summaryrefslogtreecommitdiff
path: root/drivers/nvme/host/core.c
blob: add040168e67e20aa241c87f9c1a013c8dea895a (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
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
// SPDX-License-Identifier: GPL-2.0
/*
 * NVM Express device driver
 * Copyright (c) 2011-2014, Intel Corporation.
 */

#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/compat.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/hdreg.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/list_sort.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/pr.h>
#include <linux/ptrace.h>
#include <linux/nvme_ioctl.h>
#include <linux/pm_qos.h>
#include <asm/unaligned.h>

#include "nvme.h"
#include "fabrics.h"

#define CREATE_TRACE_POINTS
#include "trace.h"

#define NVME_MINORS		(1U << MINORBITS)

unsigned int admin_timeout = 60;
module_param(admin_timeout, uint, 0644);
MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands");
EXPORT_SYMBOL_GPL(admin_timeout);

unsigned int nvme_io_timeout = 30;
module_param_named(io_timeout, nvme_io_timeout, uint, 0644);
MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
EXPORT_SYMBOL_GPL(nvme_io_timeout);

static unsigned char shutdown_timeout = 5;
module_param(shutdown_timeout, byte, 0644);
MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");

static u8 nvme_max_retries = 5;
module_param_named(max_retries, nvme_max_retries, byte, 0644);
MODULE_PARM_DESC(max_retries, "max number of retries a command may have");

static unsigned long default_ps_max_latency_us = 100000;
module_param(default_ps_max_latency_us, ulong, 0644);
MODULE_PARM_DESC(default_ps_max_latency_us,
		 "max power saving latency for new devices; use PM QOS to change per device");

static bool force_apst;
module_param(force_apst, bool, 0644);
MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off");

static bool streams;
module_param(streams, bool, 0644);
MODULE_PARM_DESC(streams, "turn on support for Streams write directives");

/*
 * nvme_wq - hosts nvme related works that are not reset or delete
 * nvme_reset_wq - hosts nvme reset works
 * nvme_delete_wq - hosts nvme delete works
 *
 * nvme_wq will host works such as scan, aen handling, fw activation,
 * keep-alive, periodic reconnects etc. nvme_reset_wq
 * runs reset works which also flush works hosted on nvme_wq for
 * serialization purposes. nvme_delete_wq host controller deletion
 * works which flush reset works for serialization.
 */
struct workqueue_struct *nvme_wq;
EXPORT_SYMBOL_GPL(nvme_wq);

struct workqueue_struct *nvme_reset_wq;
EXPORT_SYMBOL_GPL(nvme_reset_wq);

struct workqueue_struct *nvme_delete_wq;
EXPORT_SYMBOL_GPL(nvme_delete_wq);

static LIST_HEAD(nvme_subsystems);
static DEFINE_MUTEX(nvme_subsystems_lock);

static DEFINE_IDA(nvme_instance_ida);
static dev_t nvme_chr_devt;
static struct class *nvme_class;
static struct class *nvme_subsys_class;

static int nvme_revalidate_disk(struct gendisk *disk);
static void nvme_put_subsystem(struct nvme_subsystem *subsys);
static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
					   unsigned nsid);

static void nvme_set_queue_dying(struct nvme_ns *ns)
{
	/*
	 * Revalidating a dead namespace sets capacity to 0. This will end
	 * buffered writers dirtying pages that can't be synced.
	 */
	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
		return;
	blk_set_queue_dying(ns->queue);
	/* Forcibly unquiesce queues to avoid blocking dispatch */
	blk_mq_unquiesce_queue(ns->queue);
	/*
	 * Revalidate after unblocking dispatchers that may be holding bd_butex
	 */
	revalidate_disk(ns->disk);
}

static void nvme_queue_scan(struct nvme_ctrl *ctrl)
{
	/*
	 * Only new queue scan work when admin and IO queues are both alive
	 */
	if (ctrl->state == NVME_CTRL_LIVE && ctrl->tagset)
		queue_work(nvme_wq, &ctrl->scan_work);
}

/*
 * Use this function to proceed with scheduling reset_work for a controller
 * that had previously been set to the resetting state. This is intended for
 * code paths that can't be interrupted by other reset attempts. A hot removal
 * may prevent this from succeeding.
 */
int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
{
	if (ctrl->state != NVME_CTRL_RESETTING)
		return -EBUSY;
	if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
		return -EBUSY;
	return 0;
}
EXPORT_SYMBOL_GPL(nvme_try_sched_reset);

int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
{
	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
		return -EBUSY;
	if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
		return -EBUSY;
	return 0;
}
EXPORT_SYMBOL_GPL(nvme_reset_ctrl);

int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
{
	int ret;

	ret = nvme_reset_ctrl(ctrl);
	if (!ret) {
		flush_work(&ctrl->reset_work);
		if (ctrl->state != NVME_CTRL_LIVE)
			ret = -ENETRESET;
	}

	return ret;
}
EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync);

static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
{
	dev_info(ctrl->device,
		 "Removing ctrl: NQN \"%s\"\n", ctrl->opts->subsysnqn);

	flush_work(&ctrl->reset_work);
	nvme_stop_ctrl(ctrl);
	nvme_remove_namespaces(ctrl);
	ctrl->ops->delete_ctrl(ctrl);
	nvme_uninit_ctrl(ctrl);
}

static void nvme_delete_ctrl_work(struct work_struct *work)
{
	struct nvme_ctrl *ctrl =
		container_of(work, struct nvme_ctrl, delete_work);

	nvme_do_delete_ctrl(ctrl);
}

int nvme_delete_ctrl(struct nvme_ctrl *ctrl)
{
	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING))
		return -EBUSY;
	if (!queue_work(nvme_delete_wq, &ctrl->delete_work))
		return -EBUSY;
	return 0;
}
EXPORT_SYMBOL_GPL(nvme_delete_ctrl);

static void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
{
	/*
	 * Keep a reference until nvme_do_delete_ctrl() complete,
	 * since ->delete_ctrl can free the controller.
	 */
	nvme_get_ctrl(ctrl);
	if (nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING))
		nvme_do_delete_ctrl(ctrl);
	nvme_put_ctrl(ctrl);
}

static blk_status_t nvme_error_status(u16 status)
{
	switch (status & 0x7ff) {
	case NVME_SC_SUCCESS:
		return BLK_STS_OK;
	case NVME_SC_CAP_EXCEEDED:
		return BLK_STS_NOSPC;
	case NVME_SC_LBA_RANGE:
	case NVME_SC_CMD_INTERRUPTED:
	case NVME_SC_NS_NOT_READY:
		return BLK_STS_TARGET;
	case NVME_SC_BAD_ATTRIBUTES:
	case NVME_SC_ONCS_NOT_SUPPORTED:
	case NVME_SC_INVALID_OPCODE:
	case NVME_SC_INVALID_FIELD:
	case NVME_SC_INVALID_NS:
		return BLK_STS_NOTSUPP;
	case NVME_SC_WRITE_FAULT:
	case NVME_SC_READ_ERROR:
	case NVME_SC_UNWRITTEN_BLOCK:
	case NVME_SC_ACCESS_DENIED:
	case NVME_SC_READ_ONLY:
	case NVME_SC_COMPARE_FAILED:
		return BLK_STS_MEDIUM;
	case NVME_SC_GUARD_CHECK:
	case NVME_SC_APPTAG_CHECK:
	case NVME_SC_REFTAG_CHECK:
	case NVME_SC_INVALID_PI:
		return BLK_STS_PROTECTION;
	case NVME_SC_RESERVATION_CONFLICT:
		return BLK_STS_NEXUS;
	case NVME_SC_HOST_PATH_ERROR:
		return BLK_STS_TRANSPORT;
	default:
		return BLK_STS_IOERR;
	}
}

static inline bool nvme_req_needs_retry(struct request *req)
{
	if (blk_noretry_request(req))
		return false;
	if (nvme_req(req)->status & NVME_SC_DNR)
		return false;
	if (nvme_req(req)->retries >= nvme_max_retries)
		return false;
	return true;
}

static void nvme_retry_req(struct request *req)
{
	struct nvme_ns *ns = req->q->queuedata;
	unsigned long delay = 0;
	u16 crd;

	/* The mask and shift result must be <= 3 */
	crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11;
	if (ns && crd)
		delay = ns->ctrl->crdt[crd - 1] * 100;

	nvme_req(req)->retries++;
	blk_mq_requeue_request(req, false);
	blk_mq_delay_kick_requeue_list(req->q, delay);
}

void nvme_complete_rq(struct request *req)
{
	blk_status_t status = nvme_error_status(nvme_req(req)->status);

	trace_nvme_complete_rq(req);

	nvme_cleanup_cmd(req);

	if (nvme_req(req)->ctrl->kas)
		nvme_req(req)->ctrl->comp_seen = true;

	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
		if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req))
			return;

		if (!blk_queue_dying(req->q)) {
			nvme_retry_req(req);
			return;
		}
	}

	nvme_trace_bio_complete(req, status);
	blk_mq_end_request(req, status);
}
EXPORT_SYMBOL_GPL(nvme_complete_rq);

bool nvme_cancel_request(struct request *req, void *data, bool reserved)
{
	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
				"Cancelling I/O %d", req->tag);

	/* don't abort one completed request */
	if (blk_mq_request_completed(req))
		return true;

	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
	blk_mq_force_complete_rq(req);
	return true;
}
EXPORT_SYMBOL_GPL(nvme_cancel_request);

bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
		enum nvme_ctrl_state new_state)
{
	enum nvme_ctrl_state old_state;
	unsigned long flags;
	bool changed = false;

	spin_lock_irqsave(&ctrl->lock, flags);

	old_state = ctrl->state;
	switch (new_state) {
	case NVME_CTRL_LIVE:
		switch (old_state) {
		case NVME_CTRL_NEW:
		case NVME_CTRL_RESETTING:
		case NVME_CTRL_CONNECTING:
			changed = true;
			/* FALLTHRU */
		default:
			break;
		}
		break;
	case NVME_CTRL_RESETTING:
		switch (old_state) {
		case NVME_CTRL_NEW:
		case NVME_CTRL_LIVE:
			changed = true;
			/* FALLTHRU */
		default:
			break;
		}
		break;
	case NVME_CTRL_CONNECTING:
		switch (old_state) {
		case NVME_CTRL_NEW:
		case NVME_CTRL_RESETTING:
			changed = true;
			/* FALLTHRU */
		default:
			break;
		}
		break;
	case NVME_CTRL_DELETING:
		switch (old_state) {
		case NVME_CTRL_LIVE:
		case NVME_CTRL_RESETTING:
		case NVME_CTRL_CONNECTING:
			changed = true;
			/* FALLTHRU */
		default:
			break;
		}
		break;
	case NVME_CTRL_DEAD:
		switch (old_state) {
		case NVME_CTRL_DELETING:
			changed = true;
			/* FALLTHRU */
		default:
			break;
		}
		break;
	default:
		break;
	}

	if (changed) {
		ctrl->state = new_state;
		wake_up_all(&ctrl->state_wq);
	}

	spin_unlock_irqrestore(&ctrl->lock, flags);
	if (changed && ctrl->state == NVME_CTRL_LIVE)
		nvme_kick_requeue_lists(ctrl);
	return changed;
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);

/*
 * Returns true for sink states that can't ever transition back to live.
 */
static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
{
	switch (ctrl->state) {
	case NVME_CTRL_NEW:
	case NVME_CTRL_LIVE:
	case NVME_CTRL_RESETTING:
	case NVME_CTRL_CONNECTING:
		return false;
	case NVME_CTRL_DELETING:
	case NVME_CTRL_DEAD:
		return true;
	default:
		WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
		return true;
	}
}

/*
 * Waits for the controller state to be resetting, or returns false if it is
 * not possible to ever transition to that state.
 */
bool nvme_wait_reset(struct nvme_ctrl *ctrl)
{
	wait_event(ctrl->state_wq,
		   nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) ||
		   nvme_state_terminal(ctrl));
	return ctrl->state == NVME_CTRL_RESETTING;
}
EXPORT_SYMBOL_GPL(nvme_wait_reset);

static void nvme_free_ns_head(struct kref *ref)
{
	struct nvme_ns_head *head =
		container_of(ref, struct nvme_ns_head, ref);

	nvme_mpath_remove_disk(head);
	ida_simple_remove(&head->subsys->ns_ida, head->instance);
	cleanup_srcu_struct(&head->srcu);
	nvme_put_subsystem(head->subsys);
	kfree(head);
}

static void nvme_put_ns_head(struct nvme_ns_head *head)
{
	kref_put(&head->ref, nvme_free_ns_head);
}

static void nvme_free_ns(struct kref *kref)
{
	struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);

	if (ns->ndev)
		nvme_nvm_unregister(ns);

	put_disk(ns->disk);
	nvme_put_ns_head(ns->head);
	nvme_put_ctrl(ns->ctrl);
	kfree(ns);
}

static void nvme_put_ns(struct nvme_ns *ns)
{
	kref_put(&ns->kref, nvme_free_ns);
}

static inline void nvme_clear_nvme_request(struct request *req)
{
	if (!(req->rq_flags & RQF_DONTPREP)) {
		nvme_req(req)->retries = 0;
		nvme_req(req)->flags = 0;
		req->rq_flags |= RQF_DONTPREP;
	}
}

struct request *nvme_alloc_request(struct request_queue *q,
		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
{
	unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
	struct request *req;

	if (qid == NVME_QID_ANY) {
		req = blk_mq_alloc_request(q, op, flags);
	} else {
		req = blk_mq_alloc_request_hctx(q, op, flags,
				qid ? qid - 1 : 0);
	}
	if (IS_ERR(req))
		return req;

	req->cmd_flags |= REQ_FAILFAST_DRIVER;
	nvme_clear_nvme_request(req);
	nvme_req(req)->cmd = cmd;

	return req;
}
EXPORT_SYMBOL_GPL(nvme_alloc_request);

static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
{
	struct nvme_command c;

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

	c.directive.opcode = nvme_admin_directive_send;
	c.directive.nsid = cpu_to_le32(NVME_NSID_ALL);
	c.directive.doper = NVME_DIR_SND_ID_OP_ENABLE;
	c.directive.dtype = NVME_DIR_IDENTIFY;
	c.directive.tdtype = NVME_DIR_STREAMS;
	c.directive.endir = enable ? NVME_DIR_ENDIR : 0;

	return nvme_submit_sync_cmd(ctrl->admin_q, &c, NULL, 0);
}

static int nvme_disable_streams(struct nvme_ctrl *ctrl)
{
	return nvme_toggle_streams(ctrl, false);
}

static int nvme_enable_streams(struct nvme_ctrl *ctrl)
{
	return nvme_toggle_streams(ctrl, true);
}

static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
				  struct streams_directive_params *s, u32 nsid)
{
	struct nvme_command c;

	memset(&c, 0, sizeof(c));
	memset(s, 0, sizeof(*s));

	c.directive.opcode = nvme_admin_directive_recv;
	c.directive.nsid = cpu_to_le32(nsid);
	c.directive.numd = cpu_to_le32(nvme_bytes_to_numd(sizeof(*s)));
	c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM;
	c.directive.dtype = NVME_DIR_STREAMS;

	return nvme_submit_sync_cmd(ctrl->admin_q, &c, s, sizeof(*s));
}

static int nvme_configure_directives(struct nvme_ctrl *ctrl)
{
	struct streams_directive_params s;
	int ret;

	if (!(ctrl->oacs & NVME_CTRL_OACS_DIRECTIVES))
		return 0;
	if (!streams)
		return 0;

	ret = nvme_enable_streams(ctrl);
	if (ret)
		return ret;

	ret = nvme_get_stream_params(ctrl, &s, NVME_NSID_ALL);
	if (ret)
		goto out_disable_stream;

	ctrl->nssa = le16_to_cpu(s.nssa);
	if (ctrl->nssa < BLK_MAX_WRITE_HINTS - 1) {
		dev_info(ctrl->device, "too few streams (%u) available\n",
					ctrl->nssa);
		goto out_disable_stream;
	}

	ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
	dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
	return 0;

out_disable_stream:
	nvme_disable_streams(ctrl);
	return ret;
}

/*
 * Check if 'req' has a write hint associated with it. If it does, assign
 * a valid namespace stream to the write.
 */
static void nvme_assign_write_stream(struct nvme_ctrl *ctrl,
				     struct request *req, u16 *control,
				     u32 *dsmgmt)
{
	enum rw_hint streamid = req->write_hint;

	if (streamid == WRITE_LIFE_NOT_SET || streamid == WRITE_LIFE_NONE)
		streamid = 0;
	else {
		streamid--;
		if (WARN_ON_ONCE(streamid > ctrl->nr_streams))
			return;

		*control |= NVME_RW_DTYPE_STREAMS;
		*dsmgmt |= streamid << 16;
	}

	if (streamid < ARRAY_SIZE(req->q->write_hints))
		req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9;
}

static inline void nvme_setup_flush(struct nvme_ns *ns,
		struct nvme_command *cmnd)
{
	cmnd->common.opcode = nvme_cmd_flush;
	cmnd->common.nsid = cpu_to_le32(ns->head->ns_id);
}

static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
		struct nvme_command *cmnd)
{
	unsigned short segments = blk_rq_nr_discard_segments(req), n = 0;
	struct nvme_dsm_range *range;
	struct bio *bio;

	/*
	 * Some devices do not consider the DSM 'Number of Ranges' field when
	 * determining how much data to DMA. Always allocate memory for maximum
	 * number of segments to prevent device reading beyond end of buffer.
	 */
	static const size_t alloc_size = sizeof(*range) * NVME_DSM_MAX_RANGES;

	range = kzalloc(alloc_size, GFP_ATOMIC | __GFP_NOWARN);
	if (!range) {
		/*
		 * If we fail allocation our range, fallback to the controller
		 * discard page. If that's also busy, it's safe to return
		 * busy, as we know we can make progress once that's freed.
		 */
		if (test_and_set_bit_lock(0, &ns->ctrl->discard_page_busy))
			return BLK_STS_RESOURCE;

		range = page_address(ns->ctrl->discard_page);
	}

	__rq_for_each_bio(bio, req) {
		u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector);
		u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;

		if (n < segments) {
			range[n].cattr = cpu_to_le32(0);
			range[n].nlb = cpu_to_le32(nlb);
			range[n].slba = cpu_to_le64(slba);
		}
		n++;
	}

	if (WARN_ON_ONCE(n != segments)) {
		if (virt_to_page(range) == ns->ctrl->discard_page)
			clear_bit_unlock(0, &ns->ctrl->discard_page_busy);
		else
			kfree(range);
		return BLK_STS_IOERR;
	}

	cmnd->dsm.opcode = nvme_cmd_dsm;
	cmnd->dsm.nsid = cpu_to_le32(ns->head->ns_id);
	cmnd->dsm.nr = cpu_to_le32(segments - 1);
	cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);

	req->special_vec.bv_page = virt_to_page(range);
	req->special_vec.bv_offset = offset_in_page(range);
	req->special_vec.bv_len = alloc_size;
	req->rq_flags |= RQF_SPECIAL_PAYLOAD;

	return BLK_STS_OK;
}

static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
		struct request *req, struct nvme_command *cmnd)
{
	if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
		return nvme_setup_discard(ns, req, cmnd);

	cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes;
	cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id);
	cmnd->write_zeroes.slba =
		cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
	cmnd->write_zeroes.length =
		cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
	cmnd->write_zeroes.control = 0;
	return BLK_STS_OK;
}

static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
		struct request *req, struct nvme_command *cmnd)
{
	struct nvme_ctrl *ctrl = ns->ctrl;
	u16 control = 0;
	u32 dsmgmt = 0;

	if (req->cmd_flags & REQ_FUA)
		control |= NVME_RW_FUA;
	if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
		control |= NVME_RW_LR;

	if (req->cmd_flags & REQ_RAHEAD)
		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;

	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
	cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
	cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);

	if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams)
		nvme_assign_write_stream(ctrl, req, &control, &dsmgmt);

	if (ns->ms) {
		/*
		 * If formated with metadata, the block layer always provides a
		 * metadata buffer if CONFIG_BLK_DEV_INTEGRITY is enabled.  Else
		 * we enable the PRACT bit for protection information or set the
		 * namespace capacity to zero to prevent any I/O.
		 */
		if (!blk_integrity_rq(req)) {
			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))
				return BLK_STS_NOTSUPP;
			control |= NVME_RW_PRINFO_PRACT;
		}

		switch (ns->pi_type) {
		case NVME_NS_DPS_PI_TYPE3:
			control |= NVME_RW_PRINFO_PRCHK_GUARD;
			break;
		case NVME_NS_DPS_PI_TYPE1:
		case NVME_NS_DPS_PI_TYPE2:
			control |= NVME_RW_PRINFO_PRCHK_GUARD |
					NVME_RW_PRINFO_PRCHK_REF;
			cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
			break;
		}
	}

	cmnd->rw.control = cpu_to_le16(control);
	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
	return 0;
}

void nvme_cleanup_cmd(struct request *req)
{
	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
		struct nvme_ns *ns = req->rq_disk->private_data;
		struct page *page = req->special_vec.bv_page;

		if (page == ns->ctrl->discard_page)
			clear_bit_unlock(0, &ns->ctrl->discard_page_busy);
		else
			kfree(page_address(page) + req->special_vec.bv_offset);
	}
}
EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);

blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
		struct nvme_command *cmd)
{
	blk_status_t ret = BLK_STS_OK;

	nvme_clear_nvme_request(req);

	memset(cmd, 0, sizeof(*cmd));
	switch (req_op(req)) {
	case REQ_OP_DRV_IN:
	case REQ_OP_DRV_OUT:
		memcpy(cmd, nvme_req(req)->cmd, sizeof(*cmd));
		break;
	case REQ_OP_FLUSH:
		nvme_setup_flush(ns, cmd);
		break;
	case REQ_OP_WRITE_ZEROES:
		ret = nvme_setup_write_zeroes(ns, req, cmd);
		break;
	case REQ_OP_DISCARD:
		ret = nvme_setup_discard(ns, req, cmd);
		break;
	case REQ_OP_READ:
	case REQ_OP_WRITE:
		ret = nvme_setup_rw(ns, req, cmd);
		break;
	default:
		WARN_ON_ONCE(1);
		return BLK_STS_IOERR;
	}

	cmd->common.command_id = req->tag;
	trace_nvme_setup_cmd(req, cmd);
	return ret;
}
EXPORT_SYMBOL_GPL(nvme_setup_cmd);

static void nvme_end_sync_rq(struct request *rq, blk_status_t error)
{
	struct completion *waiting = rq->end_io_data;

	rq->end_io_data = NULL;
	complete(waiting);
}

static void nvme_execute_rq_polled(struct request_queue *q,
		struct gendisk *bd_disk, struct request *rq, int at_head)
{
	DECLARE_COMPLETION_ONSTACK(wait);

	WARN_ON_ONCE(!test_bit(QUEUE_FLAG_POLL, &q->queue_flags));

	rq->cmd_flags |= REQ_HIPRI;
	rq->end_io_data = &wait;
	blk_execute_rq_nowait(q, bd_disk, rq, at_head, nvme_end_sync_rq);

	while (!completion_done(&wait)) {
		blk_poll(q, request_to_qc_t(rq->mq_hctx, rq), true);
		cond_resched();
	}
}

/*
 * Returns 0 on success.  If the result is negative, it's a Linux error code;
 * if the result is positive, it's an NVM Express status code
 */
int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
		union nvme_result *result, void *buffer, unsigned bufflen,
		unsigned timeout, int qid, int at_head,
		blk_mq_req_flags_t flags, bool poll)
{
	struct request *req;
	int ret;

	req = nvme_alloc_request(q, cmd, flags, qid);
	if (IS_ERR(req))
		return PTR_ERR(req);

	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;

	if (buffer && bufflen) {
		ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
		if (ret)
			goto out;
	}

	if (poll)
		nvme_execute_rq_polled(req->q, NULL, req, at_head);
	else
		blk_execute_rq(req->q, NULL, req, at_head);
	if (result)
		*result = nvme_req(req)->result;
	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
		ret = -EINTR;
	else
		ret = nvme_req(req)->status;
 out:
	blk_mq_free_request(req);
	return ret;
}
EXPORT_SYMBOL_GPL(__nvme_submit_sync_cmd);

int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
		void *buffer, unsigned bufflen)
{
	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0,
			NVME_QID_ANY, 0, 0, false);
}
EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);

static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf,
		unsigned len, u32 seed, bool write)
{
	struct bio_integrity_payload *bip;
	int ret = -ENOMEM;
	void *buf;

	buf = kmalloc(len, GFP_KERNEL);
	if (!buf)
		goto out;

	ret = -EFAULT;
	if (write && copy_from_user(buf, ubuf, len))
		goto out_free_meta;

	bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
	if (IS_ERR(bip)) {
		ret = PTR_ERR(bip);
		goto out_free_meta;
	}

	bip->bip_iter.bi_size = len;
	bip->bip_iter.bi_sector = seed;
	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
			offset_in_page(buf));
	if (ret == len)
		return buf;
	ret = -ENOMEM;
out_free_meta:
	kfree(buf);
out:
	return ERR_PTR(ret);
}

static int nvme_submit_user_cmd(struct request_queue *q,
		struct nvme_command *cmd, void __user *ubuffer,
		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
		u32 meta_seed, u64 *result, unsigned timeout)
{
	bool write = nvme_is_write(cmd);
	struct nvme_ns *ns = q->queuedata;
	struct gendisk *disk = ns ? ns->disk : NULL;
	struct request *req;
	struct bio *bio = NULL;
	void *meta = NULL;
	int ret;

	req = nvme_alloc_request(q, cmd, 0, NVME_QID_ANY);
	if (IS_ERR(req))
		return PTR_ERR(req);

	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
	nvme_req(req)->flags |= NVME_REQ_USERCMD;

	if (ubuffer && bufflen) {
		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
				GFP_KERNEL);
		if (ret)
			goto out;
		bio = req->bio;
		bio->bi_disk = disk;
		if (disk && meta_buffer && meta_len) {
			meta = nvme_add_user_metadata(bio, meta_buffer, meta_len,
					meta_seed, write);
			if (IS_ERR(meta)) {
				ret = PTR_ERR(meta);
				goto out_unmap;
			}
			req->cmd_flags |= REQ_INTEGRITY;
		}
	}

	blk_execute_rq(req->q, disk, req, 0);
	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
		ret = -EINTR;
	else
		ret = nvme_req(req)->status;
	if (result)
		*result = le64_to_cpu(nvme_req(req)->result.u64);
	if (meta && !ret && !write) {
		if (copy_to_user(meta_buffer, meta, meta_len))
			ret = -EFAULT;
	}
	kfree(meta);
 out_unmap:
	if (bio)
		blk_rq_unmap_user(bio);
 out:
	blk_mq_free_request(req);
	return ret;
}

static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
{
	struct nvme_ctrl *ctrl = rq->end_io_data;
	unsigned long flags;
	bool startka = false;

	blk_mq_free_request(rq);

	if (status) {
		dev_err(ctrl->device,
			"failed nvme_keep_alive_end_io error=%d\n",
				status);
		return;
	}

	ctrl->comp_seen = false;
	spin_lock_irqsave(&ctrl->lock, flags);
	if (ctrl->state == NVME_CTRL_LIVE ||
	    ctrl->state == NVME_CTRL_CONNECTING)
		startka = true;
	spin_unlock_irqrestore(&ctrl->lock, flags);
	if (startka)
		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
}

static int nvme_keep_alive(struct nvme_ctrl *ctrl)
{
	struct request *rq;

	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, BLK_MQ_REQ_RESERVED,
			NVME_QID_ANY);
	if (IS_ERR(rq))
		return PTR_ERR(rq);

	rq->timeout = ctrl->kato * HZ;
	rq->end_io_data = ctrl;

	blk_execute_rq_nowait(rq->q, NULL, rq, 0, nvme_keep_alive_end_io);

	return 0;
}

static void nvme_keep_alive_work(struct work_struct *work)
{
	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
			struct nvme_ctrl, ka_work);
	bool comp_seen = ctrl->comp_seen;

	if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) {
		dev_dbg(ctrl->device,
			"reschedule traffic based keep-alive timer\n");
		ctrl->comp_seen = false;
		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
		return;
	}

	if (nvme_keep_alive(ctrl)) {
		/* allocation failure, reset the controller */
		dev_err(ctrl->device, "keep-alive failed\n");
		nvme_reset_ctrl(ctrl);
		return;
	}
}

static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
{
	if (unlikely(ctrl->kato == 0))
		return;

	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
}

void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
{
	if (unlikely(ctrl->kato == 0))
		return;

	cancel_delayed_work_sync(&ctrl->ka_work);
}
EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);

/*
 * In NVMe 1.0 the CNS field was just a binary controller or namespace
 * flag, thus sending any new CNS opcodes has a big chance of not working.
 * Qemu unfortunately had that bug after reporting a 1.1 version compliance
 * (but not for any later version).
 */
static bool nvme_ctrl_limited_cns(struct nvme_ctrl *ctrl)
{
	if (ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)
		return ctrl->vs < NVME_VS(1, 2, 0);
	return ctrl->vs < NVME_VS(1, 1, 0);
}

static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
{
	struct nvme_command c = { };
	int error;

	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
	c.identify.opcode = nvme_admin_identify;
	c.identify.cns = NVME_ID_CNS_CTRL;

