summaryrefslogtreecommitdiffstats
path: root/fs/aio.c
blob: 667054c7c0671afec4cc67af104db132a5a245b5 (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
/*
 *	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.
 */
#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/uio.h>

#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/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 <asm/kmap_types.h>
#include <asm/uaccess.h>

#include "internal.h"

#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[0];
}; /* 128 bytes + ring size */

#define AIO_RING_PAGES	8

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

struct kioctx_cpu {
	unsigned		reqs_available;
};

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 work_struct	free_work;

	/*
	 * signals when all in-flight requests are done
	 */
	struct completion *requests_done;

	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;
};

/*------ 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 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 qstr this = QSTR_INIT("[aio]", 5);
	struct file *file;
	struct path path;
	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;

	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
	if (!path.dentry) {
		iput(inode);
		return ERR_PTR(-ENOMEM);
	}
	path.mnt = mntget(aio_mnt);

	d_instantiate(path.dentry, inode);
	file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops);
	if (IS_ERR(file)) {
		path_put(&path);
		return file;
	}

	file->f_flags = O_RDWR;
	return file;
}

static struct dentry *aio_mount(struct file_system_type *fs_type,
				int flags, const char *dev_name, void *data)
{
	static const struct dentry_operations ops = {
		.d_dname	= simple_dname,
	};
	return mount_pseudo(fs_type, "aio:", NULL, &ops, AIO_RING_MAGIC);
}

/* 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",
		.mount		= aio_mount,
		.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(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);

	pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page));

	return 0;
}
__initcall(aio_setup);

static void put_aio_ring_file(struct kioctx *ctx)
{
	struct file *aio_ring_file = ctx->aio_ring_file;
	if (aio_ring_file) {
		truncate_setsize(aio_ring_file->f_inode, 0);

		/* Prevent further access to the kioctx from migratepages */
		spin_lock(&aio_ring_file->f_inode->i_mapping->private_lock);
		aio_ring_file->f_inode->i_mapping->private_data = NULL;
		ctx->aio_ring_file = NULL;
		spin_unlock(&aio_ring_file->f_inode->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_mmap(struct file *file, struct vm_area_struct *vma)
{
	vma->vm_flags |= VM_DONTEXPAND;
	vma->vm_ops = &generic_file_vm_ops;
	return 0;
}

static void aio_ring_remap(struct file *file, struct vm_area_struct *vma)
{
	struct mm_struct *mm = vma->vm_mm;
	struct kioctx_table *table;
	int i;

	spin_lock(&mm->ioctx_lock);
	rcu_read_lock();
	table = rcu_dereference(mm->ioctx_table);
	for (i = 0; i < table->nr; i++) {
		struct kioctx *ctx;

		ctx = table->table[i];
		if (ctx && ctx->aio_ring_file == file) {
			ctx->user_id = ctx->mmap_base = vma->vm_start;
			break;
		}
	}

	rcu_read_unlock();
	spin_unlock(&mm->ioctx_lock);
}

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

#if IS_ENABLED(CONFIG_MIGRATION)
static int aio_migratepage(struct address_space *mapping, struct page *new,
			struct page *old, enum migrate_mode mode)
{
	struct kioctx *ctx;
	unsigned long flags;
	pgoff_t idx;
	int rc;

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

	if (rc != 0)
		goto out_unlock;

	/* Writeback must be complete */
	BUG_ON(PageWriteback(old));
	get_page(new);

	rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1);
	if (rc != MIGRATEPAGE_SUCCESS) {
		put_page(new);
		goto out_unlock;
	}

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

	/* The old page is no longer accessible. */
	put_page(old);

