summaryrefslogtreecommitdiff
path: root/drivers/block/pktcdvd.c
blob: 7bfc058cb66504b1445e8e286a0db335a5e75ea7 (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
/*
 * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
 * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
 * Copyright (C) 2006 Thomas Maier <balagi@justmail.de>
 *
 * May be copied or modified under the terms of the GNU General Public
 * License.  See linux/COPYING for more information.
 *
 * Packet writing layer for ATAPI and SCSI CD-RW, DVD+RW, DVD-RW and
 * DVD-RAM devices.
 *
 * Theory of operation:
 *
 * At the lowest level, there is the standard driver for the CD/DVD device,
 * such as drivers/scsi/sr.c. This driver can handle read and write requests,
 * but it doesn't know anything about the special restrictions that apply to
 * packet writing. One restriction is that write requests must be aligned to
 * packet boundaries on the physical media, and the size of a write request
 * must be equal to the packet size. Another restriction is that a
 * GPCMD_FLUSH_CACHE command has to be issued to the drive before a read
 * command, if the previous command was a write.
 *
 * The purpose of the packet writing driver is to hide these restrictions from
 * higher layers, such as file systems, and present a block device that can be
 * randomly read and written using 2kB-sized blocks.
 *
 * The lowest layer in the packet writing driver is the packet I/O scheduler.
 * Its data is defined by the struct packet_iosched and includes two bio
 * queues with pending read and write requests. These queues are processed
 * by the pkt_iosched_process_queue() function. The write requests in this
 * queue are already properly aligned and sized. This layer is responsible for
 * issuing the flush cache commands and scheduling the I/O in a good order.
 *
 * The next layer transforms unaligned write requests to aligned writes. This
 * transformation requires reading missing pieces of data from the underlying
 * block device, assembling the pieces to full packets and queuing them to the
 * packet I/O scheduler.
 *
 * At the top layer there is a custom ->submit_bio function that forwards
 * read requests directly to the iosched queue and puts write requests in the
 * unaligned write queue. A kernel thread performs the necessary read
 * gathering to convert the unaligned writes to aligned writes and then feeds
 * them to the packet I/O scheduler.
 *
 *************************************************************************/

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/backing-dev.h>
#include <linux/compat.h>
#include <linux/debugfs.h>
#include <linux/device.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/freezer.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/nospec.h>
#include <linux/pktcdvd.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/uaccess.h>

#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_ioctl.h>

#include <asm/unaligned.h>

#define DRIVER_NAME	"pktcdvd"

#define MAX_SPEED 0xffff

static DEFINE_MUTEX(pktcdvd_mutex);
static struct pktcdvd_device *pkt_devs[MAX_WRITERS];
static struct proc_dir_entry *pkt_proc;
static int pktdev_major;
static int write_congestion_on  = PKT_WRITE_CONGESTION_ON;
static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
static struct mutex ctl_mutex;	/* Serialize open/close/setup/teardown */
static mempool_t psd_pool;
static struct bio_set pkt_bio_set;

/* /sys/class/pktcdvd */
static struct class	class_pktcdvd;
static struct dentry	*pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */

/* forward declaration */
static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev);
static int pkt_remove_dev(dev_t pkt_dev);

static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd)
{
	return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1);
}

/**********************************************************
 * sysfs interface for pktcdvd
 * by (C) 2006  Thomas Maier <balagi@justmail.de>
 
  /sys/class/pktcdvd/pktcdvd[0-7]/
                     stat/reset
                     stat/packets_started
                     stat/packets_finished
                     stat/kb_written
                     stat/kb_read
                     stat/kb_read_gather
                     write_queue/size
                     write_queue/congestion_off
                     write_queue/congestion_on
 **********************************************************/

static ssize_t packets_started_show(struct device *dev,
				    struct device_attribute *attr, char *buf)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);

	return sysfs_emit(buf, "%lu\n", pd->stats.pkt_started);
}
static DEVICE_ATTR_RO(packets_started);

static ssize_t packets_finished_show(struct device *dev,
				     struct device_attribute *attr, char *buf)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);

	return sysfs_emit(buf, "%lu\n", pd->stats.pkt_ended);
}
static DEVICE_ATTR_RO(packets_finished);

static ssize_t kb_written_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);

	return sysfs_emit(buf, "%lu\n", pd->stats.secs_w >> 1);
}
static DEVICE_ATTR_RO(kb_written);

static ssize_t kb_read_show(struct device *dev,
			    struct device_attribute *attr, char *buf)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);

	return sysfs_emit(buf, "%lu\n", pd->stats.secs_r >> 1);
}
static DEVICE_ATTR_RO(kb_read);

static ssize_t kb_read_gather_show(struct device *dev,
				   struct device_attribute *attr, char *buf)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);

	return sysfs_emit(buf, "%lu\n", pd->stats.secs_rg >> 1);
}
static DEVICE_ATTR_RO(kb_read_gather);

static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
			   const char *buf, size_t len)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);

	if (len > 0) {
		pd->stats.pkt_started = 0;
		pd->stats.pkt_ended = 0;
		pd->stats.secs_w = 0;
		pd->stats.secs_rg = 0;
		pd->stats.secs_r = 0;
	}
	return len;
}
static DEVICE_ATTR_WO(reset);

static struct attribute *pkt_stat_attrs[] = {
	&dev_attr_packets_finished.attr,
	&dev_attr_packets_started.attr,
	&dev_attr_kb_read.attr,
	&dev_attr_kb_written.attr,
	&dev_attr_kb_read_gather.attr,
	&dev_attr_reset.attr,
	NULL,
};

static const struct attribute_group pkt_stat_group = {
	.name = "stat",
	.attrs = pkt_stat_attrs,
};

static ssize_t size_show(struct device *dev,
			 struct device_attribute *attr, char *buf)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);
	int n;

	spin_lock(&pd->lock);
	n = sysfs_emit(buf, "%d\n", pd->bio_queue_size);
	spin_unlock(&pd->lock);
	return n;
}
static DEVICE_ATTR_RO(size);

static void init_write_congestion_marks(int* lo, int* hi)
{
	if (*hi > 0) {
		*hi = max(*hi, 500);
		*hi = min(*hi, 1000000);
		if (*lo <= 0)
			*lo = *hi - 100;
		else {
			*lo = min(*lo, *hi - 100);
			*lo = max(*lo, 100);
		}
	} else {
		*hi = -1;
		*lo = -1;
	}
}

static ssize_t congestion_off_show(struct device *dev,
				   struct device_attribute *attr, char *buf)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);
	int n;

	spin_lock(&pd->lock);
	n = sysfs_emit(buf, "%d\n", pd->write_congestion_off);
	spin_unlock(&pd->lock);
	return n;
}

static ssize_t congestion_off_store(struct device *dev,
				    struct device_attribute *attr,
				    const char *buf, size_t len)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);
	int val, ret;

	ret = kstrtoint(buf, 10, &val);
	if (ret)
		return ret;

	spin_lock(&pd->lock);
	pd->write_congestion_off = val;
	init_write_congestion_marks(&pd->write_congestion_off, &pd->write_congestion_on);
	spin_unlock(&pd->lock);
	return len;
}
static DEVICE_ATTR_RW(congestion_off);

static ssize_t congestion_on_show(struct device *dev,
				  struct device_attribute *attr, char *buf)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);
	int n;

	spin_lock(&pd->lock);
	n = sysfs_emit(buf, "%d\n", pd->write_congestion_on);
	spin_unlock(&pd->lock);
	return n;
}

static ssize_t congestion_on_store(struct device *dev,
				   struct device_attribute *attr,
				   const char *buf, size_t len)
{
	struct pktcdvd_device *pd = dev_get_drvdata(dev);
	int val, ret;

	ret = kstrtoint(buf, 10, &val);
	if (ret)
		return ret;

	spin_lock(&pd->lock);
	pd->write_congestion_on = val;
	init_write_congestion_marks(&pd->write_congestion_off, &pd->write_congestion_on);
	spin_unlock(&pd->lock);
	return len;
}
static DEVICE_ATTR_RW(congestion_on);

static struct attribute *pkt_wq_attrs[] = {
	&dev_attr_congestion_on.attr,
	&dev_attr_congestion_off.attr,
	&dev_attr_size.attr,
	NULL,
};

static const struct attribute_group pkt_wq_group = {
	.name = "write_queue",
	.attrs = pkt_wq_attrs,
};

static const struct attribute_group *pkt_groups[] = {
	&pkt_stat_group,
	&pkt_wq_group,
	NULL,
};

static void pkt_sysfs_dev_new(struct pktcdvd_device *pd)
{
	if (class_is_registered(&class_pktcdvd)) {
		pd->dev = device_create_with_groups(&class_pktcdvd, NULL,
						    MKDEV(0, 0), pd, pkt_groups,
						    "%s", pd->disk->disk_name);
		if (IS_ERR(pd->dev))
			pd->dev = NULL;
	}
}

static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd)
{
	if (class_is_registered(&class_pktcdvd))
		device_unregister(pd->dev);
}


/********************************************************************
  /sys/class/pktcdvd/
                     add            map block device
                     remove         unmap packet dev
                     device_map     show mappings
 *******************************************************************/

static ssize_t device_map_show(const struct class *c, const struct class_attribute *attr,
			       char *data)
{
	int n = 0;
	int idx;
	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
	for (idx = 0; idx < MAX_WRITERS; idx++) {
		struct pktcdvd_device *pd = pkt_devs[idx];
		if (!pd)
			continue;
		n += sysfs_emit_at(data, n, "%s %u:%u %u:%u\n",
			pd->disk->disk_name,
			MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev),
			MAJOR(pd->bdev->bd_dev),
			MINOR(pd->bdev->bd_dev));
	}
	mutex_unlock(&ctl_mutex);
	return n;
}
static CLASS_ATTR_RO(device_map);

static ssize_t add_store(const struct class *c, const struct class_attribute *attr,
			 const char *buf, size_t count)
{
	unsigned int major, minor;

	if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
		/* pkt_setup_dev() expects caller to hold reference to self */
		if (!try_module_get(THIS_MODULE))
			return -ENODEV;

		pkt_setup_dev(MKDEV(major, minor), NULL);

		module_put(THIS_MODULE);

		return count;
	}

	return -EINVAL;
}
static CLASS_ATTR_WO(add);

static ssize_t remove_store(const struct class *c, const struct class_attribute *attr,
			    const char *buf, size_t count)
{
	unsigned int major, minor;
	if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
		pkt_remove_dev(MKDEV(major, minor));
		return count;
	}
	return -EINVAL;
}
static CLASS_ATTR_WO(remove);

static struct attribute *class_pktcdvd_attrs[] = {
	&class_attr_add.attr,
	&class_attr_remove.attr,
	&class_attr_device_map.attr,
	NULL,
};
ATTRIBUTE_GROUPS(class_pktcdvd);

static struct class class_pktcdvd = {
	.name		= DRIVER_NAME,
	.class_groups	= class_pktcdvd_groups,
};

static int pkt_sysfs_init(void)
{
	/*
	 * create control files in sysfs
	 * /sys/class/pktcdvd/...
	 */
	return class_register(&class_pktcdvd);
}

static void pkt_sysfs_cleanup(void)
{
	class_unregister(&class_pktcdvd);
}

/********************************************************************
  entries in debugfs

