summaryrefslogtreecommitdiff
path: root/fs/file.c
blob: b5591efb87f56c5ef62ac70ca24fd5e638167a23 (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/file.c
 *
 *  Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes
 *
 *  Manage the dynamic fd arrays in the process files_struct.
 */

#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/close_range.h>
#include <net/sock.h>
#include <linux/io_uring.h>

unsigned int sysctl_nr_open __read_mostly = 1024*1024;
unsigned int sysctl_nr_open_min = BITS_PER_LONG;
/* our min() is unusable in constant expressions ;-/ */
#define __const_min(x, y) ((x) < (y) ? (x) : (y))
unsigned int sysctl_nr_open_max =
	__const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG;

static void __free_fdtable(struct fdtable *fdt)
{
	kvfree(fdt->fd);
	kvfree(fdt->open_fds);
	kfree(fdt);
}

static void free_fdtable_rcu(struct rcu_head *rcu)
{
	__free_fdtable(container_of(rcu, struct fdtable, rcu));
}

#define BITBIT_NR(nr)	BITS_TO_LONGS(BITS_TO_LONGS(nr))
#define BITBIT_SIZE(nr)	(BITBIT_NR(nr) * sizeof(long))

/*
 * Copy 'count' fd bits from the old table to the new table and clear the extra
 * space if any.  This does not copy the file pointers.  Called with the files
 * spinlock held for write.
 */
static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
			    unsigned int count)
{
	unsigned int cpy, set;

	cpy = count / BITS_PER_BYTE;
	set = (nfdt->max_fds - count) / BITS_PER_BYTE;
	memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
	memset((char *)nfdt->open_fds + cpy, 0, set);
	memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
	memset((char *)nfdt->close_on_exec + cpy, 0, set);

	cpy = BITBIT_SIZE(count);
	set = BITBIT_SIZE(nfdt->max_fds) - cpy;
	memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
	memset((char *)nfdt->full_fds_bits + cpy, 0, set);
}

/*
 * Copy all file descriptors from the old table to the new, expanded table and
 * clear the extra space.  Called with the files spinlock held for write.
 */
static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
{
	size_t cpy, set;

	BUG_ON(nfdt->max_fds < ofdt->max_fds);

	cpy = ofdt->max_fds * sizeof(struct file *);
	set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *);
	memcpy(nfdt->fd, ofdt->fd, cpy);
	memset((char *)nfdt->fd + cpy, 0, set);

	copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds);
}

static struct fdtable * alloc_fdtable(unsigned int nr)
{
	struct fdtable *fdt;
	void *data;

	/*
	 * Figure out how many fds we actually want to support in this fdtable.
	 * Allocation steps are keyed to the size of the fdarray, since it
	 * grows far faster than any of the other dynamic data. We try to fit
	 * the fdarray into comfortable page-tuned chunks: starting at 1024B
	 * and growing in powers of two from there on.
	 */
	nr /= (1024 / sizeof(struct file *));
	nr = roundup_pow_of_two(nr + 1);
	nr *= (1024 / sizeof(struct file *));
	/*
	 * Note that this can drive nr *below* what we had passed if sysctl_nr_open
	 * had been set lower between the check in expand_files() and here.  Deal
	 * with that in caller, it's cheaper that way.
	 *
	 * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise
	 * bitmaps handling below becomes unpleasant, to put it mildly...
	 */
	if (unlikely(nr > sysctl_nr_open))
		nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1;

	fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT);
	if (!fdt)
		goto out;
	fdt->max_fds = nr;
	data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT);
	if (!data)
		goto out_fdt;
	fdt->fd = data;

	data = kvmalloc(max_t(size_t,
				 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES),
				 GFP_KERNEL_ACCOUNT);
	if (!data)
		goto out_arr;
	fdt->open_fds = data;
	data += nr / BITS_PER_BYTE;
	fdt->close_on_exec = data;
	data += nr / BITS_PER_BYTE;
	fdt->full_fds_bits = data;

	return fdt;

out_arr:
	kvfree(fdt->fd);
out_fdt:
	kfree(fdt);
out:
	return NULL;
}

/*
 * Expand the file descriptor table.
 * This function will allocate a new fdtable and both fd array and fdset, of
 * the given size.
 * Return <0 error code on error; 1 on successful completion.
 * The files->file_lock should be held on entry, and will be held on exit.
 */
static int expand_fdtable(struct files_struct *files, unsigned int nr)
	__releases(files->file_lock)
	__acquires(files->file_lock)
{
	struct fdtable *new_fdt, *cur_fdt;

	spin_unlock(&files->file_lock);
	new_fdt = alloc_fdtable(nr);

