summaryrefslogtreecommitdiff
path: root/fs/io_uring.c
blob: e54c4127422e42ff34aa02367ad788f13d5f34a4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
11128
11129
11130
11131
11132
11133
11134
11135
11136
11137
11138
11139
11140
11141
11142
11143
11144
11145
11146
11147
11148
11149
11150
11151
11152
11153
11154
11155
11156
11157
11158
11159
11160
11161
11162
11163
11164
11165
11166
11167
11168
11169
11170
11171
11172
11173
11174
11175
11176
11177
11178
11179
11180
11181
11182
11183
11184
11185
11186
11187
11188
11189
11190
11191
11192
11193
11194
11195
11196
11197
11198
11199
11200
11201
11202
11203
11204
11205
11206
11207
11208
11209
11210
11211
11212
11213
11214
11215
11216
11217
11218
11219
11220
11221
11222
11223
11224
11225
11226
11227
11228
11229
11230
11231
11232
11233
11234
11235
11236
11237
// 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_cqe (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 <net/compat.h>
#include <linux/refcount.h>
#include <linux/uio.h>
#include <linux/bits.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/percpu.h>
#include <linux/slab.h>
#include <linux/blk-mq.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 <linux/highmem.h>
#include <linux/namei.h>
#include <linux/fsnotify.h>
#include <linux/fadvise.h>
#include <linux/eventpoll.h>
#include <linux/splice.h>
#include <linux/task_work.h>
#include <linux/pagemap.h>
#include <linux/io_uring.h>
#include <linux/tracehook.h>
#include <linux/audit.h>
#include <linux/security.h>

#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>

#include <uapi/linux/io_uring.h>

#include "internal.h"
#include "io-wq.h"

#define IORING_MAX_ENTRIES	32768
#define IORING_MAX_CQ_ENTRIES	(2 * IORING_MAX_ENTRIES)
#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8

/* only define max */
#define IORING_MAX_FIXED_FILES	(1U << 15)
#define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
				 IORING_REGISTER_LAST + IORING_OP_LAST)

#define IO_RSRC_TAG_TABLE_SHIFT	(PAGE_SHIFT - 3)
#define IO_RSRC_TAG_TABLE_MAX	(1U << IO_RSRC_TAG_TABLE_SHIFT)
#define IO_RSRC_TAG_TABLE_MASK	(IO_RSRC_TAG_TABLE_MAX - 1)

#define IORING_MAX_REG_BUFFERS	(1U << 14)

#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
			  IOSQE_IO_HARDLINK | IOSQE_ASYNC)

#define SQE_VALID_FLAGS	(SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \
			IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)

#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
				REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
				REQ_F_ASYNC_DATA)

#define IO_TCTX_REFS_CACHE_NR	(1U << 10)

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 offsets
 * IORING_OFF_SQ_RING and IORING_OFF_CQ_RING.
 *
 * The offsets to the member fields are published through struct
 * io_sqring_offsets when calling io_uring_setup.
 */
struct io_rings {
	/*
	 * Head and tail offsets into the ring; the offsets need to be
	 * masked to get valid indices.
	 *
	 * The kernel controls head of the sq ring and the tail of the cq ring,
	 * and the application controls tail of the sq ring and the head of the
	 * cq ring.
	 */
	struct io_uring		sq, cq;
	/*
	 * Bitmasks to apply to head and tail offsets (constant, equals
	 * ring_entries - 1)
	 */
	u32			sq_ring_mask, cq_ring_mask;
	/* Ring sizes (constant, power of 2) */
	u32			sq_ring_entries, cq_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			sq_dropped;
	/*
	 * Runtime SQ 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			sq_flags;
	/*
	 * Runtime CQ flags
	 *
	 * Written by the application, shouldn't be modified by the
	 * kernel.
	 */
	u32			cq_flags;
	/*
	 * 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 than 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			cq_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[] ____cacheline_aligned_in_smp;
};

enum io_uring_cmd_flags {
	IO_URING_F_COMPLETE_DEFER	= 1,
	IO_URING_F_UNLOCKED		= 2,
	/* int's last bit, sign checks are usually faster than a bit test */
	IO_URING_F_NONBLOCK		= INT_MIN,
};

struct io_mapped_ubuf {
	u64		ubuf;
	u64		ubuf_end;
	unsigned int	nr_bvecs;
	unsigned long	acct_pages;
	struct bio_vec	bvec[];
};

struct io_ring_ctx;

struct io_overflow_cqe {
	struct io_uring_cqe cqe;
	struct list_head list;
};

struct io_fixed_file {
	/* file * with additional FFS_* flags */
	unsigned long file_ptr;
};

struct io_rsrc_put {
	struct list_head list;
	u64 tag;
	union {
		void *rsrc;
		struct file *file;
		struct io_mapped_ubuf *buf;
	};
};

struct io_file_table {
	struct io_fixed_file *files;
};

struct io_rsrc_node {
	struct percpu_ref		refs;
	struct list_head		node;
	struct list_head		rsrc_list;
	struct io_rsrc_data		*rsrc_data;
	struct llist_node		llist;
	bool				done;
};

typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);

struct io_rsrc_data {
	struct io_ring_ctx		*ctx;

	u64				**tags;
	unsigned int			nr;
	rsrc_put_fn			*do_put;
	atomic_t			refs;
	struct completion		done;
	bool				quiesce;
};

struct io_buffer {
	struct list_head list;
	__u64 addr;
	__u32 len;
	__u16 bid;
};

struct io_restriction {
	DECLARE_BITMAP(register_op, IORING_REGISTER_LAST);
	DECLARE_BITMAP(sqe_op, IORING_OP_LAST);
	u8 sqe_flags_allowed;
	u8 sqe_flags_required;
	bool registered;
};

enum {
	IO_SQ_THREAD_SHOULD_STOP = 0,
	IO_SQ_THREAD_SHOULD_PARK,
};

struct io_sq_data {
	refcount_t		refs;
	atomic_t		park_pending;
	struct mutex		lock;

	/* ctx's that are using this sqd */
	struct list_head	ctx_list;

	struct task_struct	*thread;
	struct wait_queue_head	wait;

	unsigned		sq_thread_idle;
	int			sq_cpu;
	pid_t			task_pid;
	pid_t			task_tgid;

	unsigned long		state;
	struct completion	exited;
};

#define IO_COMPL_BATCH			32
#define IO_REQ_CACHE_SIZE		32
#define IO_REQ_ALLOC_BATCH		8

struct io_submit_link {
	struct io_kiocb		*head;
	struct io_kiocb		*last;
};

struct io_submit_state {
	/* inline/task_work completion list, under ->uring_lock */
	struct io_wq_work_node	free_list;
	/* batch completion logic */
	struct io_wq_work_list	compl_reqs;
	struct io_submit_link	link;

	bool			plug_started;
	bool			need_plug;
	bool			flush_cqes;
	unsigned short		submit_nr;
	struct blk_plug		plug;
};

struct io_ring_ctx {
	/* const or read-mostly hot data */
	struct {
		struct percpu_ref	refs;

		struct io_rings		*rings;
		unsigned int		flags;
		unsigned int		compat: 1;
		unsigned int		drain_next: 1;
		unsigned int		eventfd_async: 1;
		unsigned int		restricted: 1;
		unsigned int		off_timeout_used: 1;
		unsigned int		drain_active: 1;
		unsigned int		drain_disabled: 1;
	} ____cacheline_aligned_in_smp;

	/* submission data */
	struct {
		struct mutex		uring_lock;

		/*
		 * 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			*sq_array;
		struct io_uring_sqe	*sq_sqes;
		unsigned		cached_sq_head;
		unsigned		sq_entries;
		struct list_head	defer_list;

		/*
		 * Fixed resources fast path, should be accessed only under
		 * uring_lock, and updated through io_uring_register(2)
		 */
		struct io_rsrc_node	*rsrc_node;
		int			rsrc_cached_refs;
		struct io_file_table	file_table;
		unsigned		nr_user_files;
		unsigned		nr_user_bufs;
		struct io_mapped_ubuf	**user_bufs;

		struct io_submit_state	submit_state;
		struct list_head	timeout_list;
		struct list_head	ltimeout_list;
		struct list_head	cq_overflow_list;
		struct xarray		io_buffers;
		struct xarray		personalities;
		u32			pers_next;
		unsigned		sq_thread_idle;
	} ____cacheline_aligned_in_smp;

	/* IRQ completion list, under ->completion_lock */
	struct io_wq_work_list	locked_free_list;
	unsigned int		locked_free_nr;

	const struct cred	*sq_creds;	/* cred used for __io_sq_thread() */
	struct io_sq_data	*sq_data;	/* if using sq thread polling */

	struct wait_queue_head	sqo_sq_wait;
	struct list_head	sqd_list;

	unsigned long		check_cq_overflow;

	struct {
		unsigned		cached_cq_tail;
		unsigned		cq_entries;
		struct eventfd_ctx	*cq_ev_fd;
		struct wait_queue_head	cq_wait;
		unsigned		cq_extra;
		atomic_t		cq_timeouts;
		unsigned		cq_last_tm_flush;
	} ____cacheline_aligned_in_smp;

	struct {
		spinlock_t		completion_lock;

		spinlock_t		timeout_lock;

		/*
		 * ->iopoll_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 io_wq_work_list	iopoll_list;
		struct hlist_head	*cancel_hash;
		unsigned		cancel_hash_bits;
		bool			poll_multi_queue;
	} ____cacheline_aligned_in_smp;

	struct io_restriction		restrictions;

	/* slow path rsrc auxilary data, used by update/register */
	struct {
		struct io_rsrc_node		*rsrc_backup_node;
		struct io_mapped_ubuf		*dummy_ubuf;
		struct io_rsrc_data		*file_data;
		struct io_rsrc_data		*buf_data;

		struct delayed_work		rsrc_put_work;
		struct llist_head		rsrc_put_llist;
		struct list_head		rsrc_ref_list;
		spinlock_t			rsrc_ref_lock;
	};

	/* Keep this last, we don't need it for the fast path */
	struct {
		#if defined(CONFIG_UNIX)
			struct socket		*ring_sock;
		#endif
		/* hashed buffered write serialization */
		struct io_wq_hash		*hash_map;

		/* Only used for accounting purposes */
		struct user_struct		*user;
		struct mm_struct		*mm_account;

		/* ctx exit and cancelation */
		struct llist_head		fallback_llist;
		struct delayed_work		fallback_work;
		struct work_struct		exit_work;
		struct list_head		tctx_list;
		struct completion		ref_comp;
		u32				iowq_limits[2];
		bool				iowq_limits_set;
	};
};

struct io_uring_task {
	/* submission side */
	int			cached_refs;
	struct xarray		xa;
	struct wait_queue_head	wait;
	const struct io_ring_ctx *last;
	struct io_wq		*io_wq;
	struct percpu_counter	inflight;
	atomic_t		inflight_tracked;
	atomic_t		in_idle;

	spinlock_t		task_lock;
	struct io_wq_work_list	task_list;
	struct io_wq_work_list	prior_task_list;
	struct callback_head	task_work;
	bool			task_running;
};

/*
 * 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;
	struct wait_queue_entry		wait;
};

struct io_poll_update {
	struct file			*file;
	u64				old_user_data;
	u64				new_user_data;
	__poll_t			events;
	bool				update_events;
	bool				update_user_data;
};

struct io_close {
	struct file			*file;
	int				fd;
	u32				file_slot;
};

struct io_timeout_data {
	struct io_kiocb			*req;
	struct hrtimer			timer;
	struct timespec64		ts;
	enum hrtimer_mode		mode;
	u32				flags;
};

struct io_accept {
	struct file			*file;
	struct sockaddr __user		*addr;
	int __user			*addr_len;
	int				flags;
	u32				file_slot;
	unsigned long			nofile;
};

struct io_sync {
	struct file			*file;
	loff_t				len;
	loff_t				off;
	int				flags;
	int				mode;
};

struct io_cancel {
	struct file			*file;
	u64				addr;
};

struct io_timeout {
	struct file			*file;
	u32				off;
	u32				target_seq;
	struct list_head		list;
	/* head of the link, used by linked timeouts only */
	struct io_kiocb			*head;
	/* for linked completions */
	struct io_kiocb			*prev;
};

struct io_timeout_rem {
	struct file			*file;
	u64				addr;

	/* timeout update */
	struct timespec64		ts;
	u32				flags;
	bool				ltimeout;
};

struct io_rw {
	/* NOTE: kiocb has the file as the first member, so don't do it here */
	struct kiocb			kiocb;
	u64				addr;
	u64				len;
};

struct io_connect {
	struct file			*file;
	struct sockaddr __user		*addr;
	int				addr_len;
};

struct io_sr_msg {
	struct file			*file;
	union {
		struct compat_msghdr __user	*umsg_compat;
		struct user_msghdr __user	*umsg;
		void __user			*buf;
	};
	int				msg_flags;
	int				bgid;
	size_t				len;
};

struct io_open {
	struct file			*file;
	int				dfd;
	u32				file_slot;
	struct filename			*filename;
	struct open_how			how;
	unsigned long			nofile;
};

struct io_rsrc_update {
	struct file			*file;
	u64				arg;
	u32				nr_args;
	u32				offset;
};

struct io_fadvise {
	struct file			*file;
	u64				offset;
	u32				len;
	u32				advice;
};

struct io_madvise {
	struct file			*file;
	u64				addr;
	u32				len;
	u32				advice;
};

struct io_epoll {
	struct file			*file;
	int				epfd;
	int				op;
	int				fd;
	struct epoll_event		event;
};

struct io_splice {
	struct file			*file_out;
	struct file			*file_in;
	loff_t				off_out;
	loff_t				off_in;
	u64				len;
	unsigned int			flags;
};

struct io_provide_buf {
	struct file			*file;
	__u64				addr;
	__u32				len;
	__u32				bgid;
	__u16				nbufs;
	__u16				bid;
};

struct io_statx {
	struct file			*file;
	int				dfd;
	unsigned int			mask;
	unsigned int			flags;
	const char __user		*filename;
	struct statx __user		*buffer;
};

struct io_shutdown {
	struct file			*file;
	int				how;
};

struct io_rename {
	struct file			*file;
	int				old_dfd;
	int				new_dfd;
	struct filename			*oldpath;
	struct filename			*newpath;
	int				flags;
};

struct io_unlink {
	struct file			*file;
	int				dfd;
	int				flags;
	struct filename			*filename;
};

struct io_mkdir {
	struct file			*file;
	int				dfd;
	umode_t				mode;
	struct filename			*filename;
};

struct io_symlink {
	struct file			*file;
	int				new_dfd;
	struct filename			*oldpath;
	struct filename			*newpath;
};

struct io_hardlink {
	struct file			*file;
	int				old_dfd;
	int				new_dfd;
	struct filename			*oldpath;
	struct filename			*newpath;
	int				flags;
};

struct io_async_connect {
	struct sockaddr_storage		address;
};

struct io_async_msghdr {
	struct iovec			fast_iov[UIO_FASTIOV];
	/* points to an allocated iov, if NULL we use fast_iov instead */
	struct iovec			*free_iov;
	struct sockaddr __user		*uaddr;
	struct msghdr			msg;
	struct sockaddr_storage		addr;
};

struct io_rw_state {
	struct iov_iter			iter;
	struct iov_iter_state		iter_state;
	struct iovec			fast_iov[UIO_FASTIOV];
};

struct io_async_rw {
	struct io_rw_state		s;
	const struct iovec		*free_iovec;
	size_t				bytes_done;
	struct wait_page_queue		wpq;
};

enum {
	REQ_F_FIXED_FILE_BIT	= IOSQE_FIXED_FILE_BIT,
	REQ_F_IO_DRAIN_BIT	= IOSQE_IO_DRAIN_BIT,
	REQ_F_LINK_BIT		= IOSQE_IO_LINK_BIT,
	REQ_F_HARDLINK_BIT	= IOSQE_IO_HARDLINK_BIT,
	REQ_F_FORCE_ASYNC_BIT	= IOSQE_ASYNC_BIT,
	REQ_F_BUFFER_SELECT_BIT	= IOSQE_BUFFER_SELECT_BIT,
	REQ_F_CQE_SKIP_BIT	= IOSQE_CQE_SKIP_SUCCESS_BIT,

	/* first byte is taken by user flags, shift it to not overlap */
	REQ_F_FAIL_BIT		= 8,
	REQ_F_INFLIGHT_BIT,
	REQ_F_CUR_POS_BIT,
	REQ_F_NOWAIT_BIT,
	REQ_F_LINK_TIMEOUT_BIT,
	REQ_F_NEED_CLEANUP_BIT,
	REQ_F_POLLED_BIT,
	REQ_F_BUFFER_SELECTED_BIT,
	REQ_F_COMPLETE_INLINE_BIT,
	REQ_F_REISSUE_BIT,
	REQ_F_CREDS_BIT,
	REQ_F_REFCOUNT_BIT,
	REQ_F_ARM_LTIMEOUT_BIT,
	REQ_F_ASYNC_DATA_BIT,
	REQ_F_SKIP_LINK_CQES_BIT,
	/* keep async read/write and isreg together and in order */
	REQ_F_SUPPORT_NOWAIT_BIT,
	REQ_F_ISREG_BIT,

	/* not a real bit, just to check we're not overflowing the space */
	__REQ_F_LAST_BIT,
};

enum {
	/* ctx owns file */
	REQ_F_FIXED_FILE	= BIT(REQ_F_FIXED_FILE_BIT),
	/* drain existing IO first */
	REQ_F_IO_DRAIN		= BIT(REQ_F_IO_DRAIN_BIT),
	/* linked sqes */
	REQ_F_LINK		= BIT(REQ_F_LINK_BIT),
	/* doesn't sever on completion < 0 */
	REQ_F_HARDLINK		= BIT(REQ_F_HARDLINK_BIT),
	/* IOSQE_ASYNC */
	REQ_F_FORCE_ASYNC	= BIT(REQ_F_FORCE_ASYNC_BIT),
	/* IOSQE_BUFFER_SELECT */
	REQ_F_BUFFER_SELECT	= BIT(REQ_F_BUFFER_SELECT_BIT),
	/* IOSQE_CQE_SKIP_SUCCESS */
	REQ_F_CQE_SKIP		= BIT(REQ_F_CQE_SKIP_BIT),

	/* fail rest of links */
	REQ_F_FAIL		= BIT(REQ_F_FAIL_BIT),
	/* on inflight list, should be cancelled and waited on exit reliably */
	REQ_F_INFLIGHT		= BIT(REQ_F_INFLIGHT_BIT),
	/* read/write uses file position */
	REQ_F_CUR_POS		= BIT(REQ_F_CUR_POS_BIT),
	/* must not punt to workers */
	REQ_F_NOWAIT		= BIT(REQ_F_NOWAIT_BIT),
	/* has or had linked timeout */
	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
	/* needs cleanup */
	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
	/* already went through poll handler */
	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
	/* buffer already selected */
	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
	/* completion is deferred through io_comp_state */
	REQ_F_COMPLETE_INLINE	= BIT(REQ_F_COMPLETE_INLINE_BIT),
	/* caller should reissue async */
	REQ_F_REISSUE		= BIT(REQ_F_REISSUE_BIT),
	/* supports async reads/writes */
	REQ_F_SUPPORT_NOWAIT	= BIT(REQ_F_SUPPORT_NOWAIT_BIT),
	/* regular file */
	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
	/* has creds assigned */
	REQ_F_CREDS		= BIT(REQ_F_CREDS_BIT),
	/* skip refcounting if not set */
	REQ_F_REFCOUNT		= BIT(REQ_F_REFCOUNT_BIT),
	/* there is a linked timeout that has to be armed */
	REQ_F_ARM_LTIMEOUT	= BIT(REQ_F_ARM_LTIMEOUT_BIT),
	/* ->async_data allocated */
	REQ_F_ASYNC_DATA	= BIT(REQ_F_ASYNC_DATA_BIT),
	/* don't post CQEs while failing linked requests */
	REQ_F_SKIP_LINK_CQES	= BIT(REQ_F_SKIP_LINK_CQES_BIT),
};

struct async_poll {
	struct io_poll_iocb	poll;
	struct io_poll_iocb	*double_poll;
};

typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked);

struct io_task_work {
	union {
		struct io_wq_work_node	node;
		struct llist_node	fallback_node;
	};
	io_req_tw_func_t		func;
};

enum {
	IORING_RSRC_FILE		= 0,
	IORING_RSRC_BUFFER		= 1,
};

/*
 * 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 io_rw		rw;
		struct io_poll_iocb	poll;
		struct io_poll_update	poll_update;
		struct io_accept	accept;
		struct io_sync		sync;
		struct io_cancel	cancel;
		struct io_timeout	timeout;
		struct io_timeout_rem	timeout_rem;
		struct io_connect	connect;
		struct io_sr_msg	sr_msg;
		struct io_open		open;
		struct io_close		close;
		struct io_rsrc_update	rsrc_update;
		struct io_fadvise	fadvise;
		struct io_madvise	madvise;
		struct io_epoll		epoll;
		struct io_splice	splice;
		struct io_provide_buf	pbuf;
		struct io_statx		statx;
		struct io_shutdown	shutdown;
		struct io_rename	rename;
		struct io_unlink	unlink;
		struct io_mkdir		mkdir;
		struct io_symlink	symlink;
		struct io_hardlink	hardlink;
	};

	u8				opcode;
	/* polled IO has completed */
	u8				iopoll_completed;
	u16				buf_index;
	unsigned int			flags;

	u64				user_data;
	u32				result;
	u32				cflags;

	struct io_ring_ctx		*ctx;
	struct task_struct		*task;

	struct percpu_ref		*fixed_rsrc_refs;
	/* store used ubuf, so we can prevent reloading */
	struct io_mapped_ubuf		*imu;

	/* used by request caches, completion batching and iopoll */
	struct io_wq_work_node		comp_list;
	atomic_t			refs;
	struct io_kiocb			*link;
	struct io_task_work		io_task_work;
	/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
	struct hlist_node		hash_node;
	/* internal polling, see IORING_FEAT_FAST_POLL */
	struct async_poll		*apoll;
	/* opcode allocated if it needs to store data for async defer */
	void				*async_data;
	struct io_wq_work		work;
	/* custom credentials, valid IFF REQ_F_CREDS is set */
	const struct cred		*creds;
	/* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
	struct io_buffer		*kbuf;
	atomic_t			poll_refs;
};

struct io_tctx_node {
	struct list_head	ctx_node;
	struct task_struct	*task;
	struct io_ring_ctx	*ctx;
};

struct io_defer_entry {
	struct list_head	list;
	struct io_kiocb		*req;
	u32			seq;
};

struct io_op_def {
	/* needs req->file assigned */
	unsigned		needs_file : 1;
	/* should block plug */
	unsigned		plug : 1;
	/* hash wq insertion if file is a regular file */
	unsigned		hash_reg_file : 1;
	/* unbound wq insertion if file is a non-regular file */
	unsigned		unbound_nonreg_file : 1;
	/* set if opcode supports polled "wait" */
	unsigned		pollin : 1;
	unsigned		pollout : 1;
	/* op supports buffer selection */
	unsigned		buffer_select : 1;
	/* do prep async if is going to be punted */
	unsigned		needs_async_setup : 1;
	/* opcode is not supported by this kernel */
	unsigned		not_supported : 1;
	/* skip auditing */
	unsigned		audit_skip : 1;
	/* size of async data needed, if any */
	unsigned short		async_size;
};

static const struct io_op_def io_op_defs[] = {
	[IORING_OP_NOP] = {},
	[IORING_OP_READV] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.needs_async_setup	= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_WRITEV] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.needs_async_setup	= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_FSYNC] = {
		.needs_file		= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_READ_FIXED] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_WRITE_FIXED] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_POLL_ADD] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_POLL_REMOVE] = {
		.audit_skip		= 1,
	},
	[IORING_OP_SYNC_FILE_RANGE] = {
		.needs_file		= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_SENDMSG] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.needs_async_setup	= 1,
		.async_size		= sizeof(struct io_async_msghdr),
	},
	[IORING_OP_RECVMSG] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.needs_async_setup	= 1,
		.async_size		= sizeof(struct io_async_msghdr),
	},
	[IORING_OP_TIMEOUT] = {
		.audit_skip		= 1,
		.async_size		= sizeof(struct io_timeout_data),
	},
	[IORING_OP_TIMEOUT_REMOVE] = {
		/* used by timeout updates' prep() */
		.audit_skip		= 1,
	},
	[IORING_OP_ACCEPT] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
	},
	[IORING_OP_ASYNC_CANCEL] = {
		.audit_skip		= 1,
	},
	[IORING_OP_LINK_TIMEOUT] = {
		.audit_skip		= 1,
		.async_size		= sizeof(struct io_timeout_data),
	},
	[IORING_OP_CONNECT] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.needs_async_setup	= 1,
		.async_size		= sizeof(struct io_async_connect),
	},
	[IORING_OP_FALLOCATE] = {
		.needs_file		= 1,
	},
	[IORING_OP_OPENAT] = {},
	[IORING_OP_CLOSE] = {},
	[IORING_OP_FILES_UPDATE] = {
		.audit_skip		= 1,
	},
	[IORING_OP_STATX] = {
		.audit_skip		= 1,
	},
	[IORING_OP_READ] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_WRITE] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_FADVISE] = {
		.needs_file		= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_MADVISE] = {},
	[IORING_OP_SEND] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_RECV] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_OPENAT2] = {
	},
	[IORING_OP_EPOLL_CTL] = {
		.unbound_nonreg_file	= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_SPLICE] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_PROVIDE_BUFFERS] = {
		.audit_skip		= 1,
	},
	[IORING_OP_REMOVE_BUFFERS] = {
		.audit_skip		= 1,
	},
	[IORING_OP_TEE] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_SHUTDOWN] = {
		.needs_file		= 1,
	},
	[IORING_OP_RENAMEAT] = {},
	[IORING_OP_UNLINKAT] = {},
	[IORING_OP_MKDIRAT] = {},
	[IORING_OP_SYMLINKAT] = {},
	[IORING_OP_LINKAT] = {},
};

/* requests with any of those set should undergo io_disarm_next() */
#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL)

static bool io_disarm_next(struct io_kiocb *req);
static void io_uring_del_tctx_node(unsigned long index);
static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
					 struct task_struct *task,
					 bool cancel_all);
static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);

static void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags);

static void io_put_req(struct io_kiocb *req);
static void io_put_req_deferred(struct io_kiocb *req);
static void io_dismantle_req(struct io_kiocb *req);
static void io_queue_linked_timeout(struct io_kiocb *req);
static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
				     struct io_uring_rsrc_update2 *up,
				     unsigned nr_args);
static void io_clean_op(struct io_kiocb *req);
static struct file *io_file_get(struct io_ring_ctx *ctx,
				struct io_kiocb *req, int fd, bool fixed);
static void __io_queue_sqe(struct io_kiocb *req);
static void io_rsrc_put_work(struct work_struct *work);

static void io_req_task_queue(struct io_kiocb *req);
static void __io_submit_flush_completions(struct io_ring_ctx *ctx);
static int io_req_prep_async(struct io_kiocb *req);

static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
				 unsigned int issue_flags, u32 slot_index);
static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags);

static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer);

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 inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
{
	if (!*locked) {
		mutex_lock(&ctx->uring_lock);
		*locked = true;
	}
}

#define io_for_each_link(pos, head) \
	for (pos = (head); pos; pos = pos->link)

/*
 * Shamelessly stolen from the mm implementation of page reference checking,
 * see commit f958d7b528b1 for details.
 */
#define req_ref_zero_or_close_to_overflow(req)	\
	((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u)

static inline bool req_ref_inc_not_zero(struct io_kiocb *req)
{
	WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT));
	return atomic_inc_not_zero(&req->refs);
}

static inline bool req_ref_put_and_test(struct io_kiocb *req)
{
	if (likely(!(req->flags & REQ_F_REFCOUNT)))
		return true;

	WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
	return atomic_dec_and_test(&req->refs);
}

static inline void req_ref_get(struct io_kiocb *req)
{
	WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT));
	WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
	atomic_inc(&req->refs);
}

static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
{
	if (!wq_list_empty(&ctx->submit_state.compl_reqs))
		__io_submit_flush_completions(ctx);
}

static inline void __io_req_set_refcount(struct io_kiocb *req, int nr)
{
	if (!(req->flags & REQ_F_REFCOUNT)) {
		req->flags |= REQ_F_REFCOUNT;
		atomic_set(&req->refs, nr);
	}
}

static inline void io_req_set_refcount(struct io_kiocb *req)
{
	__io_req_set_refcount(req, 1);
}

#define IO_RSRC_REF_BATCH	100

static inline void io_req_put_rsrc_locked(struct io_kiocb *req,
					  struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	struct percpu_ref *ref = req->fixed_rsrc_refs;

	if (ref) {
		if (ref == &ctx->rsrc_node->refs)
			ctx->rsrc_cached_refs++;
		else
			percpu_ref_put(ref);
	}
}

static inline void io_req_put_rsrc(struct io_kiocb *req, struct io_ring_ctx *ctx)
{
	if (req->fixed_rsrc_refs)
		percpu_ref_put(req->fixed_rsrc_refs);
}

static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	if (ctx->rsrc_cached_refs) {
		percpu_ref_put_many(&ctx->rsrc_node->refs, ctx->rsrc_cached_refs);
		ctx->rsrc_cached_refs = 0;
	}
}

static void io_rsrc_refs_refill(struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	ctx->rsrc_cached_refs += IO_RSRC_REF_BATCH;
	percpu_ref_get_many(&ctx->rsrc_node->refs, IO_RSRC_REF_BATCH);
}

static inline void io_req_set_rsrc_node(struct io_kiocb *req,
					struct io_ring_ctx *ctx)
{
	if (!req->fixed_rsrc_refs) {
		req->fixed_rsrc_refs = &ctx->rsrc_node->refs;
		ctx->rsrc_cached_refs--;
		if (unlikely(ctx->rsrc_cached_refs < 0))
			io_rsrc_refs_refill(ctx);
	}
}

static unsigned int __io_put_kbuf(struct io_kiocb *req)
{
	struct io_buffer *kbuf = req->kbuf;
	unsigned int cflags;

	cflags = kbuf->bid << IORING_CQE_BUFFER_SHIFT;
	cflags |= IORING_CQE_F_BUFFER;
	req->flags &= ~REQ_F_BUFFER_SELECTED;
	kfree(kbuf);
	req->kbuf = NULL;
	return cflags;
}

static inline unsigned int io_put_kbuf(struct io_kiocb *req)
{
	if (likely(!(req->flags & REQ_F_BUFFER_SELECTED)))
		return 0;
	return __io_put_kbuf(req);
}

static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl)
{
	bool got = percpu_ref_tryget(ref);

	/* already at zero, wait for ->release() */
	if (!got)
		wait_for_completion(compl);
	percpu_ref_resurrect(ref);
	if (got)
		percpu_ref_put(ref);
}

static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
			  bool cancel_all)
	__must_hold(&req->ctx->timeout_lock)
{
	struct io_kiocb *req;

	if (task && head->task != task)
		return false;
	if (cancel_all)
		return true;

	io_for_each_link(req, head) {
		if (req->flags & REQ_F_INFLIGHT)
			return true;
	}
	return false;
}

static bool io_match_linked(struct io_kiocb *head)
{
	struct io_kiocb *req;

	io_for_each_link(req, head) {
		if (req->flags & REQ_F_INFLIGHT)
			return true;
	}
	return false;
}

/*
 * As io_match_task() but protected against racing with linked timeouts.
 * User must not hold timeout_lock.
 */
static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
			       bool cancel_all)
{
	bool matched;

	if (task && head->task != task)
		return false;
	if (cancel_all)
		return true;

	if (head->flags & REQ_F_LINK_TIMEOUT) {
		struct io_ring_ctx *ctx = head->ctx;

		/* protect against races with linked timeouts */
		spin_lock_irq(&ctx->timeout_lock);
		matched = io_match_linked(head);
		spin_unlock_irq(&ctx->timeout_lock);
	} else {
		matched = io_match_linked(head);
	}
	return matched;
}

static inline bool req_has_async_data(struct io_kiocb *req)
{
	return req->flags & REQ_F_ASYNC_DATA;
}

static inline void req_set_fail(struct io_kiocb *req)
{
	req->flags |= REQ_F_FAIL;
	if (req->flags & REQ_F_CQE_SKIP) {
		req->flags &= ~REQ_F_CQE_SKIP;
		req->flags |= REQ_F_SKIP_LINK_CQES;
	}
}

static inline void req_fail_link_node(struct io_kiocb *req, int res)
{
	req_set_fail(req);
	req->result = res;
}

static __cold 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->ref_comp);
}

static inline bool io_is_timeout_noseq(struct io_kiocb *req)
{
	return !req->timeout.off;
}

static __cold void io_fallback_req_func(struct work_struct *work)
{
	struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx,
						fallback_work.work);
	struct llist_node *node = llist_del_all(&ctx->fallback_llist);
	struct io_kiocb *req, *tmp;
	bool locked = false;

	percpu_ref_get(&ctx->refs);
	llist_for_each_entry_safe(req, tmp, node, io_task_work.fallback_node)
		req->io_task_work.func(req, &locked);

	if (locked) {
		io_submit_flush_completions(ctx);
		mutex_unlock(&ctx->uring_lock);
	}
	percpu_ref_put(&ctx->refs);
}

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

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

	/*
	 * Use 5 bits less than the max cq entries, that should give us around
	 * 32 entries per hash list if totally full and uniformly spread.
	 */
	hash_bits = ilog2(p->cq_entries);
	hash_bits -= 5;
	if (hash_bits <= 0)
		hash_bits = 1;
	ctx->cancel_hash_bits = hash_bits;
	ctx->cancel_hash = kmalloc((1U << hash_bits) * sizeof(struct hlist_head),
					GFP_KERNEL);
	if (!ctx->cancel_hash)
		goto err;
	__hash_init(ctx->cancel_hash, 1U << hash_bits);

	ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL);
	if (!ctx->dummy_ubuf)
		goto err;
	/* set invalid range, so io_import_fixed() fails meeting it */
	ctx->dummy_ubuf->ubuf = -1UL;

	if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free,
			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
		goto err;

	ctx->flags = p->flags;
	init_waitqueue_head(&ctx->sqo_sq_wait);
	INIT_LIST_HEAD(&ctx->sqd_list);
	INIT_LIST_HEAD(&ctx->cq_overflow_list);
	init_completion(&ctx->ref_comp);
	xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1);
	xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
	mutex_init(&ctx->uring_lock);
	init_waitqueue_head(&ctx->cq_wait);
	spin_lock_init(&ctx->completion_lock);
	spin_lock_init(&ctx->timeout_lock);
	INIT_WQ_LIST(&ctx->iopoll_list);
	INIT_LIST_HEAD(&ctx->defer_list);
	INIT_LIST_HEAD(&ctx->timeout_list);
	INIT_LIST_HEAD(&ctx->ltimeout_list);
	spin_lock_init(&ctx->rsrc_ref_lock);
	INIT_LIST_HEAD(&ctx->rsrc_ref_list);
	INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work);
	init_llist_head(&ctx->rsrc_put_llist);
	INIT_LIST_HEAD(&ctx->tctx_list);
	ctx->submit_state.free_list.next = NULL;
	INIT_WQ_LIST(&ctx->locked_free_list);
	INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
	INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
	return ctx;
err:
	kfree(ctx->dummy_ubuf);
	kfree(ctx->cancel_hash);
	kfree(ctx);
	return NULL;
}

static void io_account_cq_overflow(struct io_ring_ctx *ctx)
{
	struct io_rings *r = ctx->rings;

	WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1);
	ctx->cq_extra--;
}

static bool req_need_defer(struct io_kiocb *req, u32 seq)
{
	if (unlikely(req->flags & REQ_F_IO_DRAIN)) {
		struct io_ring_ctx *ctx = req->ctx;

		return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail;
	}

	return false;
}

#define FFS_NOWAIT		0x1UL
#define FFS_ISREG		0x2UL
#define FFS_MASK		~(FFS_NOWAIT|FFS_ISREG)

static inline bool io_req_ffs_set(struct io_kiocb *req)
{
	return req->flags & REQ_F_FIXED_FILE;
}

static inline void io_req_track_inflight(struct io_kiocb *req)
{
	if (!(req->flags & REQ_F_INFLIGHT)) {
		req->flags |= REQ_F_INFLIGHT;
		atomic_inc(&current->io_uring->inflight_tracked);
	}
}

static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
{
	if (WARN_ON_ONCE(!req->link))
		return NULL;

	req->flags &= ~REQ_F_ARM_LTIMEOUT;
	req->flags |= REQ_F_LINK_TIMEOUT;

	/* linked timeouts should have two refs once prep'ed */
	io_req_set_refcount(req);
	__io_req_set_refcount(req->link, 2);
	return req->link;
}

static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
{
	if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT)))
		return NULL;
	return __io_prep_linked_timeout(req);
}

static void io_prep_async_work(struct io_kiocb *req)
{
	const struct io_op_def *def = &io_op_defs[req->opcode];
	struct io_ring_ctx *ctx = req->ctx;

	if (!(req->flags & REQ_F_CREDS)) {
		req->flags |= REQ_F_CREDS;
		req->creds = get_current_cred();
	}

	req->work.list.next = NULL;
	req->work.flags = 0;
	if (req->flags & REQ_F_FORCE_ASYNC)
		req->work.flags |= IO_WQ_WORK_CONCURRENT;

	if (req->flags & REQ_F_ISREG) {
		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
			io_wq_hash_work(&req->work, file_inode(req->file));
	} else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) {
		if (def->unbound_nonreg_file)
			req->work.flags |= IO_WQ_WORK_UNBOUND;
	}

	switch (req->opcode) {
	case IORING_OP_SPLICE:
	case IORING_OP_TEE:
		if (!S_ISREG(file_inode(req->splice.file_in)->i_mode))
			req->work.flags |= IO_WQ_WORK_UNBOUND;
		break;
	}
}

static void io_prep_async_link(struct io_kiocb *req)
{
	struct io_kiocb *cur;

	if (req->flags & REQ_F_LINK_TIMEOUT) {
		struct io_ring_ctx *ctx = req->ctx;

		spin_lock_irq(&ctx->timeout_lock);
		io_for_each_link(cur, req)
			io_prep_async_work(cur);
		spin_unlock_irq(&ctx->timeout_lock);
	} else {
		io_for_each_link(cur, req)
			io_prep_async_work(cur);
	}
}

static inline void io_req_add_compl_list(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_submit_state *state = &ctx->submit_state;

	if (!(req->flags & REQ_F_CQE_SKIP))
		ctx->submit_state.flush_cqes = true;
	wq_list_add_tail(&req->comp_list, &state->compl_reqs);
}

static void io_queue_async_work(struct io_kiocb *req, bool *dont_use)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_kiocb *link = io_prep_linked_timeout(req);
	struct io_uring_task *tctx = req->task->io_uring;

	BUG_ON(!tctx);
	BUG_ON(!tctx->io_wq);

	/* init ->work of the whole link before punting */
	io_prep_async_link(req);

	/*
	 * Not expected to happen, but if we do have a bug where this _can_
	 * happen, catch it here and ensure the request is marked as
	 * canceled. That will make io-wq go through the usual work cancel
	 * procedure rather than attempt to run this request (or create a new
	 * worker for it).
	 */
	if (WARN_ON_ONCE(!same_thread_group(req->task, current)))
		req->work.flags |= IO_WQ_WORK_CANCEL;

	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
					&req->work, req->flags);
	io_wq_enqueue(tctx->io_wq, &req->work);
	if (link)
		io_queue_linked_timeout(link);
}

static void io_kill_timeout(struct io_kiocb *req, int status)
	__must_hold(&req->ctx->completion_lock)
	__must_hold(&req->ctx->timeout_lock)
{
	struct io_timeout_data *io = req->async_data;

	if (hrtimer_try_to_cancel(&io->timer) != -1) {
		if (status)
			req_set_fail(req);
		atomic_set(&req->ctx->cq_timeouts,
			atomic_read(&req->ctx->cq_timeouts) + 1);
		list_del_init(&req->timeout.list);
		io_fill_cqe_req(req, status, 0);
		io_put_req_deferred(req);
	}
}

static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
{
	while (!list_empty(&ctx->defer_list)) {
		struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
						struct io_defer_entry, list);

		if (req_need_defer(de->req, de->seq))
			break;
		list_del_init(&de->list);
		io_req_task_queue(de->req);
		kfree(de);
	}
}

static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
	__must_hold(&ctx->completion_lock)
{
	u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);

	spin_lock_irq(&ctx->timeout_lock);
	while (!list_empty(&ctx->timeout_list)) {
		u32 events_needed, events_got;
		struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
						struct io_kiocb, timeout.list);

		if (io_is_timeout_noseq(req))
			break;

		/*
		 * Since seq can easily wrap around over time, subtract
		 * the last seq at which timeouts were flushed before comparing.
		 * Assuming not more than 2^31-1 events have happened since,
		 * these subtractions won't have wrapped, so we can check if
		 * target is in [last_seq, current_seq] by comparing the two.
		 */
		events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush;
		events_got = seq - ctx->cq_last_tm_flush;
		if (events_got < events_needed)
			break;

		list_del_init(&req->timeout.list);
		io_kill_timeout(req, 0);
	}
	ctx->cq_last_tm_flush = seq;
	spin_unlock_irq(&ctx->timeout_lock);
}

static __cold void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
{
	if (ctx->off_timeout_used)
		io_flush_timeouts(ctx);
	if (ctx->drain_active)
		io_queue_deferred(ctx);
}

static inline void io_commit_cqring(struct io_ring_ctx *ctx)
{
	if (unlikely(ctx->off_timeout_used || ctx->drain_active))
		__io_commit_cqring_flush(ctx);
	/* order cqe stores with ring update */
	smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail);
}

static inline bool io_sqring_full(struct io_ring_ctx *ctx)
{
	struct io_rings *r = ctx->rings;

	return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries;
}

static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
{
	return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
}

static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx)
{
	struct io_rings *rings = ctx->rings;
	unsigned tail, mask = ctx->cq_entries - 1;

	/*
	 * 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 (__io_cqring_events(ctx) == ctx->cq_entries)
		return NULL;

	tail = ctx->cached_cq_tail++;
	return &rings->cqes[tail & mask];
}

static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
{
	if (likely(!ctx->cq_ev_fd))
		return false;
	if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
		return false;
	return !ctx->eventfd_async || io_wq_current_is_worker();
}

/*
 * This should only get called when at least one event has been posted.
 * Some applications rely on the eventfd notification count only changing
 * IFF a new CQE has been added to the CQ ring. There's no depedency on
 * 1:1 relationship between how many times this function is called (and
 * hence the eventfd count) and number of CQEs posted to the CQ ring.
 */
static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
{
	/*
	 * wake_up_all() may seem excessive, but io_wake_function() and
	 * io_should_wake() handle the termination of the loop and only
	 * wake as many waiters as we need to.
	 */
	if (wq_has_sleeper(&ctx->cq_wait))
		wake_up_all(&ctx->cq_wait);
	if (io_should_trigger_evfd(ctx))
		eventfd_signal(ctx->cq_ev_fd, 1);
}

static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
{
	/* see waitqueue_active() comment */
	smp_mb();

	if (ctx->flags & IORING_SETUP_SQPOLL) {
		if (waitqueue_active(&ctx->cq_wait))
			wake_up_all(&ctx->cq_wait);
	}
	if (io_should_trigger_evfd(ctx))
		eventfd_signal(ctx->cq_ev_fd, 1);
}

/* Returns true if there are no backlogged entries after the flush */
static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
	bool all_flushed, posted;

	if (!force && __io_cqring_events(ctx) == ctx->cq_entries)
		return false;

	posted = false;
	spin_lock(&ctx->completion_lock);
	while (!list_empty(&ctx->cq_overflow_list)) {
		struct io_uring_cqe *cqe = io_get_cqe(ctx);
		struct io_overflow_cqe *ocqe;

		if (!cqe && !force)
			break;
		ocqe = list_first_entry(&ctx->cq_overflow_list,
					struct io_overflow_cqe, list);
		if (cqe)
			memcpy(cqe, &ocqe->cqe, sizeof(*cqe));
		else
			io_account_cq_overflow(ctx);

		posted = true;
		list_del(&ocqe->list);
		kfree(ocqe);
	}

	all_flushed = list_empty(&ctx->cq_overflow_list);
	if (all_flushed) {
		clear_bit(0, &ctx->check_cq_overflow);
		WRITE_ONCE(ctx->rings->sq_flags,
			   ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW);
	}

	if (posted)
		io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	if (posted)
		io_cqring_ev_posted(ctx);
	return all_flushed;
}

static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx)
{
	bool ret = true;

	if (test_bit(0, &ctx->check_cq_overflow)) {
		/* iopoll syncs against uring_lock, not completion_lock */
		if (ctx->flags & IORING_SETUP_IOPOLL)
			mutex_lock(&ctx->uring_lock);
		ret = __io_cqring_overflow_flush(ctx, false);
		if (ctx->flags & IORING_SETUP_IOPOLL)
			mutex_unlock(&ctx->uring_lock);
	}

	return ret;
}

/* must to be called somewhat shortly after putting a request */
static inline void io_put_task(struct task_struct *task, int nr)
{
	struct io_uring_task *tctx = task->io_uring;

	if (likely(task == current)) {
		tctx->cached_refs += nr;
	} else {
		percpu_counter_sub(&tctx->inflight, nr);
		if (unlikely(atomic_read(&tctx->in_idle)))
			wake_up(&tctx->wait);
		put_task_struct_many(task, nr);
	}
}

static void io_task_refs_refill(struct io_uring_task *tctx)
{
	unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR;

	percpu_counter_add(&tctx->inflight, refill);
	refcount_add(refill, &current->usage);
	tctx->cached_refs += refill;
}

static inline void io_get_task_refs(int nr)
{
	struct io_uring_task *tctx = current->io_uring;

	tctx->cached_refs -= nr;
	if (unlikely(tctx->cached_refs < 0))
		io_task_refs_refill(tctx);
}

static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
{
	struct io_uring_task *tctx = task->io_uring;
	unsigned int refs = tctx->cached_refs;

	if (refs) {
		tctx->cached_refs = 0;
		percpu_counter_sub(&tctx->inflight, refs);
		put_task_struct_many(task, refs);
	}
}

static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
				     s32 res, u32 cflags)
{
	struct io_overflow_cqe *ocqe;

	ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT);
	if (!ocqe) {
		/*
		 * If we're in ring overflow flush mode, or in task cancel mode,
		 * or cannot allocate an overflow entry, then we need to drop it
		 * on the floor.
		 */
		io_account_cq_overflow(ctx);
		return false;
	}
	if (list_empty(&ctx->cq_overflow_list)) {
		set_bit(0, &ctx->check_cq_overflow);
		WRITE_ONCE(ctx->rings->sq_flags,
			   ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW);

	}
	ocqe->cqe.user_data = user_data;
	ocqe->cqe.res = res;
	ocqe->cqe.flags = cflags;
	list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
	return true;
}

static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data,
				 s32 res, u32 cflags)
{
	struct io_uring_cqe *cqe;

	trace_io_uring_complete(ctx, user_data, res, cflags);

	/*
	 * 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_cqe(ctx);
	if (likely(cqe)) {
		WRITE_ONCE(cqe->user_data, user_data);
		WRITE_ONCE(cqe->res, res);
		WRITE_ONCE(cqe->flags, cflags);
		return true;
	}
	return io_cqring_event_overflow(ctx, user_data, res, cflags);
}

static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags)
{
	if (!(req->flags & REQ_F_CQE_SKIP))
		__io_fill_cqe(req->ctx, req->user_data, res, cflags);
}

static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data,
				     s32 res, u32 cflags)
{
	ctx->cq_extra++;
	return __io_fill_cqe(ctx, user_data, res, cflags);
}

static void __io_req_complete_post(struct io_kiocb *req, s32 res,
				   u32 cflags)
{
	struct io_ring_ctx *ctx = req->ctx;

	if (!(req->flags & REQ_F_CQE_SKIP))
		__io_fill_cqe(ctx, req->user_data, res, cflags);
	/*
	 * If we're the last reference to this request, add to our locked
	 * free_list cache.
	 */
	if (req_ref_put_and_test(req)) {
		if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
			if (req->flags & IO_DISARM_MASK)
				io_disarm_next(req);
			if (req->link) {
				io_req_task_queue(req->link);
				req->link = NULL;
			}
		}
		io_req_put_rsrc(req, ctx);
		io_dismantle_req(req);
		io_put_task(req->task, 1);
		wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
		ctx->locked_free_nr++;
	}
}

static void io_req_complete_post(struct io_kiocb *req, s32 res,
				 u32 cflags)
{
	struct io_ring_ctx *ctx = req->ctx;

	spin_lock(&ctx->completion_lock);
	__io_req_complete_post(req, res, cflags);
	io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	io_cqring_ev_posted(ctx);
}

static inline void io_req_complete_state(struct io_kiocb *req, s32 res,
					 u32 cflags)
{
	req->result = res;
	req->cflags = cflags;
	req->flags |= REQ_F_COMPLETE_INLINE;
}

static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
				     s32 res, u32 cflags)
{
	if (issue_flags & IO_URING_F_COMPLETE_DEFER)
		io_req_complete_state(req, res, cflags);
	else
		io_req_complete_post(req, res, cflags);
}

static inline void io_req_complete(struct io_kiocb *req, s32 res)
{
	__io_req_complete(req, 0, res, 0);
}

static void io_req_complete_failed(struct io_kiocb *req, s32 res)
{
	req_set_fail(req);
	io_req_complete_post(req, res, 0);
}

static void io_req_complete_fail_submit(struct io_kiocb *req)
{
	/*
	 * We don't submit, fail them all, for that replace hardlinks with
	 * normal links. Extra REQ_F_LINK is tolerated.
	 */
	req->flags &= ~REQ_F_HARDLINK;
	req->flags |= REQ_F_LINK;
	io_req_complete_failed(req, req->result);
}

/*
 * Don't initialise the fields below on every allocation, but do that in
 * advance and keep them valid across allocations.
 */
static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx)
{
	req->ctx = ctx;
	req->link = NULL;
	req->async_data = NULL;
	/* not necessary, but safer to zero */
	req->result = 0;
}

static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
					struct io_submit_state *state)
{
	spin_lock(&ctx->completion_lock);
	wq_list_splice(&ctx->locked_free_list, &state->free_list);
	ctx->locked_free_nr = 0;
	spin_unlock(&ctx->completion_lock);
}

/* Returns true IFF there are requests in the cache */
static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
{
	struct io_submit_state *state = &ctx->submit_state;

	/*
	 * If we have more than a batch's worth of requests in our IRQ side
	 * locked cache, grab the lock and move them over to our submission
	 * side cache.
	 */
	if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH)
		io_flush_cached_locked_reqs(ctx, state);
	return !!state->free_list.next;
}

/*
 * A request might get retired back into the request caches even before opcode
 * handlers and io_issue_sqe() are done with it, e.g. inline completion path.
 * Because of that, io_alloc_req() should be called only under ->uring_lock
 * and with extra caution to not get a request that is still worked on.
 */
static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	struct io_submit_state *state = &ctx->submit_state;
	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
	void *reqs[IO_REQ_ALLOC_BATCH];
	struct io_kiocb *req;
	int ret, i;

	if (likely(state->free_list.next || io_flush_cached_reqs(ctx)))
		return true;

	ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), 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)) {
		reqs[0] = kmem_cache_alloc(req_cachep, gfp);
		if (!reqs[0])
			return false;
		ret = 1;
	}

	percpu_ref_get_many(&ctx->refs, ret);
	for (i = 0; i < ret; i++) {
		req = reqs[i];

		io_preinit_req(req, ctx);
		wq_stack_add_head(&req->comp_list, &state->free_list);
	}
	return true;
}

static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx)
{
	if (unlikely(!ctx->submit_state.free_list.next))
		return __io_alloc_req_refill(ctx);
	return true;
}

static inline struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
{
	struct io_wq_work_node *node;

	node = wq_stack_extract(&ctx->submit_state.free_list);
	return container_of(node, struct io_kiocb, comp_list);
}

static inline void io_put_file(struct file *file)
{
	if (file)
		fput(file);
}

static inline void io_dismantle_req(struct io_kiocb *req)
{
	unsigned int flags = req->flags;

	if (unlikely(flags & IO_REQ_CLEAN_FLAGS))
		io_clean_op(req);
	if (!(flags & REQ_F_FIXED_FILE))
		io_put_file(req->file);
}

static __cold void __io_free_req(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;

	io_req_put_rsrc(req, ctx);
	io_dismantle_req(req);
	io_put_task(req->task, 1);

	spin_lock(&ctx->completion_lock);
	wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
	ctx->locked_free_nr++;
	spin_unlock(&ctx->completion_lock);
}

static inline void io_remove_next_linked(struct io_kiocb *req)
{
	struct io_kiocb *nxt = req->link;

	req->link = nxt->link;
	nxt->link = NULL;
}

static bool io_kill_linked_timeout(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
	__must_hold(&req->ctx->timeout_lock)
{
	struct io_kiocb *link = req->link;

	if (link && link->opcode == IORING_OP_LINK_TIMEOUT) {
		struct io_timeout_data *io = link->async_data;

		io_remove_next_linked(req);
		link->timeout.head = NULL;
		if (hrtimer_try_to_cancel(&io->timer) != -1) {
			list_del(&link->timeout.list);
			/* leave REQ_F_CQE_SKIP to io_fill_cqe_req */
			io_fill_cqe_req(link, -ECANCELED, 0);
			io_put_req_deferred(link);
			return true;
		}
	}
	return false;
}

static void io_fail_links(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	struct io_kiocb *nxt, *link = req->link;
	bool ignore_cqes = req->flags & REQ_F_SKIP_LINK_CQES;

	req->link = NULL;
	while (link) {
		long res = -ECANCELED;

		if (link->flags & REQ_F_FAIL)
			res = link->result;

		nxt = link->link;
		link->link = NULL;

		trace_io_uring_fail_link(req, link);
		if (!ignore_cqes) {
			link->flags &= ~REQ_F_CQE_SKIP;
			io_fill_cqe_req(link, res, 0);
		}
		io_put_req_deferred(link);
		link = nxt;
	}
}

static bool io_disarm_next(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	bool posted = false;

	if (req->flags & REQ_F_ARM_LTIMEOUT) {
		struct io_kiocb *link = req->link;

		req->flags &= ~REQ_F_ARM_LTIMEOUT;
		if (link && link->opcode == IORING_OP_LINK_TIMEOUT) {
			io_remove_next_linked(req);
			/* leave REQ_F_CQE_SKIP to io_fill_cqe_req */
			io_fill_cqe_req(link, -ECANCELED, 0);
			io_put_req_deferred(link);
			posted = true;
		}
	} else if (req->flags & REQ_F_LINK_TIMEOUT) {
		struct io_ring_ctx *ctx = req->ctx;

		spin_lock_irq(&ctx->timeout_lock);
		posted = io_kill_linked_timeout(req);
		spin_unlock_irq(&ctx->timeout_lock);
	}
	if (unlikely((req->flags & REQ_F_FAIL) &&
		     !(req->flags & REQ_F_HARDLINK))) {
		posted |= (req->link != NULL);
		io_fail_links(req);
	}
	return posted;
}

static void __io_req_find_next_prep(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	bool posted;

	spin_lock(&ctx->completion_lock);
	posted = io_disarm_next(req);
	if (posted)
		io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	if (posted)
		io_cqring_ev_posted(ctx);
}

static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
{
	struct io_kiocb *nxt;

	if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK))))
		return NULL;
	/*
	 * If LINK is set, we have dependent requests in this chain. If we
	 * didn't fail this request, queue the first one up, moving any other
	 * dependencies to the next request. In case of failure, fail the rest
	 * of the chain.
	 */
	if (unlikely(req->flags & IO_DISARM_MASK))
		__io_req_find_next_prep(req);
	nxt = req->link;
	req->link = NULL;
	return nxt;
}

static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked)
{
	if (!ctx)
		return;
	if (*locked) {
		io_submit_flush_completions(ctx);
		mutex_unlock(&ctx->uring_lock);
		*locked = false;
	}
	percpu_ref_put(&ctx->refs);
}

static inline void ctx_commit_and_unlock(struct io_ring_ctx *ctx)
{
	io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	io_cqring_ev_posted(ctx);
}

static void handle_prev_tw_list(struct io_wq_work_node *node,
				struct io_ring_ctx **ctx, bool *uring_locked)
{
	if (*ctx && !*uring_locked)
		spin_lock(&(*ctx)->completion_lock);

	do {
		struct io_wq_work_node *next = node->next;
		struct io_kiocb *req = container_of(node, struct io_kiocb,
						    io_task_work.node);

		if (req->ctx != *ctx) {
			if (unlikely(!*uring_locked && *ctx))
				ctx_commit_and_unlock(*ctx);

			ctx_flush_and_put(*ctx, uring_locked);
			*ctx = req->ctx;
			/* if not contended, grab and improve batching */
			*uring_locked = mutex_trylock(&(*ctx)->uring_lock);
			percpu_ref_get(&(*ctx)->refs);
			if (unlikely(!*uring_locked))
				spin_lock(&(*ctx)->completion_lock);
		}
		if (likely(*uring_locked))
			req->io_task_work.func(req, uring_locked);
		else
			__io_req_complete_post(req, req->result, io_put_kbuf(req));
		node = next;
	} while (node);

	if (unlikely(!*uring_locked))
		ctx_commit_and_unlock(*ctx);
}

static void handle_tw_list(struct io_wq_work_node *node,
			   struct io_ring_ctx **ctx, bool *locked)
{
	do {
		struct io_wq_work_node *next = node->next;
		struct io_kiocb *req = container_of(node, struct io_kiocb,
						    io_task_work.node);

		if (req->ctx != *ctx) {
			ctx_flush_and_put(*ctx, locked);
			*ctx = req->ctx;
			/* if not contended, grab and improve batching */
			*locked = mutex_trylock(&(*ctx)->uring_lock);
			percpu_ref_get(&(*ctx)->refs);
		}
		req->io_task_work.func(req, locked);
		node = next;
	} while (node);
}

static void tctx_task_work(struct callback_head *cb)
{
	bool uring_locked = false;
	struct io_ring_ctx *ctx = NULL;
	struct io_uring_task *tctx = container_of(cb, struct io_uring_task,
						  task_work);

	while (1) {
		struct io_wq_work_node *node1, *node2;

		if (!tctx->task_list.first &&
		    !tctx->prior_task_list.first && uring_locked)
			io_submit_flush_completions(ctx);

		spin_lock_irq(&tctx->task_lock);
		node1 = tctx->prior_task_list.first;
		node2 = tctx->task_list.first;
		INIT_WQ_LIST(&tctx->task_list);
		INIT_WQ_LIST(&tctx->prior_task_list);
		if (!node2 && !node1)
			tctx->task_running = false;
		spin_unlock_irq(&tctx->task_lock);
		if (!node2 && !node1)
			break;

		if (node1)
			handle_prev_tw_list(node1, &ctx, &uring_locked);

		if (node2)
			handle_tw_list(node2, &ctx, &uring_locked);
		cond_resched();
	}

	ctx_flush_and_put(ctx, &uring_locked);

	/* relaxed read is enough as only the task itself sets ->in_idle */
	if (unlikely(atomic_read(&tctx->in_idle)))
		io_uring_drop_tctx_refs(current);
}

static void io_req_task_work_add(struct io_kiocb *req, bool priority)
{
	struct task_struct *tsk = req->task;
	struct io_uring_task *tctx = tsk->io_uring;
	enum task_work_notify_mode notify;
	struct io_wq_work_node *node;
	unsigned long flags;
	bool running;

	WARN_ON_ONCE(!tctx);

	spin_lock_irqsave(&tctx->task_lock, flags);
	if (priority)
		wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list);
	else
		wq_list_add_tail(&req->io_task_work.node, &tctx->task_list);
	running = tctx->task_running;
	if (!running)
		tctx->task_running = true;
	spin_unlock_irqrestore(&tctx->task_lock, flags);

	/* task_work already pending, we're done */
	if (running)
		return;

	/*
	 * SQPOLL kernel thread doesn't need notification, just a wakeup. For
	 * all other cases, use TWA_SIGNAL unconditionally to ensure we're
	 * processing task_work. There's no reliable way to tell if TWA_RESUME
	 * will do the job.
	 */
	notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL;
	if (likely(!task_work_add(tsk, &tctx->task_work, notify))) {
		if (notify == TWA_NONE)
			wake_up_process(tsk);
		return;
	}

	spin_lock_irqsave(&tctx->task_lock, flags);
	tctx->task_running = false;
	node = wq_list_merge(&tctx->prior_task_list, &tctx->task_list);
	spin_unlock_irqrestore(&tctx->task_lock, flags);

	while (node) {
		req = container_of(node, struct io_kiocb, io_task_work.node);
		node = node->next;
		if (llist_add(&req->io_task_work.fallback_node,
			      &req->ctx->fallback_llist))
			schedule_delayed_work(&req->ctx->fallback_work, 1);
	}
}

static void io_req_task_cancel(struct io_kiocb *req, bool *locked)
{
	struct io_ring_ctx *ctx = req->ctx;

	/* not needed for normal modes, but SQPOLL depends on it */
	io_tw_lock(ctx, locked);
	io_req_complete_failed(req, req->result);
}

static void io_req_task_submit(struct io_kiocb *req, bool *locked)
{
	struct io_ring_ctx *ctx = req->ctx;

	io_tw_lock(ctx, locked);
	/* req->task == current here, checking PF_EXITING is safe */
	if (likely(!(req->task->flags & PF_EXITING)))
		__io_queue_sqe(req);
	else
		io_req_complete_failed(req, -EFAULT);
}

static void io_req_task_queue_fail(struct io_kiocb *req, int ret)
{
	req->result = ret;
	req->io_task_work.func = io_req_task_cancel;
	io_req_task_work_add(req, false);
}

static void io_req_task_queue(struct io_kiocb *req)
{
	req->io_task_work.func = io_req_task_submit;
	io_req_task_work_add(req, false);
}

static void io_req_task_queue_reissue(struct io_kiocb *req)
{
	req->io_task_work.func = io_queue_async_work;
	io_req_task_work_add(req, false);
}

static inline void io_queue_next(struct io_kiocb *req)
{
	struct io_kiocb *nxt = io_req_find_next(req);

	if (nxt)
		io_req_task_queue(nxt);
}

static void io_free_req(struct io_kiocb *req)
{
	io_queue_next(req);
	__io_free_req(req);
}

static void io_free_req_work(struct io_kiocb *req, bool *locked)
{
	io_free_req(req);
}

static void io_free_batch_list(struct io_ring_ctx *ctx,
				struct io_wq_work_node *node)
	__must_hold(&ctx->uring_lock)
{
	struct task_struct *task = NULL;
	int task_refs = 0;

	do {
		struct io_kiocb *req = container_of(node, struct io_kiocb,
						    comp_list);

		if (unlikely(req->flags & REQ_F_REFCOUNT)) {
			node = req->comp_list.next;
			if (!req_ref_put_and_test(req))
				continue;
		}

		io_req_put_rsrc_locked(req, ctx);
		io_queue_next(req);
		io_dismantle_req(req);

		if (req->task != task) {
			if (task)
				io_put_task(task, task_refs);
			task = req->task;
			task_refs = 0;
		}
		task_refs++;
		node = req->comp_list.next;
		wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
	} while (node);

	if (task)
		io_put_task(task, task_refs);
}

static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	struct io_wq_work_node *node, *prev;
	struct io_submit_state *state = &ctx->submit_state;

	if (state->flush_cqes) {
		spin_lock(&ctx->completion_lock);
		wq_list_for_each(node, prev, &state->compl_reqs) {
			struct io_kiocb *req = container_of(node, struct io_kiocb,
						    comp_list);

			if (!(req->flags & REQ_F_CQE_SKIP))
				__io_fill_cqe(ctx, req->user_data, req->result,
					      req->cflags);
		}

		io_commit_cqring(ctx);
		spin_unlock(&ctx->completion_lock);
		io_cqring_ev_posted(ctx);
		state->flush_cqes = false;
	}

	io_free_batch_list(ctx, state->compl_reqs.first);
	INIT_WQ_LIST(&state->compl_reqs);
}

/*
 * Drop reference to request, return next in chain (if there is one) if this
 * was the last reference to this request.
 */
static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req)
{
	struct io_kiocb *nxt = NULL;

	if (req_ref_put_and_test(req)) {
		nxt = io_req_find_next(req);
		__io_free_req(req);
	}
	return nxt;
}

static inline void io_put_req(struct io_kiocb *req)
{
	if (req_ref_put_and_test(req))
		io_free_req(req);
}

static inline void io_put_req_deferred(struct io_kiocb *req)
{
	if (req_ref_put_and_test(req)) {
		req->io_task_work.func = io_free_req_work;
		io_req_task_work_add(req, false);
	}
}

static unsigned io_cqring_events(struct io_ring_ctx *ctx)
{
	/* See comment at the top of this file */
	smp_rmb();
	return __io_cqring_events(ctx);
}

static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
{
	struct io_rings *rings = ctx->rings;

	/* make sure SQ entry isn't read before tail */
	return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
}

static inline bool io_run_task_work(void)
{
	if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) {
		__set_current_state(TASK_RUNNING);
		tracehook_notify_signal();
		return true;
	}

	return false;
}

static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
{
	struct io_wq_work_node *pos, *start, *prev;
	unsigned int poll_flags = BLK_POLL_NOSLEEP;
	DEFINE_IO_COMP_BATCH(iob);
	int nr_events = 0;

	/*
	 * Only spin for completions if we don't have multiple devices hanging
	 * off our complete list.
	 */
	if (ctx->poll_multi_queue || force_nonspin)
		poll_flags |= BLK_POLL_ONESHOT;

	wq_list_for_each(pos, start, &ctx->iopoll_list) {
		struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
		struct kiocb *kiocb = &req->rw.kiocb;
		int ret;

		/*
		 * Move completed and retryable entries to our local lists.
		 * If we find a request that requires polling, break out
		 * and complete those lists first, if we have entries there.
		 */
		if (READ_ONCE(req->iopoll_completed))
			break;

		ret = kiocb->ki_filp->f_op->iopoll(kiocb, &iob, poll_flags);
		if (unlikely(ret < 0))
			return ret;
		else if (ret)
			poll_flags |= BLK_POLL_ONESHOT;

		/* iopoll may have completed current req */
		if (!rq_list_empty(iob.req_list) ||
		    READ_ONCE(req->iopoll_completed))
			break;
	}

	if (!rq_list_empty(iob.req_list))
		iob.complete(&iob);
	else if (!pos)
		return 0;

	prev = start;
	wq_list_for_each_resume(pos, prev) {
		struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);

		/* order with io_complete_rw_iopoll(), e.g. ->result updates */
		if (!smp_load_acquire(&req->iopoll_completed))
			break;
		if (unlikely(req->flags & REQ_F_CQE_SKIP))
			continue;

		__io_fill_cqe(ctx, req->user_data, req->result, io_put_kbuf(req));
		nr_events++;
	}

	if (unlikely(!nr_events))
		return 0;

	io_commit_cqring(ctx);
	io_cqring_ev_posted_iopoll(ctx);
	pos = start ? start->next : ctx->iopoll_list.first;
	wq_list_cut(&ctx->iopoll_list, prev, start);
	io_free_batch_list(ctx, pos);
	return nr_events;
}

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

	mutex_lock(&ctx->uring_lock);
	while (!wq_list_empty(&ctx->iopoll_list)) {
		/* let it sleep and repeat later if can't complete a request */
		if (io_do_iopoll(ctx, true) == 0)
			break;
		/*
		 * Ensure we allow local-to-the-cpu processing to take place,
		 * in this case we need to ensure that we reap all events.
		 * Also let task_work, etc. to progress by releasing the mutex
		 */
		if (need_resched()) {
			mutex_unlock(&ctx->uring_lock);
			cond_resched();
			mutex_lock(&ctx->uring_lock);
		}
	}
	mutex_unlock(&ctx->uring_lock);
}

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

	/*
	 * 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);
	/*
	 * Don't enter poll loop if we already have events pending.
	 * If we do, we can potentially be spinning for commands that
	 * already triggered a CQE (eg in error).
	 */
	if (test_bit(0, &ctx->check_cq_overflow))
		__io_cqring_overflow_flush(ctx, false);
	if (io_cqring_events(ctx))
		goto out;
	do {
		/*
		 * If a submit got punted to a workqueue, we can have the
		 * application entering polling for a command before it gets
		 * issued. That app will hold the uring_lock for the duration
		 * of the poll right here, so we need to take a breather every
		 * now and then to ensure that the issue has a chance to add
		 * the poll to the issued list. Otherwise we can spin here
		 * forever, while the workqueue is stuck trying to acquire the
		 * very same mutex.
		 */
		if (wq_list_empty(&ctx->iopoll_list)) {
			u32 tail = ctx->cached_cq_tail;

			mutex_unlock(&ctx->uring_lock);
			io_run_task_work();
			mutex_lock(&ctx->uring_lock);

			/* some requests don't go through iopoll_list */
			if (tail != ctx->cached_cq_tail ||
			    wq_list_empty(&ctx->iopoll_list))
				break;
		}
		ret = io_do_iopoll(ctx, !min);
		if (ret < 0)
			break;
		nr_events += ret;
		ret = 0;
	} while (nr_events < min && !need_resched());
out:
	mutex_unlock(&ctx->uring_lock);
	return ret;
}

static void kiocb_end_write(struct io_kiocb *req)
{
	/*
	 * Tell lockdep we inherited freeze protection from submission
	 * thread.
	 */
	if (req->flags & REQ_F_ISREG) {
		struct super_block *sb = file_inode(req->file)->i_sb;

