aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/nvme/host/pci.c
blob: 8991e79b2b87ab0459f9f5ee9c33478f4f6bf00f (plain) (blame)
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
/*
 * 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/aer.h>
#include <linux/async.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/blk-mq-pci.h>
#include <linux/dmi.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/once.h>
#include <linux/pci.h>
#include <linux/t10-pi.h>
#include <linux/types.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/sed-opal.h>

#include "nvme.h"

#define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
#define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))

#define SGES_PER_PAGE	(PAGE_SIZE / sizeof(struct nvme_sgl_desc))

/*
 * These can be higher, but we need to ensure that any command doesn't
 * require an sg allocation that needs more than a page of data.
 */
#define NVME_MAX_KB_SZ	4096
#define NVME_MAX_SEGS	127

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

static bool use_cmb_sqes = true;
module_param(use_cmb_sqes, bool, 0444);
MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O SQes");

static unsigned int max_host_mem_size_mb = 128;
module_param(max_host_mem_size_mb, uint, 0444);
MODULE_PARM_DESC(max_host_mem_size_mb,
	"Maximum Host Memory Buffer (HMB) size per controller (in MiB)");

static unsigned int sgl_threshold = SZ_32K;
module_param(sgl_threshold, uint, 0644);
MODULE_PARM_DESC(sgl_threshold,
		"Use SGLs when average request segment size is larger or equal to "
		"this size. Use 0 to disable SGLs.");

static int io_queue_depth_set(const char *val, const struct kernel_param *kp);
static const struct kernel_param_ops io_queue_depth_ops = {
	.set = io_queue_depth_set,
	.get = param_get_int,
};

static int io_queue_depth = 1024;
module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");

struct nvme_dev;
struct nvme_queue;

static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);

/*
 * Represents an NVM Express device.  Each nvme_dev is a PCI function.
 */
struct nvme_dev {
	struct nvme_queue *queues;
	struct blk_mq_tag_set tagset;
	struct blk_mq_tag_set admin_tagset;
	u32 __iomem *dbs;
	struct device *dev;
	struct dma_pool *prp_page_pool;
	struct dma_pool *prp_small_pool;
	unsigned online_queues;
	unsigned max_qid;
	unsigned int num_vecs;
	int q_depth;
	u32 db_stride;
	void __iomem *bar;
	unsigned long bar_mapped_size;
	struct work_struct remove_work;
	struct mutex shutdown_lock;
	bool subsystem;
	void __iomem *cmb;
	pci_bus_addr_t cmb_bus_addr;
	u64 cmb_size;
	u32 cmbsz;
	u32 cmbloc;
	struct nvme_ctrl ctrl;
	struct completion ioq_wait;

	mempool_t *iod_mempool;

	/* shadow doorbell buffer support: */
	u32 *dbbuf_dbs;
	dma_addr_t dbbuf_dbs_dma_addr;
	u32 *dbbuf_eis;
	dma_addr_t dbbuf_eis_dma_addr;

	/* host memory buffer support: */
	u64 host_mem_size;
	u32 nr_host_mem_descs;
	dma_addr_t host_mem_descs_dma;
	struct nvme_host_mem_buf_desc *host_mem_descs;
	void **host_mem_desc_bufs;
};

static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
{
	int n = 0, ret;

	ret = kstrtoint(val, 10, &n);
	if (ret != 0 || n < 2)
		return -EINVAL;

	return param_set_int(val, kp);
}

static inline unsigned int sq_idx(unsigned int qid, u32 stride)
{
	return qid * 2 * stride;
}

static inline unsigned int cq_idx(unsigned int qid, u32 stride)
{
	return (qid * 2 + 1) * stride;
}

static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
{
	return container_of(ctrl, struct nvme_dev, ctrl);
}

/*
 * 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;
	spinlock_t sq_lock;
	struct nvme_command *sq_cmds;
	struct nvme_command __iomem *sq_cmds_io;
	spinlock_t cq_lock ____cacheline_aligned_in_smp;
	volatile struct nvme_completion *cqes;
	struct blk_mq_tags **tags;
	dma_addr_t sq_dma_addr;
	dma_addr_t cq_dma_addr;
	u32 __iomem *q_db;
	u16 q_depth;
	s16 cq_vector;
	u16 sq_tail;
	u16 cq_head;
	u16 last_cq_head;
	u16 qid;
	u8 cq_phase;
	u32 *dbbuf_sq_db;
	u32 *dbbuf_cq_db;
	u32 *dbbuf_sq_ei;
	u32 *dbbuf_cq_ei;
};

/*
 * The nvme_iod describes the data in an I/O, including the list of PRP
 * entries.  You can't see it in this data structure because C doesn't let
 * me express that.  Use nvme_init_iod to ensure there's enough space
 * allocated to store the PRP list.
 */
struct nvme_iod {
	struct nvme_request req;
	struct nvme_queue *nvmeq;
	bool use_sgl;
	int aborted;
	int npages;		/* In the PRP list. 0 means small pool in use */
	int nents;		/* Used in scatterlist */
	int length;		/* Of data, in bytes */
	dma_addr_t first_dma;
	struct scatterlist meta_sg; /* metadata requires single contiguous buffer */
	struct scatterlist *sg;
	struct scatterlist inline_sg[0];
};

/*
 * 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) != NVME_IDENTIFY_DATA_SIZE);
	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
}

static inline unsigned int nvme_dbbuf_size(u32 stride)
{
	return ((num_possible_cpus() + 1) * 8 * stride);
}

static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
{
	unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);

	if (dev->dbbuf_dbs)
		return 0;

	dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size,
					    &dev->dbbuf_dbs_dma_addr,
					    GFP_KERNEL);
	if (!dev->dbbuf_dbs)
		return -ENOMEM;
	dev->dbbuf_eis = dma_alloc_coherent(dev->dev, mem_size,
					    &dev->dbbuf_eis_dma_addr,
					    GFP_KERNEL);
	if (!dev->dbbuf_eis) {
		dma_free_coherent(dev->dev, mem_size,
				  dev->dbbuf_dbs, dev->dbbuf_dbs_dma_addr);
		dev->dbbuf_dbs = NULL;
		return -ENOMEM;
	}

	return 0;
}

static void nvme_dbbuf_dma_free(struct nvme_dev *dev)
{
	unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);

	if (dev->dbbuf_dbs) {
		dma_free_coherent(dev->dev, mem_size,
				  dev->dbbuf_dbs, dev->dbbuf_dbs_dma_addr);
		dev->dbbuf_dbs = NULL;
	}
	if (dev->dbbuf_eis) {
		dma_free_coherent(dev->dev, mem_size,
				  dev->dbbuf_eis, dev->dbbuf_eis_dma_addr);
		dev->dbbuf_eis = NULL;
	}
}

static void nvme_dbbuf_init(struct nvme_dev *dev,
			    struct nvme_queue *nvmeq, int qid)
{
	if (!dev->dbbuf_dbs || !qid)
		return;

	nvmeq->dbbuf_sq_db = &dev->dbbuf_dbs[sq_idx(qid, dev->db_stride)];
	nvmeq->dbbuf_cq_db = &dev->dbbuf_dbs[cq_idx(qid, dev->db_stride)];
	nvmeq->dbbuf_sq_ei = &dev->dbbuf_eis[sq_idx(qid, dev->db_stride)];
	nvmeq->dbbuf_cq_ei = &dev->dbbuf_eis[cq_idx(qid, dev->db_stride)];
}

static void nvme_dbbuf_set(struct nvme_dev *dev)
{
	struct nvme_command c;

	if (!dev->dbbuf_dbs)
		return;

	memset(&c, 0, sizeof(c));
	c.dbbuf.opcode = nvme_admin_dbbuf;
	c.dbbuf.prp1 = cpu_to_le64(dev->dbbuf_dbs_dma_addr);
	c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);

	if (nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0)) {
		dev_warn(dev->ctrl.device, "unable to set dbbuf\n");
		/* Free memory and continue on */
		nvme_dbbuf_dma_free(dev);
	}
}

static inline int nvme_dbbuf_need_event(u16 event_idx, u16 new_idx, u16 old)
{
	return (u16)(new_idx - event_idx - 1) < (u16)(new_idx - old);
}

/* Update dbbuf and return true if an MMIO is required */
static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
					      volatile u32 *dbbuf_ei)
{
	if (dbbuf_db) {
		u16 old_value;

		/*
		 * Ensure that the queue is written before updating
		 * the doorbell in memory
		 */
		wmb();

		old_value = *dbbuf_db;
		*dbbuf_db = value;

		/*
		 * Ensure that the doorbell is updated before reading the event
		 * index from memory.  The controller needs to provide similar
		 * ordering to ensure the envent index is updated before reading
		 * the doorbell.
		 */
		mb();

		if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value))
			return false;
	}

	return true;
}

/*
 * Max size of iod being embedded in the request payload
 */
#define NVME_INT_PAGES		2
#define NVME_INT_BYTES(dev)	(NVME_INT_PAGES * (dev)->ctrl.page_size)

/*
 * 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, struct nvme_dev *dev)
{
	unsigned nprps = DIV_ROUND_UP(size + dev->ctrl.page_size,
				      dev->ctrl.page_size);
	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
}