  /sys/kernel/debug/pktcdvd[0-7]/
			info

 *******************************************************************/

static void pkt_count_states(struct pktcdvd_device *pd, int *states)
{
	struct packet_data *pkt;
	int i;

	for (i = 0; i < PACKET_NUM_STATES; i++)
		states[i] = 0;

	spin_lock(&pd->cdrw.active_list_lock);
	list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
		states[pkt->state]++;
	}
	spin_unlock(&pd->cdrw.active_list_lock);
}

static int pkt_seq_show(struct seq_file *m, void *p)
{
	struct pktcdvd_device *pd = m->private;
	char *msg;
	int states[PACKET_NUM_STATES];

	seq_printf(m, "Writer %s mapped to %pg:\n", pd->disk->disk_name, pd->bdev);

	seq_printf(m, "\nSettings:\n");
	seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2);

	if (pd->settings.write_type == 0)
		msg = "Packet";
	else
		msg = "Unknown";
	seq_printf(m, "\twrite type:\t\t%s\n", msg);

	seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable");
	seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss);

	seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode);

	if (pd->settings.block_mode == PACKET_BLOCK_MODE1)
		msg = "Mode 1";
	else if (pd->settings.block_mode == PACKET_BLOCK_MODE2)
		msg = "Mode 2";
	else
		msg = "Unknown";
	seq_printf(m, "\tblock mode:\t\t%s\n", msg);

	seq_printf(m, "\nStatistics:\n");
	seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started);
	seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended);
	seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1);
	seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1);
	seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1);

	seq_printf(m, "\nMisc:\n");
	seq_printf(m, "\treference count:\t%d\n", pd->refcnt);
	seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags);
	seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed);
	seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed);
	seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset);
	seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset);

	seq_printf(m, "\nQueue state:\n");
	seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size);
	seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios));
	seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", pd->current_sector);

	pkt_count_states(pd, states);
	seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
		   states[0], states[1], states[2], states[3], states[4], states[5]);

	seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n",
			pd->write_congestion_off,
			pd->write_congestion_on);
	return 0;
}
DEFINE_SHOW_ATTRIBUTE(pkt_seq);

static void pkt_debugfs_dev_new(struct pktcdvd_device *pd)
{
	if (!pkt_debugfs_root)
		return;
	pd->dfs_d_root = debugfs_create_dir(pd->disk->disk_name, pkt_debugfs_root);
	if (!pd->dfs_d_root)
		return;

	pd->dfs_f_info = debugfs_create_file("info", 0444, pd->dfs_d_root,
					     pd, &pkt_seq_fops);
}

static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd)
{
	if (!pkt_debugfs_root)
		return;
	debugfs_remove(pd->dfs_f_info);
	debugfs_remove(pd->dfs_d_root);
	pd->dfs_f_info = NULL;
	pd->dfs_d_root = NULL;
}

static void pkt_debugfs_init(void)
{
	pkt_debugfs_root = debugfs_create_dir(DRIVER_NAME, NULL);
}

static void pkt_debugfs_cleanup(void)
{
	debugfs_remove(pkt_debugfs_root);
	pkt_debugfs_root = NULL;
}

/* ----------------------------------------------------------*/


static void pkt_bio_finished(struct pktcdvd_device *pd)
{
	struct device *ddev = disk_to_dev(pd->disk);

	BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0);
	if (atomic_dec_and_test(&pd->cdrw.pending_bios)) {
		dev_dbg(ddev, "queue empty\n");
		atomic_set(&pd->iosched.attention, 1);
		wake_up(&pd->wqueue);
	}
}

/*
 * Allocate a packet_data struct
 */
static struct packet_data *pkt_alloc_packet_data(int frames)
{
	int i;
	struct packet_data *pkt;

	pkt = kzalloc(sizeof(struct packet_data), GFP_KERNEL);
	if (!pkt)
		goto no_pkt;

	pkt->frames = frames;
	pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL);
	if (!pkt->w_bio)
		goto no_bio;

	for (i = 0; i < frames / FRAMES_PER_PAGE; i++) {
		pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO);
		if (!pkt->pages[i])
			goto no_page;
	}

	spin_lock_init(&pkt->lock);
	bio_list_init(&pkt->orig_bios);

	for (i = 0; i < frames; i++) {
		pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL);
		if (!pkt->r_bios[i])
			goto no_rd_bio;
	}

	return pkt;

no_rd_bio:
	for (i = 0; i < frames; i++)
		kfree(pkt->r_bios[i]);
no_page:
	for (i = 0; i < frames / FRAMES_PER_PAGE; i++)
		if (pkt->pages[i])
			__free_page(pkt->pages[i]);
	kfree(pkt->w_bio);
no_bio:
	kfree(pkt);
no_pkt:
	return NULL;
}

/*
 * Free a packet_data struct
 */
static void pkt_free_packet_data(struct packet_data *pkt)
{
	int i;

	for (i = 0; i < pkt->frames; i++)
		kfree(pkt->r_bios[i]);
	for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++)
		__free_page(pkt->pages[i]);
	kfree(pkt->w_bio);
	kfree(pkt);
}

static void pkt_shrink_pktlist(struct pktcdvd_device *pd)
{
	struct packet_data *pkt, *next;

	BUG_ON(!list_empty(&pd->cdrw.pkt_active_list));

	list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_free_list, list) {
		pkt_free_packet_data(pkt);
	}
	INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
}

static int pkt_grow_pktlist(struct pktcdvd_device *pd, int nr_packets)
{
	struct packet_data *pkt;

	BUG_ON(!list_empty(&pd->cdrw.pkt_free_list));

	while (nr_packets > 0) {
		pkt = pkt_alloc_packet_data(pd->settings.size >> 2);
		if (!pkt) {
			pkt_shrink_pktlist(pd);
			return 0;
		}
		pkt->id = nr_packets;
		pkt->pd = pd;
		list_add(&pkt->list, &pd->cdrw.pkt_free_list);
		nr_packets--;
	}
	return 1;
}

static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node)
{
	struct rb_node *n = rb_next(&node->rb_node);
	if (!n)
		return NULL;
	return rb_entry(n, struct pkt_rb_node, rb_node);
}

static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node)
{
	rb_erase(&node->rb_node, &pd->bio_queue);
	mempool_free(node, &pd->rb_pool);
	pd->bio_queue_size--;
	BUG_ON(pd->bio_queue_size < 0);
}

/*
 * Find the first node in the pd->bio_queue rb tree with a starting sector >= s.
 */
static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s)
{
	struct rb_node *n = pd->bio_queue.rb_node;
	struct rb_node *next;
	struct pkt_rb_node *tmp;

	if (!n) {
		BUG_ON(pd->bio_queue_size > 0);
		return NULL;
	}

	for (;;) {
		tmp = rb_entry(n, struct pkt_rb_node, rb_node);
		if (s <= tmp->bio->bi_iter.bi_sector)
			next = n->rb_left;
		else
			next = n->rb_right;
		if (!next)
			break;
		n = next;
	}

	if (s > tmp->bio->bi_iter.bi_sector) {
		tmp = pkt_rbtree_next(tmp);
		if (!tmp)
			return NULL;
	}
	BUG_ON(s > tmp->bio->bi_iter.bi_sector);
	return tmp;
}

/*
 * Insert a node into the pd->bio_queue rb tree.
 */
static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *node)
{
	struct rb_node **p = &pd->bio_queue.rb_node;
	struct rb_node *parent = NULL;
	sector_t s = node->bio->bi_iter.bi_sector;
	struct pkt_rb_node *tmp;

	while (*p) {
		parent = *p;
		tmp = rb_entry(parent, struct pkt_rb_node, rb_node);
		if (s < tmp->bio->bi_iter.bi_sector)
			p = &(*p)->rb_left;
		else
			p = &(*p)->rb_right;
	}
	rb_link_node(&node->rb_node, parent, p);
	rb_insert_color(&node->rb_node, &pd->bio_queue);
	pd->bio_queue_size++;
}

/*
 * Send a packet_command to the underlying block device and
 * wait for completion.
 */
static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc)
{
	struct request_queue *q = bdev_get_queue(pd->bdev);
	struct scsi_cmnd *scmd;
	struct request *rq;
	int ret = 0;

	rq = scsi_alloc_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
			     REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
	if (IS_ERR(rq))
		return PTR_ERR(rq);
	scmd = blk_mq_rq_to_pdu(rq);

	if (cgc->buflen) {
		ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
				      GFP_NOIO);
		if (ret)
			goto out;
	}

	scmd->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
	memcpy(scmd->cmnd, cgc->cmd, CDROM_PACKET_SIZE);

	rq->timeout = 60*HZ;
	if (cgc->quiet)
		rq->rq_flags |= RQF_QUIET;

	blk_execute_rq(rq, false);
	if (scmd->result)
		ret = -EIO;
out:
	blk_mq_free_request(rq);
	return ret;
}

static const char *sense_key_string(__u8 index)
{
	static const char * const info[] = {
		"No sense", "Recovered error", "Not ready",
		"Medium error", "Hardware error", "Illegal request",
		"Unit attention", "Data protect", "Blank check",
	};

	return index < ARRAY_SIZE(info) ? info[index] : "INVALID";
}

/*
 * A generic sense dump / resolve mechanism should be implemented across
 * all ATAPI + SCSI devices.
 */
static void pkt_dump_sense(struct pktcdvd_device *pd,
			   struct packet_command *cgc)
{
	struct device *ddev = disk_to_dev(pd->disk);
	struct scsi_sense_hdr *sshdr = cgc->sshdr;

	if (sshdr)
		dev_err(ddev, "%*ph - sense %02x.%02x.%02x (%s)\n",
			CDROM_PACKET_SIZE, cgc->cmd,
			sshdr->sense_key, sshdr->asc, sshdr->ascq,
			sense_key_string(sshdr->sense_key));
	else
		dev_err(ddev, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
}

