summaryrefslogtreecommitdiffstats
path: root/drivers/block/nvme-core.c
blob: 51824d1f23ea53df5d49cd6d4e10e07b6b45b1fb (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
/*
 * NVM Express device driver
 * Copyright (c) 2011, 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.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc.,
 * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
 */

#include <linux/nvme.h>
#include <linux/bio.h>
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/idr.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/kdev_t.h>
#include <linux/kthread.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/pci.h>
#include <linux/poison.h>
#include <linux/ptrace.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <scsi/sg.h>
#include <asm-generic/io-64-nonatomic-lo-hi.h>

#define NVME_Q_DEPTH 1024
#define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
#define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
#define ADMIN_TIMEOUT	(60 * HZ)

static int nvme_major;
module_param(nvme_major, int, 0);

static int use_threaded_interrupts;
module_param(use_threaded_interrupts, int, 0);

static DEFINE_SPINLOCK(dev_list_lock);
static LIST_HEAD(dev_list);
static struct task_struct *nvme_thread;
static struct workqueue_struct *nvme_workq;

static void nvme_reset_failed_dev(struct work_struct *ws);

struct async_cmd_info {
	struct kthread_work work;
	struct kthread_worker *worker;
	u32 result;
	int status;
	void *ctx;
};

/*
 * An NVM Express queue.  Each device has at least two (one for admin
 * commands and one for I/O commands).
 */
struct nvme_queue {
	struct device *q_dmadev;
	struct nvme_dev *dev;
	char irqname[24];	/* nvme4294967295-65535\0 */
	spinlock_t q_lock;
	struct nvme_command *sq_cmds;
	volatile struct nvme_completion *cqes;
	dma_addr_t sq_dma_addr;
	dma_addr_t cq_dma_addr;
	wait_queue_head_t sq_full;
	wait_queue_t sq_cong_wait;
	struct bio_list sq_cong;
	u32 __iomem *q_db;
	u16 q_depth;
	u16 cq_vector;
	u16 sq_head;
	u16 sq_tail;
	u16 cq_head;
	u16 qid;
	u8 cq_phase;
	u8 cqe_seen;
	u8 q_suspended;
	struct async_cmd_info cmdinfo;
	unsigned long cmdid_data[];
};

/*
 * Check we didin't inadvertently grow the command struct
 */
static inline void _nvme_check_size(void)
{
	BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != 4096);
	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096);
	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
}

typedef void (*nvme_completion_fn)(struct nvme_dev *, void *,
						struct nvme_completion *);

struct nvme_cmd_info {
	nvme_completion_fn fn;
	void *ctx;
	unsigned long timeout;
	int aborted;
};

static struct nvme_cmd_info *nvme_cmd_info(struct nvme_queue *nvmeq)
{
	return (void *)&nvmeq->cmdid_data[BITS_TO_LONGS(nvmeq->q_depth)];
}

static unsigned nvme_queue_extra(int depth)
{
	return DIV_ROUND_UP(depth, 8) + (depth * sizeof(struct nvme_cmd_info));
}

/**
 * alloc_cmdid() - Allocate a Command ID
 * @nvmeq: The queue that will be used for this command
 * @ctx: A pointer that will be passed to the handler
 * @handler: The function to call on completion
 *
 * Allocate a Command ID for a queue.  The data passed in will
 * be passed to the completion handler.  This is implemented by using
 * the bottom two bits of the ctx pointer to store the handler ID.
 * Passing in a pointer that's not 4-byte aligned will cause a BUG.
 * We can change this if it becomes a problem.
 *
 * May be called with local interrupts disabled and the q_lock held,
 * or with interrupts enabled and no locks held.
 */
static int alloc_cmdid(struct nvme_queue *nvmeq, void *ctx,
				nvme_completion_fn handler, unsigned timeout)
{
	int depth = nvmeq->q_depth - 1;
	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
	int cmdid;

	do {
		cmdid = find_first_zero_bit(nvmeq->cmdid_data, depth);
		if (cmdid >= depth)
			return -EBUSY;
	} while (test_and_set_bit(cmdid, nvmeq->cmdid_data));

	info[cmdid].fn = handler;
	info[cmdid].ctx = ctx;
	info[cmdid].timeout = jiffies + timeout;
	info[cmdid].aborted = 0;
	return cmdid;
}

static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
				nvme_completion_fn handler, unsigned timeout)
{
	int cmdid;
	wait_event_killable(nvmeq->sq_full,
		(cmdid = alloc_cmdid(nvmeq, ctx, handler, timeout)) >= 0);
	return (cmdid < 0) ? -EINTR : cmdid;
}

/* Special values must be less than 0x1000 */
#define CMD_CTX_BASE		((void *)POISON_POINTER_DELTA)
#define CMD_CTX_CANCELLED	(0x30C + CMD_CTX_BASE)
#define CMD_CTX_COMPLETED	(0x310 + CMD_CTX_BASE)
#define CMD_CTX_INVALID		(0x314 + CMD_CTX_BASE)
#define CMD_CTX_FLUSH		(0x318 + CMD_CTX_BASE)
#define CMD_CTX_ABORT		(0x31C + CMD_CTX_BASE)

static void special_completion(struct nvme_dev *dev, void *ctx,
						struct nvme_completion *cqe)
{
	if (ctx == CMD_CTX_CANCELLED)
		return;
	if (ctx == CMD_CTX_FLUSH)
		return;
	if (ctx == CMD_CTX_ABORT) {
		++dev->abort_limit;
		return;
	}
	if (ctx == CMD_CTX_COMPLETED) {
		dev_warn(&dev->pci_dev->dev,
				"completed id %d twice on queue %d\n",
				cqe->command_id, le16_to_cpup(&cqe->sq_id));
		return;
	}
	if (ctx == CMD_CTX_INVALID) {
		dev_warn(&dev->pci_dev->dev,
				"invalid id %d completed on queue %d\n",
				cqe->command_id, le16_to_cpup(&cqe->sq_id));
		return;
	}

	dev_warn(&dev->pci_dev->dev, "Unknown special completion %p\n", ctx);
}

static void async_completion(struct nvme_dev *dev, void *ctx,
						struct nvme_completion *cqe)
{
	struct async_cmd_info *cmdinfo = ctx;
	cmdinfo->result = le32_to_cpup(&cqe->result);
	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
	queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
}

/*
 * Called with local interrupts disabled and the q_lock held.  May not sleep.
 */
static void *free_cmdid(struct nvme_queue *nvmeq, int cmdid,
						nvme_completion_fn *fn)
{
	void *ctx;
	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);

	if (cmdid >= nvmeq->q_depth) {
		*fn = special_completion;
		return CMD_CTX_INVALID;
	}
	if (fn)
		*fn = info[cmdid].fn;
	ctx = info[cmdid].ctx;
	info[cmdid].fn = special_completion;
	info[cmdid].ctx = CMD_CTX_COMPLETED;
	clear_bit(cmdid, nvmeq->cmdid_data);
	wake_up(&nvmeq->sq_full);
	return ctx;
}

static void *cancel_cmdid(struct nvme_queue *nvmeq, int cmdid,
						nvme_completion_fn *fn)
{
	void *ctx;
	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
	if (fn)
		*fn = info[cmdid].fn;
	ctx = info[cmdid].ctx;
	info[cmdid].fn = special_completion;
	info[cmdid].ctx = CMD_CTX_CANCELLED;
	return ctx;
}

struct nvme_queue *get_nvmeq(struct nvme_dev *dev)
{
	return dev->queues[get_cpu() + 1];
}

void put_nvmeq(struct nvme_queue *nvmeq)
{
	put_cpu();
}

/**
 * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
 * @nvmeq: The queue to use
 * @cmd: The command to send
 *
 * Safe to use from interrupt context
 */
static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
{
	unsigned long flags;
	u16 tail;
	spin_lock_irqsave(&nvmeq->q_lock, flags);
	tail = nvmeq->sq_tail;
	memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
	if (++tail == nvmeq->q_depth)
		tail = 0;
	writel(tail, nvmeq->q_db);
	nvmeq->sq_tail = tail;
	spin_unlock_irqrestore(&nvmeq->q_lock, flags);

	return 0;
}

static __le64 **iod_list(struct nvme_iod *iod)
{
	return ((void *)iod) + iod->offset;
}

