aboutsummaryrefslogtreecommitdiff
path: root/fs/pipe.c
blob: 070aad543382a4e30aa0bd5eef94b5dabba7219d (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/pipe.c
 *
 *  Copyright (C) 1991, 1992, 1999  Linus Torvalds
 */

#include <linux/mm.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/log2.h>
#include <linux/mount.h>
#include <linux/magic.h>
#include <linux/pipe_fs_i.h>
#include <linux/uio.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/audit.h>
#include <linux/syscalls.h>
#include <linux/fcntl.h>
#include <linux/memcontrol.h>

#include <linux/uaccess.h>
#include <asm/ioctls.h>

#include "internal.h"

/*
 * The max size that a non-root user is allowed to grow the pipe. Can
 * be set by root in /proc/sys/fs/pipe-max-size
 */
unsigned int pipe_max_size = 1048576;

/* Maximum allocatable pages per user. Hard limit is unset by default, soft
 * matches default values.
 */
unsigned long pipe_user_pages_hard;
unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;

/*
 * We use a start+len construction, which provides full use of the 
 * allocated memory.
 * -- Florian Coosmann (FGC)
 * 
 * Reads with count = 0 should always return 0.
 * -- Julian Bradfield 1999-06-07.
 *
 * FIFOs and Pipes now generate SIGIO for both readers and writers.
 * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16
 *
 * pipe_read & write cleanup
 * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09
 */

static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass)
{
	if (pipe->files)
		mutex_lock_nested(&pipe->mutex, subclass);
}

void pipe_lock(struct pipe_inode_info *pipe)
{
	/*
	 * pipe_lock() nests non-pipe inode locks (for writing to a file)
	 */
	pipe_lock_nested(pipe, I_MUTEX_PARENT);
}
EXPORT_SYMBOL(pipe_lock);

void pipe_unlock(struct pipe_inode_info *pipe)
{
	if (pipe->files)
		mutex_unlock(&pipe->mutex);
}
EXPORT_SYMBOL(pipe_unlock);

static inline void __pipe_lock(struct pipe_inode_info *pipe)
{
	mutex_lock_nested(&pipe->mutex, I_MUTEX_PARENT);
}

static inline void __pipe_unlock(struct pipe_inode_info *pipe)
{
	mutex_unlock(&pipe->mutex);
}

void pipe_double_lock(struct pipe_inode_info *pipe1,
		      struct pipe_inode_info *pipe2)
{
	BUG_ON(pipe1 == pipe2);

	if (pipe1 < pipe2) {
		pipe_lock_nested(pipe1, I_MUTEX_PARENT);
		pipe_lock_nested(pipe2, I_MUTEX_CHILD);
	} else {
		pipe_lock_nested(pipe2, I_MUTEX_PARENT);
		pipe_lock_nested(pipe1, I_MUTEX_CHILD);
	}
}

/* Drop the inode semaphore and wait for a pipe event, atomically */
void pipe_wait(struct pipe_inode_info *pipe)
{
	DEFINE_WAIT(wait);

	/*
	 * Pipes are system-local resources, so sleeping on them
	 * is considered a noninteractive wait:
	 */
	prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE);
	pipe_unlock(pipe);
	schedule();
	finish_wait(&pipe->wait, &wait);
	pipe_lock(pipe);
}

static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
				  struct pipe_buffer *buf)
{
	struct page *page = buf->page;

	/*
	 * If nobody else uses this page, and we don't already have a
	 * temporary page, let's keep track of it as a one-deep
	 * allocation cache. (Otherwise just release our reference to it)
	 */
	if (page_count(page) == 1 && !pipe->tmp_page)
		pipe->tmp_page = page;
	else
		put_page(page);
}

static int anon_pipe_buf_steal(struct pipe_inode_info *pipe,
			       struct pipe_buffer *buf)
{
	struct page *page = buf->page;

	if (page_count(page) == 1) {
		memcg_kmem_uncharge(page, 0);
		__SetPageLocked(page);
		return 0;
	}
	return 1;
}

