summaryrefslogtreecommitdiff
path: root/fs/io_uring.c
blob: 4ed4b110a154e5bc8caa044d1e667e256194f5e6 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
// SPDX-License-Identifier: GPL-2.0
/*
 * Shared application/kernel submission and completion ring pairs, for
 * supporting fast/efficient IO.
 *
 * A note on the read/write ordering memory barriers that are matched between
 * the application and kernel side.
 *
 * After the application reads the CQ ring tail, it must use an
 * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
 * before writing the tail (using smp_load_acquire to read the tail will
 * do). It also needs a smp_mb() before updating CQ head (ordering the
 * entry load(s) with the head store), pairing with an implicit barrier
 * through a control-dependency in io_get_cqring (smp_store_release to
 * store head will do). Failure to do so could lead to reading invalid
 * CQ entries.
 *
 * Likewise, the application must use an appropriate smp_wmb() before
 * writing the SQ tail (ordering SQ entry stores with the tail store),
 * which pairs with smp_load_acquire in io_get_sqring (smp_store_release
 * to store the tail will do). And it needs a barrier ordering the SQ
 * head load before writing new SQ entries (smp_load_acquire to read
 * head will do).
 *
 * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application
 * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after*
 * updating the SQ tail; a full memory barrier smp_mb() is needed
 * between.
 *
 * Also see the examples in the liburing library:
 *
 *	git://git.kernel.dk/liburing
 *
 * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens
 * from data shared between the kernel and application. This is done both
 * for ordering purposes, but also to ensure that once a value is loaded from
 * data that the application could potentially modify, it remains stable.
 *
 * Copyright (C) 2018-2019 Jens Axboe
 * Copyright (c) 2018-2019 Christoph Hellwig
 */
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <linux/compat.h>
#include <linux/refcount.h>
#include <linux/uio.h>

#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/mmu_context.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/blkdev.h>
#include <linux/bvec.h>
#include <linux/net.h>
#include <net/sock.h>
#include <net/af_unix.h>
#include <net/scm.h>
#include <linux/anon_inodes.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <linux/nospec.h>
#include <linux/sizes.h>
#include <linux/hugetlb.h>

#include <uapi/linux/io_uring.h>

#include "internal.h"

#define IORING_MAX_ENTRIES	4096
#define IORING_MAX_FIXED_FILES	1024

struct io_uring {
	u32 head ____cacheline_aligned_in_smp;
	u32 tail ____cacheline_aligned_in_smp;
};

/*
 * This data is shared with the application through the mmap at offset
 * IORING_OFF_SQ_RING.
 *
 * The offsets to the member fields are published through struct
 * io_sqring_offsets when calling io_uring_setup.
 */
struct io_sq_ring {
	/*
	 * Head and tail offsets into the ring; the offsets need to be
	 * masked to get valid indices.
	 *
	 * The kernel controls head and the application controls tail.
	 */
	struct io_uring		r;
	/*
	 * Bitmask to apply to head and tail offsets (constant, equals
	 * ring_entries - 1)
	 */
	u32			ring_mask;
	/* Ring size (constant, power of 2) */
	u32			ring_entries;
	/*
	 * Number of invalid entries dropped by the kernel due to
	 * invalid index stored in array
	 *
	 * Written by the kernel, shouldn't be modified by the
	 * application (i.e. get number of "new events" by comparing to
	 * cached value).
	 *
	 * After a new SQ head value was read by the application this
	 * counter includes all submissions that were dropped reaching
	 * the new SQ head (and possibly more).
	 */
	u32			dropped;
	/*
	 * Runtime flags
	 *
	 * Written by the kernel, shouldn't be modified by the
	 * application.
	 *
	 * The application needs a full memory barrier before checking
	 * for IORING_SQ_NEED_WAKEUP after updating the sq tail.
	 */
	u32			flags;
	/*
	 * Ring buffer of indices into array of io_uring_sqe, which is
	 * mmapped by the application using the IORING_OFF_SQES offset.
	 *
	 * This indirection could e.g. be used to assign fixed
	 * io_uring_sqe entries to operations and only submit them to
	 * the queue when needed.
	 *
	 * The kernel modifies neither the indices array nor the entries
	 * array.
	 */
	u32			array[];
};

/*
 * This data is shared with the application through the mmap at offset
 * IORING_OFF_CQ_RING.
 *
 * The offsets to the member fields are published through struct
 * io_cqring_offsets when calling io_uring_setup.
 */
struct io_cq_ring {
	/*
	 * Head and tail offsets into the ring; the offsets need to be
	 * masked to get valid indices.
	 *
	 * The application controls head and the kernel tail.
	 */
	struct io_uring		r;
	/*
	 * Bitmask to apply to head and tail offsets (constant, equals
	 * ring_entries - 1)
	 */
	u32			ring_mask;
	/* Ring size (constant, power of 2) */
	u32			ring_entries;
	/*
	 * Number of completion events lost because the queue was full;
	 * this should be avoided by the application by making sure
	 * there are not more requests pending thatn there is space in
	 * the completion queue.
	 *
	 * Written by the kernel, shouldn't be modified by the
	 * application (i.e. get number of "new events" by comparing to
	 * cached value).
	 *
	 * As completion events come in out of order this counter is not
	 * ordered with any other data.
	 */
	u32			overflow;
	/*
	 * Ring buffer of completion events.
	 *
	 * The kernel writes completion events fresh every time they are
	 * produced, so the application is allowed to modify pending
	 * entries.
	 */
	struct io_uring_cqe	cqes[];
};

struct io_mapped_ubuf {
	u64		ubuf;
	size_t		len;
	struct		bio_vec *bvec;
	unsigned int	nr_bvecs;
};

struct async_list {
	spinlock_t		lock;
	atomic_t		cnt;
	struct list_head	list;

	struct file		*file;
	off_t			io_end;
	size_t			io_pages;
};

struct io_ring_ctx {
	struct {
		struct percpu_ref	refs;
	} ____cacheline_aligned_in_smp;

	struct {
		unsigned int		flags;
		bool			compat;
		bool			account_mem;

		/* SQ ring */
		struct io_sq_ring	*sq_ring;
		unsigned		cached_sq_head;
		unsigned		sq_entries;
		unsigned		sq_mask;
		unsigned		sq_thread_idle;
		struct io_uring_sqe	*sq_sqes;

		struct list_head	defer_list;
	} ____cacheline_aligned_in_smp;

	/* IO offload */
	struct workqueue_struct	*sqo_wq;
	struct task_struct	*sqo_thread;	/* if using sq thread polling */
	struct mm_struct	*sqo_mm;
	wait_queue_head_t	sqo_wait;

	struct {
		/* CQ ring */
		struct io_cq_ring	*cq_ring;
		unsigned		cached_cq_tail;
		unsigned		cq_entries;
		unsigned		cq_mask;
		struct wait_queue_head	cq_wait;
		struct fasync_struct	*cq_fasync;
		struct eventfd_ctx	*cq_ev_fd;
	} ____cacheline_aligned_in_smp;

	/*
	 * If used, fixed file set. Writers must ensure that ->refs is dead,
	 * readers must ensure that ->refs is alive as long as the file* is
	 * used. Only updated through io_uring_register(2).
	 */
	struct file		**user_files;
	unsigned		nr_user_files;

	/* if used, fixed mapped user buffers */
	unsigned		nr_user_bufs;
	struct io_mapped_ubuf	*user_bufs;

	struct user_struct	*user;

	struct completion	ctx_done;

	struct {
		struct mutex		uring_lock;
		wait_queue_head_t	wait;
	} ____cacheline_aligned_in_smp;

	struct {
		spinlock_t		completion_lock;
		bool			poll_multi_file;
		/*
		 * ->poll_list is protected by the ctx->uring_lock for
		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
		 * For SQPOLL, only the single threaded io_sq_thread() will
		 * manipulate the list, hence no extra locking is needed there.
		 */
		struct list_head	poll_list;
		struct list_head	cancel_list;
	} ____cacheline_aligned_in_smp;

	struct async_list	pending_async[2];

#if defined(CONFIG_UNIX)
	struct socket		*ring_sock;
#endif
};

struct sqe_submit {
	const struct io_uring_sqe	*sqe;
	unsigned short			index;
	bool				has_user;
	bool				needs_lock;
	bool				needs_fixed_file;
};

/*
 * First field must be the file pointer in all the
 * iocb unions! See also 'struct kiocb' in <linux/fs.h>
 */
struct io_poll_iocb {
	struct file			*file;
	struct wait_queue_head		*head;
	__poll_t			events;
	bool				done;
	bool				canceled;
	struct wait_queue_entry		wait;
};

/*
 * NOTE! Each of the iocb union members has the file pointer
 * as the first entry in their struct definition. So you can
 * access the file pointer through any of the sub-structs,
 * or directly as just 'ki_filp' in this struct.
 */
struct io_kiocb {
	union {
		struct file		*file;
		struct kiocb		rw;
		struct io_poll_iocb	poll;
	};

	struct sqe_submit	submit;

	struct io_ring_ctx	*ctx;
	struct list_head	list;
	unsigned int		flags;
	refcount_t		refs;
#define REQ_F_NOWAIT		1	/* must not punt to workers */
#define REQ_F_IOPOLL_COMPLETED	2	/* polled IO has completed */
#define REQ_F_FIXED_FILE	4	/* ctx owns file */
#define REQ_F_SEQ_PREV		8	/* sequential with previous */
#define REQ_F_IO_DRAIN		16	/* drain existing IO first */
#define REQ_F_IO_DRAINED	32	/* drain done */
	u64			user_data;
	u32			error;	/* iopoll result from callback */
	u32			sequence;

	struct work_struct	work;
};

#define IO_PLUG_THRESHOLD		2
#define IO_IOPOLL_BATCH			8

struct io_submit_state {
	struct blk_plug		plug;

	/*
	 * io_kiocb alloc cache
	 */
	void			*reqs[IO_IOPOLL_BATCH];
	unsigned		int free_reqs;
	unsigned		int cur_req;

	/*
	 * File reference cache
	 */
	struct file		*file;
	unsigned int		fd;
	unsigned int		has_refs;
	unsigned int		used_refs;
	unsigned int		ios_left;
};

static void io_sq_wq_submit_work(struct work_struct *work);

static struct kmem_cache *req_cachep;

static const struct file_operations io_uring_fops;

struct sock *io_uring_get_socket(struct file *file)
{
#if defined(CONFIG_UNIX)
	if (file->f_op == &io_uring_fops) {
		struct io_ring_ctx *ctx = file->private_data;

		return ctx->ring_sock->sk;
	}
#endif
	return NULL;
}
EXPORT_SYMBOL(io_uring_get_socket);

static void io_ring_ctx_ref_free(struct percpu_ref *ref)
{
	struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);

	complete(&ctx->ctx_done);
}

static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
	struct io_ring_ctx *ctx;
	int i;

