summaryrefslogtreecommitdiff
path: root/fs/aio.c
blob: 77e33619de40f6711b582a575eef043c7ed760f6 (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
/*
 *	An async IO implementation for Linux
 *	Written by Benjamin LaHaise <bcrl@kvack.org>
 *
 *	Implements an efficient asynchronous io interface.
 *
 *	Copyright 2000, 2001, 2002 Red Hat, Inc.  All Rights Reserved.
 *	Copyright 2018 Christoph Hellwig.
 *
 *	See ../COPYING for licensing terms.
 */
#define pr_fmt(fmt) "%s: " fmt, __func__

#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/aio_abi.h>
#include <linux/export.h>
#include <linux/syscalls.h>
#include <linux/backing-dev.h>
#include <linux/refcount.h>
#include <linux/uio.h>

#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/aio.h>
#include <linux/highmem.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/eventfd.h>
#include <linux/blkdev.h>
#include <linux/compat.h>
#include <linux/migrate.h>
#include <linux/ramfs.h>
#include <linux/percpu-refcount.h>
#include <linux/mount.h>
#include <linux/pseudo_fs.h>

#include <linux/uaccess.h>
#include <linux/nospec.h>

#include "internal.h"

#define KIOCB_KEY		0

#define AIO_RING_MAGIC			0xa10a10a1
#define AIO_RING_COMPAT_FEATURES	1
#define AIO_RING_INCOMPAT_FEATURES	0
struct aio_ring {
	unsigned	id;	/* kernel internal index number */
	unsigned	nr;	/* number of io_events */
	unsigned	head;	/* Written to by userland or under ring_lock
				 * mutex by aio_read_events_ring(). */
	unsigned	tail;

	unsigned	magic;
	unsigned	compat_features;
	unsigned	incompat_features;
	unsigned	header_length;	/* size of aio_ring */


	struct io_event		io_events[];
}; /* 128 bytes + ring size */

/*
 * Plugging is meant to work with larger batches of IOs. If we don't
 * have more than the below, then don't bother setting up a plug.
 */
#define AIO_PLUG_THRESHOLD	2

#define AIO_RING_PAGES	8

struct kioctx_table {
	struct rcu_head		rcu;
	unsigned		nr;
	struct kioctx __rcu	*table[];
};

struct kioctx_cpu {
	unsigned		reqs_available;
};

struct ctx_rq_wait {
	struct completion comp;
	atomic_t count;
};

struct kioctx {
	struct percpu_ref	users;
	atomic_t		dead;

	struct percpu_ref	reqs;

	unsigned long		user_id;

	struct __percpu kioctx_cpu *cpu;

	/*
	 * For percpu reqs_available, number of slots we move to/from global
	 * counter at a time:
	 */
	unsigned		req_batch;
	/*
	 * This is what userspace passed to io_setup(), it's not used for
	 * anything but counting against the global max_reqs quota.
	 *
	 * The real limit is nr_events - 1, which will be larger (see
	 * aio_setup_ring())
	 */
	unsigned		max_reqs;

	/* Size of ringbuffer, in units of struct io_event */
	unsigned		nr_events;

	unsigned long		mmap_base;
	unsigned long		mmap_size;

	struct page		**ring_pages;
	long			nr_pages;

	struct rcu_work		free_rwork;	/* see free_ioctx() */

	/*
	 * signals when all in-flight requests are done
	 */
	struct ctx_rq_wait	*rq_wait;

	struct {
		/*
		 * This counts the number of available slots in the ringbuffer,
		 * so we avoid overflowing it: it's decremented (if positive)
		 * when allocating a kiocb and incremented when the resulting
		 * io_event is pulled off the ringbuffer.
		 *
		 * We batch accesses to it with a percpu version.
		 */
		atomic_t	reqs_available;
	} ____cacheline_aligned_in_smp;

	struct {
		spinlock_t	ctx_lock;
		struct list_head active_reqs;	/* used for cancellation */
	} ____cacheline_aligned_in_smp;

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

	struct {
		unsigned	tail;
		unsigned	completed_events;
		spinlock_t	completion_lock;
	} ____cacheline_aligned_in_smp;

	struct page		*internal_pages[AIO_RING_PAGES];
	struct file		*aio_ring_file;

	unsigned		id;
};

/*
 * First field must be the file pointer in all the
 * iocb unions! See also 'struct kiocb' in <linux/fs.h>
 */
struct fsync_iocb {
	struct file		*file;
	struct work_struct	work;
	bool			datasync;
	struct cred		*creds;
};

struct poll_iocb {
	struct file		*file;
	struct wait_queue_head	*head;
	__poll_t		events;
	bool			cancelled;
	bool			work_scheduled;
	bool			work_need_resched;
	struct wait_queue_entry	wait;
	struct work_struct	work;
};

/*
 * 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 aio_kiocb {
	union {
		struct file		*ki_filp;
		struct kiocb		rw;
		struct fsync_iocb	fsync;
		struct poll_iocb	poll;
	};

	struct kioctx		*ki_ctx;
	kiocb_cancel_fn		*ki_cancel;

	struct io_event		ki_res;

	struct list_head	ki_list;	/* the aio core uses this
						 * for cancellation */
	refcount_t		ki_refcnt;

	/*
	 * If the aio_resfd field of the userspace iocb is not zero,
	 * this is the underlying eventfd context to deliver events to.
	 */
	struct eventfd_ctx	*ki_eventfd;
};

/*------ sysctl variables----*/
static DEFINE_SPINLOCK(aio_nr_lock);
static unsigned long aio_nr;		/* current system wide number of aio requests */
static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */
/*----end sysctl variables---*/
#ifdef CONFIG_SYSCTL
static struct ctl_table aio_sysctls[] = {
	{
		.procname	= "aio-nr",
		.data		= &aio_nr,
		.maxlen		= sizeof(aio_nr),
		.mode		= 0444,
		.proc_handler	= proc_doulongvec_minmax,
	},
	{
		.procname	= "aio-max-nr",
		.data		= &aio_max_nr,
		.maxlen		= sizeof(aio_max_nr),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
	},
	{}
};

static void __init aio_sysctl_init(void)
{
	register_sysctl_init("fs", aio_sysctls);
}
#else
#define aio_sysctl_init() do { } while (0)
#endif

static struct kmem_cache	*kiocb_cachep;
static struct kmem_cache	*kioctx_cachep;

static struct vfsmount *aio_mnt;

static const struct file_operations aio_ring_fops;
static const struct address_space_operations aio_ctx_aops;

static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
{
	struct file *file;
	struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
	if (IS_ERR(inode))
		return ERR_CAST(inode);

	inode->i_mapping->a_ops = &aio_ctx_aops;
	inode->i_mapping->private_data = ctx;
	inode->i_size = PAGE_SIZE * nr_pages;

	file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
				O_RDWR, &aio_ring_fops);
	if (IS_ERR(file))
		iput(inode);
	return file;
}

static int aio_init_fs_context(struct fs_context *fc)
{
	if (!init_pseudo(fc, AIO_RING_MAGIC))
		return -ENOMEM;
	fc->s_iflags |= SB_I_NOEXEC;
	return 0;
}

/* aio_setup
 *	Creates the slab caches used by the aio routines, panic on
 *	failure as this is done early during the boot sequence.
 */
static int __init aio_setup(void)
{
	static struct file_system_type aio_fs = {
		.name		= "aio",
		.init_fs_context = aio_init_fs_context,
		.kill_sb	= kill_anon_super,
	};
	aio_mnt = kern_mount(&aio_fs);
	if (IS_ERR(aio_mnt))
		panic("Failed to create aio fs mount.");

	kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
	aio_sysctl_init();
	return 0;
}
__initcall(aio_setup);

static void put_aio_ring_file(struct kioctx *ctx)
{
	struct file *aio_ring_file = ctx->aio_ring_file;
	struct address_space *i_mapping;

	if (aio_ring_file) {
		truncate_setsize(file_inode(aio_ring_file), 0);

		/* Prevent further access to the kioctx from migratepages */
		i_mapping = aio_ring_file->f_mapping;
		spin_lock(&i_mapping->private_lock);
		i_mapping->private_data = NULL;
		ctx->aio_ring_file = NULL;
		spin_unlock(&i_mapping->private_lock);

		fput(aio_ring_file);
	}
}

static void aio_free_ring(struct kioctx *ctx)
{
	int i;

