fs/aio.c



1da177e4c3f4


630d9c47274a
1da177e4c3f4
b9d128f1088e
027445c37282
1da177e4c3f4


3d2d827f5ca5
1da177e4c3f4


9c3060bedd84
cfb1e33eed48
9d85cba718ef
1da177e4c3f4


1da177e4c3f4


1da177e4c3f4
d55b5fdaf408


1da177e4c3f4

e18b890bb088

1da177e4c3f4


65f27f38446e

1da177e4c3f4

25ee7e383295
1da177e4c3f4
65f27f38446e
c016e2257acd
1da177e4c3f4


0a31bd5f2bbb

1da177e4c3f4
d37adaa15962
cf15900e1209
1da177e4c3f4


385773e04806
1da177e4c3f4


11b0b5abb209
1da177e4c3f4

1da177e4c3f4


e10a4437cb37
1da177e4c3f4


1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4

e8e3c3d66fd9
1da177e4c3f4

abf137dd7712


abf137dd7712
abf137dd7712
d5470b596abd


2dd542b7aeb1
d5470b596abd

bf50722a3c4a
d5470b596abd


2dd542b7aeb1


d5470b596abd
abf137dd7712
d5470b596abd

3bd9a5d734c7


d5470b596abd
1da177e4c3f4


e23754f880f1
1da177e4c3f4


2dd542b7aeb1
1da177e4c3f4

c376222960ae
1da177e4c3f4


1da177e4c3f4


86b62a2cb4fc
1da177e4c3f4


65f27f38446e
1da177e4c3f4


9fa1cb397fa0
2dd542b7aeb1

9fa1cb397fa0
1da177e4c3f4
2dd542b7aeb1

9fa1cb397fa0
1da177e4c3f4
39fa00311f21
abf137dd7712


1da177e4c3f4


e23754f880f1

1da177e4c3f4


e23754f880f1

1da177e4c3f4


25ee7e383295
1da177e4c3f4


dee11c2364f5
1da177e4c3f4
dee11c2364f5
1da177e4c3f4


dee11c2364f5
41d10da37174
1da177e4c3f4
dee11c2364f5
1da177e4c3f4


dee11c2364f5


1da177e4c3f4


fc9b52cd8f5f
1da177e4c3f4


41d10da37174
1da177e4c3f4


385773e04806
1da177e4c3f4


fc9b52cd8f5f
1da177e4c3f4
abf137dd7712


1da177e4c3f4


1da177e4c3f4


1da177e4c3f4


1da177e4c3f4


fc9b52cd8f5f
1da177e4c3f4

1da177e4c3f4


4faa5285283f
1da177e4c3f4


1da177e4c3f4

eed4e51fb60c
1da177e4c3f4
87c3a86e1c22
1da177e4c3f4
080d676de095


69e4747ee972
080d676de095


69e4747ee972


080d676de095

69e4747ee972
080d676de095
69e4747ee972
080d676de095
880641bb9da2

69e4747ee972
080d676de095


1da177e4c3f4
080d676de095


1da177e4c3f4
1da177e4c3f4
1da177e4c3f4
1da177e4c3f4
080d676de095

1da177e4c3f4
080d676de095

1da177e4c3f4

080d676de095

1da177e4c3f4

080d676de095


1da177e4c3f4


d00689af6b3b

133890103b9d

1da177e4c3f4

eed4e51fb60c

1da177e4c3f4


e91f90bb0bb1
1da177e4c3f4

65f27f38446e
1da177e4c3f4


87c3a86e1c22

d7065da03822
1da177e4c3f4

c7b285550544
1da177e4c3f4

c7b285550544


1da177e4c3f4
c7b285550544
1da177e4c3f4
1da177e4c3f4


516e0cc5646f

1da177e4c3f4
d00689af6b3b

87c3a86e1c22
93e06b4140cc
1da177e4c3f4


87c3a86e1c22

d7065da03822
87c3a86e1c22

1da177e4c3f4
d7065da03822
1da177e4c3f4


d37adaa15962
133890103b9d

1da177e4c3f4
133890103b9d
1da177e4c3f4


fc9b52cd8f5f
1da177e4c3f4


1da177e4c3f4

385773e04806
1da177e4c3f4
d5470b596abd
1da177e4c3f4
abf137dd7712
65c24491b4fe
abf137dd7712
1da177e4c3f4
abf137dd7712