	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
	if (!ctx)
		return NULL;

	if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, 0, GFP_KERNEL)) {
		kfree(ctx);
		return NULL;
	}

	ctx->flags = p->flags;
	init_waitqueue_head(&ctx->cq_wait);
	init_completion(&ctx->ctx_done);
	mutex_init(&ctx->uring_lock);
	init_waitqueue_head(&ctx->wait);
	for (i = 0; i < ARRAY_SIZE(ctx->pending_async); i++) {
		spin_lock_init(&ctx->pending_async[i].lock);
		INIT_LIST_HEAD(&ctx->pending_async[i].list);
		atomic_set(&ctx->pending_async[i].cnt, 0);
	}
	spin_lock_init(&ctx->completion_lock);
	INIT_LIST_HEAD(&ctx->poll_list);
	INIT_LIST_HEAD(&ctx->cancel_list);
	INIT_LIST_HEAD(&ctx->defer_list);
	return ctx;
}

static inline bool io_sequence_defer(struct io_ring_ctx *ctx,
				     struct io_kiocb *req)
{
	if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
		return false;

	return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped;
}

static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
{
	struct io_kiocb *req;

	if (list_empty(&ctx->defer_list))
		return NULL;

	req = list_first_entry(&ctx->defer_list, struct io_kiocb, list);
	if (!io_sequence_defer(ctx, req)) {
		list_del_init(&req->list);
		return req;
	}

	return NULL;
}

static void __io_commit_cqring(struct io_ring_ctx *ctx)
{
	struct io_cq_ring *ring = ctx->cq_ring;

	if (ctx->cached_cq_tail != READ_ONCE(ring->r.tail)) {
		/* order cqe stores with ring update */
		smp_store_release(&ring->r.tail, ctx->cached_cq_tail);

		if (wq_has_sleeper(&ctx->cq_wait)) {
			wake_up_interruptible(&ctx->cq_wait);
			kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
		}
	}
}

static void io_commit_cqring(struct io_ring_ctx *ctx)
{
	struct io_kiocb *req;

	__io_commit_cqring(ctx);

	while ((req = io_get_deferred_req(ctx)) != NULL) {
		req->flags |= REQ_F_IO_DRAINED;
		queue_work(ctx->sqo_wq, &req->work);
	}
}

static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
{
	struct io_cq_ring *ring = ctx->cq_ring;
	unsigned tail;

	tail = ctx->cached_cq_tail;
	/*
	 * writes to the cq entry need to come after reading head; the
	 * control dependency is enough as we're using WRITE_ONCE to
	 * fill the cq entry
	 */
	if (tail - READ_ONCE(ring->r.head) == ring->ring_entries)
		return NULL;

	ctx->cached_cq_tail++;
	return &ring->cqes[tail & ctx->cq_mask];
}

static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
				 long res)
{
	struct io_uring_cqe *cqe;

	/*
	 * If we can't get a cq entry, userspace overflowed the
	 * submission (by quite a lot). Increment the overflow count in
	 * the ring.
	 */
	cqe = io_get_cqring(ctx);
	if (cqe) {
		WRITE_ONCE(cqe->user_data, ki_user_data);
		WRITE_ONCE(cqe->res, res);
		WRITE_ONCE(cqe->flags, 0);
	} else {
		unsigned overflow = READ_ONCE(ctx->cq_ring->overflow);

		WRITE_ONCE(ctx->cq_ring->overflow, overflow + 1);
	}
}

static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
{
	if (waitqueue_active(&ctx->wait))
		wake_up(&ctx->wait);
	if (waitqueue_active(&ctx->sqo_wait))
		wake_up(&ctx->sqo_wait);
	if (ctx->cq_ev_fd)
		eventfd_signal(ctx->cq_ev_fd, 1);
}

static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data,
				long res)
{
	unsigned long flags;

	spin_lock_irqsave(&ctx->completion_lock, flags);
	io_cqring_fill_event(ctx, user_data, res);
	io_commit_cqring(ctx);
	spin_unlock_irqrestore(&ctx->completion_lock, flags);

	io_cqring_ev_posted(ctx);
}

static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs)
{
	percpu_ref_put_many(&ctx->refs, refs);

	if (waitqueue_active(&ctx->wait))
		wake_up(&ctx->wait);
}

static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
				   struct io_submit_state *state)
{
	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
	struct io_kiocb *req;

	if (!percpu_ref_tryget(&ctx->refs))
		return NULL;

	if (!state) {
		req = kmem_cache_alloc(req_cachep, gfp);
		if (unlikely(!req))
			goto out;
	} else if (!state->free_reqs) {
		size_t sz;
		int ret;

		sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs));
		ret = kmem_cache_alloc_bulk(req_cachep, gfp, sz, state->reqs);

		/*
		 * Bulk alloc is all-or-nothing. If we fail to get a batch,
		 * retry single alloc to be on the safe side.
		 */
		if (unlikely(ret <= 0)) {
			state->reqs[0] = kmem_cache_alloc(req_cachep, gfp);
			if (!state->reqs[0])
				goto out;
			ret = 1;
		}
		state->free_reqs = ret - 1;
		state->cur_req = 1;
		req = state->reqs[0];
	} else {
		req = state->reqs[state->cur_req];
		state->free_reqs--;
		state->cur_req++;
	}

	req->file = NULL;
	req->ctx = ctx;
	req->flags = 0;
	/* one is dropped after submission, the other at completion */
	refcount_set(&req->refs, 2);
	return req;
out:
	io_ring_drop_ctx_refs(ctx, 1);
	return NULL;
}

static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
{
	if (*nr) {
		kmem_cache_free_bulk(req_cachep, *nr, reqs);
		io_ring_drop_ctx_refs(ctx, *nr);
		*nr = 0;
	}
}

static void io_free_req(struct io_kiocb *req)
{
	if (req->file && !(req->flags & REQ_F_FIXED_FILE))
		fput(req->file);
	io_ring_drop_ctx_refs(req->ctx, 1);
	kmem_cache_free(req_cachep, req);
}

static void io_put_req(struct io_kiocb *req)
{
	if (refcount_dec_and_test(&req->refs))
		io_free_req(req);
}

/*
 * Find and free completed poll iocbs
 */
static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
			       struct list_head *done)
{
	void *reqs[IO_IOPOLL_BATCH];
	struct io_kiocb *req;
	int to_free;

	to_free = 0;
	while (!list_empty(done)) {
		req = list_first_entry(done, struct io_kiocb, list);
		list_del(&req->list);

		io_cqring_fill_event(ctx, req->user_data, req->error);
		(*nr_events)++;

		if (refcount_dec_and_test(&req->refs)) {
			/* If we're not using fixed files, we have to pair the
			 * completion part with the file put. Use regular
			 * completions for those, only batch free for fixed
			 * file.
			 */
			if (req->flags & REQ_F_FIXED_FILE) {
				reqs[to_free++] = req;
				if (to_free == ARRAY_SIZE(reqs))
					io_free_req_many(ctx, reqs, &to_free);
			} else {
				io_free_req(req);
			}
		}
	}

	io_commit_cqring(ctx);
	io_free_req_many(ctx, reqs, &to_free);
}

static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
			long min)
{
	struct io_kiocb *req, *tmp;
	LIST_HEAD(done);
	bool spin;
	int ret;

	/*
	 * Only spin for completions if we don't have multiple devices hanging
	 * off our complete list, and we're under the requested amount.
	 */
	spin = !ctx->poll_multi_file && *nr_events < min;

	ret = 0;
	list_for_each_entry_safe(req, tmp, &ctx->poll_list, list) {
		struct kiocb *kiocb = &req->rw;

		/*
		 * Move completed entries to our local list. If we find a
		 * request that requires polling, break out and complete
		 * the done list first, if we have entries there.
		 */
		if (req->flags & REQ_F_IOPOLL_COMPLETED) {
			list_move_tail(&req->list, &done);
			continue;
		}
		if (!list_empty(&done))
			break;

		ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
		if (ret < 0)
			break;

		if (ret && spin)
			spin = false;
		ret = 0;
	}

	if (!list_empty(&done))
		io_iopoll_complete(ctx, nr_events, &done);

	return ret;
}

/*
 * Poll for a mininum of 'min' events. Note that if min == 0 we consider that a
 * non-spinning poll check - we'll still enter the driver poll loop, but only
 * as a non-spinning completion check.
 */
static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
				long min)
{
	while (!list_empty(&ctx->poll_list)) {
		int ret;

		ret = io_do_iopoll(ctx, nr_events, min);
		if (ret < 0)
			return ret;
		if (!min || *nr_events >= min)
			return 0;
	}

	return 1;
}

/*
 * We can't just wait for polled events to come to us, we have to actively
 * find and complete them.
 */
static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
{
	if (!(ctx->flags & IORING_SETUP_IOPOLL))
		return;

	mutex_lock(&ctx->uring_lock);
	while (!list_empty(&ctx->poll_list)) {
		unsigned int nr_events = 0;

		io_iopoll_getevents(ctx, &nr_events, 1);
	}
	mutex_unlock(&ctx->uring_lock);
}

static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
			   long min)
{
	int ret = 0;

	do {
		int tmin = 0;

		if (*nr_events < min)
			tmin = min - *nr_events;

		ret = io_iopoll_getevents(ctx, nr_events, tmin);
		if (ret <= 0)
			break;
		ret = 0;
	} while (min && !*nr_events && !need_resched());

	return ret;
}

static void kiocb_end_write(struct kiocb *kiocb)
{
	if (kiocb->ki_flags & IOCB_WRITE) {
		struct inode *inode = file_inode(kiocb->ki_filp);

		/*
		 * Tell lockdep we inherited freeze protection from submission
		 * thread.
		 */
		if (S_ISREG(inode->i_mode))
			__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
		file_end_write(kiocb->ki_filp);
	}
}

static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
{
	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);

	kiocb_end_write(kiocb);

	io_cqring_add_event(req->ctx, req->user_data, res);
	io_put_req(req);
}

static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
{
	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);

	kiocb_end_write(kiocb);

	req->error = res;
	if (res != -EAGAIN)
		req->flags |= REQ_F_IOPOLL_COMPLETED;
}

/*
 * After the iocb has been issued, it's safe to be found on the poll list.
 * Adding the kiocb to the list AFTER submission ensures that we don't
 * find it from a io_iopoll_getevents() thread before the issuer is done
 * accessing the kiocb cookie.
 */
static void io_iopoll_req_issued(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;

	/*
	 * Track whether we have multiple files in our lists. This will impact
	 * how we do polling eventually, not spinning if we're on potentially
	 * different devices.
	 */
	if (list_empty(&ctx->poll_list)) {
		ctx->poll_multi_file = false;
	} else if (!ctx->poll_multi_file) {
		struct io_kiocb *list_req;

		list_req = list_first_entry(&ctx->poll_list, struct io_kiocb,
						list);
		if (list_req->rw.ki_filp != req->rw.ki_filp)
			ctx->poll_multi_file = true;
	}