	/* Disconnect the kiotx from the ring file.  This prevents future
	 * accesses to the kioctx from page migration.
	 */
	put_aio_ring_file(ctx);

	for (i = 0; i < ctx->nr_pages; i++) {
		struct page *page;
		pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
				page_count(ctx->ring_pages[i]));
		page = ctx->ring_pages[i];
		if (!page)
			continue;
		ctx->ring_pages[i] = NULL;
		put_page(page);
	}

	if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) {
		kfree(ctx->ring_pages);
		ctx->ring_pages = NULL;
	}
}

static int aio_ring_mremap(struct vm_area_struct *vma)
{
	struct file *file = vma->vm_file;
	struct mm_struct *mm = vma->vm_mm;
	struct kioctx_table *table;
	int i, res = -EINVAL;

	spin_lock(&mm->ioctx_lock);
	rcu_read_lock();
	table = rcu_dereference(mm->ioctx_table);
	if (!table)
		goto out_unlock;

	for (i = 0; i < table->nr; i++) {
		struct kioctx *ctx;

		ctx = rcu_dereference(table->table[i]);
		if (ctx && ctx->aio_ring_file == file) {
			if (!atomic_read(&ctx->dead)) {
				ctx->user_id = ctx->mmap_base = vma->vm_start;
				res = 0;
			}
			break;
		}
	}

out_unlock:
	rcu_read_unlock();
	spin_unlock(&mm->ioctx_lock);
	return res;
}

static const struct vm_operations_struct aio_ring_vm_ops = {
	.mremap		= aio_ring_mremap,
#if IS_ENABLED(CONFIG_MMU)
	.fault		= filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= filemap_page_mkwrite,
#endif
};

static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
{
	vm_flags_set(vma, VM_DONTEXPAND);
	vma->vm_ops = &aio_ring_vm_ops;
	return 0;
}

static const struct file_operations aio_ring_fops = {
	.mmap = aio_ring_mmap,
};

#if IS_ENABLED(CONFIG_MIGRATION)
static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
			struct folio *src, enum migrate_mode mode)
{
	struct kioctx *ctx;
	unsigned long flags;
	pgoff_t idx;
	int rc;

	/*
	 * We cannot support the _NO_COPY case here, because copy needs to
	 * happen under the ctx->completion_lock. That does not work with the
	 * migration workflow of MIGRATE_SYNC_NO_COPY.
	 */
	if (mode == MIGRATE_SYNC_NO_COPY)
		return -EINVAL;

	rc = 0;

	/* mapping->private_lock here protects against the kioctx teardown.  */
	spin_lock(&mapping->private_lock);
	ctx = mapping->private_data;
	if (!ctx) {
		rc = -EINVAL;
		goto out;
	}

	/* The ring_lock mutex.  The prevents aio_read_events() from writing
	 * to the ring's head, and prevents page migration from mucking in
	 * a partially initialized kiotx.
	 */
	if (!mutex_trylock(&ctx->ring_lock)) {
		rc = -EAGAIN;
		goto out;
	}

	idx = src->index;
	if (idx < (pgoff_t)ctx->nr_pages) {
		/* Make sure the old folio hasn't already been changed */
		if (ctx->ring_pages[idx] != &src->page)
			rc = -EAGAIN;
	} else
		rc = -EINVAL;

	if (rc != 0)
		goto out_unlock;

	/* Writeback must be complete */
	BUG_ON(folio_test_writeback(src));
	folio_get(dst);

	rc = folio_migrate_mapping(mapping, dst, src, 1);
	if (rc != MIGRATEPAGE_SUCCESS) {
		folio_put(dst);
		goto out_unlock;
	}

	/* Take completion_lock to prevent other writes to the ring buffer
	 * while the old folio is copied to the new.  This prevents new
	 * events from being lost.
	 */
	spin_lock_irqsave(&ctx->completion_lock, flags);
	folio_migrate_copy(dst, src);
	BUG_ON(ctx->ring_pages[idx] != &src->page);
	ctx->ring_pages[idx] = &dst->page;
	spin_unlock_irqrestore(&ctx->completion_lock, flags);

	/* The old folio is no longer accessible. */
	folio_put(src);

out_unlock:
	mutex_unlock(&ctx->ring_lock);
out:
	spin_unlock(&mapping->private_lock);
	return rc;
}
#else
#define aio_migrate_folio NULL
#endif

static const struct address_space_operations aio_ctx_aops = {
	.dirty_folio	= noop_dirty_folio,
	.migrate_folio	= aio_migrate_folio,
};

static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
{
	struct aio_ring *ring;
	struct mm_struct *mm = current->mm;
	unsigned long size, unused;
	int nr_pages;
	int i;
	struct file *file;

	/* Compensate for the ring buffer's head/tail overlap entry */
	nr_events += 2;	/* 1 is required, 2 for good luck */

	size = sizeof(struct aio_ring);
	size += sizeof(struct io_event) * nr_events;

	nr_pages = PFN_UP(size);
	if (nr_pages < 0)
		return -EINVAL;

	file = aio_private_file(ctx, nr_pages);
	if (IS_ERR(file)) {
		ctx->aio_ring_file = NULL;
		return -ENOMEM;
	}

	ctx->aio_ring_file = file;
	nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
			/ sizeof(struct io_event);

	ctx->ring_pages = ctx->internal_pages;
	if (nr_pages > AIO_RING_PAGES) {
		ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
					  GFP_KERNEL);
		if (!ctx->ring_pages) {
			put_aio_ring_file(ctx);
			return -ENOMEM;
		}
	}

	for (i = 0; i < nr_pages; i++) {
		struct page *page;
		page = find_or_create_page(file->f_mapping,
					   i, GFP_USER | __GFP_ZERO);
		if (!page)
			break;
		pr_debug("pid(%d) page[%d]->count=%d\n",
			 current->pid, i, page_count(page));
		SetPageUptodate(page);
		unlock_page(page);

		ctx->ring_pages[i] = page;
	}
	ctx->nr_pages = i;

	if (unlikely(i != nr_pages)) {
		aio_free_ring(ctx);
		return -ENOMEM;
	}

	ctx->mmap_size = nr_pages * PAGE_SIZE;
	pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size);

	if (mmap_write_lock_killable(mm)) {
		ctx->mmap_size = 0;
		aio_free_ring(ctx);
		return -EINTR;
	}

	ctx->mmap_base = do_mmap(ctx->aio_ring_file, 0, ctx->mmap_size,
				 PROT_READ | PROT_WRITE,
				 MAP_SHARED, 0, &unused, NULL);
	mmap_write_unlock(mm);
	if (IS_ERR((void *)ctx->mmap_base)) {
		ctx->mmap_size = 0;
		aio_free_ring(ctx);
		return -ENOMEM;
	}

	pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);

	ctx->user_id = ctx->mmap_base;
	ctx->nr_events = nr_events; /* trusted copy */

	ring = page_address(ctx->ring_pages[0]);
	ring->nr = nr_events;	/* user copy */
	ring->id = ~0U;
	ring->head = ring->tail = 0;
	ring->magic = AIO_RING_MAGIC;
	ring->compat_features = AIO_RING_COMPAT_FEATURES;
	ring->incompat_features = AIO_RING_INCOMPAT_FEATURES;
	ring->header_length = sizeof(struct aio_ring);
	flush_dcache_page(ctx->ring_pages[0]);

	return 0;
}

#define AIO_EVENTS_PER_PAGE	(PAGE_SIZE / sizeof(struct io_event))
#define AIO_EVENTS_FIRST_PAGE	((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event))
#define AIO_EVENTS_OFFSET	(AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE)

void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
{
	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
	struct kioctx *ctx = req->ki_ctx;
	unsigned long flags;

	if (WARN_ON_ONCE(!list_empty(&req->ki_list)))
		return;

	spin_lock_irqsave(&ctx->ctx_lock, flags);
	list_add_tail(&req->ki_list, &ctx->active_reqs);
	req->ki_cancel = cancel;
	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
}
EXPORT_SYMBOL(kiocb_set_cancel_fn);

/*
 * free_ioctx() should be RCU delayed to synchronize against the RCU
 * protected lookup_ioctx() and also needs process context to call
 * aio_free_ring().  Use rcu_work.
 */
static void free_ioctx(struct work_struct *work)
{
	struct kioctx *ctx = container_of(to_rcu_work(work), struct kioctx,
					  free_rwork);
	pr_debug("freeing %p\n", ctx);

	aio_free_ring(ctx);
	free_percpu(ctx->cpu);
	percpu_ref_exit(&ctx->reqs);
	percpu_ref_exit(&ctx->users);
	kmem_cache_free(kioctx_cachep, ctx);
}

static void free_ioctx_reqs(struct percpu_ref *ref)
{
	struct kioctx *ctx = container_of(ref, struct kioctx, reqs);