/**
 * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer
 * @pipe:	the pipe that the buffer belongs to
 * @buf:	the buffer to attempt to steal
 *
 * Description:
 *	This function attempts to steal the &struct page attached to
 *	@buf. If successful, this function returns 0 and returns with
 *	the page locked. The caller may then reuse the page for whatever
 *	he wishes; the typical use is insertion into a different file
 *	page cache.
 */
int generic_pipe_buf_steal(struct pipe_inode_info *pipe,
			   struct pipe_buffer *buf)
{
	struct page *page = buf->page;

	/*
	 * A reference of one is golden, that means that the owner of this
	 * page is the only one holding a reference to it. lock the page
	 * and return OK.
	 */
	if (page_count(page) == 1) {
		lock_page(page);
		return 0;
	}

	return 1;
}
EXPORT_SYMBOL(generic_pipe_buf_steal);

/**
 * generic_pipe_buf_get - get a reference to a &struct pipe_buffer
 * @pipe:	the pipe that the buffer belongs to
 * @buf:	the buffer to get a reference to
 *
 * Description:
 *	This function grabs an extra reference to @buf. It's used in
 *	in the tee() system call, when we duplicate the buffers in one
 *	pipe into another.
 */
void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
{
	get_page(buf->page);
}
EXPORT_SYMBOL(generic_pipe_buf_get);

/**
 * generic_pipe_buf_confirm - verify contents of the pipe buffer
 * @info:	the pipe that the buffer belongs to
 * @buf:	the buffer to confirm
 *
 * Description:
 *	This function does nothing, because the generic pipe code uses
 *	pages that are always good when inserted into the pipe.
 */
int generic_pipe_buf_confirm(struct pipe_inode_info *info,
			     struct pipe_buffer *buf)
{
	return 0;
}
EXPORT_SYMBOL(generic_pipe_buf_confirm);

/**
 * generic_pipe_buf_release - put a reference to a &struct pipe_buffer
 * @pipe:	the pipe that the buffer belongs to
 * @buf:	the buffer to put a reference to
 *
 * Description:
 *	This function releases a reference to @buf.
 */
void generic_pipe_buf_release(struct pipe_inode_info *pipe,
			      struct pipe_buffer *buf)
{
	put_page(buf->page);
}
EXPORT_SYMBOL(generic_pipe_buf_release);

/* New data written to a pipe may be appended to a buffer with this type. */
static const struct pipe_buf_operations anon_pipe_buf_ops = {
	.confirm = generic_pipe_buf_confirm,
	.release = anon_pipe_buf_release,
	.steal = anon_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

static const struct pipe_buf_operations anon_pipe_buf_nomerge_ops = {
	.confirm = generic_pipe_buf_confirm,
	.release = anon_pipe_buf_release,
	.steal = anon_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

static const struct pipe_buf_operations packet_pipe_buf_ops = {
	.confirm = generic_pipe_buf_confirm,
	.release = anon_pipe_buf_release,
	.steal = anon_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

/**
 * pipe_buf_mark_unmergeable - mark a &struct pipe_buffer as unmergeable
 * @buf:	the buffer to mark
 *
 * Description:
 *	This function ensures that no future writes will be merged into the
 *	given &struct pipe_buffer. This is necessary when multiple pipe buffers
 *	share the same backing page.
 */
void pipe_buf_mark_unmergeable(struct pipe_buffer *buf)
{
	if (buf->ops == &anon_pipe_buf_ops)
		buf->ops = &anon_pipe_buf_nomerge_ops;
}

static bool pipe_buf_can_merge(struct pipe_buffer *buf)
{
	return buf->ops == &anon_pipe_buf_ops;
}

static ssize_t
pipe_read(struct kiocb *iocb, struct iov_iter *to)
{
	size_t total_len = iov_iter_count(to);
	struct file *filp = iocb->ki_filp;
	struct pipe_inode_info *pipe = filp->private_data;
	int do_wakeup;
	ssize_t ret;

