summaryrefslogtreecommitdiff
path: root/drivers/scsi/sd.c
blob: b1933041da39d414f9c6e127052ba8cbaa25e65e (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
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
/*
 *      sd.c Copyright (C) 1992 Drew Eckhardt
 *           Copyright (C) 1993, 1994, 1995, 1999 Eric Youngdale
 *
 *      Linux scsi disk driver
 *              Initial versions: Drew Eckhardt
 *              Subsequent revisions: Eric Youngdale
 *	Modification history:
 *       - Drew Eckhardt <drew@colorado.edu> original
 *       - Eric Youngdale <eric@andante.org> add scatter-gather, multiple 
 *         outstanding request, and other enhancements.
 *         Support loadable low-level scsi drivers.
 *       - Jirka Hanika <geo@ff.cuni.cz> support more scsi disks using 
 *         eight major numbers.
 *       - Richard Gooch <rgooch@atnf.csiro.au> support devfs.
 *	 - Torben Mathiasen <tmm@image.dk> Resource allocation fixes in 
 *	   sd_init and cleanups.
 *	 - Alex Davis <letmein@erols.com> Fix problem where partition info
 *	   not being read in sd_open. Fix problem where removable media 
 *	   could be ejected after sd_open.
 *	 - Douglas Gilbert <dgilbert@interlog.com> cleanup for lk 2.5.x
 *	 - Badari Pulavarty <pbadari@us.ibm.com>, Matthew Wilcox 
 *	   <willy@debian.org>, Kurt Garloff <garloff@suse.de>: 
 *	   Support 32k/1M disks.
 *
 *	Logging policy (needs CONFIG_SCSI_LOGGING defined):
 *	 - setting up transfer: SCSI_LOG_HLQUEUE levels 1 and 2
 *	 - end of transfer (bh + scsi_lib): SCSI_LOG_HLCOMPLETE level 1
 *	 - entering sd_ioctl: SCSI_LOG_IOCTL level 1
 *	 - entering other commands: SCSI_LOG_HLQUEUE level 3
 *	Note: when the logging level is set by the user, it must be greater
 *	than the level indicated above to trigger output.	
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/bio.h>
#include <linux/genhd.h>
#include <linux/hdreg.h>
#include <linux/errno.h>
#include <linux/idr.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/delay.h>
#include <linux/mutex.h>
#include <linux/string_helpers.h>
#include <linux/async.h>
#include <linux/slab.h>
#include <linux/pm_runtime.h>
#include <linux/pr.h>
#include <linux/t10-pi.h>
#include <linux/uaccess.h>
#include <asm/unaligned.h>

#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_driver.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_ioctl.h>
#include <scsi/scsicam.h>

#include "sd.h"
#include "scsi_priv.h"
#include "scsi_logging.h"

MODULE_AUTHOR("Eric Youngdale");
MODULE_DESCRIPTION("SCSI disk (sd) driver");
MODULE_LICENSE("GPL");

MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK0_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK1_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK2_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK3_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK4_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK5_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK6_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK7_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK8_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK9_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK10_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK11_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK12_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK13_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK14_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK15_MAJOR);
MODULE_ALIAS_SCSI_DEVICE(TYPE_DISK);
MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD);
MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC);
MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC);

#if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT)
#define SD_MINORS	16
#else
#define SD_MINORS	0
#endif

static void sd_config_discard(struct scsi_disk *, unsigned int);
static void sd_config_write_same(struct scsi_disk *);
static int  sd_revalidate_disk(struct gendisk *);
static void sd_unlock_native_capacity(struct gendisk *disk);
static int  sd_probe(struct device *);
static int  sd_remove(struct device *);
static void sd_shutdown(struct device *);
static int sd_suspend_system(struct device *);
static int sd_suspend_runtime(struct device *);
static int sd_resume(struct device *);
static void sd_rescan(struct device *);
static int sd_init_command(struct scsi_cmnd *SCpnt);
static void sd_uninit_command(struct scsi_cmnd *SCpnt);
static int sd_done(struct scsi_cmnd *);
static int sd_eh_action(struct scsi_cmnd *, int);
static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer);
static void scsi_disk_release(struct device *cdev);
static void sd_print_sense_hdr(struct scsi_disk *, struct scsi_sense_hdr *);
static void sd_print_result(const struct scsi_disk *, const char *, int);

static DEFINE_SPINLOCK(sd_index_lock);
static DEFINE_IDA(sd_index_ida);

/* This semaphore is used to mediate the 0->1 reference get in the
 * face of object destruction (i.e. we can't allow a get on an
 * object after last put) */
static DEFINE_MUTEX(sd_ref_mutex);

static struct kmem_cache *sd_cdb_cache;
static mempool_t *sd_cdb_pool;

static const char *sd_cache_types[] = {
	"write through", "none", "write back",
	"write back, no read (daft)"
};

static void sd_set_flush_flag(struct scsi_disk *sdkp)
{
	bool wc = false, fua = false;

	if (sdkp->WCE) {
		wc = true;
		if (sdkp->DPOFUA)
			fua = true;
	}

	blk_queue_write_cache(sdkp->disk->queue, wc, fua);
}

static ssize_t
cache_type_store(struct device *dev, struct device_attribute *attr,
		 const char *buf, size_t count)
{
	int i, ct = -1, rcd, wce, sp;
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	struct scsi_device *sdp = sdkp->device;
	char buffer[64];
	char *buffer_data;
	struct scsi_mode_data data;
	struct scsi_sense_hdr sshdr;
	static const char temp[] = "temporary ";
	int len;

	if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
		/* no cache control on RBC devices; theoretically they
		 * can do it, but there's probably so many exceptions
		 * it's not worth the risk */
		return -EINVAL;

	if (strncmp(buf, temp, sizeof(temp) - 1) == 0) {
		buf += sizeof(temp) - 1;
		sdkp->cache_override = 1;
	} else {
		sdkp->cache_override = 0;
	}

	for (i = 0; i < ARRAY_SIZE(sd_cache_types); i++) {
		len = strlen(sd_cache_types[i]);
		if (strncmp(sd_cache_types[i], buf, len) == 0 &&
		    buf[len] == '\n') {
			ct = i;
			break;
		}
	}
	if (ct < 0)
		return -EINVAL;
	rcd = ct & 0x01 ? 1 : 0;
	wce = (ct & 0x02) && !sdkp->write_prot ? 1 : 0;

	if (sdkp->cache_override) {
		sdkp->WCE = wce;
		sdkp->RCD = rcd;
		sd_set_flush_flag(sdkp);
		return count;
	}

	if (scsi_mode_sense(sdp, 0x08, 8, buffer, sizeof(buffer), SD_TIMEOUT,
			    SD_MAX_RETRIES, &data, NULL))
		return -EINVAL;
	len = min_t(size_t, sizeof(buffer), data.length - data.header_length -
		  data.block_descriptor_length);
	buffer_data = buffer + data.header_length +
		data.block_descriptor_length;
	buffer_data[2] &= ~0x05;
	buffer_data[2] |= wce << 2 | rcd;
	sp = buffer_data[0] & 0x80 ? 1 : 0;
	buffer_data[0] &= ~0x80;

	if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT,
			     SD_MAX_RETRIES, &data, &sshdr)) {
		if (scsi_sense_valid(&sshdr))
			sd_print_sense_hdr(sdkp, &sshdr);
		return -EINVAL;
	}
	revalidate_disk(sdkp->disk);
	return count;
}

static ssize_t
manage_start_stop_show(struct device *dev, struct device_attribute *attr,
		       char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	struct scsi_device *sdp = sdkp->device;

	return snprintf(buf, 20, "%u\n", sdp->manage_start_stop);
}

static ssize_t
manage_start_stop_store(struct device *dev, struct device_attribute *attr,
			const char *buf, size_t count)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	struct scsi_device *sdp = sdkp->device;

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

	sdp->manage_start_stop = simple_strtoul(buf, NULL, 10);

	return count;
}
static DEVICE_ATTR_RW(manage_start_stop);

static ssize_t
allow_restart_show(struct device *dev, struct device_attribute *attr, char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);

	return snprintf(buf, 40, "%d\n", sdkp->device->allow_restart);
}

static ssize_t
allow_restart_store(struct device *dev, struct device_attribute *attr,
		    const char *buf, size_t count)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	struct scsi_device *sdp = sdkp->device;

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

	if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
		return -EINVAL;

	sdp->allow_restart = simple_strtoul(buf, NULL, 10);

	return count;
}
static DEVICE_ATTR_RW(allow_restart);

static ssize_t
cache_type_show(struct device *dev, struct device_attribute *attr, char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	int ct = sdkp->RCD + 2*sdkp->WCE;

	return snprintf(buf, 40, "%s\n", sd_cache_types[ct]);
}
static DEVICE_ATTR_RW(cache_type);

static ssize_t
FUA_show(struct device *dev, struct device_attribute *attr, char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);

	return snprintf(buf, 20, "%u\n", sdkp->DPOFUA);
}
static DEVICE_ATTR_RO(FUA);

static ssize_t
protection_type_show(struct device *dev, struct device_attribute *attr,
		     char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);

	return snprintf(buf, 20, "%u\n", sdkp->protection_type);
}

static ssize_t
protection_type_store(struct device *dev, struct device_attribute *attr,
		      const char *buf, size_t count)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	unsigned int val;
	int err;

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

	err = kstrtouint(buf, 10, &val);

	if (err)
		return err;

	if (val >= 0 && val <= T10_PI_TYPE3_PROTECTION)
		sdkp->protection_type = val;

	return count;
}
static DEVICE_ATTR_RW(protection_type);

static ssize_t
protection_mode_show(struct device *dev, struct device_attribute *attr,
		     char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	struct scsi_device *sdp = sdkp->device;
	unsigned int dif, dix;

	dif = scsi_host_dif_capable(sdp->host, sdkp->protection_type);
	dix = scsi_host_dix_capable(sdp->host, sdkp->protection_type);

	if (!dix && scsi_host_dix_capable(sdp->host, T10_PI_TYPE0_PROTECTION)) {
		dif = 0;
		dix = 1;
	}

	if (!dif && !dix)
		return snprintf(buf, 20, "none\n");

	return snprintf(buf, 20, "%s%u\n", dix ? "dix" : "dif", dif);
}
static DEVICE_ATTR_RO(protection_mode);

static ssize_t
app_tag_own_show(struct device *dev, struct device_attribute *attr, char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);

	return snprintf(buf, 20, "%u\n", sdkp->ATO);
}
static DEVICE_ATTR_RO(app_tag_own);

static ssize_t
thin_provisioning_show(struct device *dev, struct device_attribute *attr,
		       char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);

	return snprintf(buf, 20, "%u\n", sdkp->lbpme);
}
static DEVICE_ATTR_RO(thin_provisioning);

static const char *lbp_mode[] = {
	[SD_LBP_FULL]		= "full",
	[SD_LBP_UNMAP]		= "unmap",
	[SD_LBP_WS16]		= "writesame_16",
	[SD_LBP_WS10]		= "writesame_10",
	[SD_LBP_ZERO]		= "writesame_zero",
	[SD_LBP_DISABLE]	= "disabled",
};

static ssize_t
provisioning_mode_show(struct device *dev, struct device_attribute *attr,
		       char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);

	return snprintf(buf, 20, "%s\n", lbp_mode[sdkp->provisioning_mode]);
}

static ssize_t
provisioning_mode_store(struct device *dev, struct device_attribute *attr,
			const char *buf, size_t count)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	struct scsi_device *sdp = sdkp->device;

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

	if (sd_is_zoned(sdkp)) {
		sd_config_discard(sdkp, SD_LBP_DISABLE);
		return count;
	}

	if (sdp->type != TYPE_DISK)
		return -EINVAL;

	if (!strncmp(buf, lbp_mode[SD_LBP_UNMAP], 20))
		sd_config_discard(sdkp, SD_LBP_UNMAP);
	else if (!strncmp(buf, lbp_mode[SD_LBP_WS16], 20))
		sd_config_discard(sdkp, SD_LBP_WS16);
	else if (!strncmp(buf, lbp_mode[SD_LBP_WS10], 20))
		sd_config_discard(sdkp, SD_LBP_WS10);
	else if (!strncmp(buf, lbp_mode[SD_LBP_ZERO], 20))
		sd_config_discard(sdkp, SD_LBP_ZERO);
	else if (!strncmp(buf, lbp_mode[SD_LBP_DISABLE], 20))
		sd_config_discard(sdkp, SD_LBP_DISABLE);
	else
		return -EINVAL;

	return count;
}
static DEVICE_ATTR_RW(provisioning_mode);

static ssize_t
max_medium_access_timeouts_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);

	return snprintf(buf, 20, "%u\n", sdkp->max_medium_access_timeouts);
}

static ssize_t
max_medium_access_timeouts_store(struct device *dev,
				 struct device_attribute *attr, const char *buf,
				 size_t count)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	int err;

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

	err = kstrtouint(buf, 10, &sdkp->max_medium_access_timeouts);

	return err ? err : count;
}
static DEVICE_ATTR_RW(max_medium_access_timeouts);

static ssize_t
max_write_same_blocks_show(struct device *dev, struct device_attribute *attr,
			   char *buf)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);

	return snprintf(buf, 20, "%u\n", sdkp->max_ws_blocks);
}

static ssize_t
max_write_same_blocks_store(struct device *dev, struct device_attribute *attr,
			    const char *buf, size_t count)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	struct scsi_device *sdp = sdkp->device;
	unsigned long max;
	int err;

