexus */
	struct mutex tv_tpg_mutex;
	/* Pointer to the TCM VHost I_T Nexus for this TPG endpoint */
	struct vhost_scsi_nexus *tpg_nexus;
	/* Pointer back to vhost_scsi_tport */
	struct vhost_scsi_tport *tport;
	/* Returned by vhost_scsi_make_tpg() */
	struct se_portal_group se_tpg;
	/* Pointer back to vhost_scsi, protected by tv_tpg_mutex */
	struct vhost_scsi *vhost_scsi;
};

struct vhost_scsi_tport {
	/* SCSI protocol the tport is providing */
	u8 tport_proto_id;
	/* Binary World Wide unique Port Name for Vhost Target port */
	u64 tport_wwpn;
	/* ASCII formatted WWPN for Vhost Target port */
	char tport_name[VHOST_SCSI_NAMELEN];
	/* Returned by vhost_scsi_make_tport() */
	struct se_wwn tport_wwn;
};

struct vhost_scsi_evt {
	/* event to be sent to guest */
	struct virtio_scsi_event event;
	/* event list, serviced from vhost worker thread */
	struct llist_node list;
};

enum {
	VHOST_SCSI_VQ_CTL = 0,
	VHOST_SCSI_VQ_EVT = 1,
	VHOST_SCSI_VQ_IO = 2,
};

/* Note: can't set VIRTIO_F_VERSION_1 yet, since that implies ANY_LAYOUT. */
enum {
	VHOST_SCSI_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_SCSI_F_HOTPLUG) |
					       (1ULL << VIRTIO_SCSI_F_T10_PI)
};

#define VHOST_SCSI_MAX_TARGET	256
#define VHOST_SCSI_MAX_VQ	128
#define VHOST_SCSI_MAX_EVENT	128

struct vhost_scsi_virtqueue {
	struct vhost_virtqueue vq;
	/*
	 * Reference counting for inflight reqs, used for flush operation. At
	 * each time, one reference tracks new commands submitted, while we
	 * wait for another one to reach 0.
	 */
	struct vhost_scsi_inflight inflights[2];
	/*
	 * Indicate current inflight in use, protected by vq->mutex.
	 * Writers must also take dev mutex and flush under it.
	 */
	int inflight_idx;
};

struct vhost_scsi {
	/* Protected by vhost_scsi->dev.mutex */
	struct vhost_scsi_tpg **vs_tpg;
	char vs_vhost_wwpn[TRANSPORT_IQN_LEN];

	struct vhost_dev dev;
	struct vhost_scsi_virtqueue vqs[VHOST_SCSI_MAX_VQ];

	struct vhost_work vs_completion_work; /* cmd completion work item */
	struct llist_head vs_completion_list; /* cmd completion queue */

	struct vhost_work vs_event_work; /* evt injection work item */
	struct llist_head vs_event_list; /* evt injection queue */

	bool vs_events_missed; /* any missed events, protected by vq->mutex */
	int vs_events_nr; /* num of pending events, protected by vq->mutex */
};

static struct workqueue_struct *vhost_scsi_workqueue;

/* Global spinlock to protect vhost_scsi TPG list for vhost IOCTL access */
static DEFINE_MUTEX(vhost_scsi_mutex);
static LIST_HEAD(vhost_scsi_list);

static int iov_num_pages(void __user *iov_base, size_t iov_len)
{
	return (PAGE_ALIGN((unsigned long)iov_base + iov_len) -
	       ((unsigned long)iov_base & PAGE_MASK)) >> PAGE_SHIFT;
}

static void vhost_scsi_done_inflight(struct kref *kref)
{
	struct vhost_scsi_inflight *inflight;

	inflight = container_of(kref, struct vhost_scsi_inflight, kref);
	complete(&inflight->comp);
}

static void vhost_scsi_init_inflight(struct vhost_scsi *vs,
				    struct vhost_scsi_inflight *old_inflight[])
{
	struct vhost_scsi_inflight *new_inflight;
	struct vhost_virtqueue *vq;
	int idx, i;

	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
		vq = &vs->vqs[i].vq;

		mutex_lock(&vq->mutex);

		/* store old infight */
		idx = vs->vqs[i].inflight_idx;
		if (old_inflight)
			old_inflight[i] = &vs->vqs[i].inflights[idx];

		/* setup new infight */
		vs->vqs[i].inflight_idx = idx ^ 1;
		new_inflight = &vs->vqs[i].inflights[idx ^ 1];
		kref_init(&new_inflight->kref);
		init_completion(&new_inflight->comp);

		mutex_unlock(&vq->mutex);
	}
}

static struct vhost_scsi_inflight *
vhost_scsi_get_inflight(struct vhost_virtqueue *vq)
{
	struct vhost_scsi_inflight *inflight;
	struct vhost_scsi_virtqueue *svq;

	svq = container_of(vq, struct vhost_scsi_virtqueue, vq);
	inflight = &svq->inflights[svq->inflight_idx];
	kref_get(&inflight->kref);

	return inflight;
}

static void vhost_scsi_put_inflight(struct vhost_scsi_inflight *inflight)
{
	kref_put(&inflight->kref, vhost_scsi_done_inflight);
}

static int vhost_scsi_check_true(struct se_portal_group *se_tpg)
{
	return 1;
}

static int vhost_scsi_check_false(struct se_portal_group *se_tpg)
{
	return 0;
}

static char *vhost_scsi_get_fabric_name(void)
{
	return "vhost";
}

static char *vhost_scsi_get_fabric_wwn(struct se_portal_group *se_tpg)
{
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);
	struct vhost_scsi_tport *tport = tpg->tport;

	return &tport->tport_name[0];
}

static u16 vhost_scsi_get_tpgt(struct se_portal_group *se_tpg)
{
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);
	return tpg->tport_tpgt;
}

static int vhost_scsi_check_prot_fabric_only(struct se_portal_group *se_tpg)
{
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);

	return tpg->tv_fabric_prot_type;
}

static u32 vhost_scsi_tpg_get_inst_index(struct se_portal_group *se_tpg)
{
	return 1;
}

static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
{
	struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd,
				struct vhost_scsi_cmd, tvc_se_cmd);
	struct se_session *se_sess = tv_cmd->tvc_nexus->tvn_se_sess;
	int i;

	if (tv_cmd->tvc_sgl_count) {
		for (i = 0; i < tv_cmd->tvc_sgl_count; i++)
			put_page(sg_page(&tv_cmd->tvc_sgl[i]));
	}
	if (tv_cmd->tvc_prot_sgl_count) {
		for (i = 0; i < tv_cmd->tvc_prot_sgl_count; i++)
			put_page(sg_page(&tv_cmd->tvc_prot_sgl[i]));
	}

	vhost_scsi_put_inflight(tv_cmd->inflight);
	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
}

static int vhost_scsi_shutdown_session(struct se_session *se_sess)
{
	return 0;
}

static void vhost_scsi_close_session(struct se_session *se_sess)
{
	return;
}

static u32 vhost_scsi_sess_get_index(struct se_session *se_sess)
{
	return 0;
}

static int vhost_scsi_write_pending(struct se_cmd *se_cmd)
{
	/* Go ahead and process the write immediately */
	target_execute_cmd(se_cmd);
	return 0;
}

static int vhost_scsi_write_pending_status(struct se_cmd *se_cmd)
{
	return 0;
}

static void vhost_scsi_set_default_node_attrs(struct se_node_acl *nacl)
{
	return;
}

static int vhost_scsi_get_cmd_state(struct se_cmd *se_cmd)
{
	return 0;
}

static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd)
{
	struct vhost_scsi *vs = cmd->tvc_vhost;

	llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);

	vhost_work_queue(&vs->dev, &vs->vs_completion_work);
}

static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd)
{
	struct vhost_scsi_cmd *cmd = container_of(se_cmd,
				struct vhost_scsi_cmd, tvc_se_cmd);
	vhost_scsi_complete_cmd(cmd);
	return 0;
}

static int vhost_scsi_queue_status(struct se_cmd *se_cmd)
{
	struct vhost_scsi_cmd *cmd = container_of(se_cmd,
				struct vhost_scsi_cmd, tvc_se_cmd);
	vhost_scsi_complete_cmd(cmd);
	return 0;
}

static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd)
{
	return;
}

static void vhost_scsi_aborted_task(struct se_cmd *se_cmd)
{
	return;
}

static void vhost_scsi_free_evt(struct vhost_scsi *vs, struct vhost_scsi_evt *evt)
{
	vs->vs_events_nr--;
	kfree(evt);
}

static struct vhost_scsi_evt *
vhost_scsi_allocate_evt(struct vhost_scsi *vs,
		       u32 event, u32 reason)
{
	struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
	struct vhost_scsi_evt *evt;

	if (vs->vs_events_nr > VHOST_SCSI_MAX_EVENT) {
		vs->vs_events_missed = true;
		return NULL;
	}

	evt = kzalloc(sizeof(*evt), GFP_KERNEL);
	if (!evt) {
		vq_err(vq, "Failed to allocate vhost_scsi_evt\n");
		vs->vs_events_missed = true;
		return NULL;
	}

	evt->event.event = cpu_to_vhost32(vq, event);
	evt->event.reason = cpu_to_vhost32(vq, reason);
	vs->vs_events_nr++;

	return evt;
}

static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd)
{
	struct se_cmd *se_cmd = &cmd->tvc_se_cmd;