/*
 * Calculates the number of pages needed for the SGL segments. For example a 4k
 * page can accommodate 256 SGL descriptors.
 */
static int nvme_pci_npages_sgl(unsigned int num_seg)
{
	return DIV_ROUND_UP(num_seg * sizeof(struct nvme_sgl_desc), PAGE_SIZE);
}

static unsigned int nvme_pci_iod_alloc_size(struct nvme_dev *dev,
		unsigned int size, unsigned int nseg, bool use_sgl)
{
	size_t alloc_size;

	if (use_sgl)
		alloc_size = sizeof(__le64 *) * nvme_pci_npages_sgl(nseg);
	else
		alloc_size = sizeof(__le64 *) * nvme_npages(size, dev);

	return alloc_size + sizeof(struct scatterlist) * nseg;
}

static unsigned int nvme_pci_cmd_size(struct nvme_dev *dev, bool use_sgl)
{
	unsigned int alloc_size = nvme_pci_iod_alloc_size(dev,
				    NVME_INT_BYTES(dev), NVME_INT_PAGES,
				    use_sgl);

	return sizeof(struct nvme_iod) + alloc_size;
}

static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
				unsigned int hctx_idx)
{
	struct nvme_dev *dev = data;
	struct nvme_queue *nvmeq = &dev->queues[0];

	WARN_ON(hctx_idx != 0);
	WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
	WARN_ON(nvmeq->tags);

	hctx->driver_data = nvmeq;
	nvmeq->tags = &dev->admin_tagset.tags[0];
	return 0;
}

static void nvme_admin_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
{
	struct nvme_queue *nvmeq = hctx->driver_data;

	nvmeq->tags = NULL;
}

static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
			  unsigned int hctx_idx)
{
	struct nvme_dev *dev = data;
	struct nvme_queue *nvmeq = &dev->queues[hctx_idx + 1];

	if (!nvmeq->tags)
		nvmeq->tags = &dev->tagset.tags[hctx_idx];

	WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
	hctx->driver_data = nvmeq;
	return 0;
}

static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req,
		unsigned int hctx_idx, unsigned int numa_node)
{
	struct nvme_dev *dev = set->driver_data;
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	int queue_idx = (set == &dev->tagset) ? hctx_idx + 1 : 0;
	struct nvme_queue *nvmeq = &dev->queues[queue_idx];

	BUG_ON(!nvmeq);
	iod->nvmeq = nvmeq;

	nvme_req(req)->ctrl = &dev->ctrl;
	return 0;
}

static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
{
	struct nvme_dev *dev = set->driver_data;

	return blk_mq_pci_map_queues(set, to_pci_dev(dev->dev),
			dev->num_vecs > 1 ? 1 /* admin queue */ : 0);
}

/**
 * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
 * @nvmeq: The queue to use
 * @cmd: The command to send
 */
static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
{
	spin_lock(&nvmeq->sq_lock);
	if (nvmeq->sq_cmds_io)
		memcpy_toio(&nvmeq->sq_cmds_io[nvmeq->sq_tail], cmd,
				sizeof(*cmd));
	else
		memcpy(&nvmeq->sq_cmds[nvmeq->sq_tail], cmd, sizeof(*cmd));

	if (++nvmeq->sq_tail == nvmeq->q_depth)
		nvmeq->sq_tail = 0;
	if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
			nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
		writel(nvmeq->sq_tail, nvmeq->q_db);
	spin_unlock(&nvmeq->sq_lock);
}

static void **nvme_pci_iod_list(struct request *req)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	return (void **)(iod->sg + blk_rq_nr_phys_segments(req));
}

static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	int nseg = blk_rq_nr_phys_segments(req);
	unsigned int avg_seg_size;

	if (nseg == 0)
		return false;

	avg_seg_size = DIV_ROUND_UP(blk_rq_payload_bytes(req), nseg);

	if (!(dev->ctrl.sgls & ((1 << 0) | (1 << 1))))
		return false;
	if (!iod->nvmeq->qid)
		return false;
	if (!sgl_threshold || avg_seg_size < sgl_threshold)
		return false;
	return true;
}

static blk_status_t nvme_init_iod(struct request *rq, struct nvme_dev *dev)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(rq);
	int nseg = blk_rq_nr_phys_segments(rq);
	unsigned int size = blk_rq_payload_bytes(rq);

	iod->use_sgl = nvme_pci_use_sgls(dev, rq);

	if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
		iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
		if (!iod->sg)
			return BLK_STS_RESOURCE;
	} else {
		iod->sg = iod->inline_sg;
	}

	iod->aborted = 0;
	iod->npages = -1;
	iod->nents = 0;
	iod->length = size;

	return BLK_STS_OK;
}

static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	const int last_prp = dev->ctrl.page_size / sizeof(__le64) - 1;
	dma_addr_t dma_addr = iod->first_dma, next_dma_addr;

	int i;

	if (iod->npages == 0)
		dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0],
			dma_addr);

	for (i = 0; i < iod->npages; i++) {
		void *addr = nvme_pci_iod_list(req)[i];

		if (iod->use_sgl) {
			struct nvme_sgl_desc *sg_list = addr;

			next_dma_addr =
			    le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr);
		} else {
			__le64 *prp_list = addr;

			next_dma_addr = le64_to_cpu(prp_list[last_prp]);
		}

		dma_pool_free(dev->prp_page_pool, addr, dma_addr);
		dma_addr = next_dma_addr;
	}

	if (iod->sg != iod->inline_sg)
		mempool_free(iod->sg, dev->iod_mempool);
}

static void nvme_print_sgl(struct scatterlist *sgl, int nents)
{
	int i;
	struct scatterlist *sg;

	for_each_sg(sgl, sg, nents, i) {
		dma_addr_t phys = sg_phys(sg);
		pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
			"dma_address:%pad dma_length:%d\n",
			i, &phys, sg->offset, sg->length, &sg_dma_address(sg),
			sg_dma_len(sg));
	}
}

static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
		struct request *req, struct nvme_rw_command *cmnd)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	struct dma_pool *pool;
	int length = blk_rq_payload_bytes(req);
	struct scatterlist *sg = iod->sg;
	int dma_len = sg_dma_len(sg);
	u64 dma_addr = sg_dma_address(sg);
	u32 page_size = dev->ctrl.page_size;
	int offset = dma_addr & (page_size - 1);
	__le64 *prp_list;
	void **list = nvme_pci_iod_list(req);
	dma_addr_t prp_dma;
	int nprps, i;

	length -= (page_size - offset);
	if (length <= 0) {
		iod->first_dma = 0;
		goto done;
	}

	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) {
		iod->first_dma = dma_addr;
		goto done;
	}

	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_ATOMIC, &prp_dma);
	if (!prp_list) {
		iod->first_dma = dma_addr;
		iod->npages = -1;
		return BLK_STS_RESOURCE;
	}
	list[0] = prp_list;
	iod->first_dma = prp_dma;
	i = 0;
	for (;;) {
		if (i == page_size >> 3) {
			__le64 *old_prp_list = prp_list;
			prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma);
			if (!prp_list)
				return BLK_STS_RESOURCE;
			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;
		if (unlikely(dma_len < 0))
			goto bad_sgl;
		sg = sg_next(sg);
		dma_addr = sg_dma_address(sg);
		dma_len = sg_dma_len(sg);
	}

done:
	cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
	cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma);

	return BLK_STS_OK;

 bad_sgl:
	WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
			"Invalid SGL for payload:%d nents:%d\n",
			blk_rq_payload_bytes(req), iod->nents);
	return BLK_STS_IOERR;
}

static void nvme_pci_sgl_set_data(struct nvme_sgl_desc *sge,
		struct scatterlist *sg)
{
	sge->addr = cpu_to_le64(sg_dma_address(sg));
	sge->length = cpu_to_le32(sg_dma_len(sg));
	sge->type = NVME_SGL_FMT_DATA_DESC << 4;
}

static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge,
		dma_addr_t dma_addr, int entries)
{
	sge->addr = cpu_to_le64(dma_addr);
	if (entries < SGES_PER_PAGE) {
		sge->length = cpu_to_le32(entries * sizeof(*sge));
		sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4;
	} else {
		sge->length = cpu_to_le32(PAGE_SIZE);
		sge->type = NVME_SGL_FMT_SEG_DESC << 4;
	}
}

static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
		struct request *req, struct nvme_rw_command *cmd, int entries)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	struct dma_pool *pool;
	struct nvme_sgl_desc *sg_list;
	struct scatterlist *sg = iod->sg;
	dma_addr_t sgl_dma;
	int i = 0;

