aboutsummaryrefslogtreecommitdiffstats
path: root/fs/read_write.c
blob: e6dd1c2d05920a86469030c7878413ef0fff2fc0 (plain) (blame)
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
/*
 *  linux/fs/read_write.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/slab.h> 
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/fsnotify.h>
#include <linux/security.h>
#include <linux/export.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>
#include <linux/splice.h>
#include <linux/compat.h>
#include "read_write.h"
#include "internal.h"

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

const struct file_operations generic_ro_fops = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.aio_read	= generic_file_aio_read,
	.mmap		= generic_file_readonly_mmap,
	.splice_read	= generic_file_splice_read,
};

EXPORT_SYMBOL(generic_ro_fops);

static inline int unsigned_offsets(struct file *file)
{
	return file->f_mode & FMODE_UNSIGNED_OFFSET;
}

static loff_t lseek_execute(struct file *file, struct inode *inode,
		loff_t offset, loff_t maxsize)
{
	if (offset < 0 && !unsigned_offsets(file))
		return -EINVAL;
	if (offset > maxsize)
		return -EINVAL;

	if (offset != file->f_pos) {
		file->f_pos = offset;
		file->f_version = 0;
	}
	return offset;
}

/**
 * generic_file_llseek_size - generic llseek implementation for regular files
 * @file:	file structure to seek on
 * @offset:	file offset to seek to
 * @whence:	type of seek
 * @size:	max size of this file in file system
 * @eof:	offset used for SEEK_END position
 *
 * This is a variant of generic_file_llseek that allows passing in a custom
 * maximum file size and a custom EOF position, for e.g. hashed directories
 *
 * Synchronization:
 * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms)
 * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes.
 * read/writes behave like SEEK_SET against seeks.
 */
loff_t
generic_file_llseek_size(struct file *file, loff_t offset, int whence,
		loff_t maxsize, loff_t eof)
{
	struct inode *inode = file->f_mapping->host;

	switch (whence) {
	case SEEK_END:
		offset += eof;
		break;
	case SEEK_CUR:
		/*
		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
		 * position-querying operation.  Avoid rewriting the "same"
		 * f_pos value back to the file because a concurrent read(),
		 * write() or lseek() might have altered it
		 */
		if (offset == 0)
			return file->f_pos;
		/*
		 * f_lock protects against read/modify/write race with other
		 * SEEK_CURs. Note that parallel writes and reads behave
		 * like SEEK_SET.
		 */
		spin_lock(&file->f_lock);
		offset = lseek_execute(file, inode, file->f_pos + offset,
				       maxsize);
		spin_unlock(&file->f_lock);
		return offset;
	case SEEK_DATA:
		/*
		 * In the generic case the entire file is data, so as long as
		 * offset isn't at the end of the file then the offset is data.
		 */
		if (offset >= eof)
			return -ENXIO;
		break;
	case SEEK_HOLE:
		/*
		 * There is a virtual hole at the end of the file, so as long as
		 * offset isn't i_size or larger, return i_size.
		 */
		if (offset >= eof)
			return -ENXIO;
		offset = eof;
		break;
	}

	return lseek_execute(file, inode, offset, maxsize);
}
EXPORT_SYMBOL(generic_file_llseek_size);

/**
 * generic_file_llseek - generic llseek implementation for regular files
 * @file:	file structure to seek on
 * @offset:	file offset to seek to
 * @whence:	type of seek
 *
 * This is a generic implemenation of ->llseek useable for all normal local
 * filesystems.  It just updates the file offset to the value specified by
 * @offset and @whence under i_mutex.
 */
loff_t generic_file_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;

	return generic_file_llseek_size(file, offset, whence,
					inode->i_sb->s_maxbytes,
					i_size_read(inode));
}
EXPORT_SYMBOL(generic_file_llseek);

