Free Electrons

Electrons Libres - Embedded Linux Experts

   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
/*
 * NVM Express device driver
 * Copyright (c) 2011-2014, Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 */

#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/hdreg.h>
#include <linux/kernel.h>
#include <linux/module.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/t10-pi.h>
#include <linux/pm_qos.h>
#include <asm/unaligned.h>

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

#define NVME_MINORS		(1U << MINORBITS)

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

unsigned char nvme_io_timeout = 30;
module_param_named(io_timeout, nvme_io_timeout, byte, 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 int nvme_char_major;
module_param(nvme_char_major, int, 0);

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");

struct workqueue_struct *nvme_wq;
EXPORT_SYMBOL_GPL(nvme_wq);

static LIST_HEAD(nvme_ctrl_list);
static DEFINE_SPINLOCK(dev_list_lock);

static struct class *nvme_class;

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

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

	ret = nvme_reset_ctrl(ctrl);
	if (!ret)
		flush_work(&ctrl->reset_work);
	return ret;
}

static blk_status_t nvme_error_status(struct request *req)
{
	switch (nvme_req(req)->status & 0x7ff) {
	case NVME_SC_SUCCESS:
		return BLK_STS_OK;
	case NVME_SC_CAP_EXCEEDED:
		return BLK_STS_NOSPC;
	case NVME_SC_ONCS_NOT_SUPPORTED:
		return BLK_STS_NOTSUPP;
	case NVME_SC_WRITE_FAULT:
	case NVME_SC_READ_ERROR:
	case NVME_SC_UNWRITTEN_BLOCK:
		return BLK_STS_MEDIUM;
	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 (jiffies - req->start_time >= req->timeout)
		return false;
	if (nvme_req(req)->retries >= nvme_max_retries)
		return false;
	return true;
}

void nvme_complete_rq(struct request *req)
{
	if (unlikely(nvme_req(req)->status && nvme_req_needs_retry(req))) {
		nvme_req(req)->retries++;
		blk_mq_requeue_request(req, true);
		return;
	}

	blk_mq_end_request(req, nvme_error_status(req));
}
EXPORT_SYMBOL_GPL(nvme_complete_rq);

void nvme_cancel_request(struct request *req, void *data, bool reserved)
{
	int status;

	if (!blk_mq_request_started(req))
		return;

	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
				"Cancelling I/O %d", req->tag);

	status = NVME_SC_ABORT_REQ;
	if (blk_queue_dying(req->q))
		status |= NVME_SC_DNR;
	nvme_req(req)->status = status;
	blk_mq_complete_request(req);

}
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;
	bool changed = false;

	spin_lock_irq(&ctrl->lock);

	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_RECONNECTING:
			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_RECONNECTING:
		switch (old_state) {
		case NVME_CTRL_LIVE:
			changed = true;
			/* FALLTHRU */
		default:
			break;
		}
		break;
	case NVME_CTRL_DELETING:
		switch (old_state) {
		case NVME_CTRL_LIVE:
		case NVME_CTRL_RESETTING:
		case NVME_CTRL_RECONNECTING:
			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;

	spin_unlock_irq(&ctrl->lock);

	return changed;
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);

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);

	if (ns->disk) {
		spin_lock(&dev_list_lock);
		ns->disk->private_data = NULL;
		spin_unlock(&dev_list_lock);
	}

	put_disk(ns->disk);
	ida_simple_remove(&ns->ctrl->ns_ida, ns->instance);
	nvme_put_ctrl(ns->ctrl);
	kfree(ns);
}

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

static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk)
{
	struct nvme_ns *ns;

	spin_lock(&dev_list_lock);
	ns = disk->private_data;
	if (ns) {
		if (!kref_get_unless_zero(&ns->kref))
			goto fail;
		if (!try_module_get(ns->ctrl->ops->module))
			goto fail_put_ns;
	}
	spin_unlock(&dev_list_lock);

	return ns;

fail_put_ns:
	kref_put(&ns->kref, nvme_free_ns);
fail:
	spin_unlock(&dev_list_lock);
	return NULL;
}

struct request *nvme_alloc_request(struct request_queue *q,
		struct nvme_command *cmd, unsigned int 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_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(0xffffffff);
	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((sizeof(*s) >> 2) - 1);
	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, 0xffffffff);
	if (ret)
		return ret;

	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);
		nvme_disable_streams(ctrl);
		return 0;
	}