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

static const struct address_space_operations aio_ctx_aops = {
	.set_page_dirty = __set_page_dirty_no_writeback,
#if IS_ENABLED(CONFIG_MIGRATION)
	.migratepage	= aio_migratepage,
#endif
};

static int aio_setup_ring(struct kioctx *ctx)
{
	struct aio_ring *ring;
	unsigned nr_events = ctx->max_reqs;
	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_inode->i_mapping,
					   i, GFP_HIGHUSER | __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);

	down_write(&mm->mmap_sem);
	ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
				       PROT_READ | PROT_WRITE,
				       MAP_SHARED, 0, &unused);
	up_write(&mm->mmap_sem);
	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 = kmap_atomic(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);
	kunmap_atomic(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 *req, kiocb_cancel_fn *cancel)
{
	struct kioctx *ctx = req->ki_ctx;
	unsigned long flags;

	spin_lock_irqsave(&ctx->ctx_lock, flags);

	if (!req->ki_list.next)
		list_add(&req->ki_list, &ctx->active_reqs);

	req->ki_cancel = cancel;

	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
}
EXPORT_SYMBOL(kiocb_set_cancel_fn);

static int kiocb_cancel(struct kiocb *kiocb)
{
	kiocb_cancel_fn *old, *cancel;

	/*
	 * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
	 * actually has a cancel function, hence the cmpxchg()
	 */

	cancel = ACCESS_ONCE(kiocb->ki_cancel);
	do {
		if (!cancel || cancel == KIOCB_CANCELLED)
			return -EINVAL;

		old = cancel;
		cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
	} while (cancel != old);

	return cancel(kiocb);
}

static void free_ioctx(struct work_struct *work)
{
	struct kioctx *ctx = container_of(work, struct kioctx, free_work);

	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->requests_done)
		complete(ctx->requests_done);

	INIT_WORK(&ctx->free_work, free_ioctx);
	schedule_work(&ctx->free_work);
}

/*
 * 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 kiocb *req;

	spin_lock_irq(&ctx->ctx_lock);

	while (!list_empty(&ctx->active_reqs)) {
		req = list_first_entry(&ctx->active_reqs,
				       struct kiocb, ki_list);

		list_del_init(&req->ki_list);
		kiocb_cancel(req);
	}

	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 (!table->table[i]) {
					ctx->id = i;
					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 = kmap_atomic(ctx->ring_pages[0]);
					ring->id = ctx->id;
					kunmap_atomic(ring);
					return 0;
				}

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

		table = kzalloc(sizeof(*table) + sizeof(struct kioctx *) *
				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;

	/*
	 * 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))) ||
	    (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 * 2UL))
		return ERR_PTR(-EAGAIN);

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

	ctx->max_reqs = nr_events;

	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);
	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 + nr_events > (aio_max_nr * 2UL) ||
	    aio_nr + nr_events < 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:
	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 completion *requests_done)
{
	struct kioctx_table *table;

	if (atomic_xchg(&ctx->dead, 1))
		return -EINVAL;


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

	/* percpu_ref_kill() will do the necessary call_rcu() */
	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->requests_done = requests_done;
	percpu_ref_kill(&ctx->users);
	return 0;
}

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

	if (!table)
		return;

	for (i = 0; i < table->nr; ++i) {
		struct kioctx *ctx = table->table[i];
		struct completion requests_done =
			COMPLETION_INITIALIZER_ONSTACK(requests_done);

		if (!ctx)
			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, &requests_done);

		/* Wait until all IO for the context are done. */
		wait_for_completion(&requests_done);
	}

	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 old, avail = atomic_read(&ctx->reqs_available);

		do {
			if (avail < ctx->req_batch)
				goto out;

			old = avail;
			avail = atomic_cmpxchg(&ctx->reqs_available,
					       avail, avail - ctx->req_batch);
		} while (avail != old);

		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 = kmap_atomic(ctx->ring_pages[0]);
		head = ring->head;
		kunmap_atomic(ring);