/**
 * noop_llseek - No Operation Performed llseek implementation
 * @file:	file structure to seek on
 * @offset:	file offset to seek to
 * @whence:	type of seek
 *
 * This is an implementation of ->llseek useable for the rare special case when
 * userspace expects the seek to succeed but the (device) file is actually not
 * able to perform the seek. In this case you use noop_llseek() instead of
 * falling back to the default implementation of ->llseek.
 */
loff_t noop_llseek(struct file *file, loff_t offset, int whence)
{
	return file->f_pos;
}
EXPORT_SYMBOL(noop_llseek);

loff_t no_llseek(struct file *file, loff_t offset, int whence)
{
	return -ESPIPE;
}
EXPORT_SYMBOL(no_llseek);

loff_t default_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file_inode(file);
	loff_t retval;

	mutex_lock(&inode->i_mutex);
	switch (whence) {
		case SEEK_END:
			offset += i_size_read(inode);
			break;
		case SEEK_CUR:
			if (offset == 0) {
				retval = file->f_pos;
				goto out;
			}
			offset += file->f_pos;
			break;
		case SEEK_DATA:
			/*
			 * In the generic case the entire file is data, so as
			 * long as offset isn't at the end of the file then the
			 * offset is data.
			 */
			if (offset >= inode->i_size) {
				retval = -ENXIO;
				goto out;
			}
			break;
		case SEEK_HOLE:
			/*
			 * There is a virtual hole at the end of the file, so
			 * as long as offset isn't i_size or larger, return
			 * i_size.
			 */
			if (offset >= inode->i_size) {
				retval = -ENXIO;
				goto out;
			}
			offset = inode->i_size;
			break;
	}
	retval = -EINVAL;
	if (offset >= 0 || unsigned_offsets(file)) {
		if (offset != file->f_pos) {
			file->f_pos = offset;
			file->f_version = 0;
		}
		retval = offset;
	}
out:
	mutex_unlock(&inode->i_mutex);
	return retval;
}
EXPORT_SYMBOL(default_llseek);

loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
{
	loff_t (*fn)(struct file *, loff_t, int);

	fn = no_llseek;
	if (file->f_mode & FMODE_LSEEK) {
		if (file->f_op && file->f_op->llseek)
			fn = file->f_op->llseek;
	}
	return fn(file, offset, whence);
}
EXPORT_SYMBOL(vfs_llseek);

SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
	off_t retval;
	struct fd f = fdget(fd);
	if (!f.file)
		return -EBADF;

	retval = -EINVAL;
	if (whence <= SEEK_MAX) {
		loff_t res = vfs_llseek(f.file, offset, whence);
		retval = res;
		if (res != (loff_t)retval)
			retval = -EOVERFLOW;	/* LFS: should only happen on 32 bit platforms */
	}
	fdput(f);
	return retval;
}

#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence)
{
	return sys_lseek(fd, offset, whence);
}
#endif

#ifdef __ARCH_WANT_SYS_LLSEEK
SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
		unsigned long, offset_low, loff_t __user *, result,
		unsigned int, whence)
{
	int retval;
	struct fd f = fdget(fd);
	loff_t offset;

	if (!f.file)
		return -EBADF;

	retval = -EINVAL;
	if (whence > SEEK_MAX)
		goto out_putf;

	offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low,
			whence);

	retval = (int)offset;
	if (offset >= 0) {
		retval = -EFAULT;
		if (!copy_to_user(result, &offset, sizeof(offset)))
			retval = 0;
	}
out_putf:
	fdput(f);
	return retval;
}
#endif

/*
 * rw_verify_area doesn't like huge counts. We limit
 * them to something that fits in "int" so that others
 * won't have to do range checks all the time.
 */
int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count)
{
	struct inode *inode;
	loff_t pos;
	int retval = -EINVAL;

	inode = file_inode(file);
	if (unlikely((ssize_t) count < 0))
		return retval;
	pos = *ppos;
	if (unlikely(pos < 0)) {
		if (!unsigned_offsets(file))
			return retval;
		if (count >= -pos) /* both values are in 0..LLONG_MAX */
			return -EOVERFLOW;
	} else if (unlikely((loff_t) (pos + count) < 0)) {
		if (!unsigned_offsets(file))
			return retval;
	}

	if (unlikely(inode->i_flock && mandatory_lock(inode))) {
		retval = locks_mandatory_area(
			read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
			inode, file, pos, count);
		if (retval < 0)
			return retval;
	}
	retval = security_file_permission(file,
				read_write == READ ? MAY_READ : MAY_WRITE);
	if (retval)
		return retval;
	return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
}

static void wait_on_retry_sync_kiocb(struct kiocb *iocb)
{
	set_current_state(TASK_UNINTERRUPTIBLE);
	if (!kiocbIsKicked(iocb))
		schedule();
	else
		kiocbClearKicked(iocb);
	__set_current_state(TASK_RUNNING);
}

ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
{
	struct iovec iov = { .iov_base = buf, .iov_len = len };
	struct kiocb kiocb;
	ssize_t ret;

	init_sync_kiocb(&kiocb, filp);
	kiocb.ki_pos = *ppos;
	kiocb.ki_left = len;
	kiocb.ki_nbytes = len;

	for (;;) {
		ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
		if (ret != -EIOCBRETRY)
			break;
		wait_on_retry_sync_kiocb(&kiocb);
	}

	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&kiocb);
	*ppos = kiocb.ki_pos;
	return ret;
}

EXPORT_SYMBOL(do_sync_read);

ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
{
	ssize_t ret;

	if (!(file->f_mode & FMODE_READ))
		return -EBADF;
	if (!file->f_op || (!file->f_op->read && !file->f_op->aio_read))
		return -EINVAL;
	if (unlikely(!access_ok(VERIFY_WRITE, buf, count)))
		return -EFAULT;

	ret = rw_verify_area(READ, file, pos, count);
	if (ret >= 0) {
		count = ret;
		if (file->f_op->read)
			ret = file->f_op->read(file, buf, count, pos);
		else
			ret = do_sync_read(file, buf, count, pos);
		if (ret > 0) {
			fsnotify_access(file);
			add_rchar(current, ret);
		}
		inc_syscr(current);
	}

	return ret;
}

EXPORT_SYMBOL(vfs_read);

ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
{
	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
	struct kiocb kiocb;
	ssize_t ret;

	file_start_write(filp);
	init_sync_kiocb(&kiocb, filp);
	kiocb.ki_pos = *ppos;
	kiocb.ki_left = len;
	kiocb.ki_nbytes = len;

	for (;;) {
		ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
		if (ret != -EIOCBRETRY)
			break;
		wait_on_retry_sync_kiocb(&kiocb);
	}

	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&kiocb);
	*ppos = kiocb.ki_pos;
	file_end_write(filp);
	return ret;
}

EXPORT_SYMBOL(do_sync_write);

ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos)
{
	mm_segment_t old_fs;
	const char __user *p;
	ssize_t ret;

	old_fs = get_fs();
	set_fs(get_ds());
	p = (__force const char __user *)buf;
	if (count > MAX_RW_COUNT)
		count =  MAX_RW_COUNT;
	if (file->f_op->write)
		ret = file->f_op->write(file, p, count, pos);
	else
		ret = do_sync_write(file, p, count, pos);
	set_fs(old_fs);
	if (ret > 0) {
		fsnotify_modify(file);
		add_wchar(current, ret);
	}
	inc_syscw(current);
	return ret;
}

ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
	ssize_t ret;

	if (!(file->f_mode & FMODE_WRITE))
		return -EBADF;
	if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
		return -EINVAL;
	if (unlikely(!access_ok(VERIFY_READ, buf, count)))
		return -EFAULT;

	ret = rw_verify_area(WRITE, file, pos, count);
	if (ret >= 0) {
		count = ret;
		if (file->f_op->write)
			ret = file->f_op->write(file, buf, count, pos);
		else
			ret = do_sync_write(file, buf, count, pos);
		if (ret > 0) {
			fsnotify_modify(file);
			add_wchar(current, ret);
		}
		inc_syscw(current);
	}

	return ret;
}

EXPORT_SYMBOL(vfs_write);

static inline loff_t file_pos_read(struct file *file)
{
	return file->f_pos;
}

static inline void file_pos_write(struct file *file, loff_t pos)
{
	file->f_pos = pos;
}

SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
	struct fd f = fdget(fd);
	ssize_t ret = -EBADF;

	if (f.file) {
		loff_t pos = file_pos_read(f.file);
		ret = vfs_read(f.file, buf, count, &pos);
		file_pos_write(f.file, pos);
		fdput(f);
	}
	return ret;
}

SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
		size_t, count)
{
	struct fd f = fdget(fd);
	ssize_t ret = -EBADF;

	if (f.file) {
		loff_t pos = file_pos_read(f.file);
		ret = vfs_write(f.file, buf, count, &pos);
		file_pos_write(f.file, pos);
		fdput(f);
	}

	return ret;
}

SYSCALL_DEFINE(pread64)(unsigned int fd, char __user *buf,
			size_t count, loff_t pos)
{
	struct fd f;
	ssize_t ret = -EBADF;

	if (pos < 0)
		return -EINVAL;

	f = fdget(fd);
	if (f.file) {
		ret = -ESPIPE;
		if (f.file->f_mode & FMODE_PREAD)
			ret = vfs_read(f.file, buf, count, &pos);
		fdput(f);
	}

	return ret;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_pread64(long fd, long buf, long count, loff_t pos)
{
	return SYSC_pread64((unsigned int) fd, (char __user *) buf,
			    (size_t) count, pos);
}
SYSCALL_ALIAS(sys_pread64, SyS_pread64);
#endif

SYSCALL_DEFINE(pwrite64)(unsigned int fd, const char __user *buf,
			 size_t count, loff_t pos)
{
	struct fd f;
	ssize_t ret = -EBADF;

	if (pos < 0)
		return -EINVAL;

	f = fdget(fd);
	if (f.file) {
		ret = -ESPIPE;
		if (f.file->f_mode & FMODE_PWRITE)  
			ret = vfs_write(f.file, buf, count, &pos);
		fdput(f);
	}

	return ret;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_pwrite64(long fd, long buf, long count, loff_t pos)
{
	return SYSC_pwrite64((unsigned int) fd, (const char __user *) buf,
			     (size_t) count, pos);
}
SYSCALL_ALIAS(sys_pwrite64, SyS_pwrite64);
#endif

/*
 * Reduce an iovec's length in-place.  Return the resulting number of segments
 */
unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
{
	unsigned long seg = 0;
	size_t len = 0;

	while (seg < nr_segs) {
		seg++;
		if (len + iov->iov_len >= to) {
			iov->iov_len = to - len;
			break;
		}
		len += iov->iov_len;
		iov++;
	}
	return seg;
}
EXPORT_SYMBOL(iov_shorten);

static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
		unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn)
{
	struct kiocb kiocb;
	ssize_t ret;

	init_sync_kiocb(&kiocb, filp);
	kiocb.ki_pos = *ppos;
	kiocb.ki_left = len;
	kiocb.ki_nbytes = len;

	for (;;) {
		ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
		if (ret != -EIOCBRETRY)
			break;
		wait_on_retry_sync_kiocb(&kiocb);
	}

	if (ret == -EIOCBQUEUED)
		ret = wait_on_sync_kiocb(&kiocb);
	*ppos = kiocb.ki_pos;
	return ret;
}

/* Do it by hand, with file-ops */
static ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
		unsigned long nr_segs, loff_t *ppos, io_fn_t fn)
{
	struct iovec *vector = iov;
	ssize_t ret = 0;

	while (nr_segs > 0) {
		void __user *base;
		size_t len;
		ssize_t nr;

		base = vector->iov_base;
		len = vector->iov_len;
		vector++;
		nr_segs--;

		nr = fn(filp, base, len, ppos);

		if (nr < 0) {
			if (!ret)
				ret = nr;
			break;
		}
		ret += nr;
		if (nr != len)
			break;
	}

	return ret;
}

/* A write operation does a read from user space and vice versa */
#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)

ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
			      unsigned long nr_segs, unsigned long fast_segs,
			      struct iovec *fast_pointer,
			      struct iovec **ret_pointer)
{
	unsigned long seg;
	ssize_t ret;
	struct iovec *iov = fast_pointer;

	/*
	 * SuS says "The readv() function *may* fail if the iovcnt argument
	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
	 * traditionally returned zero for zero segments, so...
	 */
	if (nr_segs == 0) {
		ret = 0;
		goto out;
	}

	/*
	 * First get the "struct iovec" from user memory and
	 * verify all the pointers
	 */
	if (nr_segs > UIO_MAXIOV) {
		ret = -EINVAL;
		goto out;
	}
	if (nr_segs > fast_segs) {
		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
		if (iov == NULL) {
			ret = -ENOMEM;
			goto out;
		}
	}
	if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
		ret = -EFAULT;
		goto out;
	}