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

	if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
		return -EINVAL;

	err = kstrtoul(buf, 10, &max);

	if (err)
		return err;

	if (max == 0)
		sdp->no_write_same = 1;
	else if (max <= SD_MAX_WS16_BLOCKS) {
		sdp->no_write_same = 0;
		sdkp->max_ws_blocks = max;
	}

	sd_config_write_same(sdkp);

	return count;
}
static DEVICE_ATTR_RW(max_write_same_blocks);

static struct attribute *sd_disk_attrs[] = {
	&dev_attr_cache_type.attr,
	&dev_attr_FUA.attr,
	&dev_attr_allow_restart.attr,
	&dev_attr_manage_start_stop.attr,
	&dev_attr_protection_type.attr,
	&dev_attr_protection_mode.attr,
	&dev_attr_app_tag_own.attr,
	&dev_attr_thin_provisioning.attr,
	&dev_attr_provisioning_mode.attr,
	&dev_attr_max_write_same_blocks.attr,
	&dev_attr_max_medium_access_timeouts.attr,
	NULL,
};
ATTRIBUTE_GROUPS(sd_disk);

static struct class sd_disk_class = {
	.name		= "scsi_disk",
	.owner		= THIS_MODULE,
	.dev_release	= scsi_disk_release,
	.dev_groups	= sd_disk_groups,
};

static const struct dev_pm_ops sd_pm_ops = {
	.suspend		= sd_suspend_system,
	.resume			= sd_resume,
	.poweroff		= sd_suspend_system,
	.restore		= sd_resume,
	.runtime_suspend	= sd_suspend_runtime,
	.runtime_resume		= sd_resume,
};

static struct scsi_driver sd_template = {
	.gendrv = {
		.name		= "sd",
		.owner		= THIS_MODULE,
		.probe		= sd_probe,
		.remove		= sd_remove,
		.shutdown	= sd_shutdown,
		.pm		= &sd_pm_ops,
	},
	.rescan			= sd_rescan,
	.init_command		= sd_init_command,
	.uninit_command		= sd_uninit_command,
	.done			= sd_done,
	.eh_action		= sd_eh_action,
};

/*
 * Dummy kobj_map->probe function.
 * The default ->probe function will call modprobe, which is
 * pointless as this module is already loaded.
 */
static struct kobject *sd_default_probe(dev_t devt, int *partno, void *data)
{
	return NULL;
}

/*
 * Device no to disk mapping:
 * 
 *       major         disc2     disc  p1
 *   |............|.............|....|....| <- dev_t
 *    31        20 19          8 7  4 3  0
 * 
 * Inside a major, we have 16k disks, however mapped non-
 * contiguously. The first 16 disks are for major0, the next
 * ones with major1, ... Disk 256 is for major0 again, disk 272 
 * for major1, ... 
 * As we stay compatible with our numbering scheme, we can reuse 
 * the well-know SCSI majors 8, 65--71, 136--143.
 */
static int sd_major(int major_idx)
{
	switch (major_idx) {
	case 0:
		return SCSI_DISK0_MAJOR;
	case 1 ... 7:
		return SCSI_DISK1_MAJOR + major_idx - 1;
	case 8 ... 15:
		return SCSI_DISK8_MAJOR + major_idx - 8;
	default:
		BUG();
		return 0;	/* shut up gcc */
	}
}

static struct scsi_disk *scsi_disk_get(struct gendisk *disk)
{
	struct scsi_disk *sdkp = NULL;

	mutex_lock(&sd_ref_mutex);

	if (disk->private_data) {
		sdkp = scsi_disk(disk);
		if (scsi_device_get(sdkp->device) == 0)
			get_device(&sdkp->dev);
		else
			sdkp = NULL;
	}
	mutex_unlock(&sd_ref_mutex);
	return sdkp;
}

static void scsi_disk_put(struct scsi_disk *sdkp)
{
	struct scsi_device *sdev = sdkp->device;

	mutex_lock(&sd_ref_mutex);
	put_device(&sdkp->dev);
	scsi_device_put(sdev);
	mutex_unlock(&sd_ref_mutex);
}

static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd,
					   unsigned int dix, unsigned int dif)
{
	struct bio *bio = scmd->request->bio;
	unsigned int prot_op = sd_prot_op(rq_data_dir(scmd->request), dix, dif);
	unsigned int protect = 0;

	if (dix) {				/* DIX Type 0, 1, 2, 3 */
		if (bio_integrity_flagged(bio, BIP_IP_CHECKSUM))
			scmd->prot_flags |= SCSI_PROT_IP_CHECKSUM;

		if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
			scmd->prot_flags |= SCSI_PROT_GUARD_CHECK;
	}

	if (dif != T10_PI_TYPE3_PROTECTION) {	/* DIX/DIF Type 0, 1, 2 */
		scmd->prot_flags |= SCSI_PROT_REF_INCREMENT;

		if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
			scmd->prot_flags |= SCSI_PROT_REF_CHECK;
	}

	if (dif) {				/* DIX/DIF Type 1, 2, 3 */
		scmd->prot_flags |= SCSI_PROT_TRANSFER_PI;

		if (bio_integrity_flagged(bio, BIP_DISK_NOCHECK))
			protect = 3 << 5;	/* Disable target PI checking */
		else
			protect = 1 << 5;	/* Enable target PI checking */
	}

	scsi_set_prot_op(scmd, prot_op);
	scsi_set_prot_type(scmd, dif);
	scmd->prot_flags &= sd_prot_flag_mask(prot_op);

	return protect;
}

static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
{
	struct request_queue *q = sdkp->disk->queue;
	unsigned int logical_block_size = sdkp->device->sector_size;
	unsigned int max_blocks = 0;

	q->limits.discard_zeroes_data = 0;

	/*
	 * When LBPRZ is reported, discard alignment and granularity
	 * must be fixed to the logical block size. Otherwise the block
	 * layer will drop misaligned portions of the request which can
	 * lead to data corruption. If LBPRZ is not set, we honor the
	 * device preference.
	 */
	if (sdkp->lbprz) {
		q->limits.discard_alignment = 0;
		q->limits.discard_granularity = logical_block_size;
	} else {
		q->limits.discard_alignment = sdkp->unmap_alignment *
			logical_block_size;
		q->limits.discard_granularity =
			max(sdkp->physical_block_size,
			    sdkp->unmap_granularity * logical_block_size);
	}

	sdkp->provisioning_mode = mode;

	switch (mode) {

	case SD_LBP_DISABLE:
		blk_queue_max_discard_sectors(q, 0);
		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
		return;

	case SD_LBP_UNMAP:
		max_blocks = min_not_zero(sdkp->max_unmap_blocks,
					  (u32)SD_MAX_WS16_BLOCKS);
		break;

	case SD_LBP_WS16:
		max_blocks = min_not_zero(sdkp->max_ws_blocks,
					  (u32)SD_MAX_WS16_BLOCKS);
		q->limits.discard_zeroes_data = sdkp->lbprz;
		break;

	case SD_LBP_WS10:
		max_blocks = min_not_zero(sdkp->max_ws_blocks,
					  (u32)SD_MAX_WS10_BLOCKS);
		q->limits.discard_zeroes_data = sdkp->lbprz;
		break;

	case SD_LBP_ZERO:
		max_blocks = min_not_zero(sdkp->max_ws_blocks,
					  (u32)SD_MAX_WS10_BLOCKS);
		q->limits.discard_zeroes_data = 1;
		break;
	}

	blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9));
	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}

/**
 * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device
 * @sdp: scsi device to operate one
 * @rq: Request to prepare
 *
 * Will issue either UNMAP or WRITE SAME(16) depending on preference
 * indicated by target device.
 **/
static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
{
	struct request *rq = cmd->request;
	struct scsi_device *sdp = cmd->device;
	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
	sector_t sector = blk_rq_pos(rq);
	unsigned int nr_sectors = blk_rq_sectors(rq);
	unsigned int len;
	int ret;
	char *buf;
	struct page *page;

	sector >>= ilog2(sdp->sector_size) - 9;
	nr_sectors >>= ilog2(sdp->sector_size) - 9;

	page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
	if (!page)
		return BLKPREP_DEFER;

	switch (sdkp->provisioning_mode) {
	case SD_LBP_UNMAP:
		buf = page_address(page);

		cmd->cmd_len = 10;
		cmd->cmnd[0] = UNMAP;
		cmd->cmnd[8] = 24;

		put_unaligned_be16(6 + 16, &buf[0]);
		put_unaligned_be16(16, &buf[2]);
		put_unaligned_be64(sector, &buf[8]);
		put_unaligned_be32(nr_sectors, &buf[16]);

		len = 24;
		break;

	case SD_LBP_WS16:
		cmd->cmd_len = 16;
		cmd->cmnd[0] = WRITE_SAME_16;
		cmd->cmnd[1] = 0x8; /* UNMAP */
		put_unaligned_be64(sector, &cmd->cmnd[2]);
		put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);

		len = sdkp->device->sector_size;
		break;

	case SD_LBP_WS10:
	case SD_LBP_ZERO:
		cmd->cmd_len = 10;
		cmd->cmnd[0] = WRITE_SAME;
		if (sdkp->provisioning_mode == SD_LBP_WS10)
			cmd->cmnd[1] = 0x8; /* UNMAP */
		put_unaligned_be32(sector, &cmd->cmnd[2]);
		put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);

		len = sdkp->device->sector_size;
		break;

	default:
		ret = BLKPREP_INVALID;
		goto out;
	}

	rq->timeout = SD_TIMEOUT;

	cmd->transfersize = len;
	cmd->allowed = SD_MAX_RETRIES;

	rq->special_vec.bv_page = page;
	rq->special_vec.bv_offset = 0;
	rq->special_vec.bv_len = len;

	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
	rq->resid_len = len;

	ret = scsi_init_io(cmd);
out:
	if (ret != BLKPREP_OK)
		__free_page(page);
	return ret;
}

static void sd_config_write_same(struct scsi_disk *sdkp)
{
	struct request_queue *q = sdkp->disk->queue;
	unsigned int logical_block_size = sdkp->device->sector_size;

	if (sdkp->device->no_write_same) {
		sdkp->max_ws_blocks = 0;
		goto out;
	}

	/* Some devices can not handle block counts above 0xffff despite
	 * supporting WRITE SAME(16). Consequently we default to 64k
	 * blocks per I/O unless the device explicitly advertises a
	 * bigger limit.
	 */
	if (sdkp->max_ws_blocks > SD_MAX_WS10_BLOCKS)
		sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks,
						   (u32)SD_MAX_WS16_BLOCKS);
	else if (sdkp->ws16 || sdkp->ws10 || sdkp->device->no_report_opcodes)
		sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks,
						   (u32)SD_MAX_WS10_BLOCKS);
	else {
		sdkp->device->no_write_same = 1;
		sdkp->max_ws_blocks = 0;
	}

out:
	blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks *
					 (logical_block_size >> 9));
}

/**
 * sd_setup_write_same_cmnd - write the same data to multiple blocks
 * @cmd: command to prepare
 *
 * Will issue either WRITE SAME(10) or WRITE SAME(16) depending on
 * preference indicated by target device.
 **/
static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
{
	struct request *rq = cmd->request;
	struct scsi_device *sdp = cmd->device;
	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
	struct bio *bio = rq->bio;
	sector_t sector = blk_rq_pos(rq);
	unsigned int nr_sectors = blk_rq_sectors(rq);
	unsigned int nr_bytes = blk_rq_bytes(rq);
	int ret;

	if (sdkp->device->no_write_same)
		return BLKPREP_INVALID;

	BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size);

	if (sd_is_zoned(sdkp)) {
		ret = sd_zbc_setup_write_cmnd(cmd);
		if (ret != BLKPREP_OK)
			return ret;
	}

	sector >>= ilog2(sdp->sector_size) - 9;
	nr_sectors >>= ilog2(sdp->sector_size) - 9;

	rq->timeout = SD_WRITE_SAME_TIMEOUT;

	if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff) {
		cmd->cmd_len = 16;
		cmd->cmnd[0] = WRITE_SAME_16;
		put_unaligned_be64(sector, &cmd->cmnd[2]);
		put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
	} else {
		cmd->cmd_len = 10;
		cmd->cmnd[0] = WRITE_SAME;
		put_unaligned_be32(sector, &cmd->cmnd[2]);
		put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
	}

	cmd->transfersize = sdp->sector_size;
	cmd->allowed = SD_MAX_RETRIES;

	/*
	 * For WRITE_SAME the data transferred in the DATA IN buffer is
	 * different from the amount of data actually written to the target.
	 *
	 * We set up __data_len to the amount of data transferred from the
	 * DATA IN buffer so that blk_rq_map_sg set up the proper S/G list
	 * to transfer a single sector of data first, but then reset it to
	 * the amount of data to be written right after so that the I/O path
	 * knows how much to actually write.
	 */
	rq->__data_len = sdp->sector_size;
	ret = scsi_init_io(cmd);
	rq->__data_len = nr_bytes;
	return ret;
}

static int sd_setup_flush_cmnd(struct scsi_cmnd *cmd)
{
	struct request *rq = cmd->request;