	/* Null read succeeds. */
	if (unlikely(total_len == 0))
		return 0;

	do_wakeup = 0;
	ret = 0;
	__pipe_lock(pipe);
	for (;;) {
		int bufs = pipe->nrbufs;
		if (bufs) {
			int curbuf = pipe->curbuf;
			struct pipe_buffer *buf = pipe->bufs + curbuf;
			size_t chars = buf->len;
			size_t written;
			int error;

			if (chars > total_len)
				chars = total_len;

			error = pipe_buf_confirm(pipe, buf);
			if (error) {
				if (!ret)
					ret = error;
				break;
			}

			written = copy_page_to_iter(buf->page, buf->offset, chars, to);
			if (unlikely(written < chars)) {
				if (!ret)
					ret = -EFAULT;
				break;
			}
			ret += chars;
			buf->offset += chars;
			buf->len -= chars;

			/* Was it a packet buffer? Clean up and exit */
			if (buf->flags & PIPE_BUF_FLAG_PACKET) {
				total_len = chars;
				buf->len = 0;
			}

			if (!buf->len) {
				pipe_buf_release(pipe, buf);
				curbuf = (curbuf + 1) & (pipe->buffers - 1);
				pipe->curbuf = curbuf;
				pipe->nrbufs = --bufs;
				do_wakeup = 1;
			}
			total_len -= chars;
			if (!total_len)
				break;	/* common path: read succeeded */
		}
		if (bufs)	/* More to do? */
			continue;
		if (!pipe->writers)
			break;
		if (!pipe->waiting_writers) {
			/* syscall merging: Usually we must not sleep
			 * if O_NONBLOCK is set, or if we got some data.
			 * But if a writer sleeps in kernel space, then
			 * we can wait for that data without violating POSIX.
			 */
			if (ret)
				break;
			if (filp->f_flags & O_NONBLOCK) {
				ret = -EAGAIN;
				break;
			}
		}
		if (signal_pending(current)) {
			if (!ret)
				ret = -ERESTARTSYS;
			break;
		}
		if (do_wakeup) {
			wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM);
 			kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
		}
		pipe_wait(pipe);
	}
	__pipe_unlock(pipe);

	/* Signal writers asynchronously that there is more room. */
	if (do_wakeup) {
		wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM);
		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
	}
	if (ret > 0)
		file_accessed(filp);
	return ret;
}

static inline int is_packetized(struct file *file)
{
	return (file->f_flags & O_DIRECT) != 0;
}

static ssize_t
pipe_write(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *filp = iocb->ki_filp;
	struct pipe_inode_info *pipe = filp->private_data;
	ssize_t ret = 0;
	int do_wakeup = 0;
	size_t total_len = iov_iter_count(from);
	ssize_t chars;

	/* Null write succeeds. */
	if (unlikely(total_len == 0))
		return 0;

	__pipe_lock(pipe);

	if (!pipe->readers) {
		send_sig(SIGPIPE, current, 0);
		ret = -EPIPE;
		goto out;
	}

	/* We try to merge small writes */
	chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */
	if (pipe->nrbufs && chars != 0) {
		int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) &
							(pipe->buffers - 1);
		struct pipe_buffer *buf = pipe->bufs + lastbuf;
		int offset = buf->offset + buf->len;

		if (pipe_buf_can_merge(buf) && offset + chars <= PAGE_SIZE) {
			ret = pipe_buf_confirm(pipe, buf);
			if (ret)
				goto out;

			ret = copy_page_from_iter(buf->page, offset, chars, from);
			if (unlikely(ret < chars)) {
				ret = -EFAULT;
				goto out;
			}
			do_wakeup = 1;
			buf->len += ret;
			if (!iov_iter_count(from))
				goto out;
		}
	}

	for (;;) {
		int bufs;

		if (!pipe->readers) {
			send_sig(SIGPIPE, current, 0);
			if (!ret)
				ret = -EPIPE;
			break;
		}
		bufs = pipe->nrbufs;
		if (bufs < pipe->buffers) {
			int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1);
			struct pipe_buffer *buf = pipe->bufs + newbuf;
			struct page *page = pipe->tmp_page;
			int copied;

			if (!page) {
				page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT);
				if (unlikely(!page)) {
					ret = ret ? : -ENOMEM;
					break;
				}
				pipe->tmp_page = page;
			}
			/* Always wake up, even if the copy fails. Otherwise
			 * we lock up (O_NONBLOCK-)readers that sleep due to
			 * syscall merging.
			 * FIXME! Is this really true?
			 */
			do_wakeup = 1;
			copied = copy_page_from_iter(page, 0, PAGE_SIZE, from);
			if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) {
				if (!ret)
					ret = -EFAULT;
				break;
			}
			ret += copied;