/*
 * flush the drive cache to media
 */
static int pkt_flush_cache(struct pktcdvd_device *pd)
{
	struct packet_command cgc;

	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
	cgc.cmd[0] = GPCMD_FLUSH_CACHE;
	cgc.quiet = 1;

	/*
	 * the IMMED bit -- we default to not setting it, although that
	 * would allow a much faster close, this is safer
	 */
#if 0
	cgc.cmd[1] = 1 << 1;
#endif
	return pkt_generic_packet(pd, &cgc);
}

/*
 * speed is given as the normal factor, e.g. 4 for 4x
 */
static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
				unsigned write_speed, unsigned read_speed)
{
	struct packet_command cgc;
	struct scsi_sense_hdr sshdr;
	int ret;

	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
	cgc.sshdr = &sshdr;
	cgc.cmd[0] = GPCMD_SET_SPEED;
	put_unaligned_be16(read_speed, &cgc.cmd[2]);
	put_unaligned_be16(write_speed, &cgc.cmd[4]);

	ret = pkt_generic_packet(pd, &cgc);
	if (ret)
		pkt_dump_sense(pd, &cgc);

	return ret;
}

/*
 * Queue a bio for processing by the low-level CD device. Must be called
 * from process context.
 */
static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
{
	spin_lock(&pd->iosched.lock);
	if (bio_data_dir(bio) == READ)
		bio_list_add(&pd->iosched.read_queue, bio);
	else
		bio_list_add(&pd->iosched.write_queue, bio);
	spin_unlock(&pd->iosched.lock);

	atomic_set(&pd->iosched.attention, 1);
	wake_up(&pd->wqueue);
}

/*
 * Process the queued read/write requests. This function handles special
 * requirements for CDRW drives:
 * - A cache flush command must be inserted before a read request if the
 *   previous request was a write.
 * - Switching between reading and writing is slow, so don't do it more often
 *   than necessary.
 * - Optimize for throughput at the expense of latency. This means that streaming
 *   writes will never be interrupted by a read, but if the drive has to seek
 *   before the next write, switch to reading instead if there are any pending
 *   read requests.
 * - Set the read speed according to current usage pattern. When only reading
 *   from the device, it's best to use the highest possible read speed, but
 *   when switching often between reading and writing, it's better to have the
 *   same read and write speeds.
 */
static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
{
	struct device *ddev = disk_to_dev(pd->disk);

	if (atomic_read(&pd->iosched.attention) == 0)
		return;
	atomic_set(&pd->iosched.attention, 0);

	for (;;) {
		struct bio *bio;
		int reads_queued, writes_queued;

		spin_lock(&pd->iosched.lock);
		reads_queued = !bio_list_empty(&pd->iosched.read_queue);
		writes_queued = !bio_list_empty(&pd->iosched.write_queue);
		spin_unlock(&pd->iosched.lock);

		if (!reads_queued && !writes_queued)
			break;

		if (pd->iosched.writing) {
			int need_write_seek = 1;
			spin_lock(&pd->iosched.lock);
			bio = bio_list_peek(&pd->iosched.write_queue);
			spin_unlock(&pd->iosched.lock);
			if (bio && (bio->bi_iter.bi_sector ==
				    pd->iosched.last_write))
				need_write_seek = 0;
			if (need_write_seek && reads_queued) {
				if (atomic_read(&pd->cdrw.pending_bios) > 0) {
					dev_dbg(ddev, "write, waiting\n");
					break;
				}
				pkt_flush_cache(pd);
				pd->iosched.writing = 0;
			}
		} else {
			if (!reads_queued && writes_queued) {
				if (atomic_read(&pd->cdrw.pending_bios) > 0) {
					dev_dbg(ddev, "read, waiting\n");
					break;
				}
				pd->iosched.writing = 1;
			}
		}

		spin_lock(&pd->iosched.lock);
		if (pd->iosched.writing)
			bio = bio_list_pop(&pd->iosched.write_queue);
		else
			bio = bio_list_pop(&pd->iosched.read_queue);
		spin_unlock(&pd->iosched.lock);

		if (!bio)
			continue;

		if (bio_data_dir(bio) == READ)
			pd->iosched.successive_reads +=
				bio->bi_iter.bi_size >> 10;
		else {
			pd->iosched.successive_reads = 0;
			pd->iosched.last_write = bio_end_sector(bio);
		}
		if (pd->iosched.successive_reads >= HI_SPEED_SWITCH) {
			if (pd->read_speed == pd->write_speed) {
				pd->read_speed = MAX_SPEED;
				pkt_set_speed(pd, pd->write_speed, pd->read_speed);
			}
		} else {
			if (pd->read_speed != pd->write_speed) {
				pd->read_speed = pd->write_speed;
				pkt_set_speed(pd, pd->write_speed, pd->read_speed);
			}
		}

		atomic_inc(&pd->cdrw.pending_bios);
		submit_bio_noacct(bio);
	}
}

/*
 * Special care is needed if the underlying block device has a small
 * max_phys_segments value.
 */
static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
{
	struct device *ddev = disk_to_dev(pd->disk);

	if ((pd->settings.size << 9) / CD_FRAMESIZE <= queue_max_segments(q)) {
		/*
		 * The cdrom device can handle one segment/frame
		 */
		clear_bit(PACKET_MERGE_SEGS, &pd->flags);
		return 0;
	}

	if ((pd->settings.size << 9) / PAGE_SIZE <= queue_max_segments(q)) {
		/*
		 * We can handle this case at the expense of some extra memory
		 * copies during write operations
		 */
		set_bit(PACKET_MERGE_SEGS, &pd->flags);
		return 0;
	}

	dev_err(ddev, "cdrom max_phys_segments too small\n");
	return -EIO;
}

static void pkt_end_io_read(struct bio *bio)
{
	struct packet_data *pkt = bio->bi_private;
	struct pktcdvd_device *pd = pkt->pd;
	BUG_ON(!pd);

	dev_dbg(disk_to_dev(pd->disk), "bio=%p sec0=%llx sec=%llx err=%d\n",
		bio, pkt->sector, bio->bi_iter.bi_sector, bio->bi_status);

	if (bio->bi_status)
		atomic_inc(&pkt->io_errors);
	bio_uninit(bio);
	if (atomic_dec_and_test(&pkt->io_wait)) {
		atomic_inc(&pkt->run_sm);
		wake_up(&pd->wqueue);
	}
	pkt_bio_finished(pd);
}

static void pkt_end_io_packet_write(struct bio *bio)
{
	struct packet_data *pkt = bio->bi_private;
	struct pktcdvd_device *pd = pkt->pd;
	BUG_ON(!pd);

	dev_dbg(disk_to_dev(pd->disk), "id=%d, err=%d\n", pkt->id, bio->bi_status);

	pd->stats.pkt_ended++;

	bio_uninit(bio);
	pkt_bio_finished(pd);
	atomic_dec(&pkt->io_wait);
	atomic_inc(&pkt->run_sm);
	wake_up(&pd->wqueue);
}

/*
 * Schedule reads for the holes in a packet
 */
static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
{
	struct device *ddev = disk_to_dev(pd->disk);
	int frames_read = 0;
	struct bio *bio;
	int f;
	char written[PACKET_MAX_SIZE];

	BUG_ON(bio_list_empty(&pkt->orig_bios));

	atomic_set(&pkt->io_wait, 0);
	atomic_set(&pkt->io_errors, 0);

	/*
	 * Figure out which frames we need to read before we can write.
	 */
	memset(written, 0, sizeof(written));
	spin_lock(&pkt->lock);
	bio_list_for_each(bio, &pkt->orig_bios) {
		int first_frame = (bio->bi_iter.bi_sector - pkt->sector) /
			(CD_FRAMESIZE >> 9);
		int num_frames = bio->bi_iter.bi_size / CD_FRAMESIZE;
		pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9);
		BUG_ON(first_frame < 0);
		BUG_ON(first_frame + num_frames > pkt->frames);
		for (f = first_frame; f < first_frame + num_frames; f++)
			written[f] = 1;
	}
	spin_unlock(&pkt->lock);

	if (pkt->cache_valid) {
		dev_dbg(ddev, "zone %llx cached\n", pkt->sector);
		goto out_account;
	}

	/*
	 * Schedule reads for missing parts of the packet.
	 */
	for (f = 0; f < pkt->frames; f++) {
		int p, offset;

		if (written[f])
			continue;

		bio = pkt->r_bios[f];
		bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ);
		bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
		bio->bi_end_io = pkt_end_io_read;
		bio->bi_private = pkt;

		p = (f * CD_FRAMESIZE) / PAGE_SIZE;
		offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
		dev_dbg(ddev, "Adding frame %d, page:%p offs:%d\n", f,
			pkt->pages[p], offset);
		if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset))
			BUG();

		atomic_inc(&pkt->io_wait);
		pkt_queue_bio(pd, bio);
		frames_read++;
	}

out_account:
	dev_dbg(ddev, "need %d frames for zone %llx\n", frames_read, pkt->sector);
	pd->stats.pkt_started++;
	pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9);
}