/*
 * Will slightly overestimate the number of pages needed.  This is OK
 * as it only leads to a small amount of wasted memory for the lifetime of
 * the I/O.
 */
static int nvme_npages(unsigned size)
{
	unsigned nprps = DIV_ROUND_UP(size + PAGE_SIZE, PAGE_SIZE);
	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
}

static struct nvme_iod *
nvme_alloc_iod(unsigned nseg, unsigned nbytes, gfp_t gfp)
{
	struct nvme_iod *iod = kmalloc(sizeof(struct nvme_iod) +
				sizeof(__le64 *) * nvme_npages(nbytes) +
				sizeof(struct scatterlist) * nseg, gfp);

	if (iod) {
		iod->offset = offsetof(struct nvme_iod, sg[nseg]);
		iod->npages = -1;
		iod->length = nbytes;
		iod->nents = 0;
		iod->start_time = jiffies;
	}

	return iod;
}

void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
{
	const int last_prp = PAGE_SIZE / 8 - 1;
	int i;
	__le64 **list = iod_list(iod);
	dma_addr_t prp_dma = iod->first_dma;

	if (iod->npages == 0)
		dma_pool_free(dev->prp_small_pool, list[0], prp_dma);
	for (i = 0; i < iod->npages; i++) {
		__le64 *prp_list = list[i];
		dma_addr_t next_prp_dma = le64_to_cpu(prp_list[last_prp]);
		dma_pool_free(dev->prp_page_pool, prp_list, prp_dma);
		prp_dma = next_prp_dma;
	}
	kfree(iod);
}

static void nvme_start_io_acct(struct bio *bio)
{
	struct gendisk *disk = bio->bi_bdev->bd_disk;
	const int rw = bio_data_dir(bio);
	int cpu = part_stat_lock();
	part_round_stats(cpu, &disk->part0);
	part_stat_inc(cpu, &disk->part0, ios[rw]);
	part_stat_add(cpu, &disk->part0, sectors[rw], bio_sectors(bio));
	part_inc_in_flight(&disk->part0, rw);
	part_stat_unlock();
}

static void nvme_end_io_acct(struct bio *bio, unsigned long start_time)
{
	struct gendisk *disk = bio->bi_bdev->bd_disk;
	const int rw = bio_data_dir(bio);
	unsigned long duration = jiffies - start_time;
	int cpu = part_stat_lock();
	part_stat_add(cpu, &disk->part0, ticks[rw], duration);
	part_round_stats(cpu, &disk->part0);
	part_dec_in_flight(&disk->part0, rw);
	part_stat_unlock();
}

static void bio_completion(struct nvme_dev *dev, void *ctx,
						struct nvme_completion *cqe)
{
	struct nvme_iod *iod = ctx;
	struct bio *bio = iod->private;
	u16 status = le16_to_cpup(&cqe->status) >> 1;

	if (iod->nents) {
		dma_unmap_sg(&dev->pci_dev->dev, iod->sg, iod->nents,
			bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
		nvme_end_io_acct(bio, iod->start_time);
	}
	nvme_free_iod(dev, iod);
	if (status)
		bio_endio(bio, -EIO);
	else
		bio_endio(bio, 0);
}

/* length is in bytes.  gfp flags indicates whether we may sleep. */
int nvme_setup_prps(struct nvme_dev *dev, struct nvme_common_command *cmd,
			struct nvme_iod *iod, int total_len, gfp_t gfp)
{
	struct dma_pool *pool;
	int length = total_len;
	struct scatterlist *sg = iod->sg;
	int dma_len = sg_dma_len(sg);
	u64 dma_addr = sg_dma_address(sg);
	int offset = offset_in_page(dma_addr);
	__le64 *prp_list;
	__le64 **list = iod_list(iod);
	dma_addr_t prp_dma;
	int nprps, i;

	cmd->prp1 = cpu_to_le64(dma_addr);
	length -= (PAGE_SIZE - offset);
	if (length <= 0)
		return total_len;

	dma_len -= (PAGE_SIZE - offset);
	if (dma_len) {
		dma_addr += (PAGE_SIZE - offset);
	} else {
		sg = sg_next(sg);
		dma_addr = sg_dma_address(sg);
		dma_len = sg_dma_len(sg);
	}

	if (length <= PAGE_SIZE) {
		cmd->prp2 = cpu_to_le64(dma_addr);
		return total_len;
	}

	nprps = DIV_ROUND_UP(length, PAGE_SIZE);
	if (nprps <= (256 / 8)) {
		pool = dev->prp_small_pool;
		iod->npages = 0;
	} else {
		pool = dev->prp_page_pool;
		iod->npages = 1;
	}

	prp_list = dma_pool_alloc(pool, gfp, &prp_dma);
	if (!prp_list) {
		cmd->prp2 = cpu_to_le64(dma_addr);
		iod->npages = -1;
		return (total_len - length) + PAGE_SIZE;
	}
	list[0] = prp_list;
	iod->first_dma = prp_dma;
	cmd->prp2 = cpu_to_le64(prp_dma);
	i = 0;
	for (;;) {
		if (i == PAGE_SIZE / 8) {
			__le64 *old_prp_list = prp_list;
			prp_list = dma_pool_alloc(pool, gfp, &prp_dma);
			if (!prp_list)
				return total_len - length;
			list[iod->npages++] = prp_list;
			prp_list[0] = old_prp_list[i - 1];
			old_prp_list[i - 1] = cpu_to_le64(prp_dma);
			i = 1;
		}
		prp_list[i++] = cpu_to_le64(dma_addr);
		dma_len -= PAGE_SIZE;
		dma_addr += PAGE_SIZE;
		length -= PAGE_SIZE;
		if (length <= 0)
			break;
		if (dma_len > 0)
			continue;
		BUG_ON(dma_len < 0);
		sg = sg_next(sg);
		dma_addr = sg_dma_address(sg);
		dma_len = sg_dma_len(sg);
	}

	return total_len;
}

static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq,
				 int len)
{
	struct bio *split = bio_split(bio, len >> 9, GFP_ATOMIC, NULL);
	if (!split)
		return -ENOMEM;

	bio_chain(split, bio);

	if (bio_list_empty(&nvmeq->sq_cong))
		add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
	bio_list_add(&nvmeq->sq_cong, split);
	bio_list_add(&nvmeq->sq_cong, bio);

	return 0;
}

/* NVMe scatterlists require no holes in the virtual address */
#define BIOVEC_NOT_VIRT_MERGEABLE(vec1, vec2)	((vec2)->bv_offset || \
			(((vec1)->bv_offset + (vec1)->bv_len) % PAGE_SIZE))

static int nvme_map_bio(struct nvme_queue *nvmeq, struct nvme_iod *iod,
		struct bio *bio, enum dma_data_direction dma_dir, int psegs)
{
	struct bio_vec bvec, bvprv;
	struct bvec_iter iter;
	struct scatterlist *sg = NULL;
	int length = 0, nsegs = 0, split_len = bio->bi_iter.bi_size;
	int first = 1;

	if (nvmeq->dev->stripe_size)
		split_len = nvmeq->dev->stripe_size -
			((bio->bi_iter.bi_sector << 9) &
			 (nvmeq->dev->stripe_size - 1));

	sg_init_table(iod->sg, psegs);
	bio_for_each_segment(bvec, bio, iter) {
		if (!first && BIOVEC_PHYS_MERGEABLE(&bvprv, &bvec)) {
			sg->length += bvec.bv_len;
		} else {
			if (!first && BIOVEC_NOT_VIRT_MERGEABLE(&bvprv, &bvec))
				return nvme_split_and_submit(bio, nvmeq,
							     length);

			sg = sg ? sg + 1 : iod->sg;
			sg_set_page(sg, bvec.bv_page,
				    bvec.bv_len, bvec.bv_offset);
			nsegs++;
		}

		if (split_len - length < bvec.bv_len)
			return nvme_split_and_submit(bio, nvmeq, split_len);
		length += bvec.bv_len;
		bvprv = bvec;
		first = 0;
	}
	iod->nents = nsegs;
	sg_mark_end(sg);
	if (dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir) == 0)
		return -ENOMEM;

	BUG_ON(length != bio->bi_iter.bi_size);
	return length;
}

/*
 * We reuse the small pool to allocate the 16-byte range here as it is not
 * worth having a special pool for these or additional cases to handle freeing
 * the iod.
 */
static int nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
		struct bio *bio, struct nvme_iod *iod, int cmdid)
{
	struct nvme_dsm_range *range;
	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];

	range = dma_pool_alloc(nvmeq->dev->prp_small_pool, GFP_ATOMIC,
							&iod->first_dma);
	if (!range)
		return -ENOMEM;

	iod_list(iod)[0] = (__le64 *)range;
	iod->npages = 0;

	range->cattr = cpu_to_le32(0);
	range->nlb = cpu_to_le32(bio->bi_iter.bi_size >> ns->lba_shift);
	range->slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));

	memset(cmnd, 0, sizeof(*cmnd));
	cmnd->dsm.opcode = nvme_cmd_dsm;
	cmnd->dsm.command_id = cmdid;
	cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
	cmnd->dsm.prp1 = cpu_to_le64(iod->first_dma);
	cmnd->dsm.nr = 0;
	cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);

	if (++nvmeq->sq_tail == nvmeq->q_depth)
		nvmeq->sq_tail = 0;
	writel(nvmeq->sq_tail, nvmeq->q_db);

	return 0;
}

static int nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
								int cmdid)
{
	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];

	memset(cmnd, 0, sizeof(*cmnd));
	cmnd->common.opcode = nvme_cmd_flush;
	cmnd->common.command_id = cmdid;
	cmnd->common.nsid = cpu_to_le32(ns->ns_id);

	if (++nvmeq->sq_tail == nvmeq->q_depth)
		nvmeq->sq_tail = 0;
	writel(nvmeq->sq_tail, nvmeq->q_db);

	return 0;
}

int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns)
{
	int cmdid = alloc_cmdid(nvmeq, (void *)CMD_CTX_FLUSH,
					special_completion, NVME_IO_TIMEOUT);
	if (unlikely(cmdid < 0))
		return cmdid;

	return nvme_submit_flush(nvmeq, ns, cmdid);
}

/*
 * Called with local interrupts disabled and the q_lock held.  May not sleep.
 */
static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
								struct bio *bio)
{
	struct nvme_command *cmnd;
	struct nvme_iod *iod;
	enum dma_data_direction dma_dir;
	int cmdid, length, result;
	u16 control;
	u32 dsmgmt;
	int psegs = bio_phys_segments(ns->queue, bio);

	if ((bio->bi_rw & REQ_FLUSH) && psegs) {
		result = nvme_submit_flush_data(nvmeq, ns);
		if (result)
			return result;
	}

	result = -ENOMEM;
	iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC);
	if (!iod)
		goto nomem;
	iod->private = bio;

