summaryrefslogtreecommitdiff
path: root/drivers/vhost/scsi.c
blob: 718fa4e0b31ec2ae5abe902a784d941ac4d56adf (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
// SPDX-License-Identifier: GPL-2.0+
/*******************************************************************************
 * Vhost kernel TCM fabric driver for virtio SCSI initiators
 *
 * (C) Copyright 2010-2013 Datera, Inc.
 * (C) Copyright 2010-2012 IBM Corp.
 *
 * Authors: Nicholas A. Bellinger <nab@daterainc.com>
 *          Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
 ****************************************************************************/

#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 <linux/blk_types.h>
#include <linux/bio.h>
#include <linux/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 "vhost.h"

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

/* Max number of requests before requeueing the job.
 * Using this limit prevents one virtqueue from starving others with
 * request.
 */
#define VHOST_SCSI_WEIGHT 256

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_target_queue_cmd() */
	u32 tvc_lun;
	u32 copied_iov:1;
	const void *saved_iter_addr;
	struct iov_iter saved_iter;
	/* 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;
	/* 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_IO_VQ	1024
#define VHOST_SCSI_MAX_EVENT	128

static unsigned vhost_scsi_max_io_vqs = 128;
module_param_named(max_io_vqs, vhost_scsi_max_io_vqs, uint, 0644);
MODULE_PARM_DESC(max_io_vqs, "Set the max number of IO virtqueues a vhost scsi device can support. The default is 128. The max is 1024.");

struct vhost_scsi_virtqueue {
	struct vhost_virtqueue vq;
	struct vhost_scsi *vs;
	/*
	 * 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_cmd *scsi_cmds;
	struct sbitmap scsi_tags;
	int max_cmds;

	struct vhost_work completion_work;
	struct llist_head completion_list;
};

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;
	struct vhost_scsi_inflight **old_inflight;

	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 */
};

struct vhost_scsi_tmf {
	struct vhost_work vwork;
	struct work_struct flush_work;
	struct vhost_scsi *vhost;
	struct vhost_scsi_virtqueue *svq;

	struct se_cmd se_cmd;
	u8 scsi_resp;
	struct vhost_scsi_inflight *inflight;
	struct iovec resp_iov;
	int in_iovs;
	int vq_desc;
};

/*
 * Context for processing request and control queue operations.
 */
struct vhost_scsi_ctx {
	int head;
	unsigned int out, in;
	size_t req_size, rsp_size;
	size_t out_size, in_size;
	u8 *target, *lunp;
	void *req;
	struct iov_iter out_iter;
};

/*
 * Global mutex to protect vhost_scsi TPG list for vhost IOCTLs and LIO
 * configfs management operations.
 */
static DEFINE_MUTEX(vhost_scsi_mutex);
static LIST_HEAD(vhost_scsi_list);

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 < vs->dev.nvqs;  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 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 void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd)
{
	struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd,
				struct vhost_scsi_cmd, tvc_se_cmd);
	struct vhost_scsi_virtqueue *svq = container_of(tv_cmd->tvc_vq,
				struct vhost_scsi_virtqueue, vq);
	struct vhost_scsi_inflight *inflight = tv_cmd->inflight;
	int i;

	if (tv_cmd->tvc_sgl_count) {
		for (i = 0; i < tv_cmd->tvc_sgl_count; i++) {
			if (tv_cmd->copied_iov)
				__free_page(sg_page(&tv_cmd->tvc_sgl[i]));
			else
				put_page(sg_page(&tv_cmd->tvc_sgl[i]));
		}
		kfree(tv_cmd->saved_iter_addr);
	}
	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]));
	}

	sbitmap_clear_bit(&svq->scsi_tags, se_cmd->map_tag);
	vhost_scsi_put_inflight(inflight);
}

static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf)
{
	struct vhost_scsi_inflight *inflight = tmf->inflight;

	kfree(tmf);
	vhost_scsi_put_inflight(inflight);
}

static void vhost_scsi_drop_cmds(struct vhost_scsi_virtqueue *svq)
{
	struct vhost_scsi_cmd *cmd, *t;
	struct llist_node *llnode;

	llnode = llist_del_all(&svq->completion_list);
	llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list)
		vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd);
}

static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
{
	if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) {
		struct vhost_scsi_tmf *tmf = container_of(se_cmd,
					struct vhost_scsi_tmf, se_cmd);

		schedule_work(&tmf->flush_work);
	} else {
		struct vhost_scsi_cmd *cmd = container_of(se_cmd,
					struct vhost_scsi_cmd, tvc_se_cmd);
		struct vhost_scsi_virtqueue *svq =  container_of(cmd->tvc_vq,
					struct vhost_scsi_virtqueue, vq);

		llist_add(&cmd->tvc_completion_list, &svq->completion_list);
		if (!vhost_vq_work_queue(&svq->vq, &svq->completion_work))
			vhost_scsi_drop_cmds(svq);
	}
}