/*
 * Find a packet matching zone, or the least recently used packet if
 * there is no match.
 */
static struct packet_data *pkt_get_packet_data(struct pktcdvd_device *pd, int zone)
{
	struct packet_data *pkt;

	list_for_each_entry(pkt, &pd->cdrw.pkt_free_list, list) {
		if (pkt->sector == zone || pkt->list.next == &pd->cdrw.pkt_free_list) {
			list_del_init(&pkt->list);
			if (pkt->sector != zone)
				pkt->cache_valid = 0;
			return pkt;
		}
	}
	BUG();
	return NULL;
}

static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *pkt)
{
	if (pkt->cache_valid) {
		list_add(&pkt->list, &pd->cdrw.pkt_free_list);
	} else {
		list_add_tail(&pkt->list, &pd->cdrw.pkt_free_list);
	}
}

static inline void pkt_set_state(struct device *ddev, struct packet_data *pkt,
				 enum packet_data_state state)
{
	static const char *state_name[] = {
		"IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED"
	};
	enum packet_data_state old_state = pkt->state;

	dev_dbg(ddev, "pkt %2d : s=%6llx %s -> %s\n",
		pkt->id, pkt->sector, state_name[old_state], state_name[state]);

	pkt->state = state;
}

/*
 * Scan the work queue to see if we can start a new packet.
 * returns non-zero if any work was done.
 */
static int pkt_handle_queue(struct pktcdvd_device *pd)
{
	struct device *ddev = disk_to_dev(pd->disk);
	struct packet_data *pkt, *p;
	struct bio *bio = NULL;
	sector_t zone = 0; /* Suppress gcc warning */
	struct pkt_rb_node *node, *first_node;
	struct rb_node *n;

	atomic_set(&pd->scan_queue, 0);

	if (list_empty(&pd->cdrw.pkt_free_list)) {
		dev_dbg(ddev, "no pkt\n");
		return 0;
	}

	/*
	 * Try to find a zone we are not already working on.
	 */
	spin_lock(&pd->lock);
	first_node = pkt_rbtree_find(pd, pd->current_sector);
	if (!first_node) {
		n = rb_first(&pd->bio_queue);
		if (n)
			first_node = rb_entry(n, struct pkt_rb_node, rb_node);
	}
	node = first_node;
	while (node) {
		bio = node->bio;
		zone = get_zone(bio->bi_iter.bi_sector, pd);
		list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) {
			if (p->sector == zone) {
				bio = NULL;
				goto try_next_bio;
			}
		}
		break;
try_next_bio:
		node = pkt_rbtree_next(node);
		if (!node) {
			n = rb_first(&pd->bio_queue);
			if (n)
				node = rb_entry(n, struct pkt_rb_node, rb_node);
		}
		if (node == first_node)
			node = NULL;
	}
	spin_unlock(&pd->lock);
	if (!bio) {
		dev_dbg(ddev, "no bio\n");
		return 0;
	}

	pkt = pkt_get_packet_data(pd, zone);

	pd->current_sector = zone + pd->settings.size;
	pkt->sector = zone;
	BUG_ON(pkt->frames != pd->settings.size >> 2);
	pkt->write_size = 0;

	/*
	 * Scan work queue for bios in the same zone and link them
	 * to this packet.
	 */
	spin_lock(&pd->lock);
	dev_dbg(ddev, "looking for zone %llx\n", zone);
	while ((node = pkt_rbtree_find(pd, zone)) != NULL) {
		sector_t tmp = get_zone(node->bio->bi_iter.bi_sector, pd);

		bio = node->bio;
		dev_dbg(ddev, "found zone=%llx\n", tmp);
		if (tmp != zone)
			break;
		pkt_rbtree_erase(pd, node);
		spin_lock(&pkt->lock);
		bio_list_add(&pkt->orig_bios, bio);
		pkt->write_size += bio->bi_iter.bi_size / CD_FRAMESIZE;
		spin_unlock(&pkt->lock);
	}
	/* check write congestion marks, and if bio_queue_size is
	 * below, wake up any waiters
	 */
	if (pd->congested &&
	    pd->bio_queue_size <= pd->write_congestion_off) {
		pd->congested = false;
		wake_up_var(&pd->congested);
	}
	spin_unlock(&pd->lock);

	pkt->sleep_time = max(PACKET_WAIT_TIME, 1);
	pkt_set_state(ddev, pkt, PACKET_WAITING_STATE);
	atomic_set(&pkt->run_sm, 1);

	spin_lock(&pd->cdrw.active_list_lock);
	list_add(&pkt->list, &pd->cdrw.pkt_active_list);
	spin_unlock(&pd->cdrw.active_list_lock);

	return 1;
}

/**
 * bio_list_copy_data - copy contents of data buffers from one chain of bios to
 * another
 * @src: source bio list
 * @dst: destination bio list
 *
 * Stops when it reaches the end of either the @src list or @dst list - that is,
 * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of
 * bios).
 */
static void bio_list_copy_data(struct bio *dst, struct bio *src)
{
	struct bvec_iter src_iter = src->bi_iter;
	struct bvec_iter dst_iter = dst->bi_iter;

	while (1) {
		if (!src_iter.bi_size) {
			src = src->bi_next;
			if (!src)
				break;

			src_iter = src->bi_iter;
		}

		if (!dst_iter.bi_size) {
			dst = dst->bi_next;
			if (!dst)
				break;

			dst_iter = dst->bi_iter;
		}

		bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
	}
}

/*
 * Assemble a bio to write one packet and queue the bio for processing
 * by the underlying block device.
 */
static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
{
	struct device *ddev = disk_to_dev(pd->disk);
	int f;

	bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames,
		 REQ_OP_WRITE);
	pkt->w_bio->bi_iter.bi_sector = pkt->sector;
	pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
	pkt->w_bio->bi_private = pkt;

	/* XXX: locking? */
	for (f = 0; f < pkt->frames; f++) {
		struct page *page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE];
		unsigned offset = (f * CD_FRAMESIZE) % PAGE_SIZE;

		if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset))
			BUG();
	}
	dev_dbg(ddev, "vcnt=%d\n", pkt->w_bio->bi_vcnt);

	/*
	 * Fill-in bvec with data from orig_bios.
	 */
	spin_lock(&pkt->lock);
	bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head);

	pkt_set_state(ddev, pkt, PACKET_WRITE_WAIT_STATE);
	spin_unlock(&pkt->lock);

	dev_dbg(ddev, "Writing %d frames for zone %llx\n", pkt->write_size, pkt->sector);

	if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames))
		pkt->cache_valid = 1;
	else
		pkt->cache_valid = 0;

	/* Start the write request */
	atomic_set(&pkt->io_wait, 1);
	pkt_queue_bio(pd, pkt->w_bio);
}

static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status)
{
	struct bio *bio;

	if (status)
		pkt->cache_valid = 0;

	/* Finish all bios corresponding to this packet */
	while ((bio = bio_list_pop(&pkt->orig_bios))) {
		bio->bi_status = status;
		bio_endio(bio);
	}
}

static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt)
{
	struct device *ddev = disk_to_dev(pd->disk);

	dev_dbg(ddev, "pkt %d\n", pkt->id);

	for (;;) {
		switch (pkt->state) {
		case PACKET_WAITING_STATE:
			if ((pkt->write_size < pkt->frames) && (pkt->sleep_time > 0))
				return;

			pkt->sleep_time = 0;
			pkt_gather_data(pd, pkt);
			pkt_set_state(ddev, pkt, PACKET_READ_WAIT_STATE);
			break;

		case PACKET_READ_WAIT_STATE:
			if (atomic_read(&pkt->io_wait) > 0)
				return;

			if (atomic_read(&pkt->io_errors) > 0) {
				pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE);
			} else {
				pkt_start_write(pd, pkt);
			}
			break;

		case PACKET_WRITE_WAIT_STATE:
			if (atomic_read(&pkt->io_wait) > 0)
				return;

			if (!pkt->w_bio->bi_status) {
				pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE);
			} else {
				pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE);
			}
			break;

		case PACKET_RECOVERY_STATE:
			dev_dbg(ddev, "No recovery possible\n");
			pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE);
			break;

		case PACKET_FINISHED_STATE:
			pkt_finish_packet(pkt, pkt->w_bio->bi_status);
			return;

		default:
			BUG();
			break;
		}
	}
}

static void pkt_handle_packets(struct pktcdvd_device *pd)
{
	struct device *ddev = disk_to_dev(pd->disk);
	struct packet_data *pkt, *next;

	/*
	 * Run state machine for active packets
	 */
	list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
		if (atomic_read(&pkt->run_sm) > 0) {
			atomic_set(&pkt->run_sm, 0);
			pkt_run_state_machine(pd, pkt);
		}
	}

	/*
	 * Move no longer active packets to the free list
	 */
	spin_lock(&pd->cdrw.active_list_lock);
	list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_active_list, list) {
		if (pkt->state == PACKET_FINISHED_STATE) {
			list_del(&pkt->list);
			pkt_put_packet_data(pd, pkt);
			pkt_set_state(ddev, pkt, PACKET_IDLE_STATE);
			atomic_set(&pd->scan_queue, 1);
		}
	}
	spin_unlock(&pd->cdrw.active_list_lock);
}

/*
 * kcdrwd is woken up when writes have been queued for one of our
 * registered devices
 */
static int kcdrwd(void *foobar)
{
	struct pktcdvd_device *pd = foobar;
	struct device *ddev = disk_to_dev(pd->disk);
	struct packet_data *pkt;
	int states[PACKET_NUM_STATES];
	long min_sleep_time, residue;

	set_user_nice(current, MIN_NICE);
	set_freezable();

	for (;;) {
		DECLARE_WAITQUEUE(wait, current);

		/*
		 * Wait until there is something to do
		 */
		add_wait_queue(&pd->wqueue, &wait);
		for (;;) {
			set_current_state(TASK_INTERRUPTIBLE);

			/* Check if we need to run pkt_handle_queue */
			if (atomic_read(&pd->scan_queue) > 0)
				goto work_to_do;

			/* Check if we need to run the state machine for some packet */
			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
				if (atomic_read(&pkt->run_sm) > 0)
					goto work_to_do;
			}

			/* Check if we need to process the iosched queues */
			if (atomic_read(&pd->iosched.attention) != 0)
				goto work_to_do;

			/* Otherwise, go to sleep */
			pkt_count_states(pd, states);
			dev_dbg(ddev, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
				states[0], states[1], states[2], states[3], states[4], states[5]);

			min_sleep_time = MAX_SCHEDULE_TIMEOUT;
			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
				if (pkt->sleep_time && pkt->sleep_time < min_sleep_time)
					min_sleep_time = pkt->sleep_time;
			}

			dev_dbg(ddev, "sleeping\n");
			residue = schedule_timeout(min_sleep_time);
			dev_dbg(ddev, "wake up\n");