	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;
}

/*
 * 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)
{
	memset(cmnd, 0, sizeof(*cmnd));
	cmnd->common.opcode = nvme_cmd_flush;
	cmnd->common.nsid = cpu_to_le32(ns->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;

	range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC);
	if (!range)
		return BLK_STS_RESOURCE;

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

		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)) {
		kfree(range);
		return BLK_STS_IOERR;
	}

	memset(cmnd, 0, sizeof(*cmnd));
	cmnd->dsm.opcode = nvme_cmd_dsm;
	cmnd->dsm.nsid = cpu_to_le32(ns->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 = sizeof(*range) * segments;
	req->rq_flags |= RQF_SPECIAL_PAYLOAD;

	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 formated with metadata, require the block layer provide a buffer
	 * unless this namespace is formated such that the metadata can be
	 * stripped/generated by the controller with PRACT=1.
	 */
	if (ns && ns->ms &&
	    (!ns->pi_type || ns->ms != sizeof(struct t10_pi_tuple)) &&
	    !blk_integrity_rq(req) && !blk_rq_is_passthrough(req))
		return BLK_STS_NOTSUPP;

	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;

	memset(cmnd, 0, sizeof(*cmnd));
	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(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) {
		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(
					nvme_block_nr(ns, blk_rq_pos(req)));
			break;
		}
		if (!blk_integrity_rq(req))
			control |= NVME_RW_PRINFO_PRACT;
	}

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

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

	if (!(req->rq_flags & RQF_DONTPREP)) {
		nvme_req(req)->retries = 0;
		nvme_req(req)->flags = 0;
		req->rq_flags |= RQF_DONTPREP;
	}

	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:
		/* currently only aliased to deallocate for a few ctrls: */
	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;
	return ret;
}
EXPORT_SYMBOL_GPL(nvme_setup_cmd);

/*
 * 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, int flags)
{
	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;
	}

	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);
}
EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);

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,
		u32 *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;

	if (ubuffer && bufflen) {
		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
				GFP_KERNEL);
		if (ret)
			goto out;
		bio = req->bio;

		if (!disk)
			goto submit;
		bio->bi_bdev = bdget_disk(disk, 0);
		if (!bio->bi_bdev) {
			ret = -ENODEV;
			goto out_unmap;
		}

		if (meta_buffer && meta_len) {
			struct bio_integrity_payload *bip;

			meta = kmalloc(meta_len, GFP_KERNEL);
			if (!meta) {
				ret = -ENOMEM;
				goto out_unmap;
			}

			if (write) {
				if (copy_from_user(meta, meta_buffer,
						meta_len)) {
					ret = -EFAULT;
					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 = meta_len;
			bip->bip_iter.bi_sector = meta_seed;

			ret = bio_integrity_add_page(bio, virt_to_page(meta),
					meta_len, offset_in_page(meta));
			if (ret != meta_len) {
				ret = -ENOMEM;
				goto out_free_meta;
			}
		}
	}
 submit:
	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 = le32_to_cpu(nvme_req(req)->result.u32);
	if (meta && !ret && !write) {
		if (copy_to_user(meta_buffer, meta, meta_len))
			ret = -EFAULT;
	}
 out_free_meta:
	kfree(meta);
 out_unmap:
	if (bio) {
		if (disk && bio->bi_bdev)
			bdput(bio->bi_bdev);
		blk_rq_unmap_user(bio);
	}
 out:
	blk_mq_free_request(req);
	return ret;
}

int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
		void __user *ubuffer, unsigned bufflen, u32 *result,
		unsigned timeout)
{
	return __nvme_submit_user_cmd(q, cmd, ubuffer, bufflen, NULL, 0, 0,
			result, timeout);
}

static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
{
	struct nvme_ctrl *ctrl = rq->end_io_data;

	blk_mq_free_request(rq);

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

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

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

	memset(&c, 0, sizeof(c));
	c.common.opcode = nvme_admin_keep_alive;

	rq = nvme_alloc_request(ctrl->admin_q, &c, 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);

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

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

	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
}
EXPORT_SYMBOL_GPL(nvme_start_keep_alive);

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);

