summaryrefslogtreecommitdiff
path: root/drivers/scsi/sg.c
blob: ba9ba0e04f42587476a3d0472104aca342e4f4ef (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
/*
 *  History:
 *  Started: Aug 9 by Lawrence Foard (entropy@world.std.com),
 *           to allow user process control of SCSI devices.
 *  Development Sponsored by Killy Corp. NY NY
 *
 * Original driver (sg.c):
 *        Copyright (C) 1992 Lawrence Foard
 * Version 2 and 3 extensions to driver:
 *        Copyright (C) 1998 - 2014 Douglas Gilbert
 *
 * 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, or (at your option)
 * any later version.
 *
 */

static int sg_version_num = 30536;	/* 2 digits for each component */
#define SG_VERSION_STR "3.5.36"

/*
 *  D. P. Gilbert (dgilbert@interlog.com), notes:
 *      - scsi logging is available via SCSI_LOG_TIMEOUT macros. First
 *        the kernel/module needs to be built with CONFIG_SCSI_LOGGING
 *        (otherwise the macros compile to empty statements).
 *
 */
#include <linux/module.h>

#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/mtio.h>
#include <linux/ioctl.h>
#include <linux/slab.h>
#include <linux/fcntl.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/moduleparam.h>
#include <linux/cdev.h>
#include <linux/idr.h>
#include <linux/seq_file.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/blktrace_api.h>
#include <linux/mutex.h>
#include <linux/atomic.h>
#include <linux/ratelimit.h>
#include <linux/uio.h>
#include <linux/cred.h> /* for sg_check_file_access() */

#include "scsi.h"
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_driver.h>
#include <scsi/scsi_ioctl.h>
#include <scsi/sg.h>

#include "scsi_logging.h"

#ifdef CONFIG_SCSI_PROC_FS
#include <linux/proc_fs.h>
static char *sg_version_date = "20140603";

static int sg_proc_init(void);
#endif

#define SG_ALLOW_DIO_DEF 0

#define SG_MAX_DEVS 32768

/* SG_MAX_CDB_SIZE should be 260 (spc4r37 section 3.1.30) however the type
 * of sg_io_hdr::cmd_len can only represent 255. All SCSI commands greater
 * than 16 bytes are "variable length" whose length is a multiple of 4
 */
#define SG_MAX_CDB_SIZE 252

#define SG_DEFAULT_TIMEOUT mult_frac(SG_DEFAULT_TIMEOUT_USER, HZ, USER_HZ)

int sg_big_buff = SG_DEF_RESERVED_SIZE;
/* N.B. This variable is readable and writeable via
   /proc/scsi/sg/def_reserved_size . Each time sg_open() is called a buffer
   of this size (or less if there is not enough memory) will be reserved
   for use by this file descriptor. [Deprecated usage: this variable is also
   readable via /proc/sys/kernel/sg-big-buff if the sg driver is built into
   the kernel (i.e. it is not a module).] */
static int def_reserved_size = -1;	/* picks up init parameter */
static int sg_allow_dio = SG_ALLOW_DIO_DEF;

static int scatter_elem_sz = SG_SCATTER_SZ;
static int scatter_elem_sz_prev = SG_SCATTER_SZ;

#define SG_SECTOR_SZ 512

static int sg_add_device(struct device *, struct class_interface *);
static void sg_remove_device(struct device *, struct class_interface *);

static DEFINE_IDR(sg_index_idr);
static DEFINE_RWLOCK(sg_index_lock);	/* Also used to lock
							   file descriptor list for device */

static struct class_interface sg_interface = {
	.add_dev        = sg_add_device,
	.remove_dev     = sg_remove_device,
};

typedef struct sg_scatter_hold { /* holding area for scsi scatter gather info */
	unsigned short k_use_sg; /* Count of kernel scatter-gather pieces */
	unsigned sglist_len; /* size of malloc'd scatter-gather list ++ */
	unsigned bufflen;	/* Size of (aggregate) data buffer */
	struct page **pages;
	int page_order;
	char dio_in_use;	/* 0->indirect IO (or mmap), 1->dio */
	unsigned char cmd_opcode; /* first byte of command */
} Sg_scatter_hold;

struct sg_device;		/* forward declarations */
struct sg_fd;

typedef struct sg_request {	/* SG_MAX_QUEUE requests outstanding per file */
	struct list_head entry;	/* list entry */
	struct sg_fd *parentfp;	/* NULL -> not in use */
	Sg_scatter_hold data;	/* hold buffer, perhaps scatter list */
	sg_io_hdr_t header;	/* scsi command+info, see <scsi/sg.h> */
	unsigned char sense_b[SCSI_SENSE_BUFFERSIZE];
	char res_used;		/* 1 -> using reserve buffer, 0 -> not ... */
	char orphan;		/* 1 -> drop on sight, 0 -> normal */
	char sg_io_owned;	/* 1 -> packet belongs to SG_IO */
	/* done protected by rq_list_lock */
	char done;		/* 0->before bh, 1->before read, 2->read */
	struct request *rq;
	struct bio *bio;
	struct execute_work ew;
} Sg_request;

typedef struct sg_fd {		/* holds the state of a file descriptor */
	struct list_head sfd_siblings;  /* protected by device's sfd_lock */
	struct sg_device *parentdp;	/* owning device */
	wait_queue_head_t read_wait;	/* queue read until command done */
	rwlock_t rq_list_lock;	/* protect access to list in req_arr */
	struct mutex f_mutex;	/* protect against changes in this fd */
	int timeout;		/* defaults to SG_DEFAULT_TIMEOUT      */
	int timeout_user;	/* defaults to SG_DEFAULT_TIMEOUT_USER */
	Sg_scatter_hold reserve;	/* buffer held for this file descriptor */
	struct list_head rq_list; /* head of request list */
	struct fasync_struct *async_qp;	/* used by asynchronous notification */
	Sg_request req_arr[SG_MAX_QUEUE];	/* used as singly-linked list */
	char force_packid;	/* 1 -> pack_id input to read(), 0 -> ignored */
	char cmd_q;		/* 1 -> allow command queuing, 0 -> don't */
	unsigned char next_cmd_len; /* 0: automatic, >0: use on next write() */
	char keep_orphan;	/* 0 -> drop orphan (def), 1 -> keep for read() */
	char mmap_called;	/* 0 -> mmap() never called on this fd */
	char res_in_use;	/* 1 -> 'reserve' array in use */
	struct kref f_ref;
	struct execute_work ew;
} Sg_fd;

typedef struct sg_device { /* holds the state of each scsi generic device */
	struct scsi_device *device;
	wait_queue_head_t open_wait;    /* queue open() when O_EXCL present */
	struct mutex open_rel_lock;     /* held when in open() or release() */
	int sg_tablesize;	/* adapter's max scatter-gather table size */
	u32 index;		/* device index number */
	struct list_head sfds;
	rwlock_t sfd_lock;      /* protect access to sfd list */
	atomic_t detaching;     /* 0->device usable, 1->device detaching */
	bool exclude;		/* 1->open(O_EXCL) succeeded and is active */
	int open_cnt;		/* count of opens (perhaps < num(sfds) ) */
	char sgdebug;		/* 0->off, 1->sense, 9->dump dev, 10-> all devs */
	struct gendisk *disk;
	struct cdev * cdev;	/* char_dev [sysfs: /sys/cdev/major/sg<n>] */
	struct kref d_ref;
} Sg_device;

/* tasklet or soft irq callback */
static void sg_rq_end_io(struct request *rq, blk_status_t status);
static int sg_start_req(Sg_request *srp, unsigned char *cmd);
static int sg_finish_rem_req(Sg_request * srp);
static int sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size);
static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count,
			   Sg_request * srp);
static ssize_t sg_new_write(Sg_fd *sfp, struct file *file,
			const char __user *buf, size_t count, int blocking,
			int read_only, int sg_io_owned, Sg_request **o_srp);
static int sg_common_write(Sg_fd * sfp, Sg_request * srp,
			   unsigned char *cmnd, int timeout, int blocking);
static int sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer);
static void sg_remove_scat(Sg_fd * sfp, Sg_scatter_hold * schp);
static void sg_build_reserve(Sg_fd * sfp, int req_size);
static void sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size);
static void sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp);
static Sg_fd *sg_add_sfp(Sg_device * sdp);
static void sg_remove_sfp(struct kref *);
static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id);
static Sg_request *sg_add_request(Sg_fd * sfp);
static int sg_remove_request(Sg_fd * sfp, Sg_request * srp);
static Sg_device *sg_get_dev(int dev);
static void sg_device_destroy(struct kref *kref);

#define SZ_SG_HEADER sizeof(struct sg_header)
#define SZ_SG_IO_HDR sizeof(sg_io_hdr_t)
#define SZ_SG_IOVEC sizeof(sg_iovec_t)
#define SZ_SG_REQ_INFO sizeof(sg_req_info_t)

#define sg_printk(prefix, sdp, fmt, a...) \
	sdev_prefix_printk(prefix, (sdp)->device,		\
			   (sdp)->disk->disk_name, fmt, ##a)

/*
 * The SCSI interfaces that use read() and write() as an asynchronous variant of
 * ioctl(..., SG_IO, ...) are fundamentally unsafe, since there are lots of ways
 * to trigger read() and write() calls from various contexts with elevated
 * privileges. This can lead to kernel memory corruption (e.g. if these
 * interfaces are called through splice()) and privilege escalation inside
 * userspace (e.g. if a process with access to such a device passes a file
 * descriptor to a SUID binary as stdin/stdout/stderr).
 *
 * This function provides protection for the legacy API by restricting the
 * calling context.
 */
static int sg_check_file_access(struct file *filp, const char *caller)
{
	if (filp->f_cred != current_real_cred()) {
		pr_err_once("%s: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n",
			caller, task_tgid_vnr(current), current->comm);
		return -EPERM;
	}
	if (uaccess_kernel()) {
		pr_err_once("%s: process %d (%s) called from kernel context, this is not allowed.\n",
			caller, task_tgid_vnr(current), current->comm);
		return -EACCES;
	}
	return 0;
}

static int sg_allow_access(struct file *filp, unsigned char *cmd)
{
	struct sg_fd *sfp = filp->private_data;

	if (sfp->parentdp->device->type == TYPE_SCANNER)
		return 0;

	return blk_verify_command(cmd, filp->f_mode);
}

static int
open_wait(Sg_device *sdp, int flags)
{
	int retval = 0;

	if (flags & O_EXCL) {
		while (sdp->open_cnt > 0) {
			mutex_unlock(&sdp->open_rel_lock);
			retval = wait_event_interruptible(sdp->open_wait,
					(atomic_read(&sdp->detaching) ||
					 !sdp->open_cnt));
			mutex_lock(&sdp->open_rel_lock);

			if (retval) /* -ERESTARTSYS */
				return retval;
			if (atomic_read(&sdp->detaching))
				return -ENODEV;
		}
	} else {
		while (sdp->exclude) {
			mutex_unlock(&sdp->open_rel_lock);
			retval = wait_event_interruptible(sdp->open_wait,
					(atomic_read(&sdp->detaching) ||
					 !sdp->exclude));
			mutex_lock(&sdp->open_rel_lock);

			if (retval) /* -ERESTARTSYS */
				return retval;
			if (atomic_read(&sdp->detaching))
				return -ENODEV;
		}
	}

	return retval;
}

/* Returns 0 on success, else a negated errno value */
static int
sg_open(struct inode *inode, struct file *filp)
{
	int dev = iminor(inode);
	int flags = filp->f_flags;
	struct request_queue *q;
	Sg_device *sdp;
	Sg_fd *sfp;
	int retval;

	nonseekable_open(inode, filp);
	if ((flags & O_EXCL) && (O_RDONLY == (flags & O_ACCMODE)))
		return -EPERM; /* Can't lock it with read only access */
	sdp = sg_get_dev(dev);
	if (IS_ERR(sdp))
		return PTR_ERR(sdp);