		__sb_writers_acquired(sb, SB_FREEZE_WRITE);
		sb_end_write(sb);
	}
}

#ifdef CONFIG_BLOCK
static bool io_resubmit_prep(struct io_kiocb *req)
{
	struct io_async_rw *rw = req->async_data;

	if (!req_has_async_data(req))
		return !io_req_prep_async(req);
	iov_iter_restore(&rw->s.iter, &rw->s.iter_state);
	return true;
}

static bool io_rw_should_reissue(struct io_kiocb *req)
{
	umode_t mode = file_inode(req->file)->i_mode;
	struct io_ring_ctx *ctx = req->ctx;

	if (!S_ISBLK(mode) && !S_ISREG(mode))
		return false;
	if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() &&
	    !(ctx->flags & IORING_SETUP_IOPOLL)))
		return false;
	/*
	 * If ref is dying, we might be running poll reap from the exit work.
	 * Don't attempt to reissue from that path, just let it fail with
	 * -EAGAIN.
	 */
	if (percpu_ref_is_dying(&ctx->refs))
		return false;
	/*
	 * Play it safe and assume not safe to re-import and reissue if we're
	 * not in the original thread group (or in task context).
	 */
	if (!same_thread_group(req->task, current) || !in_task())
		return false;
	return true;
}
#else
static bool io_resubmit_prep(struct io_kiocb *req)
{
	return false;
}
static bool io_rw_should_reissue(struct io_kiocb *req)
{
	return false;
}
#endif

static bool __io_complete_rw_common(struct io_kiocb *req, long res)
{
	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
		kiocb_end_write(req);
	if (unlikely(res != req->result)) {
		if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
		    io_rw_should_reissue(req)) {
			req->flags |= REQ_F_REISSUE;
			return true;
		}
		req_set_fail(req);
		req->result = res;
	}
	return false;
}

static inline void io_req_task_complete(struct io_kiocb *req, bool *locked)
{
	unsigned int cflags = io_put_kbuf(req);
	int res = req->result;

	if (*locked) {
		io_req_complete_state(req, res, cflags);
		io_req_add_compl_list(req);
	} else {
		io_req_complete_post(req, res, cflags);
	}
}

static void __io_complete_rw(struct io_kiocb *req, long res,
			     unsigned int issue_flags)
{
	if (__io_complete_rw_common(req, res))
		return;
	__io_req_complete(req, issue_flags, req->result, io_put_kbuf(req));
}

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

	if (__io_complete_rw_common(req, res))
		return;
	req->result = res;
	req->io_task_work.func = io_req_task_complete;
	io_req_task_work_add(req, !!(req->ctx->flags & IORING_SETUP_SQPOLL));
}

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

	if (kiocb->ki_flags & IOCB_WRITE)
		kiocb_end_write(req);
	if (unlikely(res != req->result)) {
		if (res == -EAGAIN && io_rw_should_reissue(req)) {
			req->flags |= REQ_F_REISSUE;
			return;
		}
		req->result = res;
	}

	/* order with io_iopoll_complete() checking ->iopoll_completed */
	smp_store_release(&req->iopoll_completed, 1);
}

/*
 * 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_do_iopoll() thread before the issuer is done
 * accessing the kiocb cookie.
 */
static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;

	/* workqueue context doesn't hold uring_lock, grab it now */
	if (unlikely(needs_lock))
		mutex_lock(&ctx->uring_lock);

	/*
	 * 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 (wq_list_empty(&ctx->iopoll_list)) {
		ctx->poll_multi_queue = false;
	} else if (!ctx->poll_multi_queue) {
		struct io_kiocb *list_req;

		list_req = container_of(ctx->iopoll_list.first, struct io_kiocb,
					comp_list);
		if (list_req->file != req->file)
			ctx->poll_multi_queue = true;
	}

	/*
	 * For fast devices, IO may have already completed. If it has, add
	 * it to the front so we find it first.
	 */
	if (READ_ONCE(req->iopoll_completed))
		wq_list_add_head(&req->comp_list, &ctx->iopoll_list);
	else
		wq_list_add_tail(&req->comp_list, &ctx->iopoll_list);

	if (unlikely(needs_lock)) {
		/*
		 * If IORING_SETUP_SQPOLL is enabled, sqes are either handle
		 * in sq thread task context or in io worker task context. If
		 * current task context is sq thread, we don't need to check
		 * whether should wake up sq thread.
		 */
		if ((ctx->flags & IORING_SETUP_SQPOLL) &&
		    wq_has_sleeper(&ctx->sq_data->wait))
			wake_up(&ctx->sq_data->wait);

		mutex_unlock(&ctx->uring_lock);
	}
}

static bool io_bdev_nowait(struct block_device *bdev)
{
	return !bdev || blk_queue_nowait(bdev_get_queue(bdev));
}

/*
 * 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_nowait(struct file *file, umode_t mode)
{
	if (S_ISBLK(mode)) {
		if (IS_ENABLED(CONFIG_BLOCK) &&
		    io_bdev_nowait(I_BDEV(file->f_mapping->host)))
			return true;
		return false;
	}
	if (S_ISSOCK(mode))
		return true;
	if (S_ISREG(mode)) {
		if (IS_ENABLED(CONFIG_BLOCK) &&
		    io_bdev_nowait(file->f_inode->i_sb->s_bdev) &&
		    file->f_op != &io_uring_fops)
			return true;
		return false;
	}

	/* any ->read/write should understand O_NONBLOCK */
	if (file->f_flags & O_NONBLOCK)
		return true;
	return file->f_mode & FMODE_NOWAIT;
}

/*
 * 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 unsigned int io_file_get_flags(struct file *file)
{
	umode_t mode = file_inode(file)->i_mode;
	unsigned int res = 0;

	if (S_ISREG(mode))
		res |= FFS_ISREG;
	if (__io_file_supports_nowait(file, mode))
		res |= FFS_NOWAIT;
	return res;
}

static inline bool io_file_supports_nowait(struct io_kiocb *req)
{
	return req->flags & REQ_F_SUPPORT_NOWAIT;
}

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

	if (!io_req_ffs_set(req))
		req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;

	kiocb->ki_pos = READ_ONCE(sqe->off);
	if (kiocb->ki_pos == -1) {
		if (!(file->f_mode & FMODE_STREAM)) {
			req->flags |= REQ_F_CUR_POS;
			kiocb->ki_pos = file->f_pos;
		} else {
			kiocb->ki_pos = 0;
		}
	}
	kiocb->ki_flags = iocb_flags(file);
	ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
	if (unlikely(ret))
		return ret;

	/*
	 * If the file is marked O_NONBLOCK, still allow retry for it if it
	 * supports async. Otherwise it's impossible to use O_NONBLOCK files
	 * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
	 */
	if ((kiocb->ki_flags & IOCB_NOWAIT) ||
	    ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
		req->flags |= REQ_F_NOWAIT;

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

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

	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();
	}

	req->imu = NULL;
	req->rw.addr = READ_ONCE(sqe->addr);
	req->rw.len = READ_ONCE(sqe->len);
	req->buf_index = READ_ONCE(sqe->buf_index);
	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;
		fallthrough;
	default:
		kiocb->ki_complete(kiocb, ret);
	}
}

static void kiocb_done(struct io_kiocb *req, ssize_t ret,
		       unsigned int issue_flags)
{
	struct io_async_rw *io = req->async_data;

	/* add previously done IO, if any */
	if (req_has_async_data(req) && io->bytes_done > 0) {
		if (ret < 0)
			ret = io->bytes_done;
		else
			ret += io->bytes_done;
	}

	if (req->flags & REQ_F_CUR_POS)
		req->file->f_pos = req->rw.kiocb.ki_pos;
	if (ret >= 0 && (req->rw.kiocb.ki_complete == io_complete_rw))
		__io_complete_rw(req, ret, issue_flags);
	else
		io_rw_done(&req->rw.kiocb, ret);

	if (req->flags & REQ_F_REISSUE) {
		req->flags &= ~REQ_F_REISSUE;
		if (io_resubmit_prep(req)) {
			io_req_task_queue_reissue(req);
		} else {
			req_set_fail(req);
			req->result = ret;
			req->io_task_work.func = io_req_task_complete;
			io_req_task_work_add(req, false);
		}
	}
}

static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
			     struct io_mapped_ubuf *imu)
{
	size_t len = req->rw.len;
	u64 buf_end, buf_addr = req->rw.addr;
	size_t offset;

	if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end)))
		return -EFAULT;
	/* not inside the mapped region */
	if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end))
		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) {
		/*
		 * Don't use iov_iter_advance() here, as it's really slow for
		 * using the latter parts of a big fixed buffer - it iterates
		 * over each segment manually. We can cheat a bit here, because
		 * we know that:
		 *
		 * 1) it's a BVEC iter, we set it up
		 * 2) all bvecs are PAGE_SIZE in size, except potentially the
		 *    first and last bvec
		 *
		 * So just find our index, and adjust the iterator afterwards.
		 * If the offset is within the first bvec (or the whole first
		 * bvec, just use iov_iter_advance(). This makes it easier
		 * since we can just skip the first segment, which may not
		 * be PAGE_SIZE aligned.
		 */
		const struct bio_vec *bvec = imu->bvec;

		if (offset <= bvec->bv_len) {
			iov_iter_advance(iter, offset);
		} else {
			unsigned long seg_skip;

			/* skip first vec */
			offset -= bvec->bv_len;
			seg_skip = 1 + (offset >> PAGE_SHIFT);

			iter->bvec = bvec + seg_skip;
			iter->nr_segs -= seg_skip;
			iter->count -= bvec->bv_len + offset;
			iter->iov_offset = offset & ~PAGE_MASK;
		}
	}

	return 0;
}

static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
{
	struct io_mapped_ubuf *imu = req->imu;
	u16 index, buf_index = req->buf_index;

	if (likely(!imu)) {
		struct io_ring_ctx *ctx = req->ctx;

		if (unlikely(buf_index >= ctx->nr_user_bufs))
			return -EFAULT;
		io_req_set_rsrc_node(req, ctx);
		index = array_index_nospec(buf_index, ctx->nr_user_bufs);
		imu = READ_ONCE(ctx->user_bufs[index]);
		req->imu = imu;
	}
	return __io_import_fixed(req, rw, iter, imu);
}

static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock)
{
	if (needs_lock)
		mutex_unlock(&ctx->uring_lock);
}

static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock)
{
	/*
	 * "Normal" inline submissions always hold the uring_lock, since we
	 * grab it from the system call. Same is true for the SQPOLL offload.
	 * The only exception is when we've detached the request and issue it
	 * from an async worker thread, grab the lock for that case.
	 */
	if (needs_lock)
		mutex_lock(&ctx->uring_lock);
}

static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
					  int bgid, unsigned int issue_flags)
{
	struct io_buffer *kbuf = req->kbuf;
	struct io_buffer *head;
	bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;

	if (req->flags & REQ_F_BUFFER_SELECTED)
		return kbuf;

	io_ring_submit_lock(req->ctx, needs_lock);

	lockdep_assert_held(&req->ctx->uring_lock);

	head = xa_load(&req->ctx->io_buffers, bgid);
	if (head) {
		if (!list_empty(&head->list)) {
			kbuf = list_last_entry(&head->list, struct io_buffer,
							list);
			list_del(&kbuf->list);
		} else {
			kbuf = head;
			xa_erase(&req->ctx->io_buffers, bgid);
		}
		if (*len > kbuf->len)
			*len = kbuf->len;
		req->flags |= REQ_F_BUFFER_SELECTED;
		req->kbuf = kbuf;
	} else {
		kbuf = ERR_PTR(-ENOBUFS);
	}

	io_ring_submit_unlock(req->ctx, needs_lock);
	return kbuf;
}

static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
					unsigned int issue_flags)
{
	struct io_buffer *kbuf;
	u16 bgid;

	bgid = req->buf_index;
	kbuf = io_buffer_select(req, len, bgid, issue_flags);
	if (IS_ERR(kbuf))
		return kbuf;
	return u64_to_user_ptr(kbuf->addr);
}

#ifdef CONFIG_COMPAT
static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
				unsigned int issue_flags)
{
	struct compat_iovec __user *uiov;
	compat_ssize_t clen;
	void __user *buf;
	ssize_t len;

	uiov = u64_to_user_ptr(req->rw.addr);
	if (!access_ok(uiov, sizeof(*uiov)))
		return -EFAULT;
	if (__get_user(clen, &uiov->iov_len))
		return -EFAULT;
	if (clen < 0)
		return -EINVAL;

	len = clen;
	buf = io_rw_buffer_select(req, &len, issue_flags);
	if (IS_ERR(buf))
		return PTR_ERR(buf);
	iov[0].iov_base = buf;
	iov[0].iov_len = (compat_size_t) len;
	return 0;
}
#endif

static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
				      unsigned int issue_flags)
{
	struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr);
	void __user *buf;
	ssize_t len;

	if (copy_from_user(iov, uiov, sizeof(*uiov)))
		return -EFAULT;

	len = iov[0].iov_len;
	if (len < 0)
		return -EINVAL;
	buf = io_rw_buffer_select(req, &len, issue_flags);
	if (IS_ERR(buf))
		return PTR_ERR(buf);
	iov[0].iov_base = buf;
	iov[0].iov_len = len;
	return 0;
}

static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
				    unsigned int issue_flags)
{
	if (req->flags & REQ_F_BUFFER_SELECTED) {
		struct io_buffer *kbuf = req->kbuf;

		iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
		iov[0].iov_len = kbuf->len;
		return 0;
	}
	if (req->rw.len != 1)
		return -EINVAL;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		return io_compat_import(req, iov, issue_flags);
#endif

	return __io_iov_buffer_select(req, iov, issue_flags);
}

static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req,
				       struct io_rw_state *s,
				       unsigned int issue_flags)
{
	struct iov_iter *iter = &s->iter;
	u8 opcode = req->opcode;
	struct iovec *iovec;
	void __user *buf;
	size_t sqe_len;
	ssize_t ret;

	if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
		ret = io_import_fixed(req, rw, iter);
		if (ret)
			return ERR_PTR(ret);
		return NULL;
	}

	/* buffer index only valid with fixed read/write, or buffer select  */
	if (unlikely(req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT)))
		return ERR_PTR(-EINVAL);

	buf = u64_to_user_ptr(req->rw.addr);
	sqe_len = req->rw.len;

	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
		if (req->flags & REQ_F_BUFFER_SELECT) {
			buf = io_rw_buffer_select(req, &sqe_len, issue_flags);
			if (IS_ERR(buf))
				return ERR_CAST(buf);
			req->rw.len = sqe_len;
		}

		ret = import_single_range(rw, buf, sqe_len, s->fast_iov, iter);
		if (ret)
			return ERR_PTR(ret);
		return NULL;
	}

	iovec = s->fast_iov;
	if (req->flags & REQ_F_BUFFER_SELECT) {
		ret = io_iov_buffer_select(req, iovec, issue_flags);
		if (ret)
			return ERR_PTR(ret);
		iov_iter_init(iter, rw, iovec, 1, iovec->iov_len);
		return NULL;
	}

	ret = __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, &iovec, iter,
			      req->ctx->compat);
	if (unlikely(ret < 0))
		return ERR_PTR(ret);
	return iovec;
}

static inline int io_import_iovec(int rw, struct io_kiocb *req,
				  struct iovec **iovec, struct io_rw_state *s,
				  unsigned int issue_flags)
{
	*iovec = __io_import_iovec(rw, req, s, issue_flags);
	if (unlikely(IS_ERR(*iovec)))
		return PTR_ERR(*iovec);

	iov_iter_save_state(&s->iter, &s->iter_state);
	return 0;
}

static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
{
	return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos;
}

/*
 * For files that don't have ->read_iter() and ->write_iter(), handle them
 * by looping over ->read() or ->write() manually.
 */
static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter)
{
	struct kiocb *kiocb = &req->rw.kiocb;
	struct file *file = req->file;
	ssize_t ret = 0;

	/*
	 * Don't support polled IO through this interface, and we can't
	 * support non-blocking either. For the latter, this just causes
	 * the kiocb to be handled from an async context.
	 */
	if (kiocb->ki_flags & IOCB_HIPRI)
		return -EOPNOTSUPP;
	if ((kiocb->ki_flags & IOCB_NOWAIT) &&
	    !(kiocb->ki_filp->f_flags & O_NONBLOCK))
		return -EAGAIN;

	while (iov_iter_count(iter)) {
		struct iovec iovec;
		ssize_t nr;

		if (!iov_iter_is_bvec(iter)) {
			iovec = iov_iter_iovec(iter);
		} else {
			iovec.iov_base = u64_to_user_ptr(req->rw.addr);
			iovec.iov_len = req->rw.len;
		}

		if (rw == READ) {
			nr = file->f_op->read(file, iovec.iov_base,
					      iovec.iov_len, io_kiocb_ppos(kiocb));
		} else {
			nr = file->f_op->write(file, iovec.iov_base,
					       iovec.iov_len, io_kiocb_ppos(kiocb));
		}

		if (nr < 0) {
			if (!ret)
				ret = nr;
			break;
		}
		if (!iov_iter_is_bvec(iter)) {
			iov_iter_advance(iter, nr);
		} else {
			req->rw.len -= nr;
			req->rw.addr += nr;
		}
		ret += nr;
		if (nr != iovec.iov_len)
			break;
	}

	return ret;
}

static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
			  const struct iovec *fast_iov, struct iov_iter *iter)
{
	struct io_async_rw *rw = req->async_data;

	memcpy(&rw->s.iter, iter, sizeof(*iter));
	rw->free_iovec = iovec;
	rw->bytes_done = 0;
	/* can only be fixed buffers, no need to do anything */
	if (iov_iter_is_bvec(iter))
		return;
	if (!iovec) {
		unsigned iov_off = 0;

		rw->s.iter.iov = rw->s.fast_iov;
		if (iter->iov != fast_iov) {
			iov_off = iter->iov - fast_iov;
			rw->s.iter.iov += iov_off;
		}
		if (rw->s.fast_iov != fast_iov)
			memcpy(rw->s.fast_iov + iov_off, fast_iov + iov_off,
			       sizeof(struct iovec) * iter->nr_segs);
	} else {
		req->flags |= REQ_F_NEED_CLEANUP;
	}
}

static inline bool io_alloc_async_data(struct io_kiocb *req)
{
	WARN_ON_ONCE(!io_op_defs[req->opcode].async_size);
	req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL);
	if (req->async_data) {
		req->flags |= REQ_F_ASYNC_DATA;
		return false;
	}
	return true;
}

static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
			     struct io_rw_state *s, bool force)
{
	if (!force && !io_op_defs[req->opcode].needs_async_setup)
		return 0;
	if (!req_has_async_data(req)) {
		struct io_async_rw *iorw;

		if (io_alloc_async_data(req)) {
			kfree(iovec);
			return -ENOMEM;
		}

		io_req_map_rw(req, iovec, s->fast_iov, &s->iter);
		iorw = req->async_data;
		/* we've copied and mapped the iter, ensure state is saved */
		iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state);
	}
	return 0;
}

static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
{
	struct io_async_rw *iorw = req->async_data;
	struct iovec *iov;
	int ret;

	/* submission path, ->uring_lock should already be taken */
	ret = io_import_iovec(rw, req, &iov, &iorw->s, 0);
	if (unlikely(ret < 0))
		return ret;

	iorw->bytes_done = 0;
	iorw->free_iovec = iov;
	if (iov)
		req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (unlikely(!(req->file->f_mode & FMODE_READ)))
		return -EBADF;
	return io_prep_rw(req, sqe);
}

/*
 * This is our waitqueue callback handler, registered through __folio_lock_async()
 * when we initially tried to do the IO with the iocb armed our waitqueue.
 * This gets called when the page is unlocked, and we generally expect that to
 * happen when the page IO is completed and the page is now uptodate. This will
 * queue a task_work based retry of the operation, attempting to copy the data
 * again. If the latter fails because the page was NOT uptodate, then we will
 * do a thread based blocking retry of the operation. That's the unexpected
 * slow path.
 */
static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
			     int sync, void *arg)
{
	struct wait_page_queue *wpq;
	struct io_kiocb *req = wait->private;
	struct wait_page_key *key = arg;

	wpq = container_of(wait, struct wait_page_queue, wait);

	if (!wake_page_match(wpq, key))
		return 0;

	req->rw.kiocb.ki_flags &= ~IOCB_WAITQ;
	list_del_init(&wait->entry);
	io_req_task_queue(req);
	return 1;
}

/*
 * This controls whether a given IO request should be armed for async page
 * based retry. If we return false here, the request is handed to the async
 * worker threads for retry. If we're doing buffered reads on a regular file,
 * we prepare a private wait_page_queue entry and retry the operation. This
 * will either succeed because the page is now uptodate and unlocked, or it
 * will register a callback when the page is unlocked at IO completion. Through
 * that callback, io_uring uses task_work to setup a retry of the operation.
 * That retry will attempt the buffered read again. The retry will generally
 * succeed, or in rare cases where it fails, we then fall back to using the
 * async worker threads for a blocking retry.
 */
static bool io_rw_should_retry(struct io_kiocb *req)
{
	struct io_async_rw *rw = req->async_data;
	struct wait_page_queue *wait = &rw->wpq;
	struct kiocb *kiocb = &req->rw.kiocb;

	/* never retry for NOWAIT, we just complete with -EAGAIN */
	if (req->flags & REQ_F_NOWAIT)
		return false;

	/* Only for buffered IO */
	if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI))
		return false;

	/*
	 * just use poll if we can, and don't attempt if the fs doesn't
	 * support callback based unlocks
	 */
	if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
		return false;

	wait->wait.func = io_async_buf_func;
	wait->wait.private = req;
	wait->wait.flags = 0;
	INIT_LIST_HEAD(&wait->wait.entry);
	kiocb->ki_flags |= IOCB_WAITQ;
	kiocb->ki_flags &= ~IOCB_NOWAIT;
	kiocb->ki_waitq = wait;
	return true;
}

static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
{
	if (likely(req->file->f_op->read_iter))
		return call_read_iter(req->file, &req->rw.kiocb, iter);
	else if (req->file->f_op->read)
		return loop_rw_iter(READ, req, iter);
	else
		return -EINVAL;
}

static bool need_read_all(struct io_kiocb *req)
{
	return req->flags & REQ_F_ISREG ||
		S_ISBLK(file_inode(req->file)->i_mode);
}

static int io_read(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_rw_state __s, *s = &__s;
	struct iovec *iovec;
	struct kiocb *kiocb = &req->rw.kiocb;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
	struct io_async_rw *rw;
	ssize_t ret, ret2;

	if (!req_has_async_data(req)) {
		ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
		if (unlikely(ret < 0))
			return ret;
	} else {
		rw = req->async_data;
		s = &rw->s;
		/*
		 * We come here from an earlier attempt, restore our state to
		 * match in case it doesn't. It's cheap enough that we don't
		 * need to make this conditional.
		 */
		iov_iter_restore(&s->iter, &s->iter_state);
		iovec = NULL;
	}
	req->result = iov_iter_count(&s->iter);

	if (force_nonblock) {
		/* If the file doesn't support async, just async punt */
		if (unlikely(!io_file_supports_nowait(req))) {
			ret = io_setup_async_rw(req, iovec, s, true);
			return ret ?: -EAGAIN;
		}
		kiocb->ki_flags |= IOCB_NOWAIT;
	} else {
		/* Ensure we clear previously set non-block flag */
		kiocb->ki_flags &= ~IOCB_NOWAIT;
	}

	ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result);
	if (unlikely(ret)) {
		kfree(iovec);
		return ret;
	}

	ret = io_iter_do_read(req, &s->iter);

	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
		req->flags &= ~REQ_F_REISSUE;
		/* IOPOLL retry should happen for io-wq threads */
		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
			goto done;
		/* no retry on NONBLOCK nor RWF_NOWAIT */
		if (req->flags & REQ_F_NOWAIT)
			goto done;
		ret = 0;
	} else if (ret == -EIOCBQUEUED) {
		goto out_free;
	} else if (ret == req->result || ret <= 0 || !force_nonblock ||
		   (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
		/* read all, failed, already did sync or don't want to retry */
		goto done;
	}

	/*
	 * Don't depend on the iter state matching what was consumed, or being
	 * untouched in case of error. Restore it and we'll advance it
	 * manually if we need to.
	 */
	iov_iter_restore(&s->iter, &s->iter_state);

	ret2 = io_setup_async_rw(req, iovec, s, true);
	if (ret2)
		return ret2;

	iovec = NULL;
	rw = req->async_data;
	s = &rw->s;
	/*
	 * Now use our persistent iterator and state, if we aren't already.
	 * We've restored and mapped the iter to match.
	 */

	do {
		/*
		 * We end up here because of a partial read, either from
		 * above or inside this loop. Advance the iter by the bytes
		 * that were consumed.
		 */
		iov_iter_advance(&s->iter, ret);
		if (!iov_iter_count(&s->iter))
			break;
		rw->bytes_done += ret;
		iov_iter_save_state(&s->iter, &s->iter_state);

		/* if we can retry, do so with the callbacks armed */
		if (!io_rw_should_retry(req)) {
			kiocb->ki_flags &= ~IOCB_WAITQ;
			return -EAGAIN;
		}

		/*
		 * Now retry read with the IOCB_WAITQ parts set in the iocb. If
		 * we get -EIOCBQUEUED, then we'll get a notification when the
		 * desired page gets unlocked. We can also get a partial read
		 * here, and if we do, then just retry at the new offset.
		 */
		ret = io_iter_do_read(req, &s->iter);
		if (ret == -EIOCBQUEUED)
			return 0;
		/* we got some bytes, but not all. retry. */
		kiocb->ki_flags &= ~IOCB_WAITQ;
		iov_iter_restore(&s->iter, &s->iter_state);
	} while (ret > 0);
done:
	kiocb_done(req, ret, issue_flags);
out_free:
	/* it's faster to check here then delegate to kfree */
	if (iovec)
		kfree(iovec);
	return 0;
}

static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
		return -EBADF;
	req->rw.kiocb.ki_hint = ki_hint_validate(file_write_hint(req->file));
	return io_prep_rw(req, sqe);
}

static int io_write(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_rw_state __s, *s = &__s;
	struct iovec *iovec;
	struct kiocb *kiocb = &req->rw.kiocb;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
	ssize_t ret, ret2;

	if (!req_has_async_data(req)) {
		ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags);
		if (unlikely(ret < 0))
			return ret;
	} else {
		struct io_async_rw *rw = req->async_data;

		s = &rw->s;
		iov_iter_restore(&s->iter, &s->iter_state);
		iovec = NULL;
	}
	req->result = iov_iter_count(&s->iter);

	if (force_nonblock) {
		/* If the file doesn't support async, just async punt */
		if (unlikely(!io_file_supports_nowait(req)))
			goto copy_iov;

		/* file path doesn't support NOWAIT for non-direct_IO */
		if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
		    (req->flags & REQ_F_ISREG))
			goto copy_iov;

		kiocb->ki_flags |= IOCB_NOWAIT;
	} else {
		/* Ensure we clear previously set non-block flag */
		kiocb->ki_flags &= ~IOCB_NOWAIT;
	}

	ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result);
	if (unlikely(ret))
		goto out_free;

	/*
	 * 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 (req->flags & REQ_F_ISREG) {
		sb_start_write(file_inode(req->file)->i_sb);
		__sb_writers_release(file_inode(req->file)->i_sb,
					SB_FREEZE_WRITE);
	}
	kiocb->ki_flags |= IOCB_WRITE;

	if (likely(req->file->f_op->write_iter))
		ret2 = call_write_iter(req->file, kiocb, &s->iter);
	else if (req->file->f_op->write)
		ret2 = loop_rw_iter(WRITE, req, &s->iter);
	else
		ret2 = -EINVAL;

	if (req->flags & REQ_F_REISSUE) {
		req->flags &= ~REQ_F_REISSUE;
		ret2 = -EAGAIN;
	}

	/*
	 * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
	 * retry them without IOCB_NOWAIT.
	 */
	if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
		ret2 = -EAGAIN;
	/* no retry on NONBLOCK nor RWF_NOWAIT */
	if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT))
		goto done;
	if (!force_nonblock || ret2 != -EAGAIN) {
		/* IOPOLL retry should happen for io-wq threads */
		if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL))
			goto copy_iov;
done:
		kiocb_done(req, ret2, issue_flags);
	} else {
copy_iov:
		iov_iter_restore(&s->iter, &s->iter_state);
		ret = io_setup_async_rw(req, iovec, s, false);
		return ret ?: -EAGAIN;
	}
out_free:
	/* it's reportedly faster than delegating the null check to kfree() */
	if (iovec)
		kfree(iovec);
	return ret;
}

static int io_renameat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_rename *ren = &req->rename;
	const char __user *oldf, *newf;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)
		return -EINVAL;
	if (unlikely(req->flags & REQ_F_FIXED_FILE))
		return -EBADF;

	ren->old_dfd = READ_ONCE(sqe->fd);
	oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	ren->new_dfd = READ_ONCE(sqe->len);
	ren->flags = READ_ONCE(sqe->rename_flags);

	ren->oldpath = getname(oldf);
	if (IS_ERR(ren->oldpath))
		return PTR_ERR(ren->oldpath);

	ren->newpath = getname(newf);
	if (IS_ERR(ren->newpath)) {
		putname(ren->oldpath);
		return PTR_ERR(ren->newpath);
	}

	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_renameat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_rename *ren = &req->rename;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd,
				ren->newpath, ren->flags);

	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_unlinkat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_unlink *un = &req->unlink;
	const char __user *fname;

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

	un->dfd = READ_ONCE(sqe->fd);

	un->flags = READ_ONCE(sqe->unlink_flags);
	if (un->flags & ~AT_REMOVEDIR)
		return -EINVAL;

	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
	un->filename = getname(fname);
	if (IS_ERR(un->filename))
		return PTR_ERR(un->filename);

	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_unlink *un = &req->unlink;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	if (un->flags & AT_REMOVEDIR)
		ret = do_rmdir(un->dfd, un->filename);
	else
		ret = do_unlinkat(un->dfd, un->filename);

	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_mkdirat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_mkdir *mkd = &req->mkdir;
	const char __user *fname;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->off || sqe->rw_flags || sqe->buf_index ||
	    sqe->splice_fd_in)
		return -EINVAL;
	if (unlikely(req->flags & REQ_F_FIXED_FILE))
		return -EBADF;

	mkd->dfd = READ_ONCE(sqe->fd);
	mkd->mode = READ_ONCE(sqe->len);

	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
	mkd->filename = getname(fname);
	if (IS_ERR(mkd->filename))
		return PTR_ERR(mkd->filename);

	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_mkdir *mkd = &req->mkdir;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode);

	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_symlinkat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_symlink *sl = &req->symlink;
	const char __user *oldpath, *newpath;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->len || sqe->rw_flags || sqe->buf_index ||
	    sqe->splice_fd_in)
		return -EINVAL;
	if (unlikely(req->flags & REQ_F_FIXED_FILE))
		return -EBADF;

	sl->new_dfd = READ_ONCE(sqe->fd);
	oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr));
	newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2));

	sl->oldpath = getname(oldpath);
	if (IS_ERR(sl->oldpath))
		return PTR_ERR(sl->oldpath);

	sl->newpath = getname(newpath);
	if (IS_ERR(sl->newpath)) {
		putname(sl->oldpath);
		return PTR_ERR(sl->newpath);
	}

	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_symlink *sl = &req->symlink;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath);

	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_linkat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_hardlink *lnk = &req->hardlink;
	const char __user *oldf, *newf;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
		return -EINVAL;
	if (unlikely(req->flags & REQ_F_FIXED_FILE))
		return -EBADF;

	lnk->old_dfd = READ_ONCE(sqe->fd);
	lnk->new_dfd = READ_ONCE(sqe->len);
	oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	lnk->flags = READ_ONCE(sqe->hardlink_flags);

	lnk->oldpath = getname(oldf);
	if (IS_ERR(lnk->oldpath))
		return PTR_ERR(lnk->oldpath);

	lnk->newpath = getname(newf);
	if (IS_ERR(lnk->newpath)) {
		putname(lnk->oldpath);
		return PTR_ERR(lnk->newpath);
	}

	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_hardlink *lnk = &req->hardlink;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd,
				lnk->newpath, lnk->flags);

	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_shutdown_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_NET)
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (unlikely(sqe->ioprio || sqe->off || sqe->addr || sqe->rw_flags ||
		     sqe->buf_index || sqe->splice_fd_in))
		return -EINVAL;

	req->shutdown.how = READ_ONCE(sqe->len);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags)
{
#if defined(CONFIG_NET)
	struct socket *sock;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	ret = __sys_shutdown_sock(sock, req->shutdown.how);
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int __io_splice_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_splice *sp = &req->splice;
	unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL;

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

	sp->file_in = NULL;
	sp->len = READ_ONCE(sqe->len);
	sp->flags = READ_ONCE(sqe->splice_flags);

	if (unlikely(sp->flags & ~valid_flags))
		return -EINVAL;

	sp->file_in = io_file_get(req->ctx, req, READ_ONCE(sqe->splice_fd_in),
				  (sp->flags & SPLICE_F_FD_IN_FIXED));
	if (!sp->file_in)
		return -EBADF;
	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_tee_prep(struct io_kiocb *req,
		       const struct io_uring_sqe *sqe)
{
	if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off))
		return -EINVAL;
	return __io_splice_prep(req, sqe);
}

static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_splice *sp = &req->splice;
	struct file *in = sp->file_in;
	struct file *out = sp->file_out;
	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
	long ret = 0;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;
	if (sp->len)
		ret = do_tee(in, out, sp->len, flags);

	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
		io_put_file(in);
	req->flags &= ~REQ_F_NEED_CLEANUP;

	if (ret != sp->len)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_splice *sp = &req->splice;

	sp->off_in = READ_ONCE(sqe->splice_off_in);
	sp->off_out = READ_ONCE(sqe->off);
	return __io_splice_prep(req, sqe);
}

static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_splice *sp = &req->splice;
	struct file *in = sp->file_in;
	struct file *out = sp->file_out;
	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
	loff_t *poff_in, *poff_out;
	long ret = 0;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
	poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;

	if (sp->len)
		ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);

	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
		io_put_file(in);
	req->flags &= ~REQ_F_NEED_CLEANUP;

	if (ret != sp->len)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

/*
 * IORING_OP_NOP just posts a completion event, nothing else.
 */
static int io_nop(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;

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

	__io_req_complete(req, issue_flags, 0, 0);
	return 0;
}

static int io_fsync_prep(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 ||
		     sqe->splice_fd_in))
		return -EINVAL;

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

	req->sync.off = READ_ONCE(sqe->off);
	req->sync.len = READ_ONCE(sqe->len);
	return 0;
}

static int io_fsync(struct io_kiocb *req, unsigned int issue_flags)
{
	loff_t end = req->sync.off + req->sync.len;
	int ret;

	/* fsync always requires a blocking context */
	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = vfs_fsync_range(req->file, req->sync.off,
				end > 0 ? end : LLONG_MAX,
				req->sync.flags & IORING_FSYNC_DATASYNC);
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_fallocate_prep(struct io_kiocb *req,
			     const struct io_uring_sqe *sqe)
{
	if (sqe->ioprio || sqe->buf_index || sqe->rw_flags ||
	    sqe->splice_fd_in)
		return -EINVAL;
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	req->sync.off = READ_ONCE(sqe->off);
	req->sync.len = READ_ONCE(sqe->addr);
	req->sync.mode = READ_ONCE(sqe->len);
	return 0;
}

static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags)
{
	int ret;