	/*
	 * For fast devices, IO may have already completed. If it has, add
	 * it to the front so we find it first.
	 */
	if (req->flags & REQ_F_IOPOLL_COMPLETED)
		list_add(&req->list, &ctx->poll_list);
	else
		list_add_tail(&req->list, &ctx->poll_list);
}

static void io_file_put(struct io_submit_state *state)
{
	if (state->file) {
		int diff = state->has_refs - state->used_refs;

		if (diff)
			fput_many(state->file, diff);
		state->file = NULL;
	}
}

/*
 * Get as many references to a file as we have IOs left in this submission,
 * assuming most submissions are for one file, or at least that each file
 * has more than one submission.
 */
static struct file *io_file_get(struct io_submit_state *state, int fd)
{
	if (!state)
		return fget(fd);

	if (state->file) {
		if (state->fd == fd) {
			state->used_refs++;
			state->ios_left--;
			return state->file;
		}
		io_file_put(state);
	}
	state->file = fget_many(fd, state->ios_left);
	if (!state->file)
		return NULL;

	state->fd = fd;
	state->has_refs = state->ios_left;
	state->used_refs = 1;
	state->ios_left--;
	return state->file;
}

/*
 * If we tracked the file through the SCM inflight mechanism, we could support
 * any file. For now, just ensure that anything potentially problematic is done
 * inline.
 */
static bool io_file_supports_async(struct file *file)
{
	umode_t mode = file_inode(file)->i_mode;

	if (S_ISBLK(mode) || S_ISCHR(mode))
		return true;
	if (S_ISREG(mode) && file->f_op != &io_uring_fops)
		return true;

	return false;
}

static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
		      bool force_nonblock)
{
	const struct io_uring_sqe *sqe = s->sqe;
	struct io_ring_ctx *ctx = req->ctx;
	struct kiocb *kiocb = &req->rw;
	unsigned ioprio;
	int ret;

	if (!req->file)
		return -EBADF;

	if (force_nonblock && !io_file_supports_async(req->file))
		force_nonblock = false;

	kiocb->ki_pos = READ_ONCE(sqe->off);
	kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
	kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));

	ioprio = READ_ONCE(sqe->ioprio);
	if (ioprio) {
		ret = ioprio_check_cap(ioprio);
		if (ret)
			return ret;

		kiocb->ki_ioprio = ioprio;
	} else
		kiocb->ki_ioprio = get_current_ioprio();

	ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
	if (unlikely(ret))
		return ret;

	/* don't allow async punt if RWF_NOWAIT was requested */
	if (kiocb->ki_flags & IOCB_NOWAIT)
		req->flags |= REQ_F_NOWAIT;

	if (force_nonblock)
		kiocb->ki_flags |= IOCB_NOWAIT;

	if (ctx->flags & IORING_SETUP_IOPOLL) {
		if (!(kiocb->ki_flags & IOCB_DIRECT) ||
		    !kiocb->ki_filp->f_op->iopoll)
			return -EOPNOTSUPP;

		req->error = 0;
		kiocb->ki_flags |= IOCB_HIPRI;
		kiocb->ki_complete = io_complete_rw_iopoll;
	} else {
		if (kiocb->ki_flags & IOCB_HIPRI)
			return -EINVAL;
		kiocb->ki_complete = io_complete_rw;
	}
	return 0;
}

static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
{
	switch (ret) {
	case -EIOCBQUEUED:
		break;
	case -ERESTARTSYS:
	case -ERESTARTNOINTR:
	case -ERESTARTNOHAND:
	case -ERESTART_RESTARTBLOCK:
		/*
		 * We can't just restart the syscall, since previously
		 * submitted sqes may already be in progress. Just fail this
		 * IO with EINTR.
		 */
		ret = -EINTR;
		/* fall through */
	default:
		kiocb->ki_complete(kiocb, ret, 0);
	}
}

static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
			   const struct io_uring_sqe *sqe,
			   struct iov_iter *iter)
{
	size_t len = READ_ONCE(sqe->len);
	struct io_mapped_ubuf *imu;
	unsigned index, buf_index;
	size_t offset;
	u64 buf_addr;

	/* attempt to use fixed buffers without having provided iovecs */
	if (unlikely(!ctx->user_bufs))
		return -EFAULT;

	buf_index = READ_ONCE(sqe->buf_index);
	if (unlikely(buf_index >= ctx->nr_user_bufs))
		return -EFAULT;

	index = array_index_nospec(buf_index, ctx->nr_user_bufs);
	imu = &ctx->user_bufs[index];
	buf_addr = READ_ONCE(sqe->addr);

	/* overflow */
	if (buf_addr + len < buf_addr)
		return -EFAULT;
	/* not inside the mapped region */
	if (buf_addr < imu->ubuf || buf_addr + len > imu->ubuf + imu->len)
		return -EFAULT;

	/*
	 * May not be a start of buffer, set size appropriately
	 * and advance us to the beginning.
	 */
	offset = buf_addr - imu->ubuf;
	iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len);
	if (offset)
		iov_iter_advance(iter, offset);
	return 0;
}

static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
			   const struct sqe_submit *s, struct iovec **iovec,
			   struct iov_iter *iter)
{
	const struct io_uring_sqe *sqe = s->sqe;
	void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
	size_t sqe_len = READ_ONCE(sqe->len);
	u8 opcode;

	/*
	 * We're reading ->opcode for the second time, but the first read
	 * doesn't care whether it's _FIXED or not, so it doesn't matter
	 * whether ->opcode changes concurrently. The first read does care
	 * about whether it is a READ or a WRITE, so we don't trust this read
	 * for that purpose and instead let the caller pass in the read/write
	 * flag.
	 */
	opcode = READ_ONCE(sqe->opcode);
	if (opcode == IORING_OP_READ_FIXED ||
	    opcode == IORING_OP_WRITE_FIXED) {
		int ret = io_import_fixed(ctx, rw, sqe, iter);
		*iovec = NULL;
		return ret;
	}

	if (!s->has_user)
		return -EFAULT;

#ifdef CONFIG_COMPAT
	if (ctx->compat)
		return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
						iovec, iter);
#endif

	return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
}

/*
 * Make a note of the last file/offset/direction we punted to async
 * context. We'll use this information to see if we can piggy back a
 * sequential request onto the previous one, if it's still hasn't been
 * completed by the async worker.
 */
static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
{
	struct async_list *async_list = &req->ctx->pending_async[rw];
	struct kiocb *kiocb = &req->rw;
	struct file *filp = kiocb->ki_filp;
	off_t io_end = kiocb->ki_pos + len;

	if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) {
		unsigned long max_pages;

		/* Use 8x RA size as a decent limiter for both reads/writes */
		max_pages = filp->f_ra.ra_pages;
		if (!max_pages)
			max_pages = VM_READAHEAD_PAGES;
		max_pages *= 8;

		/* If max pages are exceeded, reset the state */
		len >>= PAGE_SHIFT;
		if (async_list->io_pages + len <= max_pages) {
			req->flags |= REQ_F_SEQ_PREV;
			async_list->io_pages += len;
		} else {
			io_end = 0;
			async_list->io_pages = 0;
		}
	}

	/* New file? Reset state. */
	if (async_list->file != filp) {
		async_list->io_pages = 0;
		async_list->file = filp;
	}
	async_list->io_end = io_end;
}

static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
		   bool force_nonblock)
{
	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
	struct kiocb *kiocb = &req->rw;
	struct iov_iter iter;
	struct file *file;
	size_t iov_count;
	int ret;

	ret = io_prep_rw(req, s, force_nonblock);
	if (ret)
		return ret;
	file = kiocb->ki_filp;

	if (unlikely(!(file->f_mode & FMODE_READ)))
		return -EBADF;
	if (unlikely(!file->f_op->read_iter))
		return -EINVAL;

	ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter);
	if (ret)
		return ret;

	iov_count = iov_iter_count(&iter);
	ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count);
	if (!ret) {
		ssize_t ret2;

		/* Catch -EAGAIN return for forced non-blocking submission */
		ret2 = call_read_iter(file, kiocb, &iter);
		if (!force_nonblock || ret2 != -EAGAIN) {
			io_rw_done(kiocb, ret2);
		} else {
			/*
			 * If ->needs_lock is true, we're already in async
			 * context.
			 */
			if (!s->needs_lock)
				io_async_list_note(READ, req, iov_count);
			ret = -EAGAIN;
		}
	}
	kfree(iovec);
	return ret;
}

static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
		    bool force_nonblock)
{
	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
	struct kiocb *kiocb = &req->rw;
	struct iov_iter iter;
	struct file *file;
	size_t iov_count;
	int ret;

	ret = io_prep_rw(req, s, force_nonblock);
	if (ret)
		return ret;

	file = kiocb->ki_filp;
	if (unlikely(!(file->f_mode & FMODE_WRITE)))
		return -EBADF;
	if (unlikely(!file->f_op->write_iter))
		return -EINVAL;

	ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter);
	if (ret)
		return ret;

	iov_count = iov_iter_count(&iter);

	ret = -EAGAIN;
	if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) {
		/* If ->needs_lock is true, we're already in async context. */
		if (!s->needs_lock)
			io_async_list_note(WRITE, req, iov_count);
		goto out_free;
	}

	ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count);
	if (!ret) {
		ssize_t ret2;

		/*
		 * Open-code file_start_write here to grab freeze protection,
		 * which will be released by another thread in
		 * io_complete_rw().  Fool lockdep by telling it the lock got
		 * released so that it doesn't complain about the held lock when
		 * we return to userspace.
		 */
		if (S_ISREG(file_inode(file)->i_mode)) {
			__sb_start_write(file_inode(file)->i_sb,
						SB_FREEZE_WRITE, true);
			__sb_writers_release(file_inode(file)->i_sb,
						SB_FREEZE_WRITE);
		}
		kiocb->ki_flags |= IOCB_WRITE;

		ret2 = call_write_iter(file, kiocb, &iter);
		if (!force_nonblock || ret2 != -EAGAIN) {
			io_rw_done(kiocb, ret2);
		} else {
			/*
			 * If ->needs_lock is true, we're already in async
			 * context.
			 */
			if (!s->needs_lock)
				io_async_list_note(WRITE, req, iov_count);
			ret = -EAGAIN;
		}
	}
out_free:
	kfree(iovec);
	return ret;
}

/*
 * IORING_OP_NOP just posts a completion event, nothing else.
 */
static int io_nop(struct io_kiocb *req, u64 user_data)
{
	struct io_ring_ctx *ctx = req->ctx;
	long err = 0;

	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	io_cqring_add_event(ctx, user_data, err);
	io_put_req(req);
	return 0;
}

static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_ring_ctx *ctx = req->ctx;

	if (!req->file)
		return -EBADF;

	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index))
		return -EINVAL;

	return 0;
}

static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
		    bool force_nonblock)
{
	loff_t sqe_off = READ_ONCE(sqe->off);
	loff_t sqe_len = READ_ONCE(sqe->len);
	loff_t end = sqe_off + sqe_len;
	unsigned fsync_flags;
	int ret;

	fsync_flags = READ_ONCE(sqe->fsync_flags);
	if (unlikely(fsync_flags & ~IORING_FSYNC_DATASYNC))
		return -EINVAL;

	ret = io_prep_fsync(req, sqe);
	if (ret)
		return ret;