	result = -EBUSY;
	cmdid = alloc_cmdid(nvmeq, iod, bio_completion, NVME_IO_TIMEOUT);
	if (unlikely(cmdid < 0))
		goto free_iod;

	if (bio->bi_rw & REQ_DISCARD) {
		result = nvme_submit_discard(nvmeq, ns, bio, iod, cmdid);
		if (result)
			goto free_cmdid;
		return result;
	}
	if ((bio->bi_rw & REQ_FLUSH) && !psegs)
		return nvme_submit_flush(nvmeq, ns, cmdid);

	control = 0;
	if (bio->bi_rw & REQ_FUA)
		control |= NVME_RW_FUA;
	if (bio->bi_rw & (REQ_FAILFAST_DEV | REQ_RAHEAD))
		control |= NVME_RW_LR;

	dsmgmt = 0;
	if (bio->bi_rw & REQ_RAHEAD)
		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;

	cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];

	memset(cmnd, 0, sizeof(*cmnd));
	if (bio_data_dir(bio)) {
		cmnd->rw.opcode = nvme_cmd_write;
		dma_dir = DMA_TO_DEVICE;
	} else {
		cmnd->rw.opcode = nvme_cmd_read;
		dma_dir = DMA_FROM_DEVICE;
	}

	result = nvme_map_bio(nvmeq, iod, bio, dma_dir, psegs);
	if (result <= 0)
		goto free_cmdid;
	length = result;

	cmnd->rw.command_id = cmdid;
	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
	length = nvme_setup_prps(nvmeq->dev, &cmnd->common, iod, length,
								GFP_ATOMIC);
	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
	cmnd->rw.length = cpu_to_le16((length >> ns->lba_shift) - 1);
	cmnd->rw.control = cpu_to_le16(control);
	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);

	nvme_start_io_acct(bio);
	if (++nvmeq->sq_tail == nvmeq->q_depth)
		nvmeq->sq_tail = 0;
	writel(nvmeq->sq_tail, nvmeq->q_db);

	return 0;

 free_cmdid:
	free_cmdid(nvmeq, cmdid, NULL);
 free_iod:
	nvme_free_iod(nvmeq->dev, iod);
 nomem:
	return result;
}

static int nvme_process_cq(struct nvme_queue *nvmeq)
{
	u16 head, phase;

	head = nvmeq->cq_head;
	phase = nvmeq->cq_phase;

	for (;;) {
		void *ctx;
		nvme_completion_fn fn;
		struct nvme_completion cqe = nvmeq->cqes[head];
		if ((le16_to_cpu(cqe.status) & 1) != phase)
			break;
		nvmeq->sq_head = le16_to_cpu(cqe.sq_head);
		if (++head == nvmeq->q_depth) {
			head = 0;
			phase = !phase;
		}

		ctx = free_cmdid(nvmeq, cqe.command_id, &fn);
		fn(nvmeq->dev, ctx, &cqe);
	}

	/* If the controller ignores the cq head doorbell and continuously
	 * writes to the queue, it is theoretically possible to wrap around
	 * the queue twice and mistakenly return IRQ_NONE.  Linux only
	 * requires that 0.1% of your interrupts are handled, so this isn't
	 * a big problem.
	 */
	if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
		return 0;

	writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
	nvmeq->cq_head = head;
	nvmeq->cq_phase = phase;

	nvmeq->cqe_seen = 1;
	return 1;
}

static void nvme_make_request(struct request_queue *q, struct bio *bio)
{
	struct nvme_ns *ns = q->queuedata;
	struct nvme_queue *nvmeq = get_nvmeq(ns->dev);
	int result = -EBUSY;

	if (!nvmeq) {
		put_nvmeq(NULL);
		bio_endio(bio, -EIO);
		return;
	}

	spin_lock_irq(&nvmeq->q_lock);
	if (!nvmeq->q_suspended && bio_list_empty(&nvmeq->sq_cong))
		result = nvme_submit_bio_queue(nvmeq, ns, bio);
	if (unlikely(result)) {
		if (bio_list_empty(&nvmeq->sq_cong))
			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
		bio_list_add(&nvmeq->sq_cong, bio);
	}

	nvme_process_cq(nvmeq);
	spin_unlock_irq(&nvmeq->q_lock);
	put_nvmeq(nvmeq);
}

static irqreturn_t nvme_irq(int irq, void *data)
{
	irqreturn_t result;
	struct nvme_queue *nvmeq = data;
	spin_lock(&nvmeq->q_lock);
	nvme_process_cq(nvmeq);
	result = nvmeq->cqe_seen ? IRQ_HANDLED : IRQ_NONE;
	nvmeq->cqe_seen = 0;
	spin_unlock(&nvmeq->q_lock);
	return result;
}

static irqreturn_t nvme_irq_check(int irq, void *data)
{
	struct nvme_queue *nvmeq = data;
	struct nvme_completion cqe = nvmeq->cqes[nvmeq->cq_head];
	if ((le16_to_cpu(cqe.status) & 1) != nvmeq->cq_phase)
		return IRQ_NONE;
	return IRQ_WAKE_THREAD;
}

static void nvme_abort_command(struct nvme_queue *nvmeq, int cmdid)
{
	spin_lock_irq(&nvmeq->q_lock);
	cancel_cmdid(nvmeq, cmdid, NULL);
	spin_unlock_irq(&nvmeq->q_lock);
}

struct sync_cmd_info {
	struct task_struct *task;
	u32 result;
	int status;
};

static void sync_completion(struct nvme_dev *dev, void *ctx,
						struct nvme_completion *cqe)
{
	struct sync_cmd_info *cmdinfo = ctx;
	cmdinfo->result = le32_to_cpup(&cqe->result);
	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
	wake_up_process(cmdinfo->task);
}

/*
 * 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 nvme_queue *nvmeq, struct nvme_command *cmd,
						u32 *result, unsigned timeout)
{
	int cmdid;
	struct sync_cmd_info cmdinfo;

	cmdinfo.task = current;
	cmdinfo.status = -EINTR;

	cmdid = alloc_cmdid_killable(nvmeq, &cmdinfo, sync_completion,
								timeout);
	if (cmdid < 0)
		return cmdid;
	cmd->common.command_id = cmdid;

	set_current_state(TASK_KILLABLE);
	nvme_submit_cmd(nvmeq, cmd);
	schedule_timeout(timeout);

	if (cmdinfo.status == -EINTR) {
		nvme_abort_command(nvmeq, cmdid);
		return -EINTR;
	}

	if (result)
		*result = cmdinfo.result;

	return cmdinfo.status;
}

static int nvme_submit_async_cmd(struct nvme_queue *nvmeq,
			struct nvme_command *cmd,
			struct async_cmd_info *cmdinfo, unsigned timeout)
{
	int cmdid;

	cmdid = alloc_cmdid_killable(nvmeq, cmdinfo, async_completion, timeout);
	if (cmdid < 0)
		return cmdid;
	cmdinfo->status = -EINTR;
	cmd->common.command_id = cmdid;
	nvme_submit_cmd(nvmeq, cmd);
	return 0;
}

int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
								u32 *result)
{
	return nvme_submit_sync_cmd(dev->queues[0], cmd, result, ADMIN_TIMEOUT);
}

static int nvme_submit_admin_cmd_async(struct nvme_dev *dev,
		struct nvme_command *cmd, struct async_cmd_info *cmdinfo)
{
	return nvme_submit_async_cmd(dev->queues[0], cmd, cmdinfo,
								ADMIN_TIMEOUT);
}

static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
{
	int status;
	struct nvme_command c;

	memset(&c, 0, sizeof(c));
	c.delete_queue.opcode = opcode;
	c.delete_queue.qid = cpu_to_le16(id);

	status = nvme_submit_admin_cmd(dev, &c, NULL);
	if (status)
		return -EIO;
	return 0;
}

static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
						struct nvme_queue *nvmeq)
{
	int status;
	struct nvme_command c;
	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;

	memset(&c, 0, sizeof(c));
	c.create_cq.opcode = nvme_admin_create_cq;
	c.create_cq.prp1 = cpu_to_le64(nvmeq->cq_dma_addr);
	c.create_cq.cqid = cpu_to_le16(qid);
	c.create_cq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
	c.create_cq.cq_flags = cpu_to_le16(flags);
	c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);

	status = nvme_submit_admin_cmd(dev, &c, NULL);
	if (status)
		return -EIO;
	return 0;
}

static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
						struct nvme_queue *nvmeq)
{
	int status;
	struct nvme_command c;
	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;

	memset(&c, 0, sizeof(c));
	c.create_sq.opcode = nvme_admin_create_sq;
	c.create_sq.prp1 = cpu_to_le64(nvmeq->sq_dma_addr);
	c.create_sq.sqid = cpu_to_le16(qid);
	c.create_sq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
	c.create_sq.sq_flags = cpu_to_le16(flags);
	c.create_sq.cqid = cpu_to_le16(qid);

	status = nvme_submit_admin_cmd(dev, &c, NULL);
	if (status)
		return -EIO;
	return 0;
}

static int adapter_delete_cq(struct nvme_dev *dev, u16 cqid)
{
	return adapter_delete_queue(dev, nvme_admin_delete_cq, cqid);
}

static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid)
{
	return adapter_delete_queue(dev, nvme_admin_delete_sq, sqid);
}

int nvme_identify(struct nvme_dev *dev, unsigned nsid, unsigned cns,
							dma_addr_t dma_addr)
{
	struct nvme_command c;