	/* setting the transfer type as SGL */
	cmd->flags = NVME_CMD_SGL_METABUF;

	if (entries == 1) {
		nvme_pci_sgl_set_data(&cmd->dptr.sgl, sg);
		return BLK_STS_OK;
	}

	if (entries <= (256 / sizeof(struct nvme_sgl_desc))) {
		pool = dev->prp_small_pool;
		iod->npages = 0;
	} else {
		pool = dev->prp_page_pool;
		iod->npages = 1;
	}

	sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma);
	if (!sg_list) {
		iod->npages = -1;
		return BLK_STS_RESOURCE;
	}

	nvme_pci_iod_list(req)[0] = sg_list;
	iod->first_dma = sgl_dma;

	nvme_pci_sgl_set_seg(&cmd->dptr.sgl, sgl_dma, entries);

	do {
		if (i == SGES_PER_PAGE) {
			struct nvme_sgl_desc *old_sg_desc = sg_list;
			struct nvme_sgl_desc *link = &old_sg_desc[i - 1];

			sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma);
			if (!sg_list)
				return BLK_STS_RESOURCE;

			i = 0;
			nvme_pci_iod_list(req)[iod->npages++] = sg_list;
			sg_list[i++] = *link;
			nvme_pci_sgl_set_seg(link, sgl_dma, entries);
		}

		nvme_pci_sgl_set_data(&sg_list[i++], sg);
		sg = sg_next(sg);
	} while (--entries > 0);

	return BLK_STS_OK;
}

static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
		struct nvme_command *cmnd)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	struct request_queue *q = req->q;
	enum dma_data_direction dma_dir = rq_data_dir(req) ?
			DMA_TO_DEVICE : DMA_FROM_DEVICE;
	blk_status_t ret = BLK_STS_IOERR;
	int nr_mapped;

	sg_init_table(iod->sg, blk_rq_nr_phys_segments(req));
	iod->nents = blk_rq_map_sg(q, req, iod->sg);
	if (!iod->nents)
		goto out;

	ret = BLK_STS_RESOURCE;
	nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, dma_dir,
			DMA_ATTR_NO_WARN);
	if (!nr_mapped)
		goto out;

	if (iod->use_sgl)
		ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw, nr_mapped);
	else
		ret = nvme_pci_setup_prps(dev, req, &cmnd->rw);

	if (ret != BLK_STS_OK)
		goto out_unmap;

	ret = BLK_STS_IOERR;
	if (blk_integrity_rq(req)) {
		if (blk_rq_count_integrity_sg(q, req->bio) != 1)
			goto out_unmap;

		sg_init_table(&iod->meta_sg, 1);
		if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1)
			goto out_unmap;

		if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir))
			goto out_unmap;
	}

	if (blk_integrity_rq(req))
		cmnd->rw.metadata = cpu_to_le64(sg_dma_address(&iod->meta_sg));
	return BLK_STS_OK;

out_unmap:
	dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
out:
	return ret;
}

static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	enum dma_data_direction dma_dir = rq_data_dir(req) ?
			DMA_TO_DEVICE : DMA_FROM_DEVICE;

	if (iod->nents) {
		dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
		if (blk_integrity_rq(req))
			dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir);
	}

	nvme_cleanup_cmd(req);
	nvme_free_iod(dev, req);
}

/*
 * NOTE: ns is NULL when called on the admin queue.
 */
static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
			 const struct blk_mq_queue_data *bd)
{
	struct nvme_ns *ns = hctx->queue->queuedata;
	struct nvme_queue *nvmeq = hctx->driver_data;
	struct nvme_dev *dev = nvmeq->dev;
	struct request *req = bd->rq;
	struct nvme_command cmnd;
	blk_status_t ret;

	/*
	 * We should not need to do this, but we're still using this to
	 * ensure we can drain requests on a dying queue.
	 */
	if (unlikely(nvmeq->cq_vector < 0))
		return BLK_STS_IOERR;

	ret = nvme_setup_cmd(ns, req, &cmnd);
	if (ret)
		return ret;

	ret = nvme_init_iod(req, dev);
	if (ret)
		goto out_free_cmd;

	if (blk_rq_nr_phys_segments(req)) {
		ret = nvme_map_data(dev, req, &cmnd);
		if (ret)
			goto out_cleanup_iod;
	}

	blk_mq_start_request(req);
	nvme_submit_cmd(nvmeq, &cmnd);
	return BLK_STS_OK;
out_cleanup_iod:
	nvme_free_iod(dev, req);
out_free_cmd:
	nvme_cleanup_cmd(req);
	return ret;
}

static void nvme_pci_complete_rq(struct request *req)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);

	nvme_unmap_data(iod->nvmeq->dev, req);
	nvme_complete_rq(req);
}

/* We read the CQE phase first to check if the rest of the entry is valid */
static inline bool nvme_cqe_pending(struct nvme_queue *nvmeq)
{
	return (le16_to_cpu(nvmeq->cqes[nvmeq->cq_head].status) & 1) ==
			nvmeq->cq_phase;
}

static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
{
	u16 head = nvmeq->cq_head;

	if (nvme_dbbuf_update_and_check_event(head, nvmeq->dbbuf_cq_db,
					      nvmeq->dbbuf_cq_ei))
		writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
}

static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
{
	volatile struct nvme_completion *cqe = &nvmeq->cqes[idx];
	struct request *req;

	if (unlikely(cqe->command_id >= nvmeq->q_depth)) {
		dev_warn(nvmeq->dev->ctrl.device,
			"invalid id %d completed on queue %d\n",
			cqe->command_id, le16_to_cpu(cqe->sq_id));
		return;
	}

	/*
	 * AEN requests are special as they don't time out and can
	 * survive any kind of queue freeze and often don't respond to
	 * aborts.  We don't even bother to allocate a struct request
	 * for them but rather special case them here.
	 */
	if (unlikely(nvmeq->qid == 0 &&
			cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) {
		nvme_complete_async_event(&nvmeq->dev->ctrl,
				cqe->status, &cqe->result);
		return;
	}

	req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id);
	nvme_end_request(req, cqe->status, cqe->result);
}

static void nvme_complete_cqes(struct nvme_queue *nvmeq, u16 start, u16 end)
{
	while (start != end) {
		nvme_handle_cqe(nvmeq, start);
		if (++start == nvmeq->q_depth)
			start = 0;
	}
}

static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
{
	if (++nvmeq->cq_head == nvmeq->q_depth) {
		nvmeq->cq_head = 0;
		nvmeq->cq_phase = !nvmeq->cq_phase;
	}
}

static inline bool nvme_process_cq(struct nvme_queue *nvmeq, u16 *start,
		u16 *end, int tag)
{
	bool found = false;

	*start = nvmeq->cq_head;
	while (!found && nvme_cqe_pending(nvmeq)) {
		if (nvmeq->cqes[nvmeq->cq_head].command_id == tag)
			found = true;
		nvme_update_cq_head(nvmeq);
	}
	*end = nvmeq->cq_head;

	if (*start != *end)
		nvme_ring_cq_doorbell(nvmeq);
	return found;
}

static irqreturn_t nvme_irq(int irq, void *data)
{
	struct nvme_queue *nvmeq = data;
	irqreturn_t ret = IRQ_NONE;
	u16 start, end;

	spin_lock(&nvmeq->cq_lock);
	if (nvmeq->cq_head != nvmeq->last_cq_head)
		ret = IRQ_HANDLED;
	nvme_process_cq(nvmeq, &start, &end, -1);
	nvmeq->last_cq_head = nvmeq->cq_head;
	spin_unlock(&nvmeq->cq_lock);

	if (start != end) {
		nvme_complete_cqes(nvmeq, start, end);
		return IRQ_HANDLED;
	}

	return ret;
}

static irqreturn_t nvme_irq_check(int irq, void *data)
{
	struct nvme_queue *nvmeq = data;
	if (nvme_cqe_pending(nvmeq))
		return IRQ_WAKE_THREAD;
	return IRQ_NONE;
}

static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag)
{
	u16 start, end;
	bool found;

	if (!nvme_cqe_pending(nvmeq))
		return 0;

	spin_lock_irq(&nvmeq->cq_lock);
	found = nvme_process_cq(nvmeq, &start, &end, tag);
	spin_unlock_irq(&nvmeq->cq_lock);

	nvme_complete_cqes(nvmeq, start, end);
	return found;
}

static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
{
	struct nvme_queue *nvmeq = hctx->driver_data;

	return __nvme_poll(nvmeq, tag);
}

static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
{
	struct nvme_dev *dev = to_nvme_dev(ctrl);
	struct nvme_queue *nvmeq = &dev->queues[0];
	struct nvme_command c;

	memset(&c, 0, sizeof(c));
	c.common.opcode = nvme_admin_async_event;
	c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
	nvme_submit_cmd(nvmeq, &c);
}

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

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

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

static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
		struct nvme_queue *nvmeq, s16 vector)
{
	struct nvme_command c;
	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;

	/*
	 * Note: we (ab)use the fact that the prp fields survive if no data
	 * is attached to the request.
	 */
	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(vector);

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

static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
						struct nvme_queue *nvmeq)
{
	struct nvme_ctrl *ctrl = &dev->ctrl;
	struct nvme_command c;
	int flags = NVME_QUEUE_PHYS_CONTIG;

	/*
	 * Some drives have a bug that auto-enables WRRU if MEDIUM isn't
	 * set. Since URGENT priority is zeroes, it makes all queues
	 * URGENT.
	 */
	if (ctrl->quirks & NVME_QUIRK_MEDIUM_PRIO_SQ)
		flags |= NVME_SQ_PRIO_MEDIUM;

	/*
	 * Note: we (ab)use the fact that the prp fields survive if no data
	 * is attached to the request.
	 */
	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);

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

static void abort_endio(struct request *req, blk_status_t error)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	struct nvme_queue *nvmeq = iod->nvmeq;

	dev_warn(nvmeq->dev->ctrl.device,
		 "Abort status: 0x%x", nvme_req(req)->status);
	atomic_inc(&nvmeq->dev->ctrl.abort_limit);
	blk_mq_free_request(req);
}

static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
{

	/* If true, indicates loss of adapter communication, possibly by a
	 * NVMe Subsystem reset.
	 */
	bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO);

	/* If there is a reset/reinit ongoing, we shouldn't reset again. */
	switch (dev->ctrl.state) {
	case NVME_CTRL_RESETTING:
	case NVME_CTRL_CONNECTING:
		return false;
	default:
		break;
	}