	/* make sure all __fd_install() have seen resize_in_progress
	 * or have finished their rcu_read_lock_sched() section.
	 */
	if (atomic_read(&files->count) > 1)
		synchronize_rcu();

	spin_lock(&files->file_lock);
	if (!new_fdt)
		return -ENOMEM;
	/*
	 * extremely unlikely race - sysctl_nr_open decreased between the check in
	 * caller and alloc_fdtable().  Cheaper to catch it here...
	 */
	if (unlikely(new_fdt->max_fds <= nr)) {
		__free_fdtable(new_fdt);
		return -EMFILE;
	}
	cur_fdt = files_fdtable(files);
	BUG_ON(nr < cur_fdt->max_fds);
	copy_fdtable(new_fdt, cur_fdt);
	rcu_assign_pointer(files->fdt, new_fdt);
	if (cur_fdt != &files->fdtab)
		call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
	/* coupled with smp_rmb() in __fd_install() */
	smp_wmb();
	return 1;
}

/*
 * Expand files.
 * This function will expand the file structures, if the requested size exceeds
 * the current capacity and there is room for expansion.
 * Return <0 error code on error; 0 when nothing done; 1 when files were
 * expanded and execution may have blocked.
 * The files->file_lock should be held on entry, and will be held on exit.
 */
static int expand_files(struct files_struct *files, unsigned int nr)
	__releases(files->file_lock)
	__acquires(files->file_lock)
{
	struct fdtable *fdt;
	int expanded = 0;

repeat:
	fdt = files_fdtable(files);

	/* Do we need to expand? */
	if (nr < fdt->max_fds)
		return expanded;

	/* Can we expand? */
	if (nr >= sysctl_nr_open)
		return -EMFILE;

	if (unlikely(files->resize_in_progress)) {
		spin_unlock(&files->file_lock);
		expanded = 1;
		wait_event(files->resize_wait, !files->resize_in_progress);
		spin_lock(&files->file_lock);
		goto repeat;
	}

	/* All good, so we try */
	files->resize_in_progress = true;
	expanded = expand_fdtable(files, nr);
	files->resize_in_progress = false;

	wake_up_all(&files->resize_wait);
	return expanded;
}

static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt)
{
	__set_bit(fd, fdt->close_on_exec);
}

static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt)
{
	if (test_bit(fd, fdt->close_on_exec))
		__clear_bit(fd, fdt->close_on_exec);
}

static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt)
{
	__set_bit(fd, fdt->open_fds);
	fd /= BITS_PER_LONG;
	if (!~fdt->open_fds[fd])
		__set_bit(fd, fdt->full_fds_bits);
}

static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt)
{
	__clear_bit(fd, fdt->open_fds);
	__clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits);
}

static unsigned int count_open_files(struct fdtable *fdt)
{
	unsigned int size = fdt->max_fds;
	unsigned int i;

	/* Find the last open fd */
	for (i = size / BITS_PER_LONG; i > 0; ) {
		if (fdt->open_fds[--i])
			break;
	}
	i = (i + 1) * BITS_PER_LONG;
	return i;
}

static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds)
{
	unsigned int count;

	count = count_open_files(fdt);
	if (max_fds < NR_OPEN_DEFAULT)
		max_fds = NR_OPEN_DEFAULT;
	return min(count, max_fds);
}