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_queue_data_in(struct se_cmd *se_cmd)
{
	transport_generic_free_cmd(se_cmd, 0);
	return 0;
}

static int vhost_scsi_queue_status(struct se_cmd *se_cmd)
{
	transport_generic_free_cmd(se_cmd, 0);
	return 0;
}

static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd)
{
	struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf,
						  se_cmd);

	tmf->scsi_resp = se_cmd->se_tmr_req->response;
	transport_generic_free_cmd(&tmf->se_cmd, 0);
}

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 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 (!vhost_vq_get_backend(vq)) {
		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_complete_events(struct vhost_scsi *vs, bool drop)
{
	struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
	struct vhost_scsi_evt *evt, *t;
	struct llist_node *llnode;

	mutex_lock(&vq->mutex);
	llnode = llist_del_all(&vs->vs_event_list);
	llist_for_each_entry_safe(evt, t, llnode, list) {
		if (!drop)
			vhost_scsi_do_evt_work(vs, evt);
		vhost_scsi_free_evt(vs, evt);
	}
	mutex_unlock(&vq->mutex);
}

static void vhost_scsi_evt_work(struct vhost_work *work)
{
	struct vhost_scsi *vs = container_of(work, struct vhost_scsi,
					     vs_event_work);
	vhost_scsi_complete_events(vs, false);
}

static int vhost_scsi_copy_sgl_to_iov(struct vhost_scsi_cmd *cmd)
{
	struct iov_iter *iter = &cmd->saved_iter;
	struct scatterlist *sg = cmd->tvc_sgl;
	struct page *page;
	size_t len;
	int i;

	for (i = 0; i < cmd->tvc_sgl_count; i++) {
		page = sg_page(&sg[i]);
		len = sg[i].length;

		if (copy_page_to_iter(page, 0, len, iter) != len) {
			pr_err("Could not copy data while handling misaligned cmd. Error %zu\n",
			       len);
			return -1;
		}
	}

	return 0;
}

/* 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_virtqueue *svq = container_of(work,
				struct vhost_scsi_virtqueue, completion_work);
	struct virtio_scsi_cmd_resp v_rsp;
	struct vhost_scsi_cmd *cmd, *t;
	struct llist_node *llnode;
	struct se_cmd *se_cmd;
	struct iov_iter iov_iter;
	bool signal = false;
	int ret;

	llnode = llist_del_all(&svq->completion_list);
	llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list) {
		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));

		if (cmd->saved_iter_addr && vhost_scsi_copy_sgl_to_iov(cmd)) {
			v_rsp.response = VIRTIO_SCSI_S_BAD_TARGET;
		} else {
			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, ITER_DEST, 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))) {
			signal = true;

			vhost_add_used(cmd->tvc_vq, cmd->tvc_vq_desc, 0);
		} else
			pr_err("Faulted on virtio_scsi_cmd_resp\n");

		vhost_scsi_release_cmd_res(se_cmd);
	}

	if (signal)
		vhost_signal(&svq->vs->dev, &svq->vq);
}

static struct vhost_scsi_cmd *
vhost_scsi_get_cmd(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_virtqueue *svq = container_of(vq,
					struct vhost_scsi_virtqueue, vq);
	struct vhost_scsi_cmd *cmd;
	struct vhost_scsi_nexus *tv_nexus;
	struct scatterlist *sg, *prot_sg;
	struct iovec *tvc_resp_iov;
	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);
	}

	tag = sbitmap_get(&svq->scsi_tags);
	if (tag < 0) {
		pr_err("Unable to obtain tag for vhost_scsi_cmd\n");
		return ERR_PTR(-ENOMEM);
	}

	cmd = &svq->scsi_cmds[tag];
	sg = cmd->tvc_sgl;
	prot_sg = cmd->tvc_prot_sgl;
	pages = cmd->tvc_upages;
	tvc_resp_iov = cmd->tvc_resp_iov;
	memset(cmd, 0, sizeof(*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);
	cmd->tvc_resp_iov = tvc_resp_iov;

	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,
		      struct iov_iter *iter,
		      struct scatterlist *sgl,
		      bool is_prot)
{
	struct page **pages = cmd->tvc_upages;
	struct scatterlist *sg = sgl;
	ssize_t bytes, mapped_bytes;
	size_t offset, mapped_offset;
	unsigned int npages = 0;

	bytes = iov_iter_get_pages2(iter, pages, LONG_MAX,
				VHOST_SCSI_PREALLOC_UPAGES, &offset);
	/* No pages were pinned */
	if (bytes <= 0)
		return bytes < 0 ? bytes : -EFAULT;

	mapped_bytes = bytes;
	mapped_offset = offset;

	while (bytes) {
		unsigned n = min_t(unsigned, PAGE_SIZE - offset, bytes);
		/*
		 * The block layer requires bios/requests to be a multiple of
		 * 512 bytes, but Windows can send us vecs that are misaligned.
		 * This can result in bios and later requests with misaligned
		 * sizes if we have to break up a cmd/scatterlist into multiple
		 * bios.
		 *
		 * We currently only break up a command into multiple bios if
		 * we hit the vec/seg limit, so check if our sgl_count is
		 * greater than the max and if a vec in the cmd has a
		 * misaligned offset/size.
		 */
		if (!is_prot &&
		    (offset & (SECTOR_SIZE - 1) || n & (SECTOR_SIZE - 1)) &&
		    cmd->tvc_sgl_count > BIO_MAX_VECS) {
			WARN_ONCE(true,
				  "vhost-scsi detected misaligned IO. Performance may be degraded.");
			goto revert_iter_get_pages;
		}