	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
				      "sg_open: flags=0x%x\n", flags));

	/* This driver's module count bumped by fops_get in <linux/fs.h> */
	/* Prevent the device driver from vanishing while we sleep */
	retval = scsi_device_get(sdp->device);
	if (retval)
		goto sg_put;

	retval = scsi_autopm_get_device(sdp->device);
	if (retval)
		goto sdp_put;

	/* scsi_block_when_processing_errors() may block so bypass
	 * check if O_NONBLOCK. Permits SCSI commands to be issued
	 * during error recovery. Tread carefully. */
	if (!((flags & O_NONBLOCK) ||
	      scsi_block_when_processing_errors(sdp->device))) {
		retval = -ENXIO;
		/* we are in error recovery for this device */
		goto error_out;
	}

	mutex_lock(&sdp->open_rel_lock);
	if (flags & O_NONBLOCK) {
		if (flags & O_EXCL) {
			if (sdp->open_cnt > 0) {
				retval = -EBUSY;
				goto error_mutex_locked;
			}
		} else {
			if (sdp->exclude) {
				retval = -EBUSY;
				goto error_mutex_locked;
			}
		}
	} else {
		retval = open_wait(sdp, flags);
		if (retval) /* -ERESTARTSYS or -ENODEV */
			goto error_mutex_locked;
	}

	/* N.B. at this point we are holding the open_rel_lock */
	if (flags & O_EXCL)
		sdp->exclude = true;

	if (sdp->open_cnt < 1) {  /* no existing opens */
		sdp->sgdebug = 0;
		q = sdp->device->request_queue;
		sdp->sg_tablesize = queue_max_segments(q);
	}
	sfp = sg_add_sfp(sdp);
	if (IS_ERR(sfp)) {
		retval = PTR_ERR(sfp);
		goto out_undo;
	}

	filp->private_data = sfp;
	sdp->open_cnt++;
	mutex_unlock(&sdp->open_rel_lock);

	retval = 0;
sg_put:
	kref_put(&sdp->d_ref, sg_device_destroy);
	return retval;

out_undo:
	if (flags & O_EXCL) {
		sdp->exclude = false;   /* undo if error */
		wake_up_interruptible(&sdp->open_wait);
	}
error_mutex_locked:
	mutex_unlock(&sdp->open_rel_lock);
error_out:
	scsi_autopm_put_device(sdp->device);
sdp_put:
	scsi_device_put(sdp->device);
	goto sg_put;
}

/* Release resources associated with a successful sg_open()
 * Returns 0 on success, else a negated errno value */
static int
sg_release(struct inode *inode, struct file *filp)
{
	Sg_device *sdp;
	Sg_fd *sfp;

	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
		return -ENXIO;
	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_release\n"));

	mutex_lock(&sdp->open_rel_lock);
	scsi_autopm_put_device(sdp->device);
	kref_put(&sfp->f_ref, sg_remove_sfp);
	sdp->open_cnt--;

	/* possibly many open()s waiting on exlude clearing, start many;
	 * only open(O_EXCL)s wait on 0==open_cnt so only start one */
	if (sdp->exclude) {
		sdp->exclude = false;
		wake_up_interruptible_all(&sdp->open_wait);
	} else if (0 == sdp->open_cnt) {
		wake_up_interruptible(&sdp->open_wait);
	}
	mutex_unlock(&sdp->open_rel_lock);
	return 0;
}

static ssize_t
sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
{
	Sg_device *sdp;
	Sg_fd *sfp;
	Sg_request *srp;
	int req_pack_id = -1;
	sg_io_hdr_t *hp;
	struct sg_header *old_hdr = NULL;
	int retval = 0;

	/*
	 * This could cause a response to be stranded. Close the associated
	 * file descriptor to free up any resources being held.
	 */
	retval = sg_check_file_access(filp, __func__);
	if (retval)
		return retval;

	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
		return -ENXIO;
	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
				      "sg_read: count=%d\n", (int) count));

	if (!access_ok(VERIFY_WRITE, buf, count))
		return -EFAULT;
	if (sfp->force_packid && (count >= SZ_SG_HEADER)) {
		old_hdr = kmalloc(SZ_SG_HEADER, GFP_KERNEL);
		if (!old_hdr)
			return -ENOMEM;
		if (__copy_from_user(old_hdr, buf, SZ_SG_HEADER)) {
			retval = -EFAULT;
			goto free_old_hdr;
		}
		if (old_hdr->reply_len < 0) {
			if (count >= SZ_SG_IO_HDR) {
				sg_io_hdr_t *new_hdr;
				new_hdr = kmalloc(SZ_SG_IO_HDR, GFP_KERNEL);
				if (!new_hdr) {
					retval = -ENOMEM;
					goto free_old_hdr;
				}
				retval =__copy_from_user
				    (new_hdr, buf, SZ_SG_IO_HDR);
				req_pack_id = new_hdr->pack_id;
				kfree(new_hdr);
				if (retval) {
					retval = -EFAULT;
					goto free_old_hdr;
				}
			}
		} else
			req_pack_id = old_hdr->pack_id;
	}
	srp = sg_get_rq_mark(sfp, req_pack_id);
	if (!srp) {		/* now wait on packet to arrive */
		if (atomic_read(&sdp->detaching)) {
			retval = -ENODEV;
			goto free_old_hdr;
		}
		if (filp->f_flags & O_NONBLOCK) {
			retval = -EAGAIN;
			goto free_old_hdr;
		}
		retval = wait_event_interruptible(sfp->read_wait,
			(atomic_read(&sdp->detaching) ||
			(srp = sg_get_rq_mark(sfp, req_pack_id))));
		if (atomic_read(&sdp->detaching)) {
			retval = -ENODEV;
			goto free_old_hdr;
		}
		if (retval) {
			/* -ERESTARTSYS as signal hit process */
			goto free_old_hdr;
		}
	}
	if (srp->header.interface_id != '\0') {
		retval = sg_new_read(sfp, buf, count, srp);
		goto free_old_hdr;
	}

	hp = &srp->header;
	if (old_hdr == NULL) {
		old_hdr = kmalloc(SZ_SG_HEADER, GFP_KERNEL);
		if (! old_hdr) {
			retval = -ENOMEM;
			goto free_old_hdr;
		}
	}
	memset(old_hdr, 0, SZ_SG_HEADER);
	old_hdr->reply_len = (int) hp->timeout;
	old_hdr->pack_len = old_hdr->reply_len; /* old, strange behaviour */
	old_hdr->pack_id = hp->pack_id;
	old_hdr->twelve_byte =
	    ((srp->data.cmd_opcode >= 0xc0) && (12 == hp->cmd_len)) ? 1 : 0;
	old_hdr->target_status = hp->masked_status;
	old_hdr->host_status = hp->host_status;
	old_hdr->driver_status = hp->driver_status;
	if ((CHECK_CONDITION & hp->masked_status) ||
	    (DRIVER_SENSE & hp->driver_status))
		memcpy(old_hdr->sense_buffer, srp->sense_b,
		       sizeof (old_hdr->sense_buffer));
	switch (hp->host_status) {
	/* This setup of 'result' is for backward compatibility and is best
	   ignored by the user who should use target, host + driver status */
	case DID_OK:
	case DID_PASSTHROUGH:
	case DID_SOFT_ERROR:
		old_hdr->result = 0;
		break;
	case DID_NO_CONNECT:
	case DID_BUS_BUSY:
	case DID_TIME_OUT:
		old_hdr->result = EBUSY;
		break;
	case DID_BAD_TARGET:
	case DID_ABORT:
	case DID_PARITY:
	case DID_RESET:
	case DID_BAD_INTR:
		old_hdr->result = EIO;
		break;
	case DID_ERROR:
		old_hdr->result = (srp->sense_b[0] == 0 && 
				  hp->masked_status == GOOD) ? 0 : EIO;
		break;
	default:
		old_hdr->result = EIO;
		break;
	}

	/* Now copy the result back to the user buffer.  */
	if (count >= SZ_SG_HEADER) {
		if (__copy_to_user(buf, old_hdr, SZ_SG_HEADER)) {
			retval = -EFAULT;
			goto free_old_hdr;
		}
		buf += SZ_SG_HEADER;
		if (count > old_hdr->reply_len)
			count = old_hdr->reply_len;
		if (count > SZ_SG_HEADER) {
			if (sg_read_oxfer(srp, buf, count - SZ_SG_HEADER)) {
				retval = -EFAULT;
				goto free_old_hdr;
			}
		}
	} else
		count = (old_hdr->result == 0) ? 0 : -EIO;
	sg_finish_rem_req(srp);
	sg_remove_request(sfp, srp);
	retval = count;
free_old_hdr:
	kfree(old_hdr);
	return retval;
}

static ssize_t
sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp)
{
	sg_io_hdr_t *hp = &srp->header;
	int err = 0, err2;
	int len;

	if (count < SZ_SG_IO_HDR) {
		err = -EINVAL;
		goto err_out;
	}
	hp->sb_len_wr = 0;
	if ((hp->mx_sb_len > 0) && hp->sbp) {
		if ((CHECK_CONDITION & hp->masked_status) ||
		    (DRIVER_SENSE & hp->driver_status)) {
			int sb_len = SCSI_SENSE_BUFFERSIZE;
			sb_len = (hp->mx_sb_len > sb_len) ? sb_len : hp->mx_sb_len;
			len = 8 + (int) srp->sense_b[7];	/* Additional sense length field */
			len = (len > sb_len) ? sb_len : len;
			if (copy_to_user(hp->sbp, srp->sense_b, len)) {
				err = -EFAULT;
				goto err_out;
			}
			hp->sb_len_wr = len;
		}
	}
	if (hp->masked_status || hp->host_status || hp->driver_status)
		hp->info |= SG_INFO_CHECK;
	if (copy_to_user(buf, hp, SZ_SG_IO_HDR)) {
		err = -EFAULT;
		goto err_out;
	}
err_out:
	err2 = sg_finish_rem_req(srp);
	sg_remove_request(sfp, srp);
	return err ? : err2 ? : count;
}

static ssize_t
sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
{
	int mxsize, cmd_size, k;
	int input_size, blocking;
	unsigned char opcode;
	Sg_device *sdp;
	Sg_fd *sfp;
	Sg_request *srp;
	struct sg_header old_hdr;
	sg_io_hdr_t *hp;
	unsigned char cmnd[SG_MAX_CDB_SIZE];
	int retval;

	retval = sg_check_file_access(filp, __func__);
	if (retval)
		return retval;