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_identify_ns_descs(struct nvme_ns *ns, unsigned nsid)
{
	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(ns->ctrl->admin_q, &c, data,
				      NVME_IDENTIFY_DATA_SIZE);
	if (status)
		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;

		switch (cur->nidt) {
		case NVME_NIDT_EUI64:
			if (cur->nidl != NVME_NIDT_EUI64_LEN) {
				dev_warn(ns->ctrl->device,
					 "ctrl returned bogus length: %d for NVME_NIDT_EUI64\n",
					 cur->nidl);
				goto free_data;
			}
			len = NVME_NIDT_EUI64_LEN;
			memcpy(ns->eui, data + pos + sizeof(*cur), len);
			break;
		case NVME_NIDT_NGUID:
			if (cur->nidl != NVME_NIDT_NGUID_LEN) {
				dev_warn(ns->ctrl->device,
					 "ctrl returned bogus length: %d for NVME_NIDT_NGUID\n",
					 cur->nidl);
				goto free_data;
			}
			len = NVME_NIDT_NGUID_LEN;
			memcpy(ns->nguid, data + pos + sizeof(*cur), len);
			break;
		case NVME_NIDT_UUID:
			if (cur->nidl != NVME_NIDT_UUID_LEN) {
				dev_warn(ns->ctrl->device,
					 "ctrl returned bogus length: %d for NVME_NIDT_UUID\n",
					 cur->nidl);
				goto free_data;
			}
			len = NVME_NIDT_UUID_LEN;
			uuid_copy(&ns->uuid, data + pos + sizeof(*cur));
			break;
		default:
			/* Skip unnkown types */
			len = cur->nidl;
			break;
		}

		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, 0x1000);
}

static int nvme_identify_ns(struct nvme_ctrl *dev, 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(struct nvme_id_ns), GFP_KERNEL);
	if (!*id)
		return -ENOMEM;

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

static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
		      void *buffer, size_t buflen, u32 *result)
{
	struct nvme_command c;
	union nvme_result res;
	int ret;

	memset(&c, 0, sizeof(c));
	c.features.opcode = nvme_admin_set_features;
	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);
	if (ret >= 0 && result)
		*result = le32_to_cpu(res.u32);
	return ret;
}

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);

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 = (void __user *)(uintptr_t)io.metadata;

	if (ns->ext) {
		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->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,
			(void __user *)(uintptr_t)io.addr, length,
			metadata, meta_len, io.slba, NULL, 0);
}

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;
	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[0] = cpu_to_le32(cmd.cdw10);
	c.common.cdw10[1] = cpu_to_le32(cmd.cdw11);
	c.common.cdw10[2] = cpu_to_le32(cmd.cdw12);
	c.common.cdw10[3] = cpu_to_le32(cmd.cdw13);
	c.common.cdw10[4] = cpu_to_le32(cmd.cdw14);
	c.common.cdw10[5] = cpu_to_le32(cmd.cdw15);

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

	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
			&cmd.result, timeout);
	if (status >= 0) {
		if (put_user(cmd.result, &ucmd->result))
			return -EFAULT;
	}

	return status;
}

static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
		unsigned int cmd, unsigned long arg)
{
	struct nvme_ns *ns = bdev->bd_disk->private_data;

	switch (cmd) {
	case NVME_IOCTL_ID:
		force_successful_syscall_return();
		return ns->ns_id;
	case NVME_IOCTL_ADMIN_CMD:
		return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
	case NVME_IOCTL_IO_CMD:
		return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
	case NVME_IOCTL_SUBMIT_IO:
		return nvme_submit_io(ns, (void __user *)arg);
	default:
#ifdef CONFIG_NVM
		if (ns->ndev)
			return nvme_nvm_ioctl(ns, cmd, arg);
#endif
		if (is_sed_ioctl(cmd))
			return sed_ioctl(ns->ctrl->opal_dev, cmd,
					 (void __user *) arg);
		return -ENOTTY;
	}
}

#ifdef CONFIG_COMPAT
static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
			unsigned int cmd, unsigned long arg)
{
	return nvme_ioctl(bdev, mode, cmd, arg);
}
#else
#define nvme_compat_ioctl	NULL
#endif

static int nvme_open(struct block_device *bdev, fmode_t mode)
{
	return nvme_get_ns_from_disk(bdev->bd_disk) ? 0 : -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_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id,
		u16 bs)
{
	struct nvme_ns *ns = disk->private_data;
	u16 old_ms = ns->ms;
	u8 pi_type = 0;

	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);