	/* TODO locking against target/backend threads? */
	transport_generic_free_cmd(se_cmd, 0);

}

static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd)
{
	return target_put_sess_cmd(se_cmd);
}

static void
vhost_scsi_do_evt_work(struct vhost_scsi *vs, struct vhost_scsi_evt *evt)
{
	struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
	struct virtio_scsi_event *event = &evt->event;
	struct virtio_scsi_event __user *eventp;
	unsigned out, in;
	int head, ret;

	if (!vq->private_data) {
		vs->vs_events_missed = true;
		return;
	}

again:
	vhost_disable_notify(&vs->dev, vq);
	head = vhost_get_vq_desc(vq, vq->iov,
			ARRAY_SIZE(vq->iov), &out, &in,
			NULL, NULL);
	if (head < 0) {
		vs->vs_events_missed = true;
		return;
	}
	if (head == vq->num) {
		if (vhost_enable_notify(&vs->dev, vq))
			goto again;
		vs->vs_events_missed = true;
		return;
	}

	if ((vq->iov[out].iov_len != sizeof(struct virtio_scsi_event))) {
		vq_err(vq, "Expecting virtio_scsi_event, got %zu bytes\n",
				vq->iov[out].iov_len);
		vs->vs_events_missed = true;
		return;
	}

	if (vs->vs_events_missed) {
		event->event |= cpu_to_vhost32(vq, VIRTIO_SCSI_T_EVENTS_MISSED);
		vs->vs_events_missed = false;
	}

	eventp = vq->iov[out].iov_base;
	ret = __copy_to_user(eventp, event, sizeof(*event));
	if (!ret)
		vhost_add_used_and_signal(&vs->dev, vq, head, 0);
	else
		vq_err(vq, "Faulted on vhost_scsi_send_event\n");
}

static void vhost_scsi_evt_work(struct vhost_work *work)
{
	struct vhost_scsi *vs = container_of(work, struct vhost_scsi,
					vs_event_work);
	struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
	struct vhost_scsi_evt *evt;
	struct llist_node *llnode;

	mutex_lock(&vq->mutex);
	llnode = llist_del_all(&vs->vs_event_list);
	while (llnode) {
		evt = llist_entry(llnode, struct vhost_scsi_evt, list);
		llnode = llist_next(llnode);
		vhost_scsi_do_evt_work(vs, evt);
		vhost_scsi_free_evt(vs, evt);
	}
	mutex_unlock(&vq->mutex);
}

/* Fill in status and signal that we are done processing this command
 *
 * This is scheduled in the vhost work queue so we are called with the owner
 * process mm and can access the vring.
 */
static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
{
	struct vhost_scsi *vs = container_of(work, struct vhost_scsi,
					vs_completion_work);
	DECLARE_BITMAP(signal, VHOST_SCSI_MAX_VQ);
	struct virtio_scsi_cmd_resp v_rsp;
	struct vhost_scsi_cmd *cmd;
	struct llist_node *llnode;
	struct se_cmd *se_cmd;
	struct iov_iter iov_iter;
	int ret, vq;

	bitmap_zero(signal, VHOST_SCSI_MAX_VQ);
	llnode = llist_del_all(&vs->vs_completion_list);
	while (llnode) {
		cmd = llist_entry(llnode, struct vhost_scsi_cmd,
				     tvc_completion_list);
		llnode = llist_next(llnode);
		se_cmd = &cmd->tvc_se_cmd;

		pr_debug("%s tv_cmd %p resid %u status %#02x\n", __func__,
			cmd, se_cmd->residual_count, se_cmd->scsi_status);

		memset(&v_rsp, 0, sizeof(v_rsp));
		v_rsp.resid = cpu_to_vhost32(cmd->tvc_vq, se_cmd->residual_count);
		/* TODO is status_qualifier field needed? */
		v_rsp.status = se_cmd->scsi_status;
		v_rsp.sense_len = cpu_to_vhost32(cmd->tvc_vq,
						 se_cmd->scsi_sense_length);
		memcpy(v_rsp.sense, cmd->tvc_sense_buf,
		       se_cmd->scsi_sense_length);

		iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov,
			      cmd->tvc_in_iovs, sizeof(v_rsp));
		ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter);
		if (likely(ret == sizeof(v_rsp))) {
			struct vhost_scsi_virtqueue *q;
			vhost_add_used(cmd->tvc_vq, cmd->tvc_vq_desc, 0);
			q = container_of(cmd->tvc_vq, struct vhost_scsi_virtqueue, vq);
			vq = q - vs->vqs;
			__set_bit(vq, signal);
		} else
			pr_err("Faulted on virtio_scsi_cmd_resp\n");

		vhost_scsi_free_cmd(cmd);
	}

	vq = -1;
	while ((vq = find_next_bit(signal, VHOST_SCSI_MAX_VQ, vq + 1))
		< VHOST_SCSI_MAX_VQ)
		vhost_signal(&vs->dev, &vs->vqs[vq].vq);
}

static struct vhost_scsi_cmd *
vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
		   unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr,
		   u32 exp_data_len, int data_direction)
{
	struct vhost_scsi_cmd *cmd;
	struct vhost_scsi_nexus *tv_nexus;
	struct se_session *se_sess;
	struct scatterlist *sg, *prot_sg;
	struct page **pages;
	int tag;

	tv_nexus = tpg->tpg_nexus;
	if (!tv_nexus) {
		pr_err("Unable to locate active struct vhost_scsi_nexus\n");
		return ERR_PTR(-EIO);
	}
	se_sess = tv_nexus->tvn_se_sess;

	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
	if (tag < 0) {
		pr_err("Unable to obtain tag for vhost_scsi_cmd\n");
		return ERR_PTR(-ENOMEM);
	}

	cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[tag];
	sg = cmd->tvc_sgl;
	prot_sg = cmd->tvc_prot_sgl;
	pages = cmd->tvc_upages;
	memset(cmd, 0, sizeof(struct vhost_scsi_cmd));

	cmd->tvc_sgl = sg;
	cmd->tvc_prot_sgl = prot_sg;
	cmd->tvc_upages = pages;
	cmd->tvc_se_cmd.map_tag = tag;
	cmd->tvc_tag = scsi_tag;
	cmd->tvc_lun = lun;
	cmd->tvc_task_attr = task_attr;
	cmd->tvc_exp_data_len = exp_data_len;
	cmd->tvc_data_direction = data_direction;
	cmd->tvc_nexus = tv_nexus;
	cmd->inflight = vhost_scsi_get_inflight(vq);

	memcpy(cmd->tvc_cdb, cdb, VHOST_SCSI_MAX_CDB_SIZE);

	return cmd;
}

/*
 * Map a user memory range into a scatterlist
 *
 * Returns the number of scatterlist entries used or -errno on error.
 */
static int
vhost_scsi_map_to_sgl(struct vhost_scsi_cmd *cmd,
		      void __user *ptr,
		      size_t len,
		      struct scatterlist *sgl,
		      bool write)
{
	unsigned int npages = 0, offset, nbytes;
	unsigned int pages_nr = iov_num_pages(ptr, len);
	struct scatterlist *sg = sgl;
	struct page **pages = cmd->tvc_upages;
	int ret, i;

	if (pages_nr > VHOST_SCSI_PREALLOC_UPAGES) {
		pr_err("vhost_scsi_map_to_sgl() pages_nr: %u greater than"
		       " preallocated VHOST_SCSI_PREALLOC_UPAGES: %u\n",
			pages_nr, VHOST_SCSI_PREALLOC_UPAGES);
		return -ENOBUFS;
	}

	ret = get_user_pages_fast((unsigned long)ptr, pages_nr, write, pages);
	/* No pages were pinned */
	if (ret < 0)
		goto out;
	/* Less pages pinned than wanted */
	if (ret != pages_nr) {
		for (i = 0; i < ret; i++)
			put_page(pages[i]);
		ret = -EFAULT;
		goto out;
	}

	while (len > 0) {
		offset = (uintptr_t)ptr & ~PAGE_MASK;
		nbytes = min_t(unsigned int, PAGE_SIZE - offset, len);
		sg_set_page(sg, pages[npages], nbytes, offset);
		ptr += nbytes;
		len -= nbytes;
		sg++;
		npages++;
	}