	/* fallocate always requiring blocking context */
	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;
	ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
				req->sync.len);
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	const char __user *fname;
	int ret;

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

	/* open.how should be already initialised */
	if (!(req->open.how.flags & O_PATH) && force_o_largefile())
		req->open.how.flags |= O_LARGEFILE;

	req->open.dfd = READ_ONCE(sqe->fd);
	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
	req->open.filename = getname(fname);
	if (IS_ERR(req->open.filename)) {
		ret = PTR_ERR(req->open.filename);
		req->open.filename = NULL;
		return ret;
	}

	req->open.file_slot = READ_ONCE(sqe->file_index);
	if (req->open.file_slot && (req->open.how.flags & O_CLOEXEC))
		return -EINVAL;

	req->open.nofile = rlimit(RLIMIT_NOFILE);
	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	u64 mode = READ_ONCE(sqe->len);
	u64 flags = READ_ONCE(sqe->open_flags);

	req->open.how = build_open_how(flags, mode);
	return __io_openat_prep(req, sqe);
}

static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct open_how __user *how;
	size_t len;
	int ret;

	how = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	len = READ_ONCE(sqe->len);
	if (len < OPEN_HOW_SIZE_VER0)
		return -EINVAL;

	ret = copy_struct_from_user(&req->open.how, sizeof(req->open.how), how,
					len);
	if (ret)
		return ret;

	return __io_openat_prep(req, sqe);
}

static int io_openat2(struct io_kiocb *req, unsigned int issue_flags)
{
	struct open_flags op;
	struct file *file;
	bool resolve_nonblock, nonblock_set;
	bool fixed = !!req->open.file_slot;
	int ret;

	ret = build_open_flags(&req->open.how, &op);
	if (ret)
		goto err;
	nonblock_set = op.open_flag & O_NONBLOCK;
	resolve_nonblock = req->open.how.resolve & RESOLVE_CACHED;
	if (issue_flags & IO_URING_F_NONBLOCK) {
		/*
		 * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open,
		 * it'll always -EAGAIN
		 */
		if (req->open.how.flags & (O_TRUNC | O_CREAT | O_TMPFILE))
			return -EAGAIN;
		op.lookup_flags |= LOOKUP_CACHED;
		op.open_flag |= O_NONBLOCK;
	}

	if (!fixed) {
		ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile);
		if (ret < 0)
			goto err;
	}

	file = do_filp_open(req->open.dfd, req->open.filename, &op);
	if (IS_ERR(file)) {
		/*
		 * We could hang on to this 'fd' on retrying, but seems like
		 * marginal gain for something that is now known to be a slower
		 * path. So just put it, and we'll get a new one when we retry.
		 */
		if (!fixed)
			put_unused_fd(ret);

		ret = PTR_ERR(file);
		/* only retry if RESOLVE_CACHED wasn't already set by application */
		if (ret == -EAGAIN &&
		    (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK)))
			return -EAGAIN;
		goto err;
	}

	if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set)
		file->f_flags &= ~O_NONBLOCK;
	fsnotify_open(file);

	if (!fixed)
		fd_install(ret, file);
	else
		ret = io_install_fixed_file(req, file, issue_flags,
					    req->open.file_slot - 1);
err:
	putname(req->open.filename);
	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_openat(struct io_kiocb *req, unsigned int issue_flags)
{
	return io_openat2(req, issue_flags);
}

static int io_remove_buffers_prep(struct io_kiocb *req,
				  const struct io_uring_sqe *sqe)
{
	struct io_provide_buf *p = &req->pbuf;
	u64 tmp;

	if (sqe->ioprio || sqe->rw_flags || sqe->addr || sqe->len || sqe->off ||
	    sqe->splice_fd_in)
		return -EINVAL;

	tmp = READ_ONCE(sqe->fd);
	if (!tmp || tmp > USHRT_MAX)
		return -EINVAL;

	memset(p, 0, sizeof(*p));
	p->nbufs = tmp;
	p->bgid = READ_ONCE(sqe->buf_group);
	return 0;
}

static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf,
			       int bgid, unsigned nbufs)
{
	unsigned i = 0;

	/* shouldn't happen */
	if (!nbufs)
		return 0;

	/* the head kbuf is the list itself */
	while (!list_empty(&buf->list)) {
		struct io_buffer *nxt;

		nxt = list_first_entry(&buf->list, struct io_buffer, list);
		list_del(&nxt->list);
		kfree(nxt);
		if (++i == nbufs)
			return i;
		cond_resched();
	}
	i++;
	kfree(buf);
	xa_erase(&ctx->io_buffers, bgid);

	return i;
}

static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_provide_buf *p = &req->pbuf;
	struct io_ring_ctx *ctx = req->ctx;
	struct io_buffer *head;
	int ret = 0;
	bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;

	io_ring_submit_lock(ctx, needs_lock);

	lockdep_assert_held(&ctx->uring_lock);

	ret = -ENOENT;
	head = xa_load(&ctx->io_buffers, p->bgid);
	if (head)
		ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs);
	if (ret < 0)
		req_set_fail(req);

	/* complete before unlock, IOPOLL may need the lock */
	__io_req_complete(req, issue_flags, ret, 0);
	io_ring_submit_unlock(ctx, needs_lock);
	return 0;
}

static int io_provide_buffers_prep(struct io_kiocb *req,
				   const struct io_uring_sqe *sqe)
{
	unsigned long size, tmp_check;
	struct io_provide_buf *p = &req->pbuf;
	u64 tmp;

	if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in)
		return -EINVAL;

	tmp = READ_ONCE(sqe->fd);
	if (!tmp || tmp > USHRT_MAX)
		return -E2BIG;
	p->nbufs = tmp;
	p->addr = READ_ONCE(sqe->addr);
	p->len = READ_ONCE(sqe->len);

	if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs,
				&size))
		return -EOVERFLOW;
	if (check_add_overflow((unsigned long)p->addr, size, &tmp_check))
		return -EOVERFLOW;

	size = (unsigned long)p->len * p->nbufs;
	if (!access_ok(u64_to_user_ptr(p->addr), size))
		return -EFAULT;

	p->bgid = READ_ONCE(sqe->buf_group);
	tmp = READ_ONCE(sqe->off);
	if (tmp > USHRT_MAX)
		return -E2BIG;
	p->bid = tmp;
	return 0;
}

static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head)
{
	struct io_buffer *buf;
	u64 addr = pbuf->addr;
	int i, bid = pbuf->bid;

	for (i = 0; i < pbuf->nbufs; i++) {
		buf = kmalloc(sizeof(*buf), GFP_KERNEL_ACCOUNT);
		if (!buf)
			break;

		buf->addr = addr;
		buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT);
		buf->bid = bid;
		addr += pbuf->len;
		bid++;
		if (!*head) {
			INIT_LIST_HEAD(&buf->list);
			*head = buf;
		} else {
			list_add_tail(&buf->list, &(*head)->list);
		}
	}

	return i ? i : -ENOMEM;
}

static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_provide_buf *p = &req->pbuf;
	struct io_ring_ctx *ctx = req->ctx;
	struct io_buffer *head, *list;
	int ret = 0;
	bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;

	io_ring_submit_lock(ctx, needs_lock);

	lockdep_assert_held(&ctx->uring_lock);

	list = head = xa_load(&ctx->io_buffers, p->bgid);

	ret = io_add_buffers(p, &head);
	if (ret >= 0 && !list) {
		ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL);
		if (ret < 0)
			__io_remove_buffers(ctx, head, p->bgid, -1U);
	}
	if (ret < 0)
		req_set_fail(req);
	/* complete before unlock, IOPOLL may need the lock */
	__io_req_complete(req, issue_flags, ret, 0);
	io_ring_submit_unlock(ctx, needs_lock);
	return 0;
}

static int io_epoll_ctl_prep(struct io_kiocb *req,
			     const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_EPOLL)
	if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)
		return -EINVAL;
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	req->epoll.epfd = READ_ONCE(sqe->fd);
	req->epoll.op = READ_ONCE(sqe->len);
	req->epoll.fd = READ_ONCE(sqe->off);

	if (ep_op_has_event(req->epoll.op)) {
		struct epoll_event __user *ev;

		ev = u64_to_user_ptr(READ_ONCE(sqe->addr));
		if (copy_from_user(&req->epoll.event, ev, sizeof(*ev)))
			return -EFAULT;
	}

	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags)
{
#if defined(CONFIG_EPOLL)
	struct io_epoll *ie = &req->epoll;
	int ret;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock);
	if (force_nonblock && ret == -EAGAIN)
		return -EAGAIN;

	if (ret < 0)
		req_set_fail(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
	if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->splice_fd_in)
		return -EINVAL;
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	req->madvise.addr = READ_ONCE(sqe->addr);
	req->madvise.len = READ_ONCE(sqe->len);
	req->madvise.advice = READ_ONCE(sqe->fadvise_advice);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_madvise(struct io_kiocb *req, unsigned int issue_flags)
{
#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
	struct io_madvise *ma = &req->madvise;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice);
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (sqe->ioprio || sqe->buf_index || sqe->addr || sqe->splice_fd_in)
		return -EINVAL;
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	req->fadvise.offset = READ_ONCE(sqe->off);
	req->fadvise.len = READ_ONCE(sqe->len);
	req->fadvise.advice = READ_ONCE(sqe->fadvise_advice);
	return 0;
}

static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_fadvise *fa = &req->fadvise;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK) {
		switch (fa->advice) {
		case POSIX_FADV_NORMAL:
		case POSIX_FADV_RANDOM:
		case POSIX_FADV_SEQUENTIAL:
			break;
		default:
			return -EAGAIN;
		}
	}

	ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice);
	if (ret < 0)
		req_set_fail(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)
		return -EINVAL;
	if (req->flags & REQ_F_FIXED_FILE)
		return -EBADF;

	req->statx.dfd = READ_ONCE(sqe->fd);
	req->statx.mask = READ_ONCE(sqe->len);
	req->statx.filename = u64_to_user_ptr(READ_ONCE(sqe->addr));
	req->statx.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	req->statx.flags = READ_ONCE(sqe->statx_flags);

	return 0;
}

static int io_statx(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_statx *ctx = &req->statx;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask,
		       ctx->buffer);

	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->off || sqe->addr || sqe->len ||
	    sqe->rw_flags || sqe->buf_index)
		return -EINVAL;
	if (req->flags & REQ_F_FIXED_FILE)
		return -EBADF;

	req->close.fd = READ_ONCE(sqe->fd);
	req->close.file_slot = READ_ONCE(sqe->file_index);
	if (req->close.file_slot && req->close.fd)
		return -EINVAL;

	return 0;
}

static int io_close(struct io_kiocb *req, unsigned int issue_flags)
{
	struct files_struct *files = current->files;
	struct io_close *close = &req->close;
	struct fdtable *fdt;
	struct file *file = NULL;
	int ret = -EBADF;

	if (req->close.file_slot) {
		ret = io_close_fixed(req, issue_flags);
		goto err;
	}

	spin_lock(&files->file_lock);
	fdt = files_fdtable(files);
	if (close->fd >= fdt->max_fds) {
		spin_unlock(&files->file_lock);
		goto err;
	}
	file = fdt->fd[close->fd];
	if (!file || file->f_op == &io_uring_fops) {
		spin_unlock(&files->file_lock);
		file = NULL;
		goto err;
	}

	/* if the file has a flush method, be safe and punt to async */
	if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) {
		spin_unlock(&files->file_lock);
		return -EAGAIN;
	}

	ret = __close_fd_get_file(close->fd, &file);
	spin_unlock(&files->file_lock);
	if (ret < 0) {
		if (ret == -ENOENT)
			ret = -EBADF;
		goto err;
	}

	/* No ->flush() or already async, safely close from here */
	ret = filp_close(file, current->files);
err:
	if (ret < 0)
		req_set_fail(req);
	if (file)
		fput(file);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

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

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

	req->sync.off = READ_ONCE(sqe->off);
	req->sync.len = READ_ONCE(sqe->len);
	req->sync.flags = READ_ONCE(sqe->sync_range_flags);
	return 0;
}

static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags)
{
	int ret;

	/* sync_file_range always requires a blocking context */
	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = sync_file_range(req->file, req->sync.off, req->sync.len,
				req->sync.flags);
	if (ret < 0)
		req_set_fail(req);
	io_req_complete(req, ret);
	return 0;
}

#if defined(CONFIG_NET)
static int io_setup_async_msg(struct io_kiocb *req,
			      struct io_async_msghdr *kmsg)
{
	struct io_async_msghdr *async_msg = req->async_data;

	if (async_msg)
		return -EAGAIN;
	if (io_alloc_async_data(req)) {
		kfree(kmsg->free_iov);
		return -ENOMEM;
	}
	async_msg = req->async_data;
	req->flags |= REQ_F_NEED_CLEANUP;
	memcpy(async_msg, kmsg, sizeof(*kmsg));
	async_msg->msg.msg_name = &async_msg->addr;
	/* if were using fast_iov, set it to the new one */
	if (!async_msg->free_iov)
		async_msg->msg.msg_iter.iov = async_msg->fast_iov;

	return -EAGAIN;
}

static int io_sendmsg_copy_hdr(struct io_kiocb *req,
			       struct io_async_msghdr *iomsg)
{
	iomsg->msg.msg_name = &iomsg->addr;
	iomsg->free_iov = iomsg->fast_iov;
	return sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg,
				   req->sr_msg.msg_flags, &iomsg->free_iov);
}

static int io_sendmsg_prep_async(struct io_kiocb *req)
{
	int ret;

	ret = io_sendmsg_copy_hdr(req, req->async_data);
	if (!ret)
		req->flags |= REQ_F_NEED_CLEANUP;
	return ret;
}

static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_sr_msg *sr = &req->sr_msg;

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

	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
	sr->len = READ_ONCE(sqe->len);
	sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
	if (sr->msg_flags & MSG_DONTWAIT)
		req->flags |= REQ_F_NOWAIT;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		sr->msg_flags |= MSG_CMSG_COMPAT;
#endif
	return 0;
}

static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_async_msghdr iomsg, *kmsg;
	struct socket *sock;
	unsigned flags;
	int min_ret = 0;
	int ret;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	if (req_has_async_data(req)) {
		kmsg = req->async_data;
	} else {
		ret = io_sendmsg_copy_hdr(req, &iomsg);
		if (ret)
			return ret;
		kmsg = &iomsg;
	}

	flags = req->sr_msg.msg_flags;
	if (issue_flags & IO_URING_F_NONBLOCK)
		flags |= MSG_DONTWAIT;
	if (flags & MSG_WAITALL)
		min_ret = iov_iter_count(&kmsg->msg.msg_iter);

	ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);

	if (ret < min_ret) {
		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
			return io_setup_async_msg(req, kmsg);
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		req_set_fail(req);
	}
	/* fast path, check for non-NULL to avoid function call */
	if (kmsg->free_iov)
		kfree(kmsg->free_iov);
	req->flags &= ~REQ_F_NEED_CLEANUP;
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_send(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_sr_msg *sr = &req->sr_msg;
	struct msghdr msg;
	struct iovec iov;
	struct socket *sock;
	unsigned flags;
	int min_ret = 0;
	int ret;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	ret = import_single_range(WRITE, sr->buf, sr->len, &iov, &msg.msg_iter);
	if (unlikely(ret))
		return ret;

	msg.msg_name = NULL;
	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_namelen = 0;

	flags = req->sr_msg.msg_flags;
	if (issue_flags & IO_URING_F_NONBLOCK)
		flags |= MSG_DONTWAIT;
	if (flags & MSG_WAITALL)
		min_ret = iov_iter_count(&msg.msg_iter);

	msg.msg_flags = flags;
	ret = sock_sendmsg(sock, &msg);
	if (ret < min_ret) {
		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
			return -EAGAIN;
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		req_set_fail(req);
	}
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
				 struct io_async_msghdr *iomsg)
{
	struct io_sr_msg *sr = &req->sr_msg;
	struct iovec __user *uiov;
	size_t iov_len;
	int ret;

	ret = __copy_msghdr_from_user(&iomsg->msg, sr->umsg,
					&iomsg->uaddr, &uiov, &iov_len);
	if (ret)
		return ret;

	if (req->flags & REQ_F_BUFFER_SELECT) {
		if (iov_len > 1)
			return -EINVAL;
		if (copy_from_user(iomsg->fast_iov, uiov, sizeof(*uiov)))
			return -EFAULT;
		sr->len = iomsg->fast_iov[0].iov_len;
		iomsg->free_iov = NULL;
	} else {
		iomsg->free_iov = iomsg->fast_iov;
		ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
				     &iomsg->free_iov, &iomsg->msg.msg_iter,
				     false);
		if (ret > 0)
			ret = 0;
	}

	return ret;
}

#ifdef CONFIG_COMPAT
static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
					struct io_async_msghdr *iomsg)
{
	struct io_sr_msg *sr = &req->sr_msg;
	struct compat_iovec __user *uiov;
	compat_uptr_t ptr;
	compat_size_t len;
	int ret;

	ret = __get_compat_msghdr(&iomsg->msg, sr->umsg_compat, &iomsg->uaddr,
				  &ptr, &len);
	if (ret)
		return ret;

	uiov = compat_ptr(ptr);
	if (req->flags & REQ_F_BUFFER_SELECT) {
		compat_ssize_t clen;

		if (len > 1)
			return -EINVAL;
		if (!access_ok(uiov, sizeof(*uiov)))
			return -EFAULT;
		if (__get_user(clen, &uiov->iov_len))
			return -EFAULT;
		if (clen < 0)
			return -EINVAL;
		sr->len = clen;
		iomsg->free_iov = NULL;
	} else {
		iomsg->free_iov = iomsg->fast_iov;
		ret = __import_iovec(READ, (struct iovec __user *)uiov, len,
				   UIO_FASTIOV, &iomsg->free_iov,
				   &iomsg->msg.msg_iter, true);
		if (ret < 0)
			return ret;
	}

	return 0;
}
#endif

static int io_recvmsg_copy_hdr(struct io_kiocb *req,
			       struct io_async_msghdr *iomsg)
{
	iomsg->msg.msg_name = &iomsg->addr;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		return __io_compat_recvmsg_copy_hdr(req, iomsg);
#endif

	return __io_recvmsg_copy_hdr(req, iomsg);
}

static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req,
					       unsigned int issue_flags)
{
	struct io_sr_msg *sr = &req->sr_msg;

	return io_buffer_select(req, &sr->len, sr->bgid, issue_flags);
}

static int io_recvmsg_prep_async(struct io_kiocb *req)
{
	int ret;

	ret = io_recvmsg_copy_hdr(req, req->async_data);
	if (!ret)
		req->flags |= REQ_F_NEED_CLEANUP;
	return ret;
}

static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_sr_msg *sr = &req->sr_msg;

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

	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
	sr->len = READ_ONCE(sqe->len);
	sr->bgid = READ_ONCE(sqe->buf_group);
	sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
	if (sr->msg_flags & MSG_DONTWAIT)
		req->flags |= REQ_F_NOWAIT;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		sr->msg_flags |= MSG_CMSG_COMPAT;
#endif
	return 0;
}

static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_async_msghdr iomsg, *kmsg;
	struct socket *sock;
	struct io_buffer *kbuf;
	unsigned flags;
	int ret, min_ret = 0;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	if (req_has_async_data(req)) {
		kmsg = req->async_data;
	} else {
		ret = io_recvmsg_copy_hdr(req, &iomsg);
		if (ret)
			return ret;
		kmsg = &iomsg;
	}

	if (req->flags & REQ_F_BUFFER_SELECT) {
		kbuf = io_recv_buffer_select(req, issue_flags);
		if (IS_ERR(kbuf))
			return PTR_ERR(kbuf);
		kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
		kmsg->fast_iov[0].iov_len = req->sr_msg.len;
		iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov,
				1, req->sr_msg.len);
	}

	flags = req->sr_msg.msg_flags;
	if (force_nonblock)
		flags |= MSG_DONTWAIT;
	if (flags & MSG_WAITALL)
		min_ret = iov_iter_count(&kmsg->msg.msg_iter);

	ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg,
					kmsg->uaddr, flags);
	if (ret < min_ret) {
		if (ret == -EAGAIN && force_nonblock)
			return io_setup_async_msg(req, kmsg);
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		req_set_fail(req);
	} else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
		req_set_fail(req);
	}

	/* fast path, check for non-NULL to avoid function call */
	if (kmsg->free_iov)
		kfree(kmsg->free_iov);
	req->flags &= ~REQ_F_NEED_CLEANUP;
	__io_req_complete(req, issue_flags, ret, io_put_kbuf(req));
	return 0;
}

static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_buffer *kbuf;
	struct io_sr_msg *sr = &req->sr_msg;
	struct msghdr msg;
	void __user *buf = sr->buf;
	struct socket *sock;
	struct iovec iov;
	unsigned flags;
	int ret, min_ret = 0;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	if (req->flags & REQ_F_BUFFER_SELECT) {
		kbuf = io_recv_buffer_select(req, issue_flags);
		if (IS_ERR(kbuf))
			return PTR_ERR(kbuf);
		buf = u64_to_user_ptr(kbuf->addr);
	}

	ret = import_single_range(READ, buf, sr->len, &iov, &msg.msg_iter);
	if (unlikely(ret))
		goto out_free;

	msg.msg_name = NULL;
	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_namelen = 0;
	msg.msg_iocb = NULL;
	msg.msg_flags = 0;

	flags = req->sr_msg.msg_flags;
	if (force_nonblock)
		flags |= MSG_DONTWAIT;
	if (flags & MSG_WAITALL)
		min_ret = iov_iter_count(&msg.msg_iter);

	ret = sock_recvmsg(sock, &msg, flags);
out_free:
	if (ret < min_ret) {
		if (ret == -EAGAIN && force_nonblock)
			return -EAGAIN;
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		req_set_fail(req);
	} else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
		req_set_fail(req);
	}

	__io_req_complete(req, issue_flags, ret, io_put_kbuf(req));
	return 0;
}

static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_accept *accept = &req->accept;

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

	accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
	accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	accept->flags = READ_ONCE(sqe->accept_flags);
	accept->nofile = rlimit(RLIMIT_NOFILE);

	accept->file_slot = READ_ONCE(sqe->file_index);
	if (accept->file_slot && ((req->open.how.flags & O_CLOEXEC) ||
				  (accept->flags & SOCK_CLOEXEC)))
		return -EINVAL;
	if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
		return -EINVAL;
	if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK))
		accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
	return 0;
}

static int io_accept(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_accept *accept = &req->accept;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
	unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0;
	bool fixed = !!accept->file_slot;
	struct file *file;
	int ret, fd;

	if (req->file->f_flags & O_NONBLOCK)
		req->flags |= REQ_F_NOWAIT;

	if (!fixed) {
		fd = __get_unused_fd_flags(accept->flags, accept->nofile);
		if (unlikely(fd < 0))
			return fd;
	}
	file = do_accept(req->file, file_flags, accept->addr, accept->addr_len,
			 accept->flags);
	if (IS_ERR(file)) {
		if (!fixed)
			put_unused_fd(fd);
		ret = PTR_ERR(file);
		if (ret == -EAGAIN && force_nonblock)
			return -EAGAIN;
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		req_set_fail(req);
	} else if (!fixed) {
		fd_install(fd, file);
		ret = fd;
	} else {
		ret = io_install_fixed_file(req, file, issue_flags,
					    accept->file_slot - 1);
	}
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_connect_prep_async(struct io_kiocb *req)
{
	struct io_async_connect *io = req->async_data;
	struct io_connect *conn = &req->connect;

	return move_addr_to_kernel(conn->addr, conn->addr_len, &io->address);
}

static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_connect *conn = &req->connect;

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

	conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
	conn->addr_len =  READ_ONCE(sqe->addr2);
	return 0;
}

static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_async_connect __io, *io;
	unsigned file_flags;
	int ret;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	if (req_has_async_data(req)) {
		io = req->async_data;
	} else {
		ret = move_addr_to_kernel(req->connect.addr,
						req->connect.addr_len,
						&__io.address);
		if (ret)
			goto out;
		io = &__io;
	}

	file_flags = force_nonblock ? O_NONBLOCK : 0;

	ret = __sys_connect_file(req->file, &io->address,
					req->connect.addr_len, file_flags);
	if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) {
		if (req_has_async_data(req))
			return -EAGAIN;
		if (io_alloc_async_data(req)) {
			ret = -ENOMEM;
			goto out;
		}
		memcpy(req->async_data, &__io, sizeof(__io));
		return -EAGAIN;
	}
	if (ret == -ERESTARTSYS)
		ret = -EINTR;
out:
	if (ret < 0)
		req_set_fail(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}
#else /* !CONFIG_NET */
#define IO_NETOP_FN(op)							\
static int io_##op(struct io_kiocb *req, unsigned int issue_flags)	\
{									\
	return -EOPNOTSUPP;						\
}

#define IO_NETOP_PREP(op)						\
IO_NETOP_FN(op)								\
static int io_##op##_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) \
{									\
	return -EOPNOTSUPP;						\
}									\

#define IO_NETOP_PREP_ASYNC(op)						\
IO_NETOP_PREP(op)							\
static int io_##op##_prep_async(struct io_kiocb *req)			\
{									\
	return -EOPNOTSUPP;						\
}

IO_NETOP_PREP_ASYNC(sendmsg);
IO_NETOP_PREP_ASYNC(recvmsg);
IO_NETOP_PREP_ASYNC(connect);
IO_NETOP_PREP(accept);
IO_NETOP_FN(send);
IO_NETOP_FN(recv);
#endif /* CONFIG_NET */

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

#define IO_POLL_CANCEL_FLAG	BIT(31)
#define IO_POLL_REF_MASK	((1u << 20)-1)

/*
 * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can
 * bump it and acquire ownership. It's disallowed to modify requests while not
 * owning it, that prevents from races for enqueueing task_work's and b/w
 * arming poll and wakeups.
 */
static inline bool io_poll_get_ownership(struct io_kiocb *req)
{
	return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK);
}

static void io_poll_mark_cancelled(struct io_kiocb *req)
{
	atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs);
}

static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req)
{
	/* pure poll stashes this in ->async_data, poll driven retry elsewhere */
	if (req->opcode == IORING_OP_POLL_ADD)
		return req->async_data;
	return req->apoll->double_poll;
}

static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req)
{
	if (req->opcode == IORING_OP_POLL_ADD)
		return &req->poll;
	return &req->apoll->poll;
}

static void io_poll_req_insert(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct hlist_head *list;

	list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
	hlist_add_head(&req->hash_node, list);
}

static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
			      wait_queue_func_t wake_func)
{
	poll->head = NULL;
#define IO_POLL_UNMASK	(EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP)
	/* mask in events that we always want/need */
	poll->events = events | IO_POLL_UNMASK;
	INIT_LIST_HEAD(&poll->wait.entry);
	init_waitqueue_func_entry(&poll->wait, wake_func);
}

static inline void io_poll_remove_entry(struct io_poll_iocb *poll)
{
	struct wait_queue_head *head = smp_load_acquire(&poll->head);

	if (head) {
		spin_lock_irq(&head->lock);
		list_del_init(&poll->wait.entry);
		poll->head = NULL;
		spin_unlock_irq(&head->lock);
	}
}

static void io_poll_remove_entries(struct io_kiocb *req)
{
	struct io_poll_iocb *poll = io_poll_get_single(req);
	struct io_poll_iocb *poll_double = io_poll_get_double(req);

	/*
	 * While we hold the waitqueue lock and the waitqueue is nonempty,
	 * wake_up_pollfree() will wait for us.  However, taking the waitqueue
	 * lock in the first place can race with the waitqueue being freed.
	 *
	 * We solve this as eventpoll does: by taking advantage of the fact that
	 * all users of wake_up_pollfree() will RCU-delay the actual free.  If
	 * we enter rcu_read_lock() and see that the pointer to the queue is
	 * non-NULL, we can then lock it without the memory being freed out from
	 * under us.
	 *
	 * Keep holding rcu_read_lock() as long as we hold the queue lock, in
	 * case the caller deletes the entry from the queue, leaving it empty.
	 * In that case, only RCU prevents the queue memory from being freed.
	 */
	rcu_read_lock();
	io_poll_remove_entry(poll);
	if (poll_double)
		io_poll_remove_entry(poll_double);
	rcu_read_unlock();
}

/*
 * All poll tw should go through this. Checks for poll events, manages
 * references, does rewait, etc.
 *
 * Returns a negative error on failure. >0 when no action require, which is
 * either spurious wakeup or multishot CQE is served. 0 when it's done with
 * the request, then the mask is stored in req->result.
 */
static int io_poll_check_events(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_poll_iocb *poll = io_poll_get_single(req);
	int v;

	/* req->task == current here, checking PF_EXITING is safe */
	if (unlikely(req->task->flags & PF_EXITING))
		io_poll_mark_cancelled(req);

	do {
		v = atomic_read(&req->poll_refs);

		/* tw handler should be the owner, and so have some references */
		if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK)))
			return 0;
		if (v & IO_POLL_CANCEL_FLAG)
			return -ECANCELED;

		if (!req->result) {
			struct poll_table_struct pt = { ._key = poll->events };

			req->result = vfs_poll(req->file, &pt) & poll->events;
		}

		/* multishot, just fill an CQE and proceed */
		if (req->result && !(poll->events & EPOLLONESHOT)) {
			__poll_t mask = mangle_poll(req->result & poll->events);
			bool filled;

			spin_lock(&ctx->completion_lock);
			filled = io_fill_cqe_aux(ctx, req->user_data, mask,
						 IORING_CQE_F_MORE);
			io_commit_cqring(ctx);
			spin_unlock(&ctx->completion_lock);
			if (unlikely(!filled))
				return -ECANCELED;
			io_cqring_ev_posted(ctx);
		} else if (req->result) {
			return 0;
		}

		/*
		 * Release all references, retry if someone tried to restart
		 * task_work while we were executing it.
		 */
	} while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs));

	return 1;
}

static void io_poll_task_func(struct io_kiocb *req, bool *locked)
{
	struct io_ring_ctx *ctx = req->ctx;
	int ret;

	ret = io_poll_check_events(req);
	if (ret > 0)
		return;

	if (!ret) {
		req->result = mangle_poll(req->result & req->poll.events);
	} else {
		req->result = ret;
		req_set_fail(req);
	}

	io_poll_remove_entries(req);
	spin_lock(&ctx->completion_lock);
	hash_del(&req->hash_node);
	__io_req_complete_post(req, req->result, 0);
	io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	io_cqring_ev_posted(ctx);
}

static void io_apoll_task_func(struct io_kiocb *req, bool *locked)
{
	struct io_ring_ctx *ctx = req->ctx;
	int ret;

	ret = io_poll_check_events(req);
	if (ret > 0)
		return;

	io_poll_remove_entries(req);
	spin_lock(&ctx->completion_lock);
	hash_del(&req->hash_node);
	spin_unlock(&ctx->completion_lock);

	if (!ret)
		io_req_task_submit(req, locked);
	else
		io_req_complete_failed(req, ret);
}

static void __io_poll_execute(struct io_kiocb *req, int mask)
{
	req->result = mask;
	if (req->opcode == IORING_OP_POLL_ADD)
		req->io_task_work.func = io_poll_task_func;
	else
		req->io_task_work.func = io_apoll_task_func;

	trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask);
	io_req_task_work_add(req, false);
}

static inline void io_poll_execute(struct io_kiocb *req, int res)
{
	if (io_poll_get_ownership(req))
		__io_poll_execute(req, res);
}

static void io_poll_cancel_req(struct io_kiocb *req)
{
	io_poll_mark_cancelled(req);
	/* kick tw, which should complete the request */
	io_poll_execute(req, 0);
}

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

	if (unlikely(mask & POLLFREE)) {
		io_poll_mark_cancelled(req);
		/* we have to kick tw in case it's not already */
		io_poll_execute(req, 0);

		/*
		 * If the waitqueue is being freed early but someone is already
		 * holds ownership over it, we have to tear down the request as
		 * best we can. That means immediately removing the request from
		 * its waitqueue and preventing all further accesses to the
		 * waitqueue via the request.
		 */
		list_del_init(&poll->wait.entry);

		/*
		 * Careful: this *must* be the last step, since as soon
		 * as req->head is NULL'ed out, the request can be
		 * completed and freed, since aio_poll_complete_work()
		 * will no longer need to take the waitqueue lock.
		 */
		smp_store_release(&poll->head, NULL);
		return 1;
	}

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

	if (io_poll_get_ownership(req)) {
		/* optional, saves extra locking for removal in tw handler */
		if (mask && poll->events & EPOLLONESHOT) {
			list_del_init(&poll->wait.entry);
			poll->head = NULL;
		}
		__io_poll_execute(req, mask);
	}
	return 1;
}

static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
			    struct wait_queue_head *head,
			    struct io_poll_iocb **poll_ptr)
{
	struct io_kiocb *req = pt->req;

	/*
	 * The file being polled uses multiple waitqueues for poll handling
	 * (e.g. one for read, one for write). Setup a separate io_poll_iocb
	 * if this happens.
	 */
	if (unlikely(pt->nr_entries)) {
		struct io_poll_iocb *first = poll;

		/* double add on the same waitqueue head, ignore */
		if (first->head == head)
			return;
		/* already have a 2nd entry, fail a third attempt */
		if (*poll_ptr) {
			if ((*poll_ptr)->head == head)
				return;
			pt->error = -EINVAL;
			return;
		}

		poll = kmalloc(sizeof(*poll), GFP_ATOMIC);
		if (!poll) {
			pt->error = -ENOMEM;
			return;
		}
		io_init_poll_iocb(poll, first->events, first->wait.func);
		*poll_ptr = poll;
		if (req->opcode == IORING_OP_POLL_ADD)
			req->flags |= REQ_F_ASYNC_DATA;
	}

	pt->nr_entries++;
	poll->head = head;
	poll->wait.private = req;

	if (poll->events & EPOLLEXCLUSIVE)
		add_wait_queue_exclusive(head, &poll->wait);
	else
		add_wait_queue(head, &poll->wait);
}

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);

	__io_queue_proc(&pt->req->poll, pt, head,
			(struct io_poll_iocb **) &pt->req->async_data);
}

static int __io_arm_poll_handler(struct io_kiocb *req,
				 struct io_poll_iocb *poll,
				 struct io_poll_table *ipt, __poll_t mask)
{
	struct io_ring_ctx *ctx = req->ctx;
	int v;

	INIT_HLIST_NODE(&req->hash_node);
	io_init_poll_iocb(poll, mask, io_poll_wake);
	poll->file = req->file;
	poll->wait.private = req;

	ipt->pt._key = mask;
	ipt->req = req;
	ipt->error = 0;
	ipt->nr_entries = 0;