	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
		return -ENXIO;
	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
				      "sg_write: count=%d\n", (int) count));
	if (atomic_read(&sdp->detaching))
		return -ENODEV;
	if (!((filp->f_flags & O_NONBLOCK) ||
	      scsi_block_when_processing_errors(sdp->device)))
		return -ENXIO;

	if (!access_ok(VERIFY_READ, buf, count))
		return -EFAULT;	/* protects following copy_from_user()s + get_user()s */
	if (count < SZ_SG_HEADER)
		return -EIO;
	if (__copy_from_user(&old_hdr, buf, SZ_SG_HEADER))
		return -EFAULT;
	blocking = !(filp->f_flags & O_NONBLOCK);
	if (old_hdr.reply_len < 0)
		return sg_new_write(sfp, filp, buf, count,
				    blocking, 0, 0, NULL);
	if (count < (SZ_SG_HEADER + 6))
		return -EIO;	/* The minimum scsi command length is 6 bytes. */

	if (!(srp = sg_add_request(sfp))) {
		SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sdp,
					      "sg_write: queue full\n"));
		return -EDOM;
	}
	buf += SZ_SG_HEADER;
	__get_user(opcode, buf);
	mutex_lock(&sfp->f_mutex);
	if (sfp->next_cmd_len > 0) {
		cmd_size = sfp->next_cmd_len;
		sfp->next_cmd_len = 0;	/* reset so only this write() effected */
	} else {
		cmd_size = COMMAND_SIZE(opcode);	/* based on SCSI command group */
		if ((opcode >= 0xc0) && old_hdr.twelve_byte)
			cmd_size = 12;
	}
	mutex_unlock(&sfp->f_mutex);
	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp,
		"sg_write:   scsi opcode=0x%02x, cmd_size=%d\n", (int) opcode, cmd_size));
/* Determine buffer size.  */
	input_size = count - cmd_size;
	mxsize = (input_size > old_hdr.reply_len) ? input_size : old_hdr.reply_len;
	mxsize -= SZ_SG_HEADER;
	input_size -= SZ_SG_HEADER;
	if (input_size < 0) {
		sg_remove_request(sfp, srp);
		return -EIO;	/* User did not pass enough bytes for this command. */
	}
	hp = &srp->header;
	hp->interface_id = '\0';	/* indicator of old interface tunnelled */
	hp->cmd_len = (unsigned char) cmd_size;
	hp->iovec_count = 0;
	hp->mx_sb_len = 0;
	if (input_size > 0)
		hp->dxfer_direction = (old_hdr.reply_len > SZ_SG_HEADER) ?
		    SG_DXFER_TO_FROM_DEV : SG_DXFER_TO_DEV;
	else
		hp->dxfer_direction = (mxsize > 0) ? SG_DXFER_FROM_DEV : SG_DXFER_NONE;
	hp->dxfer_len = mxsize;
	if ((hp->dxfer_direction == SG_DXFER_TO_DEV) ||
	    (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV))
		hp->dxferp = (char __user *)buf + cmd_size;
	else
		hp->dxferp = NULL;
	hp->sbp = NULL;
	hp->timeout = old_hdr.reply_len;	/* structure abuse ... */
	hp->flags = input_size;	/* structure abuse ... */
	hp->pack_id = old_hdr.pack_id;
	hp->usr_ptr = NULL;
	if (__copy_from_user(cmnd, buf, cmd_size))
		return -EFAULT;
	/*
	 * SG_DXFER_TO_FROM_DEV is functionally equivalent to SG_DXFER_FROM_DEV,
	 * but is is possible that the app intended SG_DXFER_TO_DEV, because there
	 * is a non-zero input_size, so emit a warning.
	 */
	if (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV) {
		printk_ratelimited(KERN_WARNING
				   "sg_write: data in/out %d/%d bytes "
				   "for SCSI command 0x%x-- guessing "
				   "data in;\n   program %s not setting "
				   "count and/or reply_len properly\n",
				   old_hdr.reply_len - (int)SZ_SG_HEADER,
				   input_size, (unsigned int) cmnd[0],
				   current->comm);
	}
	k = sg_common_write(sfp, srp, cmnd, sfp->timeout, blocking);
	return (k < 0) ? k : count;
}

static ssize_t
sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf,
		 size_t count, int blocking, int read_only, int sg_io_owned,
		 Sg_request **o_srp)
{
	int k;
	Sg_request *srp;
	sg_io_hdr_t *hp;
	unsigned char cmnd[SG_MAX_CDB_SIZE];
	int timeout;
	unsigned long ul_timeout;

	if (count < SZ_SG_IO_HDR)
		return -EINVAL;
	if (!access_ok(VERIFY_READ, buf, count))
		return -EFAULT; /* protects following copy_from_user()s + get_user()s */

	sfp->cmd_q = 1;	/* when sg_io_hdr seen, set command queuing on */
	if (!(srp = sg_add_request(sfp))) {
		SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sfp->parentdp,
					      "sg_new_write: queue full\n"));
		return -EDOM;
	}
	srp->sg_io_owned = sg_io_owned;
	hp = &srp->header;
	if (__copy_from_user(hp, buf, SZ_SG_IO_HDR)) {
		sg_remove_request(sfp, srp);
		return -EFAULT;
	}
	if (hp->interface_id != 'S') {
		sg_remove_request(sfp, srp);
		return -ENOSYS;
	}
	if (hp->flags & SG_FLAG_MMAP_IO) {
		if (hp->dxfer_len > sfp->reserve.bufflen) {
			sg_remove_request(sfp, srp);
			return -ENOMEM;	/* MMAP_IO size must fit in reserve buffer */
		}
		if (hp->flags & SG_FLAG_DIRECT_IO) {
			sg_remove_request(sfp, srp);
			return -EINVAL;	/* either MMAP_IO or DIRECT_IO (not both) */
		}
		if (sfp->res_in_use) {
			sg_remove_request(sfp, srp);
			return -EBUSY;	/* reserve buffer already being used */
		}
	}
	ul_timeout = msecs_to_jiffies(srp->header.timeout);
	timeout = (ul_timeout < INT_MAX) ? ul_timeout : INT_MAX;
	if ((!hp->cmdp) || (hp->cmd_len < 6) || (hp->cmd_len > sizeof (cmnd))) {
		sg_remove_request(sfp, srp);
		return -EMSGSIZE;
	}
	if (!access_ok(VERIFY_READ, hp->cmdp, hp->cmd_len)) {
		sg_remove_request(sfp, srp);
		return -EFAULT;	/* protects following copy_from_user()s + get_user()s */
	}
	if (__copy_from_user(cmnd, hp->cmdp, hp->cmd_len)) {
		sg_remove_request(sfp, srp);
		return -EFAULT;
	}
	if (read_only && sg_allow_access(file, cmnd)) {
		sg_remove_request(sfp, srp);
		return -EPERM;
	}
	k = sg_common_write(sfp, srp, cmnd, timeout, blocking);
	if (k < 0)
		return k;
	if (o_srp)
		*o_srp = srp;
	return count;
}

static int
sg_common_write(Sg_fd * sfp, Sg_request * srp,
		unsigned char *cmnd, int timeout, int blocking)
{
	int k, at_head;
	Sg_device *sdp = sfp->parentdp;
	sg_io_hdr_t *hp = &srp->header;

	srp->data.cmd_opcode = cmnd[0];	/* hold opcode of command */
	hp->status = 0;
	hp->masked_status = 0;
	hp->msg_status = 0;
	hp->info = 0;
	hp->host_status = 0;
	hp->driver_status = 0;
	hp->resid = 0;
	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp,
			"sg_common_write:  scsi opcode=0x%02x, cmd_size=%d\n",
			(int) cmnd[0], (int) hp->cmd_len));

	if (hp->dxfer_len >= SZ_256M)
		return -EINVAL;

	k = sg_start_req(srp, cmnd);
	if (k) {
		SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sfp->parentdp,
			"sg_common_write: start_req err=%d\n", k));
		sg_finish_rem_req(srp);
		sg_remove_request(sfp, srp);
		return k;	/* probably out of space --> ENOMEM */
	}
	if (atomic_read(&sdp->detaching)) {
		if (srp->bio) {
			scsi_req_free_cmd(scsi_req(srp->rq));
			blk_end_request_all(srp->rq, BLK_STS_IOERR);
			srp->rq = NULL;
		}

		sg_finish_rem_req(srp);
		sg_remove_request(sfp, srp);
		return -ENODEV;
	}

	hp->duration = jiffies_to_msecs(jiffies);
	if (hp->interface_id != '\0' &&	/* v3 (or later) interface */
	    (SG_FLAG_Q_AT_TAIL & hp->flags))
		at_head = 0;
	else
		at_head = 1;

	srp->rq->timeout = timeout;
	kref_get(&sfp->f_ref); /* sg_rq_end_io() does kref_put(). */
	blk_execute_rq_nowait(sdp->device->request_queue, sdp->disk,
			      srp->rq, at_head, sg_rq_end_io);
	return 0;
}

static int srp_done(Sg_fd *sfp, Sg_request *srp)
{
	unsigned long flags;
	int ret;

	read_lock_irqsave(&sfp->rq_list_lock, flags);
	ret = srp->done;
	read_unlock_irqrestore(&sfp->rq_list_lock, flags);
	return ret;
}

static int max_sectors_bytes(struct request_queue *q)
{
	unsigned int max_sectors = queue_max_sectors(q);

	max_sectors = min_t(unsigned int, max_sectors, INT_MAX >> 9);

	return max_sectors << 9;
}

static void
sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo)
{
	Sg_request *srp;
	int val;
	unsigned int ms;

	val = 0;
	list_for_each_entry(srp, &sfp->rq_list, entry) {
		if (val >= SG_MAX_QUEUE)
			break;
		rinfo[val].req_state = srp->done + 1;
		rinfo[val].problem =
			srp->header.masked_status &
			srp->header.host_status &
			srp->header.driver_status;
		if (srp->done)
			rinfo[val].duration =
				srp->header.duration;
		else {
			ms = jiffies_to_msecs(jiffies);
			rinfo[val].duration =
				(ms > srp->header.duration) ?
				(ms - srp->header.duration) : 0;
		}
		rinfo[val].orphan = srp->orphan;
		rinfo[val].sg_io_owned = srp->sg_io_owned;
		rinfo[val].pack_id = srp->header.pack_id;
		rinfo[val].usr_ptr = srp->header.usr_ptr;
		val++;
	}
}

static long
sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
{
	void __user *p = (void __user *)arg;
	int __user *ip = p;
	int result, val, read_only;
	Sg_device *sdp;
	Sg_fd *sfp;
	Sg_request *srp;
	unsigned long iflags;

	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
		return -ENXIO;