	*id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
	if (!*id)
		return -ENOMEM;

	error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
			sizeof(struct nvme_id_ctrl));
	if (error)
		kfree(*id);
	return error;
}

static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
		struct nvme_ns_id_desc *cur)
{
	const char *warn_str = "ctrl returned bogus length:";
	void *data = cur;

	switch (cur->nidt) {
	case NVME_NIDT_EUI64:
		if (cur->nidl != NVME_NIDT_EUI64_LEN) {
			dev_warn(ctrl->device, "%s %d for NVME_NIDT_EUI64\n",
				 warn_str, cur->nidl);
			return -1;
		}
		memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN);
		return NVME_NIDT_EUI64_LEN;
	case NVME_NIDT_NGUID:
		if (cur->nidl != NVME_NIDT_NGUID_LEN) {
			dev_warn(ctrl->device, "%s %d for NVME_NIDT_NGUID\n",
				 warn_str, cur->nidl);
			return -1;
		}
		memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN);
		return NVME_NIDT_NGUID_LEN;
	case NVME_NIDT_UUID:
		if (cur->nidl != NVME_NIDT_UUID_LEN) {
			dev_warn(ctrl->device, "%s %d for NVME_NIDT_UUID\n",
				 warn_str, cur->nidl);
			return -1;
		}
		uuid_copy(&ids->uuid, data + sizeof(*cur));
		return NVME_NIDT_UUID_LEN;
	default:
		/* Skip unknown types */
		return cur->nidl;
	}
}

static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
		struct nvme_ns_ids *ids)
{
	struct nvme_command c = { };
	int status;
	void *data;
	int pos;
	int len;

	c.identify.opcode = nvme_admin_identify;
	c.identify.nsid = cpu_to_le32(nsid);
	c.identify.cns = NVME_ID_CNS_NS_DESC_LIST;

	data = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
	if (!data)
		return -ENOMEM;

	status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data,
				      NVME_IDENTIFY_DATA_SIZE);
	if (status) {
		dev_warn(ctrl->device,
			"Identify Descriptors failed (%d)\n", status);
		 /*
		  * Don't treat non-retryable errors as fatal, as we potentially
		  * already have a NGUID or EUI-64.  If we failed with DNR set,
		  * we want to silently ignore the error as we can still
		  * identify the device, but if the status has DNR set, we want
		  * to propagate the error back specifically for the disk
		  * revalidation flow to make sure we don't abandon the
		  * device just because of a temporal retry-able error (such
		  * as path of transport errors).
		  */
		if (status > 0 && (status & NVME_SC_DNR))
			status = 0;
		goto free_data;
	}

	for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) {
		struct nvme_ns_id_desc *cur = data + pos;

		if (cur->nidl == 0)
			break;

		len = nvme_process_ns_desc(ctrl, ids, cur);
		if (len < 0)
			goto free_data;

		len += sizeof(*cur);
	}
free_data:
	kfree(data);
	return status;
}

static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list)
{
	struct nvme_command c = { };

	c.identify.opcode = nvme_admin_identify;
	c.identify.cns = NVME_ID_CNS_NS_ACTIVE_LIST;
	c.identify.nsid = cpu_to_le32(nsid);
	return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list,
				    NVME_IDENTIFY_DATA_SIZE);
}

static int nvme_identify_ns(struct nvme_ctrl *ctrl,
		unsigned nsid, struct nvme_id_ns **id)
{
	struct nvme_command c = { };
	int error;

	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
	c.identify.opcode = nvme_admin_identify;
	c.identify.nsid = cpu_to_le32(nsid);
	c.identify.cns = NVME_ID_CNS_NS;

	*id = kmalloc(sizeof(**id), GFP_KERNEL);
	if (!*id)
		return -ENOMEM;

	error = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id));
	if (error) {
		dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
		kfree(*id);
	}

	return error;
}

static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
		unsigned int dword11, void *buffer, size_t buflen, u32 *result)
{
	union nvme_result res = { 0 };
	struct nvme_command c;
	int ret;

	memset(&c, 0, sizeof(c));
	c.features.opcode = op;
	c.features.fid = cpu_to_le32(fid);
	c.features.dword11 = cpu_to_le32(dword11);

	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res,
			buffer, buflen, 0, NVME_QID_ANY, 0, 0, false);
	if (ret >= 0 && result)
		*result = le32_to_cpu(res.u32);
	return ret;
}

int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
		      unsigned int dword11, void *buffer, size_t buflen,
		      u32 *result)
{
	return nvme_features(dev, nvme_admin_set_features, fid, dword11, buffer,
			     buflen, result);
}
EXPORT_SYMBOL_GPL(nvme_set_features);

int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid,
		      unsigned int dword11, void *buffer, size_t buflen,
		      u32 *result)
{
	return nvme_features(dev, nvme_admin_get_features, fid, dword11, buffer,
			     buflen, result);
}
EXPORT_SYMBOL_GPL(nvme_get_features);

int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
{
	u32 q_count = (*count - 1) | ((*count - 1) << 16);
	u32 result;
	int status, nr_io_queues;

	status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0,
			&result);
	if (status < 0)
		return status;

	/*
	 * Degraded controllers might return an error when setting the queue
	 * count.  We still want to be able to bring them online and offer
	 * access to the admin queue, as that might be only way to fix them up.
	 */
	if (status > 0) {
		dev_err(ctrl->device, "Could not set queue count (%d)\n", status);
		*count = 0;
	} else {
		nr_io_queues = min(result & 0xffff, result >> 16) + 1;
		*count = min(*count, nr_io_queues);
	}

	return 0;
}
EXPORT_SYMBOL_GPL(nvme_set_queue_count);

#define NVME_AEN_SUPPORTED \
	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | \
	 NVME_AEN_CFG_ANA_CHANGE | NVME_AEN_CFG_DISC_CHANGE)

static void nvme_enable_aen(struct nvme_ctrl *ctrl)
{
	u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED;
	int status;

	if (!supported_aens)
		return;

	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens,
			NULL, 0, &result);
	if (status)
		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
			 supported_aens);

	queue_work(nvme_wq, &ctrl->async_event_work);
}

/*
 * Convert integer values from ioctl structures to user pointers, silently
 * ignoring the upper bits in the compat case to match behaviour of 32-bit
 * kernels.
 */
static void __user *nvme_to_user_ptr(uintptr_t ptrval)
{
	if (in_compat_syscall())
		ptrval = (compat_uptr_t)ptrval;
	return (void __user *)ptrval;
}

static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
{
	struct nvme_user_io io;
	struct nvme_command c;
	unsigned length, meta_len;
	void __user *metadata;

	if (copy_from_user(&io, uio, sizeof(io)))
		return -EFAULT;
	if (io.flags)
		return -EINVAL;

	switch (io.opcode) {
	case nvme_cmd_write:
	case nvme_cmd_read:
	case nvme_cmd_compare:
		break;
	default:
		return -EINVAL;
	}

	length = (io.nblocks + 1) << ns->lba_shift;
	meta_len = (io.nblocks + 1) * ns->ms;
	metadata = nvme_to_user_ptr(io.metadata);

	if (ns->features & NVME_NS_EXT_LBAS) {
		length += meta_len;
		meta_len = 0;
	} else if (meta_len) {
		if ((io.metadata & 3) || !io.metadata)
			return -EINVAL;
	}

	memset(&c, 0, sizeof(c));
	c.rw.opcode = io.opcode;
	c.rw.flags = io.flags;
	c.rw.nsid = cpu_to_le32(ns->head->ns_id);
	c.rw.slba = cpu_to_le64(io.slba);
	c.rw.length = cpu_to_le16(io.nblocks);
	c.rw.control = cpu_to_le16(io.control);
	c.rw.dsmgmt = cpu_to_le32(io.dsmgmt);
	c.rw.reftag = cpu_to_le32(io.reftag);
	c.rw.apptag = cpu_to_le16(io.apptag);
	c.rw.appmask = cpu_to_le16(io.appmask);

	return nvme_submit_user_cmd(ns->queue, &c,
			nvme_to_user_ptr(io.addr), length,
			metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
}

static u32 nvme_known_admin_effects(u8 opcode)
{
	switch (opcode) {
	case nvme_admin_format_nvm:
		return NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
					NVME_CMD_EFFECTS_CSE_MASK;
	case nvme_admin_sanitize_nvm:
		return NVME_CMD_EFFECTS_CSE_MASK;
	default:
		break;
	}
	return 0;
}

static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
								u8 opcode)
{
	u32 effects = 0;

	if (ns) {
		if (ctrl->effects)
			effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
		if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
			dev_warn(ctrl->device,
				 "IO command:%02x has unhandled effects:%08x\n",
				 opcode, effects);
		return 0;
	}

	if (ctrl->effects)
		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
	effects |= nvme_known_admin_effects(opcode);

	/*
	 * For simplicity, IO to all namespaces is quiesced even if the command
	 * effects say only one namespace is affected.
	 */
	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
		mutex_lock(&ctrl->scan_lock);
		mutex_lock(&ctrl->subsys->lock);
		nvme_mpath_start_freeze(ctrl->subsys);
		nvme_mpath_wait_freeze(ctrl->subsys);
		nvme_start_freeze(ctrl);
		nvme_wait_freeze(ctrl);
	}
	return effects;
}

static void nvme_update_formats(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		if (ns->disk && nvme_revalidate_disk(ns->disk))
			nvme_set_queue_dying(ns);
	up_read(&ctrl->namespaces_rwsem);
}

static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
{
	/*
	 * Revalidate LBA changes prior to unfreezing. This is necessary to
	 * prevent memory corruption if a logical block size was changed by
	 * this command.
	 */
	if (effects & NVME_CMD_EFFECTS_LBCC)
		nvme_update_formats(ctrl);
	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
		nvme_unfreeze(ctrl);
		nvme_mpath_unfreeze(ctrl->subsys);
		mutex_unlock(&ctrl->subsys->lock);
		nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
		mutex_unlock(&ctrl->scan_lock);
	}
	if (effects & NVME_CMD_EFFECTS_CCC)
		nvme_init_identify(ctrl);
	if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) {
		nvme_queue_scan(ctrl);
		flush_work(&ctrl->scan_work);
	}
}

static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
			struct nvme_passthru_cmd __user *ucmd)
{
	struct nvme_passthru_cmd cmd;
	struct nvme_command c;
	unsigned timeout = 0;
	u32 effects;
	u64 result;
	int status;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;
	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
		return -EFAULT;
	if (cmd.flags)
		return -EINVAL;

	memset(&c, 0, sizeof(c));
	c.common.opcode = cmd.opcode;
	c.common.flags = cmd.flags;
	c.common.nsid = cpu_to_le32(cmd.nsid);
	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
	c.common.cdw15 = cpu_to_le32(cmd.cdw15);

	if (cmd.timeout_ms)
		timeout = msecs_to_jiffies(cmd.timeout_ms);

	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
			nvme_to_user_ptr(cmd.addr), cmd.data_len,
			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
			0, &result, timeout);
	nvme_passthru_end(ctrl, effects);

	if (status >= 0) {
		if (put_user(result, &ucmd->result))
			return -EFAULT;
	}

	return status;
}

static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
			struct nvme_passthru_cmd64 __user *ucmd)
{
	struct nvme_passthru_cmd64 cmd;
	struct nvme_command c;
	unsigned timeout = 0;
	u32 effects;
	int status;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;
	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
		return -EFAULT;
	if (cmd.flags)
		return -EINVAL;

	memset(&c, 0, sizeof(c));
	c.common.opcode = cmd.opcode;
	c.common.flags = cmd.flags;
	c.common.nsid = cpu_to_le32(cmd.nsid);
	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
	c.common.cdw15 = cpu_to_le32(cmd.cdw15);

	if (cmd.timeout_ms)
		timeout = msecs_to_jiffies(cmd.timeout_ms);

	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
			nvme_to_user_ptr(cmd.addr), cmd.data_len,
			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
			0, &cmd.result, timeout);
	nvme_passthru_end(ctrl, effects);

	if (status >= 0) {
		if (put_user(cmd.result, &ucmd->result))
			return -EFAULT;
	}

	return status;
}

/*
 * Issue ioctl requests on the first available path.  Note that unlike normal
 * block layer requests we will not retry failed request on another controller.
 */
static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
		struct nvme_ns_head **head, int *srcu_idx)
{
#ifdef CONFIG_NVME_MULTIPATH
	if (disk->fops == &nvme_ns_head_ops) {
		struct nvme_ns *ns;

		*head = disk->private_data;
		*srcu_idx = srcu_read_lock(&(*head)->srcu);
		ns = nvme_find_path(*head);
		if (!ns)
			srcu_read_unlock(&(*head)->srcu, *srcu_idx);
		return ns;
	}
#endif
	*head = NULL;
	*srcu_idx = -1;
	return disk->private_data;
}

static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
{
	if (head)
		srcu_read_unlock(&head->srcu, idx);
}

static bool is_ctrl_ioctl(unsigned int cmd)
{
	if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
		return true;
	if (is_sed_ioctl(cmd))
		return true;
	return false;
}

static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
				  void __user *argp,
				  struct nvme_ns_head *head,
				  int srcu_idx)
{
	struct nvme_ctrl *ctrl = ns->ctrl;
	int ret;

	nvme_get_ctrl(ns->ctrl);
	nvme_put_ns_from_disk(head, srcu_idx);

	switch (cmd) {
	case NVME_IOCTL_ADMIN_CMD:
		ret = nvme_user_cmd(ctrl, NULL, argp);
		break;
	case NVME_IOCTL_ADMIN64_CMD:
		ret = nvme_user_cmd64(ctrl, NULL, argp);
		break;
	default:
		ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
		break;
	}
	nvme_put_ctrl(ctrl);
	return ret;
}

static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
		unsigned int cmd, unsigned long arg)
{
	struct nvme_ns_head *head = NULL;
	void __user *argp = (void __user *)arg;
	struct nvme_ns *ns;
	int srcu_idx, ret;

	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
	if (unlikely(!ns))
		return -EWOULDBLOCK;

	/*
	 * Handle ioctls that apply to the controller instead of the namespace
	 * seperately and drop the ns SRCU reference early.  This avoids a
	 * deadlock when deleting namespaces using the passthrough interface.
	 */
	if (is_ctrl_ioctl(cmd))
		return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);

	switch (cmd) {
	case NVME_IOCTL_ID:
		force_successful_syscall_return();
		ret = ns->head->ns_id;
		break;
	case NVME_IOCTL_IO_CMD:
		ret = nvme_user_cmd(ns->ctrl, ns, argp);
		break;
	case NVME_IOCTL_SUBMIT_IO:
		ret = nvme_submit_io(ns, argp);
		break;
	case NVME_IOCTL_IO64_CMD:
		ret = nvme_user_cmd64(ns->ctrl, ns, argp);
		break;
	default:
		if (ns->ndev)
			ret = nvme_nvm_ioctl(ns, cmd, arg);
		else
			ret = -ENOTTY;
	}

	nvme_put_ns_from_disk(head, srcu_idx);
	return ret;
}

#ifdef CONFIG_COMPAT
struct nvme_user_io32 {
	__u8	opcode;
	__u8	flags;
	__u16	control;
	__u16	nblocks;
	__u16	rsvd;
	__u64	metadata;
	__u64	addr;
	__u64	slba;
	__u32	dsmgmt;
	__u32	reftag;
	__u16	apptag;
	__u16	appmask;
} __attribute__((__packed__));

#define NVME_IOCTL_SUBMIT_IO32	_IOW('N', 0x42, struct nvme_user_io32)

static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
		unsigned int cmd, unsigned long arg)
{
	/*
	 * Corresponds to the difference of NVME_IOCTL_SUBMIT_IO
	 * between 32 bit programs and 64 bit kernel.
	 * The cause is that the results of sizeof(struct nvme_user_io),
	 * which is used to define NVME_IOCTL_SUBMIT_IO,
	 * are not same between 32 bit compiler and 64 bit compiler.
	 * NVME_IOCTL_SUBMIT_IO32 is for 64 bit kernel handling
	 * NVME_IOCTL_SUBMIT_IO issued from 32 bit programs.
	 * Other IOCTL numbers are same between 32 bit and 64 bit.
	 * So there is nothing to do regarding to other IOCTL numbers.
	 */
	if (cmd == NVME_IOCTL_SUBMIT_IO32)
		return nvme_ioctl(bdev, mode, NVME_IOCTL_SUBMIT_IO, arg);

	return nvme_ioctl(bdev, mode, cmd, arg);
}
#else
#define nvme_compat_ioctl	NULL
#endif /* CONFIG_COMPAT */

static int nvme_open(struct block_device *bdev, fmode_t mode)
{
	struct nvme_ns *ns = bdev->bd_disk->private_data;