		sg_set_page(sg++, pages[npages++], n, offset);
		bytes -= n;
		offset = 0;
	}

	return npages;

revert_iter_get_pages:
	iov_iter_revert(iter, mapped_bytes);

	npages = 0;
	while (mapped_bytes) {
		unsigned int n = min_t(unsigned int, PAGE_SIZE - mapped_offset,
				       mapped_bytes);

		put_page(pages[npages++]);

		mapped_bytes -= n;
		mapped_offset = 0;
	}

	return -EINVAL;
}

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

	if (!iter || !iter_iov(iter)) {
		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_copy_iov_to_sgl(struct vhost_scsi_cmd *cmd, struct iov_iter *iter,
			   struct scatterlist *sg, int sg_count)
{
	size_t len = iov_iter_count(iter);
	unsigned int nbytes = 0;
	struct page *page;
	int i;

	if (cmd->tvc_data_direction == DMA_FROM_DEVICE) {
		cmd->saved_iter_addr = dup_iter(&cmd->saved_iter, iter,
						GFP_KERNEL);
		if (!cmd->saved_iter_addr)
			return -ENOMEM;
	}

	for (i = 0; i < sg_count; i++) {
		page = alloc_page(GFP_KERNEL);
		if (!page) {
			i--;
			goto err;
		}

		nbytes = min_t(unsigned int, PAGE_SIZE, len);
		sg_set_page(&sg[i], page, nbytes, 0);

		if (cmd->tvc_data_direction == DMA_TO_DEVICE &&
		    copy_page_from_iter(page, 0, nbytes, iter) != nbytes)
			goto err;

		len -= nbytes;
	}

	cmd->copied_iov = 1;
	return 0;

err:
	pr_err("Could not read %u bytes while handling misaligned cmd\n",
	       nbytes);

	for (; i >= 0; i--)
		__free_page(sg_page(&sg[i]));
	kfree(cmd->saved_iter_addr);
	return -ENOMEM;
}

static int
vhost_scsi_map_iov_to_sgl(struct vhost_scsi_cmd *cmd, struct iov_iter *iter,
			  struct scatterlist *sg, int sg_count, bool is_prot)
{
	struct scatterlist *p = sg;
	size_t revert_bytes;
	int ret;

	while (iov_iter_count(iter)) {
		ret = vhost_scsi_map_to_sgl(cmd, iter, sg, is_prot);
		if (ret < 0) {
			revert_bytes = 0;

			while (p < sg) {
				struct page *page = sg_page(p);

				if (page) {
					put_page(page);
					revert_bytes += p->length;
				}
				p++;
			}

			iov_iter_revert(iter, revert_bytes);
			return ret;
		}
		sg += ret;
	}

	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;

	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_map_iov_to_sgl(cmd, prot_iter,
						cmd->tvc_prot_sgl,
						cmd->tvc_prot_sgl_count, true);
		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_map_iov_to_sgl(cmd, data_iter, cmd->tvc_sgl,
					cmd->tvc_sgl_count, false);
	if (ret == -EINVAL) {
		sg_init_table(cmd->tvc_sgl, cmd->tvc_sgl_count);
		ret = vhost_scsi_copy_iov_to_sgl(cmd, 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_target_queue_cmd(struct vhost_scsi_cmd *cmd)
{
	struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
	struct vhost_scsi_nexus *tv_nexus;
	struct scatterlist *sg_ptr, *sg_prot_ptr = NULL;

	/* 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;
	target_init_cmd(se_cmd, tv_nexus->tvn_se_sess, &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);

	if (target_submit_prep(se_cmd, cmd->tvc_cdb, sg_ptr,
			       cmd->tvc_sgl_count, NULL, 0, sg_prot_ptr,
			       cmd->tvc_prot_sgl_count, GFP_KERNEL))
		return;

	target_submit(se_cmd);
}

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 int
vhost_scsi_get_desc(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
		    struct vhost_scsi_ctx *vc)
{
	int ret = -ENXIO;

	vc->head = vhost_get_vq_desc(vq, vq->iov,
				     ARRAY_SIZE(vq->iov), &vc->out, &vc->in,
				     NULL, NULL);

	pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n",
		 vc->head, vc->out, vc->in);

	/* On error, stop handling until the next kick. */
	if (unlikely(vc->head < 0))
		goto done;

	/* Nothing new?  Wait for eventfd to tell us they refilled. */
	if (vc->head == vq->num) {
		if (unlikely(vhost_enable_notify(&vs->dev, vq))) {
			vhost_disable_notify(&vs->dev, vq);
			ret = -EAGAIN;
		}
		goto done;
	}