			/* Insert it into the buffer array */
			buf->page = page;
			buf->ops = &anon_pipe_buf_ops;
			buf->offset = 0;
			buf->len = copied;
			buf->flags = 0;
			if (is_packetized(filp)) {
				buf->ops = &packet_pipe_buf_ops;
				buf->flags = PIPE_BUF_FLAG_PACKET;
			}
			pipe->nrbufs = ++bufs;
			pipe->tmp_page = NULL;

			if (!iov_iter_count(from))
				break;
		}
		if (bufs < pipe->buffers)
			continue;
		if (filp->f_flags & O_NONBLOCK) {
			if (!ret)
				ret = -EAGAIN;
			break;
		}
		if (signal_pending(current)) {
			if (!ret)
				ret = -ERESTARTSYS;
			break;
		}
		if (do_wakeup) {
			wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM);
			kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
			do_wakeup = 0;
		}
		pipe->waiting_writers++;
		pipe_wait(pipe);
		pipe->waiting_writers--;
	}
out:
	__pipe_unlock(pipe);
	if (do_wakeup) {
		wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM);
		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
	}
	if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) {
		int err = file_update_time(filp);
		if (err)
			ret = err;
		sb_end_write(file_inode(filp)->i_sb);
	}
	return ret;
}

static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
	struct pipe_inode_info *pipe = filp->private_data;
	int count, buf, nrbufs;

	switch (cmd) {
		case FIONREAD:
			__pipe_lock(pipe);
			count = 0;
			buf = pipe->curbuf;
			nrbufs = pipe->nrbufs;
			while (--nrbufs >= 0) {
				count += pipe->bufs[buf].len;
				buf = (buf+1) & (pipe->buffers - 1);
			}
			__pipe_unlock(pipe);

			return put_user(count, (int __user *)arg);
		default:
			return -ENOIOCTLCMD;
	}
}

/* No kernel lock held - fine */
static __poll_t
pipe_poll(struct file *filp, poll_table *wait)
{
	__poll_t mask;
	struct pipe_inode_info *pipe = filp->private_data;
	int nrbufs;

	poll_wait(filp, &pipe->wait, wait);

	/* Reading only -- no need for acquiring the semaphore.  */
	nrbufs = pipe->nrbufs;
	mask = 0;
	if (filp->f_mode & FMODE_READ) {
		mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
		if (!pipe->writers && filp->f_version != pipe->w_counter)
			mask |= EPOLLHUP;
	}

	if (filp->f_mode & FMODE_WRITE) {
		mask |= (nrbufs < pipe->buffers) ? EPOLLOUT | EPOLLWRNORM : 0;
		/*
		 * Most Unices do not set EPOLLERR for FIFOs but on Linux they
		 * behave exactly like pipes for poll().
		 */
		if (!pipe->readers)
			mask |= EPOLLERR;
	}

	return mask;
}

static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe)
{
	int kill = 0;

	spin_lock(&inode->i_lock);
	if (!--pipe->files) {
		inode->i_pipe = NULL;
		kill = 1;
	}
	spin_unlock(&inode->i_lock);

	if (kill)
		free_pipe_info(pipe);
}

static int
pipe_release(struct inode *inode, struct file *file)
{
	struct pipe_inode_info *pipe = file->private_data;