	memset(&c, 0, sizeof(c));
	c.identify.opcode = nvme_admin_identify;
	c.identify.nsid = cpu_to_le32(nsid);
	c.identify.prp1 = cpu_to_le64(dma_addr);
	c.identify.cns = cpu_to_le32(cns);

	return nvme_submit_admin_cmd(dev, &c, NULL);
}

int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid,
					dma_addr_t dma_addr, u32 *result)
{
	struct nvme_command c;

	memset(&c, 0, sizeof(c));
	c.features.opcode = nvme_admin_get_features;
	c.features.nsid = cpu_to_le32(nsid);
	c.features.prp1 = cpu_to_le64(dma_addr);
	c.features.fid = cpu_to_le32(fid);

	return nvme_submit_admin_cmd(dev, &c, result);
}

int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
					dma_addr_t dma_addr, u32 *result)
{
	struct nvme_command c;

	memset(&c, 0, sizeof(c));
	c.features.opcode = nvme_admin_set_features;
	c.features.prp1 = cpu_to_le64(dma_addr);
	c.features.fid = cpu_to_le32(fid);
	c.features.dword11 = cpu_to_le32(dword11);

	return nvme_submit_admin_cmd(dev, &c, result);
}

/**
 * nvme_abort_cmd - Attempt aborting a command
 * @cmdid: Command id of a timed out IO
 * @queue: The queue with timed out IO
 *
 * Schedule controller reset if the command was already aborted once before and
 * still hasn't been returned to the driver, or if this is the admin queue.
 */
static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
{
	int a_cmdid;
	struct nvme_command cmd;
	struct nvme_dev *dev = nvmeq->dev;
	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);

	if (!nvmeq->qid || info[cmdid].aborted) {
		if (work_busy(&dev->reset_work))
			return;
		list_del_init(&dev->node);
		dev_warn(&dev->pci_dev->dev,
			"I/O %d QID %d timeout, reset controller\n", cmdid,
								nvmeq->qid);
		PREPARE_WORK(&dev->reset_work, nvme_reset_failed_dev);
		queue_work(nvme_workq, &dev->reset_work);
		return;
	}

	if (!dev->abort_limit)
		return;

	a_cmdid = alloc_cmdid(dev->queues[0], CMD_CTX_ABORT, special_completion,
								ADMIN_TIMEOUT);
	if (a_cmdid < 0)
		return;

	memset(&cmd, 0, sizeof(cmd));
	cmd.abort.opcode = nvme_admin_abort_cmd;
	cmd.abort.cid = cmdid;
	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
	cmd.abort.command_id = a_cmdid;

	--dev->abort_limit;
	info[cmdid].aborted = 1;
	info[cmdid].timeout = jiffies + ADMIN_TIMEOUT;

	dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", cmdid,
							nvmeq->qid);
	nvme_submit_cmd(dev->queues[0], &cmd);
}

/**
 * nvme_cancel_ios - Cancel outstanding I/Os
 * @queue: The queue to cancel I/Os on
 * @timeout: True to only cancel I/Os which have timed out
 */
static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
{
	int depth = nvmeq->q_depth - 1;
	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
	unsigned long now = jiffies;
	int cmdid;

	for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) {
		void *ctx;
		nvme_completion_fn fn;
		static struct nvme_completion cqe = {
			.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1),
		};

		if (timeout && !time_after(now, info[cmdid].timeout))
			continue;
		if (info[cmdid].ctx == CMD_CTX_CANCELLED)
			continue;
		if (timeout && nvmeq->dev->initialized) {
			nvme_abort_cmd(cmdid, nvmeq);
			continue;
		}
		dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n", cmdid,
								nvmeq->qid);
		ctx = cancel_cmdid(nvmeq, cmdid, &fn);
		fn(nvmeq->dev, ctx, &cqe);
	}
}

static void nvme_free_queue(struct nvme_queue *nvmeq)
{
	spin_lock_irq(&nvmeq->q_lock);
	while (bio_list_peek(&nvmeq->sq_cong)) {
		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
		bio_endio(bio, -EIO);
	}
	spin_unlock_irq(&nvmeq->q_lock);

	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
	kfree(nvmeq);
}

static void nvme_free_queues(struct nvme_dev *dev, int lowest)
{
	int i;

	for (i = dev->queue_count - 1; i >= lowest; i--) {
		nvme_free_queue(dev->queues[i]);
		dev->queue_count--;
		dev->queues[i] = NULL;
	}
}

/**
 * nvme_suspend_queue - put queue into suspended state
 * @nvmeq - queue to suspend
 *
 * Returns 1 if already suspended, 0 otherwise.
 */
static int nvme_suspend_queue(struct nvme_queue *nvmeq)
{
	int vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;

	spin_lock_irq(&nvmeq->q_lock);
	if (nvmeq->q_suspended) {
		spin_unlock_irq(&nvmeq->q_lock);
		return 1;
	}
	nvmeq->q_suspended = 1;
	spin_unlock_irq(&nvmeq->q_lock);

	irq_set_affinity_hint(vector, NULL);
	free_irq(vector, nvmeq);

	return 0;
}

static void nvme_clear_queue(struct nvme_queue *nvmeq)
{
	spin_lock_irq(&nvmeq->q_lock);
	nvme_process_cq(nvmeq);
	nvme_cancel_ios(nvmeq, false);
	spin_unlock_irq(&nvmeq->q_lock);
}

static void nvme_disable_queue(struct nvme_dev *dev, int qid)
{
	struct nvme_queue *nvmeq = dev->queues[qid];

	if (!nvmeq)
		return;
	if (nvme_suspend_queue(nvmeq))
		return;

	/* Don't tell the adapter to delete the admin queue.
	 * Don't tell a removed adapter to delete IO queues. */
	if (qid && readl(&dev->bar->csts) != -1) {
		adapter_delete_sq(dev, qid);
		adapter_delete_cq(dev, qid);
	}
	nvme_clear_queue(nvmeq);
}

static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
							int depth, int vector)
{
	struct device *dmadev = &dev->pci_dev->dev;
	unsigned extra = nvme_queue_extra(depth);
	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq) + extra, GFP_KERNEL);
	if (!nvmeq)
		return NULL;

	nvmeq->cqes = dma_alloc_coherent(dmadev, CQ_SIZE(depth),
					&nvmeq->cq_dma_addr, GFP_KERNEL);
	if (!nvmeq->cqes)
		goto free_nvmeq;
	memset((void *)nvmeq->cqes, 0, CQ_SIZE(depth));

	nvmeq->sq_cmds = dma_alloc_coherent(dmadev, SQ_SIZE(depth),
					&nvmeq->sq_dma_addr, GFP_KERNEL);
	if (!nvmeq->sq_cmds)
		goto free_cqdma;

	nvmeq->q_dmadev = dmadev;
	nvmeq->dev = dev;
	snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
			dev->instance, qid);
	spin_lock_init(&nvmeq->q_lock);
	nvmeq->cq_head = 0;
	nvmeq->cq_phase = 1;
	init_waitqueue_head(&nvmeq->sq_full);
	init_waitqueue_entry(&nvmeq->sq_cong_wait, nvme_thread);
	bio_list_init(&nvmeq->sq_cong);
	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
	nvmeq->q_depth = depth;
	nvmeq->cq_vector = vector;
	nvmeq->qid = qid;
	nvmeq->q_suspended = 1;
	dev->queue_count++;

	return nvmeq;

 free_cqdma:
	dma_free_coherent(dmadev, CQ_SIZE(depth), (void *)nvmeq->cqes,
							nvmeq->cq_dma_addr);
 free_nvmeq:
	kfree(nvmeq);
	return NULL;
}

static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
							const char *name)
{
	if (use_threaded_interrupts)
		return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
					nvme_irq_check, nvme_irq, IRQF_SHARED,
					name, nvmeq);
	return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,
				IRQF_SHARED, name, nvmeq);
}

static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
{
	struct nvme_dev *dev = nvmeq->dev;
	unsigned extra = nvme_queue_extra(nvmeq->q_depth);

	nvmeq->sq_tail = 0;
	nvmeq->cq_head = 0;
	nvmeq->cq_phase = 1;
	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
	memset(nvmeq->cmdid_data, 0, extra);
	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
	nvme_cancel_ios(nvmeq, false);
	nvmeq->q_suspended = 0;
}

static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
{
	struct nvme_dev *dev = nvmeq->dev;
	int result;

	result = adapter_alloc_cq(dev, qid, nvmeq);
	if (result < 0)
		return result;

	result = adapter_alloc_sq(dev, qid, nvmeq);
	if (result < 0)
		goto release_cq;