/*
 * Allocate a new files structure and copy contents from the
 * passed in files structure.
 * errorp will be valid only when the returned files_struct is NULL.
 */
struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp)
{
	struct files_struct *newf;
	struct file **old_fds, **new_fds;
	unsigned int open_files, i;
	struct fdtable *old_fdt, *new_fdt;

	*errorp = -ENOMEM;
	newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
	if (!newf)
		goto out;

	atomic_set(&newf->count, 1);

	spin_lock_init(&newf->file_lock);
	newf->resize_in_progress = false;
	init_waitqueue_head(&newf->resize_wait);
	newf->next_fd = 0;
	new_fdt = &newf->fdtab;
	new_fdt->max_fds = NR_OPEN_DEFAULT;
	new_fdt->close_on_exec = newf->close_on_exec_init;
	new_fdt->open_fds = newf->open_fds_init;
	new_fdt->full_fds_bits = newf->full_fds_bits_init;
	new_fdt->fd = &newf->fd_array[0];

	spin_lock(&oldf->file_lock);
	old_fdt = files_fdtable(oldf);
	open_files = sane_fdtable_size(old_fdt, max_fds);

	/*
	 * Check whether we need to allocate a larger fd array and fd set.
	 */
	while (unlikely(open_files > new_fdt->max_fds)) {
		spin_unlock(&oldf->file_lock);

		if (new_fdt != &newf->fdtab)
			__free_fdtable(new_fdt);

		new_fdt = alloc_fdtable(open_files - 1);
		if (!new_fdt) {
			*errorp = -ENOMEM;
			goto out_release;
		}

		/* beyond sysctl_nr_open; nothing to do */
		if (unlikely(new_fdt->max_fds < open_files)) {
			__free_fdtable(new_fdt);
			*errorp = -EMFILE;
			goto out_release;
		}

		/*
		 * Reacquire the oldf lock and a pointer to its fd table
		 * who knows it may have a new bigger fd table. We need
		 * the latest pointer.
		 */
		spin_lock(&oldf->file_lock);
		old_fdt = files_fdtable(oldf);
		open_files = sane_fdtable_size(old_fdt, max_fds);
	}

	copy_fd_bitmaps(new_fdt, old_fdt, open_files);

	old_fds = old_fdt->fd;
	new_fds = new_fdt->fd;

	for (i = open_files; i != 0; i--) {
		struct file *f = *old_fds++;
		if (f) {
			get_file(f);
		} else {
			/*
			 * The fd may be claimed in the fd bitmap but not yet
			 * instantiated in the files array if a sibling thread
			 * is partway through open().  So make sure that this
			 * fd is available to the new process.
			 */
			__clear_open_fd(open_files - i, new_fdt);
		}
		rcu_assign_pointer(*new_fds++, f);
	}
	spin_unlock(&oldf->file_lock);

	/* clear the remainder */
	memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *));

	rcu_assign_pointer(newf->fdt, new_fdt);

	return newf;

out_release:
	kmem_cache_free(files_cachep, newf);
out:
	return NULL;
}

static struct fdtable *close_files(struct files_struct * files)
{
	/*
	 * It is safe to dereference the fd table without RCU or
	 * ->file_lock because this is the last reference to the
	 * files structure.
	 */
	struct fdtable *fdt = rcu_dereference_raw(files->fdt);
	unsigned int i, j = 0;

	for (;;) {
		unsigned long set;
		i = j * BITS_PER_LONG;
		if (i >= fdt->max_fds)
			break;
		set = fdt->open_fds[j++];
		while (set) {
			if (set & 1) {
				struct file * file = xchg(&fdt->fd[i], NULL);
				if (file) {
					filp_close(file, files);
					cond_resched();
				}
			}
			i++;
			set >>= 1;
		}
	}

	return fdt;
}

struct files_struct *get_files_struct(struct task_struct *task)
{
	struct files_struct *files;

	task_lock(task);
	files = task->files;
	if (files)
		atomic_inc(&files->count);
	task_unlock(task);

	return files;
}

void put_files_struct(struct files_struct *files)
{
	if (atomic_dec_and_test(&files->count)) {
		struct fdtable *fdt = close_files(files);