3bd9a5d734c7


65c24491b4fe
1da177e4c3f4

abf137dd7712
1da177e4c3f4
abf137dd7712
65c24491b4fe
1da177e4c3f4


1da177e4c3f4


1da177e4c3f4


d00689af6b3b

1da177e4c3f4


1da177e4c3f4


d6e05edc59ec
1da177e4c3f4


1da177e4c3f4


6212e3a388fd
1da177e4c3f4
1da177e4c3f4
1da177e4c3f4
a0c42bac7973


897f15fb587f
a0c42bac7973
1da177e4c3f4


c016e2257acd


1da177e4c3f4


d00689af6b3b
1da177e4c3f4


626ab0e69d37
1da177e4c3f4
d00689af6b3b

626ab0e69d37
1da177e4c3f4


dee11c2364f5
1da177e4c3f4
1da177e4c3f4


1da177e4c3f4
d3486f8b9eeb


1da177e4c3f4


65f27f38446e
1da177e4c3f4
65f27f38446e
1da177e4c3f4
1ebb1101c556
1da177e4c3f4


1ebb1101c556
1da177e4c3f4
1ebb1101c556
1da177e4c3f4

9fcf03d0d6e8
1da177e4c3f4

52bad64d95bd
1da177e4c3f4


998765e5588b
1da177e4c3f4


1da177e4c3f4
998765e5588b


1da177e4c3f4
644d3a088a3b
1da177e4c3f4
1da177e4c3f4


fac046ad0b1e
1da177e4c3f4


fc9b52cd8f5f
1da177e4c3f4


998765e5588b
1da177e4c3f4


fc9b52cd8f5f
1da177e4c3f4


20dcae324393


1da177e4c3f4

20dcae324393
1da177e4c3f4
20dcae324393
1da177e4c3f4
20dcae324393
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4