	/* PI implementation requires metadata equal t10 pi tuple size */
	if (ns->ms == sizeof(struct t10_pi_tuple))
		pi_type = id->dps & NVME_NS_DPS_PI_MASK;

	if (blk_get_integrity(disk) &&
	    (ns->pi_type != pi_type || ns->ms != old_ms ||
	     bs != queue_logical_block_size(disk->queue) ||
	     (ns->ms && ns->ext)))
		blk_integrity_unregister(disk);

	ns->pi_type = pi_type;
}

static void nvme_init_integrity(struct nvme_ns *ns)
{
	struct blk_integrity integrity;

	memset(&integrity, 0, sizeof(integrity));
	switch (ns->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 = ns->ms;
	blk_integrity_register(ns->disk, &integrity);
	blk_queue_max_integrity_segments(ns->queue, 1);
}
#else
static void nvme_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id,
		u16 bs)
{
}
static void nvme_init_integrity(struct nvme_ns *ns)
{
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */

static void nvme_set_chunk_size(struct nvme_ns *ns)
{
	u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9));
	blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
}

static void nvme_config_discard(struct nvme_ns *ns)
{
	struct nvme_ctrl *ctrl = ns->ctrl;
	u32 logical_block_size = queue_logical_block_size(ns->queue);

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

	if (ctrl->nr_streams && ns->sws && ns->sgs) {
		unsigned int sz = logical_block_size * ns->sws * ns->sgs;

		ns->queue->limits.discard_alignment = sz;
		ns->queue->limits.discard_granularity = sz;
	} else {
		ns->queue->limits.discard_alignment = logical_block_size;
		ns->queue->limits.discard_granularity = logical_block_size;
	}
	blk_queue_max_discard_sectors(ns->queue, UINT_MAX);
	blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES);
	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);

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

static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
{
	if (nvme_identify_ns(ns->ctrl, ns->ns_id, id)) {
		dev_warn(ns->ctrl->dev, "%s: Identify failure\n", __func__);
		return -ENODEV;
	}

	if ((*id)->ncap == 0) {
		kfree(*id);
		return -ENODEV;
	}

	if (ns->ctrl->vs >= NVME_VS(1, 1, 0))
		memcpy(ns->eui, (*id)->eui64, sizeof(ns->eui));
	if (ns->ctrl->vs >= NVME_VS(1, 2, 0))
		memcpy(ns->nguid, (*id)->nguid, sizeof(ns->nguid));
	if (ns->ctrl->vs >= NVME_VS(1, 3, 0)) {
		 /* Don't treat error as fatal we potentially
		  * already have a NGUID or EUI-64
		  */
		if (nvme_identify_ns_descs(ns, ns->ns_id))
			dev_warn(ns->ctrl->device,
				 "%s: Identify Descriptors failed\n", __func__);
	}

	return 0;
}

static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
{
	struct nvme_ns *ns = disk->private_data;
	struct nvme_ctrl *ctrl = ns->ctrl;
	u16 bs;

	/*
	 * 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;
	bs = 1 << ns->lba_shift;
	ns->noiob = le16_to_cpu(id->noiob);

	blk_mq_freeze_queue(disk->queue);

	if (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
		nvme_prep_integrity(disk, id, bs);
	blk_queue_logical_block_size(ns->queue, bs);
	if (ns->noiob)
		nvme_set_chunk_size(ns);
	if (ns->ms && !blk_get_integrity(disk) && !ns->ext)
		nvme_init_integrity(ns);
	if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
		set_capacity(disk, 0);
	else
		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));

	if (ctrl->oncs & NVME_CTRL_ONCS_DSM)
		nvme_config_discard(ns);
	blk_mq_unfreeze_queue(disk->queue);
}

static int nvme_revalidate_disk(struct gendisk *disk)
{
	struct nvme_ns *ns = disk->private_data;
	struct nvme_id_ns *id = NULL;
	int ret;

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

	ret = nvme_revalidate_ns(ns, &id);
	if (ret)
		return ret;

	__nvme_revalidate_disk(disk, id);
	kfree(id);

	return 0;
}

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 *ns = bdev->bd_disk->private_data;
	struct nvme_command c;
	u8 data[16] = { 0, };

	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->ns_id);
	c.common.cdw10[0] = cpu_to_le32(cdw10);

	return nvme_submit_sync_cmd(ns->queue, &c, data, 16);
}

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[0] = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
	cmd.common.cdw10[1] = cpu_to_le32(len);

	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
				      ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0);
}
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,
};

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;

		msleep(100);
		if (fatal_signal_pending(current))
			return -EINTR;
		if (time_after(jiffies, timeout)) {
			dev_err(ctrl->device,
				"Device not ready; aborting %s\n", enabled ?
						"initialisation" : "reset");
			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, u64 cap)
{
	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, cap, false);
}
EXPORT_SYMBOL_GPL(nvme_disable_ctrl);

int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
{
	/*
	 * 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 = NVME_CAP_MPSMIN(cap) + 12, page_shift = 12;
	int ret;