	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
	if (result < 0)
		goto release_sq;

	spin_lock_irq(&nvmeq->q_lock);
	nvme_init_queue(nvmeq, qid);
	spin_unlock_irq(&nvmeq->q_lock);

	return result;

 release_sq:
	adapter_delete_sq(dev, qid);
 release_cq:
	adapter_delete_cq(dev, qid);
	return result;
}

static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled)
{
	unsigned long timeout;
	u32 bit = enabled ? NVME_CSTS_RDY : 0;

	timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;

	while ((readl(&dev->bar->csts) & NVME_CSTS_RDY) != bit) {
		msleep(100);
		if (fatal_signal_pending(current))
			return -EINTR;
		if (time_after(jiffies, timeout)) {
			dev_err(&dev->pci_dev->dev,
				"Device not ready; aborting initialisation\n");
			return -ENODEV;
		}
	}

	return 0;
}

/*
 * 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!
 */
static int nvme_disable_ctrl(struct nvme_dev *dev, u64 cap)
{
	u32 cc = readl(&dev->bar->cc);

	if (cc & NVME_CC_ENABLE)
		writel(cc & ~NVME_CC_ENABLE, &dev->bar->cc);
	return nvme_wait_ready(dev, cap, false);
}

static int nvme_enable_ctrl(struct nvme_dev *dev, u64 cap)
{
	return nvme_wait_ready(dev, cap, true);
}

static int nvme_shutdown_ctrl(struct nvme_dev *dev)
{
	unsigned long timeout;
	u32 cc;

	cc = (readl(&dev->bar->cc) & ~NVME_CC_SHN_MASK) | NVME_CC_SHN_NORMAL;
	writel(cc, &dev->bar->cc);

	timeout = 2 * HZ + jiffies;
	while ((readl(&dev->bar->csts) & NVME_CSTS_SHST_MASK) !=
							NVME_CSTS_SHST_CMPLT) {
		msleep(100);
		if (fatal_signal_pending(current))
			return -EINTR;
		if (time_after(jiffies, timeout)) {
			dev_err(&dev->pci_dev->dev,
				"Device shutdown incomplete; abort shutdown\n");
			return -ENODEV;
		}
	}

	return 0;
}

static int nvme_configure_admin_queue(struct nvme_dev *dev)
{
	int result;
	u32 aqa;
	u64 cap = readq(&dev->bar->cap);
	struct nvme_queue *nvmeq;

	result = nvme_disable_ctrl(dev, cap);
	if (result < 0)
		return result;

	nvmeq = dev->queues[0];
	if (!nvmeq) {
		nvmeq = nvme_alloc_queue(dev, 0, 64, 0);
		if (!nvmeq)
			return -ENOMEM;
		dev->queues[0] = nvmeq;
	}

	aqa = nvmeq->q_depth - 1;
	aqa |= aqa << 16;

	dev->ctrl_config = NVME_CC_ENABLE | NVME_CC_CSS_NVM;
	dev->ctrl_config |= (PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT;
	dev->ctrl_config |= NVME_CC_ARB_RR | NVME_CC_SHN_NONE;
	dev->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;

	writel(aqa, &dev->bar->aqa);
	writeq(nvmeq->sq_dma_addr, &dev->bar->asq);
	writeq(nvmeq->cq_dma_addr, &dev->bar->acq);
	writel(dev->ctrl_config, &dev->bar->cc);

	result = nvme_enable_ctrl(dev, cap);
	if (result)
		return result;

	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
	if (result)
		return result;

	spin_lock_irq(&nvmeq->q_lock);
	nvme_init_queue(nvmeq, 0);
	spin_unlock_irq(&nvmeq->q_lock);
	return result;
}

struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
				unsigned long addr, unsigned length)
{
	int i, err, count, nents, offset;
	struct scatterlist *sg;
	struct page **pages;
	struct nvme_iod *iod;

	if (addr & 3)
		return ERR_PTR(-EINVAL);
	if (!length || length > INT_MAX - PAGE_SIZE)
		return ERR_PTR(-EINVAL);

	offset = offset_in_page(addr);
	count = DIV_ROUND_UP(offset + length, PAGE_SIZE);
	pages = kcalloc(count, sizeof(*pages), GFP_KERNEL);
	if (!pages)
		return ERR_PTR(-ENOMEM);

	err = get_user_pages_fast(addr, count, 1, pages);
	if (err < count) {
		count = err;
		err = -EFAULT;
		goto put_pages;
	}

	iod = nvme_alloc_iod(count, length, GFP_KERNEL);
	sg = iod->sg;
	sg_init_table(sg, count);
	for (i = 0; i < count; i++) {
		sg_set_page(&sg[i], pages[i],
			    min_t(unsigned, length, PAGE_SIZE - offset),
			    offset);
		length -= (PAGE_SIZE - offset);
		offset = 0;
	}
	sg_mark_end(&sg[i - 1]);
	iod->nents = count;

	err = -ENOMEM;
	nents = dma_map_sg(&dev->pci_dev->dev, sg, count,
				write ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
	if (!nents)
		goto free_iod;

	kfree(pages);
	return iod;

 free_iod:
	kfree(iod);
 put_pages:
	for (i = 0; i < count; i++)
		put_page(pages[i]);
	kfree(pages);
	return ERR_PTR(err);
}

void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
			struct nvme_iod *iod)
{
	int i;

	dma_unmap_sg(&dev->pci_dev->dev, iod->sg, iod->nents,
				write ? DMA_TO_DEVICE : DMA_FROM_DEVICE);

	for (i = 0; i < iod->nents; i++)
		put_page(sg_page(&iod->sg[i]));
}

static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
{
	struct nvme_dev *dev = ns->dev;
	struct nvme_queue *nvmeq;
	struct nvme_user_io io;
	struct nvme_command c;
	unsigned length, meta_len;
	int status, i;
	struct nvme_iod *iod, *meta_iod = NULL;
	dma_addr_t meta_dma_addr;
	void *meta, *uninitialized_var(meta_mem);

	if (copy_from_user(&io, uio, sizeof(io)))
		return -EFAULT;
	length = (io.nblocks + 1) << ns->lba_shift;
	meta_len = (io.nblocks + 1) * ns->ms;

	if (meta_len && ((io.metadata & 3) || !io.metadata))
		return -EINVAL;

	switch (io.opcode) {
	case nvme_cmd_write:
	case nvme_cmd_read:
	case nvme_cmd_compare:
		iod = nvme_map_user_pages(dev, io.opcode & 1, io.addr, length);
		break;
	default:
		return -EINVAL;
	}

	if (IS_ERR(iod))
		return PTR_ERR(iod);

	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);

	if (meta_len) {
		meta_iod = nvme_map_user_pages(dev, io.opcode & 1, io.metadata,
								meta_len);
		if (IS_ERR(meta_iod)) {
			status = PTR_ERR(meta_iod);
			meta_iod = NULL;
			goto unmap;
		}

		meta_mem = dma_alloc_coherent(&dev->pci_dev->dev, meta_len,
						&meta_dma_addr, GFP_KERNEL);
		if (!meta_mem) {
			status = -ENOMEM;
			goto unmap;
		}

		if (io.opcode & 1) {
			int meta_offset = 0;

			for (i = 0; i < meta_iod->nents; i++) {
				meta = kmap_atomic(sg_page(&meta_iod->sg[i])) +
						meta_iod->sg[i].offset;
				memcpy(meta_mem + meta_offset, meta,
						meta_iod->sg[i].length);
				kunmap_atomic(meta);
				meta_offset += meta_iod->sg[i].length;
			}
		}

		c.rw.metadata = cpu_to_le64(meta_dma_addr);
	}

	length = nvme_setup_prps(dev, &c.common, iod, length, GFP_KERNEL);

	nvmeq = get_nvmeq(dev);
	/*
	 * Since nvme_submit_sync_cmd sleeps, we can't keep preemption
	 * disabled.  We may be preempted at any point, and be rescheduled
	 * to a different CPU.  That will cause cacheline bouncing, but no
	 * additional races since q_lock already protects against other CPUs.
	 */
	put_nvmeq(nvmeq);
	if (length != (io.nblocks + 1) << ns->lba_shift)
		status = -ENOMEM;
	else if (!nvmeq || nvmeq->q_suspended)
		status = -EBUSY;
	else
		status = nvme_submit_sync_cmd(nvmeq, &c, NULL, NVME_IO_TIMEOUT);

	if (meta_len) {
		if (status == NVME_SC_SUCCESS && !(io.opcode & 1)) {
			int meta_offset = 0;

			for (i = 0; i < meta_iod->nents; i++) {
				meta = kmap_atomic(sg_page(&meta_iod->sg[i])) +
						meta_iod->sg[i].offset;
				memcpy(meta, meta_mem + meta_offset,
						meta_iod->sg[i].length);
				kunmap_atomic(meta);
				meta_offset += meta_iod->sg[i].length;
			}
		}

		dma_free_coherent(&dev->pci_dev->dev, meta_len, meta_mem,
								meta_dma_addr);
	}

 unmap:
	nvme_unmap_user_pages(dev, io.opcode & 1, iod);
	nvme_free_iod(dev, iod);

	if (meta_iod) {
		nvme_unmap_user_pages(dev, io.opcode & 1, meta_iod);
		nvme_free_iod(dev, meta_iod);
	}

	return status;
}

static int nvme_user_admin_cmd(struct nvme_dev *dev,
					struct nvme_admin_cmd __user *ucmd)
{
	struct nvme_admin_cmd cmd;
	struct nvme_command c;
	int status, length;
	struct nvme_iod *uninitialized_var(iod);
	unsigned timeout;

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

	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);

	length = cmd.data_len;
	if (cmd.data_len) {
		iod = nvme_map_user_pages(dev, cmd.opcode & 1, cmd.addr,
								length);
		if (IS_ERR(iod))
			return PTR_ERR(iod);
		length = nvme_setup_prps(dev, &c.common, iod, length,
								GFP_KERNEL);
	}

	timeout = cmd.timeout_ms ? msecs_to_jiffies(cmd.timeout_ms) :
								ADMIN_TIMEOUT;
	if (length != cmd.data_len)
		status = -ENOMEM;
	else
		status = nvme_submit_sync_cmd(dev->queues[0], &c, &cmd.result,
								timeout);

	if (cmd.data_len) {
		nvme_unmap_user_pages(dev, cmd.opcode & 1, iod);
		nvme_free_iod(dev, iod);
	}

	if ((status >= 0) && copy_to_user(&ucmd->result, &cmd.result,
							sizeof(cmd.result)))
		status = -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_admin_cmd(ns->dev, (void __user *)arg);
	case NVME_IOCTL_SUBMIT_IO:
		return nvme_submit_io(ns, (void __user *)arg);
	case SG_GET_VERSION_NUM:
		return nvme_sg_get_version_num((void __user *)arg);
	case SG_IO:
		return nvme_sg_io(ns, (void __user *)arg);
	default:
		return -ENOTTY;
	}
}

