summaryrefslogtreecommitdiff
path: root/fs/kernfs/file.c
blob: 553ce0a92b05013ca4ff6f6110fd38917f44665a (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
/*
 * fs/kernfs/file.c - kernfs file implementation
 *
 * Copyright (c) 2001-3 Patrick Mochel
 * Copyright (c) 2007 SUSE Linux Products GmbH
 * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
 *
 * This file is released under the GPLv2.
 */

#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/pagemap.h>
#include <linux/sched/mm.h>
#include <linux/fsnotify.h>

#include "kernfs-internal.h"

/*
 * There's one kernfs_open_file for each open file and one kernfs_open_node
 * for each kernfs_node with one or more open files.
 *
 * kernfs_node->attr.open points to kernfs_open_node.  attr.open is
 * protected by kernfs_open_node_lock.
 *
 * filp->private_data points to seq_file whose ->private points to
 * kernfs_open_file.  kernfs_open_files are chained at
 * kernfs_open_node->files, which is protected by kernfs_open_file_mutex.
 */
static DEFINE_SPINLOCK(kernfs_open_node_lock);
static DEFINE_MUTEX(kernfs_open_file_mutex);

struct kernfs_open_node {
	atomic_t		refcnt;
	atomic_t		event;
	wait_queue_head_t	poll;
	struct list_head	files; /* goes through kernfs_open_file.list */
};

/*
 * kernfs_notify() may be called from any context and bounces notifications
 * through a work item.  To minimize space overhead in kernfs_node, the
 * pending queue is implemented as a singly linked list of kernfs_nodes.
 * The list is terminated with the self pointer so that whether a
 * kernfs_node is on the list or not can be determined by testing the next
 * pointer for NULL.
 */
#define KERNFS_NOTIFY_EOL			((void *)&kernfs_notify_list)

static DEFINE_SPINLOCK(kernfs_notify_lock);
static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL;

static struct kernfs_open_file *kernfs_of(struct file *file)
{
	return ((struct seq_file *)file->private_data)->private;
}

/*
 * Determine the kernfs_ops for the given kernfs_node.  This function must
 * be called while holding an active reference.
 */
static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn)
{
	if (kn->flags & KERNFS_LOCKDEP)
		lockdep_assert_held(kn);
	return kn->attr.ops;
}

/*
 * As kernfs_seq_stop() is also called after kernfs_seq_start() or
 * kernfs_seq_next() failure, it needs to distinguish whether it's stopping
 * a seq_file iteration which is fully initialized with an active reference
 * or an aborted kernfs_seq_start() due to get_active failure.  The
 * position pointer is the only context for each seq_file iteration and
 * thus the stop condition should be encoded in it.  As the return value is
 * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable
 * choice to indicate get_active failure.
 *
 * Unfortunately, this is complicated due to the optional custom seq_file
 * operations which may return ERR_PTR(-ENODEV) too.  kernfs_seq_stop()
 * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or
 * custom seq_file operations and thus can't decide whether put_active
 * should be performed or not only on ERR_PTR(-ENODEV).
 *
 * This is worked around by factoring out the custom seq_stop() and
 * put_active part into kernfs_seq_stop_active(), skipping it from
 * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after
 * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures
 * that kernfs_seq_stop_active() is skipped only after get_active failure.
 */
static void kernfs_seq_stop_active(struct seq_file *sf, void *v)
{
	struct kernfs_open_file *of = sf->private;
	const struct kernfs_ops *ops = kernfs_ops(of->kn);

	if (ops->seq_stop)
		ops->seq_stop(sf, v);
	kernfs_put_active(of->kn);
}

static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
{
	struct kernfs_open_file *of = sf->private;
	const struct kernfs_ops *ops;

	/*
	 * @of->mutex nests outside active ref and is primarily to ensure that
	 * the ops aren't called concurrently for the same open file.
	 */
	mutex_lock(&of->mutex);
	if (!kernfs_get_active(of->kn))
		return ERR_PTR(-ENODEV);

	ops = kernfs_ops(of->kn);
	if (ops->seq_start) {
		void *next = ops->seq_start(sf, ppos);
		/* see the comment above kernfs_seq_stop_active() */
		if (next == ERR_PTR(-ENODEV))
			kernfs_seq_stop_active(sf, next);
		return next;
	} else {
		/*
		 * The same behavior and code as single_open().  Returns
		 * !NULL if pos is at the beginning; otherwise, NULL.
		 */
		return NULL + !*ppos;
	}
}

static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos)
{
	struct kernfs_open_file *of = sf->private;
	const struct kernfs_ops *ops = kernfs_ops(of->kn);