	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_ARB_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, cap, true);
}
EXPORT_SYMBOL_GPL(nvme_enable_ctrl);

int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
{
	unsigned long timeout = jiffies + (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;

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

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,
	}
};

/* 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_ctrl *ctrl, struct nvme_id_ctrl *id)
{
	size_t nqnlen;
	int off;

	nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE);
	if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) {
		strcpy(ctrl->subnqn, id->subnqn);
		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(ctrl->subnqn, NVMF_NQN_SIZE,
			"nqn.2014.08.org.nvmexpress:%4x%4x",
			le16_to_cpu(id->vid), le16_to_cpu(id->ssvid));
	memcpy(ctrl->subnqn + off, id->sn, sizeof(id->sn));
	off += sizeof(id->sn);
	memcpy(ctrl->subnqn + off, id->mn, sizeof(id->mn));
	off += sizeof(id->mn);
	memset(ctrl->subnqn + off, 0, sizeof(ctrl->subnqn) - off);
}

/*
 * 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;
	u64 cap;
	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;
	}

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

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

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

	nvme_init_subnqn(ctrl, id);

	if (!ctrl->identified) {
		/*
		 * 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.
		 */

		int i;

		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->oacs = le16_to_cpu(id->oacs);
	ctrl->vid = le16_to_cpu(id->vid);
	ctrl->oncs = le16_to_cpup(&id->oncs);
	atomic_set(&ctrl->abort_limit, id->acl + 1);
	ctrl->vwc = id->vwc;
	ctrl->cntlid = le16_to_cpup(&id->cntlid);
	memcpy(ctrl->serial, id->sn, sizeof(id->sn));
	memcpy(ctrl->model, id->mn, sizeof(id->mn));
	memcpy(ctrl->firmware_rev, id->fr, sizeof(id->fr));
	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->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)) {
			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->cntlid = le16_to_cpu(id->cntlid);
		ctrl->hmpre = le32_to_cpu(id->hmpre);
		ctrl->hmmin = le32_to_cpu(id->hmmin);
	}

	kfree(id);

	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_directives(ctrl);
	if (ret < 0)
		return ret;

	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;
	int instance = iminor(inode);
	int ret = -ENODEV;

	spin_lock(&dev_list_lock);
	list_for_each_entry(ctrl, &nvme_ctrl_list, node) {
		if (ctrl->instance != instance)
			continue;

		if (!ctrl->admin_q) {
			ret = -EWOULDBLOCK;
			break;
		}
		if (!kref_get_unless_zero(&ctrl->kref))
			break;
		file->private_data = ctrl;
		ret = 0;
		break;
	}
	spin_unlock(&dev_list_lock);

	return ret;
}

static int nvme_dev_release(struct inode *inode, struct file *file)
{
	nvme_put_ctrl(file->private_data);
	return 0;
}

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

	mutex_lock(&ctrl->namespaces_mutex);
	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);
	mutex_unlock(&ctrl->namespaces_mutex);

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

out_unlock:
	mutex_unlock(&ctrl->namespaces_mutex);
	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_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,
	.release	= nvme_dev_release,
	.unlocked_ioctl	= nvme_dev_ioctl,
	.compat_ioctl	= nvme_dev_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 ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
								char *buf)
{
	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
	struct nvme_ctrl *ctrl = ns->ctrl;
	int serial_len = sizeof(ctrl->serial);
	int model_len = sizeof(ctrl->model);

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

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

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

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

	return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", ctrl->vid,
		serial_len, ctrl->serial, model_len, ctrl->model, ns->ns_id);
}
static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL);

static ssize_t nguid_show(struct device *dev, struct device_attribute *attr,
			  char *buf)
{
	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
	return sprintf(buf, "%pU\n", ns->nguid);
}
static DEVICE_ATTR(nguid, S_IRUGO, nguid_show, NULL);

static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
								char *buf)
{
	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);