	/* At this point we know that there are no any in-flight requests */
	if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count))
		complete(&ctx->rq_wait->comp);

	/* Synchronize against RCU protected table->table[] dereferences */
	INIT_RCU_WORK(&ctx->free_rwork, free_ioctx);
	queue_rcu_work(system_wq, &ctx->free_rwork);
}

/*
 * When this function runs, the kioctx has been removed from the "hash table"
 * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted -
 * now it's safe to cancel any that need to be.
 */
static void free_ioctx_users(struct percpu_ref *ref)
{
	struct kioctx *ctx = container_of(ref, struct kioctx, users);
	struct aio_kiocb *req;

	spin_lock_irq(&ctx->ctx_lock);

	while (!list_empty(&ctx->active_reqs)) {
		req = list_first_entry(&ctx->active_reqs,
				       struct aio_kiocb, ki_list);
		req->ki_cancel(&req->rw);
		list_del_init(&req->ki_list);
	}

	spin_unlock_irq(&ctx->ctx_lock);

	percpu_ref_kill(&ctx->reqs);
	percpu_ref_put(&ctx->reqs);
}

static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
{
	unsigned i, new_nr;
	struct kioctx_table *table, *old;
	struct aio_ring *ring;

	spin_lock(&mm->ioctx_lock);
	table = rcu_dereference_raw(mm->ioctx_table);

	while (1) {
		if (table)
			for (i = 0; i < table->nr; i++)
				if (!rcu_access_pointer(table->table[i])) {
					ctx->id = i;
					rcu_assign_pointer(table->table[i], ctx);
					spin_unlock(&mm->ioctx_lock);

					/* While kioctx setup is in progress,
					 * we are protected from page migration
					 * changes ring_pages by ->ring_lock.
					 */
					ring = page_address(ctx->ring_pages[0]);
					ring->id = ctx->id;
					return 0;
				}

		new_nr = (table ? table->nr : 1) * 4;
		spin_unlock(&mm->ioctx_lock);

		table = kzalloc(struct_size(table, table, new_nr), GFP_KERNEL);
		if (!table)
			return -ENOMEM;

		table->nr = new_nr;

		spin_lock(&mm->ioctx_lock);
		old = rcu_dereference_raw(mm->ioctx_table);

		if (!old) {
			rcu_assign_pointer(mm->ioctx_table, table);
		} else if (table->nr > old->nr) {
			memcpy(table->table, old->table,
			       old->nr * sizeof(struct kioctx *));

			rcu_assign_pointer(mm->ioctx_table, table);
			kfree_rcu(old, rcu);
		} else {
			kfree(table);
			table = old;
		}
	}
}

static void aio_nr_sub(unsigned nr)
{
	spin_lock(&aio_nr_lock);
	if (WARN_ON(aio_nr - nr > aio_nr))
		aio_nr = 0;
	else
		aio_nr -= nr;
	spin_unlock(&aio_nr_lock);
}

/* ioctx_alloc
 *	Allocates and initializes an ioctx.  Returns an ERR_PTR if it failed.
 */
static struct kioctx *ioctx_alloc(unsigned nr_events)
{
	struct mm_struct *mm = current->mm;
	struct kioctx *ctx;
	int err = -ENOMEM;

	/*
	 * Store the original nr_events -- what userspace passed to io_setup(),
	 * for counting against the global limit -- before it changes.
	 */
	unsigned int max_reqs = nr_events;

	/*
	 * We keep track of the number of available ringbuffer slots, to prevent
	 * overflow (reqs_available), and we also use percpu counters for this.
	 *
	 * So since up to half the slots might be on other cpu's percpu counters
	 * and unavailable, double nr_events so userspace sees what they
	 * expected: additionally, we move req_batch slots to/from percpu
	 * counters at a time, so make sure that isn't 0:
	 */
	nr_events = max(nr_events, num_possible_cpus() * 4);
	nr_events *= 2;

	/* Prevent overflows */
	if (nr_events > (0x10000000U / sizeof(struct io_event))) {
		pr_debug("ENOMEM: nr_events too high\n");
		return ERR_PTR(-EINVAL);
	}

	if (!nr_events || (unsigned long)max_reqs > aio_max_nr)
		return ERR_PTR(-EAGAIN);

	ctx = kmem_cache_zalloc(kioctx_cachep, GFP_KERNEL);
	if (!ctx)
		return ERR_PTR(-ENOMEM);

	ctx->max_reqs = max_reqs;

	spin_lock_init(&ctx->ctx_lock);
	spin_lock_init(&ctx->completion_lock);
	mutex_init(&ctx->ring_lock);
	/* Protect against page migration throughout kiotx setup by keeping
	 * the ring_lock mutex held until setup is complete. */
	mutex_lock(&ctx->ring_lock);
	init_waitqueue_head(&ctx->wait);

	INIT_LIST_HEAD(&ctx->active_reqs);

	if (percpu_ref_init(&ctx->users, free_ioctx_users, 0, GFP_KERNEL))
		goto err;

	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs, 0, GFP_KERNEL))
		goto err;

	ctx->cpu = alloc_percpu(struct kioctx_cpu);
	if (!ctx->cpu)
		goto err;

	err = aio_setup_ring(ctx, nr_events);
	if (err < 0)
		goto err;

	atomic_set(&ctx->reqs_available, ctx->nr_events - 1);
	ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4);
	if (ctx->req_batch < 1)
		ctx->req_batch = 1;

	/* limit the number of system wide aios */
	spin_lock(&aio_nr_lock);
	if (aio_nr + ctx->max_reqs > aio_max_nr ||
	    aio_nr + ctx->max_reqs < aio_nr) {
		spin_unlock(&aio_nr_lock);
		err = -EAGAIN;
		goto err_ctx;
	}
	aio_nr += ctx->max_reqs;
	spin_unlock(&aio_nr_lock);

	percpu_ref_get(&ctx->users);	/* io_setup() will drop this ref */
	percpu_ref_get(&ctx->reqs);	/* free_ioctx_users() will drop this */

	err = ioctx_add_table(ctx, mm);
	if (err)
		goto err_cleanup;

	/* Release the ring_lock mutex now that all setup is complete. */
	mutex_unlock(&ctx->ring_lock);

	pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
		 ctx, ctx->user_id, mm, ctx->nr_events);
	return ctx;

err_cleanup:
	aio_nr_sub(ctx->max_reqs);
err_ctx:
	atomic_set(&ctx->dead, 1);
	if (ctx->mmap_size)
		vm_munmap(ctx->mmap_base, ctx->mmap_size);
	aio_free_ring(ctx);
err:
	mutex_unlock(&ctx->ring_lock);
	free_percpu(ctx->cpu);
	percpu_ref_exit(&ctx->reqs);
	percpu_ref_exit(&ctx->users);
	kmem_cache_free(kioctx_cachep, ctx);
	pr_debug("error allocating ioctx %d\n", err);
	return ERR_PTR(err);
}

/* kill_ioctx
 *	Cancels all outstanding aio requests on an aio context.  Used
 *	when the processes owning a context have all exited to encourage
 *	the rapid destruction of the kioctx.
 */
static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
		      struct ctx_rq_wait *wait)
{
	struct kioctx_table *table;

	spin_lock(&mm->ioctx_lock);
	if (atomic_xchg(&ctx->dead, 1)) {
		spin_unlock(&mm->ioctx_lock);
		return -EINVAL;
	}

	table = rcu_dereference_raw(mm->ioctx_table);
	WARN_ON(ctx != rcu_access_pointer(table->table[ctx->id]));
	RCU_INIT_POINTER(table->table[ctx->id], NULL);
	spin_unlock(&mm->ioctx_lock);

	/* free_ioctx_reqs() will do the necessary RCU synchronization */
	wake_up_all(&ctx->wait);