	/* flush requests don't perform I/O, zero the S/G table */
	memset(&cmd->sdb, 0, sizeof(cmd->sdb));

	cmd->cmnd[0] = SYNCHRONIZE_CACHE;
	cmd->cmd_len = 10;
	cmd->transfersize = 0;
	cmd->allowed = SD_MAX_RETRIES;

	rq->timeout = rq->q->rq_timeout * SD_FLUSH_TIMEOUT_MULTIPLIER;
	return BLKPREP_OK;
}

static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
{
	struct request *rq = SCpnt->request;
	struct scsi_device *sdp = SCpnt->device;
	struct gendisk *disk = rq->rq_disk;
	struct scsi_disk *sdkp = scsi_disk(disk);
	sector_t block = blk_rq_pos(rq);
	sector_t threshold;
	unsigned int this_count = blk_rq_sectors(rq);
	unsigned int dif, dix;
	bool zoned_write = sd_is_zoned(sdkp) && rq_data_dir(rq) == WRITE;
	int ret;
	unsigned char protect;

	if (zoned_write) {
		ret = sd_zbc_setup_write_cmnd(SCpnt);
		if (ret != BLKPREP_OK)
			return ret;
	}

	ret = scsi_init_io(SCpnt);
	if (ret != BLKPREP_OK)
		goto out;
	SCpnt = rq->special;

	/* from here on until we're complete, any goto out
	 * is used for a killable error condition */
	ret = BLKPREP_KILL;

	SCSI_LOG_HLQUEUE(1,
		scmd_printk(KERN_INFO, SCpnt,
			"%s: block=%llu, count=%d\n",
			__func__, (unsigned long long)block, this_count));

	if (!sdp || !scsi_device_online(sdp) ||
	    block + blk_rq_sectors(rq) > get_capacity(disk)) {
		SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
						"Finishing %u sectors\n",
						blk_rq_sectors(rq)));
		SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
						"Retry with 0x%p\n", SCpnt));
		goto out;
	}

	if (sdp->changed) {
		/*
		 * quietly refuse to do anything to a changed disc until 
		 * the changed bit has been reset
		 */
		/* printk("SCSI disk has been changed or is not present. Prohibiting further I/O.\n"); */
		goto out;
	}

	/*
	 * Some SD card readers can't handle multi-sector accesses which touch
	 * the last one or two hardware sectors.  Split accesses as needed.
	 */
	threshold = get_capacity(disk) - SD_LAST_BUGGY_SECTORS *
		(sdp->sector_size / 512);

	if (unlikely(sdp->last_sector_bug && block + this_count > threshold)) {
		if (block < threshold) {
			/* Access up to the threshold but not beyond */
			this_count = threshold - block;
		} else {
			/* Access only a single hardware sector */
			this_count = sdp->sector_size / 512;
		}
	}

	SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, "block=%llu\n",
					(unsigned long long)block));

	/*
	 * If we have a 1K hardware sectorsize, prevent access to single
	 * 512 byte sectors.  In theory we could handle this - in fact
	 * the scsi cdrom driver must be able to handle this because
	 * we typically use 1K blocksizes, and cdroms typically have
	 * 2K hardware sectorsizes.  Of course, things are simpler
	 * with the cdrom, since it is read-only.  For performance
	 * reasons, the filesystems should be able to handle this
	 * and not force the scsi disk driver to use bounce buffers
	 * for this.
	 */
	if (sdp->sector_size == 1024) {
		if ((block & 1) || (blk_rq_sectors(rq) & 1)) {
			scmd_printk(KERN_ERR, SCpnt,
				    "Bad block number requested\n");
			goto out;
		} else {
			block = block >> 1;
			this_count = this_count >> 1;
		}
	}
	if (sdp->sector_size == 2048) {
		if ((block & 3) || (blk_rq_sectors(rq) & 3)) {
			scmd_printk(KERN_ERR, SCpnt,
				    "Bad block number requested\n");
			goto out;
		} else {
			block = block >> 2;
			this_count = this_count >> 2;
		}
	}
	if (sdp->sector_size == 4096) {
		if ((block & 7) || (blk_rq_sectors(rq) & 7)) {
			scmd_printk(KERN_ERR, SCpnt,
				    "Bad block number requested\n");
			goto out;
		} else {
			block = block >> 3;
			this_count = this_count >> 3;
		}
	}
	if (rq_data_dir(rq) == WRITE) {
		SCpnt->cmnd[0] = WRITE_6;

		if (blk_integrity_rq(rq))
			sd_dif_prepare(SCpnt);

	} else if (rq_data_dir(rq) == READ) {
		SCpnt->cmnd[0] = READ_6;
	} else {
		scmd_printk(KERN_ERR, SCpnt, "Unknown command %d\n", req_op(rq));
		goto out;
	}

	SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
					"%s %d/%u 512 byte blocks.\n",
					(rq_data_dir(rq) == WRITE) ?
					"writing" : "reading", this_count,
					blk_rq_sectors(rq)));

	dix = scsi_prot_sg_count(SCpnt);
	dif = scsi_host_dif_capable(SCpnt->device->host, sdkp->protection_type);

	if (dif || dix)
		protect = sd_setup_protect_cmnd(SCpnt, dix, dif);
	else
		protect = 0;

	if (protect && sdkp->protection_type == T10_PI_TYPE2_PROTECTION) {
		SCpnt->cmnd = mempool_alloc(sd_cdb_pool, GFP_ATOMIC);

		if (unlikely(SCpnt->cmnd == NULL)) {
			ret = BLKPREP_DEFER;
			goto out;
		}

		SCpnt->cmd_len = SD_EXT_CDB_SIZE;
		memset(SCpnt->cmnd, 0, SCpnt->cmd_len);
		SCpnt->cmnd[0] = VARIABLE_LENGTH_CMD;
		SCpnt->cmnd[7] = 0x18;
		SCpnt->cmnd[9] = (rq_data_dir(rq) == READ) ? READ_32 : WRITE_32;
		SCpnt->cmnd[10] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0);

		/* LBA */
		SCpnt->cmnd[12] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0;
		SCpnt->cmnd[13] = sizeof(block) > 4 ? (unsigned char) (block >> 48) & 0xff : 0;
		SCpnt->cmnd[14] = sizeof(block) > 4 ? (unsigned char) (block >> 40) & 0xff : 0;
		SCpnt->cmnd[15] = sizeof(block) > 4 ? (unsigned char) (block >> 32) & 0xff : 0;
		SCpnt->cmnd[16] = (unsigned char) (block >> 24) & 0xff;
		SCpnt->cmnd[17] = (unsigned char) (block >> 16) & 0xff;
		SCpnt->cmnd[18] = (unsigned char) (block >> 8) & 0xff;
		SCpnt->cmnd[19] = (unsigned char) block & 0xff;

		/* Expected Indirect LBA */
		SCpnt->cmnd[20] = (unsigned char) (block >> 24) & 0xff;
		SCpnt->cmnd[21] = (unsigned char) (block >> 16) & 0xff;
		SCpnt->cmnd[22] = (unsigned char) (block >> 8) & 0xff;
		SCpnt->cmnd[23] = (unsigned char) block & 0xff;

		/* Transfer length */
		SCpnt->cmnd[28] = (unsigned char) (this_count >> 24) & 0xff;
		SCpnt->cmnd[29] = (unsigned char) (this_count >> 16) & 0xff;
		SCpnt->cmnd[30] = (unsigned char) (this_count >> 8) & 0xff;
		SCpnt->cmnd[31] = (unsigned char) this_count & 0xff;
	} else if (sdp->use_16_for_rw || (this_count > 0xffff)) {
		SCpnt->cmnd[0] += READ_16 - READ_6;
		SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0);
		SCpnt->cmnd[2] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0;
		SCpnt->cmnd[3] = sizeof(block) > 4 ? (unsigned char) (block >> 48) & 0xff : 0;
		SCpnt->cmnd[4] = sizeof(block) > 4 ? (unsigned char) (block >> 40) & 0xff : 0;
		SCpnt->cmnd[5] = sizeof(block) > 4 ? (unsigned char) (block >> 32) & 0xff : 0;
		SCpnt->cmnd[6] = (unsigned char) (block >> 24) & 0xff;
		SCpnt->cmnd[7] = (unsigned char) (block >> 16) & 0xff;
		SCpnt->cmnd[8] = (unsigned char) (block >> 8) & 0xff;
		SCpnt->cmnd[9] = (unsigned char) block & 0xff;
		SCpnt->cmnd[10] = (unsigned char) (this_count >> 24) & 0xff;
		SCpnt->cmnd[11] = (unsigned char) (this_count >> 16) & 0xff;
		SCpnt->cmnd[12] = (unsigned char) (this_count >> 8) & 0xff;
		SCpnt->cmnd[13] = (unsigned char) this_count & 0xff;
		SCpnt->cmnd[14] = SCpnt->cmnd[15] = 0;
	} else if ((this_count > 0xff) || (block > 0x1fffff) ||
		   scsi_device_protection(SCpnt->device) ||
		   SCpnt->device->use_10_for_rw) {
		SCpnt->cmnd[0] += READ_10 - READ_6;
		SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0);
		SCpnt->cmnd[2] = (unsigned char) (block >> 24) & 0xff;
		SCpnt->cmnd[3] = (unsigned char) (block >> 16) & 0xff;
		SCpnt->cmnd[4] = (unsigned char) (block >> 8) & 0xff;
		SCpnt->cmnd[5] = (unsigned char) block & 0xff;
		SCpnt->cmnd[6] = SCpnt->cmnd[9] = 0;
		SCpnt->cmnd[7] = (unsigned char) (this_count >> 8) & 0xff;
		SCpnt->cmnd[8] = (unsigned char) this_count & 0xff;
	} else {
		if (unlikely(rq->cmd_flags & REQ_FUA)) {
			/*
			 * This happens only if this drive failed
			 * 10byte rw command with ILLEGAL_REQUEST
			 * during operation and thus turned off
			 * use_10_for_rw.
			 */
			scmd_printk(KERN_ERR, SCpnt,
				    "FUA write on READ/WRITE(6) drive\n");
			goto out;
		}

		SCpnt->cmnd[1] |= (unsigned char) ((block >> 16) & 0x1f);
		SCpnt->cmnd[2] = (unsigned char) ((block >> 8) & 0xff);
		SCpnt->cmnd[3] = (unsigned char) block & 0xff;
		SCpnt->cmnd[4] = (unsigned char) this_count;
		SCpnt->cmnd[5] = 0;
	}
	SCpnt->sdb.length = this_count * sdp->sector_size;

	/*
	 * We shouldn't disconnect in the middle of a sector, so with a dumb
	 * host adapter, it's safe to assume that we can at least transfer
	 * this many bytes between each connect / disconnect.
	 */
	SCpnt->transfersize = sdp->sector_size;
	SCpnt->underflow = this_count << 9;
	SCpnt->allowed = SD_MAX_RETRIES;

	/*
	 * This indicates that the command is ready from our end to be
	 * queued.
	 */
	ret = BLKPREP_OK;
 out:
	if (zoned_write && ret != BLKPREP_OK)
		sd_zbc_cancel_write_cmnd(SCpnt);

	return ret;
}

static int sd_init_command(struct scsi_cmnd *cmd)
{
	struct request *rq = cmd->request;

	switch (req_op(rq)) {
	case REQ_OP_DISCARD:
		return sd_setup_discard_cmnd(cmd);
	case REQ_OP_WRITE_SAME:
		return sd_setup_write_same_cmnd(cmd);
	case REQ_OP_FLUSH:
		return sd_setup_flush_cmnd(cmd);
	case REQ_OP_READ:
	case REQ_OP_WRITE:
		return sd_setup_read_write_cmnd(cmd);
	case REQ_OP_ZONE_REPORT:
		return sd_zbc_setup_report_cmnd(cmd);
	case REQ_OP_ZONE_RESET:
		return sd_zbc_setup_reset_cmnd(cmd);
	default:
		BUG();
	}
}

static void sd_uninit_command(struct scsi_cmnd *SCpnt)
{
	struct request *rq = SCpnt->request;

	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
		__free_page(rq->special_vec.bv_page);

	if (SCpnt->cmnd != rq->cmd) {
		mempool_free(SCpnt->cmnd, sd_cdb_pool);
		SCpnt->cmnd = NULL;
		SCpnt->cmd_len = 0;
	}
}

/**
 *	sd_open - open a scsi disk device
 *	@inode: only i_rdev member may be used
 *	@filp: only f_mode and f_flags may be used
 *
 *	Returns 0 if successful. Returns a negated errno value in case 
 *	of error.
 *
 *	Note: This can be called from a user context (e.g. fsck(1) )
 *	or from within the kernel (e.g. as a result of a mount(1) ).
 *	In the latter case @inode and @filp carry an abridged amount
 *	of information as noted above.
 *
 *	Locking: called with bdev->bd_mutex held.
 **/
static int sd_open(struct block_device *bdev, fmode_t mode)
{
	struct scsi_disk *sdkp = scsi_disk_get(bdev->bd_disk);
	struct scsi_device *sdev;
	int retval;

	if (!sdkp)
		return -ENXIO;

	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_open\n"));

	sdev = sdkp->device;

	/*
	 * If the device is in error recovery, wait until it is done.
	 * If the device is offline, then disallow any access to it.
	 */
	retval = -ENXIO;
	if (!scsi_block_when_processing_errors(sdev))
		goto error_out;

	if (sdev->removable || sdkp->write_prot)
		check_disk_change(bdev);

	/*
	 * If the drive is empty, just let the open fail.
	 */
	retval = -ENOMEDIUM;
	if (sdev->removable && !sdkp->media_present && !(mode & FMODE_NDELAY))
		goto error_out;

	/*
	 * If the device has the write protect tab set, have the open fail
	 * if the user expects to be able to write to the thing.
	 */
	retval = -EROFS;
	if (sdkp->write_prot && (mode & FMODE_WRITE))
		goto error_out;