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

static ssize_t eui_show(struct device *dev, struct device_attribute *attr,
								char *buf)
{
	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
	return sprintf(buf, "%8phd\n", ns->eui);
}
static DEVICE_ATTR(eui, S_IRUGO, eui_show, NULL);

static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
								char *buf)
{
	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
	return sprintf(buf, "%d\n", ns->ns_id);
}
static DEVICE_ATTR(nsid, S_IRUGO, nsid_show, NULL);

static struct attribute *nvme_ns_attrs[] = {
	&dev_attr_wwid.attr,
	&dev_attr_uuid.attr,
	&dev_attr_nguid.attr,
	&dev_attr_eui.attr,
	&dev_attr_nsid.attr,
	NULL,
};

static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
		struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, struct device, kobj);
	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);

	if (a == &dev_attr_uuid.attr) {
		if (uuid_is_null(&ns->uuid) ||
		    !memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
			return 0;
	}
	if (a == &dev_attr_nguid.attr) {
		if (!memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
			return 0;
	}
	if (a == &dev_attr_eui.attr) {
		if (!memchr_inv(ns->eui, 0, sizeof(ns->eui)))
			return 0;
	}
	return a->mode;
}

static const struct attribute_group nvme_ns_attr_group = {
	.attrs		= nvme_ns_attrs,
	.is_visible	= nvme_ns_attrs_are_visible,
};

#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->field), ctrl->field);	\
}										\
static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);

#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_str_function(model);
nvme_show_str_function(serial);
nvme_show_str_function(firmware_rev);
nvme_show_int_function(cntlid);

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);

	if (device_remove_file_self(dev, attr))
		ctrl->ops->delete_ctrl(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_RECONNECTING]= "reconnecting",
		[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->subnqn);
}
static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, 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,
	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;

	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 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->ns_id - nsb->ns_id;
}

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

	mutex_lock(&ctrl->namespaces_mutex);
	list_for_each_entry(ns, &ctrl->namespaces, list) {
		if (ns->ns_id == nsid) {
			kref_get(&ns->kref);
			ret = ns;
			break;
		}
		if (ns->ns_id > nsid)
			break;
	}
	mutex_unlock(&ctrl->namespaces_mutex);
	return ret;
}

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

	if (!ctrl->nr_streams)
		return 0;

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

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

	if (ns->sws) {
		unsigned int bs = 1 << ns->lba_shift;

		blk_queue_io_min(ns->queue, bs * ns->sws);
		if (ns->sgs)
			blk_queue_io_opt(ns->queue, bs * ns->sws * ns->sgs);
	}

	return 0;
}

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 = dev_to_node(ctrl->dev);

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

	ns->instance = ida_simple_get(&ctrl->ns_ida, 1, 0, GFP_KERNEL);
	if (ns->instance < 0)
		goto out_free_ns;

	ns->queue = blk_mq_init_queue(ctrl->tagset);
	if (IS_ERR(ns->queue))
		goto out_release_instance;
	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
	ns->queue->queuedata = ns;
	ns->ctrl = ctrl;

	kref_init(&ns->kref);
	ns->ns_id = nsid;
	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);
	nvme_setup_streams_ns(ctrl, ns);

	sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance);

	if (nvme_revalidate_ns(ns, &id))
		goto out_free_queue;

	if (nvme_nvm_ns_supported(ns, id) &&
				nvme_nvm_register(ns, disk_name, node)) {
		dev_warn(ctrl->device, "%s: LightNVM init failure\n", __func__);
		goto out_free_id;
	}

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

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

	__nvme_revalidate_disk(disk, id);

	mutex_lock(&ctrl->namespaces_mutex);
	list_add_tail(&ns->list, &ctrl->namespaces);
	mutex_unlock(&ctrl->namespaces_mutex);

	kref_get(&ctrl->kref);

	kfree(id);

	device_add_disk(ctrl->device, ns->disk);
	if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
					&nvme_ns_attr_group))
		pr_warn("%s: failed to create sysfs group for identification\n",
			ns->disk->disk_name);
	if (ns->ndev && nvme_nvm_register_sysfs(ns))
		pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
			ns->disk->disk_name);
	return;
 out_free_id:
	kfree(id);
 out_free_queue:
	blk_cleanup_queue(ns->queue);
 out_release_instance:
	ida_simple_remove(&ctrl->ns_ida, ns->instance);
 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;

	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
		if (blk_get_integrity(ns->disk))
			blk_integrity_unregister(ns->disk);
		sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
					&nvme_ns_attr_group);
		if (ns->ndev)
			nvme_nvm_unregister_sysfs(ns);
		del_gendisk(ns->disk);
		blk_cleanup_queue(ns->queue);
	}

	mutex_lock(&ns->ctrl->namespaces_mutex);
	list_del_init(&ns->list);
	mutex_unlock(&ns->ctrl->namespaces_mutex);