	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
				   "sg_ioctl: cmd=0x%x\n", (int) cmd_in));
	read_only = (O_RDWR != (filp->f_flags & O_ACCMODE));

	switch (cmd_in) {
	case SG_IO:
		if (atomic_read(&sdp->detaching))
			return -ENODEV;
		if (!scsi_block_when_processing_errors(sdp->device))
			return -ENXIO;
		if (!access_ok(VERIFY_WRITE, p, SZ_SG_IO_HDR))
			return -EFAULT;
		result = sg_new_write(sfp, filp, p, SZ_SG_IO_HDR,
				 1, read_only, 1, &srp);
		if (result < 0)
			return result;
		result = wait_event_interruptible(sfp->read_wait,
			(srp_done(sfp, srp) || atomic_read(&sdp->detaching)));
		if (atomic_read(&sdp->detaching))
			return -ENODEV;
		write_lock_irq(&sfp->rq_list_lock);
		if (srp->done) {
			srp->done = 2;
			write_unlock_irq(&sfp->rq_list_lock);
			result = sg_new_read(sfp, p, SZ_SG_IO_HDR, srp);
			return (result < 0) ? result : 0;
		}
		srp->orphan = 1;
		write_unlock_irq(&sfp->rq_list_lock);
		return result;	/* -ERESTARTSYS because signal hit process */
	case SG_SET_TIMEOUT:
		result = get_user(val, ip);
		if (result)
			return result;
		if (val < 0)
			return -EIO;
		if (val >= mult_frac((s64)INT_MAX, USER_HZ, HZ))
			val = min_t(s64, mult_frac((s64)INT_MAX, USER_HZ, HZ),
				    INT_MAX);
		sfp->timeout_user = val;
		sfp->timeout = mult_frac(val, HZ, USER_HZ);

		return 0;
	case SG_GET_TIMEOUT:	/* N.B. User receives timeout as return value */
				/* strange ..., for backward compatibility */
		return sfp->timeout_user;
	case SG_SET_FORCE_LOW_DMA:
		/*
		 * N.B. This ioctl never worked properly, but failed to
		 * return an error value. So returning '0' to keep compability
		 * with legacy applications.
		 */
		return 0;
	case SG_GET_LOW_DMA:
		return put_user((int) sdp->device->host->unchecked_isa_dma, ip);
	case SG_GET_SCSI_ID:
		if (!access_ok(VERIFY_WRITE, p, sizeof (sg_scsi_id_t)))
			return -EFAULT;
		else {
			sg_scsi_id_t __user *sg_idp = p;

			if (atomic_read(&sdp->detaching))
				return -ENODEV;
			__put_user((int) sdp->device->host->host_no,
				   &sg_idp->host_no);
			__put_user((int) sdp->device->channel,
				   &sg_idp->channel);
			__put_user((int) sdp->device->id, &sg_idp->scsi_id);
			__put_user((int) sdp->device->lun, &sg_idp->lun);
			__put_user((int) sdp->device->type, &sg_idp->scsi_type);
			__put_user((short) sdp->device->host->cmd_per_lun,
				   &sg_idp->h_cmd_per_lun);
			__put_user((short) sdp->device->queue_depth,
				   &sg_idp->d_queue_depth);
			__put_user(0, &sg_idp->unused[0]);
			__put_user(0, &sg_idp->unused[1]);
			return 0;
		}
	case SG_SET_FORCE_PACK_ID:
		result = get_user(val, ip);
		if (result)
			return result;
		sfp->force_packid = val ? 1 : 0;
		return 0;
	case SG_GET_PACK_ID:
		if (!access_ok(VERIFY_WRITE, ip, sizeof (int)))
			return -EFAULT;
		read_lock_irqsave(&sfp->rq_list_lock, iflags);
		list_for_each_entry(srp, &sfp->rq_list, entry) {
			if ((1 == srp->done) && (!srp->sg_io_owned)) {
				read_unlock_irqrestore(&sfp->rq_list_lock,
						       iflags);
				__put_user(srp->header.pack_id, ip);
				return 0;
			}
		}
		read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
		__put_user(-1, ip);
		return 0;
	case SG_GET_NUM_WAITING:
		read_lock_irqsave(&sfp->rq_list_lock, iflags);
		val = 0;
		list_for_each_entry(srp, &sfp->rq_list, entry) {
			if ((1 == srp->done) && (!srp->sg_io_owned))
				++val;
		}
		read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
		return put_user(val, ip);
	case SG_GET_SG_TABLESIZE:
		return put_user(sdp->sg_tablesize, ip);
	case SG_SET_RESERVED_SIZE:
		result = get_user(val, ip);
		if (result)
			return result;
                if (val < 0)
                        return -EINVAL;
		val = min_t(int, val,
			    max_sectors_bytes(sdp->device->request_queue));
		mutex_lock(&sfp->f_mutex);
		if (val != sfp->reserve.bufflen) {
			if (sfp->mmap_called ||
			    sfp->res_in_use) {
				mutex_unlock(&sfp->f_mutex);
				return -EBUSY;
			}

			sg_remove_scat(sfp, &sfp->reserve);
			sg_build_reserve(sfp, val);
		}
		mutex_unlock(&sfp->f_mutex);
		return 0;
	case SG_GET_RESERVED_SIZE:
		val = min_t(int, sfp->reserve.bufflen,
			    max_sectors_bytes(sdp->device->request_queue));
		return put_user(val, ip);
	case SG_SET_COMMAND_Q:
		result = get_user(val, ip);
		if (result)
			return result;
		sfp->cmd_q = val ? 1 : 0;
		return 0;
	case SG_GET_COMMAND_Q:
		return put_user((int) sfp->cmd_q, ip);
	case SG_SET_KEEP_ORPHAN:
		result = get_user(val, ip);
		if (result)
			return result;
		sfp->keep_orphan = val;
		return 0;
	case SG_GET_KEEP_ORPHAN:
		return put_user((int) sfp->keep_orphan, ip);
	case SG_NEXT_CMD_LEN:
		result = get_user(val, ip);
		if (result)
			return result;
		if (val > SG_MAX_CDB_SIZE)
			return -ENOMEM;
		sfp->next_cmd_len = (val > 0) ? val : 0;
		return 0;
	case SG_GET_VERSION_NUM:
		return put_user(sg_version_num, ip);
	case SG_GET_ACCESS_COUNT:
		/* faked - we don't have a real access count anymore */
		val = (sdp->device ? 1 : 0);
		return put_user(val, ip);
	case SG_GET_REQUEST_TABLE:
		if (!access_ok(VERIFY_WRITE, p, SZ_SG_REQ_INFO * SG_MAX_QUEUE))
			return -EFAULT;
		else {
			sg_req_info_t *rinfo;

			rinfo = kcalloc(SG_MAX_QUEUE, SZ_SG_REQ_INFO,
					GFP_KERNEL);
			if (!rinfo)
				return -ENOMEM;
			read_lock_irqsave(&sfp->rq_list_lock, iflags);
			sg_fill_request_table(sfp, rinfo);
			read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
			result = __copy_to_user(p, rinfo,
						SZ_SG_REQ_INFO * SG_MAX_QUEUE);
			result = result ? -EFAULT : 0;
			kfree(rinfo);
			return result;
		}
	case SG_EMULATED_HOST:
		if (atomic_read(&sdp->detaching))
			return -ENODEV;
		return put_user(sdp->device->host->hostt->emulated, ip);
	case SCSI_IOCTL_SEND_COMMAND:
		if (atomic_read(&sdp->detaching))
			return -ENODEV;
		if (read_only) {
			unsigned char opcode = WRITE_6;
			Scsi_Ioctl_Command __user *siocp = p;

			if (copy_from_user(&opcode, siocp->data, 1))
				return -EFAULT;
			if (sg_allow_access(filp, &opcode))
				return -EPERM;
		}
		return sg_scsi_ioctl(sdp->device->request_queue, NULL, filp->f_mode, p);
	case SG_SET_DEBUG:
		result = get_user(val, ip);
		if (result)
			return result;
		sdp->sgdebug = (char) val;
		return 0;
	case BLKSECTGET:
		return put_user(max_sectors_bytes(sdp->device->request_queue),
				ip);
	case BLKTRACESETUP:
		return blk_trace_setup(sdp->device->request_queue,
				       sdp->disk->disk_name,
				       MKDEV(SCSI_GENERIC_MAJOR, sdp->index),
				       NULL, p);
	case BLKTRACESTART:
		return blk_trace_startstop(sdp->device->request_queue, 1);
	case BLKTRACESTOP:
		return blk_trace_startstop(sdp->device->request_queue, 0);
	case BLKTRACETEARDOWN:
		return blk_trace_remove(sdp->device->request_queue);
	case SCSI_IOCTL_GET_IDLUN:
	case SCSI_IOCTL_GET_BUS_NUMBER:
	case SCSI_IOCTL_PROBE_HOST:
	case SG_GET_TRANSFORM:
	case SG_SCSI_RESET:
		if (atomic_read(&sdp->detaching))
			return -ENODEV;
		break;
	default:
		if (read_only)
			return -EPERM;	/* don't know so take safe approach */
		break;
	}

	result = scsi_ioctl_block_when_processing_errors(sdp->device,
			cmd_in, filp->f_flags & O_NDELAY);
	if (result)
		return result;
	return scsi_ioctl(sdp->device, cmd_in, p);
}

#ifdef CONFIG_COMPAT
static long sg_compat_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
{
	Sg_device *sdp;
	Sg_fd *sfp;
	struct scsi_device *sdev;

	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
		return -ENXIO;

	sdev = sdp->device;
	if (sdev->host->hostt->compat_ioctl) { 
		int ret;

		ret = sdev->host->hostt->compat_ioctl(sdev, cmd_in, (void __user *)arg);

		return ret;
	}
	
	return -ENOIOCTLCMD;
}
#endif

static __poll_t
sg_poll(struct file *filp, poll_table * wait)
{
	__poll_t res = 0;
	Sg_device *sdp;
	Sg_fd *sfp;
	Sg_request *srp;
	int count = 0;
	unsigned long iflags;

	sfp = filp->private_data;
	if (!sfp)
		return EPOLLERR;
	sdp = sfp->parentdp;
	if (!sdp)
		return EPOLLERR;
	poll_wait(filp, &sfp->read_wait, wait);
	read_lock_irqsave(&sfp->rq_list_lock, iflags);
	list_for_each_entry(srp, &sfp->rq_list, entry) {
		/* if any read waiting, flag it */
		if ((0 == res) && (1 == srp->done) && (!srp->sg_io_owned))
			res = EPOLLIN | EPOLLRDNORM;
		++count;
	}
	read_unlock_irqrestore(&sfp->rq_list_lock, iflags);

	if (atomic_read(&sdp->detaching))
		res |= EPOLLHUP;
	else if (!sfp->cmd_q) {
		if (0 == count)
			res |= EPOLLOUT | EPOLLWRNORM;
	} else if (count < SG_MAX_QUEUE)
		res |= EPOLLOUT | EPOLLWRNORM;
	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
				      "sg_poll: res=0x%x\n", (__force u32) res));
	return res;
}

static int
sg_fasync(int fd, struct file *filp, int mode)
{
	Sg_device *sdp;
	Sg_fd *sfp;