			/* make swsusp happy with our thread */
			try_to_freeze();

			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
				if (!pkt->sleep_time)
					continue;
				pkt->sleep_time -= min_sleep_time - residue;
				if (pkt->sleep_time <= 0) {
					pkt->sleep_time = 0;
					atomic_inc(&pkt->run_sm);
				}
			}

			if (kthread_should_stop())
				break;
		}
work_to_do:
		set_current_state(TASK_RUNNING);
		remove_wait_queue(&pd->wqueue, &wait);

		if (kthread_should_stop())
			break;

		/*
		 * if pkt_handle_queue returns true, we can queue
		 * another request.
		 */
		while (pkt_handle_queue(pd))
			;

		/*
		 * Handle packet state machine
		 */
		pkt_handle_packets(pd);

		/*
		 * Handle iosched queues
		 */
		pkt_iosched_process_queue(pd);
	}

	return 0;
}

static void pkt_print_settings(struct pktcdvd_device *pd)
{
	dev_info(disk_to_dev(pd->disk), "%s packets, %u blocks, Mode-%c disc\n",
		 pd->settings.fp ? "Fixed" : "Variable",
		 pd->settings.size >> 2,
		 pd->settings.block_mode == 8 ? '1' : '2');
}

static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control)
{
	memset(cgc->cmd, 0, sizeof(cgc->cmd));

	cgc->cmd[0] = GPCMD_MODE_SENSE_10;
	cgc->cmd[2] = page_code | (page_control << 6);
	put_unaligned_be16(cgc->buflen, &cgc->cmd[7]);
	cgc->data_direction = CGC_DATA_READ;
	return pkt_generic_packet(pd, cgc);
}

static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc)
{
	memset(cgc->cmd, 0, sizeof(cgc->cmd));
	memset(cgc->buffer, 0, 2);
	cgc->cmd[0] = GPCMD_MODE_SELECT_10;
	cgc->cmd[1] = 0x10;		/* PF */
	put_unaligned_be16(cgc->buflen, &cgc->cmd[7]);
	cgc->data_direction = CGC_DATA_WRITE;
	return pkt_generic_packet(pd, cgc);
}

static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
{
	struct packet_command cgc;
	int ret;

	/* set up command and get the disc info */
	init_cdrom_command(&cgc, di, sizeof(*di), CGC_DATA_READ);
	cgc.cmd[0] = GPCMD_READ_DISC_INFO;
	cgc.cmd[8] = cgc.buflen = 2;
	cgc.quiet = 1;

	ret = pkt_generic_packet(pd, &cgc);
	if (ret)
		return ret;

	/* not all drives have the same disc_info length, so requeue
	 * packet with the length the drive tells us it can supply
	 */
	cgc.buflen = be16_to_cpu(di->disc_information_length) +
		     sizeof(di->disc_information_length);

	if (cgc.buflen > sizeof(disc_information))
		cgc.buflen = sizeof(disc_information);

	cgc.cmd[8] = cgc.buflen;
	return pkt_generic_packet(pd, &cgc);
}

static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, track_information *ti)
{
	struct packet_command cgc;
	int ret;

	init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ);
	cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO;
	cgc.cmd[1] = type & 3;
	put_unaligned_be16(track, &cgc.cmd[4]);
	cgc.cmd[8] = 8;
	cgc.quiet = 1;

	ret = pkt_generic_packet(pd, &cgc);
	if (ret)
		return ret;

	cgc.buflen = be16_to_cpu(ti->track_information_length) +
		     sizeof(ti->track_information_length);

	if (cgc.buflen > sizeof(track_information))
		cgc.buflen = sizeof(track_information);

	cgc.cmd[8] = cgc.buflen;
	return pkt_generic_packet(pd, &cgc);
}

static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
						long *last_written)
{
	disc_information di;
	track_information ti;
	__u32 last_track;
	int ret;

	ret = pkt_get_disc_info(pd, &di);
	if (ret)
		return ret;

	last_track = (di.last_track_msb << 8) | di.last_track_lsb;
	ret = pkt_get_track_info(pd, last_track, 1, &ti);
	if (ret)
		return ret;

	/* if this track is blank, try the previous. */
	if (ti.blank) {
		last_track--;
		ret = pkt_get_track_info(pd, last_track, 1, &ti);
		if (ret)
			return ret;
	}

	/* if last recorded field is valid, return it. */
	if (ti.lra_v) {
		*last_written = be32_to_cpu(ti.last_rec_address);
	} else {
		/* make it up instead */
		*last_written = be32_to_cpu(ti.track_start) +
				be32_to_cpu(ti.track_size);
		if (ti.free_blocks)
			*last_written -= (be32_to_cpu(ti.free_blocks) + 7);
	}
	return 0;
}

/*
 * write mode select package based on pd->settings
 */
static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
{
	struct device *ddev = disk_to_dev(pd->disk);
	struct packet_command cgc;
	struct scsi_sense_hdr sshdr;
	write_param_page *wp;
	char buffer[128];
	int ret, size;

	/* doesn't apply to DVD+RW or DVD-RAM */
	if ((pd->mmc3_profile == 0x1a) || (pd->mmc3_profile == 0x12))
		return 0;

	memset(buffer, 0, sizeof(buffer));
	init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
	cgc.sshdr = &sshdr;
	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
	if (ret) {
		pkt_dump_sense(pd, &cgc);
		return ret;
	}

	size = 2 + get_unaligned_be16(&buffer[0]);
	pd->mode_offset = get_unaligned_be16(&buffer[6]);
	if (size > sizeof(buffer))
		size = sizeof(buffer);

	/*
	 * now get it all
	 */
	init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
	cgc.sshdr = &sshdr;
	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
	if (ret) {
		pkt_dump_sense(pd, &cgc);
		return ret;
	}

	/*
	 * write page is offset header + block descriptor length
	 */
	wp = (write_param_page *) &buffer[sizeof(struct mode_page_header) + pd->mode_offset];

	wp->fp = pd->settings.fp;
	wp->track_mode = pd->settings.track_mode;
	wp->write_type = pd->settings.write_type;
	wp->data_block_type = pd->settings.block_mode;

	wp->multi_session = 0;

#ifdef PACKET_USE_LS
	wp->link_size = 7;
	wp->ls_v = 1;
#endif

	if (wp->data_block_type == PACKET_BLOCK_MODE1) {
		wp->session_format = 0;
		wp->subhdr2 = 0x20;
	} else if (wp->data_block_type == PACKET_BLOCK_MODE2) {
		wp->session_format = 0x20;
		wp->subhdr2 = 8;
#if 0
		wp->mcn[0] = 0x80;
		memcpy(&wp->mcn[1], PACKET_MCN, sizeof(wp->mcn) - 1);
#endif
	} else {
		/*
		 * paranoia
		 */
		dev_err(ddev, "write mode wrong %d\n", wp->data_block_type);
		return 1;
	}
	wp->packet_size = cpu_to_be32(pd->settings.size >> 2);

	cgc.buflen = cgc.cmd[8] = size;
	ret = pkt_mode_select(pd, &cgc);
	if (ret) {
		pkt_dump_sense(pd, &cgc);
		return ret;
	}

	pkt_print_settings(pd);
	return 0;
}

/*
 * 1 -- we can write to this track, 0 -- we can't
 */
static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti)
{
	struct device *ddev = disk_to_dev(pd->disk);

	switch (pd->mmc3_profile) {
		case 0x1a: /* DVD+RW */
		case 0x12: /* DVD-RAM */
			/* The track is always writable on DVD+RW/DVD-RAM */
			return 1;
		default:
			break;
	}

	if (!ti->packet || !ti->fp)
		return 0;

	/*
	 * "good" settings as per Mt Fuji.
	 */
	if (ti->rt == 0 && ti->blank == 0)
		return 1;

	if (ti->rt == 0 && ti->blank == 1)
		return 1;

	if (ti->rt == 1 && ti->blank == 0)
		return 1;

	dev_err(ddev, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
	return 0;
}

/*
 * 1 -- we can write to this disc, 0 -- we can't
 */
static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di)
{
	struct device *ddev = disk_to_dev(pd->disk);

	switch (pd->mmc3_profile) {
		case 0x0a: /* CD-RW */
		case 0xffff: /* MMC3 not supported */
			break;
		case 0x1a: /* DVD+RW */
		case 0x13: /* DVD-RW */
		case 0x12: /* DVD-RAM */
			return 1;
		default:
			dev_dbg(ddev, "Wrong disc profile (%x)\n", pd->mmc3_profile);
			return 0;
	}

	/*
	 * for disc type 0xff we should probably reserve a new track.
	 * but i'm not sure, should we leave this to user apps? probably.
	 */
	if (di->disc_type == 0xff) {
		dev_notice(ddev, "unknown disc - no track?\n");
		return 0;
	}

	if (di->disc_type != 0x20 && di->disc_type != 0) {
		dev_err(ddev, "wrong disc type (%x)\n", di->disc_type);
		return 0;
	}

	if (di->erasable == 0) {
		dev_err(ddev, "disc not erasable\n");
		return 0;
	}

	if (di->border_status == PACKET_SESSION_RESERVED) {
		dev_err(ddev, "can't write to last track (reserved)\n");
		return 0;
	}

	return 1;
}

static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
{
	struct device *ddev = disk_to_dev(pd->disk);
	struct packet_command cgc;
	unsigned char buf[12];
	disc_information di;
	track_information ti;
	int ret, track;

	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
	cgc.cmd[0] = GPCMD_GET_CONFIGURATION;
	cgc.cmd[8] = 8;
	ret = pkt_generic_packet(pd, &cgc);
	pd->mmc3_profile = ret ? 0xffff : get_unaligned_be16(&buf[6]);

	memset(&di, 0, sizeof(disc_information));
	memset(&ti, 0, sizeof(track_information));

	ret = pkt_get_disc_info(pd, &di);
	if (ret) {
		dev_err(ddev, "failed get_disc\n");
		return ret;
	}

	if (!pkt_writable_disc(pd, &di))
		return -EROFS;

	pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;

	track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
	ret = pkt_get_track_info(pd, track, 1, &ti);
	if (ret) {
		dev_err(ddev, "failed get_track\n");
		return ret;
	}

	if (!pkt_writable_track(pd, &ti)) {
		dev_err(ddev, "can't write to this track\n");
		return -EROFS;
	}