	/* fsync always requires a blocking context */
	if (force_nonblock)
		return -EAGAIN;

	ret = vfs_fsync_range(req->rw.ki_filp, sqe_off,
				end > 0 ? end : LLONG_MAX,
				fsync_flags & IORING_FSYNC_DATASYNC);

	io_cqring_add_event(req->ctx, sqe->user_data, ret);
	io_put_req(req);
	return 0;
}

static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_ring_ctx *ctx = req->ctx;
	int ret = 0;

	if (!req->file)
		return -EBADF;

	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index))
		return -EINVAL;

	return ret;
}

static int io_sync_file_range(struct io_kiocb *req,
			      const struct io_uring_sqe *sqe,
			      bool force_nonblock)
{
	loff_t sqe_off;
	loff_t sqe_len;
	unsigned flags;
	int ret;

	ret = io_prep_sfr(req, sqe);
	if (ret)
		return ret;

	/* sync_file_range always requires a blocking context */
	if (force_nonblock)
		return -EAGAIN;

	sqe_off = READ_ONCE(sqe->off);
	sqe_len = READ_ONCE(sqe->len);
	flags = READ_ONCE(sqe->sync_range_flags);

	ret = sync_file_range(req->rw.ki_filp, sqe_off, sqe_len, flags);

	io_cqring_add_event(req->ctx, sqe->user_data, ret);
	io_put_req(req);
	return 0;
}

static void io_poll_remove_one(struct io_kiocb *req)
{
	struct io_poll_iocb *poll = &req->poll;

	spin_lock(&poll->head->lock);
	WRITE_ONCE(poll->canceled, true);
	if (!list_empty(&poll->wait.entry)) {
		list_del_init(&poll->wait.entry);
		queue_work(req->ctx->sqo_wq, &req->work);
	}
	spin_unlock(&poll->head->lock);

	list_del_init(&req->list);
}

static void io_poll_remove_all(struct io_ring_ctx *ctx)
{
	struct io_kiocb *req;

	spin_lock_irq(&ctx->completion_lock);
	while (!list_empty(&ctx->cancel_list)) {
		req = list_first_entry(&ctx->cancel_list, struct io_kiocb,list);
		io_poll_remove_one(req);
	}
	spin_unlock_irq(&ctx->completion_lock);
}

/*
 * Find a running poll command that matches one specified in sqe->addr,
 * and remove it if found.
 */
static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_kiocb *poll_req, *next;
	int ret = -ENOENT;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index ||
	    sqe->poll_events)
		return -EINVAL;

	spin_lock_irq(&ctx->completion_lock);
	list_for_each_entry_safe(poll_req, next, &ctx->cancel_list, list) {
		if (READ_ONCE(sqe->addr) == poll_req->user_data) {
			io_poll_remove_one(poll_req);
			ret = 0;
			break;
		}
	}
	spin_unlock_irq(&ctx->completion_lock);

	io_cqring_add_event(req->ctx, sqe->user_data, ret);
	io_put_req(req);
	return 0;
}

static void io_poll_complete(struct io_ring_ctx *ctx, struct io_kiocb *req,
			     __poll_t mask)
{
	req->poll.done = true;
	io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask));
	io_commit_cqring(ctx);
}

static void io_poll_complete_work(struct work_struct *work)
{
	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
	struct io_poll_iocb *poll = &req->poll;
	struct poll_table_struct pt = { ._key = poll->events };
	struct io_ring_ctx *ctx = req->ctx;
	__poll_t mask = 0;

	if (!READ_ONCE(poll->canceled))
		mask = vfs_poll(poll->file, &pt) & poll->events;

	/*
	 * Note that ->ki_cancel callers also delete iocb from active_reqs after
	 * calling ->ki_cancel.  We need the ctx_lock roundtrip here to
	 * synchronize with them.  In the cancellation case the list_del_init
	 * itself is not actually needed, but harmless so we keep it in to
	 * avoid further branches in the fast path.
	 */
	spin_lock_irq(&ctx->completion_lock);
	if (!mask && !READ_ONCE(poll->canceled)) {
		add_wait_queue(poll->head, &poll->wait);
		spin_unlock_irq(&ctx->completion_lock);
		return;
	}
	list_del_init(&req->list);
	io_poll_complete(ctx, req, mask);
	spin_unlock_irq(&ctx->completion_lock);

	io_cqring_ev_posted(ctx);
	io_put_req(req);
}

static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
			void *key)
{
	struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb,
							wait);
	struct io_kiocb *req = container_of(poll, struct io_kiocb, poll);
	struct io_ring_ctx *ctx = req->ctx;
	__poll_t mask = key_to_poll(key);
	unsigned long flags;

	/* for instances that support it check for an event match first: */
	if (mask && !(mask & poll->events))
		return 0;

	list_del_init(&poll->wait.entry);

	if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) {
		list_del(&req->list);
		io_poll_complete(ctx, req, mask);
		spin_unlock_irqrestore(&ctx->completion_lock, flags);

		io_cqring_ev_posted(ctx);
		io_put_req(req);
	} else {
		queue_work(ctx->sqo_wq, &req->work);
	}

	return 1;
}

struct io_poll_table {
	struct poll_table_struct pt;
	struct io_kiocb *req;
	int error;
};

static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
			       struct poll_table_struct *p)
{
	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);

	if (unlikely(pt->req->poll.head)) {
		pt->error = -EINVAL;
		return;
	}

	pt->error = 0;
	pt->req->poll.head = head;
	add_wait_queue(head, &pt->req->poll.wait);
}

static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_poll_iocb *poll = &req->poll;
	struct io_ring_ctx *ctx = req->ctx;
	struct io_poll_table ipt;
	bool cancel = false;
	__poll_t mask;
	u16 events;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index)
		return -EINVAL;
	if (!poll->file)
		return -EBADF;

	INIT_WORK(&req->work, io_poll_complete_work);
	events = READ_ONCE(sqe->poll_events);
	poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;

	poll->head = NULL;
	poll->done = false;
	poll->canceled = false;

	ipt.pt._qproc = io_poll_queue_proc;
	ipt.pt._key = poll->events;
	ipt.req = req;
	ipt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */

	/* initialized the list so that we can do list_empty checks */
	INIT_LIST_HEAD(&poll->wait.entry);
	init_waitqueue_func_entry(&poll->wait, io_poll_wake);

	mask = vfs_poll(poll->file, &ipt.pt) & poll->events;

	spin_lock_irq(&ctx->completion_lock);
	if (likely(poll->head)) {
		spin_lock(&poll->head->lock);
		if (unlikely(list_empty(&poll->wait.entry))) {
			if (ipt.error)
				cancel = true;
			ipt.error = 0;
			mask = 0;
		}
		if (mask || ipt.error)
			list_del_init(&poll->wait.entry);
		else if (cancel)
			WRITE_ONCE(poll->canceled, true);
		else if (!poll->done) /* actually waiting for an event */
			list_add_tail(&req->list, &ctx->cancel_list);
		spin_unlock(&poll->head->lock);
	}
	if (mask) { /* no async, we'd stolen it */
		ipt.error = 0;
		io_poll_complete(ctx, req, mask);
	}
	spin_unlock_irq(&ctx->completion_lock);

	if (mask) {
		io_cqring_ev_posted(ctx);
		io_put_req(req);
	}
	return ipt.error;
}

static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req,
			const struct io_uring_sqe *sqe)
{
	struct io_uring_sqe *sqe_copy;

	if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list))
		return 0;

	sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
	if (!sqe_copy)
		return -EAGAIN;

	spin_lock_irq(&ctx->completion_lock);
	if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) {
		spin_unlock_irq(&ctx->completion_lock);
		kfree(sqe_copy);
		return 0;
	}

	memcpy(sqe_copy, sqe, sizeof(*sqe_copy));
	req->submit.sqe = sqe_copy;

	INIT_WORK(&req->work, io_sq_wq_submit_work);
	list_add_tail(&req->list, &ctx->defer_list);
	spin_unlock_irq(&ctx->completion_lock);
	return -EIOCBQUEUED;
}

static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
			   const struct sqe_submit *s, bool force_nonblock)
{
	int ret, opcode;

	if (unlikely(s->index >= ctx->sq_entries))
		return -EINVAL;
	req->user_data = READ_ONCE(s->sqe->user_data);

	opcode = READ_ONCE(s->sqe->opcode);
	switch (opcode) {
	case IORING_OP_NOP:
		ret = io_nop(req, req->user_data);
		break;
	case IORING_OP_READV:
		if (unlikely(s->sqe->buf_index))
			return -EINVAL;
		ret = io_read(req, s, force_nonblock);
		break;
	case IORING_OP_WRITEV:
		if (unlikely(s->sqe->buf_index))
			return -EINVAL;
		ret = io_write(req, s, force_nonblock);
		break;
	case IORING_OP_READ_FIXED:
		ret = io_read(req, s, force_nonblock);
		break;
	case IORING_OP_WRITE_FIXED:
		ret = io_write(req, s, force_nonblock);
		break;
	case IORING_OP_FSYNC:
		ret = io_fsync(req, s->sqe, force_nonblock);
		break;
	case IORING_OP_POLL_ADD:
		ret = io_poll_add(req, s->sqe);
		break;
	case IORING_OP_POLL_REMOVE:
		ret = io_poll_remove(req, s->sqe);
		break;
	case IORING_OP_SYNC_FILE_RANGE:
		ret = io_sync_file_range(req, s->sqe, force_nonblock);
		break;
	default:
		ret = -EINVAL;
		break;
	}

	if (ret)
		return ret;

	if (ctx->flags & IORING_SETUP_IOPOLL) {
		if (req->error == -EAGAIN)
			return -EAGAIN;

		/* workqueue context doesn't hold uring_lock, grab it now */
		if (s->needs_lock)
			mutex_lock(&ctx->uring_lock);
		io_iopoll_req_issued(req);
		if (s->needs_lock)
			mutex_unlock(&ctx->uring_lock);
	}

	return 0;
}

static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx,
						 const struct io_uring_sqe *sqe)
{
	switch (sqe->opcode) {
	case IORING_OP_READV:
	case IORING_OP_READ_FIXED:
		return &ctx->pending_async[READ];
	case IORING_OP_WRITEV:
	case IORING_OP_WRITE_FIXED:
		return &ctx->pending_async[WRITE];
	default:
		return NULL;
	}
}

static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe)
{
	u8 opcode = READ_ONCE(sqe->opcode);

	return !(opcode == IORING_OP_READ_FIXED ||
		 opcode == IORING_OP_WRITE_FIXED);
}

static void io_sq_wq_submit_work(struct work_struct *work)
{
	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
	struct io_ring_ctx *ctx = req->ctx;
	struct mm_struct *cur_mm = NULL;
	struct async_list *async_list;
	LIST_HEAD(req_list);
	mm_segment_t old_fs;
	int ret;

	async_list = io_async_list_from_sqe(ctx, req->submit.sqe);
restart:
	do {
		struct sqe_submit *s = &req->submit;
		const struct io_uring_sqe *sqe = s->sqe;