	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
		return -ENXIO;
	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
				      "sg_fasync: mode=%d\n", mode));

	return fasync_helper(fd, filp, mode, &sfp->async_qp);
}

static vm_fault_t
sg_vma_fault(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	Sg_fd *sfp;
	unsigned long offset, len, sa;
	Sg_scatter_hold *rsv_schp;
	int k, length;

	if ((NULL == vma) || (!(sfp = (Sg_fd *) vma->vm_private_data)))
		return VM_FAULT_SIGBUS;
	rsv_schp = &sfp->reserve;
	offset = vmf->pgoff << PAGE_SHIFT;
	if (offset >= rsv_schp->bufflen)
		return VM_FAULT_SIGBUS;
	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sfp->parentdp,
				      "sg_vma_fault: offset=%lu, scatg=%d\n",
				      offset, rsv_schp->k_use_sg));
	sa = vma->vm_start;
	length = 1 << (PAGE_SHIFT + rsv_schp->page_order);
	for (k = 0; k < rsv_schp->k_use_sg && sa < vma->vm_end; k++) {
		len = vma->vm_end - sa;
		len = (len < length) ? len : length;
		if (offset < len) {
			struct page *page = nth_page(rsv_schp->pages[k],
						     offset >> PAGE_SHIFT);
			get_page(page);	/* increment page count */
			vmf->page = page;
			return 0; /* success */
		}
		sa += len;
		offset -= len;
	}

	return VM_FAULT_SIGBUS;
}

static const struct vm_operations_struct sg_mmap_vm_ops = {
	.fault = sg_vma_fault,
};

static int
sg_mmap(struct file *filp, struct vm_area_struct *vma)
{
	Sg_fd *sfp;
	unsigned long req_sz, len, sa;
	Sg_scatter_hold *rsv_schp;
	int k, length;
	int ret = 0;

	if ((!filp) || (!vma) || (!(sfp = (Sg_fd *) filp->private_data)))
		return -ENXIO;
	req_sz = vma->vm_end - vma->vm_start;
	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sfp->parentdp,
				      "sg_mmap starting, vm_start=%p, len=%d\n",
				      (void *) vma->vm_start, (int) req_sz));
	if (vma->vm_pgoff)
		return -EINVAL;	/* want no offset */
	rsv_schp = &sfp->reserve;
	mutex_lock(&sfp->f_mutex);
	if (req_sz > rsv_schp->bufflen) {
		ret = -ENOMEM;	/* cannot map more than reserved buffer */
		goto out;
	}

	sa = vma->vm_start;
	length = 1 << (PAGE_SHIFT + rsv_schp->page_order);
	for (k = 0; k < rsv_schp->k_use_sg && sa < vma->vm_end; k++) {
		len = vma->vm_end - sa;
		len = (len < length) ? len : length;
		sa += len;
	}

	sfp->mmap_called = 1;
	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
	vma->vm_private_data = sfp;
	vma->vm_ops = &sg_mmap_vm_ops;
out:
	mutex_unlock(&sfp->f_mutex);
	return ret;
}

static void
sg_rq_end_io_usercontext(struct work_struct *work)
{
	struct sg_request *srp = container_of(work, struct sg_request, ew.work);
	struct sg_fd *sfp = srp->parentfp;

	sg_finish_rem_req(srp);
	sg_remove_request(sfp, srp);
	kref_put(&sfp->f_ref, sg_remove_sfp);
}

/*
 * This function is a "bottom half" handler that is called by the mid
 * level when a command is completed (or has failed).
 */
static void
sg_rq_end_io(struct request *rq, blk_status_t status)
{
	struct sg_request *srp = rq->end_io_data;
	struct scsi_request *req = scsi_req(rq);
	Sg_device *sdp;
	Sg_fd *sfp;
	unsigned long iflags;
	unsigned int ms;
	char *sense;
	int result, resid, done = 1;

	if (WARN_ON(srp->done != 0))
		return;

	sfp = srp->parentfp;
	if (WARN_ON(sfp == NULL))
		return;

	sdp = sfp->parentdp;
	if (unlikely(atomic_read(&sdp->detaching)))
		pr_info("%s: device detaching\n", __func__);

	sense = req->sense;
	result = req->result;
	resid = req->resid_len;

	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp,
				      "sg_cmd_done: pack_id=%d, res=0x%x\n",
				      srp->header.pack_id, result));
	srp->header.resid = resid;
	ms = jiffies_to_msecs(jiffies);
	srp->header.duration = (ms > srp->header.duration) ?
				(ms - srp->header.duration) : 0;
	if (0 != result) {
		struct scsi_sense_hdr sshdr;

		srp->header.status = 0xff & result;
		srp->header.masked_status = status_byte(result);
		srp->header.msg_status = msg_byte(result);
		srp->header.host_status = host_byte(result);
		srp->header.driver_status = driver_byte(result);
		if ((sdp->sgdebug > 0) &&
		    ((CHECK_CONDITION == srp->header.masked_status) ||
		     (COMMAND_TERMINATED == srp->header.masked_status)))
			__scsi_print_sense(sdp->device, __func__, sense,
					   SCSI_SENSE_BUFFERSIZE);

		/* Following if statement is a patch supplied by Eric Youngdale */
		if (driver_byte(result) != 0
		    && scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr)
		    && !scsi_sense_is_deferred(&sshdr)
		    && sshdr.sense_key == UNIT_ATTENTION
		    && sdp->device->removable) {
			/* Detected possible disc change. Set the bit - this */
			/* may be used if there are filesystems using this device */
			sdp->device->changed = 1;
		}
	}

	if (req->sense_len)
		memcpy(srp->sense_b, req->sense, SCSI_SENSE_BUFFERSIZE);

	/* Rely on write phase to clean out srp status values, so no "else" */

	/*
	 * Free the request as soon as it is complete so that its resources
	 * can be reused without waiting for userspace to read() the
	 * result.  But keep the associated bio (if any) around until
	 * blk_rq_unmap_user() can be called from user context.
	 */
	srp->rq = NULL;
	scsi_req_free_cmd(scsi_req(rq));
	__blk_put_request(rq->q, rq);

	write_lock_irqsave(&sfp->rq_list_lock, iflags);
	if (unlikely(srp->orphan)) {
		if (sfp->keep_orphan)
			srp->sg_io_owned = 0;
		else
			done = 0;
	}
	srp->done = done;
	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);

	if (likely(done)) {
		/* Now wake up any sg_read() that is waiting for this
		 * packet.
		 */
		wake_up_interruptible(&sfp->read_wait);
		kill_fasync(&sfp->async_qp, SIGPOLL, POLL_IN);
		kref_put(&sfp->f_ref, sg_remove_sfp);
	} else {
		INIT_WORK(&srp->ew.work, sg_rq_end_io_usercontext);
		schedule_work(&srp->ew.work);
	}
}

static const struct file_operations sg_fops = {
	.owner = THIS_MODULE,
	.read = sg_read,
	.write = sg_write,
	.poll = sg_poll,
	.unlocked_ioctl = sg_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl = sg_compat_ioctl,
#endif
	.open = sg_open,
	.mmap = sg_mmap,
	.release = sg_release,
	.fasync = sg_fasync,
	.llseek = no_llseek,
};

static struct class *sg_sysfs_class;

static int sg_sysfs_valid = 0;

static Sg_device *
sg_alloc(struct gendisk *disk, struct scsi_device *scsidp)
{
	struct request_queue *q = scsidp->request_queue;
	Sg_device *sdp;
	unsigned long iflags;
	int error;
	u32 k;

	sdp = kzalloc(sizeof(Sg_device), GFP_KERNEL);
	if (!sdp) {
		sdev_printk(KERN_WARNING, scsidp, "%s: kmalloc Sg_device "
			    "failure\n", __func__);
		return ERR_PTR(-ENOMEM);
	}

	idr_preload(GFP_KERNEL);
	write_lock_irqsave(&sg_index_lock, iflags);

	error = idr_alloc(&sg_index_idr, sdp, 0, SG_MAX_DEVS, GFP_NOWAIT);
	if (error < 0) {
		if (error == -ENOSPC) {
			sdev_printk(KERN_WARNING, scsidp,
				    "Unable to attach sg device type=%d, minor number exceeds %d\n",
				    scsidp->type, SG_MAX_DEVS - 1);
			error = -ENODEV;
		} else {
			sdev_printk(KERN_WARNING, scsidp, "%s: idr "
				    "allocation Sg_device failure: %d\n",
				    __func__, error);
		}
		goto out_unlock;
	}
	k = error;

	SCSI_LOG_TIMEOUT(3, sdev_printk(KERN_INFO, scsidp,
					"sg_alloc: dev=%d \n", k));
	sprintf(disk->disk_name, "sg%d", k);
	disk->first_minor = k;
	sdp->disk = disk;
	sdp->device = scsidp;
	mutex_init(&sdp->open_rel_lock);
	INIT_LIST_HEAD(&sdp->sfds);
	init_waitqueue_head(&sdp->open_wait);
	atomic_set(&sdp->detaching, 0);
	rwlock_init(&sdp->sfd_lock);
	sdp->sg_tablesize = queue_max_segments(q);
	sdp->index = k;
	kref_init(&sdp->d_ref);
	error = 0;

out_unlock:
	write_unlock_irqrestore(&sg_index_lock, iflags);
	idr_preload_end();

	if (error) {
		kfree(sdp);
		return ERR_PTR(error);
	}
	return sdp;
}

static int
sg_add_device(struct device *cl_dev, struct class_interface *cl_intf)
{
	struct scsi_device *scsidp = to_scsi_device(cl_dev->parent);
	struct gendisk *disk;
	Sg_device *sdp = NULL;
	struct cdev * cdev = NULL;
	int error;
	unsigned long iflags;

	disk = alloc_disk(1);
	if (!disk) {
		pr_warn("%s: alloc_disk failed\n", __func__);
		return -ENOMEM;
	}
	disk->major = SCSI_GENERIC_MAJOR;

	error = -ENOMEM;
	cdev = cdev_alloc();
	if (!cdev) {
		pr_warn("%s: cdev_alloc failed\n", __func__);
		goto out;
	}
	cdev->owner = THIS_MODULE;
	cdev->ops = &sg_fops;

	sdp = sg_alloc(disk, scsidp);
	if (IS_ERR(sdp)) {
		pr_warn("%s: sg_alloc failed\n", __func__);
		error = PTR_ERR(sdp);
		goto out;
	}

	error = cdev_add(cdev, MKDEV(SCSI_GENERIC_MAJOR, sdp->index), 1);
	if (error)
		goto cdev_add_err;

	sdp->cdev = cdev;
	if (sg_sysfs_valid) {
		struct device *sg_class_member;

		sg_class_member = device_create(sg_sysfs_class, cl_dev->parent,
						MKDEV(SCSI_GENERIC_MAJOR,
						      sdp->index),
						sdp, "%s", disk->disk_name);
		if (IS_ERR(sg_class_member)) {
			pr_err("%s: device_create failed\n", __func__);
			error = PTR_ERR(sg_class_member);
			goto cdev_add_err;
		}
		error = sysfs_create_link(&scsidp->sdev_gendev.kobj,
					  &sg_class_member->kobj, "generic");
		if (error)
			pr_err("%s: unable to make symlink 'generic' back "
			       "to sg%d\n", __func__, sdp->index);
	} else
		pr_warn("%s: sg_sys Invalid\n", __func__);

	sdev_printk(KERN_NOTICE, scsidp, "Attached scsi generic sg%d "
		    "type %d\n", sdp->index, scsidp->type);

	dev_set_drvdata(cl_dev, sdp);

	return 0;

cdev_add_err:
	write_lock_irqsave(&sg_index_lock, iflags);
	idr_remove(&sg_index_idr, sdp->index);
	write_unlock_irqrestore(&sg_index_lock, iflags);
	kfree(sdp);

out:
	put_disk(disk);
	if (cdev)
		cdev_del(cdev);
	return error;
}

static void
sg_device_destroy(struct kref *kref)
{
	struct sg_device *sdp = container_of(kref, struct sg_device, d_ref);
	unsigned long flags;

	/* CAUTION!  Note that the device can still be found via idr_find()
	 * even though the refcount is 0.  Therefore, do idr_remove() BEFORE
	 * any other cleanup.
	 */

	write_lock_irqsave(&sg_index_lock, flags);
	idr_remove(&sg_index_idr, sdp->index);
	write_unlock_irqrestore(&sg_index_lock, flags);