	/*
	 * we keep packet size in 512 byte units, makes it easier to
	 * deal with request calculations.
	 */
	pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2;
	if (pd->settings.size == 0) {
		dev_notice(ddev, "detected zero packet size!\n");
		return -ENXIO;
	}
	if (pd->settings.size > PACKET_MAX_SECTORS) {
		dev_err(ddev, "packet size is too big\n");
		return -EROFS;
	}
	pd->settings.fp = ti.fp;
	pd->offset = (be32_to_cpu(ti.track_start) << 2) & (pd->settings.size - 1);

	if (ti.nwa_v) {
		pd->nwa = be32_to_cpu(ti.next_writable);
		set_bit(PACKET_NWA_VALID, &pd->flags);
	}

	/*
	 * in theory we could use lra on -RW media as well and just zero
	 * blocks that haven't been written yet, but in practice that
	 * is just a no-go. we'll use that for -R, naturally.
	 */
	if (ti.lra_v) {
		pd->lra = be32_to_cpu(ti.last_rec_address);
		set_bit(PACKET_LRA_VALID, &pd->flags);
	} else {
		pd->lra = 0xffffffff;
		set_bit(PACKET_LRA_VALID, &pd->flags);
	}

	/*
	 * fine for now
	 */
	pd->settings.link_loss = 7;
	pd->settings.write_type = 0;	/* packet */
	pd->settings.track_mode = ti.track_mode;

	/*
	 * mode1 or mode2 disc
	 */
	switch (ti.data_mode) {
		case PACKET_MODE1:
			pd->settings.block_mode = PACKET_BLOCK_MODE1;
			break;
		case PACKET_MODE2:
			pd->settings.block_mode = PACKET_BLOCK_MODE2;
			break;
		default:
			dev_err(ddev, "unknown data mode\n");
			return -EROFS;
	}
	return 0;
}

/*
 * enable/disable write caching on drive
 */
static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd)
{
	struct device *ddev = disk_to_dev(pd->disk);
	struct packet_command cgc;
	struct scsi_sense_hdr sshdr;
	unsigned char buf[64];
	bool set = IS_ENABLED(CONFIG_CDROM_PKTCDVD_WCACHE);
	int ret;

	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
	cgc.sshdr = &sshdr;
	cgc.buflen = pd->mode_offset + 12;

	/*
	 * caching mode page might not be there, so quiet this command
	 */
	cgc.quiet = 1;

	ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
	if (ret)
		return ret;

	/*
	 * use drive write caching -- we need deferred error handling to be
	 * able to successfully recover with this option (drive will return good
	 * status as soon as the cdb is validated).
	 */
	buf[pd->mode_offset + 10] |= (set << 2);

	cgc.buflen = cgc.cmd[8] = 2 + get_unaligned_be16(&buf[0]);
	ret = pkt_mode_select(pd, &cgc);
	if (ret) {
		dev_err(ddev, "write caching control failed\n");
		pkt_dump_sense(pd, &cgc);
	} else if (!ret && set)
		dev_notice(ddev, "enabled write caching\n");
	return ret;
}

static int pkt_lock_door(struct pktcdvd_device *pd, int lockflag)
{
	struct packet_command cgc;

	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
	cgc.cmd[0] = GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL;
	cgc.cmd[4] = lockflag ? 1 : 0;
	return pkt_generic_packet(pd, &cgc);
}

/*
 * Returns drive maximum write speed
 */
static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
						unsigned *write_speed)
{
	struct packet_command cgc;
	struct scsi_sense_hdr sshdr;
	unsigned char buf[256+18];
	unsigned char *cap_buf;
	int ret, offset;

	cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
	cgc.sshdr = &sshdr;

	ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
	if (ret) {
		cgc.buflen = pd->mode_offset + cap_buf[1] + 2 +
			     sizeof(struct mode_page_header);
		ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
		if (ret) {
			pkt_dump_sense(pd, &cgc);
			return ret;
		}
	}

	offset = 20;			    /* Obsoleted field, used by older drives */
	if (cap_buf[1] >= 28)
		offset = 28;		    /* Current write speed selected */
	if (cap_buf[1] >= 30) {
		/* If the drive reports at least one "Logical Unit Write
		 * Speed Performance Descriptor Block", use the information
		 * in the first block. (contains the highest speed)
		 */
		int num_spdb = get_unaligned_be16(&cap_buf[30]);
		if (num_spdb > 0)
			offset = 34;
	}

	*write_speed = get_unaligned_be16(&cap_buf[offset]);
	return 0;
}

/* These tables from cdrecord - I don't have orange book */
/* standard speed CD-RW (1-4x) */
static char clv_to_speed[16] = {
	/* 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 */
	   0, 2, 4, 6, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
};
/* high speed CD-RW (-10x) */
static char hs_clv_to_speed[16] = {
	/* 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 */
	   0, 2, 4, 6, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
};
/* ultra high speed CD-RW */
static char us_clv_to_speed[16] = {
	/* 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 */
	   0, 2, 4, 8, 0, 0,16, 0,24,32,40,48, 0, 0, 0, 0
};

/*
 * reads the maximum media speed from ATIP
 */
static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
						unsigned *speed)
{
	struct device *ddev = disk_to_dev(pd->disk);
	struct packet_command cgc;
	struct scsi_sense_hdr sshdr;
	unsigned char buf[64];
	unsigned int size, st, sp;
	int ret;

	init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
	cgc.sshdr = &sshdr;
	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
	cgc.cmd[1] = 2;
	cgc.cmd[2] = 4; /* READ ATIP */
	cgc.cmd[8] = 2;
	ret = pkt_generic_packet(pd, &cgc);
	if (ret) {
		pkt_dump_sense(pd, &cgc);
		return ret;
	}
	size = 2 + get_unaligned_be16(&buf[0]);
	if (size > sizeof(buf))
		size = sizeof(buf);

	init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
	cgc.sshdr = &sshdr;
	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
	cgc.cmd[1] = 2;
	cgc.cmd[2] = 4;
	cgc.cmd[8] = size;
	ret = pkt_generic_packet(pd, &cgc);
	if (ret) {
		pkt_dump_sense(pd, &cgc);
		return ret;
	}

	if (!(buf[6] & 0x40)) {
		dev_notice(ddev, "disc type is not CD-RW\n");
		return 1;
	}
	if (!(buf[6] & 0x4)) {
		dev_notice(ddev, "A1 values on media are not valid, maybe not CDRW?\n");
		return 1;
	}

	st = (buf[6] >> 3) & 0x7; /* disc sub-type */

	sp = buf[16] & 0xf; /* max speed from ATIP A1 field */

	/* Info from cdrecord */
	switch (st) {
		case 0: /* standard speed */
			*speed = clv_to_speed[sp];
			break;
		case 1: /* high speed */
			*speed = hs_clv_to_speed[sp];
			break;
		case 2: /* ultra high speed */
			*speed = us_clv_to_speed[sp];
			break;
		default:
			dev_notice(ddev, "unknown disc sub-type %d\n", st);
			return 1;
	}
	if (*speed) {
		dev_info(ddev, "maximum media speed: %d\n", *speed);
		return 0;
	} else {
		dev_notice(ddev, "unknown speed %d for sub-type %d\n", sp, st);
		return 1;
	}
}

static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
{
	struct device *ddev = disk_to_dev(pd->disk);
	struct packet_command cgc;
	struct scsi_sense_hdr sshdr;
	int ret;

	dev_dbg(ddev, "Performing OPC\n");

	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
	cgc.sshdr = &sshdr;
	cgc.timeout = 60*HZ;
	cgc.cmd[0] = GPCMD_SEND_OPC;
	cgc.cmd[1] = 1;
	ret = pkt_generic_packet(pd, &cgc);
	if (ret)
		pkt_dump_sense(pd, &cgc);
	return ret;
}

static int pkt_open_write(struct pktcdvd_device *pd)
{
	struct device *ddev = disk_to_dev(pd->disk);
	int ret;
	unsigned int write_speed, media_write_speed, read_speed;

	ret = pkt_probe_settings(pd);
	if (ret) {
		dev_dbg(ddev, "failed probe\n");
		return ret;
	}

	ret = pkt_set_write_settings(pd);
	if (ret) {
		dev_notice(ddev, "failed saving write settings\n");
		return -EIO;
	}

	pkt_write_caching(pd);

	ret = pkt_get_max_speed(pd, &write_speed);
	if (ret)
		write_speed = 16 * 177;
	switch (pd->mmc3_profile) {
		case 0x13: /* DVD-RW */
		case 0x1a: /* DVD+RW */
		case 0x12: /* DVD-RAM */
			dev_notice(ddev, "write speed %ukB/s\n", write_speed);
			break;
		default:
			ret = pkt_media_speed(pd, &media_write_speed);
			if (ret)
				media_write_speed = 16;
			write_speed = min(write_speed, media_write_speed * 177);
			dev_notice(ddev, "write speed %ux\n", write_speed / 176);
			break;
	}
	read_speed = write_speed;

	ret = pkt_set_speed(pd, write_speed, read_speed);
	if (ret) {
		dev_notice(ddev, "couldn't set write speed\n");
		return -EIO;
	}
	pd->write_speed = write_speed;
	pd->read_speed = read_speed;

	ret = pkt_perform_opc(pd);
	if (ret)
		dev_notice(ddev, "Optimum Power Calibration failed\n");

	return 0;
}

/*
 * called at open time.
 */
static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
{
	struct device *ddev = disk_to_dev(pd->disk);
	int ret;
	long lba;
	struct request_queue *q;
	struct block_device *bdev;