	/*
	 * It is possible that the disk changing stuff resulted in
	 * the device being taken offline.  If this is the case,
	 * report this to the user, and don't pretend that the
	 * open actually succeeded.
	 */
	retval = -ENXIO;
	if (!scsi_device_online(sdev))
		goto error_out;

	if ((atomic_inc_return(&sdkp->openers) == 1) && sdev->removable) {
		if (scsi_block_when_processing_errors(sdev))
			scsi_set_medium_removal(sdev, SCSI_REMOVAL_PREVENT);
	}

	return 0;

error_out:
	scsi_disk_put(sdkp);
	return retval;	
}

/**
 *	sd_release - invoked when the (last) close(2) is called on this
 *	scsi disk.
 *	@inode: only i_rdev member may be used
 *	@filp: only f_mode and f_flags may be used
 *
 *	Returns 0. 
 *
 *	Note: may block (uninterruptible) if error recovery is underway
 *	on this disk.
 *
 *	Locking: called with bdev->bd_mutex held.
 **/
static void sd_release(struct gendisk *disk, fmode_t mode)
{
	struct scsi_disk *sdkp = scsi_disk(disk);
	struct scsi_device *sdev = sdkp->device;

	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_release\n"));

	if (atomic_dec_return(&sdkp->openers) == 0 && sdev->removable) {
		if (scsi_block_when_processing_errors(sdev))
			scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW);
	}

	/*
	 * XXX and what if there are packets in flight and this close()
	 * XXX is followed by a "rmmod sd_mod"?
	 */

	scsi_disk_put(sdkp);
}

static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
	struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk);
	struct scsi_device *sdp = sdkp->device;
	struct Scsi_Host *host = sdp->host;
	sector_t capacity = logical_to_sectors(sdp, sdkp->capacity);
	int diskinfo[4];

	/* default to most commonly used values */
	diskinfo[0] = 0x40;	/* 1 << 6 */
	diskinfo[1] = 0x20;	/* 1 << 5 */
	diskinfo[2] = capacity >> 11;

	/* override with calculated, extended default, or driver values */
	if (host->hostt->bios_param)
		host->hostt->bios_param(sdp, bdev, capacity, diskinfo);
	else
		scsicam_bios_param(bdev, capacity, diskinfo);

	geo->heads = diskinfo[0];
	geo->sectors = diskinfo[1];
	geo->cylinders = diskinfo[2];
	return 0;
}

/**
 *	sd_ioctl - process an ioctl
 *	@inode: only i_rdev/i_bdev members may be used
 *	@filp: only f_mode and f_flags may be used
 *	@cmd: ioctl command number
 *	@arg: this is third argument given to ioctl(2) system call.
 *	Often contains a pointer.
 *
 *	Returns 0 if successful (some ioctls return positive numbers on
 *	success as well). Returns a negated errno value in case of error.
 *
 *	Note: most ioctls are forward onto the block subsystem or further
 *	down in the scsi subsystem.
 **/
static int sd_ioctl(struct block_device *bdev, fmode_t mode,
		    unsigned int cmd, unsigned long arg)
{
	struct gendisk *disk = bdev->bd_disk;
	struct scsi_disk *sdkp = scsi_disk(disk);
	struct scsi_device *sdp = sdkp->device;
	void __user *p = (void __user *)arg;
	int error;
    
	SCSI_LOG_IOCTL(1, sd_printk(KERN_INFO, sdkp, "sd_ioctl: disk=%s, "
				    "cmd=0x%x\n", disk->disk_name, cmd));

	error = scsi_verify_blk_ioctl(bdev, cmd);
	if (error < 0)
		return error;

	/*
	 * If we are in the middle of error recovery, don't let anyone
	 * else try and use this device.  Also, if error recovery fails, it
	 * may try and take the device offline, in which case all further
	 * access to the device is prohibited.
	 */
	error = scsi_ioctl_block_when_processing_errors(sdp, cmd,
			(mode & FMODE_NDELAY) != 0);
	if (error)
		goto out;

	/*
	 * Send SCSI addressing ioctls directly to mid level, send other
	 * ioctls to block level and then onto mid level if they can't be
	 * resolved.
	 */
	switch (cmd) {
		case SCSI_IOCTL_GET_IDLUN:
		case SCSI_IOCTL_GET_BUS_NUMBER:
			error = scsi_ioctl(sdp, cmd, p);
			break;
		default:
			error = scsi_cmd_blk_ioctl(bdev, mode, cmd, p);
			if (error != -ENOTTY)
				break;
			error = scsi_ioctl(sdp, cmd, p);
			break;
	}
out:
	return error;
}

static void set_media_not_present(struct scsi_disk *sdkp)
{
	if (sdkp->media_present)
		sdkp->device->changed = 1;

	if (sdkp->device->removable) {
		sdkp->media_present = 0;
		sdkp->capacity = 0;
	}
}

static int media_not_present(struct scsi_disk *sdkp,
			     struct scsi_sense_hdr *sshdr)
{
	if (!scsi_sense_valid(sshdr))
		return 0;

	/* not invoked for commands that could return deferred errors */
	switch (sshdr->sense_key) {
	case UNIT_ATTENTION:
	case NOT_READY:
		/* medium not present */
		if (sshdr->asc == 0x3A) {
			set_media_not_present(sdkp);
			return 1;
		}
	}
	return 0;
}

/**
 *	sd_check_events - check media events
 *	@disk: kernel device descriptor
 *	@clearing: disk events currently being cleared
 *
 *	Returns mask of DISK_EVENT_*.
 *
 *	Note: this function is invoked from the block subsystem.
 **/
static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing)
{
	struct scsi_disk *sdkp = scsi_disk_get(disk);
	struct scsi_device *sdp;
	struct scsi_sense_hdr *sshdr = NULL;
	int retval;

	if (!sdkp)
		return 0;

	sdp = sdkp->device;
	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_check_events\n"));

	/*
	 * If the device is offline, don't send any commands - just pretend as
	 * if the command failed.  If the device ever comes back online, we
	 * can deal with it then.  It is only because of unrecoverable errors
	 * that we would ever take a device offline in the first place.
	 */
	if (!scsi_device_online(sdp)) {
		set_media_not_present(sdkp);
		goto out;
	}

	/*
	 * Using TEST_UNIT_READY enables differentiation between drive with
	 * no cartridge loaded - NOT READY, drive with changed cartridge -
	 * UNIT ATTENTION, or with same cartridge - GOOD STATUS.
	 *
	 * Drives that auto spin down. eg iomega jaz 1G, will be started
	 * by sd_spinup_disk() from sd_revalidate_disk(), which happens whenever
	 * sd_revalidate() is called.
	 */
	retval = -ENODEV;

	if (scsi_block_when_processing_errors(sdp)) {
		sshdr  = kzalloc(sizeof(*sshdr), GFP_KERNEL);
		retval = scsi_test_unit_ready(sdp, SD_TIMEOUT, SD_MAX_RETRIES,
					      sshdr);
	}

	/* failed to execute TUR, assume media not present */
	if (host_byte(retval)) {
		set_media_not_present(sdkp);
		goto out;
	}

	if (media_not_present(sdkp, sshdr))
		goto out;

	/*
	 * For removable scsi disk we have to recognise the presence
	 * of a disk in the drive.
	 */
	if (!sdkp->media_present)
		sdp->changed = 1;
	sdkp->media_present = 1;
out:
	/*
	 * sdp->changed is set under the following conditions:
	 *
	 *	Medium present state has changed in either direction.
	 *	Device has indicated UNIT_ATTENTION.
	 */
	kfree(sshdr);
	retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0;
	sdp->changed = 0;
	scsi_disk_put(sdkp);
	return retval;
}

static int sd_sync_cache(struct scsi_disk *sdkp)
{
	int retries, res;
	struct scsi_device *sdp = sdkp->device;
	const int timeout = sdp->request_queue->rq_timeout
		* SD_FLUSH_TIMEOUT_MULTIPLIER;
	struct scsi_sense_hdr sshdr;

	if (!scsi_device_online(sdp))
		return -ENODEV;

	for (retries = 3; retries > 0; --retries) {
		unsigned char cmd[10] = { 0 };

		cmd[0] = SYNCHRONIZE_CACHE;
		/*
		 * Leave the rest of the command zero to indicate
		 * flush everything.
		 */
		res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0,
					     &sshdr, timeout, SD_MAX_RETRIES,
					     NULL, 0, RQF_PM);
		if (res == 0)
			break;
	}

	if (res) {
		sd_print_result(sdkp, "Synchronize Cache(10) failed", res);

		if (driver_byte(res) & DRIVER_SENSE)
			sd_print_sense_hdr(sdkp, &sshdr);
		/* we need to evaluate the error return  */
		if (scsi_sense_valid(&sshdr) &&
			(sshdr.asc == 0x3a ||	/* medium not present */
			 sshdr.asc == 0x20))	/* invalid command */
				/* this is no error here */
				return 0;

		switch (host_byte(res)) {
		/* ignore errors due to racing a disconnection */
		case DID_BAD_TARGET:
		case DID_NO_CONNECT:
			return 0;
		/* signal the upper layer it might try again */
		case DID_BUS_BUSY:
		case DID_IMM_RETRY:
		case DID_REQUEUE:
		case DID_SOFT_ERROR:
			return -EBUSY;
		default:
			return -EIO;
		}
	}
	return 0;
}

static void sd_rescan(struct device *dev)
{
	struct scsi_disk *sdkp = dev_get_drvdata(dev);

	revalidate_disk(sdkp->disk);
}


#ifdef CONFIG_COMPAT
/* 
 * This gets directly called from VFS. When the ioctl 
 * is not recognized we go back to the other translation paths. 
 */
static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode,
			   unsigned int cmd, unsigned long arg)
{
	struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device;
	int error;

	error = scsi_ioctl_block_when_processing_errors(sdev, cmd,
			(mode & FMODE_NDELAY) != 0);
	if (error)
		return error;
	       
	/* 
	 * Let the static ioctl translation table take care of it.
	 */
	if (!sdev->host->hostt->compat_ioctl)
		return -ENOIOCTLCMD; 
	return sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg);
}
#endif

static char sd_pr_type(enum pr_type type)
{
	switch (type) {
	case PR_WRITE_EXCLUSIVE:
		return 0x01;
	case PR_EXCLUSIVE_ACCESS:
		return 0x03;
	case PR_WRITE_EXCLUSIVE_REG_ONLY:
		return 0x05;
	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
		return 0x06;
	case PR_WRITE_EXCLUSIVE_ALL_REGS:
		return 0x07;
	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
		return 0x08;
	default:
		return 0;
	}
};

static int sd_pr_command(struct block_device *bdev, u8 sa,
		u64 key, u64 sa_key, u8 type, u8 flags)
{
	struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device;
	struct scsi_sense_hdr sshdr;
	int result;
	u8 cmd[16] = { 0, };
	u8 data[24] = { 0, };

	cmd[0] = PERSISTENT_RESERVE_OUT;
	cmd[1] = sa;
	cmd[2] = type;
	put_unaligned_be32(sizeof(data), &cmd[5]);

	put_unaligned_be64(key, &data[0]);
	put_unaligned_be64(sa_key, &data[8]);
	data[20] = flags;

	result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, &data, sizeof(data),
			&sshdr, SD_TIMEOUT, SD_MAX_RETRIES, NULL);

	if ((driver_byte(result) & DRIVER_SENSE) &&
	    (scsi_sense_valid(&sshdr))) {
		sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result);
		scsi_print_sense_hdr(sdev, NULL, &sshdr);
	}

	return result;
}

static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
		u32 flags)
{
	if (flags & ~PR_FL_IGNORE_KEY)
		return -EOPNOTSUPP;
	return sd_pr_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00,
			old_key, new_key, 0,
			(1 << 0) /* APTPL */);
}

static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
		u32 flags)
{
	if (flags)
		return -EOPNOTSUPP;
	return sd_pr_command(bdev, 0x01, key, 0, sd_pr_type(type), 0);
}

static int sd_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
{
	return sd_pr_command(bdev, 0x02, key, 0, sd_pr_type(type), 0);
}

static int sd_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
		enum pr_type type, bool abort)
{
	return sd_pr_command(bdev, abort ? 0x05 : 0x04, old_key, new_key,
			     sd_pr_type(type), 0);
}

static int sd_pr_clear(struct block_device *bdev, u64 key)
{
	return sd_pr_command(bdev, 0x03, key, 0, 0, 0);
}

static const struct pr_ops sd_pr_ops = {
	.pr_register	= sd_pr_register,
	.pr_reserve	= sd_pr_reserve,
	.pr_release	= sd_pr_release,
	.pr_preempt	= sd_pr_preempt,
	.pr_clear	= sd_pr_clear,
};

static const struct block_device_operations sd_fops = {
	.owner			= THIS_MODULE,
	.open			= sd_open,
	.release		= sd_release,
	.ioctl			= sd_ioctl,
	.getgeo			= sd_getgeo,
#ifdef CONFIG_COMPAT
	.compat_ioctl		= sd_compat_ioctl,
#endif
	.check_events		= sd_check_events,
	.revalidate_disk	= sd_revalidate_disk,
	.unlock_native_capacity	= sd_unlock_native_capacity,
	.pr_ops			= &sd_pr_ops,
};

/**
 *	sd_eh_action - error handling callback
 *	@scmd:		sd-issued command that has failed
 *	@eh_disp:	The recovery disposition suggested by the midlayer
 *
 *	This function is called by the SCSI midlayer upon completion of an
 *	error test command (currently TEST UNIT READY). The result of sending
 *	the eh command is passed in eh_disp.  We're looking for devices that
 *	fail medium access commands but are OK with non access commands like
 *	test unit ready (so wrongly see the device as having a successful
 *	recovery)
 **/
static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp)
{
	struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk);

	if (!scsi_device_online(scmd->device) ||
	    !scsi_medium_access_command(scmd) ||
	    host_byte(scmd->result) != DID_TIME_OUT ||
	    eh_disp != SUCCESS)
		return eh_disp;