e8e3c3d66fd9
4bf69b2a0609

1da177e4c3f4


e8e3c3d66fd9

1da177e4c3f4

8d1c98b0b5c0


87c3a86e1c22
8d1c98b0b5c0

1da177e4c3f4


6cb2a21049b8


1da177e4c3f4


dee11c2364f5
1da177e4c3f4

385773e04806
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4


e8e3c3d66fd9
1da177e4c3f4


c6f3a97f86a5
1da177e4c3f4


1da177e4c3f4


e92adcba261f


1da177e4c3f4

e00ba3dae077


1da177e4c3f4


c6f3a97f86a5
1da177e4c3f4


1da177e4c3f4


abf137dd7712
1da177e4c3f4

abf137dd7712

1da177e4c3f4


e92adcba261f


e91f90bb0bb1
1da177e4c3f4


002c8976ee53
1da177e4c3f4


d55b5fdaf408


1da177e4c3f4


86b62a2cb4fc

1da177e4c3f4
86b62a2cb4fc
1da177e4c3f4


642b5123ac5e
1da177e4c3f4

002c8976ee53
1da177e4c3f4


eed4e51fb60c
1da177e4c3f4
eed4e51fb60c


897f15fb587f
eed4e51fb60c
1da177e4c3f4
eed4e51fb60c


1da177e4c3f4

eed4e51fb60c
1da177e4c3f4

eed4e51fb60c


1da177e4c3f4
eed4e51fb60c


1da177e4c3f4
c2ec66828fd2


897f15fb587f
eed4e51fb60c


1da177e4c3f4
eed4e51fb60c

1da177e4c3f4


7adfa2ff3efa


1da177e4c3f4


9d85cba718ef
eed4e51fb60c


9d85cba718ef


fcf634098c00
9d85cba718ef


fcf634098c00
eed4e51fb60c


eed4e51fb60c


1da177e4c3f4


9d85cba718ef
1da177e4c3f4


8766ce41018a


eed4e51fb60c


1da177e4c3f4

eed4e51fb60c
1da177e4c3f4


8766ce41018a


eed4e51fb60c


9d85cba718ef
eed4e51fb60c


9d85cba718ef
eed4e51fb60c

1da177e4c3f4

eed4e51fb60c
1da177e4c3f4


d5470b596abd
080d676de095

1da177e4c3f4


9c3060bedd84
1da177e4c3f4


080d676de095
1da177e4c3f4


87e2831c3fa3
9c3060bedd84


133890103b9d
801678c5a3b4
9c3060bedd84
87c3a86e1c22
9c3060bedd84


1da177e4c3f4
212079cf4ee9
1da177e4c3f4


1da177e4c3f4
9d85cba718ef
1da177e4c3f4


7137c6bd4552


ac0b1bc1edbe
ac0b1bc1edbe
954d3e95369c


1da177e4c3f4
cfb1e33eed48
1da177e4c3f4


9d85cba718ef

1da177e4c3f4


080d676de095
9f5b9425468c
080d676de095
1da177e4c3f4


75e1c70fc314


1da177e4c3f4


080d676de095

9f5b9425468c

1da177e4c3f4


080d676de095
1da177e4c3f4


9f5b9425468c
1da177e4c3f4
69e4747ee972
1da177e4c3f4


9d85cba718ef


1da177e4c3f4

1da177e4c3f4
25ee7e383295

1da177e4c3f4

d00689af6b3b


1da177e4c3f4


002c8976ee53

1da177e4c3f4


8f58202bf6b9
1da177e4c3f4


642b5123ac5e


1da177e4c3f4
002c8976ee53


1da177e4c3f4


2e41025598ea
1da177e4c3f4


598af051a79d
1da177e4c3f4


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


/*
 *	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.
 *
 *	See ../COPYING for licensing terms.
 */
#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/uio.h>

#define DEBUG 0

#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/mmu_context.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 <asm/kmap_types.h>
#include <asm/uaccess.h>

#if DEBUG > 1
#define dprintk		printk
#else
#define dprintk(x...)	do { ; } while (0)
#endif

/*------ sysctl variables----*/
static DEFINE_SPINLOCK(aio_nr_lock);
unsigned long aio_nr;		/* current system wide number of aio requests */
unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */
/*----end sysctl variables---*/

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

static struct workqueue_struct *aio_wq;

/* Used for rare fput completion. */
static void aio_fput_routine(struct work_struct *);
static DECLARE_WORK(fput_work, aio_fput_routine);

static DEFINE_SPINLOCK(fput_lock);
static LIST_HEAD(fput_head);

static void aio_kick_handler(struct work_struct *);
static void aio_queue_work(struct kioctx *);

/* 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)
{
	kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);

	aio_wq = alloc_workqueue("aio", 0, 1);	/* used to limit concurrency */
	BUG_ON(!aio_wq);

	pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page));

	return 0;
}
__initcall(aio_setup);

static void aio_free_ring(struct kioctx *ctx)
{
	struct aio_ring_info *info = &ctx->ring_info;
	long i;

	for (i=0; i<info->nr_pages; i++)
		put_page(info->ring_pages[i]);

	if (info->mmap_size) {
		down_write(&ctx->mm->mmap_sem);
		do_munmap(ctx->mm, info->mmap_base, info->mmap_size);
		up_write(&ctx->mm->mmap_sem);
	}

	if (info->ring_pages && info->ring_pages != info->internal_pages)
		kfree(info->ring_pages);
	info->ring_pages = NULL;
	info->nr = 0;
}

static int aio_setup_ring(struct kioctx *ctx)
{
	struct aio_ring *ring;
	struct aio_ring_info *info = &ctx->ring_info;
	unsigned nr_events = ctx->max_reqs;
	unsigned long size;
	int nr_pages;