out:
	return ret;
}

static int
vhost_scsi_calc_sgls(struct iov_iter *iter, size_t bytes, int max_sgls)
{
	int sgl_count = 0;

	if (!iter || !iter->iov) {
		pr_err("%s: iter->iov is NULL, but expected bytes: %zu"
		       " present\n", __func__, bytes);
		return -EINVAL;
	}

	sgl_count = iov_iter_npages(iter, 0xffff);
	if (sgl_count > max_sgls) {
		pr_err("%s: requested sgl_count: %d exceeds pre-allocated"
		       " max_sgls: %d\n", __func__, sgl_count, max_sgls);
		return -EINVAL;
	}
	return sgl_count;
}

static int
vhost_scsi_iov_to_sgl(struct vhost_scsi_cmd *cmd, bool write,
		      struct iov_iter *iter,
		      struct scatterlist *sg, int sg_count)
{
	size_t off = iter->iov_offset;
	int i, ret;

	for (i = 0; i < iter->nr_segs; i++) {
		void __user *base = iter->iov[i].iov_base + off;
		size_t len = iter->iov[i].iov_len - off;

		ret = vhost_scsi_map_to_sgl(cmd, base, len, sg, write);
		if (ret < 0) {
			for (i = 0; i < sg_count; i++) {
				struct page *page = sg_page(&sg[i]);
				if (page)
					put_page(page);
			}
			return ret;
		}
		sg += ret;
		off = 0;
	}
	return 0;
}

static int
vhost_scsi_mapal(struct vhost_scsi_cmd *cmd,
		 size_t prot_bytes, struct iov_iter *prot_iter,
		 size_t data_bytes, struct iov_iter *data_iter)
{
	int sgl_count, ret;
	bool write = (cmd->tvc_data_direction == DMA_FROM_DEVICE);

	if (prot_bytes) {
		sgl_count = vhost_scsi_calc_sgls(prot_iter, prot_bytes,
						 VHOST_SCSI_PREALLOC_PROT_SGLS);
		if (sgl_count < 0)
			return sgl_count;

		sg_init_table(cmd->tvc_prot_sgl, sgl_count);
		cmd->tvc_prot_sgl_count = sgl_count;
		pr_debug("%s prot_sg %p prot_sgl_count %u\n", __func__,
			 cmd->tvc_prot_sgl, cmd->tvc_prot_sgl_count);

		ret = vhost_scsi_iov_to_sgl(cmd, write, prot_iter,
					    cmd->tvc_prot_sgl,
					    cmd->tvc_prot_sgl_count);
		if (ret < 0) {
			cmd->tvc_prot_sgl_count = 0;
			return ret;
		}
	}
	sgl_count = vhost_scsi_calc_sgls(data_iter, data_bytes,
					 VHOST_SCSI_PREALLOC_SGLS);
	if (sgl_count < 0)
		return sgl_count;

	sg_init_table(cmd->tvc_sgl, sgl_count);
	cmd->tvc_sgl_count = sgl_count;
	pr_debug("%s data_sg %p data_sgl_count %u\n", __func__,
		  cmd->tvc_sgl, cmd->tvc_sgl_count);

	ret = vhost_scsi_iov_to_sgl(cmd, write, data_iter,
				    cmd->tvc_sgl, cmd->tvc_sgl_count);
	if (ret < 0) {
		cmd->tvc_sgl_count = 0;
		return ret;
	}
	return 0;
}

static int vhost_scsi_to_tcm_attr(int attr)
{
	switch (attr) {
	case VIRTIO_SCSI_S_SIMPLE:
		return TCM_SIMPLE_TAG;
	case VIRTIO_SCSI_S_ORDERED:
		return TCM_ORDERED_TAG;
	case VIRTIO_SCSI_S_HEAD:
		return TCM_HEAD_TAG;
	case VIRTIO_SCSI_S_ACA:
		return TCM_ACA_TAG;
	default:
		break;
	}
	return TCM_SIMPLE_TAG;
}

static void vhost_scsi_submission_work(struct work_struct *work)
{
	struct vhost_scsi_cmd *cmd =
		container_of(work, struct vhost_scsi_cmd, work);
	struct vhost_scsi_nexus *tv_nexus;
	struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
	struct scatterlist *sg_ptr, *sg_prot_ptr = NULL;
	int rc;

	/* FIXME: BIDI operation */
	if (cmd->tvc_sgl_count) {
		sg_ptr = cmd->tvc_sgl;

		if (cmd->tvc_prot_sgl_count)
			sg_prot_ptr = cmd->tvc_prot_sgl;
		else
			se_cmd->prot_pto = true;
	} else {
		sg_ptr = NULL;
	}
	tv_nexus = cmd->tvc_nexus;

	se_cmd->tag = 0;
	rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess,
			cmd->tvc_cdb, &cmd->tvc_sense_buf[0],
			cmd->tvc_lun, cmd->tvc_exp_data_len,
			vhost_scsi_to_tcm_attr(cmd->tvc_task_attr),
			cmd->tvc_data_direction, TARGET_SCF_ACK_KREF,
			sg_ptr, cmd->tvc_sgl_count, NULL, 0, sg_prot_ptr,
			cmd->tvc_prot_sgl_count);
	if (rc < 0) {
		transport_send_check_condition_and_sense(se_cmd,
				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0);
		transport_generic_free_cmd(se_cmd, 0);
	}
}

static void
vhost_scsi_send_bad_target(struct vhost_scsi *vs,
			   struct vhost_virtqueue *vq,
			   int head, unsigned out)
{
	struct virtio_scsi_cmd_resp __user *resp;
	struct virtio_scsi_cmd_resp rsp;
	int ret;

	memset(&rsp, 0, sizeof(rsp));
	rsp.response = VIRTIO_SCSI_S_BAD_TARGET;
	resp = vq->iov[out].iov_base;
	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
	if (!ret)
		vhost_add_used_and_signal(&vs->dev, vq, head, 0);
	else
		pr_err("Faulted on virtio_scsi_cmd_resp\n");
}

static void
vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
{
	struct vhost_scsi_tpg **vs_tpg, *tpg;
	struct virtio_scsi_cmd_req v_req;
	struct virtio_scsi_cmd_req_pi v_req_pi;
	struct vhost_scsi_cmd *cmd;
	struct iov_iter out_iter, in_iter, prot_iter, data_iter;
	u64 tag;
	u32 exp_data_len, data_direction;
	unsigned out, in;
	int head, ret, prot_bytes;
	size_t req_size, rsp_size = sizeof(struct virtio_scsi_cmd_resp);
	size_t out_size, in_size;
	u16 lun;
	u8 *target, *lunp, task_attr;
	bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI);
	void *req, *cdb;

	mutex_lock(&vq->mutex);
	/*
	 * We can handle the vq only after the endpoint is setup by calling the
	 * VHOST_SCSI_SET_ENDPOINT ioctl.
	 */
	vs_tpg = vq->private_data;
	if (!vs_tpg)
		goto out;

	vhost_disable_notify(&vs->dev, vq);

	for (;;) {
		head = vhost_get_vq_desc(vq, vq->iov,
					 ARRAY_SIZE(vq->iov), &out, &in,
					 NULL, NULL);
		pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n",
			 head, out, in);
		/* On error, stop handling until the next kick. */
		if (unlikely(head < 0))
			break;
		/* Nothing new?  Wait for eventfd to tell us they refilled. */
		if (head == vq->num) {
			if (unlikely(vhost_enable_notify(&vs->dev, vq))) {
				vhost_disable_notify(&vs->dev, vq);
				continue;
			}
			break;
		}
		/*
		 * Check for a sane response buffer so we can report early
		 * errors back to the guest.
		 */
		if (unlikely(vq->iov[out].iov_len < rsp_size)) {
			vq_err(vq, "Expecting at least virtio_scsi_cmd_resp"
				" size, got %zu bytes\n", vq->iov[out].iov_len);
			break;
		}
		/*
		 * Setup pointers and values based upon different virtio-scsi
		 * request header if T10_PI is enabled in KVM guest.
		 */
		if (t10_pi) {
			req = &v_req_pi;
			req_size = sizeof(v_req_pi);
			lunp = &v_req_pi.lun[0];
			target = &v_req_pi.lun[1];
		} else {
			req = &v_req;
			req_size = sizeof(v_req);
			lunp = &v_req.lun[0];
			target = &v_req.lun[1];
		}
		/*
		 * FIXME: Not correct for BIDI operation
		 */
		out_size = iov_length(vq->iov, out);
		in_size = iov_length(&vq->iov[out], in);