		/* free the arrays if they are not embedded */
		if (fdt != &files->fdtab)
			__free_fdtable(fdt);
		kmem_cache_free(files_cachep, files);
	}
}

void exit_files(struct task_struct *tsk)
{
	struct files_struct * files = tsk->files;

	if (files) {
		io_uring_files_cancel(files);
		task_lock(tsk);
		tsk->files = NULL;
		task_unlock(tsk);
		put_files_struct(files);
	}
}

struct files_struct init_files = {
	.count		= ATOMIC_INIT(1),
	.fdt		= &init_files.fdtab,
	.fdtab		= {
		.max_fds	= NR_OPEN_DEFAULT,
		.fd		= &init_files.fd_array[0],
		.close_on_exec	= init_files.close_on_exec_init,
		.open_fds	= init_files.open_fds_init,
		.full_fds_bits	= init_files.full_fds_bits_init,
	},
	.file_lock	= __SPIN_LOCK_UNLOCKED(init_files.file_lock),
	.resize_wait	= __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait),
};

static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
{
	unsigned int maxfd = fdt->max_fds;
	unsigned int maxbit = maxfd / BITS_PER_LONG;
	unsigned int bitbit = start / BITS_PER_LONG;

	bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG;
	if (bitbit > maxfd)
		return maxfd;
	if (bitbit > start)
		start = bitbit;
	return find_next_zero_bit(fdt->open_fds, maxfd, start);
}

/*
 * allocate a file descriptor, mark it busy.
 */
int __alloc_fd(struct files_struct *files,
	       unsigned start, unsigned end, unsigned flags)
{
	unsigned int fd;
	int error;
	struct fdtable *fdt;

	spin_lock(&files->file_lock);
repeat:
	fdt = files_fdtable(files);
	fd = start;
	if (fd < files->next_fd)
		fd = files->next_fd;

	if (fd < fdt->max_fds)
		fd = find_next_fd(fdt, fd);

	/*
	 * N.B. For clone tasks sharing a files structure, this test
	 * will limit the total number of files that can be opened.
	 */
	error = -EMFILE;
	if (fd >= end)
		goto out;

	error = expand_files(files, fd);
	if (error < 0)
		goto out;

	/*
	 * If we needed to expand the fs array we
	 * might have blocked - try again.
	 */
	if (error)
		goto repeat;

	if (start <= files->next_fd)
		files->next_fd = fd + 1;

	__set_open_fd(fd, fdt);
	if (flags & O_CLOEXEC)
		__set_close_on_exec(fd, fdt);
	else
		__clear_close_on_exec(fd, fdt);
	error = fd;
#if 1
	/* Sanity check */
	if (rcu_access_pointer(fdt->fd[fd]) != NULL) {
		printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
		rcu_assign_pointer(fdt->fd[fd], NULL);
	}
#endif

out:
	spin_unlock(&files->file_lock);
	return error;
}

static int alloc_fd(unsigned start, unsigned flags)
{
	return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags);
}

int __get_unused_fd_flags(unsigned flags, unsigned long nofile)
{
	return __alloc_fd(current->files, 0, nofile, flags);
}

int get_unused_fd_flags(unsigned flags)
{
	return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE));
}
EXPORT_SYMBOL(get_unused_fd_flags);

static void __put_unused_fd(struct files_struct *files, unsigned int fd)
{
	struct fdtable *fdt = files_fdtable(files);
	__clear_open_fd(fd, fdt);
	if (fd < files->next_fd)
		files->next_fd = fd;
}

void put_unused_fd(unsigned int fd)
{
	struct files_struct *files = current->files;
	spin_lock(&files->file_lock);
	__put_unused_fd(files, fd);
	spin_unlock(&files->file_lock);
}

EXPORT_SYMBOL(put_unused_fd);