	/*
	 * It'd be more correct to do this in free_ioctx(), after all
	 * the outstanding kiocbs have finished - but by then io_destroy
	 * has already returned, so io_setup() could potentially return
	 * -EAGAIN with no ioctxs actually in use (as far as userspace
	 *  could tell).
	 */
	aio_nr_sub(ctx->max_reqs);

	if (ctx->mmap_size)
		vm_munmap(ctx->mmap_base, ctx->mmap_size);

	ctx->rq_wait = wait;
	percpu_ref_kill(&ctx->users);
	return 0;
}

/*
 * exit_aio: called when the last user of mm goes away.  At this point, there is
 * no way for any new requests to be submited or any of the io_* syscalls to be
 * called on the context.
 *
 * There may be outstanding kiocbs, but free_ioctx() will explicitly wait on
 * them.
 */
void exit_aio(struct mm_struct *mm)
{
	struct kioctx_table *table = rcu_dereference_raw(mm->ioctx_table);
	struct ctx_rq_wait wait;
	int i, skipped;

	if (!table)
		return;

	atomic_set(&wait.count, table->nr);
	init_completion(&wait.comp);

	skipped = 0;
	for (i = 0; i < table->nr; ++i) {
		struct kioctx *ctx =
			rcu_dereference_protected(table->table[i], true);

		if (!ctx) {
			skipped++;
			continue;
		}

		/*
		 * We don't need to bother with munmap() here - exit_mmap(mm)
		 * is coming and it'll unmap everything. And we simply can't,
		 * this is not necessarily our ->mm.
		 * Since kill_ioctx() uses non-zero ->mmap_size as indicator
		 * that it needs to unmap the area, just set it to 0.
		 */
		ctx->mmap_size = 0;
		kill_ioctx(mm, ctx, &wait);
	}

	if (!atomic_sub_and_test(skipped, &wait.count)) {
		/* Wait until all IO for the context are done. */
		wait_for_completion(&wait.comp);
	}

	RCU_INIT_POINTER(mm->ioctx_table, NULL);
	kfree(table);
}

static void put_reqs_available(struct kioctx *ctx, unsigned nr)
{
	struct kioctx_cpu *kcpu;
	unsigned long flags;

	local_irq_save(flags);
	kcpu = this_cpu_ptr(ctx->cpu);
	kcpu->reqs_available += nr;

	while (kcpu->reqs_available >= ctx->req_batch * 2) {
		kcpu->reqs_available -= ctx->req_batch;
		atomic_add(ctx->req_batch, &ctx->reqs_available);
	}

	local_irq_restore(flags);
}

static bool __get_reqs_available(struct kioctx *ctx)
{
	struct kioctx_cpu *kcpu;
	bool ret = false;
	unsigned long flags;

	local_irq_save(flags);
	kcpu = this_cpu_ptr(ctx->cpu);
	if (!kcpu->reqs_available) {
		int avail = atomic_read(&ctx->reqs_available);

		do {
			if (avail < ctx->req_batch)
				goto out;
		} while (!atomic_try_cmpxchg(&ctx->reqs_available,
					     &avail, avail - ctx->req_batch));

		kcpu->reqs_available += ctx->req_batch;
	}

	ret = true;
	kcpu->reqs_available--;
out:
	local_irq_restore(flags);
	return ret;
}

/* refill_reqs_available
 *	Updates the reqs_available reference counts used for tracking the
 *	number of free slots in the completion ring.  This can be called
 *	from aio_complete() (to optimistically update reqs_available) or
 *	from aio_get_req() (the we're out of events case).  It must be
 *	called holding ctx->completion_lock.
 */
static void refill_reqs_available(struct kioctx *ctx, unsigned head,
                                  unsigned tail)
{
	unsigned events_in_ring, completed;

	/* Clamp head since userland can write to it. */
	head %= ctx->nr_events;
	if (head <= tail)
		events_in_ring = tail - head;
	else
		events_in_ring = ctx->nr_events - (head - tail);

	completed = ctx->completed_events;
	if (events_in_ring < completed)
		completed -= events_in_ring;
	else
		completed = 0;

	if (!completed)
		return;

	ctx->completed_events -= completed;
	put_reqs_available(ctx, completed);
}

/* user_refill_reqs_available
 *	Called to refill reqs_available when aio_get_req() encounters an
 *	out of space in the completion ring.
 */
static void user_refill_reqs_available(struct kioctx *ctx)
{
	spin_lock_irq(&ctx->completion_lock);
	if (ctx->completed_events) {
		struct aio_ring *ring;
		unsigned head;

		/* Access of ring->head may race with aio_read_events_ring()
		 * here, but that's okay since whether we read the old version
		 * or the new version, and either will be valid.  The important
		 * part is that head cannot pass tail since we prevent
		 * aio_complete() from updating tail by holding
		 * ctx->completion_lock.  Even if head is invalid, the check
		 * against ctx->completed_events below will make sure we do the
		 * safe/right thing.
		 */
		ring = page_address(ctx->ring_pages[0]);
		head = ring->head;

		refill_reqs_available(ctx, head, ctx->tail);
	}

	spin_unlock_irq(&ctx->completion_lock);
}

static bool get_reqs_available(struct kioctx *ctx)
{
	if (__get_reqs_available(ctx))
		return true;
	user_refill_reqs_available(ctx);
	return __get_reqs_available(ctx);
}

/* aio_get_req
 *	Allocate a slot for an aio request.
 * Returns NULL if no requests are free.
 *
 * The refcount is initialized to 2 - one for the async op completion,
 * one for the synchronous code that does this.
 */
static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
{
	struct aio_kiocb *req;

	req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL);
	if (unlikely(!req))
		return NULL;

	if (unlikely(!get_reqs_available(ctx))) {
		kmem_cache_free(kiocb_cachep, req);
		return NULL;
	}

	percpu_ref_get(&ctx->reqs);
	req->ki_ctx = ctx;
	INIT_LIST_HEAD(&req->ki_list);
	refcount_set(&req->ki_refcnt, 2);
	req->ki_eventfd = NULL;
	return req;
}

static struct kioctx *lookup_ioctx(unsigned long ctx_id)
{
	struct aio_ring __user *ring  = (void __user *)ctx_id;
	struct mm_struct *mm = current->mm;
	struct kioctx *ctx, *ret = NULL;
	struct kioctx_table *table;
	unsigned id;

	if (get_user(id, &ring->id))
		return NULL;

	rcu_read_lock();
	table = rcu_dereference(mm->ioctx_table);

	if (!table || id >= table->nr)
		goto out;

	id = array_index_nospec(id, table->nr);
	ctx = rcu_dereference(table->table[id]);
	if (ctx && ctx->user_id == ctx_id) {
		if (percpu_ref_tryget_live(&ctx->users))
			ret = ctx;
	}
out:
	rcu_read_unlock();
	return ret;
}

static inline void iocb_destroy(struct aio_kiocb *iocb)
{
	if (iocb->ki_eventfd)
		eventfd_ctx_put(iocb->ki_eventfd);
	if (iocb->ki_filp)
		fput(iocb->ki_filp);
	percpu_ref_put(&iocb->ki_ctx->reqs);
	kmem_cache_free(kiocb_cachep, iocb);
}

/* aio_complete
 *	Called when the io request on the given iocb is complete.
 */
static void aio_complete(struct aio_kiocb *iocb)
{
	struct kioctx	*ctx = iocb->ki_ctx;
	struct aio_ring	*ring;
	struct io_event	*ev_page, *event;
	unsigned tail, pos, head;
	unsigned long	flags;

	/*
	 * Add a completion event to the ring buffer. Must be done holding
	 * ctx->completion_lock to prevent other code from messing with the tail
	 * pointer since we might be called from irq context.
	 */
	spin_lock_irqsave(&ctx->completion_lock, flags);

	tail = ctx->tail;
	pos = tail + AIO_EVENTS_OFFSET;

	if (++tail >= ctx->nr_events)
		tail = 0;

	ev_page = page_address(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
	event = ev_page + pos % AIO_EVENTS_PER_PAGE;

	*event = iocb->ki_res;

	flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);

	pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb,
		 (void __user *)(unsigned long)iocb->ki_res.obj,
		 iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2);

	/* after flagging the request as done, we
	 * must never even look at it again
	 */
	smp_wmb();	/* make event visible before updating tail */

	ctx->tail = tail;

	ring = page_address(ctx->ring_pages[0]);
	head = ring->head;
	ring->tail = tail;
	flush_dcache_page(ctx->ring_pages[0]);

	ctx->completed_events++;
	if (ctx->completed_events > 1)
		refill_reqs_available(ctx, head, tail);
	spin_unlock_irqrestore(&ctx->completion_lock, flags);

	pr_debug("added to ring %p at [%u]\n", iocb, tail);