		/*
		 * Copy over the virtio-scsi request header, which for a
		 * ANY_LAYOUT enabled guest may span multiple iovecs, or a
		 * single iovec may contain both the header + outgoing
		 * WRITE payloads.
		 *
		 * copy_from_iter() will advance out_iter, so that it will
		 * point at the start of the outgoing WRITE payload, if
		 * DMA_TO_DEVICE is set.
		 */
		iov_iter_init(&out_iter, WRITE, vq->iov, out, out_size);

		ret = copy_from_iter(req, req_size, &out_iter);
		if (unlikely(ret != req_size)) {
			vq_err(vq, "Faulted on copy_from_iter\n");
			vhost_scsi_send_bad_target(vs, vq, head, out);
			continue;
		}
		/* virtio-scsi spec requires byte 0 of the lun to be 1 */
		if (unlikely(*lunp != 1)) {
			vq_err(vq, "Illegal virtio-scsi lun: %u\n", *lunp);
			vhost_scsi_send_bad_target(vs, vq, head, out);
			continue;
		}

		tpg = ACCESS_ONCE(vs_tpg[*target]);
		if (unlikely(!tpg)) {
			/* Target does not exist, fail the request */
			vhost_scsi_send_bad_target(vs, vq, head, out);
			continue;
		}
		/*
		 * Determine data_direction by calculating the total outgoing
		 * iovec sizes + incoming iovec sizes vs. virtio-scsi request +
		 * response headers respectively.
		 *
		 * For DMA_TO_DEVICE this is out_iter, which is already pointing
		 * to the right place.
		 *
		 * For DMA_FROM_DEVICE, the iovec will be just past the end
		 * of the virtio-scsi response header in either the same
		 * or immediately following iovec.
		 *
		 * Any associated T10_PI bytes for the outgoing / incoming
		 * payloads are included in calculation of exp_data_len here.
		 */
		prot_bytes = 0;

		if (out_size > req_size) {
			data_direction = DMA_TO_DEVICE;
			exp_data_len = out_size - req_size;
			data_iter = out_iter;
		} else if (in_size > rsp_size) {
			data_direction = DMA_FROM_DEVICE;
			exp_data_len = in_size - rsp_size;

			iov_iter_init(&in_iter, READ, &vq->iov[out], in,
				      rsp_size + exp_data_len);
			iov_iter_advance(&in_iter, rsp_size);
			data_iter = in_iter;
		} else {
			data_direction = DMA_NONE;
			exp_data_len = 0;
		}
		/*
		 * If T10_PI header + payload is present, setup prot_iter values
		 * and recalculate data_iter for vhost_scsi_mapal() mapping to
		 * host scatterlists via get_user_pages_fast().
		 */
		if (t10_pi) {
			if (v_req_pi.pi_bytesout) {
				if (data_direction != DMA_TO_DEVICE) {
					vq_err(vq, "Received non zero pi_bytesout,"
						" but wrong data_direction\n");
					vhost_scsi_send_bad_target(vs, vq, head, out);
					continue;
				}
				prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesout);
			} else if (v_req_pi.pi_bytesin) {
				if (data_direction != DMA_FROM_DEVICE) {
					vq_err(vq, "Received non zero pi_bytesin,"
						" but wrong data_direction\n");
					vhost_scsi_send_bad_target(vs, vq, head, out);
					continue;
				}
				prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesin);
			}
			/*
			 * Set prot_iter to data_iter, and advance past any
			 * preceeding prot_bytes that may be present.
			 *
			 * Also fix up the exp_data_len to reflect only the
			 * actual data payload length.
			 */
			if (prot_bytes) {
				exp_data_len -= prot_bytes;
				prot_iter = data_iter;
				iov_iter_advance(&data_iter, prot_bytes);
			}
			tag = vhost64_to_cpu(vq, v_req_pi.tag);
			task_attr = v_req_pi.task_attr;
			cdb = &v_req_pi.cdb[0];
			lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF;
		} else {
			tag = vhost64_to_cpu(vq, v_req.tag);
			task_attr = v_req.task_attr;
			cdb = &v_req.cdb[0];
			lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;
		}
		/*
		 * Check that the received CDB size does not exceeded our
		 * hardcoded max for vhost-scsi, then get a pre-allocated
		 * cmd descriptor for the new virtio-scsi tag.
		 *
		 * TODO what if cdb was too small for varlen cdb header?
		 */
		if (unlikely(scsi_command_size(cdb) > VHOST_SCSI_MAX_CDB_SIZE)) {
			vq_err(vq, "Received SCSI CDB with command_size: %d that"
				" exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n",
				scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE);
			vhost_scsi_send_bad_target(vs, vq, head, out);
			continue;
		}
		cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr,
					 exp_data_len + prot_bytes,
					 data_direction);
		if (IS_ERR(cmd)) {
			vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
			       PTR_ERR(cmd));
			vhost_scsi_send_bad_target(vs, vq, head, out);
			continue;
		}
		cmd->tvc_vhost = vs;
		cmd->tvc_vq = vq;
		cmd->tvc_resp_iov = vq->iov[out];
		cmd->tvc_in_iovs = in;

		pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
			 cmd->tvc_cdb[0], cmd->tvc_lun);
		pr_debug("cmd: %p exp_data_len: %d, prot_bytes: %d data_direction:"
			 " %d\n", cmd, exp_data_len, prot_bytes, data_direction);

		if (data_direction != DMA_NONE) {
			ret = vhost_scsi_mapal(cmd,
					       prot_bytes, &prot_iter,
					       exp_data_len, &data_iter);
			if (unlikely(ret)) {
				vq_err(vq, "Failed to map iov to sgl\n");
				vhost_scsi_release_cmd(&cmd->tvc_se_cmd);
				vhost_scsi_send_bad_target(vs, vq, head, out);
				continue;
			}
		}
		/*
		 * Save the descriptor from vhost_get_vq_desc() to be used to
		 * complete the virtio-scsi request in TCM callback context via
		 * vhost_scsi_queue_data_in() and vhost_scsi_queue_status()
		 */
		cmd->tvc_vq_desc = head;
		/*
		 * Dispatch cmd descriptor for cmwq execution in process
		 * context provided by vhost_scsi_workqueue.  This also ensures
		 * cmd is executed on the same kworker CPU as this vhost
		 * thread to gain positive L2 cache locality effects.
		 */
		INIT_WORK(&cmd->work, vhost_scsi_submission_work);
		queue_work(vhost_scsi_workqueue, &cmd->work);
	}
out:
	mutex_unlock(&vq->mutex);
}

static void vhost_scsi_ctl_handle_kick(struct vhost_work *work)
{
	pr_debug("%s: The handling func for control queue.\n", __func__);
}

static void
vhost_scsi_send_evt(struct vhost_scsi *vs,
		   struct vhost_scsi_tpg *tpg,
		   struct se_lun *lun,
		   u32 event,
		   u32 reason)
{
	struct vhost_scsi_evt *evt;

	evt = vhost_scsi_allocate_evt(vs, event, reason);
	if (!evt)
		return;

	if (tpg && lun) {
		/* TODO: share lun setup code with virtio-scsi.ko */
		/*
		 * Note: evt->event is zeroed when we allocate it and
		 * lun[4-7] need to be zero according to virtio-scsi spec.
		 */
		evt->event.lun[0] = 0x01;
		evt->event.lun[1] = tpg->tport_tpgt;
		if (lun->unpacked_lun >= 256)
			evt->event.lun[2] = lun->unpacked_lun >> 8 | 0x40 ;
		evt->event.lun[3] = lun->unpacked_lun & 0xFF;
	}

	llist_add(&evt->list, &vs->vs_event_list);
	vhost_work_queue(&vs->dev, &vs->vs_event_work);
}

static void vhost_scsi_evt_handle_kick(struct vhost_work *work)
{
	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
						poll.work);
	struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev);

	mutex_lock(&vq->mutex);
	if (!vq->private_data)
		goto out;

	if (vs->vs_events_missed)
		vhost_scsi_send_evt(vs, NULL, NULL, VIRTIO_SCSI_T_NO_EVENT, 0);
out:
	mutex_unlock(&vq->mutex);
}

static void vhost_scsi_handle_kick(struct vhost_work *work)
{
	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
						poll.work);
	struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev);

	vhost_scsi_handle_vq(vs, vq);
}

static void vhost_scsi_flush_vq(struct vhost_scsi *vs, int index)
{
	vhost_poll_flush(&vs->vqs[index].vq.poll);
}

/* Callers must hold dev mutex */
static void vhost_scsi_flush(struct vhost_scsi *vs)
{
	struct vhost_scsi_inflight *old_inflight[VHOST_SCSI_MAX_VQ];
	int i;

	/* Init new inflight and remember the old inflight */
	vhost_scsi_init_inflight(vs, old_inflight);

	/*
	 * The inflight->kref was initialized to 1. We decrement it here to
	 * indicate the start of the flush operation so that it will reach 0
	 * when all the reqs are finished.
	 */
	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
		kref_put(&old_inflight[i]->kref, vhost_scsi_done_inflight);