	/*
	 * The device has timed out executing a medium access command.
	 * However, the TEST UNIT READY command sent during error
	 * handling completed successfully. Either the device is in the
	 * process of recovering or has it suffered an internal failure
	 * that prevents access to the storage medium.
	 */
	sdkp->medium_access_timed_out++;

	/*
	 * If the device keeps failing read/write commands but TEST UNIT
	 * READY always completes successfully we assume that medium
	 * access is no longer possible and take the device offline.
	 */
	if (sdkp->medium_access_timed_out >= sdkp->max_medium_access_timeouts) {
		scmd_printk(KERN_ERR, scmd,
			    "Medium access timeout failure. Offlining disk!\n");
		scsi_device_set_state(scmd->device, SDEV_OFFLINE);

		return FAILED;
	}

	return eh_disp;
}

static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd)
{
	u64 start_lba = blk_rq_pos(scmd->request);
	u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512);
	u64 factor = scmd->device->sector_size / 512;
	u64 bad_lba;
	int info_valid;
	/*
	 * resid is optional but mostly filled in.  When it's unused,
	 * its value is zero, so we assume the whole buffer transferred
	 */
	unsigned int transferred = scsi_bufflen(scmd) - scsi_get_resid(scmd);
	unsigned int good_bytes;

	if (scmd->request->cmd_type != REQ_TYPE_FS)
		return 0;

	info_valid = scsi_get_sense_info_fld(scmd->sense_buffer,
					     SCSI_SENSE_BUFFERSIZE,
					     &bad_lba);
	if (!info_valid)
		return 0;

	if (scsi_bufflen(scmd) <= scmd->device->sector_size)
		return 0;

	/* be careful ... don't want any overflows */
	do_div(start_lba, factor);
	do_div(end_lba, factor);

	/* The bad lba was reported incorrectly, we have no idea where
	 * the error is.
	 */
	if (bad_lba < start_lba  || bad_lba >= end_lba)
		return 0;

	/* This computation should always be done in terms of
	 * the resolution of the device's medium.
	 */
	good_bytes = (bad_lba - start_lba) * scmd->device->sector_size;
	return min(good_bytes, transferred);
}

/**
 *	sd_done - bottom half handler: called when the lower level
 *	driver has completed (successfully or otherwise) a scsi command.
 *	@SCpnt: mid-level's per command structure.
 *
 *	Note: potentially run from within an ISR. Must not block.
 **/
static int sd_done(struct scsi_cmnd *SCpnt)
{
	int result = SCpnt->result;
	unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt);
	struct scsi_sense_hdr sshdr;
	struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk);
	struct request *req = SCpnt->request;
	int sense_valid = 0;
	int sense_deferred = 0;
	unsigned char op = SCpnt->cmnd[0];
	unsigned char unmap = SCpnt->cmnd[1] & 8;

	switch (req_op(req)) {
	case REQ_OP_DISCARD:
	case REQ_OP_WRITE_SAME:
	case REQ_OP_ZONE_RESET:
		if (!result) {
			good_bytes = blk_rq_bytes(req);
			scsi_set_resid(SCpnt, 0);
		} else {
			good_bytes = 0;
			scsi_set_resid(SCpnt, blk_rq_bytes(req));
		}
		break;
	case REQ_OP_ZONE_REPORT:
		if (!result) {
			good_bytes = scsi_bufflen(SCpnt)
				- scsi_get_resid(SCpnt);
			scsi_set_resid(SCpnt, 0);
		} else {
			good_bytes = 0;
			scsi_set_resid(SCpnt, blk_rq_bytes(req));
		}
		break;
	}

	if (result) {
		sense_valid = scsi_command_normalize_sense(SCpnt, &sshdr);
		if (sense_valid)
			sense_deferred = scsi_sense_is_deferred(&sshdr);
	}
	sdkp->medium_access_timed_out = 0;

	if (driver_byte(result) != DRIVER_SENSE &&
	    (!sense_valid || sense_deferred))
		goto out;

	switch (sshdr.sense_key) {
	case HARDWARE_ERROR:
	case MEDIUM_ERROR:
		good_bytes = sd_completed_bytes(SCpnt);
		break;
	case RECOVERED_ERROR:
		good_bytes = scsi_bufflen(SCpnt);
		break;
	case NO_SENSE:
		/* This indicates a false check condition, so ignore it.  An
		 * unknown amount of data was transferred so treat it as an
		 * error.
		 */
		SCpnt->result = 0;
		memset(SCpnt->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
		break;
	case ABORTED_COMMAND:
		if (sshdr.asc == 0x10)  /* DIF: Target detected corruption */
			good_bytes = sd_completed_bytes(SCpnt);
		break;
	case ILLEGAL_REQUEST:
		if (sshdr.asc == 0x10)  /* DIX: Host detected corruption */
			good_bytes = sd_completed_bytes(SCpnt);
		/* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
		if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
			switch (op) {
			case UNMAP:
				sd_config_discard(sdkp, SD_LBP_DISABLE);
				break;
			case WRITE_SAME_16:
			case WRITE_SAME:
				if (unmap)
					sd_config_discard(sdkp, SD_LBP_DISABLE);
				else {
					sdkp->device->no_write_same = 1;
					sd_config_write_same(sdkp);

					good_bytes = 0;
					req->__data_len = blk_rq_bytes(req);
					req->rq_flags |= RQF_QUIET;
				}
			}
		}
		break;
	default:
		break;
	}

 out:
	if (sd_is_zoned(sdkp))
		sd_zbc_complete(SCpnt, good_bytes, &sshdr);

	SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt,
					   "sd_done: completed %d of %d bytes\n",
					   good_bytes, scsi_bufflen(SCpnt)));

	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt))
		sd_dif_complete(SCpnt, good_bytes);

	return good_bytes;
}

/*
 * spinup disk - called only in sd_revalidate_disk()
 */
static void
sd_spinup_disk(struct scsi_disk *sdkp)
{
	unsigned char cmd[10];
	unsigned long spintime_expire = 0;
	int retries, spintime;
	unsigned int the_result;
	struct scsi_sense_hdr sshdr;
	int sense_valid = 0;

	spintime = 0;

	/* Spin up drives, as required.  Only do this at boot time */
	/* Spinup needs to be done for module loads too. */
	do {
		retries = 0;

		do {
			cmd[0] = TEST_UNIT_READY;
			memset((void *) &cmd[1], 0, 9);

			the_result = scsi_execute_req(sdkp->device, cmd,
						      DMA_NONE, NULL, 0,
						      &sshdr, SD_TIMEOUT,
						      SD_MAX_RETRIES, NULL);

			/*
			 * If the drive has indicated to us that it
			 * doesn't have any media in it, don't bother
			 * with any more polling.
			 */
			if (media_not_present(sdkp, &sshdr))
				return;

			if (the_result)
				sense_valid = scsi_sense_valid(&sshdr);
			retries++;
		} while (retries < 3 && 
			 (!scsi_status_is_good(the_result) ||
			  ((driver_byte(the_result) & DRIVER_SENSE) &&
			  sense_valid && sshdr.sense_key == UNIT_ATTENTION)));

		if ((driver_byte(the_result) & DRIVER_SENSE) == 0) {
			/* no sense, TUR either succeeded or failed
			 * with a status error */
			if(!spintime && !scsi_status_is_good(the_result)) {
				sd_print_result(sdkp, "Test Unit Ready failed",
						the_result);
			}
			break;
		}

		/*
		 * The device does not want the automatic start to be issued.
		 */
		if (sdkp->device->no_start_on_add)
			break;

		if (sense_valid && sshdr.sense_key == NOT_READY) {
			if (sshdr.asc == 4 && sshdr.ascq == 3)
				break;	/* manual intervention required */
			if (sshdr.asc == 4 && sshdr.ascq == 0xb)
				break;	/* standby */
			if (sshdr.asc == 4 && sshdr.ascq == 0xc)
				break;	/* unavailable */
			/*
			 * Issue command to spin up drive when not ready
			 */
			if (!spintime) {
				sd_printk(KERN_NOTICE, sdkp, "Spinning up disk...");
				cmd[0] = START_STOP;
				cmd[1] = 1;	/* Return immediately */
				memset((void *) &cmd[2], 0, 8);
				cmd[4] = 1;	/* Start spin cycle */
				if (sdkp->device->start_stop_pwr_cond)
					cmd[4] |= 1 << 4;
				scsi_execute_req(sdkp->device, cmd, DMA_NONE,
						 NULL, 0, &sshdr,
						 SD_TIMEOUT, SD_MAX_RETRIES,
						 NULL);
				spintime_expire = jiffies + 100 * HZ;
				spintime = 1;
			}
			/* Wait 1 second for next try */
			msleep(1000);
			printk(".");

		/*
		 * Wait for USB flash devices with slow firmware.
		 * Yes, this sense key/ASC combination shouldn't
		 * occur here.  It's characteristic of these devices.
		 */
		} else if (sense_valid &&
				sshdr.sense_key == UNIT_ATTENTION &&
				sshdr.asc == 0x28) {
			if (!spintime) {
				spintime_expire = jiffies + 5 * HZ;
				spintime = 1;
			}
			/* Wait 1 second for next try */
			msleep(1000);
		} else {
			/* we don't understand the sense code, so it's
			 * probably pointless to loop */
			if(!spintime) {
				sd_printk(KERN_NOTICE, sdkp, "Unit Not Ready\n");
				sd_print_sense_hdr(sdkp, &sshdr);
			}
			break;
		}
				
	} while (spintime && time_before_eq(jiffies, spintime_expire));

	if (spintime) {
		if (scsi_status_is_good(the_result))
			printk("ready\n");
		else
			printk("not responding...\n");
	}
}

/*
 * Determine whether disk supports Data Integrity Field.
 */
static int sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer)
{
	struct scsi_device *sdp = sdkp->device;
	u8 type;
	int ret = 0;

	if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0)
		return ret;

	type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */

	if (type > T10_PI_TYPE3_PROTECTION)
		ret = -ENODEV;
	else if (scsi_host_dif_capable(sdp->host, type))
		ret = 1;

	if (sdkp->first_scan || type != sdkp->protection_type)
		switch (ret) {
		case -ENODEV:
			sd_printk(KERN_ERR, sdkp, "formatted with unsupported" \
				  " protection type %u. Disabling disk!\n",
				  type);
			break;
		case 1:
			sd_printk(KERN_NOTICE, sdkp,
				  "Enabling DIF Type %u protection\n", type);
			break;
		case 0:
			sd_printk(KERN_NOTICE, sdkp,
				  "Disabling DIF Type %u protection\n", type);
			break;
		}

	sdkp->protection_type = type;

	return ret;
}

static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp,
			struct scsi_sense_hdr *sshdr, int sense_valid,
			int the_result)
{
	if (driver_byte(the_result) & DRIVER_SENSE)
		sd_print_sense_hdr(sdkp, sshdr);
	else
		sd_printk(KERN_NOTICE, sdkp, "Sense not available.\n");

	/*
	 * Set dirty bit for removable devices if not ready -
	 * sometimes drives will not report this properly.
	 */
	if (sdp->removable &&
	    sense_valid && sshdr->sense_key == NOT_READY)
		set_media_not_present(sdkp);

	/*
	 * We used to set media_present to 0 here to indicate no media
	 * in the drive, but some drives fail read capacity even with
	 * media present, so we can't do that.
	 */
	sdkp->capacity = 0; /* unknown mapped to zero - as usual */
}

#define RC16_LEN 32
#if RC16_LEN > SD_BUF_SIZE
#error RC16_LEN must not be more than SD_BUF_SIZE
#endif

#define READ_CAPACITY_RETRIES_ON_RESET	10

static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
						unsigned char *buffer)
{
	unsigned char cmd[16];
	struct scsi_sense_hdr sshdr;
	int sense_valid = 0;
	int the_result;
	int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET;
	unsigned int alignment;
	unsigned long long lba;
	unsigned sector_size;

	if (sdp->no_read_capacity_16)
		return -EINVAL;

	do {
		memset(cmd, 0, 16);
		cmd[0] = SERVICE_ACTION_IN_16;
		cmd[1] = SAI_READ_CAPACITY_16;
		cmd[13] = RC16_LEN;
		memset(buffer, 0, RC16_LEN);

		the_result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE,
					buffer, RC16_LEN, &sshdr,
					SD_TIMEOUT, SD_MAX_RETRIES, NULL);

		if (media_not_present(sdkp, &sshdr))
			return -ENODEV;

		if (the_result) {
			sense_valid = scsi_sense_valid(&sshdr);
			if (sense_valid &&
			    sshdr.sense_key == ILLEGAL_REQUEST &&
			    (sshdr.asc == 0x20 || sshdr.asc == 0x24) &&
			    sshdr.ascq == 0x00)
				/* Invalid Command Operation Code or
				 * Invalid Field in CDB, just retry
				 * silently with RC10 */
				return -EINVAL;
			if (sense_valid &&
			    sshdr.sense_key == UNIT_ATTENTION &&
			    sshdr.asc == 0x29 && sshdr.ascq == 0x00)
				/* Device reset might occur several times,
				 * give it one more chance */
				if (--reset_retries > 0)
					continue;
		}
		retries--;