	SCSI_LOG_TIMEOUT(3,
		sg_printk(KERN_INFO, sdp, "sg_device_destroy\n"));

	put_disk(sdp->disk);
	kfree(sdp);
}

static void
sg_remove_device(struct device *cl_dev, struct class_interface *cl_intf)
{
	struct scsi_device *scsidp = to_scsi_device(cl_dev->parent);
	Sg_device *sdp = dev_get_drvdata(cl_dev);
	unsigned long iflags;
	Sg_fd *sfp;
	int val;

	if (!sdp)
		return;
	/* want sdp->detaching non-zero as soon as possible */
	val = atomic_inc_return(&sdp->detaching);
	if (val > 1)
		return; /* only want to do following once per device */

	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
				      "%s\n", __func__));

	read_lock_irqsave(&sdp->sfd_lock, iflags);
	list_for_each_entry(sfp, &sdp->sfds, sfd_siblings) {
		wake_up_interruptible_all(&sfp->read_wait);
		kill_fasync(&sfp->async_qp, SIGPOLL, POLL_HUP);
	}
	wake_up_interruptible_all(&sdp->open_wait);
	read_unlock_irqrestore(&sdp->sfd_lock, iflags);

	sysfs_remove_link(&scsidp->sdev_gendev.kobj, "generic");
	device_destroy(sg_sysfs_class, MKDEV(SCSI_GENERIC_MAJOR, sdp->index));
	cdev_del(sdp->cdev);
	sdp->cdev = NULL;

	kref_put(&sdp->d_ref, sg_device_destroy);
}

module_param_named(scatter_elem_sz, scatter_elem_sz, int, S_IRUGO | S_IWUSR);
module_param_named(def_reserved_size, def_reserved_size, int,
		   S_IRUGO | S_IWUSR);
module_param_named(allow_dio, sg_allow_dio, int, S_IRUGO | S_IWUSR);

MODULE_AUTHOR("Douglas Gilbert");
MODULE_DESCRIPTION("SCSI generic (sg) driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(SG_VERSION_STR);
MODULE_ALIAS_CHARDEV_MAJOR(SCSI_GENERIC_MAJOR);

MODULE_PARM_DESC(scatter_elem_sz, "scatter gather element "
                "size (default: max(SG_SCATTER_SZ, PAGE_SIZE))");
MODULE_PARM_DESC(def_reserved_size, "size of buffer reserved for each fd");
MODULE_PARM_DESC(allow_dio, "allow direct I/O (default: 0 (disallow))");

static int __init
init_sg(void)
{
	int rc;

	if (scatter_elem_sz < PAGE_SIZE) {
		scatter_elem_sz = PAGE_SIZE;
		scatter_elem_sz_prev = scatter_elem_sz;
	}
	if (def_reserved_size >= 0)
		sg_big_buff = def_reserved_size;
	else
		def_reserved_size = sg_big_buff;

	rc = register_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), 
				    SG_MAX_DEVS, "sg");
	if (rc)
		return rc;
        sg_sysfs_class = class_create(THIS_MODULE, "scsi_generic");
        if ( IS_ERR(sg_sysfs_class) ) {
		rc = PTR_ERR(sg_sysfs_class);
		goto err_out;
        }
	sg_sysfs_valid = 1;
	rc = scsi_register_interface(&sg_interface);
	if (0 == rc) {
#ifdef CONFIG_SCSI_PROC_FS
		sg_proc_init();
#endif				/* CONFIG_SCSI_PROC_FS */
		return 0;
	}
	class_destroy(sg_sysfs_class);
err_out:
	unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS);
	return rc;
}

static void __exit
exit_sg(void)
{
#ifdef CONFIG_SCSI_PROC_FS
	remove_proc_subtree("scsi/sg", NULL);
#endif				/* CONFIG_SCSI_PROC_FS */
	scsi_unregister_interface(&sg_interface);
	class_destroy(sg_sysfs_class);
	sg_sysfs_valid = 0;
	unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0),
				 SG_MAX_DEVS);
	idr_destroy(&sg_index_idr);
}

static int
sg_start_req(Sg_request *srp, unsigned char *cmd)
{
	int res;
	struct request *rq;
	struct scsi_request *req;
	Sg_fd *sfp = srp->parentfp;
	sg_io_hdr_t *hp = &srp->header;
	int dxfer_len = (int) hp->dxfer_len;
	int dxfer_dir = hp->dxfer_direction;
	unsigned int iov_count = hp->iovec_count;
	Sg_scatter_hold *req_schp = &srp->data;
	Sg_scatter_hold *rsv_schp = &sfp->reserve;
	struct request_queue *q = sfp->parentdp->device->request_queue;
	struct rq_map_data *md, map_data;
	int rw = hp->dxfer_direction == SG_DXFER_TO_DEV ? WRITE : READ;
	unsigned char *long_cmdp = NULL;

	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp,
				      "sg_start_req: dxfer_len=%d\n",
				      dxfer_len));

	if (hp->cmd_len > BLK_MAX_CDB) {
		long_cmdp = kzalloc(hp->cmd_len, GFP_KERNEL);
		if (!long_cmdp)
			return -ENOMEM;
	}

	/*
	 * NOTE
	 *
	 * With scsi-mq enabled, there are a fixed number of preallocated
	 * requests equal in number to shost->can_queue.  If all of the
	 * preallocated requests are already in use, then blk_get_request()
	 * will sleep until an active command completes, freeing up a request.
	 * Although waiting in an asynchronous interface is less than ideal, we
	 * do not want to use BLK_MQ_REQ_NOWAIT here because userspace might
	 * not expect an EWOULDBLOCK from this condition.
	 */
	rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ?
			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
	if (IS_ERR(rq)) {
		kfree(long_cmdp);
		return PTR_ERR(rq);
	}
	req = scsi_req(rq);

	if (hp->cmd_len > BLK_MAX_CDB)
		req->cmd = long_cmdp;
	memcpy(req->cmd, cmd, hp->cmd_len);
	req->cmd_len = hp->cmd_len;

	srp->rq = rq;
	rq->end_io_data = srp;
	req->retries = SG_DEFAULT_RETRIES;

	if ((dxfer_len <= 0) || (dxfer_dir == SG_DXFER_NONE))
		return 0;

	if (sg_allow_dio && hp->flags & SG_FLAG_DIRECT_IO &&
	    dxfer_dir != SG_DXFER_UNKNOWN && !iov_count &&
	    !sfp->parentdp->device->host->unchecked_isa_dma &&
	    blk_rq_aligned(q, (unsigned long)hp->dxferp, dxfer_len))
		md = NULL;
	else
		md = &map_data;

	if (md) {
		mutex_lock(&sfp->f_mutex);
		if (dxfer_len <= rsv_schp->bufflen &&
		    !sfp->res_in_use) {
			sfp->res_in_use = 1;
			sg_link_reserve(sfp, srp, dxfer_len);
		} else if (hp->flags & SG_FLAG_MMAP_IO) {
			res = -EBUSY; /* sfp->res_in_use == 1 */
			if (dxfer_len > rsv_schp->bufflen)
				res = -ENOMEM;
			mutex_unlock(&sfp->f_mutex);
			return res;
		} else {
			res = sg_build_indirect(req_schp, sfp, dxfer_len);
			if (res) {
				mutex_unlock(&sfp->f_mutex);
				return res;
			}
		}
		mutex_unlock(&sfp->f_mutex);

		md->pages = req_schp->pages;
		md->page_order = req_schp->page_order;
		md->nr_entries = req_schp->k_use_sg;
		md->offset = 0;
		md->null_mapped = hp->dxferp ? 0 : 1;
		if (dxfer_dir == SG_DXFER_TO_FROM_DEV)
			md->from_user = 1;
		else
			md->from_user = 0;
	}

	if (iov_count) {
		struct iovec *iov = NULL;
		struct iov_iter i;

		res = import_iovec(rw, hp->dxferp, iov_count, 0, &iov, &i);
		if (res < 0)
			return res;

		iov_iter_truncate(&i, hp->dxfer_len);
		if (!iov_iter_count(&i)) {
			kfree(iov);
			return -EINVAL;
		}

		res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC);
		kfree(iov);
	} else
		res = blk_rq_map_user(q, rq, md, hp->dxferp,
				      hp->dxfer_len, GFP_ATOMIC);

	if (!res) {
		srp->bio = rq->bio;

		if (!md) {
			req_schp->dio_in_use = 1;
			hp->info |= SG_INFO_DIRECT_IO;
		}
	}
	return res;
}

static int
sg_finish_rem_req(Sg_request *srp)
{
	int ret = 0;

	Sg_fd *sfp = srp->parentfp;
	Sg_scatter_hold *req_schp = &srp->data;

	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp,
				      "sg_finish_rem_req: res_used=%d\n",
				      (int) srp->res_used));
	if (srp->bio)
		ret = blk_rq_unmap_user(srp->bio);

	if (srp->rq) {
		scsi_req_free_cmd(scsi_req(srp->rq));
		blk_put_request(srp->rq);
	}

	if (srp->res_used)
		sg_unlink_reserve(sfp, srp);
	else
		sg_remove_scat(sfp, req_schp);

	return ret;
}

static int
sg_build_sgat(Sg_scatter_hold * schp, const Sg_fd * sfp, int tablesize)
{
	int sg_bufflen = tablesize * sizeof(struct page *);
	gfp_t gfp_flags = GFP_ATOMIC | __GFP_NOWARN;

	schp->pages = kzalloc(sg_bufflen, gfp_flags);
	if (!schp->pages)
		return -ENOMEM;
	schp->sglist_len = sg_bufflen;
	return tablesize;	/* number of scat_gath elements allocated */
}

static int
sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
{
	int ret_sz = 0, i, k, rem_sz, num, mx_sc_elems;
	int sg_tablesize = sfp->parentdp->sg_tablesize;
	int blk_size = buff_size, order;
	gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN;
	struct sg_device *sdp = sfp->parentdp;

	if (blk_size < 0)
		return -EFAULT;
	if (0 == blk_size)
		++blk_size;	/* don't know why */
	/* round request up to next highest SG_SECTOR_SZ byte boundary */
	blk_size = ALIGN(blk_size, SG_SECTOR_SZ);
	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp,
		"sg_build_indirect: buff_size=%d, blk_size=%d\n",
		buff_size, blk_size));

	/* N.B. ret_sz carried into this block ... */
	mx_sc_elems = sg_build_sgat(schp, sfp, sg_tablesize);
	if (mx_sc_elems < 0)
		return mx_sc_elems;	/* most likely -ENOMEM */

	num = scatter_elem_sz;
	if (unlikely(num != scatter_elem_sz_prev)) {
		if (num < PAGE_SIZE) {
			scatter_elem_sz = PAGE_SIZE;
			scatter_elem_sz_prev = PAGE_SIZE;
		} else
			scatter_elem_sz_prev = num;
	}

	if (sdp->device->host->unchecked_isa_dma)
		gfp_mask |= GFP_DMA;

	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
		gfp_mask |= __GFP_ZERO;

	order = get_order(num);
retry:
	ret_sz = 1 << (PAGE_SHIFT + order);

	for (k = 0, rem_sz = blk_size; rem_sz > 0 && k < mx_sc_elems;
	     k++, rem_sz -= ret_sz) {

		num = (rem_sz > scatter_elem_sz_prev) ?
			scatter_elem_sz_prev : rem_sz;

		schp->pages[k] = alloc_pages(gfp_mask | __GFP_ZERO, order);
		if (!schp->pages[k])
			goto out;

		if (num == scatter_elem_sz_prev) {
			if (unlikely(ret_sz > scatter_elem_sz_prev)) {
				scatter_elem_sz = ret_sz;
				scatter_elem_sz_prev = ret_sz;
			}
		}