	/*
	 * Check if the user asked us to deliver the result through an
	 * eventfd. The eventfd_signal() function is safe to be called
	 * from IRQ context.
	 */
	if (iocb->ki_eventfd)
		eventfd_signal(iocb->ki_eventfd, 1);

	/*
	 * We have to order our ring_info tail store above and test
	 * of the wait list below outside the wait lock.  This is
	 * like in wake_up_bit() where clearing a bit has to be
	 * ordered with the unlocked test.
	 */
	smp_mb();

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

static inline void iocb_put(struct aio_kiocb *iocb)
{
	if (refcount_dec_and_test(&iocb->ki_refcnt)) {
		aio_complete(iocb);
		iocb_destroy(iocb);
	}
}

/* aio_read_events_ring
 *	Pull an event off of the ioctx's event ring.  Returns the number of
 *	events fetched
 */
static long aio_read_events_ring(struct kioctx *ctx,
				 struct io_event __user *event, long nr)
{
	struct aio_ring *ring;
	unsigned head, tail, pos;
	long ret = 0;
	int copy_ret;

	/*
	 * The mutex can block and wake us up and that will cause
	 * wait_event_interruptible_hrtimeout() to schedule without sleeping
	 * and repeat. This should be rare enough that it doesn't cause
	 * peformance issues. See the comment in read_events() for more detail.
	 */
	sched_annotate_sleep();
	mutex_lock(&ctx->ring_lock);

	/* Access to ->ring_pages here is protected by ctx->ring_lock. */
	ring = page_address(ctx->ring_pages[0]);
	head = ring->head;
	tail = ring->tail;

	/*
	 * Ensure that once we've read the current tail pointer, that
	 * we also see the events that were stored up to the tail.
	 */
	smp_rmb();

	pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events);

	if (head == tail)
		goto out;

	head %= ctx->nr_events;
	tail %= ctx->nr_events;

	while (ret < nr) {
		long avail;
		struct io_event *ev;
		struct page *page;

		avail = (head <= tail ?  tail : ctx->nr_events) - head;
		if (head == tail)
			break;

		pos = head + AIO_EVENTS_OFFSET;
		page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE];
		pos %= AIO_EVENTS_PER_PAGE;

		avail = min(avail, nr - ret);
		avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos);

		ev = page_address(page);
		copy_ret = copy_to_user(event + ret, ev + pos,
					sizeof(*ev) * avail);

		if (unlikely(copy_ret)) {
			ret = -EFAULT;
			goto out;
		}

		ret += avail;
		head += avail;
		head %= ctx->nr_events;
	}

	ring = page_address(ctx->ring_pages[0]);
	ring->head = head;
	flush_dcache_page(ctx->ring_pages[0]);

	pr_debug("%li  h%u t%u\n", ret, head, tail);
out:
	mutex_unlock(&ctx->ring_lock);

	return ret;
}

static bool aio_read_events(struct kioctx *ctx, long min_nr, long nr,
			    struct io_event __user *event, long *i)
{
	long ret = aio_read_events_ring(ctx, event + *i, nr - *i);

	if (ret > 0)
		*i += ret;

	if (unlikely(atomic_read(&ctx->dead)))
		ret = -EINVAL;

	if (!*i)
		*i = ret;

	return ret < 0 || *i >= min_nr;
}

static long read_events(struct kioctx *ctx, long min_nr, long nr,
			struct io_event __user *event,
			ktime_t until)
{
	long ret = 0;

	/*
	 * Note that aio_read_events() is being called as the conditional - i.e.
	 * we're calling it after prepare_to_wait() has set task state to
	 * TASK_INTERRUPTIBLE.
	 *
	 * But aio_read_events() can block, and if it blocks it's going to flip
	 * the task state back to TASK_RUNNING.
	 *
	 * This should be ok, provided it doesn't flip the state back to
	 * TASK_RUNNING and return 0 too much - that causes us to spin. That
	 * will only happen if the mutex_lock() call blocks, and we then find
	 * the ringbuffer empty. So in practice we should be ok, but it's
	 * something to be aware of when touching this code.
	 */
	if (until == 0)
		aio_read_events(ctx, min_nr, nr, event, &ret);
	else
		wait_event_interruptible_hrtimeout(ctx->wait,
				aio_read_events(ctx, min_nr, nr, event, &ret),
				until);
	return ret;
}

/* sys_io_setup:
 *	Create an aio_context capable of receiving at least nr_events.
 *	ctxp must not point to an aio_context that already exists, and
 *	must be initialized to 0 prior to the call.  On successful
 *	creation of the aio_context, *ctxp is filled in with the resulting 
 *	handle.  May fail with -EINVAL if *ctxp is not initialized,
 *	if the specified nr_events exceeds internal limits.  May fail 
 *	with -EAGAIN if the specified nr_events exceeds the user's limit 
 *	of available events.  May fail with -ENOMEM if insufficient kernel
 *	resources are available.  May fail with -EFAULT if an invalid
 *	pointer is passed for ctxp.  Will fail with -ENOSYS if not
 *	implemented.
 */
SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
{
	struct kioctx *ioctx = NULL;
	unsigned long ctx;
	long ret;

	ret = get_user(ctx, ctxp);
	if (unlikely(ret))
		goto out;

	ret = -EINVAL;
	if (unlikely(ctx || nr_events == 0)) {
		pr_debug("EINVAL: ctx %lu nr_events %u\n",
		         ctx, nr_events);
		goto out;
	}

	ioctx = ioctx_alloc(nr_events);
	ret = PTR_ERR(ioctx);
	if (!IS_ERR(ioctx)) {
		ret = put_user(ioctx->user_id, ctxp);
		if (ret)
			kill_ioctx(current->mm, ioctx, NULL);
		percpu_ref_put(&ioctx->users);
	}

out:
	return ret;
}

#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_events, u32 __user *, ctx32p)
{
	struct kioctx *ioctx = NULL;
	unsigned long ctx;
	long ret;

	ret = get_user(ctx, ctx32p);
	if (unlikely(ret))
		goto out;

	ret = -EINVAL;
	if (unlikely(ctx || nr_events == 0)) {
		pr_debug("EINVAL: ctx %lu nr_events %u\n",
		         ctx, nr_events);
		goto out;
	}

	ioctx = ioctx_alloc(nr_events);
	ret = PTR_ERR(ioctx);
	if (!IS_ERR(ioctx)) {
		/* truncating is ok because it's a user address */
		ret = put_user((u32)ioctx->user_id, ctx32p);
		if (ret)
			kill_ioctx(current->mm, ioctx, NULL);
		percpu_ref_put(&ioctx->users);
	}

out:
	return ret;
}
#endif

/* sys_io_destroy:
 *	Destroy the aio_context specified.  May cancel any outstanding 
 *	AIOs and block on completion.  Will fail with -ENOSYS if not
 *	implemented.  May fail with -EINVAL if the context pointed to
 *	is invalid.
 */
SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
{
	struct kioctx *ioctx = lookup_ioctx(ctx);
	if (likely(NULL != ioctx)) {
		struct ctx_rq_wait wait;
		int ret;

		init_completion(&wait.comp);
		atomic_set(&wait.count, 1);

		/* Pass requests_done to kill_ioctx() where it can be set
		 * in a thread-safe way. If we try to set it here then we have
		 * a race condition if two io_destroy() called simultaneously.
		 */
		ret = kill_ioctx(current->mm, ioctx, &wait);
		percpu_ref_put(&ioctx->users);

		/* Wait until all IO for the context are done. Otherwise kernel
		 * keep using user-space buffers even if user thinks the context
		 * is destroyed.
		 */
		if (!ret)
			wait_for_completion(&wait.comp);

		return ret;
	}
	pr_debug("EINVAL: invalid context id\n");
	return -EINVAL;
}

static void aio_remove_iocb(struct aio_kiocb *iocb)
{
	struct kioctx *ctx = iocb->ki_ctx;
	unsigned long flags;

	spin_lock_irqsave(&ctx->ctx_lock, flags);
	list_del(&iocb->ki_list);
	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
}

static void aio_complete_rw(struct kiocb *kiocb, long res)
{
	struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw);

	if (!list_empty_careful(&iocb->ki_list))
		aio_remove_iocb(iocb);