		/* Ensure we clear previously set non-block flag */
		req->rw.ki_flags &= ~IOCB_NOWAIT;

		ret = 0;
		if (io_sqe_needs_user(sqe) && !cur_mm) {
			if (!mmget_not_zero(ctx->sqo_mm)) {
				ret = -EFAULT;
			} else {
				cur_mm = ctx->sqo_mm;
				use_mm(cur_mm);
				old_fs = get_fs();
				set_fs(USER_DS);
			}
		}

		if (!ret) {
			s->has_user = cur_mm != NULL;
			s->needs_lock = true;
			do {
				ret = __io_submit_sqe(ctx, req, s, false);
				/*
				 * We can get EAGAIN for polled IO even though
				 * we're forcing a sync submission from here,
				 * since we can't wait for request slots on the
				 * block side.
				 */
				if (ret != -EAGAIN)
					break;
				cond_resched();
			} while (1);
		}

		/* drop submission reference */
		io_put_req(req);

		if (ret) {
			io_cqring_add_event(ctx, sqe->user_data, ret);
			io_put_req(req);
		}

		/* async context always use a copy of the sqe */
		kfree(sqe);

		if (!async_list)
			break;
		if (!list_empty(&req_list)) {
			req = list_first_entry(&req_list, struct io_kiocb,
						list);
			list_del(&req->list);
			continue;
		}
		if (list_empty(&async_list->list))
			break;

		req = NULL;
		spin_lock(&async_list->lock);
		if (list_empty(&async_list->list)) {
			spin_unlock(&async_list->lock);
			break;
		}
		list_splice_init(&async_list->list, &req_list);
		spin_unlock(&async_list->lock);

		req = list_first_entry(&req_list, struct io_kiocb, list);
		list_del(&req->list);
	} while (req);

	/*
	 * Rare case of racing with a submitter. If we find the count has
	 * dropped to zero AND we have pending work items, then restart
	 * the processing. This is a tiny race window.
	 */
	if (async_list) {
		ret = atomic_dec_return(&async_list->cnt);
		while (!ret && !list_empty(&async_list->list)) {
			spin_lock(&async_list->lock);
			atomic_inc(&async_list->cnt);
			list_splice_init(&async_list->list, &req_list);
			spin_unlock(&async_list->lock);

			if (!list_empty(&req_list)) {
				req = list_first_entry(&req_list,
							struct io_kiocb, list);
				list_del(&req->list);
				goto restart;
			}
			ret = atomic_dec_return(&async_list->cnt);
		}
	}

	if (cur_mm) {
		set_fs(old_fs);
		unuse_mm(cur_mm);
		mmput(cur_mm);
	}
}

/*
 * See if we can piggy back onto previously submitted work, that is still
 * running. We currently only allow this if the new request is sequential
 * to the previous one we punted.
 */
static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req)
{
	bool ret = false;

	if (!list)
		return false;
	if (!(req->flags & REQ_F_SEQ_PREV))
		return false;
	if (!atomic_read(&list->cnt))
		return false;

	ret = true;
	spin_lock(&list->lock);
	list_add_tail(&req->list, &list->list);
	if (!atomic_read(&list->cnt)) {
		list_del_init(&req->list);
		ret = false;
	}
	spin_unlock(&list->lock);
	return ret;
}

static bool io_op_needs_file(const struct io_uring_sqe *sqe)
{
	int op = READ_ONCE(sqe->opcode);

	switch (op) {
	case IORING_OP_NOP:
	case IORING_OP_POLL_REMOVE:
		return false;
	default:
		return true;
	}
}

static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
			   struct io_submit_state *state, struct io_kiocb *req)
{
	unsigned flags;
	int fd;

	flags = READ_ONCE(s->sqe->flags);
	fd = READ_ONCE(s->sqe->fd);

	if (flags & IOSQE_IO_DRAIN) {
		req->flags |= REQ_F_IO_DRAIN;
		req->sequence = ctx->cached_sq_head - 1;
	}

	if (!io_op_needs_file(s->sqe))
		return 0;

	if (flags & IOSQE_FIXED_FILE) {
		if (unlikely(!ctx->user_files ||
		    (unsigned) fd >= ctx->nr_user_files))
			return -EBADF;
		req->file = ctx->user_files[fd];
		req->flags |= REQ_F_FIXED_FILE;
	} else {
		if (s->needs_fixed_file)
			return -EBADF;
		req->file = io_file_get(state, fd);
		if (unlikely(!req->file))
			return -EBADF;
	}

	return 0;
}

static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
			 struct io_submit_state *state)
{
	struct io_kiocb *req;
	int ret;

	/* enforce forwards compatibility on users */
	if (unlikely(s->sqe->flags & ~(IOSQE_FIXED_FILE | IOSQE_IO_DRAIN)))
		return -EINVAL;

	req = io_get_req(ctx, state);
	if (unlikely(!req))
		return -EAGAIN;

	ret = io_req_set_file(ctx, s, state, req);
	if (unlikely(ret))
		goto out;

	ret = io_req_defer(ctx, req, s->sqe);
	if (ret) {
		if (ret == -EIOCBQUEUED)
			ret = 0;
		return ret;
	}

	ret = __io_submit_sqe(ctx, req, s, true);
	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
		struct io_uring_sqe *sqe_copy;

		sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
		if (sqe_copy) {
			struct async_list *list;

			memcpy(sqe_copy, s->sqe, sizeof(*sqe_copy));
			s->sqe = sqe_copy;

			memcpy(&req->submit, s, sizeof(*s));
			list = io_async_list_from_sqe(ctx, s->sqe);
			if (!io_add_to_prev_work(list, req)) {
				if (list)
					atomic_inc(&list->cnt);
				INIT_WORK(&req->work, io_sq_wq_submit_work);
				queue_work(ctx->sqo_wq, &req->work);
			}

			/*
			 * Queued up for async execution, worker will release
			 * submit reference when the iocb is actually
			 * submitted.
			 */
			return 0;
		}
	}

out:
	/* drop submission reference */
	io_put_req(req);

	/* and drop final reference, if we failed */
	if (ret)
		io_put_req(req);

	return ret;
}

/*
 * Batched submission is done, ensure local IO is flushed out.
 */
static void io_submit_state_end(struct io_submit_state *state)
{
	blk_finish_plug(&state->plug);
	io_file_put(state);
	if (state->free_reqs)
		kmem_cache_free_bulk(req_cachep, state->free_reqs,
					&state->reqs[state->cur_req]);
}

/*
 * Start submission side cache.
 */
static void io_submit_state_start(struct io_submit_state *state,
				  struct io_ring_ctx *ctx, unsigned max_ios)
{
	blk_start_plug(&state->plug);
	state->free_reqs = 0;
	state->file = NULL;
	state->ios_left = max_ios;
}

static void io_commit_sqring(struct io_ring_ctx *ctx)
{
	struct io_sq_ring *ring = ctx->sq_ring;

	if (ctx->cached_sq_head != READ_ONCE(ring->r.head)) {
		/*
		 * Ensure any loads from the SQEs are done at this point,
		 * since once we write the new head, the application could
		 * write new data to them.
		 */
		smp_store_release(&ring->r.head, ctx->cached_sq_head);
	}
}

/*
 * Fetch an sqe, if one is available. Note that s->sqe will point to memory
 * that is mapped by userspace. This means that care needs to be taken to
 * ensure that reads are stable, as we cannot rely on userspace always
 * being a good citizen. If members of the sqe are validated and then later
 * used, it's important that those reads are done through READ_ONCE() to
 * prevent a re-load down the line.
 */
static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
{
	struct io_sq_ring *ring = ctx->sq_ring;
	unsigned head;

	/*
	 * The cached sq head (or cq tail) serves two purposes:
	 *
	 * 1) allows us to batch the cost of updating the user visible
	 *    head updates.
	 * 2) allows the kernel side to track the head on its own, even
	 *    though the application is the one updating it.
	 */
	head = ctx->cached_sq_head;
	/* make sure SQ entry isn't read before tail */
	if (head == smp_load_acquire(&ring->r.tail))
		return false;

	head = READ_ONCE(ring->array[head & ctx->sq_mask]);
	if (head < ctx->sq_entries) {
		s->index = head;
		s->sqe = &ctx->sq_sqes[head];
		ctx->cached_sq_head++;
		return true;
	}

	/* drop invalid entries */
	ctx->cached_sq_head++;
	ring->dropped++;
	return false;
}

static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
			  unsigned int nr, bool has_user, bool mm_fault)
{
	struct io_submit_state state, *statep = NULL;
	int ret, i, submitted = 0;

	if (nr > IO_PLUG_THRESHOLD) {
		io_submit_state_start(&state, ctx, nr);
		statep = &state;
	}

	for (i = 0; i < nr; i++) {
		if (unlikely(mm_fault)) {
			ret = -EFAULT;
		} else {
			sqes[i].has_user = has_user;
			sqes[i].needs_lock = true;
			sqes[i].needs_fixed_file = true;
			ret = io_submit_sqe(ctx, &sqes[i], statep);
		}
		if (!ret) {
			submitted++;
			continue;
		}

		io_cqring_add_event(ctx, sqes[i].sqe->user_data, ret);
	}

	if (statep)
		io_submit_state_end(&state);

	return submitted;
}

static int io_sq_thread(void *data)
{
	struct sqe_submit sqes[IO_IOPOLL_BATCH];
	struct io_ring_ctx *ctx = data;
	struct mm_struct *cur_mm = NULL;
	mm_segment_t old_fs;
	DEFINE_WAIT(wait);
	unsigned inflight;
	unsigned long timeout;

	old_fs = get_fs();
	set_fs(USER_DS);

	timeout = inflight = 0;
	while (!kthread_should_park()) {
		bool all_fixed, mm_fault = false;
		int i;

		if (inflight) {
			unsigned nr_events = 0;

			if (ctx->flags & IORING_SETUP_IOPOLL) {
				/*
				 * We disallow the app entering submit/complete
				 * with polling, but we still need to lock the
				 * ring to prevent racing with polled issue
				 * that got punted to a workqueue.
				 */
				mutex_lock(&ctx->uring_lock);
				io_iopoll_check(ctx, &nr_events, 0);
				mutex_unlock(&ctx->uring_lock);
			} else {
				/*
				 * Normal IO, just pretend everything completed.
				 * We don't have to poll completions for that.
				 */
				nr_events = inflight;
			}

			inflight -= nr_events;
			if (!inflight)
				timeout = jiffies + ctx->sq_thread_idle;
		}

		if (!io_get_sqring(ctx, &sqes[0])) {
			/*
			 * We're polling. If we're within the defined idle
			 * period, then let us spin without work before going
			 * to sleep.
			 */
			if (inflight || !time_after(jiffies, timeout)) {
				cpu_relax();
				continue;
			}