		SCSI_LOG_TIMEOUT(5, sg_printk(KERN_INFO, sfp->parentdp,
				 "sg_build_indirect: k=%d, num=%d, ret_sz=%d\n",
				 k, num, ret_sz));
	}		/* end of for loop */

	schp->page_order = order;
	schp->k_use_sg = k;
	SCSI_LOG_TIMEOUT(5, sg_printk(KERN_INFO, sfp->parentdp,
			 "sg_build_indirect: k_use_sg=%d, rem_sz=%d\n",
			 k, rem_sz));

	schp->bufflen = blk_size;
	if (rem_sz > 0)	/* must have failed */
		return -ENOMEM;
	return 0;
out:
	for (i = 0; i < k; i++)
		__free_pages(schp->pages[i], order);

	if (--order >= 0)
		goto retry;

	return -ENOMEM;
}

static void
sg_remove_scat(Sg_fd * sfp, Sg_scatter_hold * schp)
{
	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp,
			 "sg_remove_scat: k_use_sg=%d\n", schp->k_use_sg));
	if (schp->pages && schp->sglist_len > 0) {
		if (!schp->dio_in_use) {
			int k;

			for (k = 0; k < schp->k_use_sg && schp->pages[k]; k++) {
				SCSI_LOG_TIMEOUT(5,
					sg_printk(KERN_INFO, sfp->parentdp,
					"sg_remove_scat: k=%d, pg=0x%p\n",
					k, schp->pages[k]));
				__free_pages(schp->pages[k], schp->page_order);
			}

			kfree(schp->pages);
		}
	}
	memset(schp, 0, sizeof (*schp));
}

static int
sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer)
{
	Sg_scatter_hold *schp = &srp->data;
	int k, num;

	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, srp->parentfp->parentdp,
			 "sg_read_oxfer: num_read_xfer=%d\n",
			 num_read_xfer));
	if ((!outp) || (num_read_xfer <= 0))
		return 0;

	num = 1 << (PAGE_SHIFT + schp->page_order);
	for (k = 0; k < schp->k_use_sg && schp->pages[k]; k++) {
		if (num > num_read_xfer) {
			if (__copy_to_user(outp, page_address(schp->pages[k]),
					   num_read_xfer))
				return -EFAULT;
			break;
		} else {
			if (__copy_to_user(outp, page_address(schp->pages[k]),
					   num))
				return -EFAULT;
			num_read_xfer -= num;
			if (num_read_xfer <= 0)
				break;
			outp += num;
		}
	}

	return 0;
}

static void
sg_build_reserve(Sg_fd * sfp, int req_size)
{
	Sg_scatter_hold *schp = &sfp->reserve;

	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp,
			 "sg_build_reserve: req_size=%d\n", req_size));
	do {
		if (req_size < PAGE_SIZE)
			req_size = PAGE_SIZE;
		if (0 == sg_build_indirect(schp, sfp, req_size))
			return;
		else
			sg_remove_scat(sfp, schp);
		req_size >>= 1;	/* divide by 2 */
	} while (req_size > (PAGE_SIZE / 2));
}

static void
sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size)
{
	Sg_scatter_hold *req_schp = &srp->data;
	Sg_scatter_hold *rsv_schp = &sfp->reserve;
	int k, num, rem;

	srp->res_used = 1;
	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp,
			 "sg_link_reserve: size=%d\n", size));
	rem = size;

	num = 1 << (PAGE_SHIFT + rsv_schp->page_order);
	for (k = 0; k < rsv_schp->k_use_sg; k++) {
		if (rem <= num) {
			req_schp->k_use_sg = k + 1;
			req_schp->sglist_len = rsv_schp->sglist_len;
			req_schp->pages = rsv_schp->pages;

			req_schp->bufflen = size;
			req_schp->page_order = rsv_schp->page_order;
			break;
		} else
			rem -= num;
	}

	if (k >= rsv_schp->k_use_sg)
		SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sfp->parentdp,
				 "sg_link_reserve: BAD size\n"));
}

static void
sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp)
{
	Sg_scatter_hold *req_schp = &srp->data;

	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, srp->parentfp->parentdp,
				      "sg_unlink_reserve: req->k_use_sg=%d\n",
				      (int) req_schp->k_use_sg));
	req_schp->k_use_sg = 0;
	req_schp->bufflen = 0;
	req_schp->pages = NULL;
	req_schp->page_order = 0;
	req_schp->sglist_len = 0;
	srp->res_used = 0;
	/* Called without mutex lock to avoid deadlock */
	sfp->res_in_use = 0;
}

static Sg_request *
sg_get_rq_mark(Sg_fd * sfp, int pack_id)
{
	Sg_request *resp;
	unsigned long iflags;

	write_lock_irqsave(&sfp->rq_list_lock, iflags);
	list_for_each_entry(resp, &sfp->rq_list, entry) {
		/* look for requests that are ready + not SG_IO owned */
		if ((1 == resp->done) && (!resp->sg_io_owned) &&
		    ((-1 == pack_id) || (resp->header.pack_id == pack_id))) {
			resp->done = 2;	/* guard against other readers */
			write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
			return resp;
		}
	}
	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
	return NULL;
}

/* always adds to end of list */
static Sg_request *
sg_add_request(Sg_fd * sfp)
{
	int k;
	unsigned long iflags;
	Sg_request *rp = sfp->req_arr;

	write_lock_irqsave(&sfp->rq_list_lock, iflags);
	if (!list_empty(&sfp->rq_list)) {
		if (!sfp->cmd_q)
			goto out_unlock;

		for (k = 0; k < SG_MAX_QUEUE; ++k, ++rp) {
			if (!rp->parentfp)
				break;
		}
		if (k >= SG_MAX_QUEUE)
			goto out_unlock;
	}
	memset(rp, 0, sizeof (Sg_request));
	rp->parentfp = sfp;
	rp->header.duration = jiffies_to_msecs(jiffies);
	list_add_tail(&rp->entry, &sfp->rq_list);
	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
	return rp;
out_unlock:
	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
	return NULL;
}

/* Return of 1 for found; 0 for not found */
static int
sg_remove_request(Sg_fd * sfp, Sg_request * srp)
{
	unsigned long iflags;
	int res = 0;

	if (!sfp || !srp || list_empty(&sfp->rq_list))
		return res;
	write_lock_irqsave(&sfp->rq_list_lock, iflags);
	if (!list_empty(&srp->entry)) {
		list_del(&srp->entry);
		srp->parentfp = NULL;
		res = 1;
	}
	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
	return res;
}

static Sg_fd *
sg_add_sfp(Sg_device * sdp)
{
	Sg_fd *sfp;
	unsigned long iflags;
	int bufflen;

	sfp = kzalloc(sizeof(*sfp), GFP_ATOMIC | __GFP_NOWARN);
	if (!sfp)
		return ERR_PTR(-ENOMEM);

	init_waitqueue_head(&sfp->read_wait);
	rwlock_init(&sfp->rq_list_lock);
	INIT_LIST_HEAD(&sfp->rq_list);
	kref_init(&sfp->f_ref);
	mutex_init(&sfp->f_mutex);
	sfp->timeout = SG_DEFAULT_TIMEOUT;
	sfp->timeout_user = SG_DEFAULT_TIMEOUT_USER;
	sfp->force_packid = SG_DEF_FORCE_PACK_ID;
	sfp->cmd_q = SG_DEF_COMMAND_Q;
	sfp->keep_orphan = SG_DEF_KEEP_ORPHAN;
	sfp->parentdp = sdp;
	write_lock_irqsave(&sdp->sfd_lock, iflags);
	if (atomic_read(&sdp->detaching)) {
		write_unlock_irqrestore(&sdp->sfd_lock, iflags);
		kfree(sfp);
		return ERR_PTR(-ENODEV);
	}
	list_add_tail(&sfp->sfd_siblings, &sdp->sfds);
	write_unlock_irqrestore(&sdp->sfd_lock, iflags);
	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
				      "sg_add_sfp: sfp=0x%p\n", sfp));
	if (unlikely(sg_big_buff != def_reserved_size))
		sg_big_buff = def_reserved_size;

	bufflen = min_t(int, sg_big_buff,
			max_sectors_bytes(sdp->device->request_queue));
	sg_build_reserve(sfp, bufflen);
	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
				      "sg_add_sfp: bufflen=%d, k_use_sg=%d\n",
				      sfp->reserve.bufflen,
				      sfp->reserve.k_use_sg));

	kref_get(&sdp->d_ref);
	__module_get(THIS_MODULE);
	return sfp;
}

static void
sg_remove_sfp_usercontext(struct work_struct *work)
{
	struct sg_fd *sfp = container_of(work, struct sg_fd, ew.work);
	struct sg_device *sdp = sfp->parentdp;
	Sg_request *srp;
	unsigned long iflags;

	/* Cleanup any responses which were never read(). */
	write_lock_irqsave(&sfp->rq_list_lock, iflags);
	while (!list_empty(&sfp->rq_list)) {
		srp = list_first_entry(&sfp->rq_list, Sg_request, entry);
		sg_finish_rem_req(srp);
		list_del(&srp->entry);
		srp->parentfp = NULL;
	}
	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);

	if (sfp->reserve.bufflen > 0) {
		SCSI_LOG_TIMEOUT(6, sg_printk(KERN_INFO, sdp,
				"sg_remove_sfp:    bufflen=%d, k_use_sg=%d\n",
				(int) sfp->reserve.bufflen,
				(int) sfp->reserve.k_use_sg));
		sg_remove_scat(sfp, &sfp->reserve);
	}

	SCSI_LOG_TIMEOUT(6, sg_printk(KERN_INFO, sdp,
			"sg_remove_sfp: sfp=0x%p\n", sfp));
	kfree(sfp);

	scsi_device_put(sdp->device);
	kref_put(&sdp->d_ref, sg_device_destroy);
	module_put(THIS_MODULE);
}

static void
sg_remove_sfp(struct kref *kref)
{
	struct sg_fd *sfp = container_of(kref, struct sg_fd, f_ref);
	struct sg_device *sdp = sfp->parentdp;
	unsigned long iflags;

	write_lock_irqsave(&sdp->sfd_lock, iflags);
	list_del(&sfp->sfd_siblings);
	write_unlock_irqrestore(&sdp->sfd_lock, iflags);

	INIT_WORK(&sfp->ew.work, sg_remove_sfp_usercontext);
	schedule_work(&sfp->ew.work);
}

#ifdef CONFIG_SCSI_PROC_FS
static int
sg_idr_max_id(int id, void *p, void *data)
{
	int *k = data;

	if (*k < id)
		*k = id;

	return 0;
}

static int
sg_last_dev(void)
{
	int k = -1;
	unsigned long iflags;

	read_lock_irqsave(&sg_index_lock, iflags);
	idr_for_each(&sg_index_idr, sg_idr_max_id, &k);
	read_unlock_irqrestore(&sg_index_lock, iflags);
	return k + 1;		/* origin 1 */
}
#endif