#ifdef CONFIG_NVME_MULTIPATH
	/* should never be called due to GENHD_FL_HIDDEN */
	if (WARN_ON_ONCE(ns->head->disk))
		goto fail;
#endif
	if (!kref_get_unless_zero(&ns->kref))
		goto fail;
	if (!try_module_get(ns->ctrl->ops->module))
		goto fail_put_ns;

	return 0;

fail_put_ns:
	nvme_put_ns(ns);
fail:
	return -ENXIO;
}

static void nvme_release(struct gendisk *disk, fmode_t mode)
{
	struct nvme_ns *ns = disk->private_data;

	module_put(ns->ctrl->ops->module);
	nvme_put_ns(ns);
}

static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
	/* some standard values */
	geo->heads = 1 << 6;
	geo->sectors = 1 << 5;
	geo->cylinders = get_capacity(bdev->bd_disk) >> 11;
	return 0;
}

#ifdef CONFIG_BLK_DEV_INTEGRITY
static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type,
				u32 max_integrity_segments)
{
	struct blk_integrity integrity;

	memset(&integrity, 0, sizeof(integrity));
	switch (pi_type) {
	case NVME_NS_DPS_PI_TYPE3:
		integrity.profile = &t10_pi_type3_crc;
		integrity.tag_size = sizeof(u16) + sizeof(u32);
		integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
		break;
	case NVME_NS_DPS_PI_TYPE1:
	case NVME_NS_DPS_PI_TYPE2:
		integrity.profile = &t10_pi_type1_crc;
		integrity.tag_size = sizeof(u16);
		integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
		break;
	default:
		integrity.profile = NULL;
		break;
	}
	integrity.tuple_size = ms;
	blk_integrity_register(disk, &integrity);
	blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
}
#else
static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type,
				u32 max_integrity_segments)
{
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */

static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
{
	struct nvme_ctrl *ctrl = ns->ctrl;
	struct request_queue *queue = disk->queue;
	u32 size = queue_logical_block_size(queue);

	if (!(ctrl->oncs & NVME_CTRL_ONCS_DSM)) {
		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue);
		return;
	}

	if (ctrl->nr_streams && ns->sws && ns->sgs)
		size *= ns->sws * ns->sgs;

	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
			NVME_DSM_MAX_RANGES);

	queue->limits.discard_alignment = 0;
	queue->limits.discard_granularity = size;

	/* If discard is already enabled, don't reset queue limits */
	if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue))
		return;

	blk_queue_max_discard_sectors(queue, UINT_MAX);
	blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);

	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
}

static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns)
{
	u64 max_blocks;

	if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) ||
	    (ns->ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES))
		return;
	/*
	 * Even though NVMe spec explicitly states that MDTS is not
	 * applicable to the write-zeroes:- "The restriction does not apply to
	 * commands that do not transfer data between the host and the
	 * controller (e.g., Write Uncorrectable ro Write Zeroes command).".
	 * In order to be more cautious use controller's max_hw_sectors value
	 * to configure the maximum sectors for the write-zeroes which is
	 * configured based on the controller's MDTS field in the
	 * nvme_init_identify() if available.
	 */
	if (ns->ctrl->max_hw_sectors == UINT_MAX)
		max_blocks = (u64)USHRT_MAX + 1;
	else
		max_blocks = ns->ctrl->max_hw_sectors + 1;

	blk_queue_max_write_zeroes_sectors(disk->queue,
					   nvme_lba_to_sect(ns, max_blocks));
}

static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
		struct nvme_id_ns *id, struct nvme_ns_ids *ids)
{
	memset(ids, 0, sizeof(*ids));

	if (ctrl->vs >= NVME_VS(1, 1, 0))
		memcpy(ids->eui64, id->eui64, sizeof(id->eui64));
	if (ctrl->vs >= NVME_VS(1, 2, 0))
		memcpy(ids->nguid, id->nguid, sizeof(id->nguid));
	if (ctrl->vs >= NVME_VS(1, 3, 0))
		return nvme_identify_ns_descs(ctrl, nsid, ids);
	return 0;
}

static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
{
	return !uuid_is_null(&ids->uuid) ||
		memchr_inv(ids->nguid, 0, sizeof(ids->nguid)) ||
		memchr_inv(ids->eui64, 0, sizeof(ids->eui64));
}

static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
{
	return uuid_equal(&a->uuid, &b->uuid) &&
		memcmp(&a->nguid, &b->nguid, sizeof(a->nguid)) == 0 &&
		memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0;
}

static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
				 u32 *phys_bs, u32 *io_opt)
{
	struct streams_directive_params s;
	int ret;

	if (!ctrl->nr_streams)
		return 0;

	ret = nvme_get_stream_params(ctrl, &s, ns->head->ns_id);
	if (ret)
		return ret;

	ns->sws = le32_to_cpu(s.sws);
	ns->sgs = le16_to_cpu(s.sgs);

	if (ns->sws) {
		*phys_bs = ns->sws * (1 << ns->lba_shift);
		if (ns->sgs)
			*io_opt = *phys_bs * ns->sgs;
	}

	return 0;
}

static void nvme_update_disk_info(struct gendisk *disk,
		struct nvme_ns *ns, struct nvme_id_ns *id)
{
	sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze));
	unsigned short bs = 1 << ns->lba_shift;
	u32 atomic_bs, phys_bs, io_opt = 0;

	if (ns->lba_shift > PAGE_SHIFT) {
		/* unsupported block size, set capacity to 0 later */
		bs = (1 << 9);
	}
	blk_mq_freeze_queue(disk->queue);
	blk_integrity_unregister(disk);

	atomic_bs = phys_bs = bs;
	nvme_setup_streams_ns(ns->ctrl, ns, &phys_bs, &io_opt);
	if (id->nabo == 0) {
		/*
		 * Bit 1 indicates whether NAWUPF is defined for this namespace
		 * and whether it should be used instead of AWUPF. If NAWUPF ==
		 * 0 then AWUPF must be used instead.
		 */
		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
		else
			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
	}

	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
		/* NPWG = Namespace Preferred Write Granularity */
		phys_bs = bs * (1 + le16_to_cpu(id->npwg));
		/* NOWS = Namespace Optimal Write Size */
		io_opt = bs * (1 + le16_to_cpu(id->nows));
	}

	blk_queue_logical_block_size(disk->queue, bs);
	/*
	 * Linux filesystems assume writing a single physical block is
	 * an atomic operation. Hence limit the physical block size to the
	 * value of the Atomic Write Unit Power Fail parameter.
	 */
	blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
	blk_queue_io_min(disk->queue, phys_bs);
	blk_queue_io_opt(disk->queue, io_opt);

	/*
	 * The block layer can't support LBA sizes larger than the page size
	 * yet, so catch this early and don't allow block I/O.
	 */
	if (ns->lba_shift > PAGE_SHIFT)
		capacity = 0;

	/*
	 * Register a metadata profile for PI, or the plain non-integrity NVMe
	 * metadata masquerading as Type 0 if supported, otherwise reject block
	 * I/O to namespaces with metadata except when the namespace supports
	 * PI, as it can strip/insert in that case.
	 */
	if (ns->ms) {
		if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
		    (ns->features & NVME_NS_METADATA_SUPPORTED))
			nvme_init_integrity(disk, ns->ms, ns->pi_type,
					    ns->ctrl->max_integrity_segments);
		else if (!nvme_ns_has_pi(ns))
			capacity = 0;
	}

	set_capacity_revalidate_and_notify(disk, capacity, false);

	nvme_config_discard(disk, ns);
	nvme_config_write_zeroes(disk, ns);

	if (id->nsattr & NVME_NS_ATTR_RO)
		set_disk_ro(disk, true);
	else
		set_disk_ro(disk, false);

	blk_mq_unfreeze_queue(disk->queue);
}

static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
{
	struct nvme_ns *ns = disk->private_data;
	struct nvme_ctrl *ctrl = ns->ctrl;
	u32 iob;

	/*
	 * If identify namespace failed, use default 512 byte block size so
	 * block layer can use before failing read/write for 0 capacity.
	 */
	ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
	if (ns->lba_shift == 0)
		ns->lba_shift = 9;

	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
	    is_power_of_2(ctrl->max_hw_sectors))
		iob = ctrl->max_hw_sectors;
	else
		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));

	ns->features = 0;
	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
	/* the PI implementation requires metadata equal t10 pi tuple size */
	if (ns->ms == sizeof(struct t10_pi_tuple))
		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
	else
		ns->pi_type = 0;

	if (ns->ms) {
		/*
		 * For PCIe only the separate metadata pointer is supported,
		 * as the block layer supplies metadata in a separate bio_vec
		 * chain. For Fabrics, only metadata as part of extended data
		 * LBA is supported on the wire per the Fabrics specification,
		 * but the HBA/HCA will do the remapping from the separate
		 * metadata buffers for us.
		 */
		if (id->flbas & NVME_NS_FLBAS_META_EXT) {
			ns->features |= NVME_NS_EXT_LBAS;
			if ((ctrl->ops->flags & NVME_F_FABRICS) &&
			    (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) &&
			    ctrl->max_integrity_segments)
				ns->features |= NVME_NS_METADATA_SUPPORTED;
		} else {
			if (WARN_ON_ONCE(ctrl->ops->flags & NVME_F_FABRICS))
				return -EINVAL;
			if (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
				ns->features |= NVME_NS_METADATA_SUPPORTED;
		}
	}

	if (iob)
		blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob));
	nvme_update_disk_info(disk, ns, id);
#ifdef CONFIG_NVME_MULTIPATH
	if (ns->head->disk) {
		nvme_update_disk_info(ns->head->disk, ns, id);
		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
		nvme_mpath_update_disk_size(ns->head->disk);
	}
#endif
	return 0;
}

static int nvme_revalidate_disk(struct gendisk *disk)
{
	struct nvme_ns *ns = disk->private_data;
	struct nvme_ctrl *ctrl = ns->ctrl;
	struct nvme_id_ns *id;
	struct nvme_ns_ids ids;
	int ret = 0;

	if (test_bit(NVME_NS_DEAD, &ns->flags)) {
		set_capacity(disk, 0);
		return -ENODEV;
	}

	ret = nvme_identify_ns(ctrl, ns->head->ns_id, &id);
	if (ret)
		goto out;

	if (id->ncap == 0) {
		ret = -ENODEV;
		goto free_id;
	}

	ret = nvme_report_ns_ids(ctrl, ns->head->ns_id, id, &ids);
	if (ret)
		goto free_id;

	if (!nvme_ns_ids_equal(&ns->head->ids, &ids)) {
		dev_err(ctrl->device,
			"identifiers changed for nsid %d\n", ns->head->ns_id);
		ret = -ENODEV;
		goto free_id;
	}

	ret = __nvme_revalidate_disk(disk, id);
free_id:
	kfree(id);
out:
	/*
	 * Only fail the function if we got a fatal error back from the
	 * device, otherwise ignore the error and just move on.
	 */
	if (ret == -ENOMEM || (ret > 0 && !(ret & NVME_SC_DNR)))
		ret = 0;
	else if (ret > 0)
		ret = blk_status_to_errno(nvme_error_status(ret));
	return ret;
}

static char nvme_pr_type(enum pr_type type)
{
	switch (type) {
	case PR_WRITE_EXCLUSIVE:
		return 1;
	case PR_EXCLUSIVE_ACCESS:
		return 2;
	case PR_WRITE_EXCLUSIVE_REG_ONLY:
		return 3;
	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
		return 4;
	case PR_WRITE_EXCLUSIVE_ALL_REGS:
		return 5;
	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
		return 6;
	default:
		return 0;
	}
};

static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
				u64 key, u64 sa_key, u8 op)
{
	struct nvme_ns_head *head = NULL;
	struct nvme_ns *ns;
	struct nvme_command c;
	int srcu_idx, ret;
	u8 data[16] = { 0, };

	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
	if (unlikely(!ns))
		return -EWOULDBLOCK;

	put_unaligned_le64(key, &data[0]);
	put_unaligned_le64(sa_key, &data[8]);

	memset(&c, 0, sizeof(c));
	c.common.opcode = op;
	c.common.nsid = cpu_to_le32(ns->head->ns_id);
	c.common.cdw10 = cpu_to_le32(cdw10);

	ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
	nvme_put_ns_from_disk(head, srcu_idx);
	return ret;
}

static int nvme_pr_register(struct block_device *bdev, u64 old,
		u64 new, unsigned flags)
{
	u32 cdw10;

	if (flags & ~PR_FL_IGNORE_KEY)
		return -EOPNOTSUPP;

	cdw10 = old ? 2 : 0;
	cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0;
	cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */
	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register);
}

static int nvme_pr_reserve(struct block_device *bdev, u64 key,
		enum pr_type type, unsigned flags)
{
	u32 cdw10;

	if (flags & ~PR_FL_IGNORE_KEY)
		return -EOPNOTSUPP;

	cdw10 = nvme_pr_type(type) << 8;
	cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0);
	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire);
}

static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
		enum pr_type type, bool abort)
{
	u32 cdw10 = nvme_pr_type(type) << 8 | (abort ? 2 : 1);
	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
}

static int nvme_pr_clear(struct block_device *bdev, u64 key)
{
	u32 cdw10 = 1 | (key ? 1 << 3 : 0);
	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register);
}

static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
{
	u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 1 << 3 : 0);
	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
}

static const struct pr_ops nvme_pr_ops = {
	.pr_register	= nvme_pr_register,
	.pr_reserve	= nvme_pr_reserve,
	.pr_release	= nvme_pr_release,
	.pr_preempt	= nvme_pr_preempt,
	.pr_clear	= nvme_pr_clear,
};

#ifdef CONFIG_BLK_SED_OPAL
int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
		bool send)
{
	struct nvme_ctrl *ctrl = data;
	struct nvme_command cmd;

	memset(&cmd, 0, sizeof(cmd));
	if (send)
		cmd.common.opcode = nvme_admin_security_send;
	else
		cmd.common.opcode = nvme_admin_security_recv;
	cmd.common.nsid = 0;
	cmd.common.cdw10 = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
	cmd.common.cdw11 = cpu_to_le32(len);

	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
				      ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0, false);
}
EXPORT_SYMBOL_GPL(nvme_sec_submit);
#endif /* CONFIG_BLK_SED_OPAL */

static const struct block_device_operations nvme_fops = {
	.owner		= THIS_MODULE,
	.ioctl		= nvme_ioctl,
	.compat_ioctl	= nvme_compat_ioctl,
	.open		= nvme_open,
	.release	= nvme_release,
	.getgeo		= nvme_getgeo,
	.revalidate_disk= nvme_revalidate_disk,
	.pr_ops		= &nvme_pr_ops,
};

#ifdef CONFIG_NVME_MULTIPATH
static int nvme_ns_head_open(struct block_device *bdev, fmode_t mode)
{
	struct nvme_ns_head *head = bdev->bd_disk->private_data;

	if (!kref_get_unless_zero(&head->ref))
		return -ENXIO;
	return 0;
}

static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode)
{
	nvme_put_ns_head(disk->private_data);
}

const struct block_device_operations nvme_ns_head_ops = {
	.owner		= THIS_MODULE,
	.open		= nvme_ns_head_open,
	.release	= nvme_ns_head_release,
	.ioctl		= nvme_ioctl,
	.compat_ioctl	= nvme_compat_ioctl,
	.getgeo		= nvme_getgeo,
	.pr_ops		= &nvme_pr_ops,
};
#endif /* CONFIG_NVME_MULTIPATH */

static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
{
	unsigned long timeout =
		((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
	u32 csts, bit = enabled ? NVME_CSTS_RDY : 0;
	int ret;

	while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) {
		if (csts == ~0)
			return -ENODEV;
		if ((csts & NVME_CSTS_RDY) == bit)
			break;

		usleep_range(1000, 2000);
		if (fatal_signal_pending(current))
			return -EINTR;
		if (time_after(jiffies, timeout)) {
			dev_err(ctrl->device,
				"Device not ready; aborting %s, CSTS=0x%x\n",
				enabled ? "initialisation" : "reset", csts);
			return -ENODEV;
		}
	}

	return ret;
}

/*
 * If the device has been passed off to us in an enabled state, just clear
 * the enabled bit.  The spec says we should set the 'shutdown notification
 * bits', but doing so may cause the device to complete commands to the
 * admin queue ... and we don't know what memory that might be pointing at!
 */
int nvme_disable_ctrl(struct nvme_ctrl *ctrl)
{
	int ret;

	ctrl->ctrl_config &= ~NVME_CC_SHN_MASK;
	ctrl->ctrl_config &= ~NVME_CC_ENABLE;