	/* Flush both the vhost poll and vhost work */
	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
		vhost_scsi_flush_vq(vs, i);
	vhost_work_flush(&vs->dev, &vs->vs_completion_work);
	vhost_work_flush(&vs->dev, &vs->vs_event_work);

	/* Wait for all reqs issued before the flush to be finished */
	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
		wait_for_completion(&old_inflight[i]->comp);
}

/*
 * Called from vhost_scsi_ioctl() context to walk the list of available
 * vhost_scsi_tpg with an active struct vhost_scsi_nexus
 *
 *  The lock nesting rule is:
 *    vhost_scsi_mutex -> vs->dev.mutex -> tpg->tv_tpg_mutex -> vq->mutex
 */
static int
vhost_scsi_set_endpoint(struct vhost_scsi *vs,
			struct vhost_scsi_target *t)
{
	struct se_portal_group *se_tpg;
	struct vhost_scsi_tport *tv_tport;
	struct vhost_scsi_tpg *tpg;
	struct vhost_scsi_tpg **vs_tpg;
	struct vhost_virtqueue *vq;
	int index, ret, i, len;
	bool match = false;

	mutex_lock(&vhost_scsi_mutex);
	mutex_lock(&vs->dev.mutex);

	/* Verify that ring has been setup correctly. */
	for (index = 0; index < vs->dev.nvqs; ++index) {
		/* Verify that ring has been setup correctly. */
		if (!vhost_vq_access_ok(&vs->vqs[index].vq)) {
			ret = -EFAULT;
			goto out;
		}
	}

	len = sizeof(vs_tpg[0]) * VHOST_SCSI_MAX_TARGET;
	vs_tpg = kzalloc(len, GFP_KERNEL);
	if (!vs_tpg) {
		ret = -ENOMEM;
		goto out;
	}
	if (vs->vs_tpg)
		memcpy(vs_tpg, vs->vs_tpg, len);

	list_for_each_entry(tpg, &vhost_scsi_list, tv_tpg_list) {
		mutex_lock(&tpg->tv_tpg_mutex);
		if (!tpg->tpg_nexus) {
			mutex_unlock(&tpg->tv_tpg_mutex);
			continue;
		}
		if (tpg->tv_tpg_vhost_count != 0) {
			mutex_unlock(&tpg->tv_tpg_mutex);
			continue;
		}
		tv_tport = tpg->tport;

		if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
			if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) {
				kfree(vs_tpg);
				mutex_unlock(&tpg->tv_tpg_mutex);
				ret = -EEXIST;
				goto out;
			}
			/*
			 * In order to ensure individual vhost-scsi configfs
			 * groups cannot be removed while in use by vhost ioctl,
			 * go ahead and take an explicit se_tpg->tpg_group.cg_item
			 * dependency now.
			 */
			se_tpg = &tpg->se_tpg;
			ret = target_depend_item(&se_tpg->tpg_group.cg_item);
			if (ret) {
				pr_warn("configfs_depend_item() failed: %d\n", ret);
				kfree(vs_tpg);
				mutex_unlock(&tpg->tv_tpg_mutex);
				goto out;
			}
			tpg->tv_tpg_vhost_count++;
			tpg->vhost_scsi = vs;
			vs_tpg[tpg->tport_tpgt] = tpg;
			smp_mb__after_atomic();
			match = true;
		}
		mutex_unlock(&tpg->tv_tpg_mutex);
	}

	if (match) {
		memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
		       sizeof(vs->vs_vhost_wwpn));
		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
			vq = &vs->vqs[i].vq;
			mutex_lock(&vq->mutex);
			vq->private_data = vs_tpg;
			vhost_init_used(vq);
			mutex_unlock(&vq->mutex);
		}
		ret = 0;
	} else {
		ret = -EEXIST;
	}

	/*
	 * Act as synchronize_rcu to make sure access to
	 * old vs->vs_tpg is finished.
	 */
	vhost_scsi_flush(vs);
	kfree(vs->vs_tpg);
	vs->vs_tpg = vs_tpg;

out:
	mutex_unlock(&vs->dev.mutex);
	mutex_unlock(&vhost_scsi_mutex);
	return ret;
}

static int
vhost_scsi_clear_endpoint(struct vhost_scsi *vs,
			  struct vhost_scsi_target *t)
{
	struct se_portal_group *se_tpg;
	struct vhost_scsi_tport *tv_tport;
	struct vhost_scsi_tpg *tpg;
	struct vhost_virtqueue *vq;
	bool match = false;
	int index, ret, i;
	u8 target;

	mutex_lock(&vhost_scsi_mutex);
	mutex_lock(&vs->dev.mutex);
	/* Verify that ring has been setup correctly. */
	for (index = 0; index < vs->dev.nvqs; ++index) {
		if (!vhost_vq_access_ok(&vs->vqs[index].vq)) {
			ret = -EFAULT;
			goto err_dev;
		}
	}

	if (!vs->vs_tpg) {
		ret = 0;
		goto err_dev;
	}

	for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) {
		target = i;
		tpg = vs->vs_tpg[target];
		if (!tpg)
			continue;

		mutex_lock(&tpg->tv_tpg_mutex);
		tv_tport = tpg->tport;
		if (!tv_tport) {
			ret = -ENODEV;
			goto err_tpg;
		}

		if (strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
			pr_warn("tv_tport->tport_name: %s, tpg->tport_tpgt: %hu"
				" does not match t->vhost_wwpn: %s, t->vhost_tpgt: %hu\n",
				tv_tport->tport_name, tpg->tport_tpgt,
				t->vhost_wwpn, t->vhost_tpgt);
			ret = -EINVAL;
			goto err_tpg;
		}
		tpg->tv_tpg_vhost_count--;
		tpg->vhost_scsi = NULL;
		vs->vs_tpg[target] = NULL;
		match = true;
		mutex_unlock(&tpg->tv_tpg_mutex);
		/*
		 * Release se_tpg->tpg_group.cg_item configfs dependency now
		 * to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur.
		 */
		se_tpg = &tpg->se_tpg;
		target_undepend_item(&se_tpg->tpg_group.cg_item);
	}
	if (match) {
		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
			vq = &vs->vqs[i].vq;
			mutex_lock(&vq->mutex);
			vq->private_data = NULL;
			mutex_unlock(&vq->mutex);
		}
	}
	/*
	 * Act as synchronize_rcu to make sure access to
	 * old vs->vs_tpg is finished.
	 */
	vhost_scsi_flush(vs);
	kfree(vs->vs_tpg);
	vs->vs_tpg = NULL;
	WARN_ON(vs->vs_events_nr);
	mutex_unlock(&vs->dev.mutex);
	mutex_unlock(&vhost_scsi_mutex);
	return 0;

err_tpg:
	mutex_unlock(&tpg->tv_tpg_mutex);
err_dev:
	mutex_unlock(&vs->dev.mutex);
	mutex_unlock(&vhost_scsi_mutex);
	return ret;
}

static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features)
{
	struct vhost_virtqueue *vq;
	int i;

	if (features & ~VHOST_SCSI_FEATURES)
		return -EOPNOTSUPP;

	mutex_lock(&vs->dev.mutex);
	if ((features & (1 << VHOST_F_LOG_ALL)) &&
	    !vhost_log_access_ok(&vs->dev)) {
		mutex_unlock(&vs->dev.mutex);
		return -EFAULT;
	}

	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
		vq = &vs->vqs[i].vq;
		mutex_lock(&vq->mutex);
		vq->acked_features = features;
		mutex_unlock(&vq->mutex);
	}
	mutex_unlock(&vs->dev.mutex);
	return 0;
}

static int vhost_scsi_open(struct inode *inode, struct file *f)
{
	struct vhost_scsi *vs;
	struct vhost_virtqueue **vqs;
	int r = -ENOMEM, i;

	vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
	if (!vs) {
		vs = vzalloc(sizeof(*vs));
		if (!vs)
			goto err_vs;
	}

	vqs = kmalloc(VHOST_SCSI_MAX_VQ * sizeof(*vqs), GFP_KERNEL);
	if (!vqs)
		goto err_vqs;

	vhost_work_init(&vs->vs_completion_work, vhost_scsi_complete_cmd_work);
	vhost_work_init(&vs->vs_event_work, vhost_scsi_evt_work);

	vs->vs_events_nr = 0;
	vs->vs_events_missed = false;

	vqs[VHOST_SCSI_VQ_CTL] = &vs->vqs[VHOST_SCSI_VQ_CTL].vq;
	vqs[VHOST_SCSI_VQ_EVT] = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
	vs->vqs[VHOST_SCSI_VQ_CTL].vq.handle_kick = vhost_scsi_ctl_handle_kick;
	vs->vqs[VHOST_SCSI_VQ_EVT].vq.handle_kick = vhost_scsi_evt_handle_kick;
	for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) {
		vqs[i] = &vs->vqs[i].vq;
		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
	}
	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ);