	} while (the_result && retries);

	if (the_result) {
		sd_print_result(sdkp, "Read Capacity(16) failed", the_result);
		read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result);
		return -EINVAL;
	}

	sector_size = get_unaligned_be32(&buffer[8]);
	lba = get_unaligned_be64(&buffer[0]);

	if (sd_read_protection_type(sdkp, buffer) < 0) {
		sdkp->capacity = 0;
		return -ENODEV;
	}

	if ((sizeof(sdkp->capacity) == 4) && (lba >= 0xffffffffULL)) {
		sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
			"kernel compiled with support for large block "
			"devices.\n");
		sdkp->capacity = 0;
		return -EOVERFLOW;
	}

	/* Logical blocks per physical block exponent */
	sdkp->physical_block_size = (1 << (buffer[13] & 0xf)) * sector_size;

	/* RC basis */
	sdkp->rc_basis = (buffer[12] >> 4) & 0x3;

	/* Lowest aligned logical block */
	alignment = ((buffer[14] & 0x3f) << 8 | buffer[15]) * sector_size;
	blk_queue_alignment_offset(sdp->request_queue, alignment);
	if (alignment && sdkp->first_scan)
		sd_printk(KERN_NOTICE, sdkp,
			  "physical block alignment offset: %u\n", alignment);

	if (buffer[14] & 0x80) { /* LBPME */
		sdkp->lbpme = 1;

		if (buffer[14] & 0x40) /* LBPRZ */
			sdkp->lbprz = 1;

		sd_config_discard(sdkp, SD_LBP_WS16);
	}

	sdkp->capacity = lba + 1;
	return sector_size;
}

static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp,
						unsigned char *buffer)
{
	unsigned char cmd[16];
	struct scsi_sense_hdr sshdr;
	int sense_valid = 0;
	int the_result;
	int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET;
	sector_t lba;
	unsigned sector_size;

	do {
		cmd[0] = READ_CAPACITY;
		memset(&cmd[1], 0, 9);
		memset(buffer, 0, 8);

		the_result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE,
					buffer, 8, &sshdr,
					SD_TIMEOUT, SD_MAX_RETRIES, NULL);

		if (media_not_present(sdkp, &sshdr))
			return -ENODEV;

		if (the_result) {
			sense_valid = scsi_sense_valid(&sshdr);
			if (sense_valid &&
			    sshdr.sense_key == UNIT_ATTENTION &&
			    sshdr.asc == 0x29 && sshdr.ascq == 0x00)
				/* Device reset might occur several times,
				 * give it one more chance */
				if (--reset_retries > 0)
					continue;
		}
		retries--;

	} while (the_result && retries);

	if (the_result) {
		sd_print_result(sdkp, "Read Capacity(10) failed", the_result);
		read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result);
		return -EINVAL;
	}

	sector_size = get_unaligned_be32(&buffer[4]);
	lba = get_unaligned_be32(&buffer[0]);

	if (sdp->no_read_capacity_16 && (lba == 0xffffffff)) {
		/* Some buggy (usb cardreader) devices return an lba of
		   0xffffffff when the want to report a size of 0 (with
		   which they really mean no media is present) */
		sdkp->capacity = 0;
		sdkp->physical_block_size = sector_size;
		return sector_size;
	}

	if ((sizeof(sdkp->capacity) == 4) && (lba == 0xffffffff)) {
		sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
			"kernel compiled with support for large block "
			"devices.\n");
		sdkp->capacity = 0;
		return -EOVERFLOW;
	}

	sdkp->capacity = lba + 1;
	sdkp->physical_block_size = sector_size;
	return sector_size;
}

static int sd_try_rc16_first(struct scsi_device *sdp)
{
	if (sdp->host->max_cmd_len < 16)
		return 0;
	if (sdp->try_rc_10_first)
		return 0;
	if (sdp->scsi_level > SCSI_SPC_2)
		return 1;
	if (scsi_device_protection(sdp))
		return 1;
	return 0;
}

/*
 * read disk capacity
 */
static void
sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer)
{
	int sector_size;
	struct scsi_device *sdp = sdkp->device;

	if (sd_try_rc16_first(sdp)) {
		sector_size = read_capacity_16(sdkp, sdp, buffer);
		if (sector_size == -EOVERFLOW)
			goto got_data;
		if (sector_size == -ENODEV)
			return;
		if (sector_size < 0)
			sector_size = read_capacity_10(sdkp, sdp, buffer);
		if (sector_size < 0)
			return;
	} else {
		sector_size = read_capacity_10(sdkp, sdp, buffer);
		if (sector_size == -EOVERFLOW)
			goto got_data;
		if (sector_size < 0)
			return;
		if ((sizeof(sdkp->capacity) > 4) &&
		    (sdkp->capacity > 0xffffffffULL)) {
			int old_sector_size = sector_size;
			sd_printk(KERN_NOTICE, sdkp, "Very big device. "
					"Trying to use READ CAPACITY(16).\n");
			sector_size = read_capacity_16(sdkp, sdp, buffer);
			if (sector_size < 0) {
				sd_printk(KERN_NOTICE, sdkp,
					"Using 0xffffffff as device size\n");
				sdkp->capacity = 1 + (sector_t) 0xffffffff;
				sector_size = old_sector_size;
				goto got_data;
			}
		}
	}

	/* Some devices are known to return the total number of blocks,
	 * not the highest block number.  Some devices have versions
	 * which do this and others which do not.  Some devices we might
	 * suspect of doing this but we don't know for certain.
	 *
	 * If we know the reported capacity is wrong, decrement it.  If
	 * we can only guess, then assume the number of blocks is even
	 * (usually true but not always) and err on the side of lowering
	 * the capacity.
	 */
	if (sdp->fix_capacity ||
	    (sdp->guess_capacity && (sdkp->capacity & 0x01))) {
		sd_printk(KERN_INFO, sdkp, "Adjusting the sector count "
				"from its reported value: %llu\n",
				(unsigned long long) sdkp->capacity);
		--sdkp->capacity;
	}

got_data:
	if (sector_size == 0) {
		sector_size = 512;
		sd_printk(KERN_NOTICE, sdkp, "Sector size 0 reported, "
			  "assuming 512.\n");
	}

	if (sector_size != 512 &&
	    sector_size != 1024 &&
	    sector_size != 2048 &&
	    sector_size != 4096) {
		sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n",
			  sector_size);
		/*
		 * The user might want to re-format the drive with
		 * a supported sectorsize.  Once this happens, it
		 * would be relatively trivial to set the thing up.
		 * For this reason, we leave the thing in the table.
		 */
		sdkp->capacity = 0;
		/*
		 * set a bogus sector size so the normal read/write
		 * logic in the block layer will eventually refuse any
		 * request on this device without tripping over power
		 * of two sector size assumptions
		 */
		sector_size = 512;
	}
	blk_queue_logical_block_size(sdp->request_queue, sector_size);
	blk_queue_physical_block_size(sdp->request_queue,
				      sdkp->physical_block_size);
	sdkp->device->sector_size = sector_size;

	if (sdkp->capacity > 0xffffffff)
		sdp->use_16_for_rw = 1;

}

/*
 * Print disk capacity
 */
static void
sd_print_capacity(struct scsi_disk *sdkp,
		  sector_t old_capacity)
{
	int sector_size = sdkp->device->sector_size;
	char cap_str_2[10], cap_str_10[10];

	string_get_size(sdkp->capacity, sector_size,
			STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
	string_get_size(sdkp->capacity, sector_size,
			STRING_UNITS_10, cap_str_10,
			sizeof(cap_str_10));

	if (sdkp->first_scan || old_capacity != sdkp->capacity) {
		sd_printk(KERN_NOTICE, sdkp,
			  "%llu %d-byte logical blocks: (%s/%s)\n",
			  (unsigned long long)sdkp->capacity,
			  sector_size, cap_str_10, cap_str_2);

		if (sdkp->physical_block_size != sector_size)
			sd_printk(KERN_NOTICE, sdkp,
				  "%u-byte physical blocks\n",
				  sdkp->physical_block_size);

		sd_zbc_print_zones(sdkp);
	}
}

/* called with buffer of length 512 */
static inline int
sd_do_mode_sense(struct scsi_device *sdp, int dbd, int modepage,
		 unsigned char *buffer, int len, struct scsi_mode_data *data,
		 struct scsi_sense_hdr *sshdr)
{
	return scsi_mode_sense(sdp, dbd, modepage, buffer, len,
			       SD_TIMEOUT, SD_MAX_RETRIES, data,
			       sshdr);
}

/*
 * read write protect setting, if possible - called only in sd_revalidate_disk()
 * called with buffer of length SD_BUF_SIZE
 */
static void
sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer)
{
	int res;
	struct scsi_device *sdp = sdkp->device;
	struct scsi_mode_data data;
	int old_wp = sdkp->write_prot;

	set_disk_ro(sdkp->disk, 0);
	if (sdp->skip_ms_page_3f) {
		sd_first_printk(KERN_NOTICE, sdkp, "Assuming Write Enabled\n");
		return;
	}

	if (sdp->use_192_bytes_for_3f) {
		res = sd_do_mode_sense(sdp, 0, 0x3F, buffer, 192, &data, NULL);
	} else {
		/*
		 * First attempt: ask for all pages (0x3F), but only 4 bytes.
		 * We have to start carefully: some devices hang if we ask
		 * for more than is available.
		 */
		res = sd_do_mode_sense(sdp, 0, 0x3F, buffer, 4, &data, NULL);

		/*
		 * Second attempt: ask for page 0 When only page 0 is
		 * implemented, a request for page 3F may return Sense Key
		 * 5: Illegal Request, Sense Code 24: Invalid field in
		 * CDB.
		 */
		if (!scsi_status_is_good(res))
			res = sd_do_mode_sense(sdp, 0, 0, buffer, 4, &data, NULL);

		/*
		 * Third attempt: ask 255 bytes, as we did earlier.
		 */
		if (!scsi_status_is_good(res))
			res = sd_do_mode_sense(sdp, 0, 0x3F, buffer, 255,
					       &data, NULL);
	}

	if (!scsi_status_is_good(res)) {
		sd_first_printk(KERN_WARNING, sdkp,
			  "Test WP failed, assume Write Enabled\n");
	} else {
		sdkp->write_prot = ((data.device_specific & 0x80) != 0);
		set_disk_ro(sdkp->disk, sdkp->write_prot);
		if (sdkp->first_scan || old_wp != sdkp->write_prot) {
			sd_printk(KERN_NOTICE, sdkp, "Write Protect is %s\n",
				  sdkp->write_prot ? "on" : "off");
			sd_printk(KERN_DEBUG, sdkp, "Mode Sense: %4ph\n", buffer);
		}
	}
}

/*
 * sd_read_cache_type - called only from sd_revalidate_disk()
 * called with buffer of length SD_BUF_SIZE
 */
static void
sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer)
{
	int len = 0, res;
	struct scsi_device *sdp = sdkp->device;

	int dbd;
	int modepage;
	int first_len;
	struct scsi_mode_data data;
	struct scsi_sense_hdr sshdr;
	int old_wce = sdkp->WCE;
	int old_rcd = sdkp->RCD;
	int old_dpofua = sdkp->DPOFUA;


	if (sdkp->cache_override)
		return;

	first_len = 4;
	if (sdp->skip_ms_page_8) {
		if (sdp->type == TYPE_RBC)
			goto defaults;
		else {
			if (sdp->skip_ms_page_3f)
				goto defaults;
			modepage = 0x3F;
			if (sdp->use_192_bytes_for_3f)
				first_len = 192;
			dbd = 0;
		}
	} else if (sdp->type == TYPE_RBC) {
		modepage = 6;
		dbd = 8;
	} else {
		modepage = 8;
		dbd = 0;
	}

	/* cautiously ask */
	res = sd_do_mode_sense(sdp, dbd, modepage, buffer, first_len,
			&data, &sshdr);

	if (!scsi_status_is_good(res))
		goto bad_sense;

	if (!data.header_length) {
		modepage = 6;
		first_len = 0;
		sd_first_printk(KERN_ERR, sdkp,
				"Missing header in MODE_SENSE response\n");
	}

	/* that went OK, now ask for the proper length */
	len = data.length;

	/*
	 * We're only interested in the first three bytes, actually.
	 * But the data cache page is defined for the first 20.
	 */
	if (len < 3)
		goto bad_sense;
	else if (len > SD_BUF_SIZE) {
		sd_first_printk(KERN_NOTICE, sdkp, "Truncating mode parameter "
			  "data from %d to %d bytes\n", len, SD_BUF_SIZE);
		len = SD_BUF_SIZE;
	}
	if (modepage == 0x3F && sdp->use_192_bytes_for_3f)
		len = 192;

	/* Get the data */
	if (len > first_len)
		res = sd_do_mode_sense(sdp, dbd, modepage, buffer, len,
				&data, &sshdr);

	if (scsi_status_is_good(res)) {
		int offset = data.header_length + data.block_descriptor_length;

		while (offset < len) {
			u8 page_code = buffer[offset] & 0x3F;
			u8 spf       = buffer[offset] & 0x40;

			if (page_code == 8 || page_code == 6) {
				/* We're interested only in the first 3 bytes.
				 */
				if (len - offset <= 2) {
					sd_first_printk(KERN_ERR, sdkp,
						"Incomplete mode parameter "
							"data\n");
					goto defaults;
				} else {
					modepage = page_code;
					goto Page_found;
				}
			} else {
				/* Go to the next page */
				if (spf && len - offset > 3)
					offset += 4 + (buffer[offset+2] << 8) +
						buffer[offset+3];
				else if (!spf && len - offset > 1)
					offset += 2 + buffer[offset+1];
				else {
					sd_first_printk(KERN_ERR, sdkp,
							"Incomplete mode "
							"parameter data\n");
					goto defaults;
				}
			}
		}

		sd_first_printk(KERN_ERR, sdkp, "No Caching mode page found\n");
		goto defaults;