	/* We shouldn't reset unless the controller is on fatal error state
	 * _or_ if we lost the communication with it.
	 */
	if (!(csts & NVME_CSTS_CFS) && !nssro)
		return false;

	return true;
}

static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
{
	/* Read a config register to help see what died. */
	u16 pci_status;
	int result;

	result = pci_read_config_word(to_pci_dev(dev->dev), PCI_STATUS,
				      &pci_status);
	if (result == PCIBIOS_SUCCESSFUL)
		dev_warn(dev->ctrl.device,
			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS=0x%hx\n",
			 csts, pci_status);
	else
		dev_warn(dev->ctrl.device,
			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n",
			 csts, result);
}

static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
{
	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
	struct nvme_queue *nvmeq = iod->nvmeq;
	struct nvme_dev *dev = nvmeq->dev;
	struct request *abort_req;
	struct nvme_command cmd;
	u32 csts = readl(dev->bar + NVME_REG_CSTS);

	/* If PCI error recovery process is happening, we cannot reset or
	 * the recovery mechanism will surely fail.
	 */
	mb();
	if (pci_channel_offline(to_pci_dev(dev->dev)))
		return BLK_EH_RESET_TIMER;

	/*
	 * Reset immediately if the controller is failed
	 */
	if (nvme_should_reset(dev, csts)) {
		nvme_warn_reset(dev, csts);
		nvme_dev_disable(dev, false);
		nvme_reset_ctrl(&dev->ctrl);
		return BLK_EH_DONE;
	}

	/*
	 * Did we miss an interrupt?
	 */
	if (__nvme_poll(nvmeq, req->tag)) {
		dev_warn(dev->ctrl.device,
			 "I/O %d QID %d timeout, completion polled\n",
			 req->tag, nvmeq->qid);
		return BLK_EH_DONE;
	}

	/*
	 * Shutdown immediately if controller times out while starting. The
	 * reset work will see the pci device disabled when it gets the forced
	 * cancellation error. All outstanding requests are completed on
	 * shutdown, so we return BLK_EH_DONE.
	 */
	switch (dev->ctrl.state) {
	case NVME_CTRL_CONNECTING:
	case NVME_CTRL_RESETTING:
		dev_warn_ratelimited(dev->ctrl.device,
			 "I/O %d QID %d timeout, disable controller\n",
			 req->tag, nvmeq->qid);
		nvme_dev_disable(dev, false);
		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
		return BLK_EH_DONE;
	default:
		break;
	}

	/*
 	 * Shutdown the controller immediately and schedule a 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.
	 */
	if (!nvmeq->qid || iod->aborted) {
		dev_warn(dev->ctrl.device,
			 "I/O %d QID %d timeout, reset controller\n",
			 req->tag, nvmeq->qid);
		nvme_dev_disable(dev, false);
		nvme_reset_ctrl(&dev->ctrl);

		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
		return BLK_EH_DONE;
	}

	if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
		atomic_inc(&dev->ctrl.abort_limit);
		return BLK_EH_RESET_TIMER;
	}
	iod->aborted = 1;

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

	dev_warn(nvmeq->dev->ctrl.device,
		"I/O %d QID %d timeout, aborting\n",
		 req->tag, nvmeq->qid);

	abort_req = nvme_alloc_request(dev->ctrl.admin_q, &cmd,
			BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
	if (IS_ERR(abort_req)) {
		atomic_inc(&dev->ctrl.abort_limit);
		return BLK_EH_RESET_TIMER;
	}

	abort_req->timeout = ADMIN_TIMEOUT;
	abort_req->end_io_data = NULL;
	blk_execute_rq_nowait(abort_req->q, NULL, abort_req, 0, abort_endio);

	/*
	 * The aborted req will be completed on receiving the abort req.
	 * We enable the timer again. If hit twice, it'll cause a device reset,
	 * as the device then is in a faulty state.
	 */
	return BLK_EH_RESET_TIMER;
}

static void nvme_free_queue(struct nvme_queue *nvmeq)
{
	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
	if (nvmeq->sq_cmds)
		dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
}

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

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

/**
 * nvme_suspend_queue - put queue into suspended state
 * @nvmeq - queue to suspend
 */
static int nvme_suspend_queue(struct nvme_queue *nvmeq)
{
	int vector;

	spin_lock_irq(&nvmeq->cq_lock);
	if (nvmeq->cq_vector == -1) {
		spin_unlock_irq(&nvmeq->cq_lock);
		return 1;
	}
	vector = nvmeq->cq_vector;
	nvmeq->dev->online_queues--;
	nvmeq->cq_vector = -1;
	spin_unlock_irq(&nvmeq->cq_lock);

	/*
	 * Ensure that nvme_queue_rq() sees it ->cq_vector == -1 without
	 * having to grab the lock.
	 */
	mb();

	if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
		blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q);

	pci_free_irq(to_pci_dev(nvmeq->dev->dev), vector, nvmeq);

	return 0;
}

static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
{
	struct nvme_queue *nvmeq = &dev->queues[0];
	u16 start, end;

	if (shutdown)
		nvme_shutdown_ctrl(&dev->ctrl);
	else
		nvme_disable_ctrl(&dev->ctrl, dev->ctrl.cap);

	spin_lock_irq(&nvmeq->cq_lock);
	nvme_process_cq(nvmeq, &start, &end, -1);
	spin_unlock_irq(&nvmeq->cq_lock);

	nvme_complete_cqes(nvmeq, start, end);
}

static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
				int entry_size)
{
	int q_depth = dev->q_depth;
	unsigned q_size_aligned = roundup(q_depth * entry_size,
					  dev->ctrl.page_size);

	if (q_size_aligned * nr_io_queues > dev->cmb_size) {
		u64 mem_per_q = div_u64(dev->cmb_size, nr_io_queues);
		mem_per_q = round_down(mem_per_q, dev->ctrl.page_size);
		q_depth = div_u64(mem_per_q, entry_size);

		/*
		 * Ensure the reduced q_depth is above some threshold where it
		 * would be better to map queues in system memory with the
		 * original depth
		 */
		if (q_depth < 64)
			return -ENOMEM;
	}

	return q_depth;
}

static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
				int qid, int depth)
{
	/* CMB SQEs will be mapped before creation */
	if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS))
		return 0;

	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
					    &nvmeq->sq_dma_addr, GFP_KERNEL);
	if (!nvmeq->sq_cmds)
		return -ENOMEM;
	return 0;
}

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

	if (dev->ctrl.queue_count > qid)
		return 0;

	nvmeq->cqes = dma_zalloc_coherent(dev->dev, CQ_SIZE(depth),
					  &nvmeq->cq_dma_addr, GFP_KERNEL);
	if (!nvmeq->cqes)
		goto free_nvmeq;

	if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth))
		goto free_cqdma;

	nvmeq->q_dmadev = dev->dev;
	nvmeq->dev = dev;
	spin_lock_init(&nvmeq->sq_lock);
	spin_lock_init(&nvmeq->cq_lock);
	nvmeq->cq_head = 0;
	nvmeq->cq_phase = 1;
	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
	nvmeq->q_depth = depth;
	nvmeq->qid = qid;
	nvmeq->cq_vector = -1;
	dev->ctrl.queue_count++;

	return 0;

 free_cqdma:
	dma_free_coherent(dev->dev, CQ_SIZE(depth), (void *)nvmeq->cqes,
							nvmeq->cq_dma_addr);
 free_nvmeq:
	return -ENOMEM;
}

static int queue_request_irq(struct nvme_queue *nvmeq)
{
	struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev);
	int nr = nvmeq->dev->ctrl.instance;

	if (use_threaded_interrupts) {
		return pci_request_irq(pdev, nvmeq->cq_vector, nvme_irq_check,
				nvme_irq, nvmeq, "nvme%dq%d", nr, nvmeq->qid);
	} else {
		return pci_request_irq(pdev, nvmeq->cq_vector, nvme_irq,
				NULL, nvmeq, "nvme%dq%d", nr, nvmeq->qid);
	}
}

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

	spin_lock_irq(&nvmeq->cq_lock);
	nvmeq->sq_tail = 0;
	nvmeq->cq_head = 0;
	nvmeq->cq_phase = 1;
	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
	nvme_dbbuf_init(dev, nvmeq, qid);
	dev->online_queues++;
	spin_unlock_irq(&nvmeq->cq_lock);
}

static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
{
	struct nvme_dev *dev = nvmeq->dev;
	int result;
	s16 vector;

	if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
		unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth),
						      dev->ctrl.page_size);
		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
		nvmeq->sq_cmds_io = dev->cmb + offset;
	}

	/*
	 * A queue's vector matches the queue identifier unless the controller
	 * has only one vector available.
	 */
	vector = dev->num_vecs == 1 ? 0 : qid;
	result = adapter_alloc_cq(dev, qid, nvmeq, vector);
	if (result)
		return result;