	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_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
		if (ns->ns_id > nsid)
			nvme_ns_remove(ns);
	}
}

static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
{
	struct nvme_ns *ns;
	__le32 *ns_list;
	unsigned i, j, nsid, prev = 0, num_lists = DIV_ROUND_UP(nn, 1024);
	int ret = 0;

	ns_list = kzalloc(0x1000, GFP_KERNEL);
	if (!ns_list)
		return -ENOMEM;

	for (i = 0; i < num_lists; i++) {
		ret = nvme_identify_ns_list(ctrl, prev, ns_list);
		if (ret)
			goto free;

		for (j = 0; j < min(nn, 1024U); j++) {
			nsid = le32_to_cpu(ns_list[j]);
			if (!nsid)
				goto out;

			nvme_validate_ns(ctrl, nsid);

			while (++prev < nsid) {
				ns = nvme_find_get_ns(ctrl, prev);
				if (ns) {
					nvme_ns_remove(ns);
					nvme_put_ns(ns);
				}
			}
		}
		nn -= j;
	}
 out:
	nvme_remove_invalid_namespaces(ctrl, prev);
 free:
	kfree(ns_list);
	return ret;
}

static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
{
	unsigned i;

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

	nvme_remove_invalid_namespaces(ctrl, nn);
}

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

	if (ctrl->state != NVME_CTRL_LIVE)
		return;

	if (nvme_identify_ctrl(ctrl, &id))
		return;

	nn = le32_to_cpu(id->nn);
	if (ctrl->vs >= NVME_VS(1, 1, 0) &&
	    !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
		if (!nvme_scan_ns_list(ctrl, nn))
			goto done;
	}
	nvme_scan_ns_sequential(ctrl, nn);
 done:
	mutex_lock(&ctrl->namespaces_mutex);
	list_sort(NULL, &ctrl->namespaces, ns_cmp);
	mutex_unlock(&ctrl->namespaces_mutex);
	kfree(id);
}

void nvme_queue_scan(struct nvme_ctrl *ctrl)
{
	/*
	 * Do not queue new scan work when a controller is reset during
	 * removal.
	 */
	if (ctrl->state == NVME_CTRL_LIVE)
		queue_work(nvme_wq, &ctrl->scan_work);
}
EXPORT_SYMBOL_GPL(nvme_queue_scan);

/*
 * 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;

	/*
	 * 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);

	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list)
		nvme_ns_remove(ns);
}
EXPORT_SYMBOL_GPL(nvme_remove_namespaces);

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

	spin_lock_irq(&ctrl->lock);
	while (ctrl->event_limit > 0) {
		int aer_idx = --ctrl->event_limit;

		spin_unlock_irq(&ctrl->lock);
		ctrl->ops->submit_async_event(ctrl, aer_idx);
		spin_lock_irq(&ctrl->lock);
	}
	spin_unlock_irq(&ctrl->lock);
}

void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
		union nvme_result *res)
{
	u32 result = le32_to_cpu(res->u32);
	bool done = true;

	switch (le16_to_cpu(status) >> 1) {
	case NVME_SC_SUCCESS:
		done = false;
		/*FALLTHRU*/
	case NVME_SC_ABORT_REQ:
		++ctrl->event_limit;
		queue_work(nvme_wq, &ctrl->async_event_work);
		break;
	default:
		break;
	}

	if (done)
		return;

	switch (result & 0xff07) {
	case NVME_AER_NOTICE_NS_CHANGED:
		dev_info(ctrl->device, "rescanning\n");
		nvme_queue_scan(ctrl);
		break;
	default:
		dev_warn(ctrl->device, "async event result %08x\n", result);
	}
}
EXPORT_SYMBOL_GPL(nvme_complete_async_event);

void nvme_queue_async_events(struct nvme_ctrl *ctrl)
{
	ctrl->event_limit = NVME_NR_AERS;
	queue_work(nvme_wq, &ctrl->async_event_work);
}
EXPORT_SYMBOL_GPL(nvme_queue_async_events);

static DEFINE_IDA(nvme_instance_ida);

static int nvme_set_instance(struct nvme_ctrl *ctrl)
{
	int instance, error;

	do {
		if (!ida_pre_get(&nvme_instance_ida, GFP_KERNEL))
			return -ENODEV;

		spin_lock(&dev_list_lock);
		error = ida_get_new(&nvme_instance_ida, &instance);
		spin_unlock(&dev_list_lock);
	} while (error == -EAGAIN);

	if (error)
		return -ENODEV;

	ctrl->instance = instance;
	return 0;
}

static void nvme_release_instance(struct nvme_ctrl *ctrl)
{
	spin_lock(&dev_list_lock);
	ida_remove(&nvme_instance_ida, ctrl->instance);
	spin_unlock(&dev_list_lock);
}