	/* 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 = (size + PAGE_SIZE-1) >> PAGE_SHIFT;

	if (nr_pages < 0)
		return -EINVAL;

	nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event);

	info->nr = 0;
	info->ring_pages = info->internal_pages;
	if (nr_pages > AIO_RING_PAGES) {
		info->ring_pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
		if (!info->ring_pages)
			return -ENOMEM;
	}

	info->mmap_size = nr_pages * PAGE_SIZE;
	dprintk("attempting mmap of %lu bytes\n", info->mmap_size);
	down_write(&ctx->mm->mmap_sem);
	info->mmap_base = do_mmap(NULL, 0, info->mmap_size, 
				  PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE,
				  0);
	if (IS_ERR((void *)info->mmap_base)) {
		up_write(&ctx->mm->mmap_sem);
		info->mmap_size = 0;
		aio_free_ring(ctx);
		return -EAGAIN;
	}

	dprintk("mmap address: 0x%08lx\n", info->mmap_base);
	info->nr_pages = get_user_pages(current, ctx->mm,
					info->mmap_base, nr_pages, 
					1, 0, info->ring_pages, NULL);
	up_write(&ctx->mm->mmap_sem);

	if (unlikely(info->nr_pages != nr_pages)) {
		aio_free_ring(ctx);
		return -EAGAIN;
	}

	ctx->user_id = info->mmap_base;

	info->nr = nr_events;		/* trusted copy */

	ring = kmap_atomic(info->ring_pages[0]);
	ring->nr = nr_events;	/* user copy */
	ring->id = ctx->user_id;
	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);
	kunmap_atomic(ring);

	return 0;
}


/* aio_ring_event: returns a pointer to the event at the given index from
 * kmap_atomic().  Release the pointer with put_aio_ring_event();
 */
#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)

#define aio_ring_event(info, nr) ({					\
	unsigned pos = (nr) + AIO_EVENTS_OFFSET;			\
	struct io_event *__event;					\
	__event = kmap_atomic(						\
			(info)->ring_pages[pos / AIO_EVENTS_PER_PAGE]); \
	__event += pos % AIO_EVENTS_PER_PAGE;				\
	__event;							\
})

#define put_aio_ring_event(event) do {		\
	struct io_event *__event = (event);	\
	(void)__event;				\
	kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK)); \
} while(0)

static void ctx_rcu_free(struct rcu_head *head)
{
	struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
	kmem_cache_free(kioctx_cachep, ctx);
}

/* __put_ioctx
 *	Called when the last user of an aio context has gone away,
 *	and the struct needs to be freed.
 */
static void __put_ioctx(struct kioctx *ctx)
{
	unsigned nr_events = ctx->max_reqs;
	BUG_ON(ctx->reqs_active);

	cancel_delayed_work_sync(&ctx->wq);
	aio_free_ring(ctx);
	mmdrop(ctx->mm);
	ctx->mm = NULL;
	if (nr_events) {
		spin_lock(&aio_nr_lock);
		BUG_ON(aio_nr - nr_events > aio_nr);
		aio_nr -= nr_events;
		spin_unlock(&aio_nr_lock);
	}
	pr_debug("__put_ioctx: freeing %p\n", ctx);
	call_rcu(&ctx->rcu_head, ctx_rcu_free);
}

static inline int try_get_ioctx(struct kioctx *kioctx)
{
	return atomic_inc_not_zero(&kioctx->users);
}

static inline void put_ioctx(struct kioctx *kioctx)
{
	BUG_ON(atomic_read(&kioctx->users) <= 0);
	if (unlikely(atomic_dec_and_test(&kioctx->users)))
		__put_ioctx(kioctx);
}

/* 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;
	struct kioctx *ctx;
	int err = -ENOMEM;

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

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

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

	ctx->max_reqs = nr_events;
	mm = ctx->mm = current->mm;
	atomic_inc(&mm->mm_count);

	atomic_set(&ctx->users, 2);
	spin_lock_init(&ctx->ctx_lock);
	spin_lock_init(&ctx->ring_info.ring_lock);
	init_waitqueue_head(&ctx->wait);