/*
 * Install a file pointer in the fd array.
 *
 * The VFS is full of places where we drop the files lock between
 * setting the open_fds bitmap and installing the file in the file
 * array.  At any such point, we are vulnerable to a dup2() race
 * installing a file in the array before us.  We need to detect this and
 * fput() the struct file we are about to overwrite in this case.
 *
 * It should never happen - if we allow dup2() do it, _really_ bad things
 * will follow.
 *
 * NOTE: __fd_install() variant is really, really low-level; don't
 * use it unless you are forced to by truly lousy API shoved down
 * your throat.  'files' *MUST* be either current->files or obtained
 * by get_files_struct(current) done by whoever had given it to you,
 * or really bad things will happen.  Normally you want to use
 * fd_install() instead.
 */

void __fd_install(struct files_struct *files, unsigned int fd,
		struct file *file)
{
	struct fdtable *fdt;

	rcu_read_lock_sched();

	if (unlikely(files->resize_in_progress)) {
		rcu_read_unlock_sched();
		spin_lock(&files->file_lock);
		fdt = files_fdtable(files);
		BUG_ON(fdt->fd[fd] != NULL);
		rcu_assign_pointer(fdt->fd[fd], file);
		spin_unlock(&files->file_lock);
		return;
	}
	/* coupled with smp_wmb() in expand_fdtable() */
	smp_rmb();
	fdt = rcu_dereference_sched(files->fdt);
	BUG_ON(fdt->fd[fd] != NULL);
	rcu_assign_pointer(fdt->fd[fd], file);
	rcu_read_unlock_sched();
}

/*
 * This consumes the "file" refcount, so callers should treat it
 * as if they had called fput(file).
 */
void fd_install(unsigned int fd, struct file *file)
{
	__fd_install(current->files, fd, file);
}

EXPORT_SYMBOL(fd_install);

static struct file *pick_file(struct files_struct *files, unsigned fd)
{
	struct file *file = NULL;
	struct fdtable *fdt;

	spin_lock(&files->file_lock);
	fdt = files_fdtable(files);
	if (fd >= fdt->max_fds)
		goto out_unlock;
	file = fdt->fd[fd];
	if (!file)
		goto out_unlock;
	rcu_assign_pointer(fdt->fd[fd], NULL);
	__put_unused_fd(files, fd);

out_unlock:
	spin_unlock(&files->file_lock);
	return file;
}

/*
 * The same warnings as for __alloc_fd()/__fd_install() apply here...
 */
int __close_fd(struct files_struct *files, unsigned fd)
{
	struct file *file;

	file = pick_file(files, fd);
	if (!file)
		return -EBADF;

	return filp_close(file, files);
}
EXPORT_SYMBOL(__close_fd); /* for ksys_close() */

/**
 * __close_range() - Close all file descriptors in a given range.
 *
 * @fd:     starting file descriptor to close
 * @max_fd: last file descriptor to close
 *
 * This closes a range of file descriptors. All file descriptors
 * from @fd up to and including @max_fd are closed.
 */
int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
{
	unsigned int cur_max;
	struct task_struct *me = current;
	struct files_struct *cur_fds = me->files, *fds = NULL;

	if (flags & ~CLOSE_RANGE_UNSHARE)
		return -EINVAL;

	if (fd > max_fd)
		return -EINVAL;

	rcu_read_lock();
	cur_max = files_fdtable(cur_fds)->max_fds;
	rcu_read_unlock();

	/* cap to last valid index into fdtable */
	cur_max--;

	if (flags & CLOSE_RANGE_UNSHARE) {
		int ret;
		unsigned int max_unshare_fds = NR_OPEN_MAX;

		/*
		 * If the requested range is greater than the current maximum,
		 * we're closing everything so only copy all file descriptors
		 * beneath the lowest file descriptor.
		 */
		if (max_fd >= cur_max)
			max_unshare_fds = fd;

		ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds);
		if (ret)
			return ret;