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

	/*
	 * Set cq_vector after alloc cq/sq, otherwise nvme_suspend_queue will
	 * invoke free_irq for it and cause a 'Trying to free already-free IRQ
	 * xxx' warning if the create CQ/SQ command times out.
	 */
	nvmeq->cq_vector = vector;
	nvme_init_queue(nvmeq, qid);
	result = queue_request_irq(nvmeq);
	if (result < 0)
		goto release_sq;

	return result;

release_sq:
	nvmeq->cq_vector = -1;
	dev->online_queues--;
	adapter_delete_sq(dev, qid);
release_cq:
	adapter_delete_cq(dev, qid);
	return result;
}

static const struct blk_mq_ops nvme_mq_admin_ops = {
	.queue_rq	= nvme_queue_rq,
	.complete	= nvme_pci_complete_rq,
	.init_hctx	= nvme_admin_init_hctx,
	.exit_hctx      = nvme_admin_exit_hctx,
	.init_request	= nvme_init_request,
	.timeout	= nvme_timeout,
};

static const struct blk_mq_ops nvme_mq_ops = {
	.queue_rq	= nvme_queue_rq,
	.complete	= nvme_pci_complete_rq,
	.init_hctx	= nvme_init_hctx,
	.init_request	= nvme_init_request,
	.map_queues	= nvme_pci_map_queues,
	.timeout	= nvme_timeout,
	.poll		= nvme_poll,
};

static void nvme_dev_remove_admin(struct nvme_dev *dev)
{
	if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q)) {
		/*
		 * If the controller was reset during removal, it's possible
		 * user requests may be waiting on a stopped queue. Start the
		 * queue to flush these to completion.
		 */
		blk_mq_unquiesce_queue(dev->ctrl.admin_q);
		blk_cleanup_queue(dev->ctrl.admin_q);
		blk_mq_free_tag_set(&dev->admin_tagset);
	}
}

static int nvme_alloc_admin_tags(struct nvme_dev *dev)
{
	if (!dev->ctrl.admin_q) {
		dev->admin_tagset.ops = &nvme_mq_admin_ops;
		dev->admin_tagset.nr_hw_queues = 1;

		dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
		dev->admin_tagset.numa_node = dev_to_node(dev->dev);
		dev->admin_tagset.cmd_size = nvme_pci_cmd_size(dev, false);
		dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
		dev->admin_tagset.driver_data = dev;

		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
			return -ENOMEM;
		dev->ctrl.admin_tagset = &dev->admin_tagset;

		dev->ctrl.admin_q = blk_mq_init_queue(&dev->admin_tagset);
		if (IS_ERR(dev->ctrl.admin_q)) {
			blk_mq_free_tag_set(&dev->admin_tagset);
			return -ENOMEM;
		}
		if (!blk_get_queue(dev->ctrl.admin_q)) {
			nvme_dev_remove_admin(dev);
			dev->ctrl.admin_q = NULL;
			return -ENODEV;
		}
	} else
		blk_mq_unquiesce_queue(dev->ctrl.admin_q);

	return 0;
}

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

static int nvme_remap_bar(struct nvme_dev *dev, unsigned long size)
{
	struct pci_dev *pdev = to_pci_dev(dev->dev);

	if (size <= dev->bar_mapped_size)
		return 0;
	if (size > pci_resource_len(pdev, 0))
		return -ENOMEM;
	if (dev->bar)
		iounmap(dev->bar);
	dev->bar = ioremap(pci_resource_start(pdev, 0), size);
	if (!dev->bar) {
		dev->bar_mapped_size = 0;
		return -ENOMEM;
	}
	dev->bar_mapped_size = size;
	dev->dbs = dev->bar + NVME_REG_DBS;

	return 0;
}

static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
{
	int result;
	u32 aqa;
	struct nvme_queue *nvmeq;

	result = nvme_remap_bar(dev, db_bar_size(dev, 0));
	if (result < 0)
		return result;

	dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1, 0) ?
				NVME_CAP_NSSRC(dev->ctrl.cap) : 0;

	if (dev->subsystem &&
	    (readl(dev->bar + NVME_REG_CSTS) & NVME_CSTS_NSSRO))
		writel(NVME_CSTS_NSSRO, dev->bar + NVME_REG_CSTS);

	result = nvme_disable_ctrl(&dev->ctrl, dev->ctrl.cap);
	if (result < 0)
		return result;

	result = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
	if (result)
		return result;

	nvmeq = &dev->queues[0];
	aqa = nvmeq->q_depth - 1;
	aqa |= aqa << 16;

	writel(aqa, dev->bar + NVME_REG_AQA);
	lo_hi_writeq(nvmeq->sq_dma_addr, dev->bar + NVME_REG_ASQ);
	lo_hi_writeq(nvmeq->cq_dma_addr, dev->bar + NVME_REG_ACQ);

	result = nvme_enable_ctrl(&dev->ctrl, dev->ctrl.cap);
	if (result)
		return result;

	nvmeq->cq_vector = 0;
	nvme_init_queue(nvmeq, 0);
	result = queue_request_irq(nvmeq);
	if (result) {
		nvmeq->cq_vector = -1;
		return result;
	}

	return result;
}

static int nvme_create_io_queues(struct nvme_dev *dev)
{
	unsigned i, max;
	int ret = 0;

	for (i = dev->ctrl.queue_count; i <= dev->max_qid; i++) {
		if (nvme_alloc_queue(dev, i, dev->q_depth)) {
			ret = -ENOMEM;
			break;
		}
	}

	max = min(dev->max_qid, dev->ctrl.queue_count - 1);
	for (i = dev->online_queues; i <= max; i++) {
		ret = nvme_create_queue(&dev->queues[i], i);
		if (ret)
			break;
	}

	/*
	 * Ignore failing Create SQ/CQ commands, we can continue with less
	 * than the desired amount of queues, and even a controller without
	 * I/O queues can still be used to issue admin commands.  This might
	 * be useful to upgrade a buggy firmware for example.
	 */
	return ret >= 0 ? 0 : ret;
}

static ssize_t nvme_cmb_show(struct device *dev,
			     struct device_attribute *attr,
			     char *buf)
{
	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));

	return scnprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz  : x%08x\n",
		       ndev->cmbloc, ndev->cmbsz);
}
static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);

static u64 nvme_cmb_size_unit(struct nvme_dev *dev)
{
	u8 szu = (dev->cmbsz >> NVME_CMBSZ_SZU_SHIFT) & NVME_CMBSZ_SZU_MASK;

	return 1ULL << (12 + 4 * szu);
}

static u32 nvme_cmb_size(struct nvme_dev *dev)
{
	return (dev->cmbsz >> NVME_CMBSZ_SZ_SHIFT) & NVME_CMBSZ_SZ_MASK;
}

static void nvme_map_cmb(struct nvme_dev *dev)
{
	u64 size, offset;
	resource_size_t bar_size;
	struct pci_dev *pdev = to_pci_dev(dev->dev);
	int bar;

	dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
	if (!dev->cmbsz)
		return;
	dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);

	if (!use_cmb_sqes)
		return;

	size = nvme_cmb_size_unit(dev) * nvme_cmb_size(dev);
	offset = nvme_cmb_size_unit(dev) * NVME_CMB_OFST(dev->cmbloc);
	bar = NVME_CMB_BIR(dev->cmbloc);
	bar_size = pci_resource_len(pdev, bar);

	if (offset > bar_size)
		return;

	/*
	 * Controllers may support a CMB size larger than their BAR,
	 * for example, due to being behind a bridge. Reduce the CMB to
	 * the reported size of the BAR
	 */
	if (size > bar_size - offset)
		size = bar_size - offset;

	dev->cmb = ioremap_wc(pci_resource_start(pdev, bar) + offset, size);
	if (!dev->cmb)
		return;
	dev->cmb_bus_addr = pci_bus_address(pdev, bar) + offset;
	dev->cmb_size = size;

	if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
				    &dev_attr_cmb.attr, NULL))
		dev_warn(dev->ctrl.device,
			 "failed to add sysfs attribute for CMB\n");
}

static inline void nvme_release_cmb(struct nvme_dev *dev)
{
	if (dev->cmb) {
		iounmap(dev->cmb);
		dev->cmb = NULL;
		sysfs_remove_file_from_group(&dev->ctrl.device->kobj,
					     &dev_attr_cmb.attr, NULL);
		dev->cmbsz = 0;
	}
}

static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
{
	u64 dma_addr = dev->host_mem_descs_dma;
	struct nvme_command c;
	int ret;

	memset(&c, 0, sizeof(c));
	c.features.opcode	= nvme_admin_set_features;
	c.features.fid		= cpu_to_le32(NVME_FEAT_HOST_MEM_BUF);
	c.features.dword11	= cpu_to_le32(bits);
	c.features.dword12	= cpu_to_le32(dev->host_mem_size >>
					      ilog2(dev->ctrl.page_size));
	c.features.dword13	= cpu_to_le32(lower_32_bits(dma_addr));
	c.features.dword14	= cpu_to_le32(upper_32_bits(dma_addr));
	c.features.dword15	= cpu_to_le32(dev->nr_host_mem_descs);

	ret = nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0);
	if (ret) {
		dev_warn(dev->ctrl.device,
			 "failed to set host mem (err %d, flags %#x).\n",
			 ret, bits);
	}
	return ret;
}