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

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

	if (ctrl->queue_count > 1) {
		nvme_queue_scan(ctrl);
		nvme_queue_async_events(ctrl);
		nvme_start_queues(ctrl);
	}
}
EXPORT_SYMBOL_GPL(nvme_start_ctrl);

void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
{
	device_destroy(nvme_class, MKDEV(nvme_char_major, ctrl->instance));

	spin_lock(&dev_list_lock);
	list_del(&ctrl->node);
	spin_unlock(&dev_list_lock);
}
EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);

static void nvme_free_ctrl(struct kref *kref)
{
	struct nvme_ctrl *ctrl = container_of(kref, struct nvme_ctrl, kref);

	put_device(ctrl->device);
	nvme_release_instance(ctrl);
	ida_destroy(&ctrl->ns_ida);

	ctrl->ops->free_ctrl(ctrl);
}

void nvme_put_ctrl(struct nvme_ctrl *ctrl)
{
	kref_put(&ctrl->kref, nvme_free_ctrl);
}
EXPORT_SYMBOL_GPL(nvme_put_ctrl);

/*
 * 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);
	INIT_LIST_HEAD(&ctrl->namespaces);
	mutex_init(&ctrl->namespaces_mutex);
	kref_init(&ctrl->kref);
	ctrl->dev = dev;
	ctrl->ops = ops;
	ctrl->quirks = quirks;
	INIT_WORK(&ctrl->scan_work, nvme_scan_work);
	INIT_WORK(&ctrl->async_event_work, nvme_async_event_work);

	ret = nvme_set_instance(ctrl);
	if (ret)
		goto out;

	ctrl->device = device_create_with_groups(nvme_class, ctrl->dev,
				MKDEV(nvme_char_major, ctrl->instance),
				ctrl, nvme_dev_attr_groups,
				"nvme%d", ctrl->instance);
	if (IS_ERR(ctrl->device)) {
		ret = PTR_ERR(ctrl->device);
		goto out_release_instance;
	}
	get_device(ctrl->device);
	ida_init(&ctrl->ns_ida);

	spin_lock(&dev_list_lock);
	list_add_tail(&ctrl->node, &nvme_ctrl_list);
	spin_unlock(&dev_list_lock);

	/*
	 * 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));

	return 0;
out_release_instance:
	nvme_release_instance(ctrl);
out:
	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;

	mutex_lock(&ctrl->namespaces_mutex);

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

	list_for_each_entry(ns, &ctrl->namespaces, list) {
		/*
		 * 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))
			continue;
		revalidate_disk(ns->disk);
		blk_set_queue_dying(ns->queue);

		/* Forcibly unquiesce queues to avoid blocking dispatch */
		blk_mq_unquiesce_queue(ns->queue);
	}
	mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_kill_queues);

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

	mutex_lock(&ctrl->namespaces_mutex);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_mq_unfreeze_queue(ns->queue);
	mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_unfreeze);

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

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

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

	mutex_lock(&ctrl->namespaces_mutex);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_mq_freeze_queue_wait(ns->queue);
	mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_wait_freeze);

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

	mutex_lock(&ctrl->namespaces_mutex);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_freeze_queue_start(ns->queue);
	mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_start_freeze);

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

	mutex_lock(&ctrl->namespaces_mutex);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_mq_quiesce_queue(ns->queue);
	mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_stop_queues);

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

	mutex_lock(&ctrl->namespaces_mutex);
	list_for_each_entry(ns, &ctrl->namespaces, list)
		blk_mq_unquiesce_queue(ns->queue);
	mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_start_queues);

int __init nvme_core_init(void)
{
	int result;

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

	result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme",
							&nvme_dev_fops);
	if (result < 0)
		goto destroy_wq;
	else if (result > 0)
		nvme_char_major = result;

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

	return 0;

unregister_chrdev:
	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
destroy_wq:
	destroy_workqueue(nvme_wq);
	return result;
}

void nvme_core_exit(void)
{
	class_destroy(nvme_class);
	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
	destroy_workqueue(nvme_wq);
}

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