		/*
		 * We used to share our file descriptor table, and have now
		 * created a private one, make sure we're using it below.
		 */
		if (fds)
			swap(cur_fds, fds);
	}

	max_fd = min(max_fd, cur_max);
	while (fd <= max_fd) {
		struct file *file;

		file = pick_file(cur_fds, fd++);
		if (!file)
			continue;

		filp_close(file, cur_fds);
		cond_resched();
	}

	if (fds) {
		/*
		 * We're done closing the files we were supposed to. Time to install
		 * the new file descriptor table and drop the old one.
		 */
		task_lock(me);
		me->files = cur_fds;
		task_unlock(me);
		put_files_struct(fds);
	}

	return 0;
}

/*
 * variant of __close_fd that gets a ref on the file for later fput.
 * The caller must ensure that filp_close() called on the file, and then
 * an fput().
 */
int __close_fd_get_file(unsigned int fd, struct file **res)
{
	struct files_struct *files = current->files;
	struct file *file;
	struct fdtable *fdt;

	spin_lock(&files->file_lock);
	fdt = files_fdtable(files);
	if (fd >= fdt->max_fds)
		goto out_unlock;
	file = fdt->fd[fd];
	if (!file)
		goto out_unlock;
	rcu_assign_pointer(fdt->fd[fd], NULL);
	__put_unused_fd(files, fd);
	spin_unlock(&files->file_lock);
	get_file(file);
	*res = file;
	return 0;

out_unlock:
	spin_unlock(&files->file_lock);
	*res = NULL;
	return -ENOENT;
}

void do_close_on_exec(struct files_struct *files)
{
	unsigned i;
	struct fdtable *fdt;

	/* exec unshares first */
	spin_lock(&files->file_lock);
	for (i = 0; ; i++) {
		unsigned long set;
		unsigned fd = i * BITS_PER_LONG;
		fdt = files_fdtable(files);
		if (fd >= fdt->max_fds)
			break;
		set = fdt->close_on_exec[i];
		if (!set)
			continue;
		fdt->close_on_exec[i] = 0;
		for ( ; set ; fd++, set >>= 1) {
			struct file *file;
			if (!(set & 1))
				continue;
			file = fdt->fd[fd];
			if (!file)
				continue;
			rcu_assign_pointer(fdt->fd[fd], NULL);
			__put_unused_fd(files, fd);
			spin_unlock(&files->file_lock);
			filp_close(file, files);
			cond_resched();
			spin_lock(&files->file_lock);
		}

	}
	spin_unlock(&files->file_lock);
}

static struct file *__fget_files(struct files_struct *files, unsigned int fd,
				 fmode_t mask, unsigned int refs)
{
	struct file *file;

	rcu_read_lock();
loop:
	file = fcheck_files(files, fd);
	if (file) {
		/* File object ref couldn't be taken.
		 * dup2() atomicity guarantee is the reason
		 * we loop to catch the new file (or NULL pointer)
		 */
		if (file->f_mode & mask)
			file = NULL;
		else if (!get_file_rcu_many(file, refs))
			goto loop;
	}
	rcu_read_unlock();

	return file;
}

static inline struct file *__fget(unsigned int fd, fmode_t mask,
				  unsigned int refs)
{
	return __fget_files(current->files, fd, mask, refs);
}

struct file *fget_many(unsigned int fd, unsigned int refs)
{
	return __fget(fd, FMODE_PATH, refs);
}

struct file *fget(unsigned int fd)
{
	return __fget(fd, FMODE_PATH, 1);
}
EXPORT_SYMBOL(fget);

struct file *fget_raw(unsigned int fd)
{
	return __fget(fd, 0, 1);
}
EXPORT_SYMBOL(fget_raw);

struct file *fget_task(struct task_struct *task, unsigned int fd)
{
	struct file *file = NULL;

	task_lock(task);
	if (task->files)
		file = __fget_files(task->files, fd, 0, 1);
	task_unlock(task);

	return file;
}

/*
 * Lightweight file lookup - no refcnt increment if fd table isn't shared.
 *
 * You can use this instead of fget if you satisfy all of the following
 * conditions:
 * 1) You must call fput_light before exiting the syscall and returning control
 *    to userspace (i.e. you cannot remember the returned struct file * after
 *    returning to userspace).
 * 2) You must not call filp_close on the returned struct file * in between
 *    calls to fget_light and fput_light.
 * 3) You must not clone the current task in between the calls to fget_light
 *    and fput_light.
 *
 * The fput_needed flag returned by fget_light should be passed to the
 * corresponding fput_light.
 */
static unsigned long __fget_light(unsigned int fd, fmode_t mask)
{
	struct files_struct *files = current->files;
	struct file *file;