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

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

	iocb->ki_res.res = res;
	iocb->ki_res.res2 = 0;
	iocb_put(iocb);
}

static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
{
	int ret;

	req->ki_complete = aio_complete_rw;
	req->private = NULL;
	req->ki_pos = iocb->aio_offset;
	req->ki_flags = req->ki_filp->f_iocb_flags;
	if (iocb->aio_flags & IOCB_FLAG_RESFD)
		req->ki_flags |= IOCB_EVENTFD;
	if (iocb->aio_flags & IOCB_FLAG_IOPRIO) {
		/*
		 * If the IOCB_FLAG_IOPRIO flag of aio_flags is set, then
		 * aio_reqprio is interpreted as an I/O scheduling
		 * class and priority.
		 */
		ret = ioprio_check_cap(iocb->aio_reqprio);
		if (ret) {
			pr_debug("aio ioprio check cap error: %d\n", ret);
			return ret;
		}

		req->ki_ioprio = iocb->aio_reqprio;
	} else
		req->ki_ioprio = get_current_ioprio();

	ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
	if (unlikely(ret))
		return ret;

	req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */
	return 0;
}

static ssize_t aio_setup_rw(int rw, const struct iocb *iocb,
		struct iovec **iovec, bool vectored, bool compat,
		struct iov_iter *iter)
{
	void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf;
	size_t len = iocb->aio_nbytes;

	if (!vectored) {
		ssize_t ret = import_single_range(rw, buf, len, *iovec, iter);
		*iovec = NULL;
		return ret;
	}

	return __import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter, compat);
}

static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
{
	switch (ret) {
	case -EIOCBQUEUED:
		break;
	case -ERESTARTSYS:
	case -ERESTARTNOINTR:
	case -ERESTARTNOHAND:
	case -ERESTART_RESTARTBLOCK:
		/*
		 * There's no easy way to restart the syscall since other AIO's
		 * may be already running. Just fail this IO with EINTR.
		 */
		ret = -EINTR;
		fallthrough;
	default:
		req->ki_complete(req, ret);
	}
}

static int aio_read(struct kiocb *req, const struct iocb *iocb,
			bool vectored, bool compat)
{
	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
	struct iov_iter iter;
	struct file *file;
	int ret;

	ret = aio_prep_rw(req, iocb);
	if (ret)
		return ret;
	file = req->ki_filp;
	if (unlikely(!(file->f_mode & FMODE_READ)))
		return -EBADF;
	if (unlikely(!file->f_op->read_iter))
		return -EINVAL;

	ret = aio_setup_rw(ITER_DEST, iocb, &iovec, vectored, compat, &iter);
	if (ret < 0)
		return ret;
	ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
	if (!ret)
		aio_rw_done(req, call_read_iter(file, req, &iter));
	kfree(iovec);
	return ret;
}

static int aio_write(struct kiocb *req, const struct iocb *iocb,
			 bool vectored, bool compat)
{
	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
	struct iov_iter iter;
	struct file *file;
	int ret;

	ret = aio_prep_rw(req, iocb);
	if (ret)
		return ret;
	file = req->ki_filp;

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

	ret = aio_setup_rw(ITER_SOURCE, iocb, &iovec, vectored, compat, &iter);
	if (ret < 0)
		return ret;
	ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
	if (!ret) {
		/*
		 * Open-code file_start_write here to grab freeze protection,
		 * which will be released by another thread in
		 * aio_complete_rw().  Fool lockdep by telling it the lock got
		 * released so that it doesn't complain about the held lock when
		 * we return to userspace.
		 */
		if (S_ISREG(file_inode(file)->i_mode)) {
			sb_start_write(file_inode(file)->i_sb);
			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
		}
		req->ki_flags |= IOCB_WRITE;
		aio_rw_done(req, call_write_iter(file, req, &iter));
	}
	kfree(iovec);
	return ret;
}

static void aio_fsync_work(struct work_struct *work)
{
	struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work);
	const struct cred *old_cred = override_creds(iocb->fsync.creds);

	iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync);
	revert_creds(old_cred);
	put_cred(iocb->fsync.creds);
	iocb_put(iocb);
}

static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
		     bool datasync)
{
	if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
			iocb->aio_rw_flags))
		return -EINVAL;

	if (unlikely(!req->file->f_op->fsync))
		return -EINVAL;

	req->creds = prepare_creds();
	if (!req->creds)
		return -ENOMEM;

	req->datasync = datasync;
	INIT_WORK(&req->work, aio_fsync_work);
	schedule_work(&req->work);
	return 0;
}

static void aio_poll_put_work(struct work_struct *work)
{
	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);

	iocb_put(iocb);
}

/*
 * Safely lock the waitqueue which the request is on, synchronizing with the
 * case where the ->poll() provider decides to free its waitqueue early.
 *
 * Returns true on success, meaning that req->head->lock was locked, req->wait
 * is on req->head, and an RCU read lock was taken.  Returns false if the
 * request was already removed from its waitqueue (which might no longer exist).
 */
static bool poll_iocb_lock_wq(struct poll_iocb *req)
{
	wait_queue_head_t *head;

	/*
	 * 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, then check whether the request is still on the queue.
	 *
	 * 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();
	head = smp_load_acquire(&req->head);
	if (head) {
		spin_lock(&head->lock);
		if (!list_empty(&req->wait.entry))
			return true;
		spin_unlock(&head->lock);
	}
	rcu_read_unlock();
	return false;
}

static void poll_iocb_unlock_wq(struct poll_iocb *req)
{
	spin_unlock(&req->head->lock);
	rcu_read_unlock();
}

static void aio_poll_complete_work(struct work_struct *work)
{
	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
	struct poll_table_struct pt = { ._key = req->events };
	struct kioctx *ctx = iocb->ki_ctx;
	__poll_t mask = 0;

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

	/*
	 * Note that ->ki_cancel callers also delete iocb from active_reqs after
	 * calling ->ki_cancel.  We need the ctx_lock roundtrip here to
	 * synchronize with them.  In the cancellation case the list_del_init
	 * itself is not actually needed, but harmless so we keep it in to
	 * avoid further branches in the fast path.
	 */
	spin_lock_irq(&ctx->ctx_lock);
	if (poll_iocb_lock_wq(req)) {
		if (!mask && !READ_ONCE(req->cancelled)) {
			/*
			 * The request isn't actually ready to be completed yet.
			 * Reschedule completion if another wakeup came in.
			 */
			if (req->work_need_resched) {
				schedule_work(&req->work);
				req->work_need_resched = false;
			} else {
				req->work_scheduled = false;
			}
			poll_iocb_unlock_wq(req);
			spin_unlock_irq(&ctx->ctx_lock);
			return;
		}
		list_del_init(&req->wait.entry);
		poll_iocb_unlock_wq(req);
	} /* else, POLLFREE has freed the waitqueue, so we must complete */
	list_del_init(&iocb->ki_list);
	iocb->ki_res.res = mangle_poll(mask);
	spin_unlock_irq(&ctx->ctx_lock);

	iocb_put(iocb);
}

/* assumes we are called with irqs disabled */
static int aio_poll_cancel(struct kiocb *iocb)
{
	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
	struct poll_iocb *req = &aiocb->poll;

	if (poll_iocb_lock_wq(req)) {
		WRITE_ONCE(req->cancelled, true);
		if (!req->work_scheduled) {
			schedule_work(&aiocb->poll.work);
			req->work_scheduled = true;
		}
		poll_iocb_unlock_wq(req);
	} /* else, the request was force-cancelled by POLLFREE already */

	return 0;
}

static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
		void *key)
{
	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
	__poll_t mask = key_to_poll(key);
	unsigned long flags;

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

	/*
	 * Complete the request inline if possible.  This requires that three
	 * conditions be met:
	 *   1. An event mask must have been passed.  If a plain wakeup was done
	 *	instead, then mask == 0 and we have to call vfs_poll() to get
	 *	the events, so inline completion isn't possible.
	 *   2. The completion work must not have already been scheduled.
	 *   3. ctx_lock must not be busy.  We have to use trylock because we
	 *	already hold the waitqueue lock, so this inverts the normal
	 *	locking order.  Use irqsave/irqrestore because not all
	 *	filesystems (e.g. fuse) call this function with IRQs disabled,
	 *	yet IRQs have to be disabled before ctx_lock is obtained.
	 */
	if (mask && !req->work_scheduled &&
	    spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
		struct kioctx *ctx = iocb->ki_ctx;

		list_del_init(&req->wait.entry);
		list_del(&iocb->ki_list);
		iocb->ki_res.res = mangle_poll(mask);
		if (iocb->ki_eventfd && !eventfd_signal_allowed()) {
			iocb = NULL;
			INIT_WORK(&req->work, aio_poll_put_work);
			schedule_work(&req->work);
		}
		spin_unlock_irqrestore(&ctx->ctx_lock, flags);
		if (iocb)
			iocb_put(iocb);
	} else {
		/*
		 * Schedule the completion work if needed.  If it was already
		 * scheduled, record that another wakeup came in.
		 *
		 * Don't remove the request from the waitqueue here, as it might
		 * not actually be complete yet (we won't know until vfs_poll()
		 * is called), and we must not miss any wakeups.  POLLFREE is an
		 * exception to this; see below.
		 */
		if (req->work_scheduled) {
			req->work_need_resched = true;
		} else {
			schedule_work(&req->work);
			req->work_scheduled = true;
		}