	/*
	 * Take the ownership to delay any tw execution up until we're done
	 * with poll arming. see io_poll_get_ownership().
	 */
	atomic_set(&req->poll_refs, 1);
	mask = vfs_poll(req->file, &ipt->pt) & poll->events;

	if (mask && (poll->events & EPOLLONESHOT)) {
		io_poll_remove_entries(req);
		/* no one else has access to the req, forget about the ref */
		return mask;
	}
	if (!mask && unlikely(ipt->error || !ipt->nr_entries)) {
		io_poll_remove_entries(req);
		if (!ipt->error)
			ipt->error = -EINVAL;
		return 0;
	}

	spin_lock(&ctx->completion_lock);
	io_poll_req_insert(req);
	spin_unlock(&ctx->completion_lock);

	if (mask) {
		/* can't multishot if failed, just queue the event we've got */
		if (unlikely(ipt->error || !ipt->nr_entries))
			poll->events |= EPOLLONESHOT;
		__io_poll_execute(req, mask);
		return 0;
	}

	/*
	 * Release ownership. If someone tried to queue a tw while it was
	 * locked, kick it off for them.
	 */
	v = atomic_dec_return(&req->poll_refs);
	if (unlikely(v & IO_POLL_REF_MASK))
		__io_poll_execute(req, 0);
	return 0;
}

static void io_async_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);
	struct async_poll *apoll = pt->req->apoll;

	__io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
}

enum {
	IO_APOLL_OK,
	IO_APOLL_ABORTED,
	IO_APOLL_READY
};

static int io_arm_poll_handler(struct io_kiocb *req)
{
	const struct io_op_def *def = &io_op_defs[req->opcode];
	struct io_ring_ctx *ctx = req->ctx;
	struct async_poll *apoll;
	struct io_poll_table ipt;
	__poll_t mask = EPOLLONESHOT | POLLERR | POLLPRI;
	int ret;

	if (!def->pollin && !def->pollout)
		return IO_APOLL_ABORTED;
	if (!file_can_poll(req->file) || (req->flags & REQ_F_POLLED))
		return IO_APOLL_ABORTED;

	if (def->pollin) {
		mask |= POLLIN | POLLRDNORM;

		/* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */
		if ((req->opcode == IORING_OP_RECVMSG) &&
		    (req->sr_msg.msg_flags & MSG_ERRQUEUE))
			mask &= ~POLLIN;
	} else {
		mask |= POLLOUT | POLLWRNORM;
	}

	apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
	if (unlikely(!apoll))
		return IO_APOLL_ABORTED;
	apoll->double_poll = NULL;
	req->apoll = apoll;
	req->flags |= REQ_F_POLLED;
	ipt.pt._qproc = io_async_queue_proc;

	ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask);
	if (ret || ipt.error)
		return ret ? IO_APOLL_READY : IO_APOLL_ABORTED;

	trace_io_uring_poll_arm(ctx, req, req->opcode, req->user_data,
				mask, apoll->poll.events);
	return IO_APOLL_OK;
}

/*
 * Returns true if we found and killed one or more poll requests
 */
static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx,
				      struct task_struct *tsk, bool cancel_all)
{
	struct hlist_node *tmp;
	struct io_kiocb *req;
	bool found = false;
	int i;

	spin_lock(&ctx->completion_lock);
	for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
		struct hlist_head *list;

		list = &ctx->cancel_hash[i];
		hlist_for_each_entry_safe(req, tmp, list, hash_node) {
			if (io_match_task_safe(req, tsk, cancel_all)) {
				io_poll_cancel_req(req);
				found = true;
			}
		}
	}
	spin_unlock(&ctx->completion_lock);
	return found;
}

static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr,
				     bool poll_only)
	__must_hold(&ctx->completion_lock)
{
	struct hlist_head *list;
	struct io_kiocb *req;

	list = &ctx->cancel_hash[hash_long(sqe_addr, ctx->cancel_hash_bits)];
	hlist_for_each_entry(req, list, hash_node) {
		if (sqe_addr != req->user_data)
			continue;
		if (poll_only && req->opcode != IORING_OP_POLL_ADD)
			continue;
		return req;
	}
	return NULL;
}

static bool io_poll_disarm(struct io_kiocb *req)
	__must_hold(&ctx->completion_lock)
{
	if (!io_poll_get_ownership(req))
		return false;
	io_poll_remove_entries(req);
	hash_del(&req->hash_node);
	return true;
}

static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr,
			  bool poll_only)
	__must_hold(&ctx->completion_lock)
{
	struct io_kiocb *req = io_poll_find(ctx, sqe_addr, poll_only);

	if (!req)
		return -ENOENT;
	io_poll_cancel_req(req);
	return 0;
}

static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe,
				     unsigned int flags)
{
	u32 events;

	events = READ_ONCE(sqe->poll32_events);
#ifdef __BIG_ENDIAN
	events = swahw32(events);
#endif
	if (!(flags & IORING_POLL_ADD_MULTI))
		events |= EPOLLONESHOT;
	return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT));
}

static int io_poll_update_prep(struct io_kiocb *req,
			       const struct io_uring_sqe *sqe)
{
	struct io_poll_update *upd = &req->poll_update;
	u32 flags;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)
		return -EINVAL;
	flags = READ_ONCE(sqe->len);
	if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA |
		      IORING_POLL_ADD_MULTI))
		return -EINVAL;
	/* meaningless without update */
	if (flags == IORING_POLL_ADD_MULTI)
		return -EINVAL;

	upd->old_user_data = READ_ONCE(sqe->addr);
	upd->update_events = flags & IORING_POLL_UPDATE_EVENTS;
	upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA;

	upd->new_user_data = READ_ONCE(sqe->off);
	if (!upd->update_user_data && upd->new_user_data)
		return -EINVAL;
	if (upd->update_events)
		upd->events = io_poll_parse_events(sqe, flags);
	else if (sqe->poll32_events)
		return -EINVAL;

	return 0;
}

static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_poll_iocb *poll = &req->poll;
	u32 flags;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr)
		return -EINVAL;
	flags = READ_ONCE(sqe->len);
	if (flags & ~IORING_POLL_ADD_MULTI)
		return -EINVAL;
	if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP))
		return -EINVAL;

	io_req_set_refcount(req);
	poll->events = io_poll_parse_events(sqe, flags);
	return 0;
}

static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_poll_iocb *poll = &req->poll;
	struct io_poll_table ipt;
	int ret;

	ipt.pt._qproc = io_poll_queue_proc;

	ret = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events);
	ret = ret ?: ipt.error;
	if (ret)
		__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_kiocb *preq;
	int ret2, ret = 0;
	bool locked;

	spin_lock(&ctx->completion_lock);
	preq = io_poll_find(ctx, req->poll_update.old_user_data, true);
	if (!preq || !io_poll_disarm(preq)) {
		spin_unlock(&ctx->completion_lock);
		ret = preq ? -EALREADY : -ENOENT;
		goto out;
	}
	spin_unlock(&ctx->completion_lock);

	if (req->poll_update.update_events || req->poll_update.update_user_data) {
		/* only mask one event flags, keep behavior flags */
		if (req->poll_update.update_events) {
			preq->poll.events &= ~0xffff;
			preq->poll.events |= req->poll_update.events & 0xffff;
			preq->poll.events |= IO_POLL_UNMASK;
		}
		if (req->poll_update.update_user_data)
			preq->user_data = req->poll_update.new_user_data;

		ret2 = io_poll_add(preq, issue_flags);
		/* successfully updated, don't complete poll request */
		if (!ret2)
			goto out;
	}

	req_set_fail(preq);
	preq->result = -ECANCELED;
	locked = !(issue_flags & IO_URING_F_UNLOCKED);
	io_req_task_complete(preq, &locked);
out:
	if (ret < 0)
		req_set_fail(req);
	/* complete update request, we're done with it */
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
{
	struct io_timeout_data *data = container_of(timer,
						struct io_timeout_data, timer);
	struct io_kiocb *req = data->req;
	struct io_ring_ctx *ctx = req->ctx;
	unsigned long flags;

	spin_lock_irqsave(&ctx->timeout_lock, flags);
	list_del_init(&req->timeout.list);
	atomic_set(&req->ctx->cq_timeouts,
		atomic_read(&req->ctx->cq_timeouts) + 1);
	spin_unlock_irqrestore(&ctx->timeout_lock, flags);

	if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS))
		req_set_fail(req);

	req->result = -ETIME;
	req->io_task_work.func = io_req_task_complete;
	io_req_task_work_add(req, false);
	return HRTIMER_NORESTART;
}

static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx,
					   __u64 user_data)
	__must_hold(&ctx->timeout_lock)
{
	struct io_timeout_data *io;
	struct io_kiocb *req;
	bool found = false;

	list_for_each_entry(req, &ctx->timeout_list, timeout.list) {
		found = user_data == req->user_data;
		if (found)
			break;
	}
	if (!found)
		return ERR_PTR(-ENOENT);

	io = req->async_data;
	if (hrtimer_try_to_cancel(&io->timer) == -1)
		return ERR_PTR(-EALREADY);
	list_del_init(&req->timeout.list);
	return req;
}

static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data)
	__must_hold(&ctx->completion_lock)
	__must_hold(&ctx->timeout_lock)
{
	struct io_kiocb *req = io_timeout_extract(ctx, user_data);

	if (IS_ERR(req))
		return PTR_ERR(req);

	req_set_fail(req);
	io_fill_cqe_req(req, -ECANCELED, 0);
	io_put_req_deferred(req);
	return 0;
}

static clockid_t io_timeout_get_clock(struct io_timeout_data *data)
{
	switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) {
	case IORING_TIMEOUT_BOOTTIME:
		return CLOCK_BOOTTIME;
	case IORING_TIMEOUT_REALTIME:
		return CLOCK_REALTIME;
	default:
		/* can't happen, vetted at prep time */
		WARN_ON_ONCE(1);
		fallthrough;
	case 0:
		return CLOCK_MONOTONIC;
	}
}

static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
				    struct timespec64 *ts, enum hrtimer_mode mode)
	__must_hold(&ctx->timeout_lock)
{
	struct io_timeout_data *io;
	struct io_kiocb *req;
	bool found = false;

	list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) {
		found = user_data == req->user_data;
		if (found)
			break;
	}
	if (!found)
		return -ENOENT;

	io = req->async_data;
	if (hrtimer_try_to_cancel(&io->timer) == -1)
		return -EALREADY;
	hrtimer_init(&io->timer, io_timeout_get_clock(io), mode);
	io->timer.function = io_link_timeout_fn;
	hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode);
	return 0;
}

static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
			     struct timespec64 *ts, enum hrtimer_mode mode)
	__must_hold(&ctx->timeout_lock)
{
	struct io_kiocb *req = io_timeout_extract(ctx, user_data);
	struct io_timeout_data *data;

	if (IS_ERR(req))
		return PTR_ERR(req);

	req->timeout.off = 0; /* noseq */
	data = req->async_data;
	list_add_tail(&req->timeout.list, &ctx->timeout_list);
	hrtimer_init(&data->timer, io_timeout_get_clock(data), mode);
	data->timer.function = io_timeout_fn;
	hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode);
	return 0;
}

static int io_timeout_remove_prep(struct io_kiocb *req,
				  const struct io_uring_sqe *sqe)
{
	struct io_timeout_rem *tr = &req->timeout_rem;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->splice_fd_in)
		return -EINVAL;

	tr->ltimeout = false;
	tr->addr = READ_ONCE(sqe->addr);
	tr->flags = READ_ONCE(sqe->timeout_flags);
	if (tr->flags & IORING_TIMEOUT_UPDATE_MASK) {
		if (hweight32(tr->flags & IORING_TIMEOUT_CLOCK_MASK) > 1)
			return -EINVAL;
		if (tr->flags & IORING_LINK_TIMEOUT_UPDATE)
			tr->ltimeout = true;
		if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS))
			return -EINVAL;
		if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2)))
			return -EFAULT;
		if (tr->ts.tv_sec < 0 || tr->ts.tv_nsec < 0)
			return -EINVAL;
	} else if (tr->flags) {
		/* timeout removal doesn't support flags */
		return -EINVAL;
	}

	return 0;
}

static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags)
{
	return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS
					    : HRTIMER_MODE_REL;
}

/*
 * Remove or update an existing timeout command
 */
static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_timeout_rem *tr = &req->timeout_rem;
	struct io_ring_ctx *ctx = req->ctx;
	int ret;

	if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) {
		spin_lock(&ctx->completion_lock);
		spin_lock_irq(&ctx->timeout_lock);
		ret = io_timeout_cancel(ctx, tr->addr);
		spin_unlock_irq(&ctx->timeout_lock);
		spin_unlock(&ctx->completion_lock);
	} else {
		enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags);

		spin_lock_irq(&ctx->timeout_lock);
		if (tr->ltimeout)
			ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode);
		else
			ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode);
		spin_unlock_irq(&ctx->timeout_lock);
	}

	if (ret < 0)
		req_set_fail(req);
	io_req_complete_post(req, ret, 0);
	return 0;
}

static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
			   bool is_timeout_link)
{
	struct io_timeout_data *data;
	unsigned flags;
	u32 off = READ_ONCE(sqe->off);

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index || sqe->len != 1 ||
	    sqe->splice_fd_in)
		return -EINVAL;
	if (off && is_timeout_link)
		return -EINVAL;
	flags = READ_ONCE(sqe->timeout_flags);
	if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK |
		      IORING_TIMEOUT_ETIME_SUCCESS))
		return -EINVAL;
	/* more than one clock specified is invalid, obviously */
	if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1)
		return -EINVAL;

	INIT_LIST_HEAD(&req->timeout.list);
	req->timeout.off = off;
	if (unlikely(off && !req->ctx->off_timeout_used))
		req->ctx->off_timeout_used = true;

	if (WARN_ON_ONCE(req_has_async_data(req)))
		return -EFAULT;
	if (io_alloc_async_data(req))
		return -ENOMEM;

	data = req->async_data;
	data->req = req;
	data->flags = flags;

	if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr)))
		return -EFAULT;

	if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)
		return -EINVAL;

	data->mode = io_translate_timeout_mode(flags);
	hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);

	if (is_timeout_link) {
		struct io_submit_link *link = &req->ctx->submit_state.link;

		if (!link->head)
			return -EINVAL;
		if (link->last->opcode == IORING_OP_LINK_TIMEOUT)
			return -EINVAL;
		req->timeout.head = link->last;
		link->last->flags |= REQ_F_ARM_LTIMEOUT;
	}
	return 0;
}

static int io_timeout(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_timeout_data *data = req->async_data;
	struct list_head *entry;
	u32 tail, off = req->timeout.off;

	spin_lock_irq(&ctx->timeout_lock);

	/*
	 * sqe->off holds how many events that need to occur for this
	 * timeout event to be satisfied. If it isn't set, then this is
	 * a pure timeout request, sequence isn't used.
	 */
	if (io_is_timeout_noseq(req)) {
		entry = ctx->timeout_list.prev;
		goto add;
	}

	tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
	req->timeout.target_seq = tail + off;

	/* Update the last seq here in case io_flush_timeouts() hasn't.
	 * This is safe because ->completion_lock is held, and submissions
	 * and completions are never mixed in the same ->completion_lock section.
	 */
	ctx->cq_last_tm_flush = tail;

	/*
	 * Insertion sort, ensuring the first entry in the list is always
	 * the one we need first.
	 */
	list_for_each_prev(entry, &ctx->timeout_list) {
		struct io_kiocb *nxt = list_entry(entry, struct io_kiocb,
						  timeout.list);

		if (io_is_timeout_noseq(nxt))
			continue;
		/* nxt.seq is behind @tail, otherwise would've been completed */
		if (off >= nxt->timeout.target_seq - tail)
			break;
	}
add:
	list_add(&req->timeout.list, entry);
	data->timer.function = io_timeout_fn;
	hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode);
	spin_unlock_irq(&ctx->timeout_lock);
	return 0;
}

struct io_cancel_data {
	struct io_ring_ctx *ctx;
	u64 user_data;
};

static bool io_cancel_cb(struct io_wq_work *work, void *data)
{
	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
	struct io_cancel_data *cd = data;

	return req->ctx == cd->ctx && req->user_data == cd->user_data;
}

static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data,
			       struct io_ring_ctx *ctx)
{
	struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, };
	enum io_wq_cancel cancel_ret;
	int ret = 0;

	if (!tctx || !tctx->io_wq)
		return -ENOENT;

	cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false);
	switch (cancel_ret) {
	case IO_WQ_CANCEL_OK:
		ret = 0;
		break;
	case IO_WQ_CANCEL_RUNNING:
		ret = -EALREADY;
		break;
	case IO_WQ_CANCEL_NOTFOUND:
		ret = -ENOENT;
		break;
	}

	return ret;
}

static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr)
{
	struct io_ring_ctx *ctx = req->ctx;
	int ret;

	WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current);

	ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
	/*
	 * Fall-through even for -EALREADY, as we may have poll armed
	 * that need unarming.
	 */
	if (!ret)
		return 0;

	spin_lock(&ctx->completion_lock);
	ret = io_poll_cancel(ctx, sqe_addr, false);
	if (ret != -ENOENT)
		goto out;

	spin_lock_irq(&ctx->timeout_lock);
	ret = io_timeout_cancel(ctx, sqe_addr);
	spin_unlock_irq(&ctx->timeout_lock);
out:
	spin_unlock(&ctx->completion_lock);
	return ret;
}

static int io_async_cancel_prep(struct io_kiocb *req,
				const struct io_uring_sqe *sqe)
{
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
		return -EINVAL;
	if (sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags ||
	    sqe->splice_fd_in)
		return -EINVAL;

	req->cancel.addr = READ_ONCE(sqe->addr);
	return 0;
}

static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	u64 sqe_addr = req->cancel.addr;
	bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
	struct io_tctx_node *node;
	int ret;

	ret = io_try_cancel_userdata(req, sqe_addr);
	if (ret != -ENOENT)
		goto done;

	/* slow path, try all io-wq's */
	io_ring_submit_lock(ctx, needs_lock);
	ret = -ENOENT;
	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
		struct io_uring_task *tctx = node->task->io_uring;

		ret = io_async_cancel_one(tctx, req->cancel.addr, ctx);
		if (ret != -ENOENT)
			break;
	}
	io_ring_submit_unlock(ctx, needs_lock);
done:
	if (ret < 0)
		req_set_fail(req);
	io_req_complete_post(req, ret, 0);
	return 0;
}

static int io_rsrc_update_prep(struct io_kiocb *req,
				const struct io_uring_sqe *sqe)
{
	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
		return -EINVAL;
	if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in)
		return -EINVAL;

	req->rsrc_update.offset = READ_ONCE(sqe->off);
	req->rsrc_update.nr_args = READ_ONCE(sqe->len);
	if (!req->rsrc_update.nr_args)
		return -EINVAL;
	req->rsrc_update.arg = READ_ONCE(sqe->addr);
	return 0;
}

static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
	struct io_uring_rsrc_update2 up;
	int ret;

	up.offset = req->rsrc_update.offset;
	up.data = req->rsrc_update.arg;
	up.nr = 0;
	up.tags = 0;
	up.resv = 0;

	io_ring_submit_lock(ctx, needs_lock);
	ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE,
					&up, req->rsrc_update.nr_args);
	io_ring_submit_unlock(ctx, needs_lock);

	if (ret < 0)
		req_set_fail(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	switch (req->opcode) {
	case IORING_OP_NOP:
		return 0;
	case IORING_OP_READV:
	case IORING_OP_READ_FIXED:
	case IORING_OP_READ:
		return io_read_prep(req, sqe);
	case IORING_OP_WRITEV:
	case IORING_OP_WRITE_FIXED:
	case IORING_OP_WRITE:
		return io_write_prep(req, sqe);
	case IORING_OP_POLL_ADD:
		return io_poll_add_prep(req, sqe);
	case IORING_OP_POLL_REMOVE:
		return io_poll_update_prep(req, sqe);
	case IORING_OP_FSYNC:
		return io_fsync_prep(req, sqe);
	case IORING_OP_SYNC_FILE_RANGE:
		return io_sfr_prep(req, sqe);
	case IORING_OP_SENDMSG:
	case IORING_OP_SEND:
		return io_sendmsg_prep(req, sqe);
	case IORING_OP_RECVMSG:
	case IORING_OP_RECV:
		return io_recvmsg_prep(req, sqe);
	case IORING_OP_CONNECT:
		return io_connect_prep(req, sqe);
	case IORING_OP_TIMEOUT:
		return io_timeout_prep(req, sqe, false);
	case IORING_OP_TIMEOUT_REMOVE:
		return io_timeout_remove_prep(req, sqe);
	case IORING_OP_ASYNC_CANCEL:
		return io_async_cancel_prep(req, sqe);
	case IORING_OP_LINK_TIMEOUT:
		return io_timeout_prep(req, sqe, true);
	case IORING_OP_ACCEPT:
		return io_accept_prep(req, sqe);
	case IORING_OP_FALLOCATE:
		return io_fallocate_prep(req, sqe);
	case IORING_OP_OPENAT:
		return io_openat_prep(req, sqe);
	case IORING_OP_CLOSE:
		return io_close_prep(req, sqe);
	case IORING_OP_FILES_UPDATE:
		return io_rsrc_update_prep(req, sqe);
	case IORING_OP_STATX:
		return io_statx_prep(req, sqe);
	case IORING_OP_FADVISE:
		return io_fadvise_prep(req, sqe);
	case IORING_OP_MADVISE:
		return io_madvise_prep(req, sqe);
	case IORING_OP_OPENAT2:
		return io_openat2_prep(req, sqe);
	case IORING_OP_EPOLL_CTL:
		return io_epoll_ctl_prep(req, sqe);
	case IORING_OP_SPLICE:
		return io_splice_prep(req, sqe);
	case IORING_OP_PROVIDE_BUFFERS:
		return io_provide_buffers_prep(req, sqe);
	case IORING_OP_REMOVE_BUFFERS:
		return io_remove_buffers_prep(req, sqe);
	case IORING_OP_TEE:
		return io_tee_prep(req, sqe);
	case IORING_OP_SHUTDOWN:
		return io_shutdown_prep(req, sqe);
	case IORING_OP_RENAMEAT:
		return io_renameat_prep(req, sqe);
	case IORING_OP_UNLINKAT:
		return io_unlinkat_prep(req, sqe);
	case IORING_OP_MKDIRAT:
		return io_mkdirat_prep(req, sqe);
	case IORING_OP_SYMLINKAT:
		return io_symlinkat_prep(req, sqe);
	case IORING_OP_LINKAT:
		return io_linkat_prep(req, sqe);
	}

	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
			req->opcode);
	return -EINVAL;
}

static int io_req_prep_async(struct io_kiocb *req)
{
	if (!io_op_defs[req->opcode].needs_async_setup)
		return 0;
	if (WARN_ON_ONCE(req_has_async_data(req)))
		return -EFAULT;
	if (io_alloc_async_data(req))
		return -EAGAIN;

	switch (req->opcode) {
	case IORING_OP_READV:
		return io_rw_prep_async(req, READ);
	case IORING_OP_WRITEV:
		return io_rw_prep_async(req, WRITE);
	case IORING_OP_SENDMSG:
		return io_sendmsg_prep_async(req);
	case IORING_OP_RECVMSG:
		return io_recvmsg_prep_async(req);
	case IORING_OP_CONNECT:
		return io_connect_prep_async(req);
	}
	printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n",
		    req->opcode);
	return -EFAULT;
}

static u32 io_get_sequence(struct io_kiocb *req)
{
	u32 seq = req->ctx->cached_sq_head;

	/* need original cached_sq_head, but it was increased for each req */
	io_for_each_link(req, req)
		seq--;
	return seq;
}

static __cold void io_drain_req(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_defer_entry *de;
	int ret;
	u32 seq = io_get_sequence(req);

	/* Still need defer if there is pending req in defer list. */
	spin_lock(&ctx->completion_lock);
	if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) {
		spin_unlock(&ctx->completion_lock);
queue:
		ctx->drain_active = false;
		io_req_task_queue(req);
		return;
	}
	spin_unlock(&ctx->completion_lock);

	ret = io_req_prep_async(req);
	if (ret) {
fail:
		io_req_complete_failed(req, ret);
		return;
	}
	io_prep_async_link(req);
	de = kmalloc(sizeof(*de), GFP_KERNEL);
	if (!de) {
		ret = -ENOMEM;
		goto fail;
	}

	spin_lock(&ctx->completion_lock);
	if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) {
		spin_unlock(&ctx->completion_lock);
		kfree(de);
		goto queue;
	}

	trace_io_uring_defer(ctx, req, req->user_data);
	de->req = req;
	de->seq = seq;
	list_add_tail(&de->list, &ctx->defer_list);
	spin_unlock(&ctx->completion_lock);
}

static void io_clean_op(struct io_kiocb *req)
{
	if (req->flags & REQ_F_BUFFER_SELECTED)
		io_put_kbuf(req);

	if (req->flags & REQ_F_NEED_CLEANUP) {
		switch (req->opcode) {
		case IORING_OP_READV:
		case IORING_OP_READ_FIXED:
		case IORING_OP_READ:
		case IORING_OP_WRITEV:
		case IORING_OP_WRITE_FIXED:
		case IORING_OP_WRITE: {
			struct io_async_rw *io = req->async_data;

			kfree(io->free_iovec);
			break;
			}
		case IORING_OP_RECVMSG:
		case IORING_OP_SENDMSG: {
			struct io_async_msghdr *io = req->async_data;

			kfree(io->free_iov);
			break;
			}
		case IORING_OP_SPLICE:
		case IORING_OP_TEE:
			if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED))
				io_put_file(req->splice.file_in);
			break;
		case IORING_OP_OPENAT:
		case IORING_OP_OPENAT2:
			if (req->open.filename)
				putname(req->open.filename);
			break;
		case IORING_OP_RENAMEAT:
			putname(req->rename.oldpath);
			putname(req->rename.newpath);
			break;
		case IORING_OP_UNLINKAT:
			putname(req->unlink.filename);
			break;
		case IORING_OP_MKDIRAT:
			putname(req->mkdir.filename);
			break;
		case IORING_OP_SYMLINKAT:
			putname(req->symlink.oldpath);
			putname(req->symlink.newpath);
			break;
		case IORING_OP_LINKAT:
			putname(req->hardlink.oldpath);
			putname(req->hardlink.newpath);
			break;
		}
	}
	if ((req->flags & REQ_F_POLLED) && req->apoll) {
		kfree(req->apoll->double_poll);
		kfree(req->apoll);
		req->apoll = NULL;
	}
	if (req->flags & REQ_F_INFLIGHT) {
		struct io_uring_task *tctx = req->task->io_uring;

		atomic_dec(&tctx->inflight_tracked);
	}
	if (req->flags & REQ_F_CREDS)
		put_cred(req->creds);
	if (req->flags & REQ_F_ASYNC_DATA) {
		kfree(req->async_data);
		req->async_data = NULL;
	}
	req->flags &= ~IO_REQ_CLEAN_FLAGS;
}

static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
{
	const struct cred *creds = NULL;
	int ret;

	if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
		creds = override_creds(req->creds);

	if (!io_op_defs[req->opcode].audit_skip)
		audit_uring_entry(req->opcode);

	switch (req->opcode) {
	case IORING_OP_NOP:
		ret = io_nop(req, issue_flags);
		break;
	case IORING_OP_READV:
	case IORING_OP_READ_FIXED:
	case IORING_OP_READ:
		ret = io_read(req, issue_flags);
		break;
	case IORING_OP_WRITEV:
	case IORING_OP_WRITE_FIXED:
	case IORING_OP_WRITE:
		ret = io_write(req, issue_flags);
		break;
	case IORING_OP_FSYNC:
		ret = io_fsync(req, issue_flags);
		break;
	case IORING_OP_POLL_ADD:
		ret = io_poll_add(req, issue_flags);
		break;
	case IORING_OP_POLL_REMOVE:
		ret = io_poll_update(req, issue_flags);
		break;
	case IORING_OP_SYNC_FILE_RANGE:
		ret = io_sync_file_range(req, issue_flags);
		break;
	case IORING_OP_SENDMSG:
		ret = io_sendmsg(req, issue_flags);
		break;
	case IORING_OP_SEND:
		ret = io_send(req, issue_flags);
		break;
	case IORING_OP_RECVMSG:
		ret = io_recvmsg(req, issue_flags);
		break;
	case IORING_OP_RECV:
		ret = io_recv(req, issue_flags);
		break;
	case IORING_OP_TIMEOUT:
		ret = io_timeout(req, issue_flags);
		break;
	case IORING_OP_TIMEOUT_REMOVE:
		ret = io_timeout_remove(req, issue_flags);
		break;
	case IORING_OP_ACCEPT:
		ret = io_accept(req, issue_flags);
		break;
	case IORING_OP_CONNECT:
		ret = io_connect(req, issue_flags);
		break;
	case IORING_OP_ASYNC_CANCEL:
		ret = io_async_cancel(req, issue_flags);
		break;
	case IORING_OP_FALLOCATE:
		ret = io_fallocate(req, issue_flags);
		break;
	case IORING_OP_OPENAT:
		ret = io_openat(req, issue_flags);
		break;
	case IORING_OP_CLOSE:
		ret = io_close(req, issue_flags);
		break;
	case IORING_OP_FILES_UPDATE:
		ret = io_files_update(req, issue_flags);
		break;
	case IORING_OP_STATX:
		ret = io_statx(req, issue_flags);
		break;
	case IORING_OP_FADVISE:
		ret = io_fadvise(req, issue_flags);
		break;
	case IORING_OP_MADVISE:
		ret = io_madvise(req, issue_flags);
		break;
	case IORING_OP_OPENAT2:
		ret = io_openat2(req, issue_flags);
		break;
	case IORING_OP_EPOLL_CTL:
		ret = io_epoll_ctl(req, issue_flags);
		break;
	case IORING_OP_SPLICE:
		ret = io_splice(req, issue_flags);
		break;
	case IORING_OP_PROVIDE_BUFFERS:
		ret = io_provide_buffers(req, issue_flags);
		break;
	case IORING_OP_REMOVE_BUFFERS:
		ret = io_remove_buffers(req, issue_flags);
		break;
	case IORING_OP_TEE:
		ret = io_tee(req, issue_flags);
		break;
	case IORING_OP_SHUTDOWN:
		ret = io_shutdown(req, issue_flags);
		break;
	case IORING_OP_RENAMEAT:
		ret = io_renameat(req, issue_flags);
		break;
	case IORING_OP_UNLINKAT:
		ret = io_unlinkat(req, issue_flags);
		break;
	case IORING_OP_MKDIRAT:
		ret = io_mkdirat(req, issue_flags);
		break;
	case IORING_OP_SYMLINKAT:
		ret = io_symlinkat(req, issue_flags);
		break;
	case IORING_OP_LINKAT:
		ret = io_linkat(req, issue_flags);
		break;
	default:
		ret = -EINVAL;
		break;
	}

	if (!io_op_defs[req->opcode].audit_skip)
		audit_uring_exit(!ret, ret);

	if (creds)
		revert_creds(creds);
	if (ret)
		return ret;
	/* If the op doesn't have a file, we're not polling for it */
	if ((req->ctx->flags & IORING_SETUP_IOPOLL) && req->file)
		io_iopoll_req_issued(req, issue_flags);

	return 0;
}

static struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
{
	struct io_kiocb *req = container_of(work, struct io_kiocb, work);

	req = io_put_req_find_next(req);
	return req ? &req->work : NULL;
}

static void io_wq_submit_work(struct io_wq_work *work)
{
	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
	unsigned int issue_flags = IO_URING_F_UNLOCKED;
	bool needs_poll = false;
	struct io_kiocb *timeout;
	int ret = 0;

	/* one will be dropped by ->io_free_work() after returning to io-wq */
	if (!(req->flags & REQ_F_REFCOUNT))
		__io_req_set_refcount(req, 2);
	else
		req_ref_get(req);

	timeout = io_prep_linked_timeout(req);
	if (timeout)
		io_queue_linked_timeout(timeout);

	/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
	if (work->flags & IO_WQ_WORK_CANCEL) {
		io_req_task_queue_fail(req, -ECANCELED);
		return;
	}

	if (req->flags & REQ_F_FORCE_ASYNC) {
		const struct io_op_def *def = &io_op_defs[req->opcode];
		bool opcode_poll = def->pollin || def->pollout;

		if (opcode_poll && file_can_poll(req->file)) {
			needs_poll = true;
			issue_flags |= IO_URING_F_NONBLOCK;
		}
	}

	do {
		ret = io_issue_sqe(req, issue_flags);
		if (ret != -EAGAIN)
			break;
		/*
		 * We can get EAGAIN for iopolled IO even though we're
		 * forcing a sync submission from here, since we can't
		 * wait for request slots on the block side.
		 */
		if (!needs_poll) {
			cond_resched();
			continue;
		}

		if (io_arm_poll_handler(req) == IO_APOLL_OK)
			return;
		/* aborted or ready, in either case retry blocking */
		needs_poll = false;
		issue_flags &= ~IO_URING_F_NONBLOCK;
	} while (1);

	/* avoid locking problems by failing it from a clean context */
	if (ret)
		io_req_task_queue_fail(req, ret);
}

static inline struct io_fixed_file *io_fixed_file_slot(struct io_file_table *table,
						       unsigned i)
{
	return &table->files[i];
}

static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
					      int index)
{
	struct io_fixed_file *slot = io_fixed_file_slot(&ctx->file_table, index);

	return (struct file *) (slot->file_ptr & FFS_MASK);
}

static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file)
{
	unsigned long file_ptr = (unsigned long) file;

	file_ptr |= io_file_get_flags(file);
	file_slot->file_ptr = file_ptr;
}

static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx,
					     struct io_kiocb *req, int fd)
{
	struct file *file;
	unsigned long file_ptr;

	if (unlikely((unsigned int)fd >= ctx->nr_user_files))
		return NULL;
	fd = array_index_nospec(fd, ctx->nr_user_files);
	file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
	file = (struct file *) (file_ptr & FFS_MASK);
	file_ptr &= ~FFS_MASK;
	/* mask in overlapping REQ_F and FFS bits */
	req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT);
	io_req_set_rsrc_node(req, ctx);
	return file;
}

static struct file *io_file_get_normal(struct io_ring_ctx *ctx,
				       struct io_kiocb *req, int fd)
{
	struct file *file = fget(fd);

	trace_io_uring_file_get(ctx, fd);

	/* we don't allow fixed io_uring files */
	if (file && unlikely(file->f_op == &io_uring_fops))
		io_req_track_inflight(req);
	return file;
}

static inline struct file *io_file_get(struct io_ring_ctx *ctx,
				       struct io_kiocb *req, int fd, bool fixed)
{
	if (fixed)
		return io_file_get_fixed(ctx, req, fd);
	else
		return io_file_get_normal(ctx, req, fd);
}

static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked)
{
	struct io_kiocb *prev = req->timeout.prev;
	int ret = -ENOENT;

	if (prev) {
		if (!(req->task->flags & PF_EXITING))
			ret = io_try_cancel_userdata(req, prev->user_data);
		io_req_complete_post(req, ret ?: -ETIME, 0);
		io_put_req(prev);
	} else {
		io_req_complete_post(req, -ETIME, 0);
	}
}

static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer)
{
	struct io_timeout_data *data = container_of(timer,
						struct io_timeout_data, timer);
	struct io_kiocb *prev, *req = data->req;
	struct io_ring_ctx *ctx = req->ctx;
	unsigned long flags;

	spin_lock_irqsave(&ctx->timeout_lock, flags);
	prev = req->timeout.head;
	req->timeout.head = NULL;