#ifdef CONFIG_COMPAT
static int nvme_compat_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 SG_IO:
		return nvme_sg_io32(ns, 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)
{
	struct nvme_ns *ns = bdev->bd_disk->private_data;
	struct nvme_dev *dev = ns->dev;

	kref_get(&dev->kref);
	return 0;
}

static void nvme_free_dev(struct kref *kref);

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

	kref_put(&dev->kref, nvme_free_dev);
}

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,
};

static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
{
	while (bio_list_peek(&nvmeq->sq_cong)) {
		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
		struct nvme_ns *ns = bio->bi_bdev->bd_disk->private_data;

		if (bio_list_empty(&nvmeq->sq_cong))
			remove_wait_queue(&nvmeq->sq_full,
							&nvmeq->sq_cong_wait);
		if (nvme_submit_bio_queue(nvmeq, ns, bio)) {
			if (bio_list_empty(&nvmeq->sq_cong))
				add_wait_queue(&nvmeq->sq_full,
							&nvmeq->sq_cong_wait);
			bio_list_add_head(&nvmeq->sq_cong, bio);
			break;
		}
	}
}

static int nvme_kthread(void *data)
{
	struct nvme_dev *dev, *next;

	while (!kthread_should_stop()) {
		set_current_state(TASK_INTERRUPTIBLE);
		spin_lock(&dev_list_lock);
		list_for_each_entry_safe(dev, next, &dev_list, node) {
			int i;
			if (readl(&dev->bar->csts) & NVME_CSTS_CFS &&
							dev->initialized) {
				if (work_busy(&dev->reset_work))
					continue;
				list_del_init(&dev->node);
				dev_warn(&dev->pci_dev->dev,
					"Failed status, reset controller\n");
				PREPARE_WORK(&dev->reset_work,
							nvme_reset_failed_dev);
				queue_work(nvme_workq, &dev->reset_work);
				continue;
			}
			for (i = 0; i < dev->queue_count; i++) {
				struct nvme_queue *nvmeq = dev->queues[i];
				if (!nvmeq)
					continue;
				spin_lock_irq(&nvmeq->q_lock);
				if (nvmeq->q_suspended)
					goto unlock;
				nvme_process_cq(nvmeq);
				nvme_cancel_ios(nvmeq, true);
				nvme_resubmit_bios(nvmeq);
 unlock:
				spin_unlock_irq(&nvmeq->q_lock);
			}
		}
		spin_unlock(&dev_list_lock);
		schedule_timeout(round_jiffies_relative(HZ));
	}
	return 0;
}

static void nvme_config_discard(struct nvme_ns *ns)
{
	u32 logical_block_size = queue_logical_block_size(ns->queue);
	ns->queue->limits.discard_zeroes_data = 0;
	ns->queue->limits.discard_alignment = logical_block_size;
	ns->queue->limits.discard_granularity = logical_block_size;
	ns->queue->limits.max_discard_sectors = 0xffffffff;
	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
}

static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
			struct nvme_id_ns *id, struct nvme_lba_range_type *rt)
{
	struct nvme_ns *ns;
	struct gendisk *disk;
	int lbaf;

	if (rt->attributes & NVME_LBART_ATTRIB_HIDE)
		return NULL;

	ns = kzalloc(sizeof(*ns), GFP_KERNEL);
	if (!ns)
		return NULL;
	ns->queue = blk_alloc_queue(GFP_KERNEL);
	if (!ns->queue)
		goto out_free_ns;
	ns->queue->queue_flags = QUEUE_FLAG_DEFAULT;
	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
	blk_queue_make_request(ns->queue, nvme_make_request);
	ns->dev = dev;
	ns->queue->queuedata = ns;

	disk = alloc_disk(0);
	if (!disk)
		goto out_free_queue;
	ns->ns_id = nsid;
	ns->disk = disk;
	lbaf = id->flbas & 0xf;
	ns->lba_shift = id->lbaf[lbaf].ds;
	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
	if (dev->max_hw_sectors)
		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);

	disk->major = nvme_major;
	disk->first_minor = 0;
	disk->fops = &nvme_fops;
	disk->private_data = ns;
	disk->queue = ns->queue;
	disk->driverfs_dev = &dev->pci_dev->dev;
	disk->flags = GENHD_FL_EXT_DEVT;
	sprintf(disk->disk_name, "nvme%dn%d", dev->instance, nsid);
	set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));

	if (dev->oncs & NVME_CTRL_ONCS_DSM)
		nvme_config_discard(ns);

	return ns;

 out_free_queue:
	blk_cleanup_queue(ns->queue);
 out_free_ns:
	kfree(ns);
	return NULL;
}

static int set_queue_count(struct nvme_dev *dev, int count)
{
	int status;
	u32 result;
	u32 q_count = (count - 1) | ((count - 1) << 16);

	status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, q_count, 0,
								&result);
	if (status)
		return status < 0 ? -EIO : -EBUSY;
	return min(result & 0xffff, result >> 16) + 1;
}

static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
{
	return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
}

static int nvme_setup_io_queues(struct nvme_dev *dev)
{
	struct nvme_queue *adminq = dev->queues[0];
	struct pci_dev *pdev = dev->pci_dev;
	int result, cpu, i, vecs, nr_io_queues, size, q_depth;

	nr_io_queues = num_online_cpus();
	result = set_queue_count(dev, nr_io_queues);
	if (result < 0)
		return result;
	if (result < nr_io_queues)
		nr_io_queues = result;

	size = db_bar_size(dev, nr_io_queues);
	if (size > 8192) {
		iounmap(dev->bar);
		do {
			dev->bar = ioremap(pci_resource_start(pdev, 0), size);
			if (dev->bar)
				break;
			if (!--nr_io_queues)
				return -ENOMEM;
			size = db_bar_size(dev, nr_io_queues);
		} while (1);
		dev->dbs = ((void __iomem *)dev->bar) + 4096;
		dev->queues[0]->q_db = dev->dbs;
	}

	/* Deregister the admin queue's interrupt */
	free_irq(dev->entry[0].vector, adminq);

	vecs = nr_io_queues;
	for (i = 0; i < vecs; i++)
		dev->entry[i].entry = i;
	for (;;) {
		result = pci_enable_msix(pdev, dev->entry, vecs);
		if (result <= 0)
			break;
		vecs = result;
	}

	if (result < 0) {
		vecs = nr_io_queues;
		if (vecs > 32)
			vecs = 32;
		for (;;) {
			result = pci_enable_msi_block(pdev, vecs);
			if (result == 0) {
				for (i = 0; i < vecs; i++)
					dev->entry[i].vector = i + pdev->irq;
				break;
			} else if (result < 0) {
				vecs = 1;
				break;
			}
			vecs = result;
		}
	}

	/*
	 * Should investigate if there's a performance win from allocating
	 * more queues than interrupt vectors; it might allow the submission
	 * path to scale better, even if the receive path is limited by the
	 * number of interrupts.
	 */
	nr_io_queues = vecs;

	result = queue_request_irq(dev, adminq, adminq->irqname);
	if (result) {
		adminq->q_suspended = 1;
		goto free_queues;
	}

	/* Free previously allocated queues that are no longer usable */
	spin_lock(&dev_list_lock);
	for (i = dev->queue_count - 1; i > nr_io_queues; i--) {
		struct nvme_queue *nvmeq = dev->queues[i];

		spin_lock_irq(&nvmeq->q_lock);
		nvme_cancel_ios(nvmeq, false);
		spin_unlock_irq(&nvmeq->q_lock);

		nvme_free_queue(nvmeq);
		dev->queue_count--;
		dev->queues[i] = NULL;
	}
	spin_unlock(&dev_list_lock);

	cpu = cpumask_first(cpu_online_mask);
	for (i = 0; i < nr_io_queues; i++) {
		irq_set_affinity_hint(dev->entry[i].vector, get_cpu_mask(cpu));
		cpu = cpumask_next(cpu, cpu_online_mask);
	}

	q_depth = min_t(int, NVME_CAP_MQES(readq(&dev->bar->cap)) + 1,
								NVME_Q_DEPTH);
	for (i = dev->queue_count - 1; i < nr_io_queues; i++) {
		dev->queues[i + 1] = nvme_alloc_queue(dev, i + 1, q_depth, i);
		if (!dev->queues[i + 1]) {
			result = -ENOMEM;
			goto free_queues;
		}
	}

	for (; i < num_possible_cpus(); i++) {
		int target = i % rounddown_pow_of_two(dev->queue_count - 1);
		dev->queues[i + 1] = dev->queues[target + 1];
	}

	for (i = 1; i < dev->queue_count; i++) {
		result = nvme_create_queue(dev->queues[i], i);
		if (result) {
			for (--i; i > 0; i--)
				nvme_disable_queue(dev, i);
			goto free_queues;
		}
	}

	return 0;

 free_queues:
	nvme_free_queues(dev, 1);
	return result;
}

/*
 * Return: error value if an error occurred setting up the queues or calling
 * Identify Device.  0 if these succeeded, even if adding some of the
 * namespaces failed.  At the moment, these failures are silent.  TBD which
 * failures should be reported.
 */
static int nvme_dev_add(struct nvme_dev *dev)
{
	struct pci_dev *pdev = dev->pci_dev;
	int res;
	unsigned nn, i;
	struct nvme_ns *ns;
	struct nvme_id_ctrl *ctrl;
	struct nvme_id_ns *id_ns;
	void *mem;
	dma_addr_t dma_addr;
	int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;