	/*
	 * Get the size of request and response buffers.
	 * FIXME: Not correct for BIDI operation
	 */
	vc->out_size = iov_length(vq->iov, vc->out);
	vc->in_size = iov_length(&vq->iov[vc->out], vc->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(&vc->out_iter, ITER_SOURCE, vq->iov, vc->out, vc->out_size);
	ret = 0;

done:
	return ret;
}

static int
vhost_scsi_chk_size(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc)
{
	if (unlikely(vc->in_size < vc->rsp_size)) {
		vq_err(vq,
		       "Response buf too small, need min %zu bytes got %zu",
		       vc->rsp_size, vc->in_size);
		return -EINVAL;
	} else if (unlikely(vc->out_size < vc->req_size)) {
		vq_err(vq,
		       "Request buf too small, need min %zu bytes got %zu",
		       vc->req_size, vc->out_size);
		return -EIO;
	}

	return 0;
}

static int
vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc,
		   struct vhost_scsi_tpg **tpgp)
{
	int ret = -EIO;

	if (unlikely(!copy_from_iter_full(vc->req, vc->req_size,
					  &vc->out_iter))) {
		vq_err(vq, "Faulted on copy_from_iter_full\n");
	} else if (unlikely(*vc->lunp != 1)) {
		/* virtio-scsi spec requires byte 0 of the lun to be 1 */
		vq_err(vq, "Illegal virtio-scsi lun: %u\n", *vc->lunp);
	} else {
		struct vhost_scsi_tpg **vs_tpg, *tpg = NULL;

		if (vc->target) {
			/* validated at handler entry */
			vs_tpg = vhost_vq_get_backend(vq);
			tpg = READ_ONCE(vs_tpg[*vc->target]);
			if (unlikely(!tpg)) {
				vq_err(vq, "Target 0x%x does not exist\n", *vc->target);
				goto out;
			}
		}

		if (tpgp)
			*tpgp = tpg;
		ret = 0;
	}
out:
	return ret;
}

static u16 vhost_buf_to_lun(u8 *lun_buf)
{
	return ((lun_buf[2] << 8) | lun_buf[3]) & 0x3FFF;
}

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_ctx vc;
	struct vhost_scsi_cmd *cmd;
	struct iov_iter in_iter, prot_iter, data_iter;
	u64 tag;
	u32 exp_data_len, data_direction;
	int ret, prot_bytes, i, c = 0;
	u16 lun;
	u8 task_attr;
	bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI);
	void *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 = vhost_vq_get_backend(vq);
	if (!vs_tpg)
		goto out;

	memset(&vc, 0, sizeof(vc));
	vc.rsp_size = sizeof(struct virtio_scsi_cmd_resp);

	vhost_disable_notify(&vs->dev, vq);

	do {
		ret = vhost_scsi_get_desc(vs, vq, &vc);
		if (ret)
			goto err;

		/*
		 * Setup pointers and values based upon different virtio-scsi
		 * request header if T10_PI is enabled in KVM guest.
		 */
		if (t10_pi) {
			vc.req = &v_req_pi;
			vc.req_size = sizeof(v_req_pi);
			vc.lunp = &v_req_pi.lun[0];
			vc.target = &v_req_pi.lun[1];
		} else {
			vc.req = &v_req;
			vc.req_size = sizeof(v_req);
			vc.lunp = &v_req.lun[0];
			vc.target = &v_req.lun[1];
		}

		/*
		 * Validate the size of request and response buffers.
		 * Check for a sane response buffer so we can report
		 * early errors back to the guest.
		 */
		ret = vhost_scsi_chk_size(vq, &vc);
		if (ret)
			goto err;

		ret = vhost_scsi_get_req(vq, &vc, &tpg);
		if (ret)
			goto err;

		ret = -EIO;	/* bad target on any error from here on */

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

			iov_iter_init(&in_iter, ITER_DEST, &vq->iov[vc.out], vc.in,
				      vc.rsp_size + exp_data_len);
			iov_iter_advance(&in_iter, vc.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");
					goto err;
				}
				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");
					goto err;
				}
				prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesin);
			}
			/*
			 * Set prot_iter to data_iter and truncate it to
			 * prot_bytes, and advance data_iter past any
			 * preceding 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_truncate(&prot_iter, prot_bytes);
				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 = vhost_buf_to_lun(v_req_pi.lun);
		} else {
			tag = vhost64_to_cpu(vq, v_req.tag);
			task_attr = v_req.task_attr;
			cdb = &v_req.cdb[0];
			lun = vhost_buf_to_lun(v_req.lun);
		}
		/*
		 * 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);
				goto err;
		}
		cmd = vhost_scsi_get_cmd(vq, tpg, cdb, tag, lun, task_attr,
					 exp_data_len + prot_bytes,
					 data_direction);
		if (IS_ERR(cmd)) {
			vq_err(vq, "vhost_scsi_get_cmd failed %ld\n",
			       PTR_ERR(cmd));
			goto err;
		}
		cmd->tvc_vhost = vs;
		cmd->tvc_vq = vq;
		for (i = 0; i < vc.in ; i++)
			cmd->tvc_resp_iov[i] = vq->iov[vc.out + i];
		cmd->tvc_in_iovs = vc.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) {
			if (unlikely(vhost_scsi_mapal(cmd, prot_bytes,
						      &prot_iter, exp_data_len,
						      &data_iter))) {
				vq_err(vq, "Failed to map iov to sgl\n");
				vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd);
				goto err;
			}
		}
		/*
		 * 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 = vc.head;
		vhost_scsi_target_queue_cmd(cmd);
		ret = 0;
err:
		/*
		 * ENXIO:  No more requests, or read error, wait for next kick
		 * EINVAL: Invalid response buffer, drop the request
		 * EIO:    Respond with bad target
		 * EAGAIN: Pending request
		 */
		if (ret == -ENXIO)
			break;
		else if (ret == -EIO)
			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
out:
	mutex_unlock(&vq->mutex);
}