	__pipe_lock(pipe);
	if (file->f_mode & FMODE_READ)
		pipe->readers--;
	if (file->f_mode & FMODE_WRITE)
		pipe->writers--;

	if (pipe->readers || pipe->writers) {
		wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM | EPOLLERR | EPOLLHUP);
		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
	}
	__pipe_unlock(pipe);

	put_pipe_info(inode, pipe);
	return 0;
}

static int
pipe_fasync(int fd, struct file *filp, int on)
{
	struct pipe_inode_info *pipe = filp->private_data;
	int retval = 0;

	__pipe_lock(pipe);
	if (filp->f_mode & FMODE_READ)
		retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
	if ((filp->f_mode & FMODE_WRITE) && retval >= 0) {
		retval = fasync_helper(fd, filp, on, &pipe->fasync_writers);
		if (retval < 0 && (filp->f_mode & FMODE_READ))
			/* this can happen only if on == T */
			fasync_helper(-1, filp, 0, &pipe->fasync_readers);
	}
	__pipe_unlock(pipe);
	return retval;
}

static unsigned long account_pipe_buffers(struct user_struct *user,
                                 unsigned long old, unsigned long new)
{
	return atomic_long_add_return(new - old, &user->pipe_bufs);
}

static bool too_many_pipe_buffers_soft(unsigned long user_bufs)
{
	unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft);

	return soft_limit && user_bufs > soft_limit;
}

static bool too_many_pipe_buffers_hard(unsigned long user_bufs)
{
	unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard);

	return hard_limit && user_bufs > hard_limit;
}

static bool is_unprivileged_user(void)
{
	return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
}

struct pipe_inode_info *alloc_pipe_info(void)
{
	struct pipe_inode_info *pipe;
	unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
	struct user_struct *user = get_current_user();
	unsigned long user_bufs;
	unsigned int max_size = READ_ONCE(pipe_max_size);

	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT);
	if (pipe == NULL)
		goto out_free_uid;

	if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE))
		pipe_bufs = max_size >> PAGE_SHIFT;

	user_bufs = account_pipe_buffers(user, 0, pipe_bufs);

	if (too_many_pipe_buffers_soft(user_bufs) && is_unprivileged_user()) {
		user_bufs = account_pipe_buffers(user, pipe_bufs, 1);
		pipe_bufs = 1;
	}

	if (too_many_pipe_buffers_hard(user_bufs) && is_unprivileged_user())
		goto out_revert_acct;

	pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer),
			     GFP_KERNEL_ACCOUNT);

	if (pipe->bufs) {
		init_waitqueue_head(&pipe->wait);
		pipe->r_counter = pipe->w_counter = 1;
		pipe->buffers = pipe_bufs;
		pipe->user = user;
		mutex_init(&pipe->mutex);
		return pipe;
	}

out_revert_acct:
	(void) account_pipe_buffers(user, pipe_bufs, 0);
	kfree(pipe);
out_free_uid:
	free_uid(user);
	return NULL;
}

void free_pipe_info(struct pipe_inode_info *pipe)
{
	int i;

	(void) account_pipe_buffers(pipe->user, pipe->buffers, 0);
	free_uid(pipe->user);
	for (i = 0; i < pipe->buffers; i++) {
		struct pipe_buffer *buf = pipe->bufs + i;
		if (buf->ops)
			pipe_buf_release(pipe, buf);
	}
	if (pipe->tmp_page)
		__free_page(pipe->tmp_page);
	kfree(pipe->bufs);
	kfree(pipe);
}

static struct vfsmount *pipe_mnt __read_mostly;

/*
 * pipefs_dname() is called from d_path().
 */
static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen)
{
	return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
				d_inode(dentry)->i_ino);
}

static const struct dentry_operations pipefs_dentry_operations = {
	.d_dname	= pipefs_dname,
};

static struct inode * get_pipe_inode(void)
{
	struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb);
	struct pipe_inode_info *pipe;

	if (!inode)
		goto fail_inode;

	inode->i_ino = get_next_ino();

	pipe = alloc_pipe_info();
	if (!pipe)
		goto fail_iput;

	inode->i_pipe = pipe;
	pipe->files = 2;
	pipe->readers = pipe->writers = 1;
	inode->i_fop = &pipefifo_fops;