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

	spin_unlock_irq(&ctx->completion_lock);
}

/* aio_get_req
 *	Allocate a slot for an aio request.
 * Returns NULL if no requests are free.
 */
static inline struct kiocb *aio_get_req(struct kioctx *ctx)
{
	struct kiocb *req;

	if (!get_reqs_available(ctx)) {
		user_refill_reqs_available(ctx);
		if (!get_reqs_available(ctx))
			return NULL;
	}

	req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
	if (unlikely(!req))
		goto out_put;

	percpu_ref_get(&ctx->reqs);

	req->ki_ctx = ctx;
	return req;
out_put:
	put_reqs_available(ctx, 1);
	return NULL;
}

static void kiocb_free(struct kiocb *req)
{
	if (req->ki_filp)
		fput(req->ki_filp);
	if (req->ki_eventfd != NULL)
		eventfd_ctx_put(req->ki_eventfd);
	kmem_cache_free(kiocb_cachep, 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;

	ctx = table->table[id];
	if (ctx && ctx->user_id == ctx_id) {
		percpu_ref_get(&ctx->users);
		ret = ctx;
	}
out:
	rcu_read_unlock();
	return ret;
}

/* aio_complete
 *	Called when the io request on the given iocb is complete.
 */
void aio_complete(struct kiocb *iocb, long res, long res2)
{
	struct kioctx	*ctx = iocb->ki_ctx;
	struct aio_ring	*ring;
	struct io_event	*ev_page, *event;
	unsigned tail, pos, head;
	unsigned long	flags;

	/*
	 * Special case handling for sync iocbs:
	 *  - events go directly into the iocb for fast handling
	 *  - the sync task with the iocb in its stack holds the single iocb
	 *    ref, no other paths have a way to get another ref
	 *  - the sync task helpfully left a reference to itself in the iocb
	 */
	if (is_sync_kiocb(iocb)) {
		iocb->ki_user_data = res;
		smp_wmb();
		iocb->ki_ctx = ERR_PTR(-EXDEV);
		wake_up_process(iocb->ki_obj.tsk);
		return;
	}

	if (iocb->ki_list.next) {
		unsigned long flags;

		spin_lock_irqsave(&ctx->ctx_lock, flags);
		list_del(&iocb->ki_list);
		spin_unlock_irqrestore(&ctx->ctx_lock, 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 = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
	event = ev_page + pos % AIO_EVENTS_PER_PAGE;

	event->obj = (u64)(unsigned long)iocb->ki_obj.user;
	event->data = iocb->ki_user_data;
	event->res = res;
	event->res2 = res2;

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

	pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n",
		 ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data,
		 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 = kmap_atomic(ctx->ring_pages[0]);
	head = ring->head;
	ring->tail = tail;
	kunmap_atomic(ring);
	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 != NULL)
		eventfd_signal(iocb->ki_eventfd, 1);

	/* everything turned out well, dispose of the aiocb. */
	kiocb_free(iocb);

	/*
	 * 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);

	percpu_ref_put(&ctx->reqs);
}
EXPORT_SYMBOL(aio_complete);

/* 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 = kmap_atomic(ctx->ring_pages[0]);
	head = ring->head;
	tail = ring->tail;
	kunmap_atomic(ring);

	/*
	 * 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;

		avail = min(avail, nr - ret);
		avail = min_t(long, avail, AIO_EVENTS_PER_PAGE -
			    ((head + AIO_EVENTS_OFFSET) % AIO_EVENTS_PER_PAGE));

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

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

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

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

	ring = kmap_atomic(ctx->ring_pages[0]);
	ring->head = head;
	kunmap_atomic(ring);
	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,
			struct timespec __user *timeout)
{
	ktime_t until = { .tv64 = KTIME_MAX };
	long ret = 0;

	if (timeout) {
		struct timespec	ts;

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

		until = timespec_to_ktime(ts);
	}

	/*
	 * 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.tv64 == 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);

	if (!ret && signal_pending(current))
		ret = -EINTR;

	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: io_setup: 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;
}

/* 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 completion requests_done =
			COMPLETION_INITIALIZER_ONSTACK(requests_done);
		int ret;