static void
vhost_scsi_send_tmf_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
			 int in_iovs, int vq_desc, struct iovec *resp_iov,
			 int tmf_resp_code)
{
	struct virtio_scsi_ctrl_tmf_resp rsp;
	struct iov_iter iov_iter;
	int ret;

	pr_debug("%s\n", __func__);
	memset(&rsp, 0, sizeof(rsp));
	rsp.response = tmf_resp_code;

	iov_iter_init(&iov_iter, ITER_DEST, resp_iov, in_iovs, sizeof(rsp));

	ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
	if (likely(ret == sizeof(rsp)))
		vhost_add_used_and_signal(&vs->dev, vq, vq_desc, 0);
	else
		pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n");
}

static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
{
	struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf,
						  vwork);
	int resp_code;

	if (tmf->scsi_resp == TMR_FUNCTION_COMPLETE)
		resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED;
	else
		resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;

	vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
				 tmf->vq_desc, &tmf->resp_iov, resp_code);
	vhost_scsi_release_tmf_res(tmf);
}

static void vhost_scsi_tmf_flush_work(struct work_struct *work)
{
	struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf,
						 flush_work);
	struct vhost_virtqueue *vq = &tmf->svq->vq;
	/*
	 * Make sure we have sent responses for other commands before we
	 * send our response.
	 */
	vhost_dev_flush(vq->dev);
	if (!vhost_vq_work_queue(vq, &tmf->vwork))
		vhost_scsi_release_tmf_res(tmf);
}

static void
vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg,
		      struct vhost_virtqueue *vq,
		      struct virtio_scsi_ctrl_tmf_req *vtmf,
		      struct vhost_scsi_ctx *vc)
{
	struct vhost_scsi_virtqueue *svq = container_of(vq,
					struct vhost_scsi_virtqueue, vq);
	struct vhost_scsi_tmf *tmf;

	if (vhost32_to_cpu(vq, vtmf->subtype) !=
	    VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET)
		goto send_reject;

	if (!tpg->tpg_nexus || !tpg->tpg_nexus->tvn_se_sess) {
		pr_err("Unable to locate active struct vhost_scsi_nexus for LUN RESET.\n");
		goto send_reject;
	}

	tmf = kzalloc(sizeof(*tmf), GFP_KERNEL);
	if (!tmf)
		goto send_reject;

	INIT_WORK(&tmf->flush_work, vhost_scsi_tmf_flush_work);
	vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work);
	tmf->vhost = vs;
	tmf->svq = svq;
	tmf->resp_iov = vq->iov[vc->out];
	tmf->vq_desc = vc->head;
	tmf->in_iovs = vc->in;
	tmf->inflight = vhost_scsi_get_inflight(vq);

	if (target_submit_tmr(&tmf->se_cmd, tpg->tpg_nexus->tvn_se_sess, NULL,
			      vhost_buf_to_lun(vtmf->lun), NULL,
			      TMR_LUN_RESET, GFP_KERNEL, 0,
			      TARGET_SCF_ACK_KREF) < 0) {
		vhost_scsi_release_tmf_res(tmf);
		goto send_reject;
	}

	return;

send_reject:
	vhost_scsi_send_tmf_resp(vs, vq, vc->in, vc->head, &vq->iov[vc->out],
				 VIRTIO_SCSI_S_FUNCTION_REJECTED);
}

static void
vhost_scsi_send_an_resp(struct vhost_scsi *vs,
			struct vhost_virtqueue *vq,
			struct vhost_scsi_ctx *vc)
{
	struct virtio_scsi_ctrl_an_resp rsp;
	struct iov_iter iov_iter;
	int ret;

	pr_debug("%s\n", __func__);
	memset(&rsp, 0, sizeof(rsp));	/* event_actual = 0 */
	rsp.response = VIRTIO_SCSI_S_OK;

	iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in, sizeof(rsp));

	ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
	if (likely(ret == sizeof(rsp)))
		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
	else
		pr_err("Faulted on virtio_scsi_ctrl_an_resp\n");
}

static void
vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
{
	struct vhost_scsi_tpg *tpg;
	union {
		__virtio32 type;
		struct virtio_scsi_ctrl_an_req an;
		struct virtio_scsi_ctrl_tmf_req tmf;
	} v_req;
	struct vhost_scsi_ctx vc;
	size_t typ_size;
	int ret, c = 0;