	/*
	 * Mark the inode dirty from the very beginning,
	 * that way it will never be moved to the dirty
	 * list because "mark_inode_dirty()" will think
	 * that it already _is_ on the dirty list.
	 */
	inode->i_state = I_DIRTY;
	inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);

	return inode;

fail_iput:
	iput(inode);

fail_inode:
	return NULL;
}

int create_pipe_files(struct file **res, int flags)
{
	struct inode *inode = get_pipe_inode();
	struct file *f;

	if (!inode)
		return -ENFILE;

	f = alloc_file_pseudo(inode, pipe_mnt, "",
				O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
				&pipefifo_fops);
	if (IS_ERR(f)) {
		free_pipe_info(inode->i_pipe);
		iput(inode);
		return PTR_ERR(f);
	}

	f->private_data = inode->i_pipe;

	res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK),
				  &pipefifo_fops);
	if (IS_ERR(res[0])) {
		put_pipe_info(inode, inode->i_pipe);
		fput(f);
		return PTR_ERR(res[0]);
	}
	res[0]->private_data = inode->i_pipe;
	res[1] = f;
	return 0;
}

static int __do_pipe_flags(int *fd, struct file **files, int flags)
{
	int error;
	int fdw, fdr;

	if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT))
		return -EINVAL;

	error = create_pipe_files(files, flags);
	if (error)
		return error;

	error = get_unused_fd_flags(flags);
	if (error < 0)
		goto err_read_pipe;
	fdr = error;

	error = get_unused_fd_flags(flags);
	if (error < 0)
		goto err_fdr;
	fdw = error;

	audit_fd_pair(fdr, fdw);
	fd[0] = fdr;
	fd[1] = fdw;
	return 0;

 err_fdr:
	put_unused_fd(fdr);
 err_read_pipe:
	fput(files[0]);
	fput(files[1]);
	return error;
}

int do_pipe_flags(int *fd, int flags)
{
	struct file *files[2];
	int error = __do_pipe_flags(fd, files, flags);
	if (!error) {
		fd_install(fd[0], files[0]);
		fd_install(fd[1], files[1]);
	}
	return error;
}

/*
 * sys_pipe() is the normal C calling standard for creating
 * a pipe. It's not the way Unix traditionally does this, though.
 */
static int do_pipe2(int __user *fildes, int flags)
{
	struct file *files[2];
	int fd[2];
	int error;

	error = __do_pipe_flags(fd, files, flags);
	if (!error) {
		if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) {
			fput(files[0]);
			fput(files[1]);
			put_unused_fd(fd[0]);
			put_unused_fd(fd[1]);
			error = -EFAULT;
		} else {
			fd_install(fd[0], files[0]);
			fd_install(fd[1], files[1]);
		}
	}
	return error;
}

SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags)
{
	return do_pipe2(fildes, flags);
}

SYSCALL_DEFINE1(pipe, int __user *, fildes)
{
	return do_pipe2(fildes, 0);
}

static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt)
{
	int cur = *cnt;	

	while (cur == *cnt) {
		pipe_wait(pipe);
		if (signal_pending(current))
			break;
	}
	return cur == *cnt ? -ERESTARTSYS : 0;
}

static void wake_up_partner(struct pipe_inode_info *pipe)
{
	wake_up_interruptible(&pipe->wait);
}

static int fifo_open(struct inode *inode, struct file *filp)
{
	struct pipe_inode_info *pipe;
	bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC;
	int ret;

	filp->f_version = 0;

	spin_lock(&inode->i_lock);
	if (inode->i_pipe) {
		pipe = inode->i_pipe;
		pipe->files++;
		spin_unlock(&inode->i_lock);
	} else {
		spin_unlock(&inode->i_lock);
		pipe = alloc_pipe_info();
		if (!pipe)
			return -ENOMEM;
		pipe->files = 1;
		spin_lock(&inode->i_lock);
		if (unlikely(inode->i_pipe)) {
			inode->i_pipe->files++;
			spin_unlock(&inode->i_lock);
			free_pipe_info(pipe);
			pipe = inode->i_pipe;
		} else {
			inode->i_pipe = pipe;
			spin_unlock(&inode->i_lock);
		}
	}
	filp->private_data = pipe;
	/* OK, we have a pipe and it's pinned down */