	INIT_LIST_HEAD(&ctx->active_reqs);
	INIT_LIST_HEAD(&ctx->run_list);
	INIT_DELAYED_WORK(&ctx->wq, aio_kick_handler);

	if (aio_setup_ring(ctx) < 0)
		goto out_freectx;

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

	/* now link into global list. */
	spin_lock(&mm->ioctx_lock);
	hlist_add_head_rcu(&ctx->list, &mm->ioctx_list);
	spin_unlock(&mm->ioctx_lock);

	dprintk("aio: allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
		ctx, ctx->user_id, current->mm, ctx->ring_info.nr);
	return ctx;

out_cleanup:
	err = -EAGAIN;
	aio_free_ring(ctx);
out_freectx:
	mmdrop(mm);
	kmem_cache_free(kioctx_cachep, ctx);
	dprintk("aio: error allocating ioctx %d\n", err);
	return ERR_PTR(err);
}

/* aio_cancel_all
 *	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 void aio_cancel_all(struct kioctx *ctx)
{
	int (*cancel)(struct kiocb *, struct io_event *);
	struct io_event res;
	spin_lock_irq(&ctx->ctx_lock);
	ctx->dead = 1;
	while (!list_empty(&ctx->active_reqs)) {
		struct list_head *pos = ctx->active_reqs.next;
		struct kiocb *iocb = list_kiocb(pos);
		list_del_init(&iocb->ki_list);
		cancel = iocb->ki_cancel;
		kiocbSetCancelled(iocb);
		if (cancel) {
			iocb->ki_users++;
			spin_unlock_irq(&ctx->ctx_lock);
			cancel(iocb, &res);
			spin_lock_irq(&ctx->ctx_lock);
		}
	}
	spin_unlock_irq(&ctx->ctx_lock);
}

static void wait_for_all_aios(struct kioctx *ctx)
{
	struct task_struct *tsk = current;
	DECLARE_WAITQUEUE(wait, tsk);

	spin_lock_irq(&ctx->ctx_lock);
	if (!ctx->reqs_active)
		goto out;

	add_wait_queue(&ctx->wait, &wait);
	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
	while (ctx->reqs_active) {
		spin_unlock_irq(&ctx->ctx_lock);
		io_schedule();
		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
		spin_lock_irq(&ctx->ctx_lock);
	}
	__set_task_state(tsk, TASK_RUNNING);
	remove_wait_queue(&ctx->wait, &wait);

out:
	spin_unlock_irq(&ctx->ctx_lock);
}

/* wait_on_sync_kiocb:
 *	Waits on the given sync kiocb to complete.
 */
ssize_t wait_on_sync_kiocb(struct kiocb *iocb)
{
	while (iocb->ki_users) {
		set_current_state(TASK_UNINTERRUPTIBLE);
		if (!iocb->ki_users)
			break;
		io_schedule();
	}
	__set_current_state(TASK_RUNNING);
	return iocb->ki_user_data;
}
EXPORT_SYMBOL(wait_on_sync_kiocb);

/* 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.  However, there may be 
 * outstanding requests which hold references to the context; as they 
 * go away, they will call put_ioctx and release any pinned memory
 * associated with the request (held via struct page * references).
 */
void exit_aio(struct mm_struct *mm)
{
	struct kioctx *ctx;

	while (!hlist_empty(&mm->ioctx_list)) {
		ctx = hlist_entry(mm->ioctx_list.first, struct kioctx, list);
		hlist_del_rcu(&ctx->list);

		aio_cancel_all(ctx);

		wait_for_all_aios(ctx);

		if (1 != atomic_read(&ctx->users))
			printk(KERN_DEBUG
				"exit_aio:ioctx still alive: %d %d %d\n",
				atomic_read(&ctx->users), ctx->dead,
				ctx->reqs_active);
		put_ioctx(ctx);
	}
}