/* must be called with sg_index_lock held */
static Sg_device *sg_lookup_dev(int dev)
{
	return idr_find(&sg_index_idr, dev);
}

static Sg_device *
sg_get_dev(int dev)
{
	struct sg_device *sdp;
	unsigned long flags;

	read_lock_irqsave(&sg_index_lock, flags);
	sdp = sg_lookup_dev(dev);
	if (!sdp)
		sdp = ERR_PTR(-ENXIO);
	else if (atomic_read(&sdp->detaching)) {
		/* If sdp->detaching, then the refcount may already be 0, in
		 * which case it would be a bug to do kref_get().
		 */
		sdp = ERR_PTR(-ENODEV);
	} else
		kref_get(&sdp->d_ref);
	read_unlock_irqrestore(&sg_index_lock, flags);

	return sdp;
}

#ifdef CONFIG_SCSI_PROC_FS
static int sg_proc_seq_show_int(struct seq_file *s, void *v);

static int sg_proc_single_open_adio(struct inode *inode, struct file *file);
static ssize_t sg_proc_write_adio(struct file *filp, const char __user *buffer,
			          size_t count, loff_t *off);
static const struct file_operations adio_fops = {
	.owner = THIS_MODULE,
	.open = sg_proc_single_open_adio,
	.read = seq_read,
	.llseek = seq_lseek,
	.write = sg_proc_write_adio,
	.release = single_release,
};

static int sg_proc_single_open_dressz(struct inode *inode, struct file *file);
static ssize_t sg_proc_write_dressz(struct file *filp, 
		const char __user *buffer, size_t count, loff_t *off);
static const struct file_operations dressz_fops = {
	.owner = THIS_MODULE,
	.open = sg_proc_single_open_dressz,
	.read = seq_read,
	.llseek = seq_lseek,
	.write = sg_proc_write_dressz,
	.release = single_release,
};

static int sg_proc_seq_show_version(struct seq_file *s, void *v);
static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v);
static int sg_proc_seq_show_dev(struct seq_file *s, void *v);
static void * dev_seq_start(struct seq_file *s, loff_t *pos);
static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos);
static void dev_seq_stop(struct seq_file *s, void *v);
static const struct seq_operations dev_seq_ops = {
	.start = dev_seq_start,
	.next  = dev_seq_next,
	.stop  = dev_seq_stop,
	.show  = sg_proc_seq_show_dev,
};

static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v);
static const struct seq_operations devstrs_seq_ops = {
	.start = dev_seq_start,
	.next  = dev_seq_next,
	.stop  = dev_seq_stop,
	.show  = sg_proc_seq_show_devstrs,
};

static int sg_proc_seq_show_debug(struct seq_file *s, void *v);
static const struct seq_operations debug_seq_ops = {
	.start = dev_seq_start,
	.next  = dev_seq_next,
	.stop  = dev_seq_stop,
	.show  = sg_proc_seq_show_debug,
};

static int
sg_proc_init(void)
{
	struct proc_dir_entry *p;

	p = proc_mkdir("scsi/sg", NULL);
	if (!p)
		return 1;

	proc_create("allow_dio", S_IRUGO | S_IWUSR, p, &adio_fops);
	proc_create_seq("debug", S_IRUGO, p, &debug_seq_ops);
	proc_create("def_reserved_size", S_IRUGO | S_IWUSR, p, &dressz_fops);
	proc_create_single("device_hdr", S_IRUGO, p, sg_proc_seq_show_devhdr);
	proc_create_seq("devices", S_IRUGO, p, &dev_seq_ops);
	proc_create_seq("device_strs", S_IRUGO, p, &devstrs_seq_ops);
	proc_create_single("version", S_IRUGO, p, sg_proc_seq_show_version);
	return 0;
}


static int sg_proc_seq_show_int(struct seq_file *s, void *v)
{
	seq_printf(s, "%d\n", *((int *)s->private));
	return 0;
}

static int sg_proc_single_open_adio(struct inode *inode, struct file *file)
{
	return single_open(file, sg_proc_seq_show_int, &sg_allow_dio);
}

static ssize_t 
sg_proc_write_adio(struct file *filp, const char __user *buffer,
		   size_t count, loff_t *off)
{
	int err;
	unsigned long num;

	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
		return -EACCES;
	err = kstrtoul_from_user(buffer, count, 0, &num);
	if (err)
		return err;
	sg_allow_dio = num ? 1 : 0;
	return count;
}

static int sg_proc_single_open_dressz(struct inode *inode, struct file *file)
{
	return single_open(file, sg_proc_seq_show_int, &sg_big_buff);
}

static ssize_t 
sg_proc_write_dressz(struct file *filp, const char __user *buffer,
		     size_t count, loff_t *off)
{
	int err;
	unsigned long k = ULONG_MAX;

	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
		return -EACCES;

	err = kstrtoul_from_user(buffer, count, 0, &k);
	if (err)
		return err;
	if (k <= 1048576) {	/* limit "big buff" to 1 MB */
		sg_big_buff = k;
		return count;
	}
	return -ERANGE;
}

static int sg_proc_seq_show_version(struct seq_file *s, void *v)
{
	seq_printf(s, "%d\t%s [%s]\n", sg_version_num, SG_VERSION_STR,
		   sg_version_date);
	return 0;
}

static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v)
{
	seq_puts(s, "host\tchan\tid\tlun\ttype\topens\tqdepth\tbusy\tonline\n");
	return 0;
}

struct sg_proc_deviter {
	loff_t	index;
	size_t	max;
};

static void * dev_seq_start(struct seq_file *s, loff_t *pos)
{
	struct sg_proc_deviter * it = kmalloc(sizeof(*it), GFP_KERNEL);

	s->private = it;
	if (! it)
		return NULL;

	it->index = *pos;
	it->max = sg_last_dev();
	if (it->index >= it->max)
		return NULL;
	return it;
}

static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos)
{
	struct sg_proc_deviter * it = s->private;

	*pos = ++it->index;
	return (it->index < it->max) ? it : NULL;
}

static void dev_seq_stop(struct seq_file *s, void *v)
{
	kfree(s->private);
}

static int sg_proc_seq_show_dev(struct seq_file *s, void *v)
{
	struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
	Sg_device *sdp;
	struct scsi_device *scsidp;
	unsigned long iflags;

	read_lock_irqsave(&sg_index_lock, iflags);
	sdp = it ? sg_lookup_dev(it->index) : NULL;
	if ((NULL == sdp) || (NULL == sdp->device) ||
	    (atomic_read(&sdp->detaching)))
		seq_puts(s, "-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n");
	else {
		scsidp = sdp->device;
		seq_printf(s, "%d\t%d\t%d\t%llu\t%d\t%d\t%d\t%d\t%d\n",
			      scsidp->host->host_no, scsidp->channel,
			      scsidp->id, scsidp->lun, (int) scsidp->type,
			      1,
			      (int) scsidp->queue_depth,
			      (int) atomic_read(&scsidp->device_busy),
			      (int) scsi_device_online(scsidp));
	}
	read_unlock_irqrestore(&sg_index_lock, iflags);
	return 0;
}

static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v)
{
	struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
	Sg_device *sdp;
	struct scsi_device *scsidp;
	unsigned long iflags;

	read_lock_irqsave(&sg_index_lock, iflags);
	sdp = it ? sg_lookup_dev(it->index) : NULL;
	scsidp = sdp ? sdp->device : NULL;
	if (sdp && scsidp && (!atomic_read(&sdp->detaching)))
		seq_printf(s, "%8.8s\t%16.16s\t%4.4s\n",
			   scsidp->vendor, scsidp->model, scsidp->rev);
	else
		seq_puts(s, "<no active device>\n");
	read_unlock_irqrestore(&sg_index_lock, iflags);
	return 0;
}

/* must be called while holding sg_index_lock */
static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
{
	int k, new_interface, blen, usg;
	Sg_request *srp;
	Sg_fd *fp;
	const sg_io_hdr_t *hp;
	const char * cp;
	unsigned int ms;

	k = 0;
	list_for_each_entry(fp, &sdp->sfds, sfd_siblings) {
		k++;
		read_lock(&fp->rq_list_lock); /* irqs already disabled */
		seq_printf(s, "   FD(%d): timeout=%dms bufflen=%d "
			   "(res)sgat=%d low_dma=%d\n", k,
			   jiffies_to_msecs(fp->timeout),
			   fp->reserve.bufflen,
			   (int) fp->reserve.k_use_sg,
			   (int) sdp->device->host->unchecked_isa_dma);
		seq_printf(s, "   cmd_q=%d f_packid=%d k_orphan=%d closed=0\n",
			   (int) fp->cmd_q, (int) fp->force_packid,
			   (int) fp->keep_orphan);
		list_for_each_entry(srp, &fp->rq_list, entry) {
			hp = &srp->header;
			new_interface = (hp->interface_id == '\0') ? 0 : 1;
			if (srp->res_used) {
				if (new_interface &&
				    (SG_FLAG_MMAP_IO & hp->flags))
					cp = "     mmap>> ";
				else
					cp = "     rb>> ";
			} else {
				if (SG_INFO_DIRECT_IO_MASK & hp->info)
					cp = "     dio>> ";
				else
					cp = "     ";
			}
			seq_puts(s, cp);
			blen = srp->data.bufflen;
			usg = srp->data.k_use_sg;
			seq_puts(s, srp->done ?
				 ((1 == srp->done) ?  "rcv:" : "fin:")
				  : "act:");
			seq_printf(s, " id=%d blen=%d",
				   srp->header.pack_id, blen);
			if (srp->done)
				seq_printf(s, " dur=%d", hp->duration);
			else {
				ms = jiffies_to_msecs(jiffies);
				seq_printf(s, " t_o/elap=%d/%d",
					(new_interface ? hp->timeout :
						  jiffies_to_msecs(fp->timeout)),
					(ms > hp->duration ? ms - hp->duration : 0));
			}
			seq_printf(s, "ms sgat=%d op=0x%02x\n", usg,
				   (int) srp->data.cmd_opcode);
		}
		if (list_empty(&fp->rq_list))
			seq_puts(s, "     No requests active\n");
		read_unlock(&fp->rq_list_lock);
	}
}

static int sg_proc_seq_show_debug(struct seq_file *s, void *v)
{
	struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
	Sg_device *sdp;
	unsigned long iflags;

	if (it && (0 == it->index))
		seq_printf(s, "max_active_device=%d  def_reserved_size=%d\n",
			   (int)it->max, sg_big_buff);

	read_lock_irqsave(&sg_index_lock, iflags);
	sdp = it ? sg_lookup_dev(it->index) : NULL;
	if (NULL == sdp)
		goto skip;
	read_lock(&sdp->sfd_lock);
	if (!list_empty(&sdp->sfds)) {
		seq_printf(s, " >>> device=%s ", sdp->disk->disk_name);
		if (atomic_read(&sdp->detaching))
			seq_puts(s, "detaching pending close ");
		else if (sdp->device) {
			struct scsi_device *scsidp = sdp->device;

			seq_printf(s, "%d:%d:%d:%llu   em=%d",
				   scsidp->host->host_no,
				   scsidp->channel, scsidp->id,
				   scsidp->lun,
				   scsidp->host->hostt->emulated);
		}
		seq_printf(s, " sg_tablesize=%d excl=%d open_cnt=%d\n",
			   sdp->sg_tablesize, sdp->exclude, sdp->open_cnt);
		sg_proc_debug_helper(s, sdp);
	}
	read_unlock(&sdp->sfd_lock);
skip:
	read_unlock_irqrestore(&sg_index_lock, iflags);
	return 0;
}

#endif				/* CONFIG_SCSI_PROC_FS */

module_init(init_sg);
module_exit(exit_sg);