	mem = dma_alloc_coherent(&pdev->dev, 8192, &dma_addr, GFP_KERNEL);
	if (!mem)
		return -ENOMEM;

	res = nvme_identify(dev, 0, 1, dma_addr);
	if (res) {
		res = -EIO;
		goto out;
	}

	ctrl = mem;
	nn = le32_to_cpup(&ctrl->nn);
	dev->oncs = le16_to_cpup(&ctrl->oncs);
	dev->abort_limit = ctrl->acl + 1;
	memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
	memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
	memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
	if (ctrl->mdts)
		dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
	if ((pdev->vendor == PCI_VENDOR_ID_INTEL) &&
			(pdev->device == 0x0953) && ctrl->vs[3])
		dev->stripe_size = 1 << (ctrl->vs[3] + shift);

	id_ns = mem;
	for (i = 1; i <= nn; i++) {
		res = nvme_identify(dev, i, 0, dma_addr);
		if (res)
			continue;

		if (id_ns->ncap == 0)
			continue;

		res = nvme_get_features(dev, NVME_FEAT_LBA_RANGE, i,
							dma_addr + 4096, NULL);
		if (res)
			memset(mem + 4096, 0, 4096);

		ns = nvme_alloc_ns(dev, i, mem, mem + 4096);
		if (ns)
			list_add_tail(&ns->list, &dev->namespaces);
	}
	list_for_each_entry(ns, &dev->namespaces, list)
		add_disk(ns->disk);
	res = 0;

 out:
	dma_free_coherent(&dev->pci_dev->dev, 8192, mem, dma_addr);
	return res;
}

static int nvme_dev_map(struct nvme_dev *dev)
{
	int bars, result = -ENOMEM;
	struct pci_dev *pdev = dev->pci_dev;

	if (pci_enable_device_mem(pdev))
		return result;

	dev->entry[0].vector = pdev->irq;
	pci_set_master(pdev);
	bars = pci_select_bars(pdev, IORESOURCE_MEM);
	if (pci_request_selected_regions(pdev, bars, "nvme"))
		goto disable_pci;

	if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) &&
	    dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)))
		goto disable;

	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
	if (!dev->bar)
		goto disable;
	if (readl(&dev->bar->csts) == -1) {
		result = -ENODEV;
		goto unmap;
	}
	dev->db_stride = 1 << NVME_CAP_STRIDE(readq(&dev->bar->cap));
	dev->dbs = ((void __iomem *)dev->bar) + 4096;

	return 0;

 unmap:
	iounmap(dev->bar);
	dev->bar = NULL;
 disable:
	pci_release_regions(pdev);
 disable_pci:
	pci_disable_device(pdev);
	return result;
}

static void nvme_dev_unmap(struct nvme_dev *dev)
{
	if (dev->pci_dev->msi_enabled)
		pci_disable_msi(dev->pci_dev);
	else if (dev->pci_dev->msix_enabled)
		pci_disable_msix(dev->pci_dev);

	if (dev->bar) {
		iounmap(dev->bar);
		dev->bar = NULL;
		pci_release_regions(dev->pci_dev);
	}

	if (pci_is_enabled(dev->pci_dev))
		pci_disable_device(dev->pci_dev);
}

struct nvme_delq_ctx {
	struct task_struct *waiter;
	struct kthread_worker *worker;
	atomic_t refcount;
};

static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev)
{
	dq->waiter = current;
	mb();

	for (;;) {
		set_current_state(TASK_KILLABLE);
		if (!atomic_read(&dq->refcount))
			break;
		if (!schedule_timeout(ADMIN_TIMEOUT) ||
					fatal_signal_pending(current)) {
			set_current_state(TASK_RUNNING);

			nvme_disable_ctrl(dev, readq(&dev->bar->cap));
			nvme_disable_queue(dev, 0);

			send_sig(SIGKILL, dq->worker->task, 1);
			flush_kthread_worker(dq->worker);
			return;
		}
	}
	set_current_state(TASK_RUNNING);
}

static void nvme_put_dq(struct nvme_delq_ctx *dq)
{
	atomic_dec(&dq->refcount);
	if (dq->waiter)
		wake_up_process(dq->waiter);
}

static struct nvme_delq_ctx *nvme_get_dq(struct nvme_delq_ctx *dq)
{
	atomic_inc(&dq->refcount);
	return dq;
}

static void nvme_del_queue_end(struct nvme_queue *nvmeq)
{
	struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx;

	nvme_clear_queue(nvmeq);
	nvme_put_dq(dq);
}

static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode,
						kthread_work_func_t fn)
{
	struct nvme_command c;

	memset(&c, 0, sizeof(c));
	c.delete_queue.opcode = opcode;
	c.delete_queue.qid = cpu_to_le16(nvmeq->qid);

	init_kthread_work(&nvmeq->cmdinfo.work, fn);
	return nvme_submit_admin_cmd_async(nvmeq->dev, &c, &nvmeq->cmdinfo);
}

static void nvme_del_cq_work_handler(struct kthread_work *work)
{
	struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
							cmdinfo.work);
	nvme_del_queue_end(nvmeq);
}

static int nvme_delete_cq(struct nvme_queue *nvmeq)
{
	return adapter_async_del_queue(nvmeq, nvme_admin_delete_cq,
						nvme_del_cq_work_handler);
}

static void nvme_del_sq_work_handler(struct kthread_work *work)
{
	struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
							cmdinfo.work);
	int status = nvmeq->cmdinfo.status;

	if (!status)
		status = nvme_delete_cq(nvmeq);
	if (status)
		nvme_del_queue_end(nvmeq);
}

static int nvme_delete_sq(struct nvme_queue *nvmeq)
{
	return adapter_async_del_queue(nvmeq, nvme_admin_delete_sq,
						nvme_del_sq_work_handler);
}

static void nvme_del_queue_start(struct kthread_work *work)
{
	struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
							cmdinfo.work);
	allow_signal(SIGKILL);
	if (nvme_delete_sq(nvmeq))
		nvme_del_queue_end(nvmeq);
}

static void nvme_disable_io_queues(struct nvme_dev *dev)
{
	int i;
	DEFINE_KTHREAD_WORKER_ONSTACK(worker);
	struct nvme_delq_ctx dq;
	struct task_struct *kworker_task = kthread_run(kthread_worker_fn,
					&worker, "nvme%d", dev->instance);

	if (IS_ERR(kworker_task)) {
		dev_err(&dev->pci_dev->dev,
			"Failed to create queue del task\n");
		for (i = dev->queue_count - 1; i > 0; i--)
			nvme_disable_queue(dev, i);
		return;
	}

	dq.waiter = NULL;
	atomic_set(&dq.refcount, 0);
	dq.worker = &worker;
	for (i = dev->queue_count - 1; i > 0; i--) {
		struct nvme_queue *nvmeq = dev->queues[i];

		if (nvme_suspend_queue(nvmeq))
			continue;
		nvmeq->cmdinfo.ctx = nvme_get_dq(&dq);
		nvmeq->cmdinfo.worker = dq.worker;
		init_kthread_work(&nvmeq->cmdinfo.work, nvme_del_queue_start);
		queue_kthread_work(dq.worker, &nvmeq->cmdinfo.work);
	}
	nvme_wait_dq(&dq, dev);
	kthread_stop(kworker_task);
}

static void nvme_dev_shutdown(struct nvme_dev *dev)
{
	int i;

	dev->initialized = 0;

	spin_lock(&dev_list_lock);
	list_del_init(&dev->node);
	spin_unlock(&dev_list_lock);

	if (!dev->bar || (dev->bar && readl(&dev->bar->csts) == -1)) {
		for (i = dev->queue_count - 1; i >= 0; i--) {
			struct nvme_queue *nvmeq = dev->queues[i];
			nvme_suspend_queue(nvmeq);
			nvme_clear_queue(nvmeq);
		}
	} else {
		nvme_disable_io_queues(dev);
		nvme_shutdown_ctrl(dev);
		nvme_disable_queue(dev, 0);
	}
	nvme_dev_unmap(dev);
}

static void nvme_dev_remove(struct nvme_dev *dev)
{
	struct nvme_ns *ns;

	list_for_each_entry(ns, &dev->namespaces, list) {
		if (ns->disk->flags & GENHD_FL_UP)
			del_gendisk(ns->disk);
		if (!blk_queue_dying(ns->queue))
			blk_cleanup_queue(ns->queue);
	}
}

static int nvme_setup_prp_pools(struct nvme_dev *dev)
{
	struct device *dmadev = &dev->pci_dev->dev;
	dev->prp_page_pool = dma_pool_create("prp list page", dmadev,
						PAGE_SIZE, PAGE_SIZE, 0);
	if (!dev->prp_page_pool)
		return -ENOMEM;

	/* Optimisation for I/Os between 4k and 128k */
	dev->prp_small_pool = dma_pool_create("prp list 256", dmadev,
						256, 256, 0);
	if (!dev->prp_small_pool) {
		dma_pool_destroy(dev->prp_page_pool);
		return -ENOMEM;
	}
	return 0;
}

static void nvme_release_prp_pools(struct nvme_dev *dev)
{
	dma_pool_destroy(dev->prp_page_pool);
	dma_pool_destroy(dev->prp_small_pool);
}

static DEFINE_IDA(nvme_instance_ida);

static int nvme_set_instance(struct nvme_dev *dev)
{
	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;

	dev->instance = instance;
	return 0;
}

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

static void nvme_free_namespaces(struct nvme_dev *dev)
{
	struct nvme_ns *ns, *next;