		/*
		 * If the waitqueue is being freed early but we can't complete
		 * the request inline, 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.  We also need to schedule the
		 * completion work (done above).  Also mark the request as
		 * cancelled, to potentially skip an unneeded call to ->poll().
		 */
		if (mask & POLLFREE) {
			WRITE_ONCE(req->cancelled, true);
			list_del_init(&req->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(&req->head, NULL);
		}
	}
	return 1;
}

struct aio_poll_table {
	struct poll_table_struct	pt;
	struct aio_kiocb		*iocb;
	bool				queued;
	int				error;
};

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

	/* multiple wait queues per file are not supported */
	if (unlikely(pt->queued)) {
		pt->error = -EINVAL;
		return;
	}

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

static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
{
	struct kioctx *ctx = aiocb->ki_ctx;
	struct poll_iocb *req = &aiocb->poll;
	struct aio_poll_table apt;
	bool cancel = false;
	__poll_t mask;

	/* reject any unknown events outside the normal event mask. */
	if ((u16)iocb->aio_buf != iocb->aio_buf)
		return -EINVAL;
	/* reject fields that are not defined for poll */
	if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
		return -EINVAL;

	INIT_WORK(&req->work, aio_poll_complete_work);
	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;

	req->head = NULL;
	req->cancelled = false;
	req->work_scheduled = false;
	req->work_need_resched = false;

	apt.pt._qproc = aio_poll_queue_proc;
	apt.pt._key = req->events;
	apt.iocb = aiocb;
	apt.queued = false;
	apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */

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

	mask = vfs_poll(req->file, &apt.pt) & req->events;
	spin_lock_irq(&ctx->ctx_lock);
	if (likely(apt.queued)) {
		bool on_queue = poll_iocb_lock_wq(req);

		if (!on_queue || req->work_scheduled) {
			/*
			 * aio_poll_wake() already either scheduled the async
			 * completion work, or completed the request inline.
			 */
			if (apt.error) /* unsupported case: multiple queues */
				cancel = true;
			apt.error = 0;
			mask = 0;
		}
		if (mask || apt.error) {
			/* Steal to complete synchronously. */
			list_del_init(&req->wait.entry);
		} else if (cancel) {
			/* Cancel if possible (may be too late though). */
			WRITE_ONCE(req->cancelled, true);
		} else if (on_queue) {
			/*
			 * Actually waiting for an event, so add the request to
			 * active_reqs so that it can be cancelled if needed.
			 */
			list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
			aiocb->ki_cancel = aio_poll_cancel;
		}
		if (on_queue)
			poll_iocb_unlock_wq(req);
	}
	if (mask) { /* no async, we'd stolen it */
		aiocb->ki_res.res = mangle_poll(mask);
		apt.error = 0;
	}
	spin_unlock_irq(&ctx->ctx_lock);
	if (mask)
		iocb_put(aiocb);
	return apt.error;
}

static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
			   struct iocb __user *user_iocb, struct aio_kiocb *req,
			   bool compat)
{
	req->ki_filp = fget(iocb->aio_fildes);
	if (unlikely(!req->ki_filp))
		return -EBADF;

	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
		struct eventfd_ctx *eventfd;
		/*
		 * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
		 * instance of the file* now. The file descriptor must be
		 * an eventfd() fd, and will be signaled for each completed
		 * event using the eventfd_signal() function.
		 */
		eventfd = eventfd_ctx_fdget(iocb->aio_resfd);
		if (IS_ERR(eventfd))
			return PTR_ERR(eventfd);

		req->ki_eventfd = eventfd;
	}

	if (unlikely(put_user(KIOCB_KEY, &user_iocb->aio_key))) {
		pr_debug("EFAULT: aio_key\n");
		return -EFAULT;
	}

	req->ki_res.obj = (u64)(unsigned long)user_iocb;
	req->ki_res.data = iocb->aio_data;
	req->ki_res.res = 0;
	req->ki_res.res2 = 0;

	switch (iocb->aio_lio_opcode) {
	case IOCB_CMD_PREAD:
		return aio_read(&req->rw, iocb, false, compat);
	case IOCB_CMD_PWRITE:
		return aio_write(&req->rw, iocb, false, compat);
	case IOCB_CMD_PREADV:
		return aio_read(&req->rw, iocb, true, compat);
	case IOCB_CMD_PWRITEV:
		return aio_write(&req->rw, iocb, true, compat);
	case IOCB_CMD_FSYNC:
		return aio_fsync(&req->fsync, iocb, false);
	case IOCB_CMD_FDSYNC:
		return aio_fsync(&req->fsync, iocb, true);
	case IOCB_CMD_POLL:
		return aio_poll(req, iocb);
	default:
		pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
		return -EINVAL;
	}
}

static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
			 bool compat)
{
	struct aio_kiocb *req;
	struct iocb iocb;
	int err;

	if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
		return -EFAULT;

	/* enforce forwards compatibility on users */
	if (unlikely(iocb.aio_reserved2)) {
		pr_debug("EINVAL: reserve field set\n");
		return -EINVAL;
	}

	/* prevent overflows */
	if (unlikely(
	    (iocb.aio_buf != (unsigned long)iocb.aio_buf) ||
	    (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) ||
	    ((ssize_t)iocb.aio_nbytes < 0)
	   )) {
		pr_debug("EINVAL: overflow check\n");
		return -EINVAL;
	}

	req = aio_get_req(ctx);
	if (unlikely(!req))
		return -EAGAIN;

	err = __io_submit_one(ctx, &iocb, user_iocb, req, compat);

	/* Done with the synchronous reference */
	iocb_put(req);

	/*
	 * If err is 0, we'd either done aio_complete() ourselves or have
	 * arranged for that to be done asynchronously.  Anything non-zero
	 * means that we need to destroy req ourselves.
	 */
	if (unlikely(err)) {
		iocb_destroy(req);
		put_reqs_available(ctx, 1);
	}
	return err;
}

/* sys_io_submit:
 *	Queue the nr iocbs pointed to by iocbpp for processing.  Returns
 *	the number of iocbs queued.  May return -EINVAL if the aio_context
 *	specified by ctx_id is invalid, if nr is < 0, if the iocb at
 *	*iocbpp[0] is not properly initialized, if the operation specified
 *	is invalid for the file descriptor in the iocb.  May fail with
 *	-EFAULT if any of the data structures point to invalid data.  May
 *	fail with -EBADF if the file descriptor specified in the first
 *	iocb is invalid.  May fail with -EAGAIN if insufficient resources
 *	are available to queue any iocbs.  Will return 0 if nr is 0.  Will
 *	fail with -ENOSYS if not implemented.
 */
SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
		struct iocb __user * __user *, iocbpp)
{
	struct kioctx *ctx;
	long ret = 0;
	int i = 0;
	struct blk_plug plug;

	if (unlikely(nr < 0))
		return -EINVAL;

	ctx = lookup_ioctx(ctx_id);
	if (unlikely(!ctx)) {
		pr_debug("EINVAL: invalid context id\n");
		return -EINVAL;
	}

	if (nr > ctx->nr_events)
		nr = ctx->nr_events;

	if (nr > AIO_PLUG_THRESHOLD)
		blk_start_plug(&plug);
	for (i = 0; i < nr; i++) {
		struct iocb __user *user_iocb;

		if (unlikely(get_user(user_iocb, iocbpp + i))) {
			ret = -EFAULT;
			break;
		}

		ret = io_submit_one(ctx, user_iocb, false);
		if (ret)
			break;
	}
	if (nr > AIO_PLUG_THRESHOLD)
		blk_finish_plug(&plug);