	/*
	 * We need to re-open the cdrom device without O_NONBLOCK to be able
	 * to read/write from/to it. It is already opened in O_NONBLOCK mode
	 * so open should not fail.
	 */
	bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd,
				 NULL);
	if (IS_ERR(bdev)) {
		ret = PTR_ERR(bdev);
		goto out;
	}

	ret = pkt_get_last_written(pd, &lba);
	if (ret) {
		dev_err(ddev, "pkt_get_last_written failed\n");
		goto out_putdev;
	}

	set_capacity(pd->disk, lba << 2);
	set_capacity_and_notify(pd->bdev->bd_disk, lba << 2);

	q = bdev_get_queue(pd->bdev);
	if (write) {
		ret = pkt_open_write(pd);
		if (ret)
			goto out_putdev;
		/*
		 * Some CDRW drives can not handle writes larger than one packet,
		 * even if the size is a multiple of the packet size.
		 */
		blk_queue_max_hw_sectors(q, pd->settings.size);
		set_bit(PACKET_WRITABLE, &pd->flags);
	} else {
		pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
		clear_bit(PACKET_WRITABLE, &pd->flags);
	}

	ret = pkt_set_segment_merging(pd, q);
	if (ret)
		goto out_putdev;

	if (write) {
		if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) {
			dev_err(ddev, "not enough memory for buffers\n");
			ret = -ENOMEM;
			goto out_putdev;
		}
		dev_info(ddev, "%lukB available on disc\n", lba << 1);
	}

	return 0;

out_putdev:
	blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
out:
	return ret;
}

/*
 * called when the device is closed. makes sure that the device flushes
 * the internal cache before we close.
 */
static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
{
	struct device *ddev = disk_to_dev(pd->disk);

	if (flush && pkt_flush_cache(pd))
		dev_notice(ddev, "not flushing cache\n");

	pkt_lock_door(pd, 0);

	pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
	blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL);

	pkt_shrink_pktlist(pd);
}

static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
{
	if (dev_minor >= MAX_WRITERS)
		return NULL;

	dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
	return pkt_devs[dev_minor];
}

static int pkt_open(struct gendisk *disk, fmode_t mode)
{
	struct pktcdvd_device *pd = NULL;
	int ret;

	mutex_lock(&pktcdvd_mutex);
	mutex_lock(&ctl_mutex);
	pd = pkt_find_dev_from_minor(disk->first_minor);
	if (!pd) {
		ret = -ENODEV;
		goto out;
	}
	BUG_ON(pd->refcnt < 0);

	pd->refcnt++;
	if (pd->refcnt > 1) {
		if ((mode & FMODE_WRITE) &&
		    !test_bit(PACKET_WRITABLE, &pd->flags)) {
			ret = -EBUSY;
			goto out_dec;
		}
	} else {
		ret = pkt_open_dev(pd, mode & FMODE_WRITE);
		if (ret)
			goto out_dec;
		/*
		 * needed here as well, since ext2 (among others) may change
		 * the blocksize at mount time
		 */
		set_blocksize(disk->part0, CD_FRAMESIZE);
	}

	mutex_unlock(&ctl_mutex);
	mutex_unlock(&pktcdvd_mutex);
	return 0;

out_dec:
	pd->refcnt--;
out:
	mutex_unlock(&ctl_mutex);
	mutex_unlock(&pktcdvd_mutex);
	return ret;
}

static void pkt_release(struct gendisk *disk)
{
	struct pktcdvd_device *pd = disk->private_data;

	mutex_lock(&pktcdvd_mutex);
	mutex_lock(&ctl_mutex);
	pd->refcnt--;
	BUG_ON(pd->refcnt < 0);
	if (pd->refcnt == 0) {
		int flush = test_bit(PACKET_WRITABLE, &pd->flags);
		pkt_release_dev(pd, flush);
	}
	mutex_unlock(&ctl_mutex);
	mutex_unlock(&pktcdvd_mutex);
}


static void pkt_end_io_read_cloned(struct bio *bio)
{
	struct packet_stacked_data *psd = bio->bi_private;
	struct pktcdvd_device *pd = psd->pd;

	psd->bio->bi_status = bio->bi_status;
	bio_put(bio);
	bio_endio(psd->bio);
	mempool_free(psd, &psd_pool);
	pkt_bio_finished(pd);
}

static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
{
	struct bio *cloned_bio =
		bio_alloc_clone(pd->bdev, bio, GFP_NOIO, &pkt_bio_set);
	struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);

	psd->pd = pd;
	psd->bio = bio;
	cloned_bio->bi_private = psd;
	cloned_bio->bi_end_io = pkt_end_io_read_cloned;
	pd->stats.secs_r += bio_sectors(bio);
	pkt_queue_bio(pd, cloned_bio);
}

static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
{
	struct pktcdvd_device *pd = q->queuedata;
	sector_t zone;
	struct packet_data *pkt;
	int was_empty, blocked_bio;
	struct pkt_rb_node *node;

	zone = get_zone(bio->bi_iter.bi_sector, pd);

	/*
	 * If we find a matching packet in state WAITING or READ_WAIT, we can
	 * just append this bio to that packet.
	 */
	spin_lock(&pd->cdrw.active_list_lock);
	blocked_bio = 0;
	list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
		if (pkt->sector == zone) {
			spin_lock(&pkt->lock);
			if ((pkt->state == PACKET_WAITING_STATE) ||
			    (pkt->state == PACKET_READ_WAIT_STATE)) {
				bio_list_add(&pkt->orig_bios, bio);
				pkt->write_size +=
					bio->bi_iter.bi_size / CD_FRAMESIZE;
				if ((pkt->write_size >= pkt->frames) &&
				    (pkt->state == PACKET_WAITING_STATE)) {
					atomic_inc(&pkt->run_sm);
					wake_up(&pd->wqueue);
				}
				spin_unlock(&pkt->lock);
				spin_unlock(&pd->cdrw.active_list_lock);
				return;
			} else {
				blocked_bio = 1;
			}
			spin_unlock(&pkt->lock);
		}
	}
	spin_unlock(&pd->cdrw.active_list_lock);

	/*
	 * Test if there is enough room left in the bio work queue
	 * (queue size >= congestion on mark).
	 * If not, wait till the work queue size is below the congestion off mark.
	 */
	spin_lock(&pd->lock);
	if (pd->write_congestion_on > 0
	    && pd->bio_queue_size >= pd->write_congestion_on) {
		struct wait_bit_queue_entry wqe;

		init_wait_var_entry(&wqe, &pd->congested, 0);
		for (;;) {
			prepare_to_wait_event(__var_waitqueue(&pd->congested),
					      &wqe.wq_entry,
					      TASK_UNINTERRUPTIBLE);
			if (pd->bio_queue_size <= pd->write_congestion_off)
				break;
			pd->congested = true;
			spin_unlock(&pd->lock);
			schedule();
			spin_lock(&pd->lock);
		}
	}
	spin_unlock(&pd->lock);

	/*
	 * No matching packet found. Store the bio in the work queue.
	 */
	node = mempool_alloc(&pd->rb_pool, GFP_NOIO);
	node->bio = bio;
	spin_lock(&pd->lock);
	BUG_ON(pd->bio_queue_size < 0);
	was_empty = (pd->bio_queue_size == 0);
	pkt_rbtree_insert(pd, node);
	spin_unlock(&pd->lock);

	/*
	 * Wake up the worker thread.
	 */
	atomic_set(&pd->scan_queue, 1);
	if (was_empty) {
		/* This wake_up is required for correct operation */
		wake_up(&pd->wqueue);
	} else if (!list_empty(&pd->cdrw.pkt_free_list) && !blocked_bio) {
		/*
		 * This wake up is not required for correct operation,
		 * but improves performance in some cases.
		 */
		wake_up(&pd->wqueue);
	}
}

static void pkt_submit_bio(struct bio *bio)
{
	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata;
	struct device *ddev = disk_to_dev(pd->disk);
	struct bio *split;

	bio = bio_split_to_limits(bio);
	if (!bio)
		return;

	dev_dbg(ddev, "start = %6llx stop = %6llx\n",
		bio->bi_iter.bi_sector, bio_end_sector(bio));

	/*
	 * Clone READ bios so we can have our own bi_end_io callback.
	 */
	if (bio_data_dir(bio) == READ) {
		pkt_make_request_read(pd, bio);
		return;
	}

	if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
		dev_notice(ddev, "WRITE for ro device (%llu)\n", bio->bi_iter.bi_sector);
		goto end_io;
	}

	if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) {
		dev_err(ddev, "wrong bio size\n");
		goto end_io;
	}

	do {
		sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
		sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);

		if (last_zone != zone) {
			BUG_ON(last_zone != zone + pd->settings.size);

			split = bio_split(bio, last_zone -
					  bio->bi_iter.bi_sector,
					  GFP_NOIO, &pkt_bio_set);
			bio_chain(split, bio);
		} else {
			split = bio;
		}

		pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
	} while (split != bio);

	return;
end_io:
	bio_io_error(bio);
}

static void pkt_init_queue(struct pktcdvd_device *pd)
{
	struct request_queue *q = pd->disk->queue;

	blk_queue_logical_block_size(q, CD_FRAMESIZE);
	blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
	q->queuedata = pd;
}

static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
{
	struct device *ddev = disk_to_dev(pd->disk);
	int i;
	struct block_device *bdev;
	struct scsi_device *sdev;

	if (pd->pkt_dev == dev) {
		dev_err(ddev, "recursive setup not allowed\n");
		return -EBUSY;
	}
	for (i = 0; i < MAX_WRITERS; i++) {
		struct pktcdvd_device *pd2 = pkt_devs[i];
		if (!pd2)
			continue;
		if (pd2->bdev->bd_dev == dev) {
			dev_err(ddev, "%pg already setup\n", pd2->bdev);
			return -EBUSY;
		}
		if (pd2->pkt_dev == dev) {
			dev_err(ddev, "can't chain pktcdvd devices\n");
			return -EBUSY;
		}
	}

	bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL, NULL);
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);
	sdev = scsi_device_from_queue(bdev->bd_disk->queue);
	if (!sdev) {
		blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
		return -EINVAL;
	}
	put_device(&sdev->sdev_gendev);