	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
	if (ret)
		return ret;

	if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY)
		msleep(NVME_QUIRK_DELAY_AMOUNT);

	return nvme_wait_ready(ctrl, ctrl->cap, false);
}
EXPORT_SYMBOL_GPL(nvme_disable_ctrl);

int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
{
	/*
	 * Default to a 4K page size, with the intention to update this
	 * path in the future to accomodate architectures with differing
	 * kernel and IO page sizes.
	 */
	unsigned dev_page_min, page_shift = 12;
	int ret;

	ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
	if (ret) {
		dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret);
		return ret;
	}
	dev_page_min = NVME_CAP_MPSMIN(ctrl->cap) + 12;

	if (page_shift < dev_page_min) {
		dev_err(ctrl->device,
			"Minimum device page size %u too large for host (%u)\n",
			1 << dev_page_min, 1 << page_shift);
		return -ENODEV;
	}

	ctrl->page_size = 1 << page_shift;

	ctrl->ctrl_config = NVME_CC_CSS_NVM;
	ctrl->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
	ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
	ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
	ctrl->ctrl_config |= NVME_CC_ENABLE;

	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
	if (ret)
		return ret;
	return nvme_wait_ready(ctrl, ctrl->cap, true);
}
EXPORT_SYMBOL_GPL(nvme_enable_ctrl);

int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
{
	unsigned long timeout = jiffies + (ctrl->shutdown_timeout * HZ);
	u32 csts;
	int ret;

	ctrl->ctrl_config &= ~NVME_CC_SHN_MASK;
	ctrl->ctrl_config |= NVME_CC_SHN_NORMAL;

	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
	if (ret)
		return ret;

	while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) {
		if ((csts & NVME_CSTS_SHST_MASK) == NVME_CSTS_SHST_CMPLT)
			break;

		msleep(100);
		if (fatal_signal_pending(current))
			return -EINTR;
		if (time_after(jiffies, timeout)) {
			dev_err(ctrl->device,
				"Device shutdown incomplete; abort shutdown\n");
			return -ENODEV;
		}
	}

	return ret;
}
EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl);

static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
		struct request_queue *q)
{
	bool vwc = false;

	if (ctrl->max_hw_sectors) {
		u32 max_segments =
			(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;

		max_segments = min_not_zero(max_segments, ctrl->max_segments);
		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
	}
	blk_queue_virt_boundary(q, ctrl->page_size - 1);
	blk_queue_dma_alignment(q, 7);
	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
		vwc = true;
	blk_queue_write_cache(q, vwc, vwc);
}

static int nvme_configure_timestamp(struct nvme_ctrl *ctrl)
{
	__le64 ts;
	int ret;

	if (!(ctrl->oncs & NVME_CTRL_ONCS_TIMESTAMP))
		return 0;

	ts = cpu_to_le64(ktime_to_ms(ktime_get_real()));
	ret = nvme_set_features(ctrl, NVME_FEAT_TIMESTAMP, 0, &ts, sizeof(ts),
			NULL);
	if (ret)
		dev_warn_once(ctrl->device,
			"could not set timestamp (%d)\n", ret);
	return ret;
}

static int nvme_configure_acre(struct nvme_ctrl *ctrl)
{
	struct nvme_feat_host_behavior *host;
	int ret;

	/* Don't bother enabling the feature if retry delay is not reported */
	if (!ctrl->crdt[0])
		return 0;

	host = kzalloc(sizeof(*host), GFP_KERNEL);
	if (!host)
		return 0;

	host->acre = NVME_ENABLE_ACRE;
	ret = nvme_set_features(ctrl, NVME_FEAT_HOST_BEHAVIOR, 0,
				host, sizeof(*host), NULL);
	kfree(host);
	return ret;
}

static int nvme_configure_apst(struct nvme_ctrl *ctrl)
{
	/*
	 * APST (Autonomous Power State Transition) lets us program a
	 * table of power state transitions that the controller will
	 * perform automatically.  We configure it with a simple
	 * heuristic: we are willing to spend at most 2% of the time
	 * transitioning between power states.  Therefore, when running
	 * in any given state, we will enter the next lower-power
	 * non-operational state after waiting 50 * (enlat + exlat)
	 * microseconds, as long as that state's exit latency is under
	 * the requested maximum latency.
	 *
	 * We will not autonomously enter any non-operational state for
	 * which the total latency exceeds ps_max_latency_us.  Users
	 * can set ps_max_latency_us to zero to turn off APST.
	 */

	unsigned apste;
	struct nvme_feat_auto_pst *table;
	u64 max_lat_us = 0;
	int max_ps = -1;
	int ret;

	/*
	 * If APST isn't supported or if we haven't been initialized yet,
	 * then don't do anything.
	 */
	if (!ctrl->apsta)
		return 0;

	if (ctrl->npss > 31) {
		dev_warn(ctrl->device, "NPSS is invalid; not using APST\n");
		return 0;
	}

	table = kzalloc(sizeof(*table), GFP_KERNEL);
	if (!table)
		return 0;

	if (!ctrl->apst_enabled || ctrl->ps_max_latency_us == 0) {
		/* Turn off APST. */
		apste = 0;
		dev_dbg(ctrl->device, "APST disabled\n");
	} else {
		__le64 target = cpu_to_le64(0);
		int state;

		/*
		 * Walk through all states from lowest- to highest-power.
		 * According to the spec, lower-numbered states use more
		 * power.  NPSS, despite the name, is the index of the
		 * lowest-power state, not the number of states.
		 */
		for (state = (int)ctrl->npss; state >= 0; state--) {
			u64 total_latency_us, exit_latency_us, transition_ms;

			if (target)
				table->entries[state] = target;

			/*
			 * Don't allow transitions to the deepest state
			 * if it's quirked off.
			 */
			if (state == ctrl->npss &&
			    (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS))
				continue;

			/*
			 * Is this state a useful non-operational state for
			 * higher-power states to autonomously transition to?
			 */
			if (!(ctrl->psd[state].flags &
			      NVME_PS_FLAGS_NON_OP_STATE))
				continue;

			exit_latency_us =
				(u64)le32_to_cpu(ctrl->psd[state].exit_lat);
			if (exit_latency_us > ctrl->ps_max_latency_us)
				continue;

			total_latency_us =
				exit_latency_us +
				le32_to_cpu(ctrl->psd[state].entry_lat);

			/*
			 * This state is good.  Use it as the APST idle
			 * target for higher power states.
			 */
			transition_ms = total_latency_us + 19;
			do_div(transition_ms, 20);
			if (transition_ms > (1 << 24) - 1)
				transition_ms = (1 << 24) - 1;

			target = cpu_to_le64((state << 3) |
					     (transition_ms << 8));

			if (max_ps == -1)
				max_ps = state;

			if (total_latency_us > max_lat_us)
				max_lat_us = total_latency_us;
		}

		apste = 1;

		if (max_ps == -1) {
			dev_dbg(ctrl->device, "APST enabled but no non-operational states are available\n");
		} else {
			dev_dbg(ctrl->device, "APST enabled: max PS = %d, max round-trip latency = %lluus, table = %*phN\n",
				max_ps, max_lat_us, (int)sizeof(*table), table);
		}
	}

	ret = nvme_set_features(ctrl, NVME_FEAT_AUTO_PST, apste,
				table, sizeof(*table), NULL);
	if (ret)
		dev_err(ctrl->device, "failed to set APST feature (%d)\n", ret);

	kfree(table);
	return ret;
}

static void nvme_set_latency_tolerance(struct device *dev, s32 val)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
	u64 latency;

	switch (val) {
	case PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT:
	case PM_QOS_LATENCY_ANY:
		latency = U64_MAX;
		break;

	default:
		latency = val;
	}

	if (ctrl->ps_max_latency_us != latency) {
		ctrl->ps_max_latency_us = latency;
		nvme_configure_apst(ctrl);
	}
}

struct nvme_core_quirk_entry {
	/*
	 * NVMe model and firmware strings are padded with spaces.  For
	 * simplicity, strings in the quirk table are padded with NULLs
	 * instead.
	 */
	u16 vid;
	const char *mn;
	const char *fr;
	unsigned long quirks;
};

static const struct nvme_core_quirk_entry core_quirks[] = {
	{
		/*
		 * This Toshiba device seems to die using any APST states.  See:
		 * https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1678184/comments/11
		 */
		.vid = 0x1179,
		.mn = "THNSF5256GPUK TOSHIBA",
		.quirks = NVME_QUIRK_NO_APST,
	},
	{
		/*
		 * This LiteON CL1-3D*-Q11 firmware version has a race
		 * condition associated with actions related to suspend to idle
		 * LiteON has resolved the problem in future firmware
		 */
		.vid = 0x14a4,
		.fr = "22301111",
		.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
	}
};

/* match is null-terminated but idstr is space-padded. */
static bool string_matches(const char *idstr, const char *match, size_t len)
{
	size_t matchlen;

	if (!match)
		return true;

	matchlen = strlen(match);
	WARN_ON_ONCE(matchlen > len);

	if (memcmp(idstr, match, matchlen))
		return false;

	for (; matchlen < len; matchlen++)
		if (idstr[matchlen] != ' ')
			return false;

	return true;
}

static bool quirk_matches(const struct nvme_id_ctrl *id,
			  const struct nvme_core_quirk_entry *q)
{
	return q->vid == le16_to_cpu(id->vid) &&
		string_matches(id->mn, q->mn, sizeof(id->mn)) &&
		string_matches(id->fr, q->fr, sizeof(id->fr));
}

static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ctrl,
		struct nvme_id_ctrl *id)
{
	size_t nqnlen;
	int off;

	if(!(ctrl->quirks & NVME_QUIRK_IGNORE_DEV_SUBNQN)) {
		nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE);
		if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) {
			strlcpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE);
			return;
		}

		if (ctrl->vs >= NVME_VS(1, 2, 1))
			dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n");
	}

	/* Generate a "fake" NQN per Figure 254 in NVMe 1.3 + ECN 001 */
	off = snprintf(subsys->subnqn, NVMF_NQN_SIZE,
			"nqn.2014.08.org.nvmexpress:%04x%04x",
			le16_to_cpu(id->vid), le16_to_cpu(id->ssvid));
	memcpy(subsys->subnqn + off, id->sn, sizeof(id->sn));
	off += sizeof(id->sn);
	memcpy(subsys->subnqn + off, id->mn, sizeof(id->mn));
	off += sizeof(id->mn);
	memset(subsys->subnqn + off, 0, sizeof(subsys->subnqn) - off);
}

static void nvme_release_subsystem(struct device *dev)
{
	struct nvme_subsystem *subsys =
		container_of(dev, struct nvme_subsystem, dev);

	if (subsys->instance >= 0)
		ida_simple_remove(&nvme_instance_ida, subsys->instance);
	kfree(subsys);
}

static void nvme_destroy_subsystem(struct kref *ref)
{
	struct nvme_subsystem *subsys =
			container_of(ref, struct nvme_subsystem, ref);

	mutex_lock(&nvme_subsystems_lock);
	list_del(&subsys->entry);
	mutex_unlock(&nvme_subsystems_lock);

	ida_destroy(&subsys->ns_ida);
	device_del(&subsys->dev);
	put_device(&subsys->dev);
}

static void nvme_put_subsystem(struct nvme_subsystem *subsys)
{
	kref_put(&subsys->ref, nvme_destroy_subsystem);
}

static struct nvme_subsystem *__nvme_find_get_subsystem(const char *subsysnqn)
{
	struct nvme_subsystem *subsys;

	lockdep_assert_held(&nvme_subsystems_lock);

	/*
	 * Fail matches for discovery subsystems. This results
	 * in each discovery controller bound to a unique subsystem.
	 * This avoids issues with validating controller values
	 * that can only be true when there is a single unique subsystem.
	 * There may be multiple and completely independent entities
	 * that provide discovery controllers.
	 */
	if (!strcmp(subsysnqn, NVME_DISC_SUBSYS_NAME))
		return NULL;

	list_for_each_entry(subsys, &nvme_subsystems, entry) {
		if (strcmp(subsys->subnqn, subsysnqn))
			continue;
		if (!kref_get_unless_zero(&subsys->ref))
			continue;
		return subsys;
	}

	return NULL;
}

#define SUBSYS_ATTR_RO(_name, _mode, _show)			\
	struct device_attribute subsys_attr_##_name = \
		__ATTR(_name, _mode, _show, NULL)

static ssize_t nvme_subsys_show_nqn(struct device *dev,
				    struct device_attribute *attr,
				    char *buf)
{
	struct nvme_subsystem *subsys =
		container_of(dev, struct nvme_subsystem, dev);

	return snprintf(buf, PAGE_SIZE, "%s\n", subsys->subnqn);
}
static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn);

#define nvme_subsys_show_str_function(field)				\
static ssize_t subsys_##field##_show(struct device *dev,		\
			    struct device_attribute *attr, char *buf)	\
{									\
	struct nvme_subsystem *subsys =					\
		container_of(dev, struct nvme_subsystem, dev);		\
	return sprintf(buf, "%.*s\n",					\
		       (int)sizeof(subsys->field), subsys->field);	\
}									\
static SUBSYS_ATTR_RO(field, S_IRUGO, subsys_##field##_show);

nvme_subsys_show_str_function(model);
nvme_subsys_show_str_function(serial);
nvme_subsys_show_str_function(firmware_rev);

static struct attribute *nvme_subsys_attrs[] = {
	&subsys_attr_model.attr,
	&subsys_attr_serial.attr,
	&subsys_attr_firmware_rev.attr,
	&subsys_attr_subsysnqn.attr,
#ifdef CONFIG_NVME_MULTIPATH
	&subsys_attr_iopolicy.attr,
#endif
	NULL,
};

static struct attribute_group nvme_subsys_attrs_group = {
	.attrs = nvme_subsys_attrs,
};

static const struct attribute_group *nvme_subsys_attrs_groups[] = {
	&nvme_subsys_attrs_group,
	NULL,
};

static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
		struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
{
	struct nvme_ctrl *tmp;

	lockdep_assert_held(&nvme_subsystems_lock);

	list_for_each_entry(tmp, &subsys->ctrls, subsys_entry) {
		if (nvme_state_terminal(tmp))
			continue;

		if (tmp->cntlid == ctrl->cntlid) {
			dev_err(ctrl->device,
				"Duplicate cntlid %u with %s, rejecting\n",
				ctrl->cntlid, dev_name(tmp->device));
			return false;
		}

		if ((id->cmic & NVME_CTRL_CMIC_MULTI_CTRL) ||
		    (ctrl->opts && ctrl->opts->discovery_nqn))
			continue;

		dev_err(ctrl->device,
			"Subsystem does not support multiple controllers\n");
		return false;
	}

	return true;
}

static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
{
	struct nvme_subsystem *subsys, *found;
	int ret;

	subsys = kzalloc(sizeof(*subsys), GFP_KERNEL);
	if (!subsys)
		return -ENOMEM;

	subsys->instance = -1;
	mutex_init(&subsys->lock);
	kref_init(&subsys->ref);
	INIT_LIST_HEAD(&subsys->ctrls);
	INIT_LIST_HEAD(&subsys->nsheads);
	nvme_init_subnqn(subsys, ctrl, id);
	memcpy(subsys->serial, id->sn, sizeof(subsys->serial));
	memcpy(subsys->model, id->mn, sizeof(subsys->model));
	memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev));
	subsys->vendor_id = le16_to_cpu(id->vid);
	subsys->cmic = id->cmic;
	subsys->awupf = le16_to_cpu(id->awupf);
#ifdef CONFIG_NVME_MULTIPATH
	subsys->iopolicy = NVME_IOPOLICY_NUMA;
#endif

	subsys->dev.class = nvme_subsys_class;
	subsys->dev.release = nvme_release_subsystem;
	subsys->dev.groups = nvme_subsys_attrs_groups;
	dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance);
	device_initialize(&subsys->dev);

	mutex_lock(&nvme_subsystems_lock);
	found = __nvme_find_get_subsystem(subsys->subnqn);
	if (found) {
		put_device(&subsys->dev);
		subsys = found;

		if (!nvme_validate_cntlid(subsys, ctrl, id)) {
			ret = -EINVAL;
			goto out_put_subsystem;
		}
	} else {
		ret = device_add(&subsys->dev);
		if (ret) {
			dev_err(ctrl->device,
				"failed to register subsystem device.\n");
			put_device(&subsys->dev);
			goto out_unlock;
		}
		ida_init(&subsys->ns_ida);
		list_add_tail(&subsys->entry, &nvme_subsystems);
	}

	ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
				dev_name(ctrl->device));
	if (ret) {
		dev_err(ctrl->device,
			"failed to create sysfs link from subsystem.\n");
		goto out_put_subsystem;
	}

	if (!found)
		subsys->instance = ctrl->instance;
	ctrl->subsys = subsys;
	list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);
	mutex_unlock(&nvme_subsystems_lock);
	return 0;

out_put_subsystem:
	nvme_put_subsystem(subsys);
out_unlock:
	mutex_unlock(&nvme_subsystems_lock);
	return ret;
}

int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
		void *log, size_t size, u64 offset)
{
	struct nvme_command c = { };
	u32 dwlen = nvme_bytes_to_numd(size);

	c.get_log_page.opcode = nvme_admin_get_log_page;
	c.get_log_page.nsid = cpu_to_le32(nsid);
	c.get_log_page.lid = log_page;
	c.get_log_page.lsp = lsp;
	c.get_log_page.numdl = cpu_to_le16(dwlen & ((1 << 16) - 1));
	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
	c.get_log_page.lpou = cpu_to_le32(upper_32_bits(offset));

	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
}

static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
{
	int ret;

	if (!ctrl->effects)
		ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);

	if (!ctrl->effects)
		return 0;

	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
			ctrl->effects, sizeof(*ctrl->effects), 0);
	if (ret) {
		kfree(ctrl->effects);
		ctrl->effects = NULL;
	}
	return ret;
}

/*
 * Initialize the cached copies of the Identify data and various controller
 * register in our nvme_ctrl structure.  This should be called as soon as
 * the admin queue is fully up and running.
 */
int nvme_init_identify(struct nvme_ctrl *ctrl)
{
	struct nvme_id_ctrl *id;
	int ret, page_shift;
	u32 max_hw_sectors;
	bool prev_apst_enabled;

	ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs);
	if (ret) {
		dev_err(ctrl->device, "Reading VS failed (%d)\n", ret);
		return ret;
	}
	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
	ctrl->sqsize = min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);

	if (ctrl->vs >= NVME_VS(1, 1, 0))
		ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap);

	ret = nvme_identify_ctrl(ctrl, &id);
	if (ret) {
		dev_err(ctrl->device, "Identify Controller failed (%d)\n", ret);
		return -EIO;
	}

	if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
		ret = nvme_get_effects_log(ctrl);
		if (ret < 0)
			goto out_free;
	}

	if (!(ctrl->ops->flags & NVME_F_FABRICS))
		ctrl->cntlid = le16_to_cpu(id->cntlid);

	if (!ctrl->identified) {
		int i;

		ret = nvme_init_subsystem(ctrl, id);
		if (ret)
			goto out_free;

		/*
		 * Check for quirks.  Quirk can depend on firmware version,
		 * so, in principle, the set of quirks present can change
		 * across a reset.  As a possible future enhancement, we
		 * could re-scan for quirks every time we reinitialize
		 * the device, but we'd have to make sure that the driver
		 * behaves intelligently if the quirks change.
		 */
		for (i = 0; i < ARRAY_SIZE(core_quirks); i++) {
			if (quirk_matches(id, &core_quirks[i]))
				ctrl->quirks |= core_quirks[i].quirks;
		}
	}

	if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) {
		dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
		ctrl->quirks &= ~NVME_QUIRK_NO_DEEPEST_PS;
	}

	ctrl->crdt[0] = le16_to_cpu(id->crdt1);
	ctrl->crdt[1] = le16_to_cpu(id->crdt2);
	ctrl->crdt[2] = le16_to_cpu(id->crdt3);

	ctrl->oacs = le16_to_cpu(id->oacs);
	ctrl->oncs = le16_to_cpu(id->oncs);
	ctrl->mtfa = le16_to_cpu(id->mtfa);
	ctrl->oaes = le32_to_cpu(id->oaes);
	ctrl->wctemp = le16_to_cpu(id->wctemp);
	ctrl->cctemp = le16_to_cpu(id->cctemp);

	atomic_set(&ctrl->abort_limit, id->acl + 1);
	ctrl->vwc = id->vwc;
	if (id->mdts)
		max_hw_sectors = 1 << (id->mdts + page_shift - 9);
	else
		max_hw_sectors = UINT_MAX;
	ctrl->max_hw_sectors =
		min_not_zero(ctrl->max_hw_sectors, max_hw_sectors);

	nvme_set_queue_limits(ctrl, ctrl->admin_q);
	ctrl->sgls = le32_to_cpu(id->sgls);
	ctrl->kas = le16_to_cpu(id->kas);
	ctrl->max_namespaces = le32_to_cpu(id->mnan);
	ctrl->ctratt = le32_to_cpu(id->ctratt);

	if (id->rtd3e) {
		/* us -> s */
		u32 transition_time = le32_to_cpu(id->rtd3e) / 1000000;

		ctrl->shutdown_timeout = clamp_t(unsigned int, transition_time,
						 shutdown_timeout, 60);

		if (ctrl->shutdown_timeout != shutdown_timeout)
			dev_info(ctrl->device,
				 "Shutdown timeout set to %u seconds\n",
				 ctrl->shutdown_timeout);
	} else
		ctrl->shutdown_timeout = shutdown_timeout;

	ctrl->npss = id->npss;
	ctrl->apsta = id->apsta;
	prev_apst_enabled = ctrl->apst_enabled;
	if (ctrl->quirks & NVME_QUIRK_NO_APST) {
		if (force_apst && id->apsta) {
			dev_warn(ctrl->device, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
			ctrl->apst_enabled = true;
		} else {
			ctrl->apst_enabled = false;
		}
	} else {
		ctrl->apst_enabled = id->apsta;
	}
	memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd));

	if (ctrl->ops->flags & NVME_F_FABRICS) {
		ctrl->icdoff = le16_to_cpu(id->icdoff);
		ctrl->ioccsz = le32_to_cpu(id->ioccsz);
		ctrl->iorcsz = le32_to_cpu(id->iorcsz);
		ctrl->maxcmd = le16_to_cpu(id->maxcmd);

		/*
		 * In fabrics we need to verify the cntlid matches the
		 * admin connect
		 */
		if (ctrl->cntlid != le16_to_cpu(id->cntlid)) {
			dev_err(ctrl->device,
				"Mismatching cntlid: Connect %u vs Identify "
				"%u, rejecting\n",
				ctrl->cntlid, le16_to_cpu(id->cntlid));
			ret = -EINVAL;
			goto out_free;
		}

		if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
			dev_err(ctrl->device,
				"keep-alive support is mandatory for fabrics\n");
			ret = -EINVAL;
			goto out_free;
		}
	} else {
		ctrl->hmpre = le32_to_cpu(id->hmpre);
		ctrl->hmmin = le32_to_cpu(id->hmmin);
		ctrl->hmminds = le32_to_cpu(id->hmminds);
		ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
	}

	ret = nvme_mpath_init(ctrl, id);
	kfree(id);

	if (ret < 0)
		return ret;

	if (ctrl->apst_enabled && !prev_apst_enabled)
		dev_pm_qos_expose_latency_tolerance(ctrl->device);
	else if (!ctrl->apst_enabled && prev_apst_enabled)
		dev_pm_qos_hide_latency_tolerance(ctrl->device);

	ret = nvme_configure_apst(ctrl);
	if (ret < 0)
		return ret;
	
	ret = nvme_configure_timestamp(ctrl);
	if (ret < 0)
		return ret;

	ret = nvme_configure_directives(ctrl);
	if (ret < 0)
		return ret;

	ret = nvme_configure_acre(ctrl);
	if (ret < 0)
		return ret;

	if (!ctrl->identified)
		nvme_hwmon_init(ctrl);

	ctrl->identified = true;

	return 0;

out_free:
	kfree(id);
	return ret;
}
EXPORT_SYMBOL_GPL(nvme_init_identify);

static int nvme_dev_open(struct inode *inode, struct file *file)
{
	struct nvme_ctrl *ctrl =
		container_of(inode->i_cdev, struct nvme_ctrl, cdev);

	switch (ctrl->state) {
	case NVME_CTRL_LIVE:
		break;
	default:
		return -EWOULDBLOCK;
	}

	file->private_data = ctrl;
	return 0;
}

static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp)
{
	struct nvme_ns *ns;
	int ret;

	down_read(&ctrl->namespaces_rwsem);
	if (list_empty(&ctrl->namespaces)) {
		ret = -ENOTTY;
		goto out_unlock;
	}

	ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
	if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) {
		dev_warn(ctrl->device,
			"NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n");
		ret = -EINVAL;
		goto out_unlock;
	}

	dev_warn(ctrl->device,
		"using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n");
	kref_get(&ns->kref);
	up_read(&ctrl->namespaces_rwsem);

	ret = nvme_user_cmd(ctrl, ns, argp);
	nvme_put_ns(ns);
	return ret;

out_unlock:
	up_read(&ctrl->namespaces_rwsem);
	return ret;
}

static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
		unsigned long arg)
{
	struct nvme_ctrl *ctrl = file->private_data;
	void __user *argp = (void __user *)arg;

	switch (cmd) {
	case NVME_IOCTL_ADMIN_CMD:
		return nvme_user_cmd(ctrl, NULL, argp);
	case NVME_IOCTL_ADMIN64_CMD:
		return nvme_user_cmd64(ctrl, NULL, argp);
	case NVME_IOCTL_IO_CMD:
		return nvme_dev_user_cmd(ctrl, argp);
	case NVME_IOCTL_RESET:
		dev_warn(ctrl->device, "resetting controller\n");
		return nvme_reset_ctrl_sync(ctrl);
	case NVME_IOCTL_SUBSYS_RESET:
		return nvme_reset_subsystem(ctrl);
	case NVME_IOCTL_RESCAN:
		nvme_queue_scan(ctrl);
		return 0;
	default:
		return -ENOTTY;
	}
}

static const struct file_operations nvme_dev_fops = {
	.owner		= THIS_MODULE,
	.open		= nvme_dev_open,
	.unlocked_ioctl	= nvme_dev_ioctl,
	.compat_ioctl	= compat_ptr_ioctl,
};

static ssize_t nvme_sysfs_reset(struct device *dev,
				struct device_attribute *attr, const char *buf,
				size_t count)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
	int ret;

	ret = nvme_reset_ctrl_sync(ctrl);
	if (ret < 0)
		return ret;
	return count;
}
static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);

static ssize_t nvme_sysfs_rescan(struct device *dev,
				struct device_attribute *attr, const char *buf,
				size_t count)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

	nvme_queue_scan(ctrl);
	return count;
}
static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan);

static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
{
	struct gendisk *disk = dev_to_disk(dev);

	if (disk->fops == &nvme_fops)
		return nvme_get_ns_from_dev(dev)->head;
	else
		return disk->private_data;
}

static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
		char *buf)
{
	struct nvme_ns_head *head = dev_to_ns_head(dev);
	struct nvme_ns_ids *ids = &head->ids;
	struct nvme_subsystem *subsys = head->subsys;
	int serial_len = sizeof(subsys->serial);
	int model_len = sizeof(subsys->model);

	if (!uuid_is_null(&ids->uuid))
		return sprintf(buf, "uuid.%pU\n", &ids->uuid);

	if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
		return sprintf(buf, "eui.%16phN\n", ids->nguid);

	if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
		return sprintf(buf, "eui.%8phN\n", ids->eui64);

	while (serial_len > 0 && (subsys->serial[serial_len - 1] == ' ' ||
				  subsys->serial[serial_len - 1] == '\0'))
		serial_len--;
	while (model_len > 0 && (subsys->model[model_len - 1] == ' ' ||
				 subsys->model[model_len - 1] == '\0'))
		model_len--;

	return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id,
		serial_len, subsys->serial, model_len, subsys->model,
		head->ns_id);
}
static DEVICE_ATTR_RO(wwid);

static ssize_t nguid_show(struct device *dev, struct device_attribute *attr,
		char *buf)
{
	return sprintf(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid);
}
static DEVICE_ATTR_RO(nguid);

static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
		char *buf)
{
	struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids;

	/* For backward compatibility expose the NGUID to userspace if
	 * we have no UUID set
	 */
	if (uuid_is_null(&ids->uuid)) {
		printk_ratelimited(KERN_WARNING
				   "No UUID available providing old NGUID\n");
		return sprintf(buf, "%pU\n", ids->nguid);
	}
	return sprintf(buf, "%pU\n", &ids->uuid);
}
static DEVICE_ATTR_RO(uuid);

static ssize_t eui_show(struct device *dev, struct device_attribute *attr,
		char *buf)
{
	return sprintf(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64);
}
static DEVICE_ATTR_RO(eui);

static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
		char *buf)
{
	return sprintf(buf, "%d\n", dev_to_ns_head(dev)->ns_id);
}
static DEVICE_ATTR_RO(nsid);

static struct attribute *nvme_ns_id_attrs[] = {
	&dev_attr_wwid.attr,
	&dev_attr_uuid.attr,
	&dev_attr_nguid.attr,
	&dev_attr_eui.attr,
	&dev_attr_nsid.attr,
#ifdef CONFIG_NVME_MULTIPATH
	&dev_attr_ana_grpid.attr,
	&dev_attr_ana_state.attr,
#endif
	NULL,
};

static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
		struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, struct device, kobj);
	struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids;

	if (a == &dev_attr_uuid.attr) {
		if (uuid_is_null(&ids->uuid) &&
		    !memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
			return 0;
	}
	if (a == &dev_attr_nguid.attr) {
		if (!memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
			return 0;
	}
	if (a == &dev_attr_eui.attr) {
		if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
			return 0;
	}
#ifdef CONFIG_NVME_MULTIPATH
	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
		if (dev_to_disk(dev)->fops != &nvme_fops) /* per-path attr */
			return 0;
		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
			return 0;
	}
#endif
	return a->mode;
}

static const struct attribute_group nvme_ns_id_attr_group = {
	.attrs		= nvme_ns_id_attrs,
	.is_visible	= nvme_ns_id_attrs_are_visible,
};

const struct attribute_group *nvme_ns_id_attr_groups[] = {
	&nvme_ns_id_attr_group,
#ifdef CONFIG_NVM
	&nvme_nvm_attr_group,
#endif
	NULL,
};