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

	for (i = 0; i < dev->nr_host_mem_descs; i++) {
		struct nvme_host_mem_buf_desc *desc = &dev->host_mem_descs[i];
		size_t size = le32_to_cpu(desc->size) * dev->ctrl.page_size;

		dma_free_coherent(dev->dev, size, dev->host_mem_desc_bufs[i],
				le64_to_cpu(desc->addr));
	}

	kfree(dev->host_mem_desc_bufs);
	dev->host_mem_desc_bufs = NULL;
	dma_free_coherent(dev->dev,
			dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs),
			dev->host_mem_descs, dev->host_mem_descs_dma);
	dev->host_mem_descs = NULL;
	dev->nr_host_mem_descs = 0;
}

static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
		u32 chunk_size)
{
	struct nvme_host_mem_buf_desc *descs;
	u32 max_entries, len;
	dma_addr_t descs_dma;
	int i = 0;
	void **bufs;
	u64 size, tmp;

	tmp = (preferred + chunk_size - 1);
	do_div(tmp, chunk_size);
	max_entries = tmp;

	if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries)
		max_entries = dev->ctrl.hmmaxd;

	descs = dma_zalloc_coherent(dev->dev, max_entries * sizeof(*descs),
			&descs_dma, GFP_KERNEL);
	if (!descs)
		goto out;

	bufs = kcalloc(max_entries, sizeof(*bufs), GFP_KERNEL);
	if (!bufs)
		goto out_free_descs;

	for (size = 0; size < preferred && i < max_entries; size += len) {
		dma_addr_t dma_addr;

		len = min_t(u64, chunk_size, preferred - size);
		bufs[i] = dma_alloc_attrs(dev->dev, len, &dma_addr, GFP_KERNEL,
				DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN);
		if (!bufs[i])
			break;

		descs[i].addr = cpu_to_le64(dma_addr);
		descs[i].size = cpu_to_le32(len / dev->ctrl.page_size);
		i++;
	}

	if (!size)
		goto out_free_bufs;

	dev->nr_host_mem_descs = i;
	dev->host_mem_size = size;
	dev->host_mem_descs = descs;
	dev->host_mem_descs_dma = descs_dma;
	dev->host_mem_desc_bufs = bufs;
	return 0;

out_free_bufs:
	while (--i >= 0) {
		size_t size = le32_to_cpu(descs[i].size) * dev->ctrl.page_size;

		dma_free_coherent(dev->dev, size, bufs[i],
				le64_to_cpu(descs[i].addr));
	}

	kfree(bufs);
out_free_descs:
	dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs,
			descs_dma);
out:
	dev->host_mem_descs = NULL;
	return -ENOMEM;
}

static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
{
	u32 chunk_size;

	/* start big and work our way down */
	for (chunk_size = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
	     chunk_size >= max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
	     chunk_size /= 2) {
		if (!__nvme_alloc_host_mem(dev, preferred, chunk_size)) {
			if (!min || dev->host_mem_size >= min)
				return 0;
			nvme_free_host_mem(dev);
		}
	}

	return -ENOMEM;
}

static int nvme_setup_host_mem(struct nvme_dev *dev)
{
	u64 max = (u64)max_host_mem_size_mb * SZ_1M;
	u64 preferred = (u64)dev->ctrl.hmpre * 4096;
	u64 min = (u64)dev->ctrl.hmmin * 4096;
	u32 enable_bits = NVME_HOST_MEM_ENABLE;
	int ret;

	preferred = min(preferred, max);
	if (min > max) {
		dev_warn(dev->ctrl.device,
			"min host memory (%lld MiB) above limit (%d MiB).\n",
			min >> ilog2(SZ_1M), max_host_mem_size_mb);
		nvme_free_host_mem(dev);
		return 0;
	}

	/*
	 * If we already have a buffer allocated check if we can reuse it.
	 */
	if (dev->host_mem_descs) {
		if (dev->host_mem_size >= min)
			enable_bits |= NVME_HOST_MEM_RETURN;
		else
			nvme_free_host_mem(dev);
	}

	if (!dev->host_mem_descs) {
		if (nvme_alloc_host_mem(dev, min, preferred)) {
			dev_warn(dev->ctrl.device,
				"failed to allocate host memory buffer.\n");
			return 0; /* controller must work without HMB */
		}

		dev_info(dev->ctrl.device,
			"allocated %lld MiB host memory buffer.\n",
			dev->host_mem_size >> ilog2(SZ_1M));
	}

	ret = nvme_set_host_mem(dev, enable_bits);
	if (ret)
		nvme_free_host_mem(dev);
	return ret;
}

static int nvme_setup_io_queues(struct nvme_dev *dev)
{
	struct nvme_queue *adminq = &dev->queues[0];
	struct pci_dev *pdev = to_pci_dev(dev->dev);
	int result, nr_io_queues;
	unsigned long size;

	struct irq_affinity affd = {
		.pre_vectors = 1
	};

	nr_io_queues = num_possible_cpus();
	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
	if (result < 0)
		return result;

	if (nr_io_queues == 0)
		return 0;

	if (dev->cmb && (dev->cmbsz & NVME_CMBSZ_SQS)) {
		result = nvme_cmb_qdepth(dev, nr_io_queues,
				sizeof(struct nvme_command));
		if (result > 0)
			dev->q_depth = result;
		else
			nvme_release_cmb(dev);
	}

	do {
		size = db_bar_size(dev, nr_io_queues);
		result = nvme_remap_bar(dev, size);
		if (!result)
			break;
		if (!--nr_io_queues)
			return -ENOMEM;
	} while (1);
	adminq->q_db = dev->dbs;

	/* Deregister the admin queue's interrupt */
	pci_free_irq(pdev, 0, adminq);

	/*
	 * If we enable msix early due to not intx, disable it again before
	 * setting up the full range we need.
	 */
	pci_free_irq_vectors(pdev);
	result = pci_alloc_irq_vectors_affinity(pdev, 1, nr_io_queues + 1,
			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
	if (result <= 0)
		return -EIO;
	dev->num_vecs = result;
	dev->max_qid = max(result - 1, 1);

	/*
	 * 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.
	 */

	result = queue_request_irq(adminq);
	if (result) {
		adminq->cq_vector = -1;
		return result;
	}
	return nvme_create_io_queues(dev);
}

static void nvme_del_queue_end(struct request *req, blk_status_t error)
{
	struct nvme_queue *nvmeq = req->end_io_data;

	blk_mq_free_request(req);
	complete(&nvmeq->dev->ioq_wait);
}

static void nvme_del_cq_end(struct request *req, blk_status_t error)
{
	struct nvme_queue *nvmeq = req->end_io_data;
	u16 start, end;

	if (!error) {
		unsigned long flags;

		spin_lock_irqsave(&nvmeq->cq_lock, flags);
		nvme_process_cq(nvmeq, &start, &end, -1);
		spin_unlock_irqrestore(&nvmeq->cq_lock, flags);

		nvme_complete_cqes(nvmeq, start, end);
	}

	nvme_del_queue_end(req, error);
}

static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
{
	struct request_queue *q = nvmeq->dev->ctrl.admin_q;
	struct request *req;
	struct nvme_command cmd;

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

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

	req->timeout = ADMIN_TIMEOUT;
	req->end_io_data = nvmeq;

	blk_execute_rq_nowait(q, NULL, req, false,
			opcode == nvme_admin_delete_cq ?
				nvme_del_cq_end : nvme_del_queue_end);
	return 0;
}

static void nvme_disable_io_queues(struct nvme_dev *dev)
{
	int pass, queues = dev->online_queues - 1;
	unsigned long timeout;
	u8 opcode = nvme_admin_delete_sq;

	for (pass = 0; pass < 2; pass++) {
		int sent = 0, i = queues;

		reinit_completion(&dev->ioq_wait);
 retry:
		timeout = ADMIN_TIMEOUT;
		for (; i > 0; i--, sent++)
			if (nvme_delete_queue(&dev->queues[i], opcode))
				break;

		while (sent--) {
			timeout = wait_for_completion_io_timeout(&dev->ioq_wait, timeout);
			if (timeout == 0)
				return;
			if (i)
				goto retry;
		}
		opcode = nvme_admin_delete_cq;
	}
}

/*
 * return error value only when tagset allocation failed
 */
static int nvme_dev_add(struct nvme_dev *dev)
{
	int ret;

	if (!dev->ctrl.tagset) {
		dev->tagset.ops = &nvme_mq_ops;
		dev->tagset.nr_hw_queues = dev->online_queues - 1;
		dev->tagset.timeout = NVME_IO_TIMEOUT;
		dev->tagset.numa_node = dev_to_node(dev->dev);
		dev->tagset.queue_depth =
				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
		dev->tagset.cmd_size = nvme_pci_cmd_size(dev, false);
		if ((dev->ctrl.sgls & ((1 << 0) | (1 << 1))) && sgl_threshold) {
			dev->tagset.cmd_size = max(dev->tagset.cmd_size,
					nvme_pci_cmd_size(dev, true));
		}
		dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
		dev->tagset.driver_data = dev;

		ret = blk_mq_alloc_tag_set(&dev->tagset);
		if (ret) {
			dev_warn(dev->ctrl.device,
				"IO queues tagset allocation failed %d\n", ret);
			return ret;
		}
		dev->ctrl.tagset = &dev->tagset;

		nvme_dbbuf_set(dev);
	} else {
		blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);

		/* Free previously allocated queues that are no longer usable */
		nvme_free_queues(dev, dev->online_queues);
	}

	return 0;
}

static int nvme_pci_enable(struct nvme_dev *dev)
{
	int result = -ENOMEM;
	struct pci_dev *pdev = to_pci_dev(dev->dev);

	if (pci_enable_device_mem(pdev))
		return result;

	pci_set_master(pdev);

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

	if (readl(dev->bar + NVME_REG_CSTS) == -1) {
		result = -ENODEV;
		goto disable;
	}