			/*
			 * Drop cur_mm before scheduling, we can't hold it for
			 * long periods (or over schedule()). Do this before
			 * adding ourselves to the waitqueue, as the unuse/drop
			 * may sleep.
			 */
			if (cur_mm) {
				unuse_mm(cur_mm);
				mmput(cur_mm);
				cur_mm = NULL;
			}

			prepare_to_wait(&ctx->sqo_wait, &wait,
						TASK_INTERRUPTIBLE);

			/* Tell userspace we may need a wakeup call */
			ctx->sq_ring->flags |= IORING_SQ_NEED_WAKEUP;
			/* make sure to read SQ tail after writing flags */
			smp_mb();

			if (!io_get_sqring(ctx, &sqes[0])) {
				if (kthread_should_park()) {
					finish_wait(&ctx->sqo_wait, &wait);
					break;
				}
				if (signal_pending(current))
					flush_signals(current);
				schedule();
				finish_wait(&ctx->sqo_wait, &wait);

				ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
				continue;
			}
			finish_wait(&ctx->sqo_wait, &wait);

			ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
		}

		i = 0;
		all_fixed = true;
		do {
			if (all_fixed && io_sqe_needs_user(sqes[i].sqe))
				all_fixed = false;

			i++;
			if (i == ARRAY_SIZE(sqes))
				break;
		} while (io_get_sqring(ctx, &sqes[i]));

		/* Unless all new commands are FIXED regions, grab mm */
		if (!all_fixed && !cur_mm) {
			mm_fault = !mmget_not_zero(ctx->sqo_mm);
			if (!mm_fault) {
				use_mm(ctx->sqo_mm);
				cur_mm = ctx->sqo_mm;
			}
		}

		inflight += io_submit_sqes(ctx, sqes, i, cur_mm != NULL,
						mm_fault);

		/* Commit SQ ring head once we've consumed all SQEs */
		io_commit_sqring(ctx);
	}

	set_fs(old_fs);
	if (cur_mm) {
		unuse_mm(cur_mm);
		mmput(cur_mm);
	}

	kthread_parkme();

	return 0;
}

static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
{
	struct io_submit_state state, *statep = NULL;
	int i, submit = 0;

	if (to_submit > IO_PLUG_THRESHOLD) {
		io_submit_state_start(&state, ctx, to_submit);
		statep = &state;
	}

	for (i = 0; i < to_submit; i++) {
		struct sqe_submit s;
		int ret;

		if (!io_get_sqring(ctx, &s))
			break;

		s.has_user = true;
		s.needs_lock = false;
		s.needs_fixed_file = false;
		submit++;

		ret = io_submit_sqe(ctx, &s, statep);
		if (ret)
			io_cqring_add_event(ctx, s.sqe->user_data, ret);
	}
	io_commit_sqring(ctx);

	if (statep)
		io_submit_state_end(statep);

	return submit;
}

static unsigned io_cqring_events(struct io_cq_ring *ring)
{
	/* See comment at the top of this file */
	smp_rmb();
	return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head);
}

/*
 * Wait until events become available, if we don't already have some. The
 * application must reap them itself, as they reside on the shared cq ring.
 */
static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
			  const sigset_t __user *sig, size_t sigsz)
{
	struct io_cq_ring *ring = ctx->cq_ring;
	sigset_t ksigmask, sigsaved;
	int ret;

	if (io_cqring_events(ring) >= min_events)
		return 0;

	if (sig) {
#ifdef CONFIG_COMPAT
		if (in_compat_syscall())
			ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig,
						      &ksigmask, &sigsaved, sigsz);
		else
#endif
			ret = set_user_sigmask(sig, &ksigmask,
					       &sigsaved, sigsz);

		if (ret)
			return ret;
	}

	ret = wait_event_interruptible(ctx->wait, io_cqring_events(ring) >= min_events);

	if (sig)
		restore_user_sigmask(sig, &sigsaved, ret == -ERESTARTSYS);

	if (ret == -ERESTARTSYS)
		ret = -EINTR;

	return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0;
}

static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
#if defined(CONFIG_UNIX)
	if (ctx->ring_sock) {
		struct sock *sock = ctx->ring_sock->sk;
		struct sk_buff *skb;

		while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
			kfree_skb(skb);
	}
#else
	int i;

	for (i = 0; i < ctx->nr_user_files; i++)
		fput(ctx->user_files[i]);
#endif
}

static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
	if (!ctx->user_files)
		return -ENXIO;

	__io_sqe_files_unregister(ctx);
	kfree(ctx->user_files);
	ctx->user_files = NULL;
	ctx->nr_user_files = 0;
	return 0;
}

static void io_sq_thread_stop(struct io_ring_ctx *ctx)
{
	if (ctx->sqo_thread) {
		/*
		 * The park is a bit of a work-around, without it we get
		 * warning spews on shutdown with SQPOLL set and affinity
		 * set to a single CPU.
		 */
		kthread_park(ctx->sqo_thread);
		kthread_stop(ctx->sqo_thread);
		ctx->sqo_thread = NULL;
	}
}

static void io_finish_async(struct io_ring_ctx *ctx)
{
	io_sq_thread_stop(ctx);

	if (ctx->sqo_wq) {
		destroy_workqueue(ctx->sqo_wq);
		ctx->sqo_wq = NULL;
	}
}

#if defined(CONFIG_UNIX)
static void io_destruct_skb(struct sk_buff *skb)
{
	struct io_ring_ctx *ctx = skb->sk->sk_user_data;

	io_finish_async(ctx);
	unix_destruct_scm(skb);
}

/*
 * Ensure the UNIX gc is aware of our file set, so we are certain that
 * the io_uring can be safely unregistered on process exit, even if we have
 * loops in the file referencing.
 */
static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
{
	struct sock *sk = ctx->ring_sock->sk;
	struct scm_fp_list *fpl;
	struct sk_buff *skb;
	int i;

	if (!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
		unsigned long inflight = ctx->user->unix_inflight + nr;

		if (inflight > task_rlimit(current, RLIMIT_NOFILE))
			return -EMFILE;
	}

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

	skb = alloc_skb(0, GFP_KERNEL);
	if (!skb) {
		kfree(fpl);
		return -ENOMEM;
	}

	skb->sk = sk;
	skb->destructor = io_destruct_skb;

	fpl->user = get_uid(ctx->user);
	for (i = 0; i < nr; i++) {
		fpl->fp[i] = get_file(ctx->user_files[i + offset]);
		unix_inflight(fpl->user, fpl->fp[i]);
	}

	fpl->max = fpl->count = nr;
	UNIXCB(skb).fp = fpl;
	refcount_add(skb->truesize, &sk->sk_wmem_alloc);
	skb_queue_head(&sk->sk_receive_queue, skb);

	for (i = 0; i < nr; i++)
		fput(fpl->fp[i]);

	return 0;
}

/*
 * If UNIX sockets are enabled, fd passing can cause a reference cycle which
 * causes regular reference counting to break down. We rely on the UNIX
 * garbage collection to take care of this problem for us.
 */
static int io_sqe_files_scm(struct io_ring_ctx *ctx)
{
	unsigned left, total;
	int ret = 0;

	total = 0;
	left = ctx->nr_user_files;
	while (left) {
		unsigned this_files = min_t(unsigned, left, SCM_MAX_FD);

		ret = __io_sqe_files_scm(ctx, this_files, total);
		if (ret)
			break;
		left -= this_files;
		total += this_files;
	}

	if (!ret)
		return 0;

	while (total < ctx->nr_user_files) {
		fput(ctx->user_files[total]);
		total++;
	}

	return ret;
}
#else
static int io_sqe_files_scm(struct io_ring_ctx *ctx)
{
	return 0;
}
#endif

static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
				 unsigned nr_args)
{
	__s32 __user *fds = (__s32 __user *) arg;
	int fd, ret = 0;
	unsigned i;

	if (ctx->user_files)
		return -EBUSY;
	if (!nr_args)
		return -EINVAL;
	if (nr_args > IORING_MAX_FIXED_FILES)
		return -EMFILE;

	ctx->user_files = kcalloc(nr_args, sizeof(struct file *), GFP_KERNEL);
	if (!ctx->user_files)
		return -ENOMEM;

	for (i = 0; i < nr_args; i++) {
		ret = -EFAULT;
		if (copy_from_user(&fd, &fds[i], sizeof(fd)))
			break;

		ctx->user_files[i] = fget(fd);

		ret = -EBADF;
		if (!ctx->user_files[i])
			break;
		/*
		 * Don't allow io_uring instances to be registered. If UNIX
		 * isn't enabled, then this causes a reference cycle and this
		 * instance can never get freed. If UNIX is enabled we'll
		 * handle it just fine, but there's still no point in allowing
		 * a ring fd as it doesn't support regular read/write anyway.
		 */
		if (ctx->user_files[i]->f_op == &io_uring_fops) {
			fput(ctx->user_files[i]);
			break;
		}
		ctx->nr_user_files++;
		ret = 0;
	}

	if (ret) {
		for (i = 0; i < ctx->nr_user_files; i++)
			fput(ctx->user_files[i]);

		kfree(ctx->user_files);
		ctx->user_files = NULL;
		ctx->nr_user_files = 0;
		return ret;
	}

	ret = io_sqe_files_scm(ctx);
	if (ret)
		io_sqe_files_unregister(ctx);

	return ret;
}

static int io_sq_offload_start(struct io_ring_ctx *ctx,
			       struct io_uring_params *p)
{
	int ret;

	init_waitqueue_head(&ctx->sqo_wait);
	mmgrab(current->mm);
	ctx->sqo_mm = current->mm;

	if (ctx->flags & IORING_SETUP_SQPOLL) {
		ret = -EPERM;
		if (!capable(CAP_SYS_ADMIN))
			goto err;

		ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
		if (!ctx->sq_thread_idle)
			ctx->sq_thread_idle = HZ;

		if (p->flags & IORING_SETUP_SQ_AFF) {
			int cpu = p->sq_thread_cpu;

			ret = -EINVAL;
			if (cpu >= nr_cpu_ids)
				goto err;
			if (!cpu_online(cpu))
				goto err;

			ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread,
							ctx, cpu,
							"io_uring-sq");
		} else {
			ctx->sqo_thread = kthread_create(io_sq_thread, ctx,
							"io_uring-sq");
		}
		if (IS_ERR(ctx->sqo_thread)) {
			ret = PTR_ERR(ctx->sqo_thread);
			ctx->sqo_thread = NULL;
			goto err;
		}
		wake_up_process(ctx->sqo_thread);
	} else if (p->flags & IORING_SETUP_SQ_AFF) {
		/* Can't have SQ_AFF without SQPOLL */
		ret = -EINVAL;
		goto err;
	}