	Page_found:
		if (modepage == 8) {
			sdkp->WCE = ((buffer[offset + 2] & 0x04) != 0);
			sdkp->RCD = ((buffer[offset + 2] & 0x01) != 0);
		} else {
			sdkp->WCE = ((buffer[offset + 2] & 0x01) == 0);
			sdkp->RCD = 0;
		}

		sdkp->DPOFUA = (data.device_specific & 0x10) != 0;
		if (sdp->broken_fua) {
			sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n");
			sdkp->DPOFUA = 0;
		} else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) {
			sd_first_printk(KERN_NOTICE, sdkp,
				  "Uses READ/WRITE(6), disabling FUA\n");
			sdkp->DPOFUA = 0;
		}

		/* No cache flush allowed for write protected devices */
		if (sdkp->WCE && sdkp->write_prot)
			sdkp->WCE = 0;

		if (sdkp->first_scan || old_wce != sdkp->WCE ||
		    old_rcd != sdkp->RCD || old_dpofua != sdkp->DPOFUA)
			sd_printk(KERN_NOTICE, sdkp,
				  "Write cache: %s, read cache: %s, %s\n",
				  sdkp->WCE ? "enabled" : "disabled",
				  sdkp->RCD ? "disabled" : "enabled",
				  sdkp->DPOFUA ? "supports DPO and FUA"
				  : "doesn't support DPO or FUA");

		return;
	}

bad_sense:
	if (scsi_sense_valid(&sshdr) &&
	    sshdr.sense_key == ILLEGAL_REQUEST &&
	    sshdr.asc == 0x24 && sshdr.ascq == 0x0)
		/* Invalid field in CDB */
		sd_first_printk(KERN_NOTICE, sdkp, "Cache data unavailable\n");
	else
		sd_first_printk(KERN_ERR, sdkp,
				"Asking for cache data failed\n");

defaults:
	if (sdp->wce_default_on) {
		sd_first_printk(KERN_NOTICE, sdkp,
				"Assuming drive cache: write back\n");
		sdkp->WCE = 1;
	} else {
		sd_first_printk(KERN_ERR, sdkp,
				"Assuming drive cache: write through\n");
		sdkp->WCE = 0;
	}
	sdkp->RCD = 0;
	sdkp->DPOFUA = 0;
}

/*
 * The ATO bit indicates whether the DIF application tag is available
 * for use by the operating system.
 */
static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer)
{
	int res, offset;
	struct scsi_device *sdp = sdkp->device;
	struct scsi_mode_data data;
	struct scsi_sense_hdr sshdr;

	if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
		return;

	if (sdkp->protection_type == 0)
		return;

	res = scsi_mode_sense(sdp, 1, 0x0a, buffer, 36, SD_TIMEOUT,
			      SD_MAX_RETRIES, &data, &sshdr);

	if (!scsi_status_is_good(res) || !data.header_length ||
	    data.length < 6) {
		sd_first_printk(KERN_WARNING, sdkp,
			  "getting Control mode page failed, assume no ATO\n");

		if (scsi_sense_valid(&sshdr))
			sd_print_sense_hdr(sdkp, &sshdr);

		return;
	}

	offset = data.header_length + data.block_descriptor_length;

	if ((buffer[offset] & 0x3f) != 0x0a) {
		sd_first_printk(KERN_ERR, sdkp, "ATO Got wrong page\n");
		return;
	}

	if ((buffer[offset + 5] & 0x80) == 0)
		return;

	sdkp->ATO = 1;

	return;
}

/**
 * sd_read_block_limits - Query disk device for preferred I/O sizes.
 * @disk: disk to query
 */
static void sd_read_block_limits(struct scsi_disk *sdkp)
{
	unsigned int sector_sz = sdkp->device->sector_size;
	const int vpd_len = 64;
	unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL);

	if (!buffer ||
	    /* Block Limits VPD */
	    scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len))
		goto out;

	blk_queue_io_min(sdkp->disk->queue,
			 get_unaligned_be16(&buffer[6]) * sector_sz);

	sdkp->max_xfer_blocks = get_unaligned_be32(&buffer[8]);
	sdkp->opt_xfer_blocks = get_unaligned_be32(&buffer[12]);

	if (buffer[3] == 0x3c) {
		unsigned int lba_count, desc_count;

		sdkp->max_ws_blocks = (u32)get_unaligned_be64(&buffer[36]);

		if (!sdkp->lbpme)
			goto out;

		lba_count = get_unaligned_be32(&buffer[20]);
		desc_count = get_unaligned_be32(&buffer[24]);

		if (lba_count && desc_count)
			sdkp->max_unmap_blocks = lba_count;

		sdkp->unmap_granularity = get_unaligned_be32(&buffer[28]);

		if (buffer[32] & 0x80)
			sdkp->unmap_alignment =
				get_unaligned_be32(&buffer[32]) & ~(1 << 31);

		if (!sdkp->lbpvpd) { /* LBP VPD page not provided */

			if (sdkp->max_unmap_blocks)
				sd_config_discard(sdkp, SD_LBP_UNMAP);
			else
				sd_config_discard(sdkp, SD_LBP_WS16);

		} else {	/* LBP VPD page tells us what to use */
			if (sdkp->lbpu && sdkp->max_unmap_blocks && !sdkp->lbprz)
				sd_config_discard(sdkp, SD_LBP_UNMAP);
			else if (sdkp->lbpws)
				sd_config_discard(sdkp, SD_LBP_WS16);
			else if (sdkp->lbpws10)
				sd_config_discard(sdkp, SD_LBP_WS10);
			else if (sdkp->lbpu && sdkp->max_unmap_blocks)
				sd_config_discard(sdkp, SD_LBP_UNMAP);
			else
				sd_config_discard(sdkp, SD_LBP_DISABLE);
		}
	}

 out:
	kfree(buffer);
}

/**
 * sd_read_block_characteristics - Query block dev. characteristics
 * @disk: disk to query
 */
static void sd_read_block_characteristics(struct scsi_disk *sdkp)
{
	struct request_queue *q = sdkp->disk->queue;
	unsigned char *buffer;
	u16 rot;
	const int vpd_len = 64;

	buffer = kmalloc(vpd_len, GFP_KERNEL);

	if (!buffer ||
	    /* Block Device Characteristics VPD */
	    scsi_get_vpd_page(sdkp->device, 0xb1, buffer, vpd_len))
		goto out;

	rot = get_unaligned_be16(&buffer[4]);

	if (rot == 1) {
		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q);
	}

	sdkp->zoned = (buffer[8] >> 4) & 3;
	if (sdkp->zoned == 1)
		q->limits.zoned = BLK_ZONED_HA;
	else if (sdkp->device->type == TYPE_ZBC)
		q->limits.zoned = BLK_ZONED_HM;
	else
		q->limits.zoned = BLK_ZONED_NONE;
	if (blk_queue_is_zoned(q) && sdkp->first_scan)
		sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n",
		      q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware");

 out:
	kfree(buffer);
}

/**
 * sd_read_block_provisioning - Query provisioning VPD page
 * @disk: disk to query
 */
static void sd_read_block_provisioning(struct scsi_disk *sdkp)
{
	unsigned char *buffer;
	const int vpd_len = 8;

	if (sdkp->lbpme == 0)
		return;

	buffer = kmalloc(vpd_len, GFP_KERNEL);

	if (!buffer || scsi_get_vpd_page(sdkp->device, 0xb2, buffer, vpd_len))
		goto out;

	sdkp->lbpvpd	= 1;
	sdkp->lbpu	= (buffer[5] >> 7) & 1;	/* UNMAP */
	sdkp->lbpws	= (buffer[5] >> 6) & 1;	/* WRITE SAME(16) with UNMAP */
	sdkp->lbpws10	= (buffer[5] >> 5) & 1;	/* WRITE SAME(10) with UNMAP */

 out:
	kfree(buffer);
}

static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer)
{
	struct scsi_device *sdev = sdkp->device;

	if (sdev->host->no_write_same) {
		sdev->no_write_same = 1;

		return;
	}

	if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY) < 0) {
		/* too large values might cause issues with arcmsr */
		int vpd_buf_len = 64;

		sdev->no_report_opcodes = 1;

		/* Disable WRITE SAME if REPORT SUPPORTED OPERATION
		 * CODES is unsupported and the device has an ATA
		 * Information VPD page (SAT).
		 */
		if (!scsi_get_vpd_page(sdev, 0x89, buffer, vpd_buf_len))
			sdev->no_write_same = 1;
	}

	if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME_16) == 1)
		sdkp->ws16 = 1;

	if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME) == 1)
		sdkp->ws10 = 1;
}

/**
 *	sd_revalidate_disk - called the first time a new disk is seen,
 *	performs disk spin up, read_capacity, etc.
 *	@disk: struct gendisk we care about
 **/
static int sd_revalidate_disk(struct gendisk *disk)
{
	struct scsi_disk *sdkp = scsi_disk(disk);
	struct scsi_device *sdp = sdkp->device;
	struct request_queue *q = sdkp->disk->queue;
	sector_t old_capacity = sdkp->capacity;
	unsigned char *buffer;
	unsigned int dev_max, rw_max;

	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
				      "sd_revalidate_disk\n"));

	/*
	 * If the device is offline, don't try and read capacity or any
	 * of the other niceties.
	 */
	if (!scsi_device_online(sdp))
		goto out;

	buffer = kmalloc(SD_BUF_SIZE, GFP_KERNEL);
	if (!buffer) {
		sd_printk(KERN_WARNING, sdkp, "sd_revalidate_disk: Memory "
			  "allocation failure.\n");
		goto out;
	}

	sd_spinup_disk(sdkp);

	/*
	 * Without media there is no reason to ask; moreover, some devices
	 * react badly if we do.
	 */
	if (sdkp->media_present) {
		sd_read_capacity(sdkp, buffer);

		if (scsi_device_supports_vpd(sdp)) {
			sd_read_block_provisioning(sdkp);
			sd_read_block_limits(sdkp);
			sd_read_block_characteristics(sdkp);
			sd_zbc_read_zones(sdkp, buffer);
		}

		sd_print_capacity(sdkp, old_capacity);

		sd_read_write_protect_flag(sdkp, buffer);
		sd_read_cache_type(sdkp, buffer);
		sd_read_app_tag_own(sdkp, buffer);
		sd_read_write_same(sdkp, buffer);
	}

	sdkp->first_scan = 0;

	/*
	 * We now have all cache related info, determine how we deal
	 * with flush requests.
	 */
	sd_set_flush_flag(sdkp);

	/* Initial block count limit based on CDB TRANSFER LENGTH field size. */
	dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS;

	/* Some devices report a maximum block count for READ/WRITE requests. */
	dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks);
	q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max);

	/*
	 * Use the device's preferred I/O size for reads and writes
	 * unless the reported value is unreasonably small, large, or
	 * garbage.
	 */
	if (sdkp->opt_xfer_blocks &&
	    sdkp->opt_xfer_blocks <= dev_max &&
	    sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS &&
	    logical_to_bytes(sdp, sdkp->opt_xfer_blocks) >= PAGE_SIZE) {
		q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
		rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
	} else
		rw_max = BLK_DEF_MAX_SECTORS;

	/* Combine with controller limits */
	q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));

	set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity));
	sd_config_write_same(sdkp);
	kfree(buffer);

 out:
	return 0;
}

/**
 *	sd_unlock_native_capacity - unlock native capacity
 *	@disk: struct gendisk to set capacity for
 *
 *	Block layer calls this function if it detects that partitions
 *	on @disk reach beyond the end of the device.  If the SCSI host
 *	implements ->unlock_native_capacity() method, it's invoked to
 *	give it a chance to adjust the device capacity.
 *
 *	CONTEXT:
 *	Defined by block layer.  Might sleep.
 */
static void sd_unlock_native_capacity(struct gendisk *disk)
{
	struct scsi_device *sdev = scsi_disk(disk)->device;

	if (sdev->host->hostt->unlock_native_capacity)
		sdev->host->hostt->unlock_native_capacity(sdev);
}

/**
 *	sd_format_disk_name - format disk name
 *	@prefix: name prefix - ie. "sd" for SCSI disks
 *	@index: index of the disk to format name for
 *	@buf: output buffer
 *	@buflen: length of the output buffer
 *
 *	SCSI disk names starts at sda.  The 26th device is sdz and the
 *	27th is sdaa.  The last one for two lettered suffix is sdzz
 *	which is followed by sdaaa.
 *
 *	This is basically 26 base counting with one extra 'nil' entry
 *	at the beginning from the second digit on and can be
 *	determined using similar method as 26 base conversion with the
 *	index shifted -1 after each digit is computed.
 *
 *	CONTEXT:
 *	Don't care.
 *
 *	RETURNS:
 *	0 on success, -errno on failure.
 */
static int sd_format_disk_name(char *prefix, int index, char *buf, int buflen)
{
	const int base = 'z' - 'a' + 1;
	char *begin = buf + strlen(prefix);
	char *end = buf + buflen;
	char *p;
	int unit;

	p = end - 1;
	*p = '\0';
	unit = base;
	do {
		if (p == begin)
			return -EINVAL;
		*--p = 'a' + (index % unit);
		index = (index / unit) - 1;
	} while (index >= 0);

	memmove(begin, p, end - p);
	memcpy(buf, prefix, strlen(prefix));

	return 0;
}

/*
 * The asynchronous part of sd_probe
 */
static void sd_probe_async(void *data, async_cookie_t cookie)
{
	struct scsi_disk *sdkp = data;
	struct scsi_device *sdp;
	struct gendisk *gd;
	u32 index;
	struct device *dev;

	sdp = sdkp->device;
	gd = sdkp->disk;
	index = sdkp->index;
	dev = &sdp->sdev_gendev;

	gd->major = sd_major((index & 0xf0) >> 4);
	gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00);
	gd->minors = SD_MINORS;

	gd->fops = &sd_fops;
	gd->private_data = &sdkp->driver;
	gd->queue = sdkp->device->request_queue;