	/*
	 * Some devices and/or platforms don't advertise or work with INTx
	 * interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll
	 * adjust this later.
	 */
	result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
	if (result < 0)
		return result;

	dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);

	dev->q_depth = min_t(int, NVME_CAP_MQES(dev->ctrl.cap) + 1,
				io_queue_depth);
	dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
	dev->dbs = dev->bar + 4096;

	/*
	 * Temporary fix for the Apple controller found in the MacBook8,1 and
	 * some MacBook7,1 to avoid controller resets and data loss.
	 */
	if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001) {
		dev->q_depth = 2;
		dev_warn(dev->ctrl.device, "detected Apple NVMe controller, "
			"set queue depth=%u to work around controller resets\n",
			dev->q_depth);
	} else if (pdev->vendor == PCI_VENDOR_ID_SAMSUNG &&
		   (pdev->device == 0xa821 || pdev->device == 0xa822) &&
		   NVME_CAP_MQES(dev->ctrl.cap) == 0) {
		dev->q_depth = 64;
		dev_err(dev->ctrl.device, "detected PM1725 NVMe controller, "
                        "set queue depth=%u\n", dev->q_depth);
	}

	nvme_map_cmb(dev);

	pci_enable_pcie_error_reporting(pdev);
	pci_save_state(pdev);
	return 0;

 disable:
	pci_disable_device(pdev);
	return result;
}

static void nvme_dev_unmap(struct nvme_dev *dev)
{
	if (dev->bar)
		iounmap(dev->bar);
	pci_release_mem_regions(to_pci_dev(dev->dev));
}

static void nvme_pci_disable(struct nvme_dev *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev->dev);

	nvme_release_cmb(dev);
	pci_free_irq_vectors(pdev);

	if (pci_is_enabled(pdev)) {
		pci_disable_pcie_error_reporting(pdev);
		pci_disable_device(pdev);
	}
}

static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
{
	int i;
	bool dead = true;
	struct pci_dev *pdev = to_pci_dev(dev->dev);

	mutex_lock(&dev->shutdown_lock);
	if (pci_is_enabled(pdev)) {
		u32 csts = readl(dev->bar + NVME_REG_CSTS);

		if (dev->ctrl.state == NVME_CTRL_LIVE ||
		    dev->ctrl.state == NVME_CTRL_RESETTING)
			nvme_start_freeze(&dev->ctrl);
		dead = !!((csts & NVME_CSTS_CFS) || !(csts & NVME_CSTS_RDY) ||
			pdev->error_state  != pci_channel_io_normal);
	}

	/*
	 * Give the controller a chance to complete all entered requests if
	 * doing a safe shutdown.
	 */
	if (!dead) {
		if (shutdown)
			nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
	}

	nvme_stop_queues(&dev->ctrl);

	if (!dead && dev->ctrl.queue_count > 0) {
		nvme_disable_io_queues(dev);
		nvme_disable_admin_queue(dev, shutdown);
	}
	for (i = dev->ctrl.queue_count - 1; i >= 0; i--)
		nvme_suspend_queue(&dev->queues[i]);

	nvme_pci_disable(dev);

	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);

	/*
	 * The driver will not be starting up queues again if shutting down so
	 * must flush all entered requests to their failed completion to avoid
	 * deadlocking blk-mq hot-cpu notifier.
	 */
	if (shutdown)
		nvme_start_queues(&dev->ctrl);
	mutex_unlock(&dev->shutdown_lock);
}

static int nvme_setup_prp_pools(struct nvme_dev *dev)
{
	dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
						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", dev->dev,
						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 void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
{
	struct nvme_dev *dev = to_nvme_dev(ctrl);

	nvme_dbbuf_dma_free(dev);
	put_device(dev->dev);
	if (dev->tagset.tags)
		blk_mq_free_tag_set(&dev->tagset);
	if (dev->ctrl.admin_q)
		blk_put_queue(dev->ctrl.admin_q);
	kfree(dev->queues);
	free_opal_dev(dev->ctrl.opal_dev);
	mempool_destroy(dev->iod_mempool);
	kfree(dev);
}

static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
{
	dev_warn(dev->ctrl.device, "Removing after probe failure status: %d\n", status);

	nvme_get_ctrl(&dev->ctrl);
	nvme_dev_disable(dev, false);
	nvme_kill_queues(&dev->ctrl);
	if (!queue_work(nvme_wq, &dev->remove_work))
		nvme_put_ctrl(&dev->ctrl);
}

static void nvme_reset_work(struct work_struct *work)
{
	struct nvme_dev *dev =
		container_of(work, struct nvme_dev, ctrl.reset_work);
	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
	int result = -ENODEV;
	enum nvme_ctrl_state new_state = NVME_CTRL_LIVE;

	if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING))
		goto out;

	/*
	 * If we're called to reset a live controller first shut it down before
	 * moving on.
	 */
	if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
		nvme_dev_disable(dev, false);

	/*
	 * Introduce CONNECTING state from nvme-fc/rdma transports to mark the
	 * initializing procedure here.
	 */
	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
		dev_warn(dev->ctrl.device,
			"failed to mark controller CONNECTING\n");
		goto out;
	}

	result = nvme_pci_enable(dev);
	if (result)
		goto out;

	result = nvme_pci_configure_admin_queue(dev);
	if (result)
		goto out;

	result = nvme_alloc_admin_tags(dev);
	if (result)
		goto out;

	/*
	 * Limit the max command size to prevent iod->sg allocations going
	 * over a single page.
	 */
	dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
	dev->ctrl.max_segments = NVME_MAX_SEGS;

	result = nvme_init_identify(&dev->ctrl);
	if (result)
		goto out;

	if (dev->ctrl.oacs & NVME_CTRL_OACS_SEC_SUPP) {
		if (!dev->ctrl.opal_dev)
			dev->ctrl.opal_dev =
				init_opal_dev(&dev->ctrl, &nvme_sec_submit);
		else if (was_suspend)
			opal_unlock_from_suspend(dev->ctrl.opal_dev);
	} else {
		free_opal_dev(dev->ctrl.opal_dev);
		dev->ctrl.opal_dev = NULL;
	}

	if (dev->ctrl.oacs & NVME_CTRL_OACS_DBBUF_SUPP) {
		result = nvme_dbbuf_dma_alloc(dev);
		if (result)
			dev_warn(dev->dev,
				 "unable to allocate dma for dbbuf\n");
	}

	if (dev->ctrl.hmpre) {
		result = nvme_setup_host_mem(dev);
		if (result < 0)
			goto out;
	}

	result = nvme_setup_io_queues(dev);
	if (result)
		goto out;

	/*
	 * Keep the controller around but remove all namespaces if we don't have
	 * any working I/O queue.
	 */
	if (dev->online_queues < 2) {
		dev_warn(dev->ctrl.device, "IO queues not created\n");
		nvme_kill_queues(&dev->ctrl);
		nvme_remove_namespaces(&dev->ctrl);
		new_state = NVME_CTRL_ADMIN_ONLY;
	} else {
		nvme_start_queues(&dev->ctrl);
		nvme_wait_freeze(&dev->ctrl);
		/* hit this only when allocate tagset fails */
		if (nvme_dev_add(dev))
			new_state = NVME_CTRL_ADMIN_ONLY;
		nvme_unfreeze(&dev->ctrl);
	}

	/*
	 * If only admin queue live, keep it to do further investigation or
	 * recovery.
	 */
	if (!nvme_change_ctrl_state(&dev->ctrl, new_state)) {
		dev_warn(dev->ctrl.device,
			"failed to mark controller state %d\n", new_state);
		goto out;
	}

	nvme_start_ctrl(&dev->ctrl);
	return;

 out:
	nvme_remove_dead_ctrl(dev, result);
}

static void nvme_remove_dead_ctrl_work(struct work_struct *work)
{
	struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work);
	struct pci_dev *pdev = to_pci_dev(dev->dev);

	if (pci_get_drvdata(pdev))
		device_release_driver(&pdev->dev);
	nvme_put_ctrl(&dev->ctrl);
}

static int nvme_pci_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
{
	*val = readl(to_nvme_dev(ctrl)->bar + off);
	return 0;
}

static int nvme_pci_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
{
	writel(val, to_nvme_dev(ctrl)->bar + off);
	return 0;
}

static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
{
	*val = readq(to_nvme_dev(ctrl)->bar + off);
	return 0;
}

static int nvme_pci_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
{
	struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);

	return snprintf(buf, size, "%s", dev_name(&pdev->dev));
}

static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
	.name			= "pcie",
	.module			= THIS_MODULE,
	.flags			= NVME_F_METADATA_SUPPORTED,
	.reg_read32		= nvme_pci_reg_read32,
	.reg_write32		= nvme_pci_reg_write32,
	.reg_read64		= nvme_pci_reg_read64,
	.free_ctrl		= nvme_pci_free_ctrl,
	.submit_async_event	= nvme_pci_submit_async_event,
	.get_address		= nvme_pci_get_address,
};

static int nvme_dev_map(struct nvme_dev *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev->dev);

	if (pci_request_mem_regions(pdev, "nvme"))
		return -ENODEV;

	if (nvme_remap_bar(dev, NVME_REG_DBS + 4096))
		goto release;