	/* Do QD, or 2 * CPUS, whatever is smallest */
	ctx->sqo_wq = alloc_workqueue("io_ring-wq", WQ_UNBOUND | WQ_FREEZABLE,
			min(ctx->sq_entries - 1, 2 * num_online_cpus()));
	if (!ctx->sqo_wq) {
		ret = -ENOMEM;
		goto err;
	}

	return 0;
err:
	io_sq_thread_stop(ctx);
	mmdrop(ctx->sqo_mm);
	ctx->sqo_mm = NULL;
	return ret;
}

static void io_unaccount_mem(struct user_struct *user, unsigned long nr_pages)
{
	atomic_long_sub(nr_pages, &user->locked_vm);
}

static int io_account_mem(struct user_struct *user, unsigned long nr_pages)
{
	unsigned long page_limit, cur_pages, new_pages;

	/* Don't allow more pages than we can safely lock */
	page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;

	do {
		cur_pages = atomic_long_read(&user->locked_vm);
		new_pages = cur_pages + nr_pages;
		if (new_pages > page_limit)
			return -ENOMEM;
	} while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
					new_pages) != cur_pages);

	return 0;
}

static void io_mem_free(void *ptr)
{
	struct page *page;

	if (!ptr)
		return;

	page = virt_to_head_page(ptr);
	if (put_page_testzero(page))
		free_compound_page(page);
}

static void *io_mem_alloc(size_t size)
{
	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP |
				__GFP_NORETRY;

	return (void *) __get_free_pages(gfp_flags, get_order(size));
}

static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries)
{
	struct io_sq_ring *sq_ring;
	struct io_cq_ring *cq_ring;
	size_t bytes;

	bytes = struct_size(sq_ring, array, sq_entries);
	bytes += array_size(sizeof(struct io_uring_sqe), sq_entries);
	bytes += struct_size(cq_ring, cqes, cq_entries);

	return (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
}

static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)
{
	int i, j;

	if (!ctx->user_bufs)
		return -ENXIO;

	for (i = 0; i < ctx->nr_user_bufs; i++) {
		struct io_mapped_ubuf *imu = &ctx->user_bufs[i];

		for (j = 0; j < imu->nr_bvecs; j++)
			put_page(imu->bvec[j].bv_page);

		if (ctx->account_mem)
			io_unaccount_mem(ctx->user, imu->nr_bvecs);
		kvfree(imu->bvec);
		imu->nr_bvecs = 0;
	}

	kfree(ctx->user_bufs);
	ctx->user_bufs = NULL;
	ctx->nr_user_bufs = 0;
	return 0;
}

static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst,
		       void __user *arg, unsigned index)
{
	struct iovec __user *src;

#ifdef CONFIG_COMPAT
	if (ctx->compat) {
		struct compat_iovec __user *ciovs;
		struct compat_iovec ciov;

		ciovs = (struct compat_iovec __user *) arg;
		if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov)))
			return -EFAULT;

		dst->iov_base = (void __user *) (unsigned long) ciov.iov_base;
		dst->iov_len = ciov.iov_len;
		return 0;
	}
#endif
	src = (struct iovec __user *) arg;
	if (copy_from_user(dst, &src[index], sizeof(*dst)))
		return -EFAULT;
	return 0;
}

static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
				  unsigned nr_args)
{
	struct vm_area_struct **vmas = NULL;
	struct page **pages = NULL;
	int i, j, got_pages = 0;
	int ret = -EINVAL;

	if (ctx->user_bufs)
		return -EBUSY;
	if (!nr_args || nr_args > UIO_MAXIOV)
		return -EINVAL;

	ctx->user_bufs = kcalloc(nr_args, sizeof(struct io_mapped_ubuf),
					GFP_KERNEL);
	if (!ctx->user_bufs)
		return -ENOMEM;

	for (i = 0; i < nr_args; i++) {
		struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
		unsigned long off, start, end, ubuf;
		int pret, nr_pages;
		struct iovec iov;
		size_t size;

		ret = io_copy_iov(ctx, &iov, arg, i);
		if (ret)
			goto err;

		/*
		 * Don't impose further limits on the size and buffer
		 * constraints here, we'll -EINVAL later when IO is
		 * submitted if they are wrong.
		 */
		ret = -EFAULT;
		if (!iov.iov_base || !iov.iov_len)
			goto err;

		/* arbitrary limit, but we need something */
		if (iov.iov_len > SZ_1G)
			goto err;

		ubuf = (unsigned long) iov.iov_base;
		end = (ubuf + iov.iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
		start = ubuf >> PAGE_SHIFT;
		nr_pages = end - start;

		if (ctx->account_mem) {
			ret = io_account_mem(ctx->user, nr_pages);
			if (ret)
				goto err;
		}

		ret = 0;
		if (!pages || nr_pages > got_pages) {
			kfree(vmas);
			kfree(pages);
			pages = kvmalloc_array(nr_pages, sizeof(struct page *),
						GFP_KERNEL);
			vmas = kvmalloc_array(nr_pages,
					sizeof(struct vm_area_struct *),
					GFP_KERNEL);
			if (!pages || !vmas) {
				ret = -ENOMEM;
				if (ctx->account_mem)
					io_unaccount_mem(ctx->user, nr_pages);
				goto err;
			}
			got_pages = nr_pages;
		}

		imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec),
						GFP_KERNEL);
		ret = -ENOMEM;
		if (!imu->bvec) {
			if (ctx->account_mem)
				io_unaccount_mem(ctx->user, nr_pages);
			goto err;
		}

		ret = 0;
		down_read(&current->mm->mmap_sem);
		pret = get_user_pages(ubuf, nr_pages,
				      FOLL_WRITE | FOLL_LONGTERM,
				      pages, vmas);
		if (pret == nr_pages) {
			/* don't support file backed memory */
			for (j = 0; j < nr_pages; j++) {
				struct vm_area_struct *vma = vmas[j];

				if (vma->vm_file &&
				    !is_file_hugepages(vma->vm_file)) {
					ret = -EOPNOTSUPP;
					break;
				}
			}
		} else {
			ret = pret < 0 ? pret : -EFAULT;
		}
		up_read(&current->mm->mmap_sem);
		if (ret) {
			/*
			 * if we did partial map, or found file backed vmas,
			 * release any pages we did get
			 */
			if (pret > 0) {
				for (j = 0; j < pret; j++)
					put_page(pages[j]);
			}
			if (ctx->account_mem)
				io_unaccount_mem(ctx->user, nr_pages);
			kvfree(imu->bvec);
			goto err;
		}

		off = ubuf & ~PAGE_MASK;
		size = iov.iov_len;
		for (j = 0; j < nr_pages; j++) {
			size_t vec_len;

			vec_len = min_t(size_t, size, PAGE_SIZE - off);
			imu->bvec[j].bv_page = pages[j];
			imu->bvec[j].bv_len = vec_len;
			imu->bvec[j].bv_offset = off;
			off = 0;
			size -= vec_len;
		}
		/* store original address for later verification */
		imu->ubuf = ubuf;
		imu->len = iov.iov_len;
		imu->nr_bvecs = nr_pages;

		ctx->nr_user_bufs++;
	}
	kvfree(pages);
	kvfree(vmas);
	return 0;
err:
	kvfree(pages);
	kvfree(vmas);
	io_sqe_buffer_unregister(ctx);
	return ret;
}

static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg)
{
	__s32 __user *fds = arg;
	int fd;

	if (ctx->cq_ev_fd)
		return -EBUSY;

	if (copy_from_user(&fd, fds, sizeof(*fds)))
		return -EFAULT;

	ctx->cq_ev_fd = eventfd_ctx_fdget(fd);
	if (IS_ERR(ctx->cq_ev_fd)) {
		int ret = PTR_ERR(ctx->cq_ev_fd);
		ctx->cq_ev_fd = NULL;
		return ret;
	}

	return 0;
}

static int io_eventfd_unregister(struct io_ring_ctx *ctx)
{
	if (ctx->cq_ev_fd) {
		eventfd_ctx_put(ctx->cq_ev_fd);
		ctx->cq_ev_fd = NULL;
		return 0;
	}

	return -ENXIO;
}

static void io_ring_ctx_free(struct io_ring_ctx *ctx)
{
	io_finish_async(ctx);
	if (ctx->sqo_mm)
		mmdrop(ctx->sqo_mm);

	io_iopoll_reap_events(ctx);
	io_sqe_buffer_unregister(ctx);
	io_sqe_files_unregister(ctx);
	io_eventfd_unregister(ctx);

#if defined(CONFIG_UNIX)
	if (ctx->ring_sock) {
		ctx->ring_sock->file = NULL; /* so that iput() is called */
		sock_release(ctx->ring_sock);
	}
#endif

	io_mem_free(ctx->sq_ring);
	io_mem_free(ctx->sq_sqes);
	io_mem_free(ctx->cq_ring);

	percpu_ref_exit(&ctx->refs);
	if (ctx->account_mem)
		io_unaccount_mem(ctx->user,
				ring_pages(ctx->sq_entries, ctx->cq_entries));
	free_uid(ctx->user);
	kfree(ctx);
}

static __poll_t io_uring_poll(struct file *file, poll_table *wait)
{
	struct io_ring_ctx *ctx = file->private_data;
	__poll_t mask = 0;

	poll_wait(file, &ctx->cq_wait, wait);
	/*
	 * synchronizes with barrier from wq_has_sleeper call in
	 * io_commit_cqring
	 */
	smp_rmb();
	if (READ_ONCE(ctx->sq_ring->r.tail) - ctx->cached_sq_head !=
	    ctx->sq_ring->ring_entries)
		mask |= EPOLLOUT | EPOLLWRNORM;
	if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail)
		mask |= EPOLLIN | EPOLLRDNORM;

	return mask;
}

static int io_uring_fasync(int fd, struct file *file, int on)
{
	struct io_ring_ctx *ctx = file->private_data;

	return fasync_helper(fd, file, on, &ctx->cq_fasync);
}

static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
{
	mutex_lock(&ctx->uring_lock);
	percpu_ref_kill(&ctx->refs);
	mutex_unlock(&ctx->uring_lock);

	io_poll_remove_all(ctx);
	io_iopoll_reap_events(ctx);
	wait_for_completion(&ctx->ctx_done);
	io_ring_ctx_free(ctx);
}

static int io_uring_release(struct inode *inode, struct file *file)
{
	struct io_ring_ctx *ctx = file->private_data;

	file->private_data = NULL;
	io_ring_ctx_wait_and_kill(ctx);
	return 0;
}

static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
{
	loff_t offset = (loff_t) vma->vm_pgoff << PAGE_SHIFT;
	unsigned long sz = vma->vm_end - vma->vm_start;
	struct io_ring_ctx *ctx = file->private_data;
	unsigned long pfn;
	struct page *page;
	void *ptr;

	switch (offset) {
	case IORING_OFF_SQ_RING:
		ptr = ctx->sq_ring;
		break;
	case IORING_OFF_SQES:
		ptr = ctx->sq_sqes;
		break;
	case IORING_OFF_CQ_RING:
		ptr = ctx->cq_ring;
		break;
	default:
		return -EINVAL;
	}

	page = virt_to_head_page(ptr);
	if (sz > (PAGE_SIZE << compound_order(page)))
		return -EINVAL;

	pfn = virt_to_phys(ptr) >> PAGE_SHIFT;
	return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot);
}

SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
		u32, min_complete, u32, flags, const sigset_t __user *, sig,
		size_t, sigsz)
{
	struct io_ring_ctx *ctx;
	long ret = -EBADF;
	int submitted = 0;
	struct fd f;

	if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP))
		return -EINVAL;

	f = fdget(fd);
	if (!f.file)
		return -EBADF;

	ret = -EOPNOTSUPP;
	if (f.file->f_op != &io_uring_fops)
		goto out_fput;

	ret = -ENXIO;
	ctx = f.file->private_data;
	if (!percpu_ref_tryget(&ctx->refs))
		goto out_fput;

	/*
	 * For SQ polling, the thread will do all submissions and completions.
	 * Just return the requested submit count, and wake the thread if
	 * we were asked to.
	 */
	if (ctx->flags & IORING_SETUP_SQPOLL) {
		if (flags & IORING_ENTER_SQ_WAKEUP)
			wake_up(&ctx->sqo_wait);
		submitted = to_submit;
		goto out_ctx;
	}

	ret = 0;
	if (to_submit) {
		to_submit = min(to_submit, ctx->sq_entries);

		mutex_lock(&ctx->uring_lock);
		submitted = io_ring_submit(ctx, to_submit);
		mutex_unlock(&ctx->uring_lock);
	}
	if (flags & IORING_ENTER_GETEVENTS) {
		unsigned nr_events = 0;

		min_complete = min(min_complete, ctx->cq_entries);

		if (ctx->flags & IORING_SETUP_IOPOLL) {
			mutex_lock(&ctx->uring_lock);
			ret = io_iopoll_check(ctx, &nr_events, min_complete);
			mutex_unlock(&ctx->uring_lock);
		} else {
			ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
		}
	}

out_ctx:
	io_ring_drop_ctx_refs(ctx, 1);
out_fput:
	fdput(f);
	return submitted ? submitted : ret;
}

static const struct file_operations io_uring_fops = {
	.release	= io_uring_release,
	.mmap		= io_uring_mmap,
	.poll		= io_uring_poll,
	.fasync		= io_uring_fasync,
};

static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
				  struct io_uring_params *p)
{
	struct io_sq_ring *sq_ring;
	struct io_cq_ring *cq_ring;
	size_t size;

	sq_ring = io_mem_alloc(struct_size(sq_ring, array, p->sq_entries));
	if (!sq_ring)
		return -ENOMEM;

	ctx->sq_ring = sq_ring;
	sq_ring->ring_mask = p->sq_entries - 1;
	sq_ring->ring_entries = p->sq_entries;
	ctx->sq_mask = sq_ring->ring_mask;
	ctx->sq_entries = sq_ring->ring_entries;

	size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
	if (size == SIZE_MAX)
		return -EOVERFLOW;

	ctx->sq_sqes = io_mem_alloc(size);
	if (!ctx->sq_sqes)
		return -ENOMEM;

	cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries));
	if (!cq_ring)
		return -ENOMEM;

	ctx->cq_ring = cq_ring;
	cq_ring->ring_mask = p->cq_entries - 1;
	cq_ring->ring_entries = p->cq_entries;
	ctx->cq_mask = cq_ring->ring_mask;
	ctx->cq_entries = cq_ring->ring_entries;
	return 0;
}

/*
 * Allocate an anonymous fd, this is what constitutes the application
 * visible backing of an io_uring instance. The application mmaps this
 * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled,
 * we have to tie this fd to a socket for file garbage collection purposes.
 */
static int io_uring_get_fd(struct io_ring_ctx *ctx)
{
	struct file *file;
	int ret;

#if defined(CONFIG_UNIX)
	ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP,
				&ctx->ring_sock);
	if (ret)
		return ret;
#endif

	ret = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
	if (ret < 0)
		goto err;

	file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx,
					O_RDWR | O_CLOEXEC);
	if (IS_ERR(file)) {
		put_unused_fd(ret);
		ret = PTR_ERR(file);
		goto err;
	}

#if defined(CONFIG_UNIX)
	ctx->ring_sock->file = file;
	ctx->ring_sock->sk->sk_user_data = ctx;
#endif
	fd_install(ret, file);
	return ret;
err:
#if defined(CONFIG_UNIX)
	sock_release(ctx->ring_sock);
	ctx->ring_sock = NULL;
#endif
	return ret;
}

static int io_uring_create(unsigned entries, struct io_uring_params *p)
{
	struct user_struct *user = NULL;
	struct io_ring_ctx *ctx;
	bool account_mem;
	int ret;

	if (!entries || entries > IORING_MAX_ENTRIES)
		return -EINVAL;

	/*
	 * Use twice as many entries for the CQ ring. It's possible for the
	 * application to drive a higher depth than the size of the SQ ring,
	 * since the sqes are only used at submission time. This allows for
	 * some flexibility in overcommitting a bit.
	 */
	p->sq_entries = roundup_pow_of_two(entries);
	p->cq_entries = 2 * p->sq_entries;

	user = get_uid(current_user());
	account_mem = !capable(CAP_IPC_LOCK);

	if (account_mem) {
		ret = io_account_mem(user,
				ring_pages(p->sq_entries, p->cq_entries));
		if (ret) {
			free_uid(user);
			return ret;
		}
	}

	ctx = io_ring_ctx_alloc(p);
	if (!ctx) {
		if (account_mem)
			io_unaccount_mem(user, ring_pages(p->sq_entries,
								p->cq_entries));
		free_uid(user);
		return -ENOMEM;
	}
	ctx->compat = in_compat_syscall();
	ctx->account_mem = account_mem;
	ctx->user = user;

	ret = io_allocate_scq_urings(ctx, p);
	if (ret)
		goto err;

	ret = io_sq_offload_start(ctx, p);
	if (ret)
		goto err;

	ret = io_uring_get_fd(ctx);
	if (ret < 0)
		goto err;

	memset(&p->sq_off, 0, sizeof(p->sq_off));
	p->sq_off.head = offsetof(struct io_sq_ring, r.head);
	p->sq_off.tail = offsetof(struct io_sq_ring, r.tail);
	p->sq_off.ring_mask = offsetof(struct io_sq_ring, ring_mask);
	p->sq_off.ring_entries = offsetof(struct io_sq_ring, ring_entries);
	p->sq_off.flags = offsetof(struct io_sq_ring, flags);
	p->sq_off.dropped = offsetof(struct io_sq_ring, dropped);
	p->sq_off.array = offsetof(struct io_sq_ring, array);

	memset(&p->cq_off, 0, sizeof(p->cq_off));
	p->cq_off.head = offsetof(struct io_cq_ring, r.head);
	p->cq_off.tail = offsetof(struct io_cq_ring, r.tail);
	p->cq_off.ring_mask = offsetof(struct io_cq_ring, ring_mask);
	p->cq_off.ring_entries = offsetof(struct io_cq_ring, ring_entries);
	p->cq_off.overflow = offsetof(struct io_cq_ring, overflow);
	p->cq_off.cqes = offsetof(struct io_cq_ring, cqes);
	return ret;
err:
	io_ring_ctx_wait_and_kill(ctx);
	return ret;
}

/*
 * Sets up an aio uring context, and returns the fd. Applications asks for a
 * ring size, we return the actual sq/cq ring sizes (among other things) in the
 * params structure passed in.
 */
static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
{
	struct io_uring_params p;
	long ret;
	int i;

	if (copy_from_user(&p, params, sizeof(p)))
		return -EFAULT;
	for (i = 0; i < ARRAY_SIZE(p.resv); i++) {
		if (p.resv[i])
			return -EINVAL;
	}

	if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
			IORING_SETUP_SQ_AFF))
		return -EINVAL;

	ret = io_uring_create(entries, &p);
	if (ret < 0)
		return ret;

	if (copy_to_user(params, &p, sizeof(p)))
		return -EFAULT;

	return ret;
}

SYSCALL_DEFINE2(io_uring_setup, u32, entries,
		struct io_uring_params __user *, params)
{
	return io_uring_setup(entries, params);
}

static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
			       void __user *arg, unsigned nr_args)
	__releases(ctx->uring_lock)
	__acquires(ctx->uring_lock)
{
	int ret;

	/*
	 * We're inside the ring mutex, if the ref is already dying, then
	 * someone else killed the ctx or is already going through
	 * io_uring_register().
	 */
	if (percpu_ref_is_dying(&ctx->refs))
		return -ENXIO;

	percpu_ref_kill(&ctx->refs);

	/*
	 * Drop uring mutex before waiting for references to exit. If another
	 * thread is currently inside io_uring_enter() it might need to grab
	 * the uring_lock to make progress. If we hold it here across the drain
	 * wait, then we can deadlock. It's safe to drop the mutex here, since
	 * no new references will come in after we've killed the percpu ref.
	 */
	mutex_unlock(&ctx->uring_lock);
	wait_for_completion(&ctx->ctx_done);
	mutex_lock(&ctx->uring_lock);

	switch (opcode) {
	case IORING_REGISTER_BUFFERS:
		ret = io_sqe_buffer_register(ctx, arg, nr_args);
		break;
	case IORING_UNREGISTER_BUFFERS:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_sqe_buffer_unregister(ctx);
		break;
	case IORING_REGISTER_FILES:
		ret = io_sqe_files_register(ctx, arg, nr_args);
		break;
	case IORING_UNREGISTER_FILES:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_sqe_files_unregister(ctx);
		break;
	case IORING_REGISTER_EVENTFD:
		ret = -EINVAL;
		if (nr_args != 1)
			break;
		ret = io_eventfd_register(ctx, arg);
		break;
	case IORING_UNREGISTER_EVENTFD:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_eventfd_unregister(ctx);
		break;
	default:
		ret = -EINVAL;
		break;
	}

	/* bring the ctx back to life */
	reinit_completion(&ctx->ctx_done);
	percpu_ref_reinit(&ctx->refs);
	return ret;
}

SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
		void __user *, arg, unsigned int, nr_args)
{
	struct io_ring_ctx *ctx;
	long ret = -EBADF;
	struct fd f;

	f = fdget(fd);
	if (!f.file)
		return -EBADF;

	ret = -EOPNOTSUPP;
	if (f.file->f_op != &io_uring_fops)
		goto out_fput;

	ctx = f.file->private_data;

	mutex_lock(&ctx->uring_lock);
	ret = __io_uring_register(ctx, opcode, arg, nr_args);
	mutex_unlock(&ctx->uring_lock);
out_fput:
	fdput(f);
	return ret;
}

static int __init io_uring_init(void)
{
	req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
	return 0;
};
__initcall(io_uring_init);