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

	memset(&vc, 0, sizeof(vc));

	vhost_disable_notify(&vs->dev, vq);

	do {
		ret = vhost_scsi_get_desc(vs, vq, &vc);
		if (ret)
			goto err;

		/*
		 * Get the request type first in order to setup
		 * other parameters dependent on the type.
		 */
		vc.req = &v_req.type;
		typ_size = sizeof(v_req.type);

		if (unlikely(!copy_from_iter_full(vc.req, typ_size,
						  &vc.out_iter))) {
			vq_err(vq, "Faulted on copy_from_iter tmf type\n");
			/*
			 * The size of the response buffer depends on the
			 * request type and must be validated against it.
			 * Since the request type is not known, don't send
			 * a response.
			 */
			continue;
		}

		switch (vhost32_to_cpu(vq, v_req.type)) {
		case VIRTIO_SCSI_T_TMF:
			vc.req = &v_req.tmf;
			vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req);
			vc.rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp);
			vc.lunp = &v_req.tmf.lun[0];
			vc.target = &v_req.tmf.lun[1];
			break;
		case VIRTIO_SCSI_T_AN_QUERY:
		case VIRTIO_SCSI_T_AN_SUBSCRIBE:
			vc.req = &v_req.an;
			vc.req_size = sizeof(struct virtio_scsi_ctrl_an_req);
			vc.rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp);
			vc.lunp = &v_req.an.lun[0];
			vc.target = NULL;
			break;
		default:
			vq_err(vq, "Unknown control request %d", v_req.type);
			continue;
		}

		/*
		 * Validate the size of request and response buffers.
		 * Check for a sane response buffer so we can report
		 * early errors back to the guest.
		 */
		ret = vhost_scsi_chk_size(vq, &vc);
		if (ret)
			goto err;

		/*
		 * Get the rest of the request now that its size is known.
		 */
		vc.req += typ_size;
		vc.req_size -= typ_size;

		ret = vhost_scsi_get_req(vq, &vc, &tpg);
		if (ret)
			goto err;

		if (v_req.type == VIRTIO_SCSI_T_TMF)
			vhost_scsi_handle_tmf(vs, tpg, vq, &v_req.tmf, &vc);
		else
			vhost_scsi_send_an_resp(vs, vq, &vc);
err:
		/*
		 * ENXIO:  No more requests, or read error, wait for next kick
		 * EINVAL: Invalid response buffer, drop the request
		 * EIO:    Respond with bad target
		 * EAGAIN: Pending request
		 */
		if (ret == -ENXIO)
			break;
		else if (ret == -EIO)
			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
out:
	mutex_unlock(&vq->mutex);
}

static void vhost_scsi_ctl_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);

	pr_debug("%s: The handling func for control queue.\n", __func__);
	vhost_scsi_ctl_handle_vq(vs, vq);
}

static void
vhost_scsi_send_evt(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
		    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);
	if (!vhost_vq_work_queue(vq, &vs->vs_event_work))
		vhost_scsi_complete_events(vs, true);
}

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 (!vhost_vq_get_backend(vq))
		goto out;

	if (vs->vs_events_missed)
		vhost_scsi_send_evt(vs, vq, 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);
}

/* Callers must hold dev mutex */
static void vhost_scsi_flush(struct vhost_scsi *vs)
{
	int i;

	/* Init new inflight and remember the old inflight */
	vhost_scsi_init_inflight(vs, 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 < vs->dev.nvqs; i++)
		kref_put(&vs->old_inflight[i]->kref, vhost_scsi_done_inflight);

	/* Flush both the vhost poll and vhost work */
	vhost_dev_flush(&vs->dev);

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

static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq)
{
	struct vhost_scsi_virtqueue *svq = container_of(vq,
					struct vhost_scsi_virtqueue, vq);
	struct vhost_scsi_cmd *tv_cmd;
	unsigned int i;

	if (!svq->scsi_cmds)
		return;

	for (i = 0; i < svq->max_cmds; i++) {
		tv_cmd = &svq->scsi_cmds[i];

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

	sbitmap_free(&svq->scsi_tags);
	kfree(svq->scsi_cmds);
	svq->scsi_cmds = NULL;
}

static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds)
{
	struct vhost_scsi_virtqueue *svq = container_of(vq,
					struct vhost_scsi_virtqueue, vq);
	struct vhost_scsi_cmd *tv_cmd;
	unsigned int i;

	if (svq->scsi_cmds)
		return 0;

	if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL,
			      NUMA_NO_NODE, false, true))
		return -ENOMEM;
	svq->max_cmds = max_cmds;

	svq->scsi_cmds = kcalloc(max_cmds, sizeof(*tv_cmd), GFP_KERNEL);
	if (!svq->scsi_cmds) {
		sbitmap_free(&svq->scsi_tags);
		return -ENOMEM;
	}

	for (i = 0; i < max_cmds; i++) {
		tv_cmd = &svq->scsi_cmds[i];

		tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS,
					  sizeof(struct scatterlist),
					  GFP_KERNEL);
		if (!tv_cmd->tvc_sgl) {
			pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
			goto out;
		}