	/* defaults, until the device tells us otherwise */
	sdp->sector_size = 512;
	sdkp->capacity = 0;
	sdkp->media_present = 1;
	sdkp->write_prot = 0;
	sdkp->cache_override = 0;
	sdkp->WCE = 0;
	sdkp->RCD = 0;
	sdkp->ATO = 0;
	sdkp->first_scan = 1;
	sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS;

	sd_revalidate_disk(gd);

	gd->flags = GENHD_FL_EXT_DEVT;
	if (sdp->removable) {
		gd->flags |= GENHD_FL_REMOVABLE;
		gd->events |= DISK_EVENT_MEDIA_CHANGE;
	}

	blk_pm_runtime_init(sdp->request_queue, dev);
	device_add_disk(dev, gd);
	if (sdkp->capacity)
		sd_dif_config_host(sdkp);

	sd_revalidate_disk(gd);

	sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n",
		  sdp->removable ? "removable " : "");
	scsi_autopm_put_device(sdp);
	put_device(&sdkp->dev);
}

/**
 *	sd_probe - called during driver initialization and whenever a
 *	new scsi device is attached to the system. It is called once
 *	for each scsi device (not just disks) present.
 *	@dev: pointer to device object
 *
 *	Returns 0 if successful (or not interested in this scsi device 
 *	(e.g. scanner)); 1 when there is an error.
 *
 *	Note: this function is invoked from the scsi mid-level.
 *	This function sets up the mapping between a given 
 *	<host,channel,id,lun> (found in sdp) and new device name 
 *	(e.g. /dev/sda). More precisely it is the block device major 
 *	and minor number that is chosen here.
 *
 *	Assume sd_probe is not re-entrant (for time being)
 *	Also think about sd_probe() and sd_remove() running coincidentally.
 **/
static int sd_probe(struct device *dev)
{
	struct scsi_device *sdp = to_scsi_device(dev);
	struct scsi_disk *sdkp;
	struct gendisk *gd;
	int index;
	int error;

	scsi_autopm_get_device(sdp);
	error = -ENODEV;
	if (sdp->type != TYPE_DISK &&
	    sdp->type != TYPE_ZBC &&
	    sdp->type != TYPE_MOD &&
	    sdp->type != TYPE_RBC)
		goto out;

#ifndef CONFIG_BLK_DEV_ZONED
	if (sdp->type == TYPE_ZBC)
		goto out;
#endif
	SCSI_LOG_HLQUEUE(3, sdev_printk(KERN_INFO, sdp,
					"sd_probe\n"));

	error = -ENOMEM;
	sdkp = kzalloc(sizeof(*sdkp), GFP_KERNEL);
	if (!sdkp)
		goto out;

	gd = alloc_disk(SD_MINORS);
	if (!gd)
		goto out_free;

	do {
		if (!ida_pre_get(&sd_index_ida, GFP_KERNEL))
			goto out_put;

		spin_lock(&sd_index_lock);
		error = ida_get_new(&sd_index_ida, &index);
		spin_unlock(&sd_index_lock);
	} while (error == -EAGAIN);

	if (error) {
		sdev_printk(KERN_WARNING, sdp, "sd_probe: memory exhausted.\n");
		goto out_put;
	}

	error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN);
	if (error) {
		sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n");
		goto out_free_index;
	}

	sdkp->device = sdp;
	sdkp->driver = &sd_template;
	sdkp->disk = gd;
	sdkp->index = index;
	atomic_set(&sdkp->openers, 0);
	atomic_set(&sdkp->device->ioerr_cnt, 0);

	if (!sdp->request_queue->rq_timeout) {
		if (sdp->type != TYPE_MOD)
			blk_queue_rq_timeout(sdp->request_queue, SD_TIMEOUT);
		else
			blk_queue_rq_timeout(sdp->request_queue,
					     SD_MOD_TIMEOUT);
	}

	device_initialize(&sdkp->dev);
	sdkp->dev.parent = dev;
	sdkp->dev.class = &sd_disk_class;
	dev_set_name(&sdkp->dev, "%s", dev_name(dev));

	error = device_add(&sdkp->dev);
	if (error)
		goto out_free_index;

	get_device(dev);
	dev_set_drvdata(dev, sdkp);

	get_device(&sdkp->dev);	/* prevent release before async_schedule */
	async_schedule_domain(sd_probe_async, sdkp, &scsi_sd_probe_domain);

	return 0;

 out_free_index:
	spin_lock(&sd_index_lock);
	ida_remove(&sd_index_ida, index);
	spin_unlock(&sd_index_lock);
 out_put:
	put_disk(gd);
 out_free:
	kfree(sdkp);
 out:
	scsi_autopm_put_device(sdp);
	return error;
}

/**
 *	sd_remove - called whenever a scsi disk (previously recognized by
 *	sd_probe) is detached from the system. It is called (potentially
 *	multiple times) during sd module unload.
 *	@sdp: pointer to mid level scsi device object
 *
 *	Note: this function is invoked from the scsi mid-level.
 *	This function potentially frees up a device name (e.g. /dev/sdc)
 *	that could be re-used by a subsequent sd_probe().
 *	This function is not called when the built-in sd driver is "exit-ed".
 **/
static int sd_remove(struct device *dev)
{
	struct scsi_disk *sdkp;
	dev_t devt;

	sdkp = dev_get_drvdata(dev);
	devt = disk_devt(sdkp->disk);
	scsi_autopm_get_device(sdkp->device);

	async_synchronize_full_domain(&scsi_sd_pm_domain);
	async_synchronize_full_domain(&scsi_sd_probe_domain);
	device_del(&sdkp->dev);
	del_gendisk(sdkp->disk);
	sd_shutdown(dev);

	sd_zbc_remove(sdkp);

	blk_register_region(devt, SD_MINORS, NULL,
			    sd_default_probe, NULL, NULL);

	mutex_lock(&sd_ref_mutex);
	dev_set_drvdata(dev, NULL);
	put_device(&sdkp->dev);
	mutex_unlock(&sd_ref_mutex);

	return 0;
}

/**
 *	scsi_disk_release - Called to free the scsi_disk structure
 *	@dev: pointer to embedded class device
 *
 *	sd_ref_mutex must be held entering this routine.  Because it is
 *	called on last put, you should always use the scsi_disk_get()
 *	scsi_disk_put() helpers which manipulate the semaphore directly
 *	and never do a direct put_device.
 **/
static void scsi_disk_release(struct device *dev)
{
	struct scsi_disk *sdkp = to_scsi_disk(dev);
	struct gendisk *disk = sdkp->disk;
	
	spin_lock(&sd_index_lock);
	ida_remove(&sd_index_ida, sdkp->index);
	spin_unlock(&sd_index_lock);

	disk->private_data = NULL;
	put_disk(disk);
	put_device(&sdkp->device->sdev_gendev);

	kfree(sdkp);
}

static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
{
	unsigned char cmd[6] = { START_STOP };	/* START_VALID */
	struct scsi_sense_hdr sshdr;
	struct scsi_device *sdp = sdkp->device;
	int res;

	if (start)
		cmd[4] |= 1;	/* START */

	if (sdp->start_stop_pwr_cond)
		cmd[4] |= start ? 1 << 4 : 3 << 4;	/* Active or Standby */

	if (!scsi_device_online(sdp))
		return -ENODEV;

	res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr,
			       SD_TIMEOUT, SD_MAX_RETRIES, NULL, 0, RQF_PM);
	if (res) {
		sd_print_result(sdkp, "Start/Stop Unit failed", res);
		if (driver_byte(res) & DRIVER_SENSE)
			sd_print_sense_hdr(sdkp, &sshdr);
		if (scsi_sense_valid(&sshdr) &&
			/* 0x3a is medium not present */
			sshdr.asc == 0x3a)
			res = 0;
	}

	/* SCSI error codes must not go to the generic layer */
	if (res)
		return -EIO;

	return 0;
}

/*
 * Send a SYNCHRONIZE CACHE instruction down to the device through
 * the normal SCSI command structure.  Wait for the command to
 * complete.
 */
static void sd_shutdown(struct device *dev)
{
	struct scsi_disk *sdkp = dev_get_drvdata(dev);

	if (!sdkp)
		return;         /* this can happen */

	if (pm_runtime_suspended(dev))
		return;

	if (sdkp->WCE && sdkp->media_present) {
		sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
		sd_sync_cache(sdkp);
	}

	if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) {
		sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
		sd_start_stop_device(sdkp, 0);
	}
}

static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
{
	struct scsi_disk *sdkp = dev_get_drvdata(dev);
	int ret = 0;

	if (!sdkp)	/* E.g.: runtime suspend following sd_remove() */
		return 0;

	if (sdkp->WCE && sdkp->media_present) {
		sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
		ret = sd_sync_cache(sdkp);
		if (ret) {
			/* ignore OFFLINE device */
			if (ret == -ENODEV)
				ret = 0;
			goto done;
		}
	}

	if (sdkp->device->manage_start_stop) {
		sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
		/* an error is not worth aborting a system sleep */
		ret = sd_start_stop_device(sdkp, 0);
		if (ignore_stop_errors)
			ret = 0;
	}

done:
	return ret;
}

static int sd_suspend_system(struct device *dev)
{
	return sd_suspend_common(dev, true);
}

static int sd_suspend_runtime(struct device *dev)
{
	return sd_suspend_common(dev, false);
}

static int sd_resume(struct device *dev)
{
	struct scsi_disk *sdkp = dev_get_drvdata(dev);

	if (!sdkp)	/* E.g.: runtime resume at the start of sd_probe() */
		return 0;

	if (!sdkp->device->manage_start_stop)
		return 0;

	sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
	return sd_start_stop_device(sdkp, 1);
}

/**
 *	init_sd - entry point for this driver (both when built in or when
 *	a module).
 *
 *	Note: this function registers this driver with the scsi mid-level.
 **/
static int __init init_sd(void)
{
	int majors = 0, i, err;

	SCSI_LOG_HLQUEUE(3, printk("init_sd: sd driver entry point\n"));

	for (i = 0; i < SD_MAJORS; i++) {
		if (register_blkdev(sd_major(i), "sd") != 0)
			continue;
		majors++;
		blk_register_region(sd_major(i), SD_MINORS, NULL,
				    sd_default_probe, NULL, NULL);
	}

	if (!majors)
		return -ENODEV;

	err = class_register(&sd_disk_class);
	if (err)
		goto err_out;

	sd_cdb_cache = kmem_cache_create("sd_ext_cdb", SD_EXT_CDB_SIZE,
					 0, 0, NULL);
	if (!sd_cdb_cache) {
		printk(KERN_ERR "sd: can't init extended cdb cache\n");
		err = -ENOMEM;
		goto err_out_class;
	}

	sd_cdb_pool = mempool_create_slab_pool(SD_MEMPOOL_SIZE, sd_cdb_cache);
	if (!sd_cdb_pool) {
		printk(KERN_ERR "sd: can't init extended cdb pool\n");
		err = -ENOMEM;
		goto err_out_cache;
	}

	err = scsi_register_driver(&sd_template.gendrv);
	if (err)
		goto err_out_driver;

	return 0;

err_out_driver:
	mempool_destroy(sd_cdb_pool);

err_out_cache:
	kmem_cache_destroy(sd_cdb_cache);

err_out_class:
	class_unregister(&sd_disk_class);
err_out:
	for (i = 0; i < SD_MAJORS; i++)
		unregister_blkdev(sd_major(i), "sd");
	return err;
}

/**
 *	exit_sd - exit point for this driver (when it is a module).
 *
 *	Note: this function unregisters this driver from the scsi mid-level.
 **/
static void __exit exit_sd(void)
{
	int i;

	SCSI_LOG_HLQUEUE(3, printk("exit_sd: exiting sd driver\n"));

	scsi_unregister_driver(&sd_template.gendrv);
	mempool_destroy(sd_cdb_pool);
	kmem_cache_destroy(sd_cdb_cache);

	class_unregister(&sd_disk_class);

	for (i = 0; i < SD_MAJORS; i++) {
		blk_unregister_region(sd_major(i), SD_MINORS);
		unregister_blkdev(sd_major(i), "sd");
	}
}

module_init(init_sd);
module_exit(exit_sd);

static void sd_print_sense_hdr(struct scsi_disk *sdkp,
			       struct scsi_sense_hdr *sshdr)
{
	scsi_print_sense_hdr(sdkp->device,
			     sdkp->disk ? sdkp->disk->disk_name : NULL, sshdr);
}

static void sd_print_result(const struct scsi_disk *sdkp, const char *msg,
			    int result)
{
	const char *hb_string = scsi_hostbyte_string(result);
	const char *db_string = scsi_driverbyte_string(result);

	if (hb_string || db_string)
		sd_printk(KERN_INFO, sdkp,
			  "%s: Result: hostbyte=%s driverbyte=%s\n", msg,
			  hb_string ? hb_string : "invalid",
			  db_string ? db_string : "invalid");
	else
		sd_printk(KERN_INFO, sdkp,
			  "%s: Result: hostbyte=0x%02x driverbyte=0x%02x\n",
			  msg, host_byte(result), driver_byte(result));
}