	if (atomic_read(&files->count) == 1) {
		file = files_lookup_fd_raw(files, fd);
		if (!file || unlikely(file->f_mode & mask))
			return 0;
		return (unsigned long)file;
	} else {
		file = __fget(fd, mask, 1);
		if (!file)
			return 0;
		return FDPUT_FPUT | (unsigned long)file;
	}
}
unsigned long __fdget(unsigned int fd)
{
	return __fget_light(fd, FMODE_PATH);
}
EXPORT_SYMBOL(__fdget);

unsigned long __fdget_raw(unsigned int fd)
{
	return __fget_light(fd, 0);
}

unsigned long __fdget_pos(unsigned int fd)
{
	unsigned long v = __fdget(fd);
	struct file *file = (struct file *)(v & ~3);

	if (file && (file->f_mode & FMODE_ATOMIC_POS)) {
		if (file_count(file) > 1) {
			v |= FDPUT_POS_UNLOCK;
			mutex_lock(&file->f_pos_lock);
		}
	}
	return v;
}

void __f_unlock_pos(struct file *f)
{
	mutex_unlock(&f->f_pos_lock);
}

/*
 * We only lock f_pos if we have threads or if the file might be
 * shared with another process. In both cases we'll have an elevated
 * file count (done either by fdget() or by fork()).
 */

void set_close_on_exec(unsigned int fd, int flag)
{
	struct files_struct *files = current->files;
	struct fdtable *fdt;
	spin_lock(&files->file_lock);
	fdt = files_fdtable(files);
	if (flag)
		__set_close_on_exec(fd, fdt);
	else
		__clear_close_on_exec(fd, fdt);
	spin_unlock(&files->file_lock);
}

bool get_close_on_exec(unsigned int fd)
{
	struct files_struct *files = current->files;
	struct fdtable *fdt;
	bool res;
	rcu_read_lock();
	fdt = files_fdtable(files);
	res = close_on_exec(fd, fdt);
	rcu_read_unlock();
	return res;
}

static int do_dup2(struct files_struct *files,
	struct file *file, unsigned fd, unsigned flags)
__releases(&files->file_lock)
{
	struct file *tofree;
	struct fdtable *fdt;

	/*
	 * We need to detect attempts to do dup2() over allocated but still
	 * not finished descriptor.  NB: OpenBSD avoids that at the price of
	 * extra work in their equivalent of fget() - they insert struct
	 * file immediately after grabbing descriptor, mark it larval if
	 * more work (e.g. actual opening) is needed and make sure that
	 * fget() treats larval files as absent.  Potentially interesting,
	 * but while extra work in fget() is trivial, locking implications
	 * and amount of surgery on open()-related paths in VFS are not.
	 * FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
	 * deadlocks in rather amusing ways, AFAICS.  All of that is out of
	 * scope of POSIX or SUS, since neither considers shared descriptor
	 * tables and this condition does not arise without those.
	 */
	fdt = files_fdtable(files);
	tofree = fdt->fd[fd];
	if (!tofree && fd_is_open(fd, fdt))
		goto Ebusy;
	get_file(file);
	rcu_assign_pointer(fdt->fd[fd], file);
	__set_open_fd(fd, fdt);
	if (flags & O_CLOEXEC)
		__set_close_on_exec(fd, fdt);
	else
		__clear_close_on_exec(fd, fdt);
	spin_unlock(&files->file_lock);

	if (tofree)
		filp_close(tofree, files);

	return fd;