/* aio_get_req
 *	Allocate a slot for an aio request.  Increments the users count
 * of the kioctx so that the kioctx stays around until all requests are
 * complete.  Returns NULL if no requests are free.
 *
 * Returns with kiocb->users set to 2.  The io submit code path holds
 * an extra reference while submitting the i/o.
 * This prevents races between the aio code path referencing the
 * req (after submitting it) and aio_complete() freeing the req.
 */
static struct kiocb *__aio_get_req(struct kioctx *ctx)
{
	struct kiocb *req = NULL;

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

	req->ki_flags = 0;
	req->ki_users = 2;
	req->ki_key = 0;
	req->ki_ctx = ctx;
	req->ki_cancel = NULL;
	req->ki_retry = NULL;
	req->ki_dtor = NULL;
	req->private = NULL;
	req->ki_iovec = NULL;
	INIT_LIST_HEAD(&req->ki_run_list);
	req->ki_eventfd = NULL;

	return req;
}

/*
 * struct kiocb's are allocated in batches to reduce the number of
 * times the ctx lock is acquired and released.
 */
#define KIOCB_BATCH_SIZE	32L
struct kiocb_batch {
	struct list_head head;
	long count; /* number of requests left to allocate */
};

static void kiocb_batch_init(struct kiocb_batch *batch, long total)
{
	INIT_LIST_HEAD(&batch->head);
	batch->count = total;
}

static void kiocb_batch_free(struct kioctx *ctx, struct kiocb_batch *batch)
{
	struct kiocb *req, *n;

	if (list_empty(&batch->head))
		return;

	spin_lock_irq(&ctx->ctx_lock);
	list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
		list_del(&req->ki_batch);
		list_del(&req->ki_list);
		kmem_cache_free(kiocb_cachep, req);
		ctx->reqs_active--;
	}
	if (unlikely(!ctx->reqs_active && ctx->dead))
		wake_up_all(&ctx->wait);
	spin_unlock_irq(&ctx->ctx_lock);
}

/*
 * Allocate a batch of kiocbs.  This avoids taking and dropping the
 * context lock a lot during setup.
 */
static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch)
{
	unsigned short allocated, to_alloc;
	long avail;
	bool called_fput = false;
	struct kiocb *req, *n;
	struct aio_ring *ring;

	to_alloc = min(batch->count, KIOCB_BATCH_SIZE);
	for (allocated = 0; allocated < to_alloc; allocated++) {
		req = __aio_get_req(ctx);
		if (!req)
			/* allocation failed, go with what we've got */
			break;
		list_add(&req->ki_batch, &batch->head);
	}

	if (allocated == 0)
		goto out;

retry:
	spin_lock_irq(&ctx->ctx_lock);
	ring = kmap_atomic(ctx->ring_info.ring_pages[0]);

	avail = aio_ring_avail(&ctx->ring_info, ring) - ctx->reqs_active;
	BUG_ON(avail < 0);
	if (avail == 0 && !called_fput) {
		/*
		 * Handle a potential starvation case.  It is possible that
		 * we hold the last reference on a struct file, causing us
		 * to delay the final fput to non-irq context.  In this case,
		 * ctx->reqs_active is artificially high.  Calling the fput
		 * routine here may free up a slot in the event completion
		 * ring, allowing this allocation to succeed.
		 */
		kunmap_atomic(ring);
		spin_unlock_irq(&ctx->ctx_lock);
		aio_fput_routine(NULL);
		called_fput = true;
		goto retry;
	}

	if (avail < allocated) {
		/* Trim back the number of requests. */
		list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
			list_del(&req->ki_batch);
			kmem_cache_free(kiocb_cachep, req);
			if (--allocated <= avail)
				break;
		}
	}

	batch->count -= allocated;
	list_for_each_entry(req, &batch->head, ki_batch) {
		list_add(&req->ki_list, &ctx->active_reqs);
		ctx->reqs_active++;
	}