	__pipe_lock(pipe);

	/* We can only do regular read/write on fifos */
	filp->f_mode &= (FMODE_READ | FMODE_WRITE);

	switch (filp->f_mode) {
	case FMODE_READ:
	/*
	 *  O_RDONLY
	 *  POSIX.1 says that O_NONBLOCK means return with the FIFO
	 *  opened, even when there is no process writing the FIFO.
	 */
		pipe->r_counter++;
		if (pipe->readers++ == 0)
			wake_up_partner(pipe);

		if (!is_pipe && !pipe->writers) {
			if ((filp->f_flags & O_NONBLOCK)) {
				/* suppress EPOLLHUP until we have
				 * seen a writer */
				filp->f_version = pipe->w_counter;
			} else {
				if (wait_for_partner(pipe, &pipe->w_counter))
					goto err_rd;
			}
		}
		break;
	
	case FMODE_WRITE:
	/*
	 *  O_WRONLY
	 *  POSIX.1 says that O_NONBLOCK means return -1 with
	 *  errno=ENXIO when there is no process reading the FIFO.
	 */
		ret = -ENXIO;
		if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers)
			goto err;

		pipe->w_counter++;
		if (!pipe->writers++)
			wake_up_partner(pipe);

		if (!is_pipe && !pipe->readers) {
			if (wait_for_partner(pipe, &pipe->r_counter))
				goto err_wr;
		}
		break;
	
	case FMODE_READ | FMODE_WRITE:
	/*
	 *  O_RDWR
	 *  POSIX.1 leaves this case "undefined" when O_NONBLOCK is set.
	 *  This implementation will NEVER block on a O_RDWR open, since
	 *  the process can at least talk to itself.
	 */

		pipe->readers++;
		pipe->writers++;
		pipe->r_counter++;
		pipe->w_counter++;
		if (pipe->readers == 1 || pipe->writers == 1)
			wake_up_partner(pipe);
		break;

	default:
		ret = -EINVAL;
		goto err;
	}

	/* Ok! */
	__pipe_unlock(pipe);
	return 0;

err_rd:
	if (!--pipe->readers)
		wake_up_interruptible(&pipe->wait);
	ret = -ERESTARTSYS;
	goto err;

err_wr:
	if (!--pipe->writers)
		wake_up_interruptible(&pipe->wait);
	ret = -ERESTARTSYS;
	goto err;

err:
	__pipe_unlock(pipe);

	put_pipe_info(inode, pipe);
	return ret;
}

const struct file_operations pipefifo_fops = {
	.open		= fifo_open,
	.llseek		= no_llseek,
	.read_iter	= pipe_read,
	.write_iter	= pipe_write,
	.poll		= pipe_poll,
	.unlocked_ioctl	= pipe_ioctl,
	.release	= pipe_release,
	.fasync		= pipe_fasync,
};

/*
 * Currently we rely on the pipe array holding a power-of-2 number
 * of pages. Returns 0 on error.
 */
unsigned int round_pipe_size(unsigned long size)
{
	if (size > (1U << 31))
		return 0;

	/* Minimum pipe size, as required by POSIX */
	if (size < PAGE_SIZE)
		return PAGE_SIZE;

	return roundup_pow_of_two(size);
}

/*
 * Allocate a new array of pipe buffers and copy the info over. Returns the
 * pipe size if successful, or return -ERROR on error.
 */
static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
{
	struct pipe_buffer *bufs;
	unsigned int size, nr_pages;
	unsigned long user_bufs;
	long ret = 0;

	size = round_pipe_size(arg);
	nr_pages = size >> PAGE_SHIFT;

	if (!nr_pages)
		return -EINVAL;