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

		tv_cmd->tvc_resp_iov = kcalloc(UIO_MAXIOV,
					       sizeof(struct iovec),
					       GFP_KERNEL);
		if (!tv_cmd->tvc_resp_iov) {
			pr_err("Unable to allocate tv_cmd->tvc_resp_iov\n");
			goto out;
		}

		tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
					       sizeof(struct scatterlist),
					       GFP_KERNEL);
		if (!tv_cmd->tvc_prot_sgl) {
			pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
			goto out;
		}
	}
	return 0;
out:
	vhost_scsi_destroy_vq_cmds(vq);
	return -ENOMEM;
}

/*
 * 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:
 *    vs->dev.mutex -> vhost_scsi_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(&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);

	mutex_lock(&vhost_scsi_mutex);
	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]) {
				mutex_unlock(&tpg->tv_tpg_mutex);
				mutex_unlock(&vhost_scsi_mutex);
				ret = -EEXIST;
				goto undepend;
			}
			/*
			 * 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("target_depend_item() failed: %d\n", ret);
				mutex_unlock(&tpg->tv_tpg_mutex);
				mutex_unlock(&vhost_scsi_mutex);
				goto undepend;
			}
			tpg->tv_tpg_vhost_count++;
			tpg->vhost_scsi = vs;
			vs_tpg[tpg->tport_tpgt] = tpg;
			match = true;
		}
		mutex_unlock(&tpg->tv_tpg_mutex);
	}
	mutex_unlock(&vhost_scsi_mutex);

	if (match) {
		memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
		       sizeof(vs->vs_vhost_wwpn));

		for (i = VHOST_SCSI_VQ_IO; i < vs->dev.nvqs; i++) {
			vq = &vs->vqs[i].vq;
			if (!vhost_vq_is_setup(vq))
				continue;

			ret = vhost_scsi_setup_vq_cmds(vq, vq->num);
			if (ret)
				goto destroy_vq_cmds;
		}

		for (i = 0; i < vs->dev.nvqs; i++) {
			vq = &vs->vqs[i].vq;
			mutex_lock(&vq->mutex);
			vhost_vq_set_backend(vq, vs_tpg);
			vhost_vq_init_access(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;
	goto out;

destroy_vq_cmds:
	for (i--; i >= VHOST_SCSI_VQ_IO; i--) {
		if (!vhost_vq_get_backend(&vs->vqs[i].vq))
			vhost_scsi_destroy_vq_cmds(&vs->vqs[i].vq);
	}
undepend:
	for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) {
		tpg = vs_tpg[i];
		if (tpg) {
			mutex_lock(&tpg->tv_tpg_mutex);
			tpg->vhost_scsi = NULL;
			tpg->tv_tpg_vhost_count--;
			mutex_unlock(&tpg->tv_tpg_mutex);
			target_undepend_item(&tpg->se_tpg.tpg_group.cg_item);
		}
	}
	kfree(vs_tpg);
out:
	mutex_unlock(&vs->dev.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(&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;

		tv_tport = tpg->tport;
		if (!tv_tport) {
			ret = -ENODEV;
			goto err_dev;
		}

		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_dev;
		}
		match = true;
	}
	if (!match)
		goto free_vs_tpg;

	/* Prevent new cmds from starting and accessing the tpgs/sessions */
	for (i = 0; i < vs->dev.nvqs; i++) {
		vq = &vs->vqs[i].vq;
		mutex_lock(&vq->mutex);
		vhost_vq_set_backend(vq, NULL);
		mutex_unlock(&vq->mutex);
	}
	/* Make sure cmds are not running before tearing them down. */
	vhost_scsi_flush(vs);

	for (i = 0; i < vs->dev.nvqs; i++) {
		vq = &vs->vqs[i].vq;
		vhost_scsi_destroy_vq_cmds(vq);
	}

	/*
	 * We can now release our hold on the tpg and sessions and userspace
	 * can free them after this point.
	 */
	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);

		tpg->tv_tpg_vhost_count--;
		tpg->vhost_scsi = NULL;
		vs->vs_tpg[target] = NULL;

		mutex_unlock(&tpg->tv_tpg_mutex);

		se_tpg = &tpg->se_tpg;
		target_undepend_item(&se_tpg->tpg_group.cg_item);
	}

free_vs_tpg:
	/*
	 * 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);
	return 0;

err_dev:
	mutex_unlock(&vs->dev.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 < vs->dev.nvqs; 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_virtqueue *svq;
	struct vhost_scsi *vs;
	struct vhost_virtqueue **vqs;
	int r = -ENOMEM, i, nvqs = vhost_scsi_max_io_vqs;

	vs = kvzalloc(sizeof(*vs), GFP_KERNEL);
	if (!vs)
		goto err_vs;