#define nvme_show_str_function(field)						\
static ssize_t  field##_show(struct device *dev,				\
			    struct device_attribute *attr, char *buf)		\
{										\
        struct nvme_ctrl *ctrl = dev_get_drvdata(dev);				\
        return sprintf(buf, "%.*s\n",						\
		(int)sizeof(ctrl->subsys->field), ctrl->subsys->field);		\
}										\
static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);

nvme_show_str_function(model);
nvme_show_str_function(serial);
nvme_show_str_function(firmware_rev);

#define nvme_show_int_function(field)						\
static ssize_t  field##_show(struct device *dev,				\
			    struct device_attribute *attr, char *buf)		\
{										\
        struct nvme_ctrl *ctrl = dev_get_drvdata(dev);				\
        return sprintf(buf, "%d\n", ctrl->field);	\
}										\
static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);

nvme_show_int_function(cntlid);
nvme_show_int_function(numa_node);
nvme_show_int_function(queue_count);
nvme_show_int_function(sqsize);

static ssize_t nvme_sysfs_delete(struct device *dev,
				struct device_attribute *attr, const char *buf,
				size_t count)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

	/* Can't delete non-created controllers */
	if (!ctrl->created)
		return -EBUSY;

	if (device_remove_file_self(dev, attr))
		nvme_delete_ctrl_sync(ctrl);
	return count;
}
static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete);

static ssize_t nvme_sysfs_show_transport(struct device *dev,
					 struct device_attribute *attr,
					 char *buf)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->ops->name);
}
static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL);

static ssize_t nvme_sysfs_show_state(struct device *dev,
				     struct device_attribute *attr,
				     char *buf)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
	static const char *const state_name[] = {
		[NVME_CTRL_NEW]		= "new",
		[NVME_CTRL_LIVE]	= "live",
		[NVME_CTRL_RESETTING]	= "resetting",
		[NVME_CTRL_CONNECTING]	= "connecting",
		[NVME_CTRL_DELETING]	= "deleting",
		[NVME_CTRL_DEAD]	= "dead",
	};

	if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
	    state_name[ctrl->state])
		return sprintf(buf, "%s\n", state_name[ctrl->state]);

	return sprintf(buf, "unknown state\n");
}

static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL);

static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev,
					 struct device_attribute *attr,
					 char *buf)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->subsys->subnqn);
}
static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL);

static ssize_t nvme_sysfs_show_hostnqn(struct device *dev,
					struct device_attribute *attr,
					char *buf)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->opts->host->nqn);
}
static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL);

static ssize_t nvme_sysfs_show_hostid(struct device *dev,
					struct device_attribute *attr,
					char *buf)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

	return snprintf(buf, PAGE_SIZE, "%pU\n", &ctrl->opts->host->id);
}
static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL);

static ssize_t nvme_sysfs_show_address(struct device *dev,
					 struct device_attribute *attr,
					 char *buf)
{
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

	return ctrl->ops->get_address(ctrl, buf, PAGE_SIZE);
}
static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL);

static struct attribute *nvme_dev_attrs[] = {
	&dev_attr_reset_controller.attr,
	&dev_attr_rescan_controller.attr,
	&dev_attr_model.attr,
	&dev_attr_serial.attr,
	&dev_attr_firmware_rev.attr,
	&dev_attr_cntlid.attr,
	&dev_attr_delete_controller.attr,
	&dev_attr_transport.attr,
	&dev_attr_subsysnqn.attr,
	&dev_attr_address.attr,
	&dev_attr_state.attr,
	&dev_attr_numa_node.attr,
	&dev_attr_queue_count.attr,
	&dev_attr_sqsize.attr,
	&dev_attr_hostnqn.attr,
	&dev_attr_hostid.attr,
	NULL
};

static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
		struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, struct device, kobj);
	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);

	if (a == &dev_attr_delete_controller.attr && !ctrl->ops->delete_ctrl)
		return 0;
	if (a == &dev_attr_address.attr && !ctrl->ops->get_address)
		return 0;
	if (a == &dev_attr_hostnqn.attr && !ctrl->opts)
		return 0;
	if (a == &dev_attr_hostid.attr && !ctrl->opts)
		return 0;

	return a->mode;
}

static struct attribute_group nvme_dev_attrs_group = {
	.attrs		= nvme_dev_attrs,
	.is_visible	= nvme_dev_attrs_are_visible,
};

static const struct attribute_group *nvme_dev_attr_groups[] = {
	&nvme_dev_attrs_group,
	NULL,
};

static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
		unsigned nsid)
{
	struct nvme_ns_head *h;

	lockdep_assert_held(&subsys->lock);

	list_for_each_entry(h, &subsys->nsheads, entry) {
		if (h->ns_id == nsid && kref_get_unless_zero(&h->ref))
			return h;
	}

	return NULL;
}

static int __nvme_check_ids(struct nvme_subsystem *subsys,
		struct nvme_ns_head *new)
{
	struct nvme_ns_head *h;

	lockdep_assert_held(&subsys->lock);

	list_for_each_entry(h, &subsys->nsheads, entry) {
		if (nvme_ns_ids_valid(&new->ids) &&
		    nvme_ns_ids_equal(&new->ids, &h->ids))
			return -EINVAL;
	}

	return 0;
}

static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
		unsigned nsid, struct nvme_ns_ids *ids)
{
	struct nvme_ns_head *head;
	size_t size = sizeof(*head);
	int ret = -ENOMEM;

#ifdef CONFIG_NVME_MULTIPATH
	size += num_possible_nodes() * sizeof(struct nvme_ns *);
#endif

	head = kzalloc(size, GFP_KERNEL);
	if (!head)
		goto out;
	ret = ida_simple_get(&ctrl->subsys->ns_ida, 1, 0, GFP_KERNEL);
	if (ret < 0)
		goto out_free_head;
	head->instance = ret;
	INIT_LIST_HEAD(&head->list);
	ret = init_srcu_struct(&head->srcu);
	if (ret)
		goto out_ida_remove;
	head->subsys = ctrl->subsys;
	head->ns_id = nsid;
	head->ids = *ids;
	kref_init(&head->ref);

	ret = __nvme_check_ids(ctrl->subsys, head);
	if (ret) {
		dev_err(ctrl->device,
			"duplicate IDs for nsid %d\n", nsid);
		goto out_cleanup_srcu;
	}

	ret = nvme_mpath_alloc_disk(ctrl, head);
	if (ret)
		goto out_cleanup_srcu;

	list_add_tail(&head->entry, &ctrl->subsys->nsheads);

	kref_get(&ctrl->subsys->ref);

	return head;
out_cleanup_srcu:
	cleanup_srcu_struct(&head->srcu);
out_ida_remove:
	ida_simple_remove(&ctrl->subsys->ns_ida, head->instance);
out_free_head:
	kfree(head);
out:
	if (ret > 0)
		ret = blk_status_to_errno(nvme_error_status(ret));
	return ERR_PTR(ret);
}

static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
		struct nvme_id_ns *id)
{
	struct nvme_ctrl *ctrl = ns->ctrl;
	bool is_shared = id->nmic & NVME_NS_NMIC_SHARED;
	struct nvme_ns_head *head = NULL;
	struct nvme_ns_ids ids;
	int ret = 0;

	ret = nvme_report_ns_ids(ctrl, nsid, id, &ids);
	if (ret) {
		if (ret < 0)
			return ret;
		return blk_status_to_errno(nvme_error_status(ret));
	}

	mutex_lock(&ctrl->subsys->lock);
	head = nvme_find_ns_head(ctrl->subsys, nsid);
	if (!head) {
		head = nvme_alloc_ns_head(ctrl, nsid, &ids);
		if (IS_ERR(head)) {
			ret = PTR_ERR(head);
			goto out_unlock;
		}
		head->shared = is_shared;
	} else {
		ret = -EINVAL;
		if (!is_shared || !head->shared) {
			dev_err(ctrl->device,
				"Duplicate unshared namespace %d\n", nsid);
			goto out_put_ns_head;
		}
		if (!nvme_ns_ids_equal(&head->ids, &ids)) {
			dev_err(ctrl->device,
				"IDs don't match for shared namespace %d\n",
					nsid);
			goto out_put_ns_head;
		}
	}

	list_add_tail(&ns->siblings, &head->list);
	ns->head = head;
	mutex_unlock(&ctrl->subsys->lock);
	return 0;

out_put_ns_head:
	nvme_put_ns_head(head);
out_unlock:
	mutex_unlock(&ctrl->subsys->lock);
	return ret;
}

static int ns_cmp(void *priv, struct list_head *a, struct list_head *b)
{
	struct nvme_ns *nsa = container_of(a, struct nvme_ns, list);
	struct nvme_ns *nsb = container_of(b, struct nvme_ns, list);

	return nsa->head->ns_id - nsb->head->ns_id;
}

static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
	struct nvme_ns *ns, *ret = NULL;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list) {
		if (ns->head->ns_id == nsid) {
			if (!kref_get_unless_zero(&ns->kref))
				continue;
			ret = ns;
			break;
		}
		if (ns->head->ns_id > nsid)
			break;
	}
	up_read(&ctrl->namespaces_rwsem);
	return ret;
}

static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
	struct nvme_ns *ns;
	struct gendisk *disk;
	struct nvme_id_ns *id;
	char disk_name[DISK_NAME_LEN];
	int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT, ret;

	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
	if (!ns)
		return;

	ns->queue = blk_mq_init_queue(ctrl->tagset);
	if (IS_ERR(ns->queue))
		goto out_free_ns;

	if (ctrl->opts && ctrl->opts->data_digest)
		ns->queue->backing_dev_info->capabilities
			|= BDI_CAP_STABLE_WRITES;

	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
		blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);

	ns->queue->queuedata = ns;
	ns->ctrl = ctrl;

	kref_init(&ns->kref);
	ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */

	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
	nvme_set_queue_limits(ctrl, ns->queue);

	ret = nvme_identify_ns(ctrl, nsid, &id);
	if (ret)
		goto out_free_queue;

	if (id->ncap == 0)	/* no namespace (legacy quirk) */
		goto out_free_id;

	ret = nvme_init_ns_head(ns, nsid, id);
	if (ret)
		goto out_free_id;
	nvme_set_disk_name(disk_name, ns, ctrl, &flags);

	disk = alloc_disk_node(0, node);
	if (!disk)
		goto out_unlink_ns;

	disk->fops = &nvme_fops;
	disk->private_data = ns;
	disk->queue = ns->queue;
	disk->flags = flags;
	memcpy(disk->disk_name, disk_name, DISK_NAME_LEN);
	ns->disk = disk;

	if (__nvme_revalidate_disk(disk, id))
		goto out_put_disk;

	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
		ret = nvme_nvm_register(ns, disk_name, node);
		if (ret) {
			dev_warn(ctrl->device, "LightNVM init failure\n");
			goto out_put_disk;
		}
	}

	down_write(&ctrl->namespaces_rwsem);
	list_add_tail(&ns->list, &ctrl->namespaces);
	up_write(&ctrl->namespaces_rwsem);

	nvme_get_ctrl(ctrl);

	device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups);

	nvme_mpath_add_disk(ns, id);
	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
	kfree(id);

	return;
 out_put_disk:
	/* prevent double queue cleanup */
	ns->disk->queue = NULL;
	put_disk(ns->disk);
 out_unlink_ns:
	mutex_lock(&ctrl->subsys->lock);
	list_del_rcu(&ns->siblings);
	if (list_empty(&ns->head->list))
		list_del_init(&ns->head->entry);
	mutex_unlock(&ctrl->subsys->lock);
	nvme_put_ns_head(ns->head);
 out_free_id:
	kfree(id);
 out_free_queue:
	blk_cleanup_queue(ns->queue);
 out_free_ns:
	kfree(ns);
}

static void nvme_ns_remove(struct nvme_ns *ns)
{
	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
		return;

	nvme_fault_inject_fini(&ns->fault_inject);

	mutex_lock(&ns->ctrl->subsys->lock);
	list_del_rcu(&ns->siblings);
	if (list_empty(&ns->head->list))
		list_del_init(&ns->head->entry);
	mutex_unlock(&ns->ctrl->subsys->lock);

	synchronize_rcu(); /* guarantee not available in head->list */
	nvme_mpath_clear_current_path(ns);
	synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */

	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
		del_gendisk(ns->disk);
		blk_cleanup_queue(ns->queue);
		if (blk_get_integrity(ns->disk))
			blk_integrity_unregister(ns->disk);
	}

	down_write(&ns->ctrl->namespaces_rwsem);
	list_del_init(&ns->list);
	up_write(&ns->ctrl->namespaces_rwsem);

	nvme_mpath_check_last_path(ns);
	nvme_put_ns(ns);
}

static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid)
{
	struct nvme_ns *ns = nvme_find_get_ns(ctrl, nsid);

	if (ns) {
		nvme_ns_remove(ns);
		nvme_put_ns(ns);
	}
}

static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
	struct nvme_ns *ns;

	ns = nvme_find_get_ns(ctrl, nsid);
	if (ns) {
		if (ns->disk && revalidate_disk(ns->disk))
			nvme_ns_remove(ns);
		nvme_put_ns(ns);
	} else
		nvme_alloc_ns(ctrl, nsid);
}

static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
					unsigned nsid)
{
	struct nvme_ns *ns, *next;
	LIST_HEAD(rm_list);

	down_write(&ctrl->namespaces_rwsem);
	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
		if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags))
			list_move_tail(&ns->list, &rm_list);
	}
	up_write(&ctrl->namespaces_rwsem);

	list_for_each_entry_safe(ns, next, &rm_list, list)
		nvme_ns_remove(ns);

}

static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
{
	const int nr_entries = NVME_IDENTIFY_DATA_SIZE / sizeof(__le32);
	__le32 *ns_list;
	u32 prev = 0;
	int ret = 0, i;

	if (nvme_ctrl_limited_cns(ctrl))
		return -EOPNOTSUPP;

	ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
	if (!ns_list)
		return -ENOMEM;

	for (;;) {
		ret = nvme_identify_ns_list(ctrl, prev, ns_list);
		if (ret)
			goto free;

		for (i = 0; i < nr_entries; i++) {
			u32 nsid = le32_to_cpu(ns_list[i]);

			if (!nsid)	/* end of the list? */
				goto out;
			nvme_validate_ns(ctrl, nsid);
			while (++prev < nsid)
				nvme_ns_remove_by_nsid(ctrl, prev);
		}
	}
 out:
	nvme_remove_invalid_namespaces(ctrl, prev);
 free:
	kfree(ns_list);
	return ret;
}

static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl)
{
	struct nvme_id_ctrl *id;
	u32 nn, i;

	if (nvme_identify_ctrl(ctrl, &id))
		return;
	nn = le32_to_cpu(id->nn);
	kfree(id);

	for (i = 1; i <= nn; i++)
		nvme_validate_ns(ctrl, i);

	nvme_remove_invalid_namespaces(ctrl, nn);
}

static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
{
	size_t log_size = NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32);
	__le32 *log;
	int error;

	log = kzalloc(log_size, GFP_KERNEL);
	if (!log)
		return;