Ebusy:
	spin_unlock(&files->file_lock);
	return -EBUSY;
}

int replace_fd(unsigned fd, struct file *file, unsigned flags)
{
	int err;
	struct files_struct *files = current->files;

	if (!file)
		return __close_fd(files, fd);

	if (fd >= rlimit(RLIMIT_NOFILE))
		return -EBADF;

	spin_lock(&files->file_lock);
	err = expand_files(files, fd);
	if (unlikely(err < 0))
		goto out_unlock;
	return do_dup2(files, file, fd, flags);

out_unlock:
	spin_unlock(&files->file_lock);
	return err;
}

/**
 * __receive_fd() - Install received file into file descriptor table
 *
 * @fd: fd to install into (if negative, a new fd will be allocated)
 * @file: struct file that was received from another process
 * @ufd: __user pointer to write new fd number to
 * @o_flags: the O_* flags to apply to the new fd entry
 *
 * Installs a received file into the file descriptor table, with appropriate
 * checks and count updates. Optionally writes the fd number to userspace, if
 * @ufd is non-NULL.
 *
 * This helper handles its own reference counting of the incoming
 * struct file.
 *
 * Returns newly install fd or -ve on error.
 */
int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags)
{
	int new_fd;
	int error;

	error = security_file_receive(file);
	if (error)
		return error;

	if (fd < 0) {
		new_fd = get_unused_fd_flags(o_flags);
		if (new_fd < 0)
			return new_fd;
	} else {
		new_fd = fd;
	}

	if (ufd) {
		error = put_user(new_fd, ufd);
		if (error) {
			if (fd < 0)
				put_unused_fd(new_fd);
			return error;
		}
	}

	if (fd < 0) {
		fd_install(new_fd, get_file(file));
	} else {
		error = replace_fd(new_fd, file, o_flags);
		if (error)
			return error;
	}

	/* Bump the sock usage counts, if any. */
	__receive_sock(file);
	return new_fd;
}

static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
{
	int err = -EBADF;
	struct file *file;
	struct files_struct *files = current->files;

	if ((flags & ~O_CLOEXEC) != 0)
		return -EINVAL;

	if (unlikely(oldfd == newfd))
		return -EINVAL;

	if (newfd >= rlimit(RLIMIT_NOFILE))
		return -EBADF;

	spin_lock(&files->file_lock);
	err = expand_files(files, newfd);
	file = fcheck(oldfd);
	if (unlikely(!file))
		goto Ebadf;
	if (unlikely(err < 0)) {
		if (err == -EMFILE)
			goto Ebadf;
		goto out_unlock;
	}
	return do_dup2(files, file, newfd, flags);

Ebadf:
	err = -EBADF;
out_unlock:
	spin_unlock(&files->file_lock);
	return err;
}

SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
{
	return ksys_dup3(oldfd, newfd, flags);
}

SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
{
	if (unlikely(newfd == oldfd)) { /* corner case */
		struct files_struct *files = current->files;
		int retval = oldfd;

		rcu_read_lock();
		if (!fcheck_files(files, oldfd))
			retval = -EBADF;
		rcu_read_unlock();
		return retval;
	}
	return ksys_dup3(oldfd, newfd, 0);
}

SYSCALL_DEFINE1(dup, unsigned int, fildes)
{
	int ret = -EBADF;
	struct file *file = fget_raw(fildes);

	if (file) {
		ret = get_unused_fd_flags(0);
		if (ret >= 0)
			fd_install(ret, file);
		else
			fput(file);
	}
	return ret;
}

int f_dupfd(unsigned int from, struct file *file, unsigned flags)
{
	int err;
	if (from >= rlimit(RLIMIT_NOFILE))
		return -EINVAL;
	err = alloc_fd(from, flags);
	if (err >= 0) {
		get_file(file);
		fd_install(err, file);
	}
	return err;
}

int iterate_fd(struct files_struct *files, unsigned n,
		int (*f)(const void *, struct file *, unsigned),
		const void *p)
{
	struct fdtable *fdt;
	int res = 0;
	if (!files)
		return 0;
	spin_lock(&files->file_lock);
	for (fdt = files_fdtable(files); n < fdt->max_fds; n++) {
		struct file *file;
		file = rcu_dereference_check_fdtable(files, fdt->fd[n]);
		if (!file)
			continue;
		res = f(p, file, n);
		if (res)
			break;
	}
	spin_unlock(&files->file_lock);
	return res;
}
EXPORT_SYMBOL(iterate_fd);