	if (nvqs > VHOST_SCSI_MAX_IO_VQ) {
		pr_err("Invalid max_io_vqs of %d. Using %d.\n", nvqs,
		       VHOST_SCSI_MAX_IO_VQ);
		nvqs = VHOST_SCSI_MAX_IO_VQ;
	} else if (nvqs == 0) {
		pr_err("Invalid max_io_vqs of %d. Using 1.\n", nvqs);
		nvqs = 1;
	}
	nvqs += VHOST_SCSI_VQ_IO;

	vs->old_inflight = kmalloc_array(nvqs, sizeof(*vs->old_inflight),
					 GFP_KERNEL | __GFP_ZERO);
	if (!vs->old_inflight)
		goto err_inflight;

	vs->vqs = kmalloc_array(nvqs, sizeof(*vs->vqs),
				GFP_KERNEL | __GFP_ZERO);
	if (!vs->vqs)
		goto err_vqs;

	vqs = kmalloc_array(nvqs, sizeof(*vqs), GFP_KERNEL);
	if (!vqs)
		goto err_local_vqs;

	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 < nvqs; i++) {
		svq = &vs->vqs[i];

		vqs[i] = &svq->vq;
		svq->vs = vs;
		init_llist_head(&svq->completion_list);
		vhost_work_init(&svq->completion_work,
				vhost_scsi_complete_cmd_work);
		svq->vq.handle_kick = vhost_scsi_handle_kick;
	}
	vhost_dev_init(&vs->dev, vqs, nvqs, UIO_MAXIOV,
		       VHOST_SCSI_WEIGHT, 0, true, NULL);

	vhost_scsi_init_inflight(vs, NULL);

	f->private_data = vs;
	return 0;

err_local_vqs:
	kfree(vs->vqs);
err_vqs:
	kfree(vs->old_inflight);
err_inflight:
	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);
	kfree(vs->dev.vqs);
	kfree(vs->vqs);
	kfree(vs->old_inflight);
	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);
	case VHOST_NEW_WORKER:
	case VHOST_FREE_WORKER:
	case VHOST_ATTACH_VRING_WORKER:
	case VHOST_GET_VRING_WORKER:
		mutex_lock(&vs->dev.mutex);
		r = vhost_worker_ioctl(&vs->dev, ioctl, argp);
		mutex_unlock(&vs->dev.mutex);
		return r;
	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;
	}
}

static const struct file_operations vhost_scsi_fops = {
	.owner          = THIS_MODULE,
	.release        = vhost_scsi_release,
	.unlocked_ioctl = vhost_scsi_ioctl,
	.compat_ioctl	= compat_ptr_ioctl,
	.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;

	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);
	/*
	 * We can't queue events if the backend has been cleared, because
	 * we could end up queueing an event after the flush.
	 */
	if (!vhost_vq_get_backend(vq))
		goto unlock;

	if (vhost_has_feature(vq, VIRTIO_SCSI_F_HOTPLUG))
		vhost_scsi_send_evt(vs, vq, tpg, lun,
				   VIRTIO_SCSI_T_TRANSPORT_RESET, reason);
unlock:
	mutex_unlock(&vq->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(&tpg->tv_tpg_mutex);
	tpg->tv_tpg_port_count++;
	vhost_scsi_hotplug(tpg, lun);
	mutex_unlock(&tpg->tv_tpg_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(&tpg->tv_tpg_mutex);
	tpg->tv_tpg_port_count--;
	vhost_scsi_hotunplug(tpg, lun);
	mutex_unlock(&tpg->tv_tpg_mutex);
}

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 sysfs_emit(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 vhost_scsi_nexus *tv_nexus;

	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;
	}

	tv_nexus = kzalloc(sizeof(*tv_nexus), GFP_KERNEL);
	if (!tv_nexus) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		pr_err("Unable to allocate struct vhost_scsi_nexus\n");
		return -ENOMEM;
	}
	/*
	 * 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 = target_setup_session(&tpg->se_tpg, 0, 0,
					TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
					(unsigned char *)name, tv_nexus, NULL);
	if (IS_ERR(tv_nexus->tvn_se_sess)) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		kfree(tv_nexus);
		return -ENOMEM;
	}
	tpg->tpg_nexus = tv_nexus;

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

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);

	/*
	 * Release the SCSI I_T Nexus to the emulated vhost Target Port
	 */
	target_remove_session(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 = sysfs_emit(page, "%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, 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(*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(*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 sysfs_emit(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 const struct target_core_fabric_ops vhost_scsi_ops = {
	.module				= THIS_MODULE,
	.fabric_name			= "vhost",
	.max_data_sg_nents		= VHOST_SCSI_PREALLOC_SGLS,
	.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_prot_fabric_only	= vhost_scsi_check_prot_fabric_only,
	.release_cmd			= vhost_scsi_release_cmd,
	.check_stop_free		= vhost_scsi_check_stop_free,
	.sess_get_initiator_sid		= NULL,
	.write_pending			= vhost_scsi_write_pending,
	.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,

	.default_submit_type		= TARGET_QUEUE_SUBMIT,
	.direct_submit_supp		= 1,
};

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);

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

	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:
	return ret;
};

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

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