	vhost_scsi_init_inflight(vs, NULL);

	f->private_data = vs;
	return 0;

err_vqs:
	kvfree(vs);
err_vs:
	return r;
}

static int vhost_scsi_release(struct inode *inode, struct file *f)
{
	struct vhost_scsi *vs = f->private_data;
	struct vhost_scsi_target t;

	mutex_lock(&vs->dev.mutex);
	memcpy(t.vhost_wwpn, vs->vs_vhost_wwpn, sizeof(t.vhost_wwpn));
	mutex_unlock(&vs->dev.mutex);
	vhost_scsi_clear_endpoint(vs, &t);
	vhost_dev_stop(&vs->dev);
	vhost_dev_cleanup(&vs->dev, false);
	/* Jobs can re-queue themselves in evt kick handler. Do extra flush. */
	vhost_scsi_flush(vs);
	kfree(vs->dev.vqs);
	kvfree(vs);
	return 0;
}

static long
vhost_scsi_ioctl(struct file *f,
		 unsigned int ioctl,
		 unsigned long arg)
{
	struct vhost_scsi *vs = f->private_data;
	struct vhost_scsi_target backend;
	void __user *argp = (void __user *)arg;
	u64 __user *featurep = argp;
	u32 __user *eventsp = argp;
	u32 events_missed;
	u64 features;
	int r, abi_version = VHOST_SCSI_ABI_VERSION;
	struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;

	switch (ioctl) {
	case VHOST_SCSI_SET_ENDPOINT:
		if (copy_from_user(&backend, argp, sizeof backend))
			return -EFAULT;
		if (backend.reserved != 0)
			return -EOPNOTSUPP;

		return vhost_scsi_set_endpoint(vs, &backend);
	case VHOST_SCSI_CLEAR_ENDPOINT:
		if (copy_from_user(&backend, argp, sizeof backend))
			return -EFAULT;
		if (backend.reserved != 0)
			return -EOPNOTSUPP;

		return vhost_scsi_clear_endpoint(vs, &backend);
	case VHOST_SCSI_GET_ABI_VERSION:
		if (copy_to_user(argp, &abi_version, sizeof abi_version))
			return -EFAULT;
		return 0;
	case VHOST_SCSI_SET_EVENTS_MISSED:
		if (get_user(events_missed, eventsp))
			return -EFAULT;
		mutex_lock(&vq->mutex);
		vs->vs_events_missed = events_missed;
		mutex_unlock(&vq->mutex);
		return 0;
	case VHOST_SCSI_GET_EVENTS_MISSED:
		mutex_lock(&vq->mutex);
		events_missed = vs->vs_events_missed;
		mutex_unlock(&vq->mutex);
		if (put_user(events_missed, eventsp))
			return -EFAULT;
		return 0;
	case VHOST_GET_FEATURES:
		features = VHOST_SCSI_FEATURES;
		if (copy_to_user(featurep, &features, sizeof features))
			return -EFAULT;
		return 0;
	case VHOST_SET_FEATURES:
		if (copy_from_user(&features, featurep, sizeof features))
			return -EFAULT;
		return vhost_scsi_set_features(vs, features);
	default:
		mutex_lock(&vs->dev.mutex);
		r = vhost_dev_ioctl(&vs->dev, ioctl, argp);
		/* TODO: flush backend after dev ioctl. */
		if (r == -ENOIOCTLCMD)
			r = vhost_vring_ioctl(&vs->dev, ioctl, argp);
		mutex_unlock(&vs->dev.mutex);
		return r;
	}
}

#ifdef CONFIG_COMPAT
static long vhost_scsi_compat_ioctl(struct file *f, unsigned int ioctl,
				unsigned long arg)
{
	return vhost_scsi_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
}
#endif

static const struct file_operations vhost_scsi_fops = {
	.owner          = THIS_MODULE,
	.release        = vhost_scsi_release,
	.unlocked_ioctl = vhost_scsi_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= vhost_scsi_compat_ioctl,
#endif
	.open           = vhost_scsi_open,
	.llseek		= noop_llseek,
};

static struct miscdevice vhost_scsi_misc = {
	MISC_DYNAMIC_MINOR,
	"vhost-scsi",
	&vhost_scsi_fops,
};

static int __init vhost_scsi_register(void)
{
	return misc_register(&vhost_scsi_misc);
}

static void vhost_scsi_deregister(void)
{
	misc_deregister(&vhost_scsi_misc);
}

static char *vhost_scsi_dump_proto_id(struct vhost_scsi_tport *tport)
{
	switch (tport->tport_proto_id) {
	case SCSI_PROTOCOL_SAS:
		return "SAS";
	case SCSI_PROTOCOL_FCP:
		return "FCP";
	case SCSI_PROTOCOL_ISCSI:
		return "iSCSI";
	default:
		break;
	}

	return "Unknown";
}

static void
vhost_scsi_do_plug(struct vhost_scsi_tpg *tpg,
		  struct se_lun *lun, bool plug)
{

	struct vhost_scsi *vs = tpg->vhost_scsi;
	struct vhost_virtqueue *vq;
	u32 reason;

	if (!vs)
		return;

	mutex_lock(&vs->dev.mutex);

	if (plug)
		reason = VIRTIO_SCSI_EVT_RESET_RESCAN;
	else
		reason = VIRTIO_SCSI_EVT_RESET_REMOVED;

	vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
	mutex_lock(&vq->mutex);
	if (vhost_has_feature(vq, VIRTIO_SCSI_F_HOTPLUG))
		vhost_scsi_send_evt(vs, tpg, lun,
				   VIRTIO_SCSI_T_TRANSPORT_RESET, reason);
	mutex_unlock(&vq->mutex);
	mutex_unlock(&vs->dev.mutex);
}

static void vhost_scsi_hotplug(struct vhost_scsi_tpg *tpg, struct se_lun *lun)
{
	vhost_scsi_do_plug(tpg, lun, true);
}

static void vhost_scsi_hotunplug(struct vhost_scsi_tpg *tpg, struct se_lun *lun)
{
	vhost_scsi_do_plug(tpg, lun, false);
}

static int vhost_scsi_port_link(struct se_portal_group *se_tpg,
			       struct se_lun *lun)
{
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);

	mutex_lock(&vhost_scsi_mutex);

	mutex_lock(&tpg->tv_tpg_mutex);
	tpg->tv_tpg_port_count++;
	mutex_unlock(&tpg->tv_tpg_mutex);

	vhost_scsi_hotplug(tpg, lun);

	mutex_unlock(&vhost_scsi_mutex);

	return 0;
}

static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg,
				  struct se_lun *lun)
{
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);

	mutex_lock(&vhost_scsi_mutex);

	mutex_lock(&tpg->tv_tpg_mutex);
	tpg->tv_tpg_port_count--;
	mutex_unlock(&tpg->tv_tpg_mutex);

	vhost_scsi_hotunplug(tpg, lun);

	mutex_unlock(&vhost_scsi_mutex);
}

static void vhost_scsi_free_cmd_map_res(struct vhost_scsi_nexus *nexus,
				       struct se_session *se_sess)
{
	struct vhost_scsi_cmd *tv_cmd;
	unsigned int i;

	if (!se_sess->sess_cmd_map)
		return;

	for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
		tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];

		kfree(tv_cmd->tvc_sgl);
		kfree(tv_cmd->tvc_prot_sgl);
		kfree(tv_cmd->tvc_upages);
	}
}

static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store(
		struct config_item *item, const char *page, size_t count)
{
	struct se_portal_group *se_tpg = attrib_to_tpg(item);
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);
	unsigned long val;
	int ret = kstrtoul(page, 0, &val);

	if (ret) {
		pr_err("kstrtoul() returned %d for fabric_prot_type\n", ret);
		return ret;
	}
	if (val != 0 && val != 1 && val != 3) {
		pr_err("Invalid vhost_scsi fabric_prot_type: %lu\n", val);
		return -EINVAL;
	}
	tpg->tv_fabric_prot_type = val;

	return count;
}

static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_show(
		struct config_item *item, char *page)
{
	struct se_portal_group *se_tpg = attrib_to_tpg(item);
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);

	return sprintf(page, "%d\n", tpg->tv_fabric_prot_type);
}

CONFIGFS_ATTR(vhost_scsi_tpg_attrib_, fabric_prot_type);

static struct configfs_attribute *vhost_scsi_tpg_attrib_attrs[] = {
	&vhost_scsi_tpg_attrib_attr_fabric_prot_type,
	NULL,
};

static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg,
				const char *name)
{
	struct se_portal_group *se_tpg;
	struct se_session *se_sess;
	struct vhost_scsi_nexus *tv_nexus;
	struct vhost_scsi_cmd *tv_cmd;
	unsigned int i;