	kunmap_atomic(ring);
	spin_unlock_irq(&ctx->ctx_lock);

out:
	return allocated;
}

static inline struct kiocb *aio_get_req(struct kioctx *ctx,
					struct kiocb_batch *batch)
{
	struct kiocb *req;

	if (list_empty(&batch->head))
		if (kiocb_batch_refill(ctx, batch) == 0)
			return NULL;
	req = list_first_entry(&batch->head, struct kiocb, ki_batch);
	list_del(&req->ki_batch);
	return req;
}

static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
{
	assert_spin_locked(&ctx->ctx_lock);

	if (req->ki_eventfd != NULL)
		eventfd_ctx_put(req->ki_eventfd);
	if (req->ki_dtor)
		req->ki_dtor(req);
	if (req->ki_iovec != &req->ki_inline_vec)
		kfree(req->ki_iovec);
	kmem_cache_free(kiocb_cachep, req);
	ctx->reqs_active--;

	if (unlikely(!ctx->reqs_active && ctx->dead))
		wake_up_all(&ctx->wait);
}

static void aio_fput_routine(struct work_struct *data)
{
	spin_lock_irq(&fput_lock);
	while (likely(!list_empty(&fput_head))) {
		struct kiocb *req = list_kiocb(fput_head.next);
		struct kioctx *ctx = req->ki_ctx;

		list_del(&req->ki_list);
		spin_unlock_irq(&fput_lock);

		/* Complete the fput(s) */
		if (req->ki_filp != NULL)
			fput(req->ki_filp);

		/* Link the iocb into the context's free list */
		rcu_read_lock();
		spin_lock_irq(&ctx->ctx_lock);
		really_put_req(ctx, req);
		/*
		 * at that point ctx might've been killed, but actual
		 * freeing is RCU'd
		 */
		spin_unlock_irq(&ctx->ctx_lock);
		rcu_read_unlock();

		spin_lock_irq(&fput_lock);
	}
	spin_unlock_irq(&fput_lock);
}

/* __aio_put_req
 *	Returns true if this put was the last user of the request.
 */
static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
{
	dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n",
		req, atomic_long_read(&req->ki_filp->f_count));

	assert_spin_locked(&ctx->ctx_lock);

	req->ki_users--;
	BUG_ON(req->ki_users < 0);
	if (likely(req->ki_users))
		return 0;
	list_del(&req->ki_list);		/* remove from active_reqs */
	req->ki_cancel = NULL;
	req->ki_retry = NULL;

	/*
	 * Try to optimize the aio and eventfd file* puts, by avoiding to
	 * schedule work in case it is not final fput() time. In normal cases,
	 * we would not be holding the last reference to the file*, so
	 * this function will be executed w/out any aio kthread wakeup.
	 */
	if (unlikely(!fput_atomic(req->ki_filp))) {
		spin_lock(&fput_lock);
		list_add(&req->ki_list, &fput_head);
		spin_unlock(&fput_lock);
		schedule_work(&fput_work);
	} else {
		req->ki_filp = NULL;
		really_put_req(ctx, req);
	}
	return 1;
}

/* aio_put_req
 *	Returns true if this put was the last user of the kiocb,
 *	false if the request is still in use.
 */
int aio_put_req(struct kiocb *req)
{
	struct kioctx *ctx = req->ki_ctx;
	int ret;
	spin_lock_irq(&ctx->ctx_lock);
	ret = __aio_put_req(ctx, req);
	spin_unlock_irq(&ctx->ctx_lock);
	return ret;
}
EXPORT_SYMBOL(aio_put_req);

static struct kioctx *lookup_ioctx(unsigned long ctx_id)
{
	struct mm_struct *mm = current->mm;
	struct kioctx *ctx, *ret = NULL;
	struct hlist_node *n;

	rcu_read_lock();

	hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) {
		/*
		 * RCU protects us against accessing freed memory but
		 * we have to be careful not to get a reference when the
		 * reference count already dropped to 0 (ctx->dead test
		 * is unreliable because of races).
		 */