	/*
	 * We don't expect the list to be empty, that will only happen if we
	 * race with the completion of the linked work.
	 */
	if (prev) {
		io_remove_next_linked(prev);
		if (!req_ref_inc_not_zero(prev))
			prev = NULL;
	}
	list_del(&req->timeout.list);
	req->timeout.prev = prev;
	spin_unlock_irqrestore(&ctx->timeout_lock, flags);

	req->io_task_work.func = io_req_task_link_timeout;
	io_req_task_work_add(req, false);
	return HRTIMER_NORESTART;
}

static void io_queue_linked_timeout(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;

	spin_lock_irq(&ctx->timeout_lock);
	/*
	 * If the back reference is NULL, then our linked request finished
	 * before we got a chance to setup the timer
	 */
	if (req->timeout.head) {
		struct io_timeout_data *data = req->async_data;

		data->timer.function = io_link_timeout_fn;
		hrtimer_start(&data->timer, timespec64_to_ktime(data->ts),
				data->mode);
		list_add_tail(&req->timeout.list, &ctx->ltimeout_list);
	}
	spin_unlock_irq(&ctx->timeout_lock);
	/* drop submission reference */
	io_put_req(req);
}

static void io_queue_sqe_arm_apoll(struct io_kiocb *req)
	__must_hold(&req->ctx->uring_lock)
{
	struct io_kiocb *linked_timeout = io_prep_linked_timeout(req);

	switch (io_arm_poll_handler(req)) {
	case IO_APOLL_READY:
		io_req_task_queue(req);
		break;
	case IO_APOLL_ABORTED:
		/*
		 * Queued up for async execution, worker will release
		 * submit reference when the iocb is actually submitted.
		 */
		io_queue_async_work(req, NULL);
		break;
	}

	if (linked_timeout)
		io_queue_linked_timeout(linked_timeout);
}

static inline void __io_queue_sqe(struct io_kiocb *req)
	__must_hold(&req->ctx->uring_lock)
{
	struct io_kiocb *linked_timeout;
	int ret;

	ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER);

	if (req->flags & REQ_F_COMPLETE_INLINE) {
		io_req_add_compl_list(req);
		return;
	}
	/*
	 * We async punt it if the file wasn't marked NOWAIT, or if the file
	 * doesn't support non-blocking read/write attempts
	 */
	if (likely(!ret)) {
		linked_timeout = io_prep_linked_timeout(req);
		if (linked_timeout)
			io_queue_linked_timeout(linked_timeout);
	} else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
		io_queue_sqe_arm_apoll(req);
	} else {
		io_req_complete_failed(req, ret);
	}
}

static void io_queue_sqe_fallback(struct io_kiocb *req)
	__must_hold(&req->ctx->uring_lock)
{
	if (req->flags & REQ_F_FAIL) {
		io_req_complete_fail_submit(req);
	} else if (unlikely(req->ctx->drain_active)) {
		io_drain_req(req);
	} else {
		int ret = io_req_prep_async(req);

		if (unlikely(ret))
			io_req_complete_failed(req, ret);
		else
			io_queue_async_work(req, NULL);
	}
}

static inline void io_queue_sqe(struct io_kiocb *req)
	__must_hold(&req->ctx->uring_lock)
{
	if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL))))
		__io_queue_sqe(req);
	else
		io_queue_sqe_fallback(req);
}

/*
 * Check SQE restrictions (opcode and flags).
 *
 * Returns 'true' if SQE is allowed, 'false' otherwise.
 */
static inline bool io_check_restriction(struct io_ring_ctx *ctx,
					struct io_kiocb *req,
					unsigned int sqe_flags)
{
	if (!test_bit(req->opcode, ctx->restrictions.sqe_op))
		return false;

	if ((sqe_flags & ctx->restrictions.sqe_flags_required) !=
	    ctx->restrictions.sqe_flags_required)
		return false;

	if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed |
			  ctx->restrictions.sqe_flags_required))
		return false;

	return true;
}

static void io_init_req_drain(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_kiocb *head = ctx->submit_state.link.head;

	ctx->drain_active = true;
	if (head) {
		/*
		 * If we need to drain a request in the middle of a link, drain
		 * the head request and the next request/link after the current
		 * link. Considering sequential execution of links,
		 * REQ_F_IO_DRAIN will be maintained for every request of our
		 * link.
		 */
		head->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC;
		ctx->drain_next = true;
	}
}

static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
		       const struct io_uring_sqe *sqe)
	__must_hold(&ctx->uring_lock)
{
	unsigned int sqe_flags;
	int personality;
	u8 opcode;

	/* req is partially pre-initialised, see io_preinit_req() */
	req->opcode = opcode = READ_ONCE(sqe->opcode);
	/* same numerical values with corresponding REQ_F_*, safe to copy */
	req->flags = sqe_flags = READ_ONCE(sqe->flags);
	req->user_data = READ_ONCE(sqe->user_data);
	req->file = NULL;
	req->fixed_rsrc_refs = NULL;
	req->task = current;

	if (unlikely(opcode >= IORING_OP_LAST)) {
		req->opcode = 0;
		return -EINVAL;
	}
	if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) {
		/* enforce forwards compatibility on users */
		if (sqe_flags & ~SQE_VALID_FLAGS)
			return -EINVAL;
		if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
		    !io_op_defs[opcode].buffer_select)
			return -EOPNOTSUPP;
		if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS)
			ctx->drain_disabled = true;
		if (sqe_flags & IOSQE_IO_DRAIN) {
			if (ctx->drain_disabled)
				return -EOPNOTSUPP;
			io_init_req_drain(req);
		}
	}
	if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) {
		if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags))
			return -EACCES;
		/* knock it to the slow queue path, will be drained there */
		if (ctx->drain_active)
			req->flags |= REQ_F_FORCE_ASYNC;
		/* if there is no link, we're at "next" request and need to drain */
		if (unlikely(ctx->drain_next) && !ctx->submit_state.link.head) {
			ctx->drain_next = false;
			ctx->drain_active = true;
			req->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC;
		}
	}

	if (io_op_defs[opcode].needs_file) {
		struct io_submit_state *state = &ctx->submit_state;

		/*
		 * Plug now if we have more than 2 IO left after this, and the
		 * target is potentially a read/write to block based storage.
		 */
		if (state->need_plug && io_op_defs[opcode].plug) {
			state->plug_started = true;
			state->need_plug = false;
			blk_start_plug_nr_ios(&state->plug, state->submit_nr);
		}

		req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd),
					(sqe_flags & IOSQE_FIXED_FILE));
		if (unlikely(!req->file))
			return -EBADF;
	}

	personality = READ_ONCE(sqe->personality);
	if (personality) {
		int ret;

		req->creds = xa_load(&ctx->personalities, personality);
		if (!req->creds)
			return -EINVAL;
		get_cred(req->creds);
		ret = security_uring_override_creds(req->creds);
		if (ret) {
			put_cred(req->creds);
			return ret;
		}
		req->flags |= REQ_F_CREDS;
	}

	return io_req_prep(req, sqe);
}

static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
			 const struct io_uring_sqe *sqe)
	__must_hold(&ctx->uring_lock)
{
	struct io_submit_link *link = &ctx->submit_state.link;
	int ret;

	ret = io_init_req(ctx, req, sqe);
	if (unlikely(ret)) {
		trace_io_uring_req_failed(sqe, ret);

		/* fail even hard links since we don't submit */
		if (link->head) {
			/*
			 * we can judge a link req is failed or cancelled by if
			 * REQ_F_FAIL is set, but the head is an exception since
			 * it may be set REQ_F_FAIL because of other req's failure
			 * so let's leverage req->result to distinguish if a head
			 * is set REQ_F_FAIL because of its failure or other req's
			 * failure so that we can set the correct ret code for it.
			 * init result here to avoid affecting the normal path.
			 */
			if (!(link->head->flags & REQ_F_FAIL))
				req_fail_link_node(link->head, -ECANCELED);
		} else if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) {
			/*
			 * the current req is a normal req, we should return
			 * error and thus break the submittion loop.
			 */
			io_req_complete_failed(req, ret);
			return ret;
		}
		req_fail_link_node(req, ret);
	}

	/* don't need @sqe from now on */
	trace_io_uring_submit_sqe(ctx, req, req->opcode, req->user_data,
				  req->flags, true,
				  ctx->flags & IORING_SETUP_SQPOLL);

	/*
	 * If we already have a head request, queue this one for async
	 * submittal once the head completes. If we don't have a head but
	 * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be
	 * submitted sync once the chain is complete. If none of those
	 * conditions are true (normal request), then just queue it.
	 */
	if (link->head) {
		struct io_kiocb *head = link->head;

		if (!(req->flags & REQ_F_FAIL)) {
			ret = io_req_prep_async(req);
			if (unlikely(ret)) {
				req_fail_link_node(req, ret);
				if (!(head->flags & REQ_F_FAIL))
					req_fail_link_node(head, -ECANCELED);
			}
		}
		trace_io_uring_link(ctx, req, head);
		link->last->link = req;
		link->last = req;

		if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK))
			return 0;
		/* last request of a link, enqueue the link */
		link->head = NULL;
		req = head;
	} else if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
		link->head = req;
		link->last = req;
		return 0;
	}

	io_queue_sqe(req);
	return 0;
}

/*
 * Batched submission is done, ensure local IO is flushed out.
 */
static void io_submit_state_end(struct io_ring_ctx *ctx)
{
	struct io_submit_state *state = &ctx->submit_state;

	if (state->link.head)
		io_queue_sqe(state->link.head);
	/* flush only after queuing links as they can generate completions */
	io_submit_flush_completions(ctx);
	if (state->plug_started)
		blk_finish_plug(&state->plug);
}

/*
 * Start submission side cache.
 */
static void io_submit_state_start(struct io_submit_state *state,
				  unsigned int max_ios)
{
	state->plug_started = false;
	state->need_plug = max_ios > 2;
	state->submit_nr = max_ios;
	/* set only head, no need to init link_last in advance */
	state->link.head = NULL;
}

static void io_commit_sqring(struct io_ring_ctx *ctx)
{
	struct io_rings *rings = ctx->rings;

	/*
	 * 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(&rings->sq.head, ctx->cached_sq_head);
}

/*
 * Fetch an sqe, if one is available. Note this returns a pointer 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 const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx)
{
	unsigned head, mask = ctx->sq_entries - 1;
	unsigned sq_idx = ctx->cached_sq_head++ & mask;

	/*
	 * 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 = READ_ONCE(ctx->sq_array[sq_idx]);
	if (likely(head < ctx->sq_entries))
		return &ctx->sq_sqes[head];

	/* drop invalid entries */
	ctx->cq_extra--;
	WRITE_ONCE(ctx->rings->sq_dropped,
		   READ_ONCE(ctx->rings->sq_dropped) + 1);
	return NULL;
}

static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
	__must_hold(&ctx->uring_lock)
{
	unsigned int entries = io_sqring_entries(ctx);
	int submitted = 0;

	if (unlikely(!entries))
		return 0;
	/* make sure SQ entry isn't read before tail */
	nr = min3(nr, ctx->sq_entries, entries);
	io_get_task_refs(nr);

	io_submit_state_start(&ctx->submit_state, nr);
	do {
		const struct io_uring_sqe *sqe;
		struct io_kiocb *req;

		if (unlikely(!io_alloc_req_refill(ctx))) {
			if (!submitted)
				submitted = -EAGAIN;
			break;
		}
		req = io_alloc_req(ctx);
		sqe = io_get_sqe(ctx);
		if (unlikely(!sqe)) {
			wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
			break;
		}
		/* will complete beyond this point, count as submitted */
		submitted++;
		if (io_submit_sqe(ctx, req, sqe))
			break;
	} while (submitted < nr);

	if (unlikely(submitted != nr)) {
		int ref_used = (submitted == -EAGAIN) ? 0 : submitted;
		int unused = nr - ref_used;

		current->io_uring->cached_refs += unused;
	}

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

	return submitted;
}

static inline bool io_sqd_events_pending(struct io_sq_data *sqd)
{
	return READ_ONCE(sqd->state);
}

static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx)
{
	/* Tell userspace we may need a wakeup call */
	spin_lock(&ctx->completion_lock);
	WRITE_ONCE(ctx->rings->sq_flags,
		   ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP);
	spin_unlock(&ctx->completion_lock);
}

static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx)
{
	spin_lock(&ctx->completion_lock);
	WRITE_ONCE(ctx->rings->sq_flags,
		   ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP);
	spin_unlock(&ctx->completion_lock);
}

static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
{
	unsigned int to_submit;
	int ret = 0;

	to_submit = io_sqring_entries(ctx);
	/* if we're handling multiple rings, cap submit size for fairness */
	if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE)
		to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE;

	if (!wq_list_empty(&ctx->iopoll_list) || to_submit) {
		const struct cred *creds = NULL;

		if (ctx->sq_creds != current_cred())
			creds = override_creds(ctx->sq_creds);

		mutex_lock(&ctx->uring_lock);
		if (!wq_list_empty(&ctx->iopoll_list))
			io_do_iopoll(ctx, true);

		/*
		 * Don't submit if refs are dying, good for io_uring_register(),
		 * but also it is relied upon by io_ring_exit_work()
		 */
		if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) &&
		    !(ctx->flags & IORING_SETUP_R_DISABLED))
			ret = io_submit_sqes(ctx, to_submit);
		mutex_unlock(&ctx->uring_lock);

		if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
			wake_up(&ctx->sqo_sq_wait);
		if (creds)
			revert_creds(creds);
	}

	return ret;
}

static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd)
{
	struct io_ring_ctx *ctx;
	unsigned sq_thread_idle = 0;

	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
		sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle);
	sqd->sq_thread_idle = sq_thread_idle;
}

static bool io_sqd_handle_event(struct io_sq_data *sqd)
{
	bool did_sig = false;
	struct ksignal ksig;

	if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) ||
	    signal_pending(current)) {
		mutex_unlock(&sqd->lock);
		if (signal_pending(current))
			did_sig = get_signal(&ksig);
		cond_resched();
		mutex_lock(&sqd->lock);
	}
	return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
}

static int io_sq_thread(void *data)
{
	struct io_sq_data *sqd = data;
	struct io_ring_ctx *ctx;
	unsigned long timeout = 0;
	char buf[TASK_COMM_LEN];
	DEFINE_WAIT(wait);

	snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
	set_task_comm(current, buf);

	if (sqd->sq_cpu != -1)
		set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
	else
		set_cpus_allowed_ptr(current, cpu_online_mask);
	current->flags |= PF_NO_SETAFFINITY;

	audit_alloc_kernel(current);

	mutex_lock(&sqd->lock);
	while (1) {
		bool cap_entries, sqt_spin = false;

		if (io_sqd_events_pending(sqd) || signal_pending(current)) {
			if (io_sqd_handle_event(sqd))
				break;
			timeout = jiffies + sqd->sq_thread_idle;
		}

		cap_entries = !list_is_singular(&sqd->ctx_list);
		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
			int ret = __io_sq_thread(ctx, cap_entries);

			if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
				sqt_spin = true;
		}
		if (io_run_task_work())
			sqt_spin = true;

		if (sqt_spin || !time_after(jiffies, timeout)) {
			cond_resched();
			if (sqt_spin)
				timeout = jiffies + sqd->sq_thread_idle;
			continue;
		}

		prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
		if (!io_sqd_events_pending(sqd) && !current->task_works) {
			bool needs_sched = true;

			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
				io_ring_set_wakeup_flag(ctx);

				if ((ctx->flags & IORING_SETUP_IOPOLL) &&
				    !wq_list_empty(&ctx->iopoll_list)) {
					needs_sched = false;
					break;
				}
				if (io_sqring_entries(ctx)) {
					needs_sched = false;
					break;
				}
			}

			if (needs_sched) {
				mutex_unlock(&sqd->lock);
				schedule();
				mutex_lock(&sqd->lock);
			}
			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
				io_ring_clear_wakeup_flag(ctx);
		}

		finish_wait(&sqd->wait, &wait);
		timeout = jiffies + sqd->sq_thread_idle;
	}

	io_uring_cancel_generic(true, sqd);
	sqd->thread = NULL;
	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
		io_ring_set_wakeup_flag(ctx);
	io_run_task_work();
	mutex_unlock(&sqd->lock);

	audit_free(current);

	complete(&sqd->exited);
	do_exit(0);
}

struct io_wait_queue {
	struct wait_queue_entry wq;
	struct io_ring_ctx *ctx;
	unsigned cq_tail;
	unsigned nr_timeouts;
};

static inline bool io_should_wake(struct io_wait_queue *iowq)
{
	struct io_ring_ctx *ctx = iowq->ctx;
	int dist = ctx->cached_cq_tail - (int) iowq->cq_tail;

	/*
	 * Wake up if we have enough events, or if a timeout occurred since we
	 * started waiting. For timeouts, we always want to return to userspace,
	 * regardless of event count.
	 */
	return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
}

static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
			    int wake_flags, void *key)
{
	struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue,
							wq);

	/*
	 * Cannot safely flush overflowed CQEs from here, ensure we wake up
	 * the task, and the next invocation will do it.
	 */
	if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->check_cq_overflow))
		return autoremove_wake_function(curr, mode, wake_flags, key);
	return -1;
}

static int io_run_task_work_sig(void)
{
	if (io_run_task_work())
		return 1;
	if (!signal_pending(current))
		return 0;
	if (test_thread_flag(TIF_NOTIFY_SIGNAL))
		return -ERESTARTSYS;
	return -EINTR;
}

/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
					  struct io_wait_queue *iowq,
					  signed long *timeout)
{
	int ret;

	/* make sure we run task_work before checking for signals */
	ret = io_run_task_work_sig();
	if (ret || io_should_wake(iowq))
		return ret;
	/* let the caller flush overflows, retry */
	if (test_bit(0, &ctx->check_cq_overflow))
		return 1;

	*timeout = schedule_timeout(*timeout);
	return !*timeout ? -ETIME : 1;
}

/*
 * 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 __kernel_timespec __user *uts)
{
	struct io_wait_queue iowq;
	struct io_rings *rings = ctx->rings;
	signed long timeout = MAX_SCHEDULE_TIMEOUT;
	int ret;

	do {
		io_cqring_overflow_flush(ctx);
		if (io_cqring_events(ctx) >= min_events)
			return 0;
		if (!io_run_task_work())
			break;
	} while (1);

	if (uts) {
		struct timespec64 ts;

		if (get_timespec64(&ts, uts))
			return -EFAULT;
		timeout = timespec64_to_jiffies(&ts);
	}

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

		if (ret)
			return ret;
	}

	init_waitqueue_func_entry(&iowq.wq, io_wake_function);
	iowq.wq.private = current;
	INIT_LIST_HEAD(&iowq.wq.entry);
	iowq.ctx = ctx;
	iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
	iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events;

	trace_io_uring_cqring_wait(ctx, min_events);
	do {
		/* if we can't even flush overflow, don't wait for more */
		if (!io_cqring_overflow_flush(ctx)) {
			ret = -EBUSY;
			break;
		}
		prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
						TASK_INTERRUPTIBLE);
		ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
		finish_wait(&ctx->cq_wait, &iowq.wq);
		cond_resched();
	} while (ret > 0);

	restore_saved_sigmask_unless(ret == -EINTR);

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

static void io_free_page_table(void **table, size_t size)
{
	unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE);

	for (i = 0; i < nr_tables; i++)
		kfree(table[i]);
	kfree(table);
}

static __cold void **io_alloc_page_table(size_t size)
{
	unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE);
	size_t init_size = size;
	void **table;

	table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL_ACCOUNT);
	if (!table)
		return NULL;

	for (i = 0; i < nr_tables; i++) {
		unsigned int this_size = min_t(size_t, size, PAGE_SIZE);

		table[i] = kzalloc(this_size, GFP_KERNEL_ACCOUNT);
		if (!table[i]) {
			io_free_page_table(table, init_size);
			return NULL;
		}
		size -= this_size;
	}
	return table;
}

static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node)
{
	percpu_ref_exit(&ref_node->refs);
	kfree(ref_node);
}

static __cold void io_rsrc_node_ref_zero(struct percpu_ref *ref)
{
	struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs);
	struct io_ring_ctx *ctx = node->rsrc_data->ctx;
	unsigned long flags;
	bool first_add = false;

	spin_lock_irqsave(&ctx->rsrc_ref_lock, flags);
	node->done = true;

	while (!list_empty(&ctx->rsrc_ref_list)) {
		node = list_first_entry(&ctx->rsrc_ref_list,
					    struct io_rsrc_node, node);
		/* recycle ref nodes in order */
		if (!node->done)
			break;
		list_del(&node->node);
		first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist);
	}
	spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags);

	if (first_add)
		mod_delayed_work(system_wq, &ctx->rsrc_put_work, HZ);
}

static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx)
{
	struct io_rsrc_node *ref_node;

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

	if (percpu_ref_init(&ref_node->refs, io_rsrc_node_ref_zero,
			    0, GFP_KERNEL)) {
		kfree(ref_node);
		return NULL;
	}
	INIT_LIST_HEAD(&ref_node->node);
	INIT_LIST_HEAD(&ref_node->rsrc_list);
	ref_node->done = false;
	return ref_node;
}

static void io_rsrc_node_switch(struct io_ring_ctx *ctx,
				struct io_rsrc_data *data_to_kill)
	__must_hold(&ctx->uring_lock)
{
	WARN_ON_ONCE(!ctx->rsrc_backup_node);
	WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node);

	io_rsrc_refs_drop(ctx);

	if (data_to_kill) {
		struct io_rsrc_node *rsrc_node = ctx->rsrc_node;

		rsrc_node->rsrc_data = data_to_kill;
		spin_lock_irq(&ctx->rsrc_ref_lock);
		list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list);
		spin_unlock_irq(&ctx->rsrc_ref_lock);

		atomic_inc(&data_to_kill->refs);
		percpu_ref_kill(&rsrc_node->refs);
		ctx->rsrc_node = NULL;
	}

	if (!ctx->rsrc_node) {
		ctx->rsrc_node = ctx->rsrc_backup_node;
		ctx->rsrc_backup_node = NULL;
	}
}

static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx)
{
	if (ctx->rsrc_backup_node)
		return 0;
	ctx->rsrc_backup_node = io_rsrc_node_alloc(ctx);
	return ctx->rsrc_backup_node ? 0 : -ENOMEM;
}

static __cold int io_rsrc_ref_quiesce(struct io_rsrc_data *data,
				      struct io_ring_ctx *ctx)
{
	int ret;

	/* As we may drop ->uring_lock, other task may have started quiesce */
	if (data->quiesce)
		return -ENXIO;

	data->quiesce = true;
	do {
		ret = io_rsrc_node_switch_start(ctx);
		if (ret)
			break;
		io_rsrc_node_switch(ctx, data);

		/* kill initial ref, already quiesced if zero */
		if (atomic_dec_and_test(&data->refs))
			break;
		mutex_unlock(&ctx->uring_lock);
		flush_delayed_work(&ctx->rsrc_put_work);
		ret = wait_for_completion_interruptible(&data->done);
		if (!ret) {
			mutex_lock(&ctx->uring_lock);
			break;
		}

		atomic_inc(&data->refs);
		/* wait for all works potentially completing data->done */
		flush_delayed_work(&ctx->rsrc_put_work);
		reinit_completion(&data->done);

		ret = io_run_task_work_sig();
		mutex_lock(&ctx->uring_lock);
	} while (ret >= 0);
	data->quiesce = false;

	return ret;
}

static u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx)
{
	unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK;
	unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT;

	return &data->tags[table_idx][off];
}

static void io_rsrc_data_free(struct io_rsrc_data *data)
{
	size_t size = data->nr * sizeof(data->tags[0][0]);

	if (data->tags)
		io_free_page_table((void **)data->tags, size);
	kfree(data);
}

static __cold int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put,
				     u64 __user *utags, unsigned nr,
				     struct io_rsrc_data **pdata)
{
	struct io_rsrc_data *data;
	int ret = -ENOMEM;
	unsigned i;

	data = kzalloc(sizeof(*data), GFP_KERNEL);
	if (!data)
		return -ENOMEM;
	data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0]));
	if (!data->tags) {
		kfree(data);
		return -ENOMEM;
	}

	data->nr = nr;
	data->ctx = ctx;
	data->do_put = do_put;
	if (utags) {
		ret = -EFAULT;
		for (i = 0; i < nr; i++) {
			u64 *tag_slot = io_get_tag_slot(data, i);

			if (copy_from_user(tag_slot, &utags[i],
					   sizeof(*tag_slot)))
				goto fail;
		}
	}

	atomic_set(&data->refs, 1);
	init_completion(&data->done);
	*pdata = data;
	return 0;
fail:
	io_rsrc_data_free(data);
	return ret;
}

static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files)
{
	table->files = kvcalloc(nr_files, sizeof(table->files[0]),
				GFP_KERNEL_ACCOUNT);
	return !!table->files;
}

static void io_free_file_tables(struct io_file_table *table)
{
	kvfree(table->files);
	table->files = NULL;
}

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++) {
		struct file *file;

		file = io_file_from_index(ctx, i);
		if (file)
			fput(file);
	}
#endif
	io_free_file_tables(&ctx->file_table);
	io_rsrc_data_free(ctx->file_data);
	ctx->file_data = NULL;
	ctx->nr_user_files = 0;
}

static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
	int ret;

	if (!ctx->file_data)
		return -ENXIO;
	ret = io_rsrc_ref_quiesce(ctx->file_data, ctx);
	if (!ret)
		__io_sqe_files_unregister(ctx);
	return ret;
}

static void io_sq_thread_unpark(struct io_sq_data *sqd)
	__releases(&sqd->lock)
{
	WARN_ON_ONCE(sqd->thread == current);

	/*
	 * Do the dance but not conditional clear_bit() because it'd race with
	 * other threads incrementing park_pending and setting the bit.
	 */
	clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
	if (atomic_dec_return(&sqd->park_pending))
		set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
	mutex_unlock(&sqd->lock);
}

static void io_sq_thread_park(struct io_sq_data *sqd)
	__acquires(&sqd->lock)
{
	WARN_ON_ONCE(sqd->thread == current);

	atomic_inc(&sqd->park_pending);
	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
	mutex_lock(&sqd->lock);
	if (sqd->thread)
		wake_up_process(sqd->thread);
}

static void io_sq_thread_stop(struct io_sq_data *sqd)
{
	WARN_ON_ONCE(sqd->thread == current);
	WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state));

	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
	mutex_lock(&sqd->lock);
	if (sqd->thread)
		wake_up_process(sqd->thread);
	mutex_unlock(&sqd->lock);
	wait_for_completion(&sqd->exited);
}

static void io_put_sq_data(struct io_sq_data *sqd)
{
	if (refcount_dec_and_test(&sqd->refs)) {
		WARN_ON_ONCE(atomic_read(&sqd->park_pending));

		io_sq_thread_stop(sqd);
		kfree(sqd);
	}
}

static void io_sq_thread_finish(struct io_ring_ctx *ctx)
{
	struct io_sq_data *sqd = ctx->sq_data;

	if (sqd) {
		io_sq_thread_park(sqd);
		list_del_init(&ctx->sqd_list);
		io_sqd_update_thread_idle(sqd);
		io_sq_thread_unpark(sqd);

		io_put_sq_data(sqd);
		ctx->sq_data = NULL;
	}
}

static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p)
{
	struct io_ring_ctx *ctx_attach;
	struct io_sq_data *sqd;
	struct fd f;

	f = fdget(p->wq_fd);
	if (!f.file)
		return ERR_PTR(-ENXIO);
	if (f.file->f_op != &io_uring_fops) {
		fdput(f);
		return ERR_PTR(-EINVAL);
	}

	ctx_attach = f.file->private_data;
	sqd = ctx_attach->sq_data;
	if (!sqd) {
		fdput(f);
		return ERR_PTR(-EINVAL);
	}
	if (sqd->task_tgid != current->tgid) {
		fdput(f);
		return ERR_PTR(-EPERM);
	}

	refcount_inc(&sqd->refs);
	fdput(f);
	return sqd;
}

static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
					 bool *attached)
{
	struct io_sq_data *sqd;

	*attached = false;
	if (p->flags & IORING_SETUP_ATTACH_WQ) {
		sqd = io_attach_sq_data(p);
		if (!IS_ERR(sqd)) {
			*attached = true;
			return sqd;
		}
		/* fall through for EPERM case, setup new sqd/task */
		if (PTR_ERR(sqd) != -EPERM)
			return sqd;
	}

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

	atomic_set(&sqd->park_pending, 0);
	refcount_set(&sqd->refs, 1);
	INIT_LIST_HEAD(&sqd->ctx_list);
	mutex_init(&sqd->lock);
	init_waitqueue_head(&sqd->wait);
	init_completion(&sqd->exited);
	return sqd;
}

#if defined(CONFIG_UNIX)
/*
 * 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, nr_files;

	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;

	nr_files = 0;
	fpl->user = get_uid(current_user());
	for (i = 0; i < nr; i++) {
		struct file *file = io_file_from_index(ctx, i + offset);

		if (!file)
			continue;
		fpl->fp[nr_files] = get_file(file);
		unix_inflight(fpl->user, fpl->fp[nr_files]);
		nr_files++;
	}

	if (nr_files) {
		fpl->max = SCM_MAX_FD;
		fpl->count = nr_files;
		UNIXCB(skb).fp = fpl;
		skb->destructor = unix_destruct_scm;
		refcount_add(skb->truesize, &sk->sk_wmem_alloc);
		skb_queue_head(&sk->sk_receive_queue, skb);

		for (i = 0; i < nr_files; i++)
			fput(fpl->fp[i]);
	} else {
		kfree_skb(skb);
		kfree(fpl);
	}

	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) {
		struct file *file = io_file_from_index(ctx, total);

		if (file)
			fput(file);
		total++;
	}

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

static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
{
	struct file *file = prsrc->file;
#if defined(CONFIG_UNIX)
	struct sock *sock = ctx->ring_sock->sk;
	struct sk_buff_head list, *head = &sock->sk_receive_queue;
	struct sk_buff *skb;
	int i;

	__skb_queue_head_init(&list);

	/*
	 * Find the skb that holds this file in its SCM_RIGHTS. When found,
	 * remove this entry and rearrange the file array.
	 */
	skb = skb_dequeue(head);
	while (skb) {
		struct scm_fp_list *fp;

		fp = UNIXCB(skb).fp;
		for (i = 0; i < fp->count; i++) {
			int left;

			if (fp->fp[i] != file)
				continue;

			unix_notinflight(fp->user, fp->fp[i]);
			left = fp->count - 1 - i;
			if (left) {
				memmove(&fp->fp[i], &fp->fp[i + 1],
						left * sizeof(struct file *));
			}
			fp->count--;
			if (!fp->count) {
				kfree_skb(skb);
				skb = NULL;
			} else {
				__skb_queue_tail(&list, skb);
			}
			fput(file);
			file = NULL;
			break;
		}

		if (!file)
			break;

		__skb_queue_tail(&list, skb);

		skb = skb_dequeue(head);
	}

	if (skb_peek(&list)) {
		spin_lock_irq(&head->lock);
		while ((skb = __skb_dequeue(&list)) != NULL)
			__skb_queue_tail(head, skb);
		spin_unlock_irq(&head->lock);
	}
#else
	fput(file);
#endif
}

static void __io_rsrc_put_work(struct io_rsrc_node *ref_node)
{
	struct io_rsrc_data *rsrc_data = ref_node->rsrc_data;
	struct io_ring_ctx *ctx = rsrc_data->ctx;
	struct io_rsrc_put *prsrc, *tmp;

	list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) {
		list_del(&prsrc->list);

		if (prsrc->tag) {
			bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL;

			io_ring_submit_lock(ctx, lock_ring);
			spin_lock(&ctx->completion_lock);
			io_fill_cqe_aux(ctx, prsrc->tag, 0, 0);
			io_commit_cqring(ctx);
			spin_unlock(&ctx->completion_lock);
			io_cqring_ev_posted(ctx);
			io_ring_submit_unlock(ctx, lock_ring);
		}

		rsrc_data->do_put(ctx, prsrc);
		kfree(prsrc);
	}

	io_rsrc_node_destroy(ref_node);
	if (atomic_dec_and_test(&rsrc_data->refs))
		complete(&rsrc_data->done);
}

static void io_rsrc_put_work(struct work_struct *work)
{
	struct io_ring_ctx *ctx;
	struct llist_node *node;

	ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work);
	node = llist_del_all(&ctx->rsrc_put_llist);

	while (node) {
		struct io_rsrc_node *ref_node;
		struct llist_node *next = node->next;

		ref_node = llist_entry(node, struct io_rsrc_node, llist);
		__io_rsrc_put_work(ref_node);
		node = next;
	}
}

static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
				 unsigned nr_args, u64 __user *tags)
{
	__s32 __user *fds = (__s32 __user *) arg;
	struct file *file;
	int fd, ret;
	unsigned i;

	if (ctx->file_data)
		return -EBUSY;
	if (!nr_args)
		return -EINVAL;
	if (nr_args > IORING_MAX_FIXED_FILES)
		return -EMFILE;
	if (nr_args > rlimit(RLIMIT_NOFILE))
		return -EMFILE;
	ret = io_rsrc_node_switch_start(ctx);
	if (ret)
		return ret;
	ret = io_rsrc_data_alloc(ctx, io_rsrc_file_put, tags, nr_args,
				 &ctx->file_data);
	if (ret)
		return ret;

	ret = -ENOMEM;
	if (!io_alloc_file_tables(&ctx->file_table, nr_args))
		goto out_free;

	for (i = 0; i < nr_args; i++, ctx->nr_user_files++) {
		if (copy_from_user(&fd, &fds[i], sizeof(fd))) {
			ret = -EFAULT;
			goto out_fput;
		}
		/* allow sparse sets */
		if (fd == -1) {
			ret = -EINVAL;
			if (unlikely(*io_get_tag_slot(ctx->file_data, i)))
				goto out_fput;
			continue;
		}

		file = fget(fd);
		ret = -EBADF;
		if (unlikely(!file))
			goto out_fput;

		/*
		 * 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 (file->f_op == &io_uring_fops) {
			fput(file);
			goto out_fput;
		}
		io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file);
	}

	ret = io_sqe_files_scm(ctx);
	if (ret) {
		__io_sqe_files_unregister(ctx);
		return ret;
	}

	io_rsrc_node_switch(ctx, NULL);
	return ret;
out_fput:
	for (i = 0; i < ctx->nr_user_files; i++) {
		file = io_file_from_index(ctx, i);
		if (file)
			fput(file);
	}
	io_free_file_tables(&ctx->file_table);
	ctx->nr_user_files = 0;
out_free:
	io_rsrc_data_free(ctx->file_data);
	ctx->file_data = NULL;
	return ret;
}

static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
				int index)
{
#if defined(CONFIG_UNIX)
	struct sock *sock = ctx->ring_sock->sk;
	struct sk_buff_head *head = &sock->sk_receive_queue;
	struct sk_buff *skb;