	mutex_lock(&tpg->tv_tpg_mutex);
	if (tpg->tpg_nexus) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		pr_debug("tpg->tpg_nexus already exists\n");
		return -EEXIST;
	}
	se_tpg = &tpg->se_tpg;

	tv_nexus = kzalloc(sizeof(struct vhost_scsi_nexus), GFP_KERNEL);
	if (!tv_nexus) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		pr_err("Unable to allocate struct vhost_scsi_nexus\n");
		return -ENOMEM;
	}
	/*
	 *  Initialize the struct se_session pointer and setup tagpool
	 *  for struct vhost_scsi_cmd descriptors
	 */
	tv_nexus->tvn_se_sess = transport_init_session_tags(
					VHOST_SCSI_DEFAULT_TAGS,
					sizeof(struct vhost_scsi_cmd),
					TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS);
	if (IS_ERR(tv_nexus->tvn_se_sess)) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		kfree(tv_nexus);
		return -ENOMEM;
	}
	se_sess = tv_nexus->tvn_se_sess;
	for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
		tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];

		tv_cmd->tvc_sgl = kzalloc(sizeof(struct scatterlist) *
					VHOST_SCSI_PREALLOC_SGLS, GFP_KERNEL);
		if (!tv_cmd->tvc_sgl) {
			mutex_unlock(&tpg->tv_tpg_mutex);
			pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
			goto out;
		}

		tv_cmd->tvc_upages = kzalloc(sizeof(struct page *) *
					VHOST_SCSI_PREALLOC_UPAGES, GFP_KERNEL);
		if (!tv_cmd->tvc_upages) {
			mutex_unlock(&tpg->tv_tpg_mutex);
			pr_err("Unable to allocate tv_cmd->tvc_upages\n");
			goto out;
		}

		tv_cmd->tvc_prot_sgl = kzalloc(sizeof(struct scatterlist) *
					VHOST_SCSI_PREALLOC_PROT_SGLS, GFP_KERNEL);
		if (!tv_cmd->tvc_prot_sgl) {
			mutex_unlock(&tpg->tv_tpg_mutex);
			pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
			goto out;
		}
	}
	/*
	 * Since we are running in 'demo mode' this call with generate a
	 * struct se_node_acl for the vhost_scsi struct se_portal_group with
	 * the SCSI Initiator port name of the passed configfs group 'name'.
	 */
	tv_nexus->tvn_se_sess->se_node_acl = core_tpg_check_initiator_node_acl(
				se_tpg, (unsigned char *)name);
	if (!tv_nexus->tvn_se_sess->se_node_acl) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		pr_debug("core_tpg_check_initiator_node_acl() failed"
				" for %s\n", name);
		goto out;
	}
	/*
	 * Now register the TCM vhost virtual I_T Nexus as active.
	 */
	transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
			tv_nexus->tvn_se_sess, tv_nexus);
	tpg->tpg_nexus = tv_nexus;

	mutex_unlock(&tpg->tv_tpg_mutex);
	return 0;

out:
	vhost_scsi_free_cmd_map_res(tv_nexus, se_sess);
	transport_free_session(se_sess);
	kfree(tv_nexus);
	return -ENOMEM;
}

static int vhost_scsi_drop_nexus(struct vhost_scsi_tpg *tpg)
{
	struct se_session *se_sess;
	struct vhost_scsi_nexus *tv_nexus;

	mutex_lock(&tpg->tv_tpg_mutex);
	tv_nexus = tpg->tpg_nexus;
	if (!tv_nexus) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		return -ENODEV;
	}

	se_sess = tv_nexus->tvn_se_sess;
	if (!se_sess) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		return -ENODEV;
	}

	if (tpg->tv_tpg_port_count != 0) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		pr_err("Unable to remove TCM_vhost I_T Nexus with"
			" active TPG port count: %d\n",
			tpg->tv_tpg_port_count);
		return -EBUSY;
	}

	if (tpg->tv_tpg_vhost_count != 0) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		pr_err("Unable to remove TCM_vhost I_T Nexus with"
			" active TPG vhost count: %d\n",
			tpg->tv_tpg_vhost_count);
		return -EBUSY;
	}

	pr_debug("TCM_vhost_ConfigFS: Removing I_T Nexus to emulated"
		" %s Initiator Port: %s\n", vhost_scsi_dump_proto_id(tpg->tport),
		tv_nexus->tvn_se_sess->se_node_acl->initiatorname);

	vhost_scsi_free_cmd_map_res(tv_nexus, se_sess);
	/*
	 * Release the SCSI I_T Nexus to the emulated vhost Target Port
	 */
	transport_deregister_session(tv_nexus->tvn_se_sess);
	tpg->tpg_nexus = NULL;
	mutex_unlock(&tpg->tv_tpg_mutex);

	kfree(tv_nexus);
	return 0;
}

static ssize_t vhost_scsi_tpg_nexus_show(struct config_item *item, char *page)
{
	struct se_portal_group *se_tpg = to_tpg(item);
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);
	struct vhost_scsi_nexus *tv_nexus;
	ssize_t ret;

	mutex_lock(&tpg->tv_tpg_mutex);
	tv_nexus = tpg->tpg_nexus;
	if (!tv_nexus) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		return -ENODEV;
	}
	ret = snprintf(page, PAGE_SIZE, "%s\n",
			tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
	mutex_unlock(&tpg->tv_tpg_mutex);

	return ret;
}

static ssize_t vhost_scsi_tpg_nexus_store(struct config_item *item,
		const char *page, size_t count)
{
	struct se_portal_group *se_tpg = to_tpg(item);
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);
	struct vhost_scsi_tport *tport_wwn = tpg->tport;
	unsigned char i_port[VHOST_SCSI_NAMELEN], *ptr, *port_ptr;
	int ret;
	/*
	 * Shutdown the active I_T nexus if 'NULL' is passed..
	 */
	if (!strncmp(page, "NULL", 4)) {
		ret = vhost_scsi_drop_nexus(tpg);
		return (!ret) ? count : ret;
	}
	/*
	 * Otherwise make sure the passed virtual Initiator port WWN matches
	 * the fabric protocol_id set in vhost_scsi_make_tport(), and call
	 * vhost_scsi_make_nexus().
	 */
	if (strlen(page) >= VHOST_SCSI_NAMELEN) {
		pr_err("Emulated NAA Sas Address: %s, exceeds"
				" max: %d\n", page, VHOST_SCSI_NAMELEN);
		return -EINVAL;
	}
	snprintf(&i_port[0], VHOST_SCSI_NAMELEN, "%s", page);

	ptr = strstr(i_port, "naa.");
	if (ptr) {
		if (tport_wwn->tport_proto_id != SCSI_PROTOCOL_SAS) {
			pr_err("Passed SAS Initiator Port %s does not"
				" match target port protoid: %s\n", i_port,
				vhost_scsi_dump_proto_id(tport_wwn));
			return -EINVAL;
		}
		port_ptr = &i_port[0];
		goto check_newline;
	}
	ptr = strstr(i_port, "fc.");
	if (ptr) {
		if (tport_wwn->tport_proto_id != SCSI_PROTOCOL_FCP) {
			pr_err("Passed FCP Initiator Port %s does not"
				" match target port protoid: %s\n", i_port,
				vhost_scsi_dump_proto_id(tport_wwn));
			return -EINVAL;
		}
		port_ptr = &i_port[3]; /* Skip over "fc." */
		goto check_newline;
	}
	ptr = strstr(i_port, "iqn.");
	if (ptr) {
		if (tport_wwn->tport_proto_id != SCSI_PROTOCOL_ISCSI) {
			pr_err("Passed iSCSI Initiator Port %s does not"
				" match target port protoid: %s\n", i_port,
				vhost_scsi_dump_proto_id(tport_wwn));
			return -EINVAL;
		}
		port_ptr = &i_port[0];
		goto check_newline;
	}
	pr_err("Unable to locate prefix for emulated Initiator Port:"
			" %s\n", i_port);
	return -EINVAL;
	/*
	 * Clear any trailing newline for the NAA WWN
	 */
check_newline:
	if (i_port[strlen(i_port)-1] == '\n')
		i_port[strlen(i_port)-1] = '\0';

	ret = vhost_scsi_make_nexus(tpg, port_ptr);
	if (ret < 0)
		return ret;

	return count;
}

CONFIGFS_ATTR(vhost_scsi_tpg_, nexus);

static struct configfs_attribute *vhost_scsi_tpg_attrs[] = {
	&vhost_scsi_tpg_attr_nexus,
	NULL,
};

static struct se_portal_group *
vhost_scsi_make_tpg(struct se_wwn *wwn,
		   struct config_group *group,
		   const char *name)
{
	struct vhost_scsi_tport *tport = container_of(wwn,
			struct vhost_scsi_tport, tport_wwn);