		/* 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, &requests_done);
		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(&requests_done);

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

typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
			    unsigned long, loff_t);
typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *);

static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
				     int rw, char __user *buf,
				     unsigned long *nr_segs,
				     size_t *len,
				     struct iovec **iovec,
				     bool compat)
{
	ssize_t ret;

	*nr_segs = *len;

#ifdef CONFIG_COMPAT
	if (compat)
		ret = compat_rw_copy_check_uvector(rw,
				(struct compat_iovec __user *)buf,
				*nr_segs, UIO_FASTIOV, *iovec, iovec);
	else
#endif
		ret = rw_copy_check_uvector(rw,
				(struct iovec __user *)buf,
				*nr_segs, UIO_FASTIOV, *iovec, iovec);
	if (ret < 0)
		return ret;

	/* len now reflect bytes instead of segs */
	*len = ret;
	return 0;
}

static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
				       int rw, char __user *buf,
				       unsigned long *nr_segs,
				       size_t len,
				       struct iovec *iovec)
{
	if (unlikely(!access_ok(!rw, buf, len)))
		return -EFAULT;

	iovec->iov_base = buf;
	iovec->iov_len = len;
	*nr_segs = 1;
	return 0;
}

/*
 * aio_run_iocb:
 *	Performs the initial checks and io submission.
 */
static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
			    char __user *buf, size_t len, bool compat)
{
	struct file *file = req->ki_filp;
	ssize_t ret;
	unsigned long nr_segs;
	int rw;
	fmode_t mode;
	aio_rw_op *rw_op;
	rw_iter_op *iter_op;
	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
	struct iov_iter iter;

	switch (opcode) {
	case IOCB_CMD_PREAD:
	case IOCB_CMD_PREADV:
		mode	= FMODE_READ;
		rw	= READ;
		rw_op	= file->f_op->aio_read;
		iter_op	= file->f_op->read_iter;
		goto rw_common;

	case IOCB_CMD_PWRITE:
	case IOCB_CMD_PWRITEV:
		mode	= FMODE_WRITE;
		rw	= WRITE;
		rw_op	= file->f_op->aio_write;
		iter_op	= file->f_op->write_iter;
		goto rw_common;
rw_common:
		if (unlikely(!(file->f_mode & mode)))
			return -EBADF;

		if (!rw_op && !iter_op)
			return -EINVAL;

		if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV)
			ret = aio_setup_vectored_rw(req, rw, buf, &nr_segs,
						&len, &iovec, compat);
		else
			ret = aio_setup_single_vector(req, rw, buf, &nr_segs,
						  len, iovec);
		if (!ret)
			ret = rw_verify_area(rw, file, &req->ki_pos, len);
		if (ret < 0) {
			if (iovec != inline_vecs)
				kfree(iovec);
			return ret;
		}

		len = ret;

		/* XXX: move/kill - rw_verify_area()? */
		/* This matches the pread()/pwrite() logic */
		if (req->ki_pos < 0) {
			ret = -EINVAL;
			break;
		}

		if (rw == WRITE)
			file_start_write(file);

		if (iter_op) {
			iov_iter_init(&iter, rw, iovec, nr_segs, len);
			ret = iter_op(req, &iter);
		} else {
			ret = rw_op(req, iovec, nr_segs, req->ki_pos);
		}

		if (rw == WRITE)
			file_end_write(file);
		break;

	case IOCB_CMD_FDSYNC:
		if (!file->f_op->aio_fsync)
			return -EINVAL;

		ret = file->f_op->aio_fsync(req, 1);
		break;

	case IOCB_CMD_FSYNC:
		if (!file->f_op->aio_fsync)
			return -EINVAL;

		ret = file->f_op->aio_fsync(req, 0);
		break;

	default:
		pr_debug("EINVAL: no operation provided\n");
		return -EINVAL;
	}

	if (iovec != inline_vecs)
		kfree(iovec);

	if (ret != -EIOCBQUEUED) {
		/*
		 * There's no easy way to restart the syscall since other AIO's
		 * may be already running. Just fail this IO with EINTR.
		 */
		if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
			     ret == -ERESTARTNOHAND ||
			     ret == -ERESTART_RESTARTBLOCK))
			ret = -EINTR;
		aio_complete(req, ret, 0);
	}

	return 0;
}

static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
			 struct iocb *iocb, bool compat)
{
	struct kiocb *req;
	ssize_t ret;