	/*
	 * We need to read the log to clear the AEN, but we don't want to rely
	 * on it for the changed namespace information as userspace could have
	 * raced with us in reading the log page, which could cause us to miss
	 * updates.
	 */
	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
			log_size, 0);
	if (error)
		dev_warn(ctrl->device,
			"reading changed ns log failed: %d\n", error);

	kfree(log);
}

static void nvme_scan_work(struct work_struct *work)
{
	struct nvme_ctrl *ctrl =
		container_of(work, struct nvme_ctrl, scan_work);

	/* No tagset on a live ctrl means IO queues could not created */
	if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset)
		return;

	if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
		dev_info(ctrl->device, "rescanning namespaces.\n");
		nvme_clear_changed_ns_log(ctrl);
	}

	mutex_lock(&ctrl->scan_lock);
	if (nvme_scan_ns_list(ctrl) != 0)
		nvme_scan_ns_sequential(ctrl);
	mutex_unlock(&ctrl->scan_lock);

	down_write(&ctrl->namespaces_rwsem);
	list_sort(NULL, &ctrl->namespaces, ns_cmp);
	up_write(&ctrl->namespaces_rwsem);
}

/*
 * This function iterates the namespace list unlocked to allow recovery from
 * controller failure. It is up to the caller to ensure the namespace list is
 * not modified by scan work while this function is executing.
 */
void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns, *next;
	LIST_HEAD(ns_list);

	/*
	 * make sure to requeue I/O to all namespaces as these
	 * might result from the scan itself and must complete
	 * for the scan_work to make progress
	 */
	nvme_mpath_clear_ctrl_paths(ctrl);

	/* prevent racing with ns scanning */
	flush_work(&ctrl->scan_work);

	/*
	 * The dead states indicates the controller was not gracefully
	 * disconnected. In that case, we won't be able to flush any data while
	 * removing the namespaces' disks; fail all the queues now to avoid
	 * potentially having to clean up the failed sync later.
	 */
	if (ctrl->state == NVME_CTRL_DEAD)
		nvme_kill_queues(ctrl);

	down_write(&ctrl->namespaces_rwsem);
	list_splice_init(&ctrl->namespaces, &ns_list);
	up_write(&ctrl->namespaces_rwsem);

	list_for_each_entry_safe(ns, next, &ns_list, list)
		nvme_ns_remove(ns);
}
EXPORT_SYMBOL_GPL(nvme_remove_namespaces);

static int nvme_class_uevent(struct device *dev, struct kobj_uevent_env *env)
{
	struct nvme_ctrl *ctrl =
		container_of(dev, struct nvme_ctrl, ctrl_device);
	struct nvmf_ctrl_options *opts = ctrl->opts;
	int ret;

	ret = add_uevent_var(env, "NVME_TRTYPE=%s", ctrl->ops->name);
	if (ret)
		return ret;

	if (opts) {
		ret = add_uevent_var(env, "NVME_TRADDR=%s", opts->traddr);
		if (ret)
			return ret;

		ret = add_uevent_var(env, "NVME_TRSVCID=%s",
				opts->trsvcid ?: "none");
		if (ret)
			return ret;

		ret = add_uevent_var(env, "NVME_HOST_TRADDR=%s",
				opts->host_traddr ?: "none");
	}
	return ret;
}

static void nvme_aen_uevent(struct nvme_ctrl *ctrl)
{
	char *envp[2] = { NULL, NULL };
	u32 aen_result = ctrl->aen_result;

	ctrl->aen_result = 0;
	if (!aen_result)
		return;

	envp[0] = kasprintf(GFP_KERNEL, "NVME_AEN=%#08x", aen_result);
	if (!envp[0])
		return;
	kobject_uevent_env(&ctrl->device->kobj, KOBJ_CHANGE, envp);
	kfree(envp[0]);
}

static void nvme_async_event_work(struct work_struct *work)
{
	struct nvme_ctrl *ctrl =
		container_of(work, struct nvme_ctrl, async_event_work);

	nvme_aen_uevent(ctrl);
	ctrl->ops->submit_async_event(ctrl);
}

static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl)
{

	u32 csts;

	if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts))
		return false;

	if (csts == ~0)
		return false;

	return ((ctrl->ctrl_config & NVME_CC_ENABLE) && (csts & NVME_CSTS_PP));
}

static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
{
	struct nvme_fw_slot_info_log *log;

	log = kmalloc(sizeof(*log), GFP_KERNEL);
	if (!log)
		return;

	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log,
			sizeof(*log), 0))
		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
	kfree(log);
}

static void nvme_fw_act_work(struct work_struct *work)
{
	struct nvme_ctrl *ctrl = container_of(work,
				struct nvme_ctrl, fw_act_work);
	unsigned long fw_act_timeout;

	if (ctrl->mtfa)
		fw_act_timeout = jiffies +
				msecs_to_jiffies(ctrl->mtfa * 100);
	else
		fw_act_timeout = jiffies +
				msecs_to_jiffies(admin_timeout * 1000);

	nvme_stop_queues(ctrl);
	while (nvme_ctrl_pp_status(ctrl)) {
		if (time_after(jiffies, fw_act_timeout)) {
			dev_warn(ctrl->device,
				"Fw activation timeout, reset controller\n");
			nvme_try_sched_reset(ctrl);
			return;
		}
		msleep(100);
	}

	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
		return;

	nvme_start_queues(ctrl);
	/* read FW slot information to clear the AER */
	nvme_get_fw_slot_info(ctrl);
}

static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
{
	u32 aer_notice_type = (result & 0xff00) >> 8;

	trace_nvme_async_event(ctrl, aer_notice_type);

	switch (aer_notice_type) {
	case NVME_AER_NOTICE_NS_CHANGED:
		set_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events);
		nvme_queue_scan(ctrl);
		break;
	case NVME_AER_NOTICE_FW_ACT_STARTING:
		/*
		 * We are (ab)using the RESETTING state to prevent subsequent
		 * recovery actions from interfering with the controller's
		 * firmware activation.
		 */
		if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
			queue_work(nvme_wq, &ctrl->fw_act_work);
		break;
#ifdef CONFIG_NVME_MULTIPATH
	case NVME_AER_NOTICE_ANA:
		if (!ctrl->ana_log_buf)
			break;
		queue_work(nvme_wq, &ctrl->ana_work);
		break;
#endif
	case NVME_AER_NOTICE_DISC_CHANGED:
		ctrl->aen_result = result;
		break;
	default:
		dev_warn(ctrl->device, "async event result %08x\n", result);
	}
}

void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
		volatile union nvme_result *res)
{
	u32 result = le32_to_cpu(res->u32);
	u32 aer_type = result & 0x07;

	if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS)
		return;

	switch (aer_type) {
	case NVME_AER_NOTICE:
		nvme_handle_aen_notice(ctrl, result);
		break;
	case NVME_AER_ERROR:
	case NVME_AER_SMART:
	case NVME_AER_CSS:
	case NVME_AER_VS:
		trace_nvme_async_event(ctrl, aer_type);
		ctrl->aen_result = result;
		break;
	default:
		break;
	}
	queue_work(nvme_wq, &ctrl->async_event_work);
}
EXPORT_SYMBOL_GPL(nvme_complete_async_event);

void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
{
	nvme_mpath_stop(ctrl);
	nvme_stop_keep_alive(ctrl);
	flush_work(&ctrl->async_event_work);
	cancel_work_sync(&ctrl->fw_act_work);
}
EXPORT_SYMBOL_GPL(nvme_stop_ctrl);

void nvme_start_ctrl(struct nvme_ctrl *ctrl)
{
	if (ctrl->kato)
		nvme_start_keep_alive(ctrl);

	nvme_enable_aen(ctrl);

	if (ctrl->queue_count > 1) {
		nvme_queue_scan(ctrl);
		nvme_start_queues(ctrl);
	}
	ctrl->created = true;
}
EXPORT_SYMBOL_GPL(nvme_start_ctrl);

void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
{
	nvme_fault_inject_fini(&ctrl->fault_inject);
	dev_pm_qos_hide_latency_tolerance(ctrl->device);
	cdev_device_del(&ctrl->cdev, ctrl->device);
	nvme_put_ctrl(ctrl);
}
EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);

static void nvme_free_ctrl(struct device *dev)
{
	struct nvme_ctrl *ctrl =
		container_of(dev, struct nvme_ctrl, ctrl_device);
	struct nvme_subsystem *subsys = ctrl->subsys;

	if (subsys && ctrl->instance != subsys->instance)
		ida_simple_remove(&nvme_instance_ida, ctrl->instance);

	kfree(ctrl->effects);
	nvme_mpath_uninit(ctrl);
	__free_page(ctrl->discard_page);

	if (subsys) {
		mutex_lock(&nvme_subsystems_lock);
		list_del(&ctrl->subsys_entry);
		sysfs_remove_link(&subsys->dev.kobj, dev_name(ctrl->device));
		mutex_unlock(&nvme_subsystems_lock);
	}

	ctrl->ops->free_ctrl(ctrl);

	if (subsys)
		nvme_put_subsystem(subsys);
}

/*
 * Initialize a NVMe controller structures.  This needs to be called during
 * earliest initialization so that we have the initialized structured around
 * during probing.
 */
int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
		const struct nvme_ctrl_ops *ops, unsigned long quirks)
{
	int ret;

	ctrl->state = NVME_CTRL_NEW;
	spin_lock_init(&ctrl->lock);
	mutex_init(&ctrl->scan_lock);
	INIT_LIST_HEAD(&ctrl->namespaces);
	init_rwsem(&ctrl->namespaces_rwsem);
	ctrl->dev = dev;
	ctrl->ops = ops;
	ctrl->quirks = quirks;
	ctrl->numa_node = NUMA_NO_NODE;
	INIT_WORK(&ctrl->scan_work, nvme_scan_work);
	INIT_WORK(&ctrl->async_event_work, nvme_async_event_work);
	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
	init_waitqueue_head(&ctrl->state_wq);

	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;

	BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) >
			PAGE_SIZE);
	ctrl->discard_page = alloc_page(GFP_KERNEL);
	if (!ctrl->discard_page) {
		ret = -ENOMEM;
		goto out;
	}

	ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);
	if (ret < 0)
		goto out;
	ctrl->instance = ret;

	device_initialize(&ctrl->ctrl_device);
	ctrl->device = &ctrl->ctrl_device;
	ctrl->device->devt = MKDEV(MAJOR(nvme_chr_devt), ctrl->instance);
	ctrl->device->class = nvme_class;
	ctrl->device->parent = ctrl->dev;
	ctrl->device->groups = nvme_dev_attr_groups;
	ctrl->device->release = nvme_free_ctrl;
	dev_set_drvdata(ctrl->device, ctrl);
	ret = dev_set_name(ctrl->device, "nvme%d", ctrl->instance);
	if (ret)
		goto out_release_instance;

	nvme_get_ctrl(ctrl);
	cdev_init(&ctrl->cdev, &nvme_dev_fops);
	ctrl->cdev.owner = ops->module;
	ret = cdev_device_add(&ctrl->cdev, ctrl->device);
	if (ret)
		goto out_free_name;

	/*
	 * Initialize latency tolerance controls.  The sysfs files won't
	 * be visible to userspace unless the device actually supports APST.
	 */
	ctrl->device->power.set_latency_tolerance = nvme_set_latency_tolerance;
	dev_pm_qos_update_user_latency_tolerance(ctrl->device,
		min(default_ps_max_latency_us, (unsigned long)S32_MAX));

	nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device));

	return 0;
out_free_name:
	nvme_put_ctrl(ctrl);
	kfree_const(ctrl->device->kobj.name);
out_release_instance:
	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
out:
	if (ctrl->discard_page)
		__free_page(ctrl->discard_page);
	return ret;
}
EXPORT_SYMBOL_GPL(nvme_init_ctrl);

/**
 * nvme_kill_queues(): Ends all namespace queues
 * @ctrl: the dead controller that needs to end
 *
 * Call this function when the driver determines it is unable to get the
 * controller in a state capable of servicing IO.
 */
void nvme_kill_queues(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);

	/* Forcibly unquiesce queues to avoid blocking dispatch */
	if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q))
		blk_mq_unquiesce_queue(ctrl->admin_q);

	list_for_each_entry(ns, &ctrl->namespaces, list)
		nvme_set_queue_dying(ns);

	up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_kill_queues);

void nvme_unfreeze(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_mq_unfreeze_queue(ns->queue);
	up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_unfreeze);

void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list) {
		timeout = blk_mq_freeze_queue_wait_timeout(ns->queue, timeout);
		if (timeout <= 0)
			break;
	}
	up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);

void nvme_wait_freeze(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_mq_freeze_queue_wait(ns->queue);
	up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_wait_freeze);

void nvme_start_freeze(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_freeze_queue_start(ns->queue);
	up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_start_freeze);

void nvme_stop_queues(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_mq_quiesce_queue(ns->queue);
	up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_stop_queues);

void nvme_start_queues(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_mq_unquiesce_queue(ns->queue);
	up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_start_queues);


void nvme_sync_queues(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_sync_queue(ns->queue);
	up_read(&ctrl->namespaces_rwsem);

	if (ctrl->admin_q)
		blk_sync_queue(ctrl->admin_q);
}
EXPORT_SYMBOL_GPL(nvme_sync_queues);

/*
 * Check we didn't inadvertently grow the command structure sizes:
 */
static inline void _nvme_check_size(void)
{
	BUILD_BUG_ON(sizeof(struct nvme_common_command) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_identify) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_download_firmware) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_dsm_cmd) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_write_zeroes_cmd) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_get_log_page_command) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_directive_cmd) != 64);
}


static int __init nvme_core_init(void)
{
	int result = -ENOMEM;

	_nvme_check_size();

	nvme_wq = alloc_workqueue("nvme-wq",
			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
	if (!nvme_wq)
		goto out;

	nvme_reset_wq = alloc_workqueue("nvme-reset-wq",
			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
	if (!nvme_reset_wq)
		goto destroy_wq;

	nvme_delete_wq = alloc_workqueue("nvme-delete-wq",
			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
	if (!nvme_delete_wq)
		goto destroy_reset_wq;

	result = alloc_chrdev_region(&nvme_chr_devt, 0, NVME_MINORS, "nvme");
	if (result < 0)
		goto destroy_delete_wq;

	nvme_class = class_create(THIS_MODULE, "nvme");
	if (IS_ERR(nvme_class)) {
		result = PTR_ERR(nvme_class);
		goto unregister_chrdev;
	}
	nvme_class->dev_uevent = nvme_class_uevent;

	nvme_subsys_class = class_create(THIS_MODULE, "nvme-subsystem");
	if (IS_ERR(nvme_subsys_class)) {
		result = PTR_ERR(nvme_subsys_class);
		goto destroy_class;
	}
	return 0;

destroy_class:
	class_destroy(nvme_class);
unregister_chrdev:
	unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
destroy_delete_wq:
	destroy_workqueue(nvme_delete_wq);
destroy_reset_wq:
	destroy_workqueue(nvme_reset_wq);
destroy_wq:
	destroy_workqueue(nvme_wq);
out:
	return result;
}

static void __exit nvme_core_exit(void)
{
	class_destroy(nvme_subsys_class);
	class_destroy(nvme_class);
	unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
	destroy_workqueue(nvme_delete_wq);
	destroy_workqueue(nvme_reset_wq);
	destroy_workqueue(nvme_wq);
	ida_destroy(&nvme_instance_ida);
}

MODULE_LICENSE("GPL");
MODULE_VERSION("1.0");
module_init(nvme_core_init);
module_exit(nvme_core_exit);