	/* This is safe, since we have a reference from open(). */
	__module_get(THIS_MODULE);

	pd->bdev = bdev;
	set_blocksize(bdev, CD_FRAMESIZE);

	pkt_init_queue(pd);

	atomic_set(&pd->cdrw.pending_bios, 0);
	pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name);
	if (IS_ERR(pd->cdrw.thread)) {
		dev_err(ddev, "can't start kernel thread\n");
		goto out_mem;
	}

	proc_create_single_data(pd->disk->disk_name, 0, pkt_proc, pkt_seq_show, pd);
	dev_notice(ddev, "writer mapped to %pg\n", bdev);
	return 0;

out_mem:
	blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
	/* This is safe: open() is still holding a reference. */
	module_put(THIS_MODULE);
	return -ENOMEM;
}

static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg)
{
	struct pktcdvd_device *pd = bdev->bd_disk->private_data;
	struct device *ddev = disk_to_dev(pd->disk);
	int ret;

	dev_dbg(ddev, "cmd %x, dev %d:%d\n", cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));

	mutex_lock(&pktcdvd_mutex);
	switch (cmd) {
	case CDROMEJECT:
		/*
		 * The door gets locked when the device is opened, so we
		 * have to unlock it or else the eject command fails.
		 */
		if (pd->refcnt == 1)
			pkt_lock_door(pd, 0);
		fallthrough;
	/*
	 * forward selected CDROM ioctls to CD-ROM, for UDF
	 */
	case CDROMMULTISESSION:
	case CDROMREADTOCENTRY:
	case CDROM_LAST_WRITTEN:
	case CDROM_SEND_PACKET:
	case SCSI_IOCTL_SEND_COMMAND:
		if (!bdev->bd_disk->fops->ioctl)
			ret = -ENOTTY;
		else
			ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
		break;
	default:
		dev_dbg(ddev, "Unknown ioctl (%x)\n", cmd);
		ret = -ENOTTY;
	}
	mutex_unlock(&pktcdvd_mutex);

	return ret;
}

static unsigned int pkt_check_events(struct gendisk *disk,
				     unsigned int clearing)
{
	struct pktcdvd_device *pd = disk->private_data;
	struct gendisk *attached_disk;

	if (!pd)
		return 0;
	if (!pd->bdev)
		return 0;
	attached_disk = pd->bdev->bd_disk;
	if (!attached_disk || !attached_disk->fops->check_events)
		return 0;
	return attached_disk->fops->check_events(attached_disk, clearing);
}

static char *pkt_devnode(struct gendisk *disk, umode_t *mode)
{
	return kasprintf(GFP_KERNEL, "pktcdvd/%s", disk->disk_name);
}

static const struct block_device_operations pktcdvd_ops = {
	.owner =		THIS_MODULE,
	.submit_bio =		pkt_submit_bio,
	.open =			pkt_open,
	.release =		pkt_release,
	.ioctl =		pkt_ioctl,
	.compat_ioctl =		blkdev_compat_ptr_ioctl,
	.check_events =		pkt_check_events,
	.devnode =		pkt_devnode,
};

/*
 * Set up mapping from pktcdvd device to CD-ROM device.
 */
static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
{
	int idx;
	int ret = -ENOMEM;
	struct pktcdvd_device *pd;
	struct gendisk *disk;

	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);

	for (idx = 0; idx < MAX_WRITERS; idx++)
		if (!pkt_devs[idx])
			break;
	if (idx == MAX_WRITERS) {
		pr_err("max %d writers supported\n", MAX_WRITERS);
		ret = -EBUSY;
		goto out_mutex;
	}

	pd = kzalloc(sizeof(struct pktcdvd_device), GFP_KERNEL);
	if (!pd)
		goto out_mutex;

	ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE,
					sizeof(struct pkt_rb_node));
	if (ret)
		goto out_mem;

	INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
	INIT_LIST_HEAD(&pd->cdrw.pkt_active_list);
	spin_lock_init(&pd->cdrw.active_list_lock);

	spin_lock_init(&pd->lock);
	spin_lock_init(&pd->iosched.lock);
	bio_list_init(&pd->iosched.read_queue);
	bio_list_init(&pd->iosched.write_queue);
	init_waitqueue_head(&pd->wqueue);
	pd->bio_queue = RB_ROOT;

	pd->write_congestion_on  = write_congestion_on;
	pd->write_congestion_off = write_congestion_off;

	ret = -ENOMEM;
	disk = blk_alloc_disk(NUMA_NO_NODE);
	if (!disk)
		goto out_mem;
	pd->disk = disk;
	disk->major = pktdev_major;
	disk->first_minor = idx;
	disk->minors = 1;
	disk->fops = &pktcdvd_ops;
	disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART;
	snprintf(disk->disk_name, sizeof(disk->disk_name), DRIVER_NAME"%d", idx);
	disk->private_data = pd;

	pd->pkt_dev = MKDEV(pktdev_major, idx);
	ret = pkt_new_dev(pd, dev);
	if (ret)
		goto out_mem2;

	/* inherit events of the host device */
	disk->events = pd->bdev->bd_disk->events;

	ret = add_disk(disk);
	if (ret)
		goto out_mem2;

	pkt_sysfs_dev_new(pd);
	pkt_debugfs_dev_new(pd);

	pkt_devs[idx] = pd;
	if (pkt_dev)
		*pkt_dev = pd->pkt_dev;

	mutex_unlock(&ctl_mutex);
	return 0;

out_mem2:
	put_disk(disk);
out_mem:
	mempool_exit(&pd->rb_pool);
	kfree(pd);
out_mutex:
	mutex_unlock(&ctl_mutex);
	pr_err("setup of pktcdvd device failed\n");
	return ret;
}

/*
 * Tear down mapping from pktcdvd device to CD-ROM device.
 */
static int pkt_remove_dev(dev_t pkt_dev)
{
	struct pktcdvd_device *pd;
	struct device *ddev;
	int idx;
	int ret = 0;

	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);

	for (idx = 0; idx < MAX_WRITERS; idx++) {
		pd = pkt_devs[idx];
		if (pd && (pd->pkt_dev == pkt_dev))
			break;
	}
	if (idx == MAX_WRITERS) {
		pr_debug("dev not setup\n");
		ret = -ENXIO;
		goto out;
	}

	if (pd->refcnt > 0) {
		ret = -EBUSY;
		goto out;
	}

	ddev = disk_to_dev(pd->disk);

	if (!IS_ERR(pd->cdrw.thread))
		kthread_stop(pd->cdrw.thread);

	pkt_devs[idx] = NULL;

	pkt_debugfs_dev_remove(pd);
	pkt_sysfs_dev_remove(pd);

	blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY);

	remove_proc_entry(pd->disk->disk_name, pkt_proc);
	dev_notice(ddev, "writer unmapped\n");

	del_gendisk(pd->disk);
	put_disk(pd->disk);

	mempool_exit(&pd->rb_pool);
	kfree(pd);

	/* This is safe: open() is still holding a reference. */
	module_put(THIS_MODULE);

out:
	mutex_unlock(&ctl_mutex);
	return ret;
}

static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
{
	struct pktcdvd_device *pd;

	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);

	pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index);
	if (pd) {
		ctrl_cmd->dev = new_encode_dev(pd->bdev->bd_dev);
		ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev);
	} else {
		ctrl_cmd->dev = 0;
		ctrl_cmd->pkt_dev = 0;
	}
	ctrl_cmd->num_devices = MAX_WRITERS;

	mutex_unlock(&ctl_mutex);
}

static long pkt_ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	struct pkt_ctrl_command ctrl_cmd;
	int ret = 0;
	dev_t pkt_dev = 0;

	if (cmd != PACKET_CTRL_CMD)
		return -ENOTTY;

	if (copy_from_user(&ctrl_cmd, argp, sizeof(struct pkt_ctrl_command)))
		return -EFAULT;

	switch (ctrl_cmd.command) {
	case PKT_CTRL_CMD_SETUP:
		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;
		ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev);
		ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev);
		break;
	case PKT_CTRL_CMD_TEARDOWN:
		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;
		ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev));
		break;
	case PKT_CTRL_CMD_STATUS:
		pkt_get_status(&ctrl_cmd);
		break;
	default:
		return -ENOTTY;
	}

	if (copy_to_user(argp, &ctrl_cmd, sizeof(struct pkt_ctrl_command)))
		return -EFAULT;
	return ret;
}

#ifdef CONFIG_COMPAT
static long pkt_ctl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	return pkt_ctl_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
}
#endif

static const struct file_operations pkt_ctl_fops = {
	.open		= nonseekable_open,
	.unlocked_ioctl	= pkt_ctl_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= pkt_ctl_compat_ioctl,
#endif
	.owner		= THIS_MODULE,
	.llseek		= no_llseek,
};

static struct miscdevice pkt_misc = {
	.minor 		= MISC_DYNAMIC_MINOR,
	.name  		= DRIVER_NAME,
	.nodename	= "pktcdvd/control",
	.fops  		= &pkt_ctl_fops
};

static int __init pkt_init(void)
{
	int ret;

	mutex_init(&ctl_mutex);

	ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE,
				    sizeof(struct packet_stacked_data));
	if (ret)
		return ret;
	ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0);
	if (ret) {
		mempool_exit(&psd_pool);
		return ret;
	}

	ret = register_blkdev(pktdev_major, DRIVER_NAME);
	if (ret < 0) {
		pr_err("unable to register block device\n");
		goto out2;
	}
	if (!pktdev_major)
		pktdev_major = ret;

	ret = pkt_sysfs_init();
	if (ret)
		goto out;

	pkt_debugfs_init();

	ret = misc_register(&pkt_misc);
	if (ret) {
		pr_err("unable to register misc device\n");
		goto out_misc;
	}

	pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL);

	return 0;

out_misc:
	pkt_debugfs_cleanup();
	pkt_sysfs_cleanup();
out:
	unregister_blkdev(pktdev_major, DRIVER_NAME);
out2:
	mempool_exit(&psd_pool);
	bioset_exit(&pkt_bio_set);
	return ret;
}

static void __exit pkt_exit(void)
{
	remove_proc_entry("driver/"DRIVER_NAME, NULL);
	misc_deregister(&pkt_misc);

	pkt_debugfs_cleanup();
	pkt_sysfs_cleanup();

	unregister_blkdev(pktdev_major, DRIVER_NAME);
	mempool_exit(&psd_pool);
	bioset_exit(&pkt_bio_set);
}

MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
MODULE_AUTHOR("Jens Axboe <axboe@suse.de>");
MODULE_LICENSE("GPL");

module_init(pkt_init);
module_exit(pkt_exit);