	struct vhost_scsi_tpg *tpg;
	u16 tpgt;
	int ret;

	if (strstr(name, "tpgt_") != name)
		return ERR_PTR(-EINVAL);
	if (kstrtou16(name + 5, 10, &tpgt) || tpgt >= VHOST_SCSI_MAX_TARGET)
		return ERR_PTR(-EINVAL);

	tpg = kzalloc(sizeof(struct vhost_scsi_tpg), GFP_KERNEL);
	if (!tpg) {
		pr_err("Unable to allocate struct vhost_scsi_tpg");
		return ERR_PTR(-ENOMEM);
	}
	mutex_init(&tpg->tv_tpg_mutex);
	INIT_LIST_HEAD(&tpg->tv_tpg_list);
	tpg->tport = tport;
	tpg->tport_tpgt = tpgt;

	ret = core_tpg_register(wwn, &tpg->se_tpg, tport->tport_proto_id);
	if (ret < 0) {
		kfree(tpg);
		return NULL;
	}
	mutex_lock(&vhost_scsi_mutex);
	list_add_tail(&tpg->tv_tpg_list, &vhost_scsi_list);
	mutex_unlock(&vhost_scsi_mutex);

	return &tpg->se_tpg;
}

static void vhost_scsi_drop_tpg(struct se_portal_group *se_tpg)
{
	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
				struct vhost_scsi_tpg, se_tpg);

	mutex_lock(&vhost_scsi_mutex);
	list_del(&tpg->tv_tpg_list);
	mutex_unlock(&vhost_scsi_mutex);
	/*
	 * Release the virtual I_T Nexus for this vhost TPG
	 */
	vhost_scsi_drop_nexus(tpg);
	/*
	 * Deregister the se_tpg from TCM..
	 */
	core_tpg_deregister(se_tpg);
	kfree(tpg);
}

static struct se_wwn *
vhost_scsi_make_tport(struct target_fabric_configfs *tf,
		     struct config_group *group,
		     const char *name)
{
	struct vhost_scsi_tport *tport;
	char *ptr;
	u64 wwpn = 0;
	int off = 0;

	/* if (vhost_scsi_parse_wwn(name, &wwpn, 1) < 0)
		return ERR_PTR(-EINVAL); */

	tport = kzalloc(sizeof(struct vhost_scsi_tport), GFP_KERNEL);
	if (!tport) {
		pr_err("Unable to allocate struct vhost_scsi_tport");
		return ERR_PTR(-ENOMEM);
	}
	tport->tport_wwpn = wwpn;
	/*
	 * Determine the emulated Protocol Identifier and Target Port Name
	 * based on the incoming configfs directory name.
	 */
	ptr = strstr(name, "naa.");
	if (ptr) {
		tport->tport_proto_id = SCSI_PROTOCOL_SAS;
		goto check_len;
	}
	ptr = strstr(name, "fc.");
	if (ptr) {
		tport->tport_proto_id = SCSI_PROTOCOL_FCP;
		off = 3; /* Skip over "fc." */
		goto check_len;
	}
	ptr = strstr(name, "iqn.");
	if (ptr) {
		tport->tport_proto_id = SCSI_PROTOCOL_ISCSI;
		goto check_len;
	}

	pr_err("Unable to locate prefix for emulated Target Port:"
			" %s\n", name);
	kfree(tport);
	return ERR_PTR(-EINVAL);

check_len:
	if (strlen(name) >= VHOST_SCSI_NAMELEN) {
		pr_err("Emulated %s Address: %s, exceeds"
			" max: %d\n", name, vhost_scsi_dump_proto_id(tport),
			VHOST_SCSI_NAMELEN);
		kfree(tport);
		return ERR_PTR(-EINVAL);
	}
	snprintf(&tport->tport_name[0], VHOST_SCSI_NAMELEN, "%s", &name[off]);

	pr_debug("TCM_VHost_ConfigFS: Allocated emulated Target"
		" %s Address: %s\n", vhost_scsi_dump_proto_id(tport), name);

	return &tport->tport_wwn;
}

static void vhost_scsi_drop_tport(struct se_wwn *wwn)
{
	struct vhost_scsi_tport *tport = container_of(wwn,
				struct vhost_scsi_tport, tport_wwn);

	pr_debug("TCM_VHost_ConfigFS: Deallocating emulated Target"
		" %s Address: %s\n", vhost_scsi_dump_proto_id(tport),
		tport->tport_name);

	kfree(tport);
}

static ssize_t
vhost_scsi_wwn_version_show(struct config_item *item, char *page)
{
	return sprintf(page, "TCM_VHOST fabric module %s on %s/%s"
		"on "UTS_RELEASE"\n", VHOST_SCSI_VERSION, utsname()->sysname,
		utsname()->machine);
}

CONFIGFS_ATTR_RO(vhost_scsi_wwn_, version);

static struct configfs_attribute *vhost_scsi_wwn_attrs[] = {
	&vhost_scsi_wwn_attr_version,
	NULL,
};

static struct target_core_fabric_ops vhost_scsi_ops = {
	.module				= THIS_MODULE,
	.name				= "vhost",
	.get_fabric_name		= vhost_scsi_get_fabric_name,
	.tpg_get_wwn			= vhost_scsi_get_fabric_wwn,
	.tpg_get_tag			= vhost_scsi_get_tpgt,
	.tpg_check_demo_mode		= vhost_scsi_check_true,
	.tpg_check_demo_mode_cache	= vhost_scsi_check_true,
	.tpg_check_demo_mode_write_protect = vhost_scsi_check_false,
	.tpg_check_prod_mode_write_protect = vhost_scsi_check_false,
	.tpg_check_prot_fabric_only	= vhost_scsi_check_prot_fabric_only,
	.tpg_get_inst_index		= vhost_scsi_tpg_get_inst_index,
	.release_cmd			= vhost_scsi_release_cmd,
	.check_stop_free		= vhost_scsi_check_stop_free,
	.shutdown_session		= vhost_scsi_shutdown_session,
	.close_session			= vhost_scsi_close_session,
	.sess_get_index			= vhost_scsi_sess_get_index,
	.sess_get_initiator_sid		= NULL,
	.write_pending			= vhost_scsi_write_pending,
	.write_pending_status		= vhost_scsi_write_pending_status,
	.set_default_node_attributes	= vhost_scsi_set_default_node_attrs,
	.get_cmd_state			= vhost_scsi_get_cmd_state,
	.queue_data_in			= vhost_scsi_queue_data_in,
	.queue_status			= vhost_scsi_queue_status,
	.queue_tm_rsp			= vhost_scsi_queue_tm_rsp,
	.aborted_task			= vhost_scsi_aborted_task,
	/*
	 * Setup callers for generic logic in target_core_fabric_configfs.c
	 */
	.fabric_make_wwn		= vhost_scsi_make_tport,
	.fabric_drop_wwn		= vhost_scsi_drop_tport,
	.fabric_make_tpg		= vhost_scsi_make_tpg,
	.fabric_drop_tpg		= vhost_scsi_drop_tpg,
	.fabric_post_link		= vhost_scsi_port_link,
	.fabric_pre_unlink		= vhost_scsi_port_unlink,

	.tfc_wwn_attrs			= vhost_scsi_wwn_attrs,
	.tfc_tpg_base_attrs		= vhost_scsi_tpg_attrs,
	.tfc_tpg_attrib_attrs		= vhost_scsi_tpg_attrib_attrs,
};

static int __init vhost_scsi_init(void)
{
	int ret = -ENOMEM;

	pr_debug("TCM_VHOST fabric module %s on %s/%s"
		" on "UTS_RELEASE"\n", VHOST_SCSI_VERSION, utsname()->sysname,
		utsname()->machine);

	/*
	 * Use our own dedicated workqueue for submitting I/O into
	 * target core to avoid contention within system_wq.
	 */
	vhost_scsi_workqueue = alloc_workqueue("vhost_scsi", 0, 0);
	if (!vhost_scsi_workqueue)
		goto out;

	ret = vhost_scsi_register();
	if (ret < 0)
		goto out_destroy_workqueue;

	ret = target_register_template(&vhost_scsi_ops);
	if (ret < 0)
		goto out_vhost_scsi_deregister;

	return 0;

out_vhost_scsi_deregister:
	vhost_scsi_deregister();
out_destroy_workqueue:
	destroy_workqueue(vhost_scsi_workqueue);
out:
	return ret;
};

static void vhost_scsi_exit(void)
{
	target_unregister_template(&vhost_scsi_ops);
	vhost_scsi_deregister();
	destroy_workqueue(vhost_scsi_workqueue);
};

MODULE_DESCRIPTION("VHOST_SCSI series fabric driver");
MODULE_ALIAS("tcm_vhost");
MODULE_LICENSE("GPL");
module_init(vhost_scsi_init);
module_exit(vhost_scsi_exit);