	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
		list_del(&ns->list);
		put_disk(ns->disk);
		kfree(ns);
	}
}

static void nvme_free_dev(struct kref *kref)
{
	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);

	nvme_free_namespaces(dev);
	kfree(dev->queues);
	kfree(dev->entry);
	kfree(dev);
}

static int nvme_dev_open(struct inode *inode, struct file *f)
{
	struct nvme_dev *dev = container_of(f->private_data, struct nvme_dev,
								miscdev);
	kref_get(&dev->kref);
	f->private_data = dev;
	return 0;
}

static int nvme_dev_release(struct inode *inode, struct file *f)
{
	struct nvme_dev *dev = f->private_data;
	kref_put(&dev->kref, nvme_free_dev);
	return 0;
}

static long nvme_dev_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
{
	struct nvme_dev *dev = f->private_data;
	switch (cmd) {
	case NVME_IOCTL_ADMIN_CMD:
		return nvme_user_admin_cmd(dev, (void __user *)arg);
	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 int nvme_dev_start(struct nvme_dev *dev)
{
	int result;

	result = nvme_dev_map(dev);
	if (result)
		return result;

	result = nvme_configure_admin_queue(dev);
	if (result)
		goto unmap;

	spin_lock(&dev_list_lock);
	list_add(&dev->node, &dev_list);
	spin_unlock(&dev_list_lock);

	result = nvme_setup_io_queues(dev);
	if (result && result != -EBUSY)
		goto disable;

	return result;

 disable:
	nvme_disable_queue(dev, 0);
	spin_lock(&dev_list_lock);
	list_del_init(&dev->node);
	spin_unlock(&dev_list_lock);
 unmap:
	nvme_dev_unmap(dev);
	return result;
}

static int nvme_remove_dead_ctrl(void *arg)
{
	struct nvme_dev *dev = (struct nvme_dev *)arg;
	struct pci_dev *pdev = dev->pci_dev;

	if (pci_get_drvdata(pdev))
		pci_stop_and_remove_bus_device(pdev);
	kref_put(&dev->kref, nvme_free_dev);
	return 0;
}

static void nvme_remove_disks(struct work_struct *ws)
{
	int i;
	struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);

	nvme_dev_remove(dev);
	spin_lock(&dev_list_lock);
	for (i = dev->queue_count - 1; i > 0; i--) {
		BUG_ON(!dev->queues[i] || !dev->queues[i]->q_suspended);
		nvme_free_queue(dev->queues[i]);
		dev->queue_count--;
		dev->queues[i] = NULL;
	}
	spin_unlock(&dev_list_lock);
}

static int nvme_dev_resume(struct nvme_dev *dev)
{
	int ret;

	ret = nvme_dev_start(dev);
	if (ret && ret != -EBUSY)
		return ret;
	if (ret == -EBUSY) {
		spin_lock(&dev_list_lock);
		PREPARE_WORK(&dev->reset_work, nvme_remove_disks);
		queue_work(nvme_workq, &dev->reset_work);
		spin_unlock(&dev_list_lock);
	}
	dev->initialized = 1;
	return 0;
}

static void nvme_dev_reset(struct nvme_dev *dev)
{
	nvme_dev_shutdown(dev);
	if (nvme_dev_resume(dev)) {
		dev_err(&dev->pci_dev->dev, "Device failed to resume\n");
		kref_get(&dev->kref);
		if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
							dev->instance))) {
			dev_err(&dev->pci_dev->dev,
				"Failed to start controller remove task\n");
			kref_put(&dev->kref, nvme_free_dev);
		}
	}
}

static void nvme_reset_failed_dev(struct work_struct *ws)
{
	struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
	nvme_dev_reset(dev);
}

static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
	int result = -ENOMEM;
	struct nvme_dev *dev;

	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
	if (!dev)
		return -ENOMEM;
	dev->entry = kcalloc(num_possible_cpus(), sizeof(*dev->entry),
								GFP_KERNEL);
	if (!dev->entry)
		goto free;
	dev->queues = kcalloc(num_possible_cpus() + 1, sizeof(void *),
								GFP_KERNEL);
	if (!dev->queues)
		goto free;

	INIT_LIST_HEAD(&dev->namespaces);
	INIT_WORK(&dev->reset_work, nvme_reset_failed_dev);
	dev->pci_dev = pdev;
	pci_set_drvdata(pdev, dev);
	result = nvme_set_instance(dev);
	if (result)
		goto free;

	result = nvme_setup_prp_pools(dev);
	if (result)
		goto release;

	result = nvme_dev_start(dev);
	if (result) {
		if (result == -EBUSY)
			goto create_cdev;
		goto release_pools;
	}

	kref_init(&dev->kref);
	result = nvme_dev_add(dev);
	if (result)
		goto shutdown;

 create_cdev:
	scnprintf(dev->name, sizeof(dev->name), "nvme%d", dev->instance);
	dev->miscdev.minor = MISC_DYNAMIC_MINOR;
	dev->miscdev.parent = &pdev->dev;
	dev->miscdev.name = dev->name;
	dev->miscdev.fops = &nvme_dev_fops;
	result = misc_register(&dev->miscdev);
	if (result)
		goto remove;

	dev->initialized = 1;
	return 0;

 remove:
	nvme_dev_remove(dev);
	nvme_free_namespaces(dev);
 shutdown:
	nvme_dev_shutdown(dev);
 release_pools:
	nvme_free_queues(dev, 0);
	nvme_release_prp_pools(dev);
 release:
	nvme_release_instance(dev);
 free:
	kfree(dev->queues);
	kfree(dev->entry);
	kfree(dev);
	return result;
}

static void nvme_shutdown(struct pci_dev *pdev)
{
	struct nvme_dev *dev = pci_get_drvdata(pdev);
	nvme_dev_shutdown(dev);
}

static void nvme_remove(struct pci_dev *pdev)
{
	struct nvme_dev *dev = pci_get_drvdata(pdev);

	spin_lock(&dev_list_lock);
	list_del_init(&dev->node);
	spin_unlock(&dev_list_lock);

	pci_set_drvdata(pdev, NULL);
	flush_work(&dev->reset_work);
	misc_deregister(&dev->miscdev);
	nvme_dev_remove(dev);
	nvme_dev_shutdown(dev);
	nvme_free_queues(dev, 0);
	nvme_release_instance(dev);
	nvme_release_prp_pools(dev);
	kref_put(&dev->kref, nvme_free_dev);
}

/* These functions are yet to be implemented */
#define nvme_error_detected NULL
#define nvme_dump_registers NULL
#define nvme_link_reset NULL
#define nvme_slot_reset NULL
#define nvme_error_resume NULL

static int nvme_suspend(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct nvme_dev *ndev = pci_get_drvdata(pdev);

	nvme_dev_shutdown(ndev);
	return 0;
}

static int nvme_resume(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct nvme_dev *ndev = pci_get_drvdata(pdev);

	if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) {
		PREPARE_WORK(&ndev->reset_work, nvme_reset_failed_dev);
		queue_work(nvme_workq, &ndev->reset_work);
	}
	return 0;
}

static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);

static const struct pci_error_handlers nvme_err_handler = {
	.error_detected	= nvme_error_detected,
	.mmio_enabled	= nvme_dump_registers,
	.link_reset	= nvme_link_reset,
	.slot_reset	= nvme_slot_reset,
	.resume		= nvme_error_resume,
};

/* Move to pci_ids.h later */
#define PCI_CLASS_STORAGE_EXPRESS	0x010802

static DEFINE_PCI_DEVICE_TABLE(nvme_id_table) = {
	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
	{ 0, }
};
MODULE_DEVICE_TABLE(pci, nvme_id_table);

static struct pci_driver nvme_driver = {
	.name		= "nvme",
	.id_table	= nvme_id_table,
	.probe		= nvme_probe,
	.remove		= nvme_remove,
	.shutdown	= nvme_shutdown,
	.driver		= {
		.pm	= &nvme_dev_pm_ops,
	},
	.err_handler	= &nvme_err_handler,
};

static int __init nvme_init(void)
{
	int result;

	nvme_thread = kthread_run(nvme_kthread, NULL, "nvme");
	if (IS_ERR(nvme_thread))
		return PTR_ERR(nvme_thread);

	result = -ENOMEM;
	nvme_workq = create_singlethread_workqueue("nvme");
	if (!nvme_workq)
		goto kill_kthread;

	result = register_blkdev(nvme_major, "nvme");
	if (result < 0)
		goto kill_workq;
	else if (result > 0)
		nvme_major = result;

	result = pci_register_driver(&nvme_driver);
	if (result)
		goto unregister_blkdev;
	return 0;

 unregister_blkdev:
	unregister_blkdev(nvme_major, "nvme");
 kill_workq:
	destroy_workqueue(nvme_workq);
 kill_kthread:
	kthread_stop(nvme_thread);
	return result;
}

static void __exit nvme_exit(void)
{
	pci_unregister_driver(&nvme_driver);
	unregister_blkdev(nvme_major, "nvme");
	destroy_workqueue(nvme_workq);
	kthread_stop(nvme_thread);
}

MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
MODULE_LICENSE("GPL");
MODULE_VERSION("0.8");
module_init(nvme_init);
module_exit(nvme_exit);
OpenPOWER on IntegriCloud