	/*
	 * If trying to increase the pipe capacity, check that an
	 * unprivileged user is not trying to exceed various limits
	 * (soft limit check here, hard limit check just below).
	 * Decreasing the pipe capacity is always permitted, even
	 * if the user is currently over a limit.
	 */
	if (nr_pages > pipe->buffers &&
			size > pipe_max_size && !capable(CAP_SYS_RESOURCE))
		return -EPERM;

	user_bufs = account_pipe_buffers(pipe->user, pipe->buffers, nr_pages);

	if (nr_pages > pipe->buffers &&
			(too_many_pipe_buffers_hard(user_bufs) ||
			 too_many_pipe_buffers_soft(user_bufs)) &&
			is_unprivileged_user()) {
		ret = -EPERM;
		goto out_revert_acct;
	}

	/*
	 * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't
	 * expect a lot of shrink+grow operations, just free and allocate
	 * again like we would do for growing. If the pipe currently
	 * contains more buffers than arg, then return busy.
	 */
	if (nr_pages < pipe->nrbufs) {
		ret = -EBUSY;
		goto out_revert_acct;
	}

	bufs = kcalloc(nr_pages, sizeof(*bufs),
		       GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
	if (unlikely(!bufs)) {
		ret = -ENOMEM;
		goto out_revert_acct;
	}

	/*
	 * The pipe array wraps around, so just start the new one at zero
	 * and adjust the indexes.
	 */
	if (pipe->nrbufs) {
		unsigned int tail;
		unsigned int head;

		tail = pipe->curbuf + pipe->nrbufs;
		if (tail < pipe->buffers)
			tail = 0;
		else
			tail &= (pipe->buffers - 1);

		head = pipe->nrbufs - tail;
		if (head)
			memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer));
		if (tail)
			memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
	}

	pipe->curbuf = 0;
	kfree(pipe->bufs);
	pipe->bufs = bufs;
	pipe->buffers = nr_pages;
	return nr_pages * PAGE_SIZE;

out_revert_acct:
	(void) account_pipe_buffers(pipe->user, nr_pages, pipe->buffers);
	return ret;
}

/*
 * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same
 * location, so checking ->i_pipe is not enough to verify that this is a
 * pipe.
 */
struct pipe_inode_info *get_pipe_info(struct file *file)
{
	return file->f_op == &pipefifo_fops ? file->private_data : NULL;
}

long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
{
	struct pipe_inode_info *pipe;
	long ret;

	pipe = get_pipe_info(file);
	if (!pipe)
		return -EBADF;

	__pipe_lock(pipe);

	switch (cmd) {
	case F_SETPIPE_SZ:
		ret = pipe_set_size(pipe, arg);
		break;
	case F_GETPIPE_SZ:
		ret = pipe->buffers * PAGE_SIZE;
		break;
	default:
		ret = -EINVAL;
		break;
	}

	__pipe_unlock(pipe);
	return ret;
}

static const struct super_operations pipefs_ops = {
	.destroy_inode = free_inode_nonrcu,
	.statfs = simple_statfs,
};

/*
 * pipefs should _never_ be mounted by userland - too much of security hassle,
 * no real gain from having the whole whorehouse mounted. So we don't need
 * any operations on the root directory. However, we need a non-trivial
 * d_name - pipe: will go nicely and kill the special-casing in procfs.
 */
static struct dentry *pipefs_mount(struct file_system_type *fs_type,
			 int flags, const char *dev_name, void *data)
{
	return mount_pseudo(fs_type, "pipe:", &pipefs_ops,
			&pipefs_dentry_operations, PIPEFS_MAGIC);
}

static struct file_system_type pipe_fs_type = {
	.name		= "pipefs",
	.mount		= pipefs_mount,
	.kill_sb	= kill_anon_super,
};

static int __init init_pipe_fs(void)
{
	int err = register_filesystem(&pipe_fs_type);

	if (!err) {
		pipe_mnt = kern_mount(&pipe_fs_type);
		if (IS_ERR(pipe_mnt)) {
			err = PTR_ERR(pipe_mnt);
			unregister_filesystem(&pipe_fs_type);
		}
	}
	return err;
}

fs_initcall(init_pipe_fs);