	/*
	 * According to the Single Unix Specification we should return EINVAL
	 * if an element length is < 0 when cast to ssize_t or if the
	 * total length would overflow the ssize_t return value of the
	 * system call.
	 *
	 * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
	 * overflow case.
	 */
	ret = 0;
	for (seg = 0; seg < nr_segs; seg++) {
		void __user *buf = iov[seg].iov_base;
		ssize_t len = (ssize_t)iov[seg].iov_len;

		/* see if we we're about to use an invalid len or if
		 * it's about to overflow ssize_t */
		if (len < 0) {
			ret = -EINVAL;
			goto out;
		}
		if (type >= 0
		    && unlikely(!access_ok(vrfy_dir(type), buf, len))) {
			ret = -EFAULT;
			goto out;
		}
		if (len > MAX_RW_COUNT - ret) {
			len = MAX_RW_COUNT - ret;
			iov[seg].iov_len = len;
		}
		ret += len;
	}
out:
	*ret_pointer = iov;
	return ret;
}

static ssize_t do_readv_writev(int type, struct file *file,
			       const struct iovec __user * uvector,
			       unsigned long nr_segs, loff_t *pos)
{
	size_t tot_len;
	struct iovec iovstack[UIO_FASTIOV];
	struct iovec *iov = iovstack;
	ssize_t ret;
	io_fn_t fn;
	iov_fn_t fnv;

	if (!file->f_op) {
		ret = -EINVAL;
		goto out;
	}

	ret = rw_copy_check_uvector(type, uvector, nr_segs,
				    ARRAY_SIZE(iovstack), iovstack, &iov);
	if (ret <= 0)
		goto out;

	tot_len = ret;
	ret = rw_verify_area(type, file, pos, tot_len);
	if (ret < 0)
		goto out;

	fnv = NULL;
	if (type == READ) {
		fn = file->f_op->read;
		fnv = file->f_op->aio_read;
	} else {
		fn = (io_fn_t)file->f_op->write;
		fnv = file->f_op->aio_write;
	}

	if (fnv) {
		file_start_write(file);
		ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
						pos, fnv);
		file_end_write(file);
	} else
		ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);

out:
	if (iov != iovstack)
		kfree(iov);
	if ((ret + (type == READ)) > 0) {
		if (type == READ)
			fsnotify_access(file);
		else
			fsnotify_modify(file);
	}
	return ret;
}

ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
		  unsigned long vlen, loff_t *pos)
{
	if (!(file->f_mode & FMODE_READ))
		return -EBADF;
	if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
		return -EINVAL;

	return do_readv_writev(READ, file, vec, vlen, pos);
}

EXPORT_SYMBOL(vfs_readv);

ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
		   unsigned long vlen, loff_t *pos)
{
	if (!(file->f_mode & FMODE_WRITE))
		return -EBADF;
	if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
		return -EINVAL;

	return do_readv_writev(WRITE, file, vec, vlen, pos);
}

EXPORT_SYMBOL(vfs_writev);

SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
		unsigned long, vlen)
{
	struct fd f = fdget(fd);
	ssize_t ret = -EBADF;

	if (f.file) {
		loff_t pos = file_pos_read(f.file);
		ret = vfs_readv(f.file, vec, vlen, &pos);
		file_pos_write(f.file, pos);
		fdput(f);
	}

	if (ret > 0)
		add_rchar(current, ret);
	inc_syscr(current);
	return ret;
}

SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
		unsigned long, vlen)
{
	struct fd f = fdget(fd);
	ssize_t ret = -EBADF;

	if (f.file) {
		loff_t pos = file_pos_read(f.file);
		ret = vfs_writev(f.file, vec, vlen, &pos);
		file_pos_write(f.file, pos);
		fdput(f);
	}

	if (ret > 0)
		add_wchar(current, ret);
	inc_syscw(current);
	return ret;
}

static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
{
#define HALF_LONG_BITS (BITS_PER_LONG / 2)
	return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
}

SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
{
	loff_t pos = pos_from_hilo(pos_h, pos_l);
	struct fd f;
	ssize_t ret = -EBADF;

	if (pos < 0)
		return -EINVAL;

	f = fdget(fd);
	if (f.file) {
		ret = -ESPIPE;
		if (f.file->f_mode & FMODE_PREAD)
			ret = vfs_readv(f.file, vec, vlen, &pos);
		fdput(f);
	}

	if (ret > 0)
		add_rchar(current, ret);
	inc_syscr(current);
	return ret;
}

SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
{
	loff_t pos = pos_from_hilo(pos_h, pos_l);
	struct fd f;
	ssize_t ret = -EBADF;

	if (pos < 0)
		return -EINVAL;

	f = fdget(fd);
	if (f.file) {
		ret = -ESPIPE;
		if (f.file->f_mode & FMODE_PWRITE)
			ret = vfs_writev(f.file, vec, vlen, &pos);
		fdput(f);
	}

	if (ret > 0)
		add_wchar(current, ret);
	inc_syscw(current);
	return ret;
}

#ifdef CONFIG_COMPAT

static ssize_t compat_do_readv_writev(int type, struct file *file,
			       const struct compat_iovec __user *uvector,
			       unsigned long nr_segs, loff_t *pos)
{
	compat_ssize_t tot_len;
	struct iovec iovstack[UIO_FASTIOV];
	struct iovec *iov = iovstack;
	ssize_t ret;
	io_fn_t fn;
	iov_fn_t fnv;

	ret = -EINVAL;
	if (!file->f_op)
		goto out;

	ret = -EFAULT;
	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
		goto out;

	ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
					       UIO_FASTIOV, iovstack, &iov);
	if (ret <= 0)
		goto out;

	tot_len = ret;
	ret = rw_verify_area(type, file, pos, tot_len);
	if (ret < 0)
		goto out;

	fnv = NULL;
	if (type == READ) {
		fn = file->f_op->read;
		fnv = file->f_op->aio_read;
	} else {
		fn = (io_fn_t)file->f_op->write;
		fnv = file->f_op->aio_write;
	}

	if (fnv) {
		file_start_write(file);
		ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
						pos, fnv);
		file_end_write(file);
	} else
		ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);

out:
	if (iov != iovstack)
		kfree(iov);
	if ((ret + (type == READ)) > 0) {
		if (type == READ)
			fsnotify_access(file);
		else
			fsnotify_modify(file);
	}
	return ret;
}

static size_t compat_readv(struct file *file,
			   const struct compat_iovec __user *vec,
			   unsigned long vlen, loff_t *pos)
{
	ssize_t ret = -EBADF;

	if (!(file->f_mode & FMODE_READ))
		goto out;

	ret = -EINVAL;
	if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
		goto out;

	ret = compat_do_readv_writev(READ, file, vec, vlen, pos);

out:
	if (ret > 0)
		add_rchar(current, ret);
	inc_syscr(current);
	return ret;
}

COMPAT_SYSCALL_DEFINE3(readv, unsigned long, fd,
		const struct compat_iovec __user *,vec,
		unsigned long, vlen)
{
	struct fd f = fdget(fd);
	ssize_t ret;
	loff_t pos;

	if (!f.file)
		return -EBADF;
	pos = f.file->f_pos;
	ret = compat_readv(f.file, vec, vlen, &pos);
	f.file->f_pos = pos;
	fdput(f);
	return ret;
}

COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
		const struct compat_iovec __user *,vec,
		unsigned long, vlen, loff_t, pos)
{
	struct fd f;
	ssize_t ret;

	if (pos < 0)
		return -EINVAL;
	f = fdget(fd);
	if (!f.file)
		return -EBADF;
	ret = -ESPIPE;
	if (f.file->f_mode & FMODE_PREAD)
		ret = compat_readv(f.file, vec, vlen, &pos);
	fdput(f);
	return ret;
}

COMPAT_SYSCALL_DEFINE5(preadv, unsigned long, fd,
		const struct compat_iovec __user *,vec,
		unsigned long, vlen, u32, pos_low, u32, pos_high)
{
	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
	return compat_sys_preadv64(fd, vec, vlen, pos);
}

static size_t compat_writev(struct file *file,
			    const struct compat_iovec __user *vec,
			    unsigned long vlen, loff_t *pos)
{
	ssize_t ret = -EBADF;

	if (!(file->f_mode & FMODE_WRITE))
		goto out;

	ret = -EINVAL;
	if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
		goto out;

	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);

out:
	if (ret > 0)
		add_wchar(current, ret);
	inc_syscw(current);
	return ret;
}