	return 0;
  release:
	pci_release_mem_regions(pdev);
	return -ENODEV;
}

static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
{
	if (pdev->vendor == 0x144d && pdev->device == 0xa802) {
		/*
		 * Several Samsung devices seem to drop off the PCIe bus
		 * randomly when APST is on and uses the deepest sleep state.
		 * This has been observed on a Samsung "SM951 NVMe SAMSUNG
		 * 256GB", a "PM951 NVMe SAMSUNG 512GB", and a "Samsung SSD
		 * 950 PRO 256GB", but it seems to be restricted to two Dell
		 * laptops.
		 */
		if (dmi_match(DMI_SYS_VENDOR, "Dell Inc.") &&
		    (dmi_match(DMI_PRODUCT_NAME, "XPS 15 9550") ||
		     dmi_match(DMI_PRODUCT_NAME, "Precision 5510")))
			return NVME_QUIRK_NO_DEEPEST_PS;
	} else if (pdev->vendor == 0x144d && pdev->device == 0xa804) {
		/*
		 * Samsung SSD 960 EVO drops off the PCIe bus after system
		 * suspend on a Ryzen board, ASUS PRIME B350M-A, as well as
		 * within few minutes after bootup on a Coffee Lake board -
		 * ASUS PRIME Z370-A
		 */
		if (dmi_match(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC.") &&
		    (dmi_match(DMI_BOARD_NAME, "PRIME B350M-A") ||
		     dmi_match(DMI_BOARD_NAME, "PRIME Z370-A")))
			return NVME_QUIRK_NO_APST;
	}

	return 0;
}

static void nvme_async_probe(void *data, async_cookie_t cookie)
{
	struct nvme_dev *dev = data;

	nvme_reset_ctrl_sync(&dev->ctrl);
	flush_work(&dev->ctrl.scan_work);
	nvme_put_ctrl(&dev->ctrl);
}

static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
	int node, result = -ENOMEM;
	struct nvme_dev *dev;
	unsigned long quirks = id->driver_data;
	size_t alloc_size;

	node = dev_to_node(&pdev->dev);
	if (node == NUMA_NO_NODE)
		set_dev_node(&pdev->dev, first_memory_node);

	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
	if (!dev)
		return -ENOMEM;

	dev->queues = kcalloc_node(num_possible_cpus() + 1,
			sizeof(struct nvme_queue), GFP_KERNEL, node);
	if (!dev->queues)
		goto free;

	dev->dev = get_device(&pdev->dev);
	pci_set_drvdata(pdev, dev);

	result = nvme_dev_map(dev);
	if (result)
		goto put_pci;

	INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work);
	INIT_WORK(&dev->remove_work, nvme_remove_dead_ctrl_work);
	mutex_init(&dev->shutdown_lock);
	init_completion(&dev->ioq_wait);

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

	quirks |= check_vendor_combination_bug(pdev);

	/*
	 * Double check that our mempool alloc size will cover the biggest
	 * command we support.
	 */
	alloc_size = nvme_pci_iod_alloc_size(dev, NVME_MAX_KB_SZ,
						NVME_MAX_SEGS, true);
	WARN_ON_ONCE(alloc_size > PAGE_SIZE);

	dev->iod_mempool = mempool_create_node(1, mempool_kmalloc,
						mempool_kfree,
						(void *) alloc_size,
						GFP_KERNEL, node);
	if (!dev->iod_mempool) {
		result = -ENOMEM;
		goto release_pools;
	}

	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
			quirks);
	if (result)
		goto release_mempool;

	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));

	nvme_get_ctrl(&dev->ctrl);
	async_schedule(nvme_async_probe, dev);

	return 0;

 release_mempool:
	mempool_destroy(dev->iod_mempool);
 release_pools:
	nvme_release_prp_pools(dev);
 unmap:
	nvme_dev_unmap(dev);
 put_pci:
	put_device(dev->dev);
 free:
	kfree(dev->queues);
	kfree(dev);
	return result;
}

static void nvme_reset_prepare(struct pci_dev *pdev)
{
	struct nvme_dev *dev = pci_get_drvdata(pdev);
	nvme_dev_disable(dev, false);
}

static void nvme_reset_done(struct pci_dev *pdev)
{
	struct nvme_dev *dev = pci_get_drvdata(pdev);
	nvme_reset_ctrl_sync(&dev->ctrl);
}

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

/*
 * The driver's remove may be called on a device in a partially initialized
 * state. This function must not have any dependencies on the device state in
 * order to proceed.
 */
static void nvme_remove(struct pci_dev *pdev)
{
	struct nvme_dev *dev = pci_get_drvdata(pdev);

	nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);

	cancel_work_sync(&dev->ctrl.reset_work);
	pci_set_drvdata(pdev, NULL);

	if (!pci_device_is_present(pdev)) {
		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
		nvme_dev_disable(dev, true);
	}

	flush_work(&dev->ctrl.reset_work);
	nvme_stop_ctrl(&dev->ctrl);
	nvme_remove_namespaces(&dev->ctrl);
	nvme_dev_disable(dev, true);
	nvme_free_host_mem(dev);
	nvme_dev_remove_admin(dev);
	nvme_free_queues(dev, 0);
	nvme_uninit_ctrl(&dev->ctrl);
	nvme_release_prp_pools(dev);
	nvme_dev_unmap(dev);
	nvme_put_ctrl(&dev->ctrl);
}

#ifdef CONFIG_PM_SLEEP
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_disable(ndev, true);
	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);

	nvme_reset_ctrl(&ndev->ctrl);
	return 0;
}
#endif

static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);

static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
						pci_channel_state_t state)
{
	struct nvme_dev *dev = pci_get_drvdata(pdev);

	/*
	 * A frozen channel requires a reset. When detected, this method will
	 * shutdown the controller to quiesce. The controller will be restarted
	 * after the slot reset through driver's slot_reset callback.
	 */
	switch (state) {
	case pci_channel_io_normal:
		return PCI_ERS_RESULT_CAN_RECOVER;
	case pci_channel_io_frozen:
		dev_warn(dev->ctrl.device,
			"frozen state error detected, reset controller\n");
		nvme_dev_disable(dev, false);
		return PCI_ERS_RESULT_NEED_RESET;
	case pci_channel_io_perm_failure:
		dev_warn(dev->ctrl.device,
			"failure state error detected, request disconnect\n");
		return PCI_ERS_RESULT_DISCONNECT;
	}
	return PCI_ERS_RESULT_NEED_RESET;
}

static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
{
	struct nvme_dev *dev = pci_get_drvdata(pdev);

	dev_info(dev->ctrl.device, "restart after slot reset\n");
	pci_restore_state(pdev);
	nvme_reset_ctrl(&dev->ctrl);
	return PCI_ERS_RESULT_RECOVERED;
}

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

	flush_work(&dev->ctrl.reset_work);
}

static const struct pci_error_handlers nvme_err_handler = {
	.error_detected	= nvme_error_detected,
	.slot_reset	= nvme_slot_reset,
	.resume		= nvme_error_resume,
	.reset_prepare	= nvme_reset_prepare,
	.reset_done	= nvme_reset_done,
};

static const struct pci_device_id nvme_id_table[] = {
	{ PCI_VDEVICE(INTEL, 0x0953),
		.driver_data = NVME_QUIRK_STRIPE_SIZE |
				NVME_QUIRK_DEALLOCATE_ZEROES, },
	{ PCI_VDEVICE(INTEL, 0x0a53),
		.driver_data = NVME_QUIRK_STRIPE_SIZE |
				NVME_QUIRK_DEALLOCATE_ZEROES, },
	{ PCI_VDEVICE(INTEL, 0x0a54),
		.driver_data = NVME_QUIRK_STRIPE_SIZE |
				NVME_QUIRK_DEALLOCATE_ZEROES, },
	{ PCI_VDEVICE(INTEL, 0x0a55),
		.driver_data = NVME_QUIRK_STRIPE_SIZE |
				NVME_QUIRK_DEALLOCATE_ZEROES, },
	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
				NVME_QUIRK_MEDIUM_PRIO_SQ },
	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
	{ PCI_DEVICE(0x1bb1, 0x0100),   /* Seagate Nytro Flash Storage */
		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
	{ PCI_DEVICE(0x1c58, 0x0023),	/* WDC SN200 adapter */
		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
	{ PCI_DEVICE(0x1c5f, 0x0540),	/* Memblaze Pblaze4 adapter */
		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
	{ PCI_DEVICE(0x144d, 0xa821),   /* Samsung PM1725 */
		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
	{ PCI_DEVICE(0x144d, 0xa822),   /* Samsung PM1725a */
		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
	{ PCI_DEVICE(0x1d1d, 0x1f1f),	/* LighNVM qemu device */
		.driver_data = NVME_QUIRK_LIGHTNVM, },
	{ PCI_DEVICE(0x1d1d, 0x2807),	/* CNEX WL */
		.driver_data = NVME_QUIRK_LIGHTNVM, },
	{ PCI_DEVICE(0x1d1d, 0x2601),	/* CNEX Granby */
		.driver_data = NVME_QUIRK_LIGHTNVM, },
	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
	{ 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,
	},
	.sriov_configure = pci_sriov_configure_simple,
	.err_handler	= &nvme_err_handler,
};

static int __init nvme_init(void)
{
	return pci_register_driver(&nvme_driver);
}

static void __exit nvme_exit(void)
{
	pci_unregister_driver(&nvme_driver);
	flush_workqueue(nvme_wq);
	_nvme_check_size();
}

MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
MODULE_LICENSE("GPL");
MODULE_VERSION("1.0");
module_init(nvme_init);
module_exit(nvme_exit);