	/*
	 * See if we can merge this file into an existing skb SCM_RIGHTS
	 * file set. If there's no room, fall back to allocating a new skb
	 * and filling it in.
	 */
	spin_lock_irq(&head->lock);
	skb = skb_peek(head);
	if (skb) {
		struct scm_fp_list *fpl = UNIXCB(skb).fp;

		if (fpl->count < SCM_MAX_FD) {
			__skb_unlink(skb, head);
			spin_unlock_irq(&head->lock);
			fpl->fp[fpl->count] = get_file(file);
			unix_inflight(fpl->user, fpl->fp[fpl->count]);
			fpl->count++;
			spin_lock_irq(&head->lock);
			__skb_queue_head(head, skb);
		} else {
			skb = NULL;
		}
	}
	spin_unlock_irq(&head->lock);

	if (skb) {
		fput(file);
		return 0;
	}

	return __io_sqe_files_scm(ctx, 1, index);
#else
	return 0;
#endif
}

static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
				 struct io_rsrc_node *node, void *rsrc)
{
	struct io_rsrc_put *prsrc;

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

	prsrc->tag = *io_get_tag_slot(data, idx);
	prsrc->rsrc = rsrc;
	list_add(&prsrc->list, &node->rsrc_list);
	return 0;
}

static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
				 unsigned int issue_flags, u32 slot_index)
{
	struct io_ring_ctx *ctx = req->ctx;
	bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
	bool needs_switch = false;
	struct io_fixed_file *file_slot;
	int ret = -EBADF;

	io_ring_submit_lock(ctx, needs_lock);
	if (file->f_op == &io_uring_fops)
		goto err;
	ret = -ENXIO;
	if (!ctx->file_data)
		goto err;
	ret = -EINVAL;
	if (slot_index >= ctx->nr_user_files)
		goto err;

	slot_index = array_index_nospec(slot_index, ctx->nr_user_files);
	file_slot = io_fixed_file_slot(&ctx->file_table, slot_index);

	if (file_slot->file_ptr) {
		struct file *old_file;

		ret = io_rsrc_node_switch_start(ctx);
		if (ret)
			goto err;

		old_file = (struct file *)(file_slot->file_ptr & FFS_MASK);
		ret = io_queue_rsrc_removal(ctx->file_data, slot_index,
					    ctx->rsrc_node, old_file);
		if (ret)
			goto err;
		file_slot->file_ptr = 0;
		needs_switch = true;
	}

	*io_get_tag_slot(ctx->file_data, slot_index) = 0;
	io_fixed_file_set(file_slot, file);
	ret = io_sqe_file_register(ctx, file, slot_index);
	if (ret) {
		file_slot->file_ptr = 0;
		goto err;
	}

	ret = 0;
err:
	if (needs_switch)
		io_rsrc_node_switch(ctx, ctx->file_data);
	io_ring_submit_unlock(ctx, needs_lock);
	if (ret)
		fput(file);
	return ret;
}

static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
{
	unsigned int offset = req->close.file_slot - 1;
	struct io_ring_ctx *ctx = req->ctx;
	bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
	struct io_fixed_file *file_slot;
	struct file *file;
	int ret, i;

	io_ring_submit_lock(ctx, needs_lock);
	ret = -ENXIO;
	if (unlikely(!ctx->file_data))
		goto out;
	ret = -EINVAL;
	if (offset >= ctx->nr_user_files)
		goto out;
	ret = io_rsrc_node_switch_start(ctx);
	if (ret)
		goto out;

	i = array_index_nospec(offset, ctx->nr_user_files);
	file_slot = io_fixed_file_slot(&ctx->file_table, i);
	ret = -EBADF;
	if (!file_slot->file_ptr)
		goto out;

	file = (struct file *)(file_slot->file_ptr & FFS_MASK);
	ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file);
	if (ret)
		goto out;

	file_slot->file_ptr = 0;
	io_rsrc_node_switch(ctx, ctx->file_data);
	ret = 0;
out:
	io_ring_submit_unlock(ctx, needs_lock);
	return ret;
}

static int __io_sqe_files_update(struct io_ring_ctx *ctx,
				 struct io_uring_rsrc_update2 *up,
				 unsigned nr_args)
{
	u64 __user *tags = u64_to_user_ptr(up->tags);
	__s32 __user *fds = u64_to_user_ptr(up->data);
	struct io_rsrc_data *data = ctx->file_data;
	struct io_fixed_file *file_slot;
	struct file *file;
	int fd, i, err = 0;
	unsigned int done;
	bool needs_switch = false;

	if (!ctx->file_data)
		return -ENXIO;
	if (up->offset + nr_args > ctx->nr_user_files)
		return -EINVAL;

	for (done = 0; done < nr_args; done++) {
		u64 tag = 0;

		if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) ||
		    copy_from_user(&fd, &fds[done], sizeof(fd))) {
			err = -EFAULT;
			break;
		}
		if ((fd == IORING_REGISTER_FILES_SKIP || fd == -1) && tag) {
			err = -EINVAL;
			break;
		}
		if (fd == IORING_REGISTER_FILES_SKIP)
			continue;

		i = array_index_nospec(up->offset + done, ctx->nr_user_files);
		file_slot = io_fixed_file_slot(&ctx->file_table, i);

		if (file_slot->file_ptr) {
			file = (struct file *)(file_slot->file_ptr & FFS_MASK);
			err = io_queue_rsrc_removal(data, up->offset + done,
						    ctx->rsrc_node, file);
			if (err)
				break;
			file_slot->file_ptr = 0;
			needs_switch = true;
		}
		if (fd != -1) {
			file = fget(fd);
			if (!file) {
				err = -EBADF;
				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 (file->f_op == &io_uring_fops) {
				fput(file);
				err = -EBADF;
				break;
			}
			*io_get_tag_slot(data, up->offset + done) = tag;
			io_fixed_file_set(file_slot, file);
			err = io_sqe_file_register(ctx, file, i);
			if (err) {
				file_slot->file_ptr = 0;
				fput(file);
				break;
			}
		}
	}

	if (needs_switch)
		io_rsrc_node_switch(ctx, data);
	return done ? done : err;
}

static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx,
					struct task_struct *task)
{
	struct io_wq_hash *hash;
	struct io_wq_data data;
	unsigned int concurrency;

	mutex_lock(&ctx->uring_lock);
	hash = ctx->hash_map;
	if (!hash) {
		hash = kzalloc(sizeof(*hash), GFP_KERNEL);
		if (!hash) {
			mutex_unlock(&ctx->uring_lock);
			return ERR_PTR(-ENOMEM);
		}
		refcount_set(&hash->refs, 1);
		init_waitqueue_head(&hash->wait);
		ctx->hash_map = hash;
	}
	mutex_unlock(&ctx->uring_lock);

	data.hash = hash;
	data.task = task;
	data.free_work = io_wq_free_work;
	data.do_work = io_wq_submit_work;

	/* Do QD, or 4 * CPUS, whatever is smallest */
	concurrency = min(ctx->sq_entries, 4 * num_online_cpus());

	return io_wq_create(concurrency, &data);
}

static __cold int io_uring_alloc_task_context(struct task_struct *task,
					      struct io_ring_ctx *ctx)
{
	struct io_uring_task *tctx;
	int ret;

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

	ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL);
	if (unlikely(ret)) {
		kfree(tctx);
		return ret;
	}

	tctx->io_wq = io_init_wq_offload(ctx, task);
	if (IS_ERR(tctx->io_wq)) {
		ret = PTR_ERR(tctx->io_wq);
		percpu_counter_destroy(&tctx->inflight);
		kfree(tctx);
		return ret;
	}

	xa_init(&tctx->xa);
	init_waitqueue_head(&tctx->wait);
	atomic_set(&tctx->in_idle, 0);
	atomic_set(&tctx->inflight_tracked, 0);
	task->io_uring = tctx;
	spin_lock_init(&tctx->task_lock);
	INIT_WQ_LIST(&tctx->task_list);
	INIT_WQ_LIST(&tctx->prior_task_list);
	init_task_work(&tctx->task_work, tctx_task_work);
	return 0;
}

void __io_uring_free(struct task_struct *tsk)
{
	struct io_uring_task *tctx = tsk->io_uring;

	WARN_ON_ONCE(!xa_empty(&tctx->xa));
	WARN_ON_ONCE(tctx->io_wq);
	WARN_ON_ONCE(tctx->cached_refs);

	percpu_counter_destroy(&tctx->inflight);
	kfree(tctx);
	tsk->io_uring = NULL;
}

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

	/* Retain compatibility with failing for an invalid attach attempt */
	if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) ==
				IORING_SETUP_ATTACH_WQ) {
		struct fd f;

		f = fdget(p->wq_fd);
		if (!f.file)
			return -ENXIO;
		if (f.file->f_op != &io_uring_fops) {
			fdput(f);
			return -EINVAL;
		}
		fdput(f);
	}
	if (ctx->flags & IORING_SETUP_SQPOLL) {
		struct task_struct *tsk;
		struct io_sq_data *sqd;
		bool attached;

		ret = security_uring_sqpoll();
		if (ret)
			return ret;

		sqd = io_get_sq_data(p, &attached);
		if (IS_ERR(sqd)) {
			ret = PTR_ERR(sqd);
			goto err;
		}

		ctx->sq_creds = get_current_cred();
		ctx->sq_data = sqd;
		ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
		if (!ctx->sq_thread_idle)
			ctx->sq_thread_idle = HZ;

		io_sq_thread_park(sqd);
		list_add(&ctx->sqd_list, &sqd->ctx_list);
		io_sqd_update_thread_idle(sqd);
		/* don't attach to a dying SQPOLL thread, would be racy */
		ret = (attached && !sqd->thread) ? -ENXIO : 0;
		io_sq_thread_unpark(sqd);

		if (ret < 0)
			goto err;
		if (attached)
			return 0;

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

			ret = -EINVAL;
			if (cpu >= nr_cpu_ids || !cpu_online(cpu))
				goto err_sqpoll;
			sqd->sq_cpu = cpu;
		} else {
			sqd->sq_cpu = -1;
		}

		sqd->task_pid = current->pid;
		sqd->task_tgid = current->tgid;
		tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
		if (IS_ERR(tsk)) {
			ret = PTR_ERR(tsk);
			goto err_sqpoll;
		}

		sqd->thread = tsk;
		ret = io_uring_alloc_task_context(tsk, ctx);
		wake_up_new_task(tsk);
		if (ret)
			goto err;
	} else if (p->flags & IORING_SETUP_SQ_AFF) {
		/* Can't have SQ_AFF without SQPOLL */
		ret = -EINVAL;
		goto err;
	}

	return 0;
err_sqpoll:
	complete(&ctx->sq_data->exited);
err:
	io_sq_thread_finish(ctx);
	return ret;
}

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

static inline 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_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages)
{
	if (ctx->user)
		__io_unaccount_mem(ctx->user, nr_pages);

	if (ctx->mm_account)
		atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm);
}

static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages)
{
	int ret;

	if (ctx->user) {
		ret = __io_account_mem(ctx->user, nr_pages);
		if (ret)
			return ret;
	}

	if (ctx->mm_account)
		atomic64_add(nr_pages, &ctx->mm_account->pinned_vm);

	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 | __GFP_ACCOUNT;

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

static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries,
				size_t *sq_offset)
{
	struct io_rings *rings;
	size_t off, sq_array_size;

	off = struct_size(rings, cqes, cq_entries);
	if (off == SIZE_MAX)
		return SIZE_MAX;

#ifdef CONFIG_SMP
	off = ALIGN(off, SMP_CACHE_BYTES);
	if (off == 0)
		return SIZE_MAX;
#endif

	if (sq_offset)
		*sq_offset = off;

	sq_array_size = array_size(sizeof(u32), sq_entries);
	if (sq_array_size == SIZE_MAX)
		return SIZE_MAX;

	if (check_add_overflow(off, sq_array_size, &off))
		return SIZE_MAX;

	return off;
}

static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot)
{
	struct io_mapped_ubuf *imu = *slot;
	unsigned int i;

	if (imu != ctx->dummy_ubuf) {
		for (i = 0; i < imu->nr_bvecs; i++)
			unpin_user_page(imu->bvec[i].bv_page);
		if (imu->acct_pages)
			io_unaccount_mem(ctx, imu->acct_pages);
		kvfree(imu);
	}
	*slot = NULL;
}

static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
{
	io_buffer_unmap(ctx, &prsrc->buf);
	prsrc->buf = NULL;
}

static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
{
	unsigned int i;

	for (i = 0; i < ctx->nr_user_bufs; i++)
		io_buffer_unmap(ctx, &ctx->user_bufs[i]);
	kfree(ctx->user_bufs);
	io_rsrc_data_free(ctx->buf_data);
	ctx->user_bufs = NULL;
	ctx->buf_data = NULL;
	ctx->nr_user_bufs = 0;
}

static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
{
	int ret;

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

	ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx);
	if (!ret)
		__io_sqe_buffers_unregister(ctx);
	return ret;
}

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 = u64_to_user_ptr((u64)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;
}

/*
 * Not super efficient, but this is just a registration time. And we do cache
 * the last compound head, so generally we'll only do a full search if we don't
 * match that one.
 *
 * We check if the given compound head page has already been accounted, to
 * avoid double accounting it. This allows us to account the full size of the
 * page, not just the constituent pages of a huge page.
 */
static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages,
				  int nr_pages, struct page *hpage)
{
	int i, j;

	/* check current page array */
	for (i = 0; i < nr_pages; i++) {
		if (!PageCompound(pages[i]))
			continue;
		if (compound_head(pages[i]) == hpage)
			return true;
	}

	/* check previously registered pages */
	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++) {
			if (!PageCompound(imu->bvec[j].bv_page))
				continue;
			if (compound_head(imu->bvec[j].bv_page) == hpage)
				return true;
		}
	}

	return false;
}

static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages,
				 int nr_pages, struct io_mapped_ubuf *imu,
				 struct page **last_hpage)
{
	int i, ret;

	imu->acct_pages = 0;
	for (i = 0; i < nr_pages; i++) {
		if (!PageCompound(pages[i])) {
			imu->acct_pages++;
		} else {
			struct page *hpage;

			hpage = compound_head(pages[i]);
			if (hpage == *last_hpage)
				continue;
			*last_hpage = hpage;
			if (headpage_already_acct(ctx, pages, i, hpage))
				continue;
			imu->acct_pages += page_size(hpage) >> PAGE_SHIFT;
		}
	}

	if (!imu->acct_pages)
		return 0;

	ret = io_account_mem(ctx, imu->acct_pages);
	if (ret)
		imu->acct_pages = 0;
	return ret;
}

static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
				  struct io_mapped_ubuf **pimu,
				  struct page **last_hpage)
{
	struct io_mapped_ubuf *imu = NULL;
	struct vm_area_struct **vmas = NULL;
	struct page **pages = NULL;
	unsigned long off, start, end, ubuf;
	size_t size;
	int ret, pret, nr_pages, i;

	if (!iov->iov_base) {
		*pimu = ctx->dummy_ubuf;
		return 0;
	}

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

	*pimu = NULL;
	ret = -ENOMEM;

	pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL);
	if (!pages)
		goto done;

	vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *),
			      GFP_KERNEL);
	if (!vmas)
		goto done;

	imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL);
	if (!imu)
		goto done;

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

			if (vma_is_shmem(vma))
				continue;
			if (vma->vm_file &&
			    !is_file_hugepages(vma->vm_file)) {
				ret = -EOPNOTSUPP;
				break;
			}
		}
	} else {
		ret = pret < 0 ? pret : -EFAULT;
	}
	mmap_read_unlock(current->mm);
	if (ret) {
		/*
		 * if we did partial map, or found file backed vmas,
		 * release any pages we did get
		 */
		if (pret > 0)
			unpin_user_pages(pages, pret);
		goto done;
	}

	ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage);
	if (ret) {
		unpin_user_pages(pages, pret);
		goto done;
	}

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

		vec_len = min_t(size_t, size, PAGE_SIZE - off);
		imu->bvec[i].bv_page = pages[i];
		imu->bvec[i].bv_len = vec_len;
		imu->bvec[i].bv_offset = off;
		off = 0;
		size -= vec_len;
	}
	/* store original address for later verification */
	imu->ubuf = ubuf;
	imu->ubuf_end = ubuf + iov->iov_len;
	imu->nr_bvecs = nr_pages;
	*pimu = imu;
	ret = 0;
done:
	if (ret)
		kvfree(imu);
	kvfree(pages);
	kvfree(vmas);
	return ret;
}

static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args)
{
	ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL);
	return ctx->user_bufs ? 0 : -ENOMEM;
}

static int io_buffer_validate(struct iovec *iov)
{
	unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1);

	/*
	 * Don't impose further limits on the size and buffer
	 * constraints here, we'll -EINVAL later when IO is
	 * submitted if they are wrong.
	 */
	if (!iov->iov_base)
		return iov->iov_len ? -EFAULT : 0;
	if (!iov->iov_len)
		return -EFAULT;

	/* arbitrary limit, but we need something */
	if (iov->iov_len > SZ_1G)
		return -EFAULT;

	if (check_add_overflow((unsigned long)iov->iov_base, acct_len, &tmp))
		return -EOVERFLOW;

	return 0;
}

static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
				   unsigned int nr_args, u64 __user *tags)
{
	struct page *last_hpage = NULL;
	struct io_rsrc_data *data;
	int i, ret;
	struct iovec iov;

	if (ctx->user_bufs)
		return -EBUSY;
	if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS)
		return -EINVAL;
	ret = io_rsrc_node_switch_start(ctx);
	if (ret)
		return ret;
	ret = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, tags, nr_args, &data);
	if (ret)
		return ret;
	ret = io_buffers_map_alloc(ctx, nr_args);
	if (ret) {
		io_rsrc_data_free(data);
		return ret;
	}

	for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) {
		ret = io_copy_iov(ctx, &iov, arg, i);
		if (ret)
			break;
		ret = io_buffer_validate(&iov);
		if (ret)
			break;
		if (!iov.iov_base && *io_get_tag_slot(data, i)) {
			ret = -EINVAL;
			break;
		}

		ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i],
					     &last_hpage);
		if (ret)
			break;
	}

	WARN_ON_ONCE(ctx->buf_data);

	ctx->buf_data = data;
	if (ret)
		__io_sqe_buffers_unregister(ctx);
	else
		io_rsrc_node_switch(ctx, NULL);
	return ret;
}

static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
				   struct io_uring_rsrc_update2 *up,
				   unsigned int nr_args)
{
	u64 __user *tags = u64_to_user_ptr(up->tags);
	struct iovec iov, __user *iovs = u64_to_user_ptr(up->data);
	struct page *last_hpage = NULL;
	bool needs_switch = false;
	__u32 done;
	int i, err;

	if (!ctx->buf_data)
		return -ENXIO;
	if (up->offset + nr_args > ctx->nr_user_bufs)
		return -EINVAL;

	for (done = 0; done < nr_args; done++) {
		struct io_mapped_ubuf *imu;
		int offset = up->offset + done;
		u64 tag = 0;

		err = io_copy_iov(ctx, &iov, iovs, done);
		if (err)
			break;
		if (tags && copy_from_user(&tag, &tags[done], sizeof(tag))) {
			err = -EFAULT;
			break;
		}
		err = io_buffer_validate(&iov);
		if (err)
			break;
		if (!iov.iov_base && tag) {
			err = -EINVAL;
			break;
		}
		err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage);
		if (err)
			break;

		i = array_index_nospec(offset, ctx->nr_user_bufs);
		if (ctx->user_bufs[i] != ctx->dummy_ubuf) {
			err = io_queue_rsrc_removal(ctx->buf_data, offset,
						    ctx->rsrc_node, ctx->user_bufs[i]);
			if (unlikely(err)) {
				io_buffer_unmap(ctx, &imu);
				break;
			}
			ctx->user_bufs[i] = NULL;
			needs_switch = true;
		}

		ctx->user_bufs[i] = imu;
		*io_get_tag_slot(ctx->buf_data, offset) = tag;
	}

	if (needs_switch)
		io_rsrc_node_switch(ctx, ctx->buf_data);
	return done ? done : err;
}

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_destroy_buffers(struct io_ring_ctx *ctx)
{
	struct io_buffer *buf;
	unsigned long index;

	xa_for_each(&ctx->io_buffers, index, buf)
		__io_remove_buffers(ctx, buf, index, -1U);
}

static void io_req_caches_free(struct io_ring_ctx *ctx)
{
	struct io_submit_state *state = &ctx->submit_state;
	int nr = 0;

	mutex_lock(&ctx->uring_lock);
	io_flush_cached_locked_reqs(ctx, state);

	while (state->free_list.next) {
		struct io_wq_work_node *node;
		struct io_kiocb *req;

		node = wq_stack_extract(&state->free_list);
		req = container_of(node, struct io_kiocb, comp_list);
		kmem_cache_free(req_cachep, req);
		nr++;
	}
	if (nr)
		percpu_ref_put_many(&ctx->refs, nr);
	mutex_unlock(&ctx->uring_lock);
}

static void io_wait_rsrc_data(struct io_rsrc_data *data)
{
	if (data && !atomic_dec_and_test(&data->refs))
		wait_for_completion(&data->done);
}

static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
{
	io_sq_thread_finish(ctx);

	if (ctx->mm_account) {
		mmdrop(ctx->mm_account);
		ctx->mm_account = NULL;
	}

	io_rsrc_refs_drop(ctx);
	/* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */
	io_wait_rsrc_data(ctx->buf_data);
	io_wait_rsrc_data(ctx->file_data);

	mutex_lock(&ctx->uring_lock);
	if (ctx->buf_data)
		__io_sqe_buffers_unregister(ctx);
	if (ctx->file_data)
		__io_sqe_files_unregister(ctx);
	if (ctx->rings)
		__io_cqring_overflow_flush(ctx, true);
	mutex_unlock(&ctx->uring_lock);
	io_eventfd_unregister(ctx);
	io_destroy_buffers(ctx);
	if (ctx->sq_creds)
		put_cred(ctx->sq_creds);

	/* there are no registered resources left, nobody uses it */
	if (ctx->rsrc_node)
		io_rsrc_node_destroy(ctx->rsrc_node);
	if (ctx->rsrc_backup_node)
		io_rsrc_node_destroy(ctx->rsrc_backup_node);
	flush_delayed_work(&ctx->rsrc_put_work);
	flush_delayed_work(&ctx->fallback_work);

	WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
	WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist));

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

	io_mem_free(ctx->rings);
	io_mem_free(ctx->sq_sqes);

	percpu_ref_exit(&ctx->refs);
	free_uid(ctx->user);
	io_req_caches_free(ctx);
	if (ctx->hash_map)
		io_wq_put_hash(ctx->hash_map);
	kfree(ctx->cancel_hash);
	kfree(ctx->dummy_ubuf);
	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 (!io_sqring_full(ctx))
		mask |= EPOLLOUT | EPOLLWRNORM;

	/*
	 * Don't flush cqring overflow list here, just do a simple check.
	 * Otherwise there could possible be ABBA deadlock:
	 *      CPU0                    CPU1
	 *      ----                    ----
	 * lock(&ctx->uring_lock);
	 *                              lock(&ep->mtx);
	 *                              lock(&ctx->uring_lock);
	 * lock(&ep->mtx);
	 *
	 * Users may get EPOLLIN meanwhile seeing nothing in cqring, this
	 * pushs them to do the flush.
	 */
	if (io_cqring_events(ctx) || test_bit(0, &ctx->check_cq_overflow))
		mask |= EPOLLIN | EPOLLRDNORM;

	return mask;
}

static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
{
	const struct cred *creds;

	creds = xa_erase(&ctx->personalities, id);
	if (creds) {
		put_cred(creds);
		return 0;
	}

	return -EINVAL;
}

struct io_tctx_exit {
	struct callback_head		task_work;
	struct completion		completion;
	struct io_ring_ctx		*ctx;
};

static __cold void io_tctx_exit_cb(struct callback_head *cb)
{
	struct io_uring_task *tctx = current->io_uring;
	struct io_tctx_exit *work;

	work = container_of(cb, struct io_tctx_exit, task_work);
	/*
	 * When @in_idle, we're in cancellation and it's racy to remove the
	 * node. It'll be removed by the end of cancellation, just ignore it.
	 */
	if (!atomic_read(&tctx->in_idle))
		io_uring_del_tctx_node((unsigned long)work->ctx);
	complete(&work->completion);
}

static __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
{
	struct io_kiocb *req = container_of(work, struct io_kiocb, work);

	return req->ctx == data;
}

static __cold void io_ring_exit_work(struct work_struct *work)
{
	struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
	unsigned long timeout = jiffies + HZ * 60 * 5;
	unsigned long interval = HZ / 20;
	struct io_tctx_exit exit;
	struct io_tctx_node *node;
	int ret;

	/*
	 * If we're doing polled IO and end up having requests being
	 * submitted async (out-of-line), then completions can come in while
	 * we're waiting for refs to drop. We need to reap these manually,
	 * as nobody else will be looking for them.
	 */
	do {
		io_uring_try_cancel_requests(ctx, NULL, true);
		if (ctx->sq_data) {
			struct io_sq_data *sqd = ctx->sq_data;
			struct task_struct *tsk;

			io_sq_thread_park(sqd);
			tsk = sqd->thread;
			if (tsk && tsk->io_uring && tsk->io_uring->io_wq)
				io_wq_cancel_cb(tsk->io_uring->io_wq,
						io_cancel_ctx_cb, ctx, true);
			io_sq_thread_unpark(sqd);
		}

		io_req_caches_free(ctx);

		if (WARN_ON_ONCE(time_after(jiffies, timeout))) {
			/* there is little hope left, don't run it too often */
			interval = HZ * 60;
		}
	} while (!wait_for_completion_timeout(&ctx->ref_comp, interval));

	init_completion(&exit.completion);
	init_task_work(&exit.task_work, io_tctx_exit_cb);
	exit.ctx = ctx;
	/*
	 * Some may use context even when all refs and requests have been put,
	 * and they are free to do so while still holding uring_lock or
	 * completion_lock, see io_req_task_submit(). Apart from other work,
	 * this lock/unlock section also waits them to finish.
	 */
	mutex_lock(&ctx->uring_lock);
	while (!list_empty(&ctx->tctx_list)) {
		WARN_ON_ONCE(time_after(jiffies, timeout));

		node = list_first_entry(&ctx->tctx_list, struct io_tctx_node,
					ctx_node);
		/* don't spin on a single task if cancellation failed */
		list_rotate_left(&ctx->tctx_list);
		ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL);
		if (WARN_ON_ONCE(ret))
			continue;

		mutex_unlock(&ctx->uring_lock);
		wait_for_completion(&exit.completion);
		mutex_lock(&ctx->uring_lock);
	}
	mutex_unlock(&ctx->uring_lock);
	spin_lock(&ctx->completion_lock);
	spin_unlock(&ctx->completion_lock);

	io_ring_ctx_free(ctx);
}

/* Returns true if we found and killed one or more timeouts */
static __cold bool io_kill_timeouts(struct io_ring_ctx *ctx,
				    struct task_struct *tsk, bool cancel_all)
{
	struct io_kiocb *req, *tmp;
	int canceled = 0;

	spin_lock(&ctx->completion_lock);
	spin_lock_irq(&ctx->timeout_lock);
	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
		if (io_match_task(req, tsk, cancel_all)) {
			io_kill_timeout(req, -ECANCELED);
			canceled++;
		}
	}
	spin_unlock_irq(&ctx->timeout_lock);
	if (canceled != 0)
		io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	if (canceled != 0)
		io_cqring_ev_posted(ctx);
	return canceled != 0;
}

static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
{
	unsigned long index;
	struct creds *creds;

	mutex_lock(&ctx->uring_lock);
	percpu_ref_kill(&ctx->refs);
	if (ctx->rings)
		__io_cqring_overflow_flush(ctx, true);
	xa_for_each(&ctx->personalities, index, creds)
		io_unregister_personality(ctx, index);
	mutex_unlock(&ctx->uring_lock);

	io_kill_timeouts(ctx, NULL, true);
	io_poll_remove_all(ctx, NULL, true);

	/* if we failed setting up the ctx, we might not have any rings */
	io_iopoll_try_reap_events(ctx);

	INIT_WORK(&ctx->exit_work, io_ring_exit_work);
	/*
	 * Use system_unbound_wq to avoid spawning tons of event kworkers
	 * if we're exiting a ton of rings at the same time. It just adds
	 * noise and overhead, there's no discernable change in runtime
	 * over using system_wq.
	 */
	queue_work(system_unbound_wq, &ctx->exit_work);
}

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;
}

struct io_task_cancel {
	struct task_struct *task;
	bool all;
};

static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
{
	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
	struct io_task_cancel *cancel = data;

	return io_match_task_safe(req, cancel->task, cancel->all);
}

static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx,
					 struct task_struct *task,
					 bool cancel_all)
{
	struct io_defer_entry *de;
	LIST_HEAD(list);

	spin_lock(&ctx->completion_lock);
	list_for_each_entry_reverse(de, &ctx->defer_list, list) {
		if (io_match_task_safe(de->req, task, cancel_all)) {
			list_cut_position(&list, &ctx->defer_list, &de->list);
			break;
		}
	}
	spin_unlock(&ctx->completion_lock);
	if (list_empty(&list))
		return false;

	while (!list_empty(&list)) {
		de = list_first_entry(&list, struct io_defer_entry, list);
		list_del_init(&de->list);
		io_req_complete_failed(de->req, -ECANCELED);
		kfree(de);
	}
	return true;
}

static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
{
	struct io_tctx_node *node;
	enum io_wq_cancel cret;
	bool ret = false;

	mutex_lock(&ctx->uring_lock);
	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
		struct io_uring_task *tctx = node->task->io_uring;

		/*
		 * io_wq will stay alive while we hold uring_lock, because it's
		 * killed after ctx nodes, which requires to take the lock.
		 */
		if (!tctx || !tctx->io_wq)
			continue;
		cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true);
		ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
	}
	mutex_unlock(&ctx->uring_lock);

	return ret;
}

static __cold void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
						struct task_struct *task,
						bool cancel_all)
{
	struct io_task_cancel cancel = { .task = task, .all = cancel_all, };
	struct io_uring_task *tctx = task ? task->io_uring : NULL;

	while (1) {
		enum io_wq_cancel cret;
		bool ret = false;

		if (!task) {
			ret |= io_uring_try_cancel_iowq(ctx);
		} else if (tctx && tctx->io_wq) {
			/*
			 * Cancels requests of all rings, not only @ctx, but
			 * it's fine as the task is in exit/exec.
			 */
			cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb,
					       &cancel, true);
			ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
		}

		/* SQPOLL thread does its own polling */
		if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) ||
		    (ctx->sq_data && ctx->sq_data->thread == current)) {
			while (!wq_list_empty(&ctx->iopoll_list)) {
				io_iopoll_try_reap_events(ctx);
				ret = true;
			}
		}

		ret |= io_cancel_defer_files(ctx, task, cancel_all);
		ret |= io_poll_remove_all(ctx, task, cancel_all);
		ret |= io_kill_timeouts(ctx, task, cancel_all);
		if (task)
			ret |= io_run_task_work();
		if (!ret)
			break;
		cond_resched();
	}
}

static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx)
{
	struct io_uring_task *tctx = current->io_uring;
	struct io_tctx_node *node;
	int ret;

	if (unlikely(!tctx)) {
		ret = io_uring_alloc_task_context(current, ctx);
		if (unlikely(ret))
			return ret;

		tctx = current->io_uring;
		if (ctx->iowq_limits_set) {
			unsigned int limits[2] = { ctx->iowq_limits[0],
						   ctx->iowq_limits[1], };

			ret = io_wq_max_workers(tctx->io_wq, limits);
			if (ret)
				return ret;
		}
	}
	if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
		node = kmalloc(sizeof(*node), GFP_KERNEL);
		if (!node)
			return -ENOMEM;
		node->ctx = ctx;
		node->task = current;

		ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx,
					node, GFP_KERNEL));
		if (ret) {
			kfree(node);
			return ret;
		}

		mutex_lock(&ctx->uring_lock);
		list_add(&node->ctx_node, &ctx->tctx_list);
		mutex_unlock(&ctx->uring_lock);
	}
	tctx->last = ctx;
	return 0;
}

/*
 * Note that this task has used io_uring. We use it for cancelation purposes.
 */
static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx)
{
	struct io_uring_task *tctx = current->io_uring;

	if (likely(tctx && tctx->last == ctx))
		return 0;
	return __io_uring_add_tctx_node(ctx);
}

/*
 * Remove this io_uring_file -> task mapping.
 */
static __cold void io_uring_del_tctx_node(unsigned long index)
{
	struct io_uring_task *tctx = current->io_uring;
	struct io_tctx_node *node;

	if (!tctx)
		return;
	node = xa_erase(&tctx->xa, index);
	if (!node)
		return;

	WARN_ON_ONCE(current != node->task);
	WARN_ON_ONCE(list_empty(&node->ctx_node));

	mutex_lock(&node->ctx->uring_lock);
	list_del(&node->ctx_node);
	mutex_unlock(&node->ctx->uring_lock);

	if (tctx->last == node->ctx)
		tctx->last = NULL;
	kfree(node);
}

static __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
{
	struct io_wq *wq = tctx->io_wq;
	struct io_tctx_node *node;
	unsigned long index;

	xa_for_each(&tctx->xa, index, node) {
		io_uring_del_tctx_node(index);
		cond_resched();
	}
	if (wq) {
		/*
		 * Must be after io_uring_del_tctx_node() (removes nodes under
		 * uring_lock) to avoid race with io_uring_try_cancel_iowq().
		 */
		io_wq_put_and_exit(wq);
		tctx->io_wq = NULL;
	}
}

static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
{
	if (tracked)
		return atomic_read(&tctx->inflight_tracked);
	return percpu_counter_sum(&tctx->inflight);
}

/*
 * Find any io_uring ctx that this task has registered or done IO on, and cancel
 * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
 */
static __cold void io_uring_cancel_generic(bool cancel_all,
					   struct io_sq_data *sqd)
{
	struct io_uring_task *tctx = current->io_uring;
	struct io_ring_ctx *ctx;
	s64 inflight;
	DEFINE_WAIT(wait);

	WARN_ON_ONCE(sqd && sqd->thread != current);

	if (!current->io_uring)
		return;
	if (tctx->io_wq)
		io_wq_exit_start(tctx->io_wq);

	atomic_inc(&tctx->in_idle);
	do {
		io_uring_drop_tctx_refs(current);
		/* read completions before cancelations */
		inflight = tctx_inflight(tctx, !cancel_all);
		if (!inflight)
			break;

		if (!sqd) {
			struct io_tctx_node *node;
			unsigned long index;

			xa_for_each(&tctx->xa, index, node) {
				/* sqpoll task will cancel all its requests */
				if (node->ctx->sq_data)
					continue;
				io_uring_try_cancel_requests(node->ctx, current,
							     cancel_all);
			}
		} else {
			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
				io_uring_try_cancel_requests(ctx, current,
							     cancel_all);
		}

		prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE);
		io_run_task_work();
		io_uring_drop_tctx_refs(current);