	percpu_ref_put(&ctx->users);
	return i ? i : ret;
}

#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
		       int, nr, compat_uptr_t __user *, iocbpp)
{
	struct kioctx *ctx;
	long ret = 0;
	int i = 0;
	struct blk_plug plug;

	if (unlikely(nr < 0))
		return -EINVAL;

	ctx = lookup_ioctx(ctx_id);
	if (unlikely(!ctx)) {
		pr_debug("EINVAL: invalid context id\n");
		return -EINVAL;
	}

	if (nr > ctx->nr_events)
		nr = ctx->nr_events;

	if (nr > AIO_PLUG_THRESHOLD)
		blk_start_plug(&plug);
	for (i = 0; i < nr; i++) {
		compat_uptr_t user_iocb;

		if (unlikely(get_user(user_iocb, iocbpp + i))) {
			ret = -EFAULT;
			break;
		}

		ret = io_submit_one(ctx, compat_ptr(user_iocb), true);
		if (ret)
			break;
	}
	if (nr > AIO_PLUG_THRESHOLD)
		blk_finish_plug(&plug);

	percpu_ref_put(&ctx->users);
	return i ? i : ret;
}
#endif

/* sys_io_cancel:
 *	Attempts to cancel an iocb previously passed to io_submit.  If
 *	the operation is successfully cancelled, the resulting event is
 *	copied into the memory pointed to by result without being placed
 *	into the completion queue and 0 is returned.  May fail with
 *	-EFAULT if any of the data structures pointed to are invalid.
 *	May fail with -EINVAL if aio_context specified by ctx_id is
 *	invalid.  May fail with -EAGAIN if the iocb specified was not
 *	cancelled.  Will fail with -ENOSYS if not implemented.
 */
SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
		struct io_event __user *, result)
{
	struct kioctx *ctx;
	struct aio_kiocb *kiocb;
	int ret = -EINVAL;
	u32 key;
	u64 obj = (u64)(unsigned long)iocb;

	if (unlikely(get_user(key, &iocb->aio_key)))
		return -EFAULT;
	if (unlikely(key != KIOCB_KEY))
		return -EINVAL;

	ctx = lookup_ioctx(ctx_id);
	if (unlikely(!ctx))
		return -EINVAL;

	spin_lock_irq(&ctx->ctx_lock);
	/* TODO: use a hash or array, this sucks. */
	list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
		if (kiocb->ki_res.obj == obj) {
			ret = kiocb->ki_cancel(&kiocb->rw);
			list_del_init(&kiocb->ki_list);
			break;
		}
	}
	spin_unlock_irq(&ctx->ctx_lock);

	if (!ret) {
		/*
		 * The result argument is no longer used - the io_event is
		 * always delivered via the ring buffer. -EINPROGRESS indicates
		 * cancellation is progress:
		 */
		ret = -EINPROGRESS;
	}

	percpu_ref_put(&ctx->users);

	return ret;
}

static long do_io_getevents(aio_context_t ctx_id,
		long min_nr,
		long nr,
		struct io_event __user *events,
		struct timespec64 *ts)
{
	ktime_t until = ts ? timespec64_to_ktime(*ts) : KTIME_MAX;
	struct kioctx *ioctx = lookup_ioctx(ctx_id);
	long ret = -EINVAL;

	if (likely(ioctx)) {
		if (likely(min_nr <= nr && min_nr >= 0))
			ret = read_events(ioctx, min_nr, nr, events, until);
		percpu_ref_put(&ioctx->users);
	}

	return ret;
}

/* io_getevents:
 *	Attempts to read at least min_nr events and up to nr events from
 *	the completion queue for the aio_context specified by ctx_id. If
 *	it succeeds, the number of read events is returned. May fail with
 *	-EINVAL if ctx_id is invalid, if min_nr is out of range, if nr is
 *	out of range, if timeout is out of range.  May fail with -EFAULT
 *	if any of the memory specified is invalid.  May return 0 or
 *	< min_nr if the timeout specified by timeout has elapsed
 *	before sufficient events are available, where timeout == NULL
 *	specifies an infinite timeout. Note that the timeout pointed to by
 *	timeout is relative.  Will fail with -ENOSYS if not implemented.
 */
#ifdef CONFIG_64BIT

SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
		long, min_nr,
		long, nr,
		struct io_event __user *, events,
		struct __kernel_timespec __user *, timeout)
{
	struct timespec64	ts;
	int			ret;

	if (timeout && unlikely(get_timespec64(&ts, timeout)))
		return -EFAULT;

	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
	if (!ret && signal_pending(current))
		ret = -EINTR;
	return ret;
}

#endif

struct __aio_sigset {
	const sigset_t __user	*sigmask;
	size_t		sigsetsize;
};

SYSCALL_DEFINE6(io_pgetevents,
		aio_context_t, ctx_id,
		long, min_nr,
		long, nr,
		struct io_event __user *, events,
		struct __kernel_timespec __user *, timeout,
		const struct __aio_sigset __user *, usig)
{
	struct __aio_sigset	ksig = { NULL, };
	struct timespec64	ts;
	bool interrupted;
	int ret;

	if (timeout && unlikely(get_timespec64(&ts, timeout)))
		return -EFAULT;

	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
		return -EFAULT;

	ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize);
	if (ret)
		return ret;

	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);

	interrupted = signal_pending(current);
	restore_saved_sigmask_unless(interrupted);
	if (interrupted && !ret)
		ret = -ERESTARTNOHAND;

	return ret;
}

#if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT)

SYSCALL_DEFINE6(io_pgetevents_time32,
		aio_context_t, ctx_id,
		long, min_nr,
		long, nr,
		struct io_event __user *, events,
		struct old_timespec32 __user *, timeout,
		const struct __aio_sigset __user *, usig)
{
	struct __aio_sigset	ksig = { NULL, };
	struct timespec64	ts;
	bool interrupted;
	int ret;

	if (timeout && unlikely(get_old_timespec32(&ts, timeout)))
		return -EFAULT;

	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
		return -EFAULT;


	ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize);
	if (ret)
		return ret;

	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);

	interrupted = signal_pending(current);
	restore_saved_sigmask_unless(interrupted);
	if (interrupted && !ret)
		ret = -ERESTARTNOHAND;

	return ret;
}

#endif

#if defined(CONFIG_COMPAT_32BIT_TIME)

SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id,
		__s32, min_nr,
		__s32, nr,
		struct io_event __user *, events,
		struct old_timespec32 __user *, timeout)
{
	struct timespec64 t;
	int ret;

	if (timeout && get_old_timespec32(&t, timeout))
		return -EFAULT;

	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
	if (!ret && signal_pending(current))
		ret = -EINTR;
	return ret;
}

#endif

#ifdef CONFIG_COMPAT

struct __compat_aio_sigset {
	compat_uptr_t		sigmask;
	compat_size_t		sigsetsize;
};

#if defined(CONFIG_COMPAT_32BIT_TIME)

COMPAT_SYSCALL_DEFINE6(io_pgetevents,
		compat_aio_context_t, ctx_id,
		compat_long_t, min_nr,
		compat_long_t, nr,
		struct io_event __user *, events,
		struct old_timespec32 __user *, timeout,
		const struct __compat_aio_sigset __user *, usig)
{
	struct __compat_aio_sigset ksig = { 0, };
	struct timespec64 t;
	bool interrupted;
	int ret;

	if (timeout && get_old_timespec32(&t, timeout))
		return -EFAULT;

	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
		return -EFAULT;

	ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize);
	if (ret)
		return ret;

	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);

	interrupted = signal_pending(current);
	restore_saved_sigmask_unless(interrupted);
	if (interrupted && !ret)
		ret = -ERESTARTNOHAND;

	return ret;
}

#endif

COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64,
		compat_aio_context_t, ctx_id,
		compat_long_t, min_nr,
		compat_long_t, nr,
		struct io_event __user *, events,
		struct __kernel_timespec __user *, timeout,
		const struct __compat_aio_sigset __user *, usig)
{
	struct __compat_aio_sigset ksig = { 0, };
	struct timespec64 t;
	bool interrupted;
	int ret;

	if (timeout && get_timespec64(&t, timeout))
		return -EFAULT;

	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
		return -EFAULT;

	ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize);
	if (ret)
		return ret;

	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);

	interrupted = signal_pending(current);
	restore_saved_sigmask_unless(interrupted);
	if (interrupted && !ret)
		ret = -ERESTARTNOHAND;

	return ret;
}
#endif