	/* enforce forwards compatibility on users */
	if (unlikely(iocb->aio_reserved1 || 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: io_submit: overflow check\n");
		return -EINVAL;
	}

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

	req->ki_filp = fget(iocb->aio_fildes);
	if (unlikely(!req->ki_filp)) {
		ret = -EBADF;
		goto out_put_req;
	}

	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
		/*
		 * 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.
		 */
		req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd);
		if (IS_ERR(req->ki_eventfd)) {
			ret = PTR_ERR(req->ki_eventfd);
			req->ki_eventfd = NULL;
			goto out_put_req;
		}
	}

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

	req->ki_obj.user = user_iocb;
	req->ki_user_data = iocb->aio_data;
	req->ki_pos = iocb->aio_offset;

	ret = aio_run_iocb(req, iocb->aio_lio_opcode,
			   (char __user *)(unsigned long)iocb->aio_buf,
			   iocb->aio_nbytes,
			   compat);
	if (ret)
		goto out_put_req;

	return 0;
out_put_req:
	put_reqs_available(ctx, 1);
	percpu_ref_put(&ctx->reqs);
	kiocb_free(req);
	return ret;
}

long do_io_submit(aio_context_t ctx_id, long nr,
		  struct iocb __user *__user *iocbpp, bool compat)
{
	struct kioctx *ctx;
	long ret = 0;
	int i = 0;
	struct blk_plug plug;

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

	if (unlikely(nr > LONG_MAX/sizeof(*iocbpp)))
		nr = LONG_MAX/sizeof(*iocbpp);

	if (unlikely(!access_ok(VERIFY_READ, iocbpp, (nr*sizeof(*iocbpp)))))
		return -EFAULT;

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

	blk_start_plug(&plug);

	/*
	 * AKPM: should this return a partial result if some of the IOs were
	 * successfully submitted?
	 */
	for (i=0; i<nr; i++) {
		struct iocb __user *user_iocb;
		struct iocb tmp;

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

		if (unlikely(copy_from_user(&tmp, user_iocb, sizeof(tmp)))) {
			ret = -EFAULT;
			break;
		}

		ret = io_submit_one(ctx, user_iocb, &tmp, compat);
		if (ret)
			break;
	}
	blk_finish_plug(&plug);

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

/* 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)
{
	return do_io_submit(ctx_id, nr, iocbpp, 0);
}

/* lookup_kiocb
 *	Finds a given iocb for cancellation.
 */
static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb,
				  u32 key)
{
	struct list_head *pos;

	assert_spin_locked(&ctx->ctx_lock);

	if (key != KIOCB_KEY)
		return NULL;

	/* TODO: use a hash or array, this sucks. */
	list_for_each(pos, &ctx->active_reqs) {
		struct kiocb *kiocb = list_kiocb(pos);
		if (kiocb->ki_obj.user == iocb)
			return kiocb;
	}
	return NULL;
}

/* 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 kiocb *kiocb;
	u32 key;
	int ret;

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

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

	spin_lock_irq(&ctx->ctx_lock);

	kiocb = lookup_kiocb(ctx, iocb, key);
	if (kiocb)
		ret = kiocb_cancel(kiocb);
	else
		ret = -EINVAL;

	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;
}

/* 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.
 */
SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
		long, min_nr,
		long, nr,
		struct io_event __user *, events,
		struct timespec __user *, timeout)
{
	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, timeout);
		percpu_ref_put(&ioctx->users);
	}
	return ret;
}