		/*
		 * If we've seen completions, retry without waiting. This
		 * avoids a race where a completion comes in before we did
		 * prepare_to_wait().
		 */
		if (inflight == tctx_inflight(tctx, !cancel_all))
			schedule();
		finish_wait(&tctx->wait, &wait);
	} while (1);

	io_uring_clean_tctx(tctx);
	if (cancel_all) {
		/*
		 * We shouldn't run task_works after cancel, so just leave
		 * ->in_idle set for normal exit.
		 */
		atomic_dec(&tctx->in_idle);
		/* for exec all current's requests should be gone, kill tctx */
		__io_uring_free(current);
	}
}

void __io_uring_cancel(bool cancel_all)
{
	io_uring_cancel_generic(cancel_all, NULL);
}

static void *io_uring_validate_mmap_request(struct file *file,
					    loff_t pgoff, size_t sz)
{
	struct io_ring_ctx *ctx = file->private_data;
	loff_t offset = pgoff << PAGE_SHIFT;
	struct page *page;
	void *ptr;

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

	page = virt_to_head_page(ptr);
	if (sz > page_size(page))
		return ERR_PTR(-EINVAL);

	return ptr;
}

#ifdef CONFIG_MMU

static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
{
	size_t sz = vma->vm_end - vma->vm_start;
	unsigned long pfn;
	void *ptr;

	ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz);
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);

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

#else /* !CONFIG_MMU */

static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
{
	return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -EINVAL;
}

static unsigned int io_uring_nommu_mmap_capabilities(struct file *file)
{
	return NOMMU_MAP_DIRECT | NOMMU_MAP_READ | NOMMU_MAP_WRITE;
}

static unsigned long io_uring_nommu_get_unmapped_area(struct file *file,
	unsigned long addr, unsigned long len,
	unsigned long pgoff, unsigned long flags)
{
	void *ptr;

	ptr = io_uring_validate_mmap_request(file, pgoff, len);
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);

	return (unsigned long) ptr;
}

#endif /* !CONFIG_MMU */

static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
{
	DEFINE_WAIT(wait);

	do {
		if (!io_sqring_full(ctx))
			break;
		prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE);

		if (!io_sqring_full(ctx))
			break;
		schedule();
	} while (!signal_pending(current));

	finish_wait(&ctx->sqo_sq_wait, &wait);
	return 0;
}

static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz,
			  struct __kernel_timespec __user **ts,
			  const sigset_t __user **sig)
{
	struct io_uring_getevents_arg arg;

	/*
	 * If EXT_ARG isn't set, then we have no timespec and the argp pointer
	 * is just a pointer to the sigset_t.
	 */
	if (!(flags & IORING_ENTER_EXT_ARG)) {
		*sig = (const sigset_t __user *) argp;
		*ts = NULL;
		return 0;
	}

	/*
	 * EXT_ARG is set - ensure we agree on the size of it and copy in our
	 * timespec and sigset_t pointers if good.
	 */
	if (*argsz != sizeof(arg))
		return -EINVAL;
	if (copy_from_user(&arg, argp, sizeof(arg)))
		return -EFAULT;
	*sig = u64_to_user_ptr(arg.sigmask);
	*argsz = arg.sigmask_sz;
	*ts = u64_to_user_ptr(arg.ts);
	return 0;
}

SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
		u32, min_complete, u32, flags, const void __user *, argp,
		size_t, argsz)
{
	struct io_ring_ctx *ctx;
	int submitted = 0;
	struct fd f;
	long ret;

	io_run_task_work();

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

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

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

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

	ret = -EBADFD;
	if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED))
		goto out;

	/*
	 * 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.
	 */
	ret = 0;
	if (ctx->flags & IORING_SETUP_SQPOLL) {
		io_cqring_overflow_flush(ctx);

		if (unlikely(ctx->sq_data->thread == NULL)) {
			ret = -EOWNERDEAD;
			goto out;
		}
		if (flags & IORING_ENTER_SQ_WAKEUP)
			wake_up(&ctx->sq_data->wait);
		if (flags & IORING_ENTER_SQ_WAIT) {
			ret = io_sqpoll_wait_sq(ctx);
			if (ret)
				goto out;
		}
		submitted = to_submit;
	} else if (to_submit) {
		ret = io_uring_add_tctx_node(ctx);
		if (unlikely(ret))
			goto out;
		mutex_lock(&ctx->uring_lock);
		submitted = io_submit_sqes(ctx, to_submit);
		mutex_unlock(&ctx->uring_lock);

		if (submitted != to_submit)
			goto out;
	}
	if (flags & IORING_ENTER_GETEVENTS) {
		const sigset_t __user *sig;
		struct __kernel_timespec __user *ts;

		ret = io_get_ext_arg(flags, argp, &argsz, &ts, &sig);
		if (unlikely(ret))
			goto out;

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

		/*
		 * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user
		 * space applications don't need to do io completion events
		 * polling again, they can rely on io_sq_thread to do polling
		 * work, which can reduce cpu usage and uring_lock contention.
		 */
		if (ctx->flags & IORING_SETUP_IOPOLL &&
		    !(ctx->flags & IORING_SETUP_SQPOLL)) {
			ret = io_iopoll_check(ctx, min_complete);
		} else {
			ret = io_cqring_wait(ctx, min_complete, sig, argsz, ts);
		}
	}

out:
	percpu_ref_put(&ctx->refs);
out_fput:
	fdput(f);
	return submitted ? submitted : ret;
}

#ifdef CONFIG_PROC_FS
static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id,
		const struct cred *cred)
{
	struct user_namespace *uns = seq_user_ns(m);
	struct group_info *gi;
	kernel_cap_t cap;
	unsigned __capi;
	int g;

	seq_printf(m, "%5d\n", id);
	seq_put_decimal_ull(m, "\tUid:\t", from_kuid_munged(uns, cred->uid));
	seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->euid));
	seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->suid));
	seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->fsuid));
	seq_put_decimal_ull(m, "\n\tGid:\t", from_kgid_munged(uns, cred->gid));
	seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->egid));
	seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->sgid));
	seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->fsgid));
	seq_puts(m, "\n\tGroups:\t");
	gi = cred->group_info;
	for (g = 0; g < gi->ngroups; g++) {
		seq_put_decimal_ull(m, g ? " " : "",
					from_kgid_munged(uns, gi->gid[g]));
	}
	seq_puts(m, "\n\tCapEff:\t");
	cap = cred->cap_effective;
	CAP_FOR_EACH_U32(__capi)
		seq_put_hex_ll(m, NULL, cap.cap[CAP_LAST_U32 - __capi], 8);
	seq_putc(m, '\n');
	return 0;
}

static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
					  struct seq_file *m)
{
	struct io_sq_data *sq = NULL;
	struct io_overflow_cqe *ocqe;
	struct io_rings *r = ctx->rings;
	unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
	unsigned int sq_head = READ_ONCE(r->sq.head);
	unsigned int sq_tail = READ_ONCE(r->sq.tail);
	unsigned int cq_head = READ_ONCE(r->cq.head);
	unsigned int cq_tail = READ_ONCE(r->cq.tail);
	unsigned int sq_entries, cq_entries;
	bool has_lock;
	unsigned int i;

	/*
	 * we may get imprecise sqe and cqe info if uring is actively running
	 * since we get cached_sq_head and cached_cq_tail without uring_lock
	 * and sq_tail and cq_head are changed by userspace. But it's ok since
	 * we usually use these info when it is stuck.
	 */
	seq_printf(m, "SqMask:\t0x%x\n", sq_mask);
	seq_printf(m, "SqHead:\t%u\n", sq_head);
	seq_printf(m, "SqTail:\t%u\n", sq_tail);
	seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head);
	seq_printf(m, "CqMask:\t0x%x\n", cq_mask);
	seq_printf(m, "CqHead:\t%u\n", cq_head);
	seq_printf(m, "CqTail:\t%u\n", cq_tail);
	seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail);
	seq_printf(m, "SQEs:\t%u\n", sq_tail - ctx->cached_sq_head);
	sq_entries = min(sq_tail - sq_head, ctx->sq_entries);
	for (i = 0; i < sq_entries; i++) {
		unsigned int entry = i + sq_head;
		unsigned int sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
		struct io_uring_sqe *sqe;

		if (sq_idx > sq_mask)
			continue;
		sqe = &ctx->sq_sqes[sq_idx];
		seq_printf(m, "%5u: opcode:%d, fd:%d, flags:%x, user_data:%llu\n",
			   sq_idx, sqe->opcode, sqe->fd, sqe->flags,
			   sqe->user_data);
	}
	seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head);
	cq_entries = min(cq_tail - cq_head, ctx->cq_entries);
	for (i = 0; i < cq_entries; i++) {
		unsigned int entry = i + cq_head;
		struct io_uring_cqe *cqe = &r->cqes[entry & cq_mask];

		seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n",
			   entry & cq_mask, cqe->user_data, cqe->res,
			   cqe->flags);
	}

	/*
	 * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
	 * since fdinfo case grabs it in the opposite direction of normal use
	 * cases. If we fail to get the lock, we just don't iterate any
	 * structures that could be going away outside the io_uring mutex.
	 */
	has_lock = mutex_trylock(&ctx->uring_lock);

	if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
		sq = ctx->sq_data;
		if (!sq->thread)
			sq = NULL;
	}

	seq_printf(m, "SqThread:\t%d\n", sq ? task_pid_nr(sq->thread) : -1);
	seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1);
	seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
	for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
		struct file *f = io_file_from_index(ctx, i);

		if (f)
			seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname);
		else
			seq_printf(m, "%5u: <none>\n", i);
	}
	seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs);
	for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) {
		struct io_mapped_ubuf *buf = ctx->user_bufs[i];
		unsigned int len = buf->ubuf_end - buf->ubuf;

		seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len);
	}
	if (has_lock && !xa_empty(&ctx->personalities)) {
		unsigned long index;
		const struct cred *cred;

		seq_printf(m, "Personalities:\n");
		xa_for_each(&ctx->personalities, index, cred)
			io_uring_show_cred(m, index, cred);
	}
	if (has_lock)
		mutex_unlock(&ctx->uring_lock);

	seq_puts(m, "PollList:\n");
	spin_lock(&ctx->completion_lock);
	for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
		struct hlist_head *list = &ctx->cancel_hash[i];
		struct io_kiocb *req;

		hlist_for_each_entry(req, list, hash_node)
			seq_printf(m, "  op=%d, task_works=%d\n", req->opcode,
					req->task->task_works != NULL);
	}

	seq_puts(m, "CqOverflowList:\n");
	list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
		struct io_uring_cqe *cqe = &ocqe->cqe;

		seq_printf(m, "  user_data=%llu, res=%d, flags=%x\n",
			   cqe->user_data, cqe->res, cqe->flags);

	}

	spin_unlock(&ctx->completion_lock);
}

static __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
{
	struct io_ring_ctx *ctx = f->private_data;

	if (percpu_ref_tryget(&ctx->refs)) {
		__io_uring_show_fdinfo(ctx, m);
		percpu_ref_put(&ctx->refs);
	}
}
#endif

static const struct file_operations io_uring_fops = {
	.release	= io_uring_release,
	.mmap		= io_uring_mmap,
#ifndef CONFIG_MMU
	.get_unmapped_area = io_uring_nommu_get_unmapped_area,
	.mmap_capabilities = io_uring_nommu_mmap_capabilities,
#endif
	.poll		= io_uring_poll,
#ifdef CONFIG_PROC_FS
	.show_fdinfo	= io_uring_show_fdinfo,
#endif
};

static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
					 struct io_uring_params *p)
{
	struct io_rings *rings;
	size_t size, sq_array_offset;

	/* make sure these are sane, as we already accounted them */
	ctx->sq_entries = p->sq_entries;
	ctx->cq_entries = p->cq_entries;

	size = rings_size(p->sq_entries, p->cq_entries, &sq_array_offset);
	if (size == SIZE_MAX)
		return -EOVERFLOW;

	rings = io_mem_alloc(size);
	if (!rings)
		return -ENOMEM;

	ctx->rings = rings;
	ctx->sq_array = (u32 *)((char *)rings + sq_array_offset);
	rings->sq_ring_mask = p->sq_entries - 1;
	rings->cq_ring_mask = p->cq_entries - 1;
	rings->sq_ring_entries = p->sq_entries;
	rings->cq_ring_entries = p->cq_entries;

	size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
	if (size == SIZE_MAX) {
		io_mem_free(ctx->rings);
		ctx->rings = NULL;
		return -EOVERFLOW;
	}

	ctx->sq_sqes = io_mem_alloc(size);
	if (!ctx->sq_sqes) {
		io_mem_free(ctx->rings);
		ctx->rings = NULL;
		return -ENOMEM;
	}

	return 0;
}

static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file)
{
	int ret, fd;

	fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
	if (fd < 0)
		return fd;

	ret = io_uring_add_tctx_node(ctx);
	if (ret) {
		put_unused_fd(fd);
		return ret;
	}
	fd_install(fd, file);
	return fd;
}

/*
 * 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 struct file *io_uring_get_file(struct io_ring_ctx *ctx)
{
	struct file *file;
#if defined(CONFIG_UNIX)
	int ret;

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

	file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
					 O_RDWR | O_CLOEXEC, NULL);
#if defined(CONFIG_UNIX)
	if (IS_ERR(file)) {
		sock_release(ctx->ring_sock);
		ctx->ring_sock = NULL;
	} else {
		ctx->ring_sock->file = file;
	}
#endif
	return file;
}

static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
				  struct io_uring_params __user *params)
{
	struct io_ring_ctx *ctx;
	struct file *file;
	int ret;

	if (!entries)
		return -EINVAL;
	if (entries > IORING_MAX_ENTRIES) {
		if (!(p->flags & IORING_SETUP_CLAMP))
			return -EINVAL;
		entries = IORING_MAX_ENTRIES;
	}

	/*
	 * 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. If the application has
	 * set IORING_SETUP_CQSIZE, it will have passed in the desired number
	 * of CQ ring entries manually.
	 */
	p->sq_entries = roundup_pow_of_two(entries);
	if (p->flags & IORING_SETUP_CQSIZE) {
		/*
		 * If IORING_SETUP_CQSIZE is set, we do the same roundup
		 * to a power-of-two, if it isn't already. We do NOT impose
		 * any cq vs sq ring sizing.
		 */
		if (!p->cq_entries)
			return -EINVAL;
		if (p->cq_entries > IORING_MAX_CQ_ENTRIES) {
			if (!(p->flags & IORING_SETUP_CLAMP))
				return -EINVAL;
			p->cq_entries = IORING_MAX_CQ_ENTRIES;
		}
		p->cq_entries = roundup_pow_of_two(p->cq_entries);
		if (p->cq_entries < p->sq_entries)
			return -EINVAL;
	} else {
		p->cq_entries = 2 * p->sq_entries;
	}

	ctx = io_ring_ctx_alloc(p);
	if (!ctx)
		return -ENOMEM;
	ctx->compat = in_compat_syscall();
	if (!capable(CAP_IPC_LOCK))
		ctx->user = get_uid(current_user());

	/*
	 * This is just grabbed for accounting purposes. When a process exits,
	 * the mm is exited and dropped before the files, hence we need to hang
	 * on to this mm purely for the purposes of being able to unaccount
	 * memory (locked/pinned vm). It's not used for anything else.
	 */
	mmgrab(current->mm);
	ctx->mm_account = current->mm;

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

	ret = io_sq_offload_create(ctx, p);
	if (ret)
		goto err;
	/* always set a rsrc node */
	ret = io_rsrc_node_switch_start(ctx);
	if (ret)
		goto err;
	io_rsrc_node_switch(ctx, NULL);

	memset(&p->sq_off, 0, sizeof(p->sq_off));
	p->sq_off.head = offsetof(struct io_rings, sq.head);
	p->sq_off.tail = offsetof(struct io_rings, sq.tail);
	p->sq_off.ring_mask = offsetof(struct io_rings, sq_ring_mask);
	p->sq_off.ring_entries = offsetof(struct io_rings, sq_ring_entries);
	p->sq_off.flags = offsetof(struct io_rings, sq_flags);
	p->sq_off.dropped = offsetof(struct io_rings, sq_dropped);
	p->sq_off.array = (char *)ctx->sq_array - (char *)ctx->rings;

	memset(&p->cq_off, 0, sizeof(p->cq_off));
	p->cq_off.head = offsetof(struct io_rings, cq.head);
	p->cq_off.tail = offsetof(struct io_rings, cq.tail);
	p->cq_off.ring_mask = offsetof(struct io_rings, cq_ring_mask);
	p->cq_off.ring_entries = offsetof(struct io_rings, cq_ring_entries);
	p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
	p->cq_off.cqes = offsetof(struct io_rings, cqes);
	p->cq_off.flags = offsetof(struct io_rings, cq_flags);

	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
			IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED |
			IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS |
			IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP;

	if (copy_to_user(params, p, sizeof(*p))) {
		ret = -EFAULT;
		goto err;
	}

	file = io_uring_get_file(ctx);
	if (IS_ERR(file)) {
		ret = PTR_ERR(file);
		goto err;
	}

	/*
	 * Install ring fd as the very last thing, so we don't risk someone
	 * having closed it before we finish setup
	 */
	ret = io_uring_install_fd(ctx, file);
	if (ret < 0) {
		/* fput will clean it up */
		fput(file);
		return ret;
	}

	trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
	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;
	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 | IORING_SETUP_CQSIZE |
			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ |
			IORING_SETUP_R_DISABLED))
		return -EINVAL;

	return  io_uring_create(entries, &p, params);
}

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

static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg,
			   unsigned nr_args)
{
	struct io_uring_probe *p;
	size_t size;
	int i, ret;

	size = struct_size(p, ops, nr_args);
	if (size == SIZE_MAX)
		return -EOVERFLOW;
	p = kzalloc(size, GFP_KERNEL);
	if (!p)
		return -ENOMEM;

	ret = -EFAULT;
	if (copy_from_user(p, arg, size))
		goto out;
	ret = -EINVAL;
	if (memchr_inv(p, 0, size))
		goto out;

	p->last_op = IORING_OP_LAST - 1;
	if (nr_args > IORING_OP_LAST)
		nr_args = IORING_OP_LAST;

	for (i = 0; i < nr_args; i++) {
		p->ops[i].op = i;
		if (!io_op_defs[i].not_supported)
			p->ops[i].flags = IO_URING_OP_SUPPORTED;
	}
	p->ops_len = i;

	ret = 0;
	if (copy_to_user(arg, p, size))
		ret = -EFAULT;
out:
	kfree(p);
	return ret;
}

static int io_register_personality(struct io_ring_ctx *ctx)
{
	const struct cred *creds;
	u32 id;
	int ret;

	creds = get_current_cred();

	ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds,
			XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL);
	if (ret < 0) {
		put_cred(creds);
		return ret;
	}
	return id;
}

static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
					   void __user *arg, unsigned int nr_args)
{
	struct io_uring_restriction *res;
	size_t size;
	int i, ret;

	/* Restrictions allowed only if rings started disabled */
	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
		return -EBADFD;

	/* We allow only a single restrictions registration */
	if (ctx->restrictions.registered)
		return -EBUSY;

	if (!arg || nr_args > IORING_MAX_RESTRICTIONS)
		return -EINVAL;

	size = array_size(nr_args, sizeof(*res));
	if (size == SIZE_MAX)
		return -EOVERFLOW;

	res = memdup_user(arg, size);
	if (IS_ERR(res))
		return PTR_ERR(res);

	ret = 0;

	for (i = 0; i < nr_args; i++) {
		switch (res[i].opcode) {
		case IORING_RESTRICTION_REGISTER_OP:
			if (res[i].register_op >= IORING_REGISTER_LAST) {
				ret = -EINVAL;
				goto out;
			}

			__set_bit(res[i].register_op,
				  ctx->restrictions.register_op);
			break;
		case IORING_RESTRICTION_SQE_OP:
			if (res[i].sqe_op >= IORING_OP_LAST) {
				ret = -EINVAL;
				goto out;
			}

			__set_bit(res[i].sqe_op, ctx->restrictions.sqe_op);
			break;
		case IORING_RESTRICTION_SQE_FLAGS_ALLOWED:
			ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags;
			break;
		case IORING_RESTRICTION_SQE_FLAGS_REQUIRED:
			ctx->restrictions.sqe_flags_required = res[i].sqe_flags;
			break;
		default:
			ret = -EINVAL;
			goto out;
		}
	}

out:
	/* Reset all restrictions if an error happened */
	if (ret != 0)
		memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
	else
		ctx->restrictions.registered = true;

	kfree(res);
	return ret;
}

static int io_register_enable_rings(struct io_ring_ctx *ctx)
{
	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
		return -EBADFD;

	if (ctx->restrictions.registered)
		ctx->restricted = 1;

	ctx->flags &= ~IORING_SETUP_R_DISABLED;
	if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait))
		wake_up(&ctx->sq_data->wait);
	return 0;
}

static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
				     struct io_uring_rsrc_update2 *up,
				     unsigned nr_args)
{
	__u32 tmp;
	int err;

	if (up->resv)
		return -EINVAL;
	if (check_add_overflow(up->offset, nr_args, &tmp))
		return -EOVERFLOW;
	err = io_rsrc_node_switch_start(ctx);
	if (err)
		return err;

	switch (type) {
	case IORING_RSRC_FILE:
		return __io_sqe_files_update(ctx, up, nr_args);
	case IORING_RSRC_BUFFER:
		return __io_sqe_buffers_update(ctx, up, nr_args);
	}
	return -EINVAL;
}

static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
				    unsigned nr_args)
{
	struct io_uring_rsrc_update2 up;

	if (!nr_args)
		return -EINVAL;
	memset(&up, 0, sizeof(up));
	if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update)))
		return -EFAULT;
	return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args);
}

static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
				   unsigned size, unsigned type)
{
	struct io_uring_rsrc_update2 up;

	if (size != sizeof(up))
		return -EINVAL;
	if (copy_from_user(&up, arg, sizeof(up)))
		return -EFAULT;
	if (!up.nr || up.resv)
		return -EINVAL;
	return __io_register_rsrc_update(ctx, type, &up, up.nr);
}

static __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
			    unsigned int size, unsigned int type)
{
	struct io_uring_rsrc_register rr;

	/* keep it extendible */
	if (size != sizeof(rr))
		return -EINVAL;

	memset(&rr, 0, sizeof(rr));
	if (copy_from_user(&rr, arg, size))
		return -EFAULT;
	if (!rr.nr || rr.resv || rr.resv2)
		return -EINVAL;

	switch (type) {
	case IORING_RSRC_FILE:
		return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data),
					     rr.nr, u64_to_user_ptr(rr.tags));
	case IORING_RSRC_BUFFER:
		return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data),
					       rr.nr, u64_to_user_ptr(rr.tags));
	}
	return -EINVAL;
}

static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
				       void __user *arg, unsigned len)
{
	struct io_uring_task *tctx = current->io_uring;
	cpumask_var_t new_mask;
	int ret;

	if (!tctx || !tctx->io_wq)
		return -EINVAL;

	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
		return -ENOMEM;

	cpumask_clear(new_mask);
	if (len > cpumask_size())
		len = cpumask_size();

	if (copy_from_user(new_mask, arg, len)) {
		free_cpumask_var(new_mask);
		return -EFAULT;
	}

	ret = io_wq_cpu_affinity(tctx->io_wq, new_mask);
	free_cpumask_var(new_mask);
	return ret;
}

static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
{
	struct io_uring_task *tctx = current->io_uring;

	if (!tctx || !tctx->io_wq)
		return -EINVAL;

	return io_wq_cpu_affinity(tctx->io_wq, NULL);
}

static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
					       void __user *arg)
	__must_hold(&ctx->uring_lock)
{
	struct io_tctx_node *node;
	struct io_uring_task *tctx = NULL;
	struct io_sq_data *sqd = NULL;
	__u32 new_count[2];
	int i, ret;

	if (copy_from_user(new_count, arg, sizeof(new_count)))
		return -EFAULT;
	for (i = 0; i < ARRAY_SIZE(new_count); i++)
		if (new_count[i] > INT_MAX)
			return -EINVAL;

	if (ctx->flags & IORING_SETUP_SQPOLL) {
		sqd = ctx->sq_data;
		if (sqd) {
			/*
			 * Observe the correct sqd->lock -> ctx->uring_lock
			 * ordering. Fine to drop uring_lock here, we hold
			 * a ref to the ctx.
			 */
			refcount_inc(&sqd->refs);
			mutex_unlock(&ctx->uring_lock);
			mutex_lock(&sqd->lock);
			mutex_lock(&ctx->uring_lock);
			if (sqd->thread)
				tctx = sqd->thread->io_uring;
		}
	} else {
		tctx = current->io_uring;
	}

	BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));

	for (i = 0; i < ARRAY_SIZE(new_count); i++)
		if (new_count[i])
			ctx->iowq_limits[i] = new_count[i];
	ctx->iowq_limits_set = true;

	if (tctx && tctx->io_wq) {
		ret = io_wq_max_workers(tctx->io_wq, new_count);
		if (ret)
			goto err;
	} else {
		memset(new_count, 0, sizeof(new_count));
	}

	if (sqd) {
		mutex_unlock(&sqd->lock);
		io_put_sq_data(sqd);
	}

	if (copy_to_user(arg, new_count, sizeof(new_count)))
		return -EFAULT;

	/* that's it for SQPOLL, only the SQPOLL task creates requests */
	if (sqd)
		return 0;

	/* now propagate the restriction to all registered users */
	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
		struct io_uring_task *tctx = node->task->io_uring;

		if (WARN_ON_ONCE(!tctx->io_wq))
			continue;

		for (i = 0; i < ARRAY_SIZE(new_count); i++)
			new_count[i] = ctx->iowq_limits[i];
		/* ignore errors, it always returns zero anyway */
		(void)io_wq_max_workers(tctx->io_wq, new_count);
	}
	return 0;
err:
	if (sqd) {
		mutex_unlock(&sqd->lock);
		io_put_sq_data(sqd);
	}
	return ret;
}

static bool io_register_op_must_quiesce(int op)
{
	switch (op) {
	case IORING_REGISTER_BUFFERS:
	case IORING_UNREGISTER_BUFFERS:
	case IORING_REGISTER_FILES:
	case IORING_UNREGISTER_FILES:
	case IORING_REGISTER_FILES_UPDATE:
	case IORING_REGISTER_PROBE:
	case IORING_REGISTER_PERSONALITY:
	case IORING_UNREGISTER_PERSONALITY:
	case IORING_REGISTER_FILES2:
	case IORING_REGISTER_FILES_UPDATE2:
	case IORING_REGISTER_BUFFERS2:
	case IORING_REGISTER_BUFFERS_UPDATE:
	case IORING_REGISTER_IOWQ_AFF:
	case IORING_UNREGISTER_IOWQ_AFF:
	case IORING_REGISTER_IOWQ_MAX_WORKERS:
		return false;
	default:
		return true;
	}
}

static __cold int io_ctx_quiesce(struct io_ring_ctx *ctx)
{
	long ret;

	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);
	do {
		ret = wait_for_completion_interruptible_timeout(&ctx->ref_comp, HZ);
		if (ret) {
			ret = min(0L, ret);
			break;
		}

		ret = io_run_task_work_sig();
		io_req_caches_free(ctx);
	} while (ret >= 0);
	mutex_lock(&ctx->uring_lock);

	if (ret)
		io_refs_resurrect(&ctx->refs, &ctx->ref_comp);
	return ret;
}

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;

	if (ctx->restricted) {
		if (opcode >= IORING_REGISTER_LAST)
			return -EINVAL;
		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
		if (!test_bit(opcode, ctx->restrictions.register_op))
			return -EACCES;
	}

	if (io_register_op_must_quiesce(opcode)) {
		ret = io_ctx_quiesce(ctx);
		if (ret)
			return ret;
	}

	switch (opcode) {
	case IORING_REGISTER_BUFFERS:
		ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL);
		break;
	case IORING_UNREGISTER_BUFFERS:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_sqe_buffers_unregister(ctx);
		break;
	case IORING_REGISTER_FILES:
		ret = io_sqe_files_register(ctx, arg, nr_args, NULL);
		break;
	case IORING_UNREGISTER_FILES:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_sqe_files_unregister(ctx);
		break;
	case IORING_REGISTER_FILES_UPDATE:
		ret = io_register_files_update(ctx, arg, nr_args);
		break;
	case IORING_REGISTER_EVENTFD:
	case IORING_REGISTER_EVENTFD_ASYNC:
		ret = -EINVAL;
		if (nr_args != 1)
			break;
		ret = io_eventfd_register(ctx, arg);
		if (ret)
			break;
		if (opcode == IORING_REGISTER_EVENTFD_ASYNC)
			ctx->eventfd_async = 1;
		else
			ctx->eventfd_async = 0;
		break;
	case IORING_UNREGISTER_EVENTFD:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_eventfd_unregister(ctx);
		break;
	case IORING_REGISTER_PROBE:
		ret = -EINVAL;
		if (!arg || nr_args > 256)
			break;
		ret = io_probe(ctx, arg, nr_args);
		break;
	case IORING_REGISTER_PERSONALITY:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_register_personality(ctx);
		break;
	case IORING_UNREGISTER_PERSONALITY:
		ret = -EINVAL;
		if (arg)
			break;
		ret = io_unregister_personality(ctx, nr_args);
		break;
	case IORING_REGISTER_ENABLE_RINGS:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_register_enable_rings(ctx);
		break;
	case IORING_REGISTER_RESTRICTIONS:
		ret = io_register_restrictions(ctx, arg, nr_args);
		break;
	case IORING_REGISTER_FILES2:
		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE);
		break;
	case IORING_REGISTER_FILES_UPDATE2:
		ret = io_register_rsrc_update(ctx, arg, nr_args,
					      IORING_RSRC_FILE);
		break;
	case IORING_REGISTER_BUFFERS2:
		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER);
		break;
	case IORING_REGISTER_BUFFERS_UPDATE:
		ret = io_register_rsrc_update(ctx, arg, nr_args,
					      IORING_RSRC_BUFFER);
		break;
	case IORING_REGISTER_IOWQ_AFF:
		ret = -EINVAL;
		if (!arg || !nr_args)
			break;
		ret = io_register_iowq_aff(ctx, arg, nr_args);
		break;
	case IORING_UNREGISTER_IOWQ_AFF:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_unregister_iowq_aff(ctx);
		break;
	case IORING_REGISTER_IOWQ_MAX_WORKERS:
		ret = -EINVAL;
		if (!arg || nr_args != 2)
			break;
		ret = io_register_iowq_max_workers(ctx, arg);
		break;
	default:
		ret = -EINVAL;
		break;
	}

	if (io_register_op_must_quiesce(opcode)) {
		/* bring the ctx back to life */
		percpu_ref_reinit(&ctx->refs);
		reinit_completion(&ctx->ref_comp);
	}
	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;

	io_run_task_work();

	mutex_lock(&ctx->uring_lock);
	ret = __io_uring_register(ctx, opcode, arg, nr_args);
	mutex_unlock(&ctx->uring_lock);
	trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs,
							ctx->cq_ev_fd != NULL, ret);
out_fput:
	fdput(f);
	return ret;
}

static int __init io_uring_init(void)
{
#define __BUILD_BUG_VERIFY_ELEMENT(stype, eoffset, etype, ename) do { \
	BUILD_BUG_ON(offsetof(stype, ename) != eoffset); \
	BUILD_BUG_ON(sizeof(etype) != sizeof_field(stype, ename)); \
} while (0)

#define BUILD_BUG_SQE_ELEM(eoffset, etype, ename) \
	__BUILD_BUG_VERIFY_ELEMENT(struct io_uring_sqe, eoffset, etype, ename)
	BUILD_BUG_ON(sizeof(struct io_uring_sqe) != 64);
	BUILD_BUG_SQE_ELEM(0,  __u8,   opcode);
	BUILD_BUG_SQE_ELEM(1,  __u8,   flags);
	BUILD_BUG_SQE_ELEM(2,  __u16,  ioprio);
	BUILD_BUG_SQE_ELEM(4,  __s32,  fd);
	BUILD_BUG_SQE_ELEM(8,  __u64,  off);
	BUILD_BUG_SQE_ELEM(8,  __u64,  addr2);
	BUILD_BUG_SQE_ELEM(16, __u64,  addr);
	BUILD_BUG_SQE_ELEM(16, __u64,  splice_off_in);
	BUILD_BUG_SQE_ELEM(24, __u32,  len);
	BUILD_BUG_SQE_ELEM(28,     __kernel_rwf_t, rw_flags);
	BUILD_BUG_SQE_ELEM(28, /* compat */   int, rw_flags);
	BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags);
	BUILD_BUG_SQE_ELEM(28, __u32,  fsync_flags);
	BUILD_BUG_SQE_ELEM(28, /* compat */ __u16,  poll_events);
	BUILD_BUG_SQE_ELEM(28, __u32,  poll32_events);
	BUILD_BUG_SQE_ELEM(28, __u32,  sync_range_flags);
	BUILD_BUG_SQE_ELEM(28, __u32,  msg_flags);
	BUILD_BUG_SQE_ELEM(28, __u32,  timeout_flags);
	BUILD_BUG_SQE_ELEM(28, __u32,  accept_flags);
	BUILD_BUG_SQE_ELEM(28, __u32,  cancel_flags);
	BUILD_BUG_SQE_ELEM(28, __u32,  open_flags);
	BUILD_BUG_SQE_ELEM(28, __u32,  statx_flags);
	BUILD_BUG_SQE_ELEM(28, __u32,  fadvise_advice);
	BUILD_BUG_SQE_ELEM(28, __u32,  splice_flags);
	BUILD_BUG_SQE_ELEM(32, __u64,  user_data);
	BUILD_BUG_SQE_ELEM(40, __u16,  buf_index);
	BUILD_BUG_SQE_ELEM(40, __u16,  buf_group);
	BUILD_BUG_SQE_ELEM(42, __u16,  personality);
	BUILD_BUG_SQE_ELEM(44, __s32,  splice_fd_in);
	BUILD_BUG_SQE_ELEM(44, __u32,  file_index);

	BUILD_BUG_ON(sizeof(struct io_uring_files_update) !=
		     sizeof(struct io_uring_rsrc_update));
	BUILD_BUG_ON(sizeof(struct io_uring_rsrc_update) >
		     sizeof(struct io_uring_rsrc_update2));

	/* ->buf_index is u16 */
	BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16));

	/* should fit into one byte */
	BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8));
	BUILD_BUG_ON(SQE_COMMON_FLAGS >= (1 << 8));
	BUILD_BUG_ON((SQE_VALID_FLAGS | SQE_COMMON_FLAGS) != SQE_VALID_FLAGS);

	BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
	BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));

	req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
				SLAB_ACCOUNT);
	return 0;
};
__initcall(io_uring_init);