COMPAT_SYSCALL_DEFINE3(writev, unsigned long, fd,
		const struct compat_iovec __user *, vec,
		unsigned long, vlen)
{
	struct fd f = fdget(fd);
	ssize_t ret;
	loff_t pos;

	if (!f.file)
		return -EBADF;
	pos = f.file->f_pos;
	ret = compat_writev(f.file, vec, vlen, &pos);
	f.file->f_pos = pos;
	fdput(f);
	return ret;
}

COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
		const struct compat_iovec __user *,vec,
		unsigned long, vlen, loff_t, pos)
{
	struct fd f;
	ssize_t ret;

	if (pos < 0)
		return -EINVAL;
	f = fdget(fd);
	if (!f.file)
		return -EBADF;
	ret = -ESPIPE;
	if (f.file->f_mode & FMODE_PWRITE)
		ret = compat_writev(f.file, vec, vlen, &pos);
	fdput(f);
	return ret;
}

COMPAT_SYSCALL_DEFINE5(pwritev, unsigned long, fd,
		const struct compat_iovec __user *,vec,
		unsigned long, vlen, u32, pos_low, u32, pos_high)
{
	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
	return compat_sys_pwritev64(fd, vec, vlen, pos);
}
#endif

ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count,
		    loff_t max)
{
	struct fd in, out;
	struct inode *in_inode, *out_inode;
	loff_t pos;
	ssize_t retval;
	int fl;

	/*
	 * Get input file, and verify that it is ok..
	 */
	retval = -EBADF;
	in = fdget(in_fd);
	if (!in.file)
		goto out;
	if (!(in.file->f_mode & FMODE_READ))
		goto fput_in;
	retval = -ESPIPE;
	if (!ppos)
		ppos = &in.file->f_pos;
	else
		if (!(in.file->f_mode & FMODE_PREAD))
			goto fput_in;
	retval = rw_verify_area(READ, in.file, ppos, count);
	if (retval < 0)
		goto fput_in;
	count = retval;

	/*
	 * Get output file, and verify that it is ok..
	 */
	retval = -EBADF;
	out = fdget(out_fd);
	if (!out.file)
		goto fput_in;
	if (!(out.file->f_mode & FMODE_WRITE))
		goto fput_out;
	retval = -EINVAL;
	in_inode = file_inode(in.file);
	out_inode = file_inode(out.file);
	retval = rw_verify_area(WRITE, out.file, &out.file->f_pos, count);
	if (retval < 0)
		goto fput_out;
	count = retval;

	if (!max)
		max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);

	pos = *ppos;
	if (unlikely(pos + count > max)) {
		retval = -EOVERFLOW;
		if (pos >= max)
			goto fput_out;
		count = max - pos;
	}

	fl = 0;
#if 0
	/*
	 * We need to debate whether we can enable this or not. The
	 * man page documents EAGAIN return for the output at least,
	 * and the application is arguably buggy if it doesn't expect
	 * EAGAIN on a non-blocking file descriptor.
	 */
	if (in.file->f_flags & O_NONBLOCK)
		fl = SPLICE_F_NONBLOCK;
#endif
	retval = do_splice_direct(in.file, ppos, out.file, count, fl);

	if (retval > 0) {
		add_rchar(current, retval);
		add_wchar(current, retval);
		fsnotify_access(in.file);
		fsnotify_modify(out.file);
	}

	inc_syscr(current);
	inc_syscw(current);
	if (*ppos > max)
		retval = -EOVERFLOW;

fput_out:
	fdput(out);
fput_in:
	fdput(in);
out:
	return retval;
}

SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count)
{
	loff_t pos;
	off_t off;
	ssize_t ret;

	if (offset) {
		if (unlikely(get_user(off, offset)))
			return -EFAULT;
		pos = off;
		ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS);
		if (unlikely(put_user(pos, offset)))
			return -EFAULT;
		return ret;
	}

	return do_sendfile(out_fd, in_fd, NULL, count, 0);
}

SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count)
{
	loff_t pos;
	ssize_t ret;

	if (offset) {
		if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t))))
			return -EFAULT;
		ret = do_sendfile(out_fd, in_fd, &pos, count, 0);
		if (unlikely(put_user(pos, offset)))
			return -EFAULT;
		return ret;
	}

	return do_sendfile(out_fd, in_fd, NULL, count, 0);
}