	if (ops->seq_next) {
		void *next = ops->seq_next(sf, v, ppos);
		/* see the comment above kernfs_seq_stop_active() */
		if (next == ERR_PTR(-ENODEV))
			kernfs_seq_stop_active(sf, next);
		return next;
	} else {
		/*
		 * The same behavior and code as single_open(), always
		 * terminate after the initial read.
		 */
		++*ppos;
		return NULL;
	}
}

static void kernfs_seq_stop(struct seq_file *sf, void *v)
{
	struct kernfs_open_file *of = sf->private;

	if (v != ERR_PTR(-ENODEV))
		kernfs_seq_stop_active(sf, v);
	mutex_unlock(&of->mutex);
}

static int kernfs_seq_show(struct seq_file *sf, void *v)
{
	struct kernfs_open_file *of = sf->private;

	of->event = atomic_read(&of->kn->attr.open->event);

	return of->kn->attr.ops->seq_show(sf, v);
}

static const struct seq_operations kernfs_seq_ops = {
	.start = kernfs_seq_start,
	.next = kernfs_seq_next,
	.stop = kernfs_seq_stop,
	.show = kernfs_seq_show,
};

/*
 * As reading a bin file can have side-effects, the exact offset and bytes
 * specified in read(2) call should be passed to the read callback making
 * it difficult to use seq_file.  Implement simplistic custom buffering for
 * bin files.
 */
static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
				       char __user *user_buf, size_t count,
				       loff_t *ppos)
{
	ssize_t len = min_t(size_t, count, PAGE_SIZE);
	const struct kernfs_ops *ops;
	char *buf;

	buf = of->prealloc_buf;
	if (buf)
		mutex_lock(&of->prealloc_mutex);
	else
		buf = kmalloc(len, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	/*
	 * @of->mutex nests outside active ref and is used both to ensure that
	 * the ops aren't called concurrently for the same open file.
	 */
	mutex_lock(&of->mutex);
	if (!kernfs_get_active(of->kn)) {
		len = -ENODEV;
		mutex_unlock(&of->mutex);
		goto out_free;
	}

	of->event = atomic_read(&of->kn->attr.open->event);
	ops = kernfs_ops(of->kn);
	if (ops->read)
		len = ops->read(of, buf, len, *ppos);
	else
		len = -EINVAL;

	kernfs_put_active(of->kn);
	mutex_unlock(&of->mutex);

	if (len < 0)
		goto out_free;

	if (copy_to_user(user_buf, buf, len)) {
		len = -EFAULT;
		goto out_free;
	}

	*ppos += len;

 out_free:
	if (buf == of->prealloc_buf)
		mutex_unlock(&of->prealloc_mutex);
	else
		kfree(buf);
	return len;
}

/**
 * kernfs_fop_read - kernfs vfs read callback
 * @file: file pointer
 * @user_buf: data to write
 * @count: number of bytes
 * @ppos: starting offset
 */
static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
			       size_t count, loff_t *ppos)
{
	struct kernfs_open_file *of = kernfs_of(file);

	if (of->kn->flags & KERNFS_HAS_SEQ_SHOW)
		return seq_read(file, user_buf, count, ppos);
	else
		return kernfs_file_direct_read(of, user_buf, count, ppos);
}

/**
 * kernfs_fop_write - kernfs vfs write callback
 * @file: file pointer
 * @user_buf: data to write
 * @count: number of bytes
 * @ppos: starting offset
 *
 * Copy data in from userland and pass it to the matching kernfs write
 * operation.
 *
 * There is no easy way for us to know if userspace is only doing a partial
 * write, so we don't support them. We expect the entire buffer to come on
 * the first write.  Hint: if you're writing a value, first read the file,
 * modify only the the value you're changing, then write entire buffer
 * back.
 */
static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
				size_t count, loff_t *ppos)
{
	struct kernfs_open_file *of = kernfs_of(file);
	const struct kernfs_ops *ops;
	ssize_t len;
	char *buf;

	if (of->atomic_write_len) {
		len = count;
		if (len > of->atomic_write_len)
			return -E2BIG;
	} else {
		len = min_t(size_t, count, PAGE_SIZE);
	}

	buf = of->prealloc_buf;
	if (buf)
		mutex_lock(&of->prealloc_mutex);
	else
		buf = kmalloc(len + 1, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	if (copy_from_user(buf, user_buf, len)) {
		len = -EFAULT;
		goto out_free;
	}
	buf[len] = '\0';	/* guarantee string termination */

	/*
	 * @of->mutex nests outside active ref and is used both to ensure that
	 * the ops aren't called concurrently for the same open file.
	 */
	mutex_lock(&of->mutex);
	if (!kernfs_get_active(of->kn)) {
		mutex_unlock(&of->mutex);
		len = -ENODEV;
		goto out_free;
	}

	ops = kernfs_ops(of->kn);
	if (ops->write)
		len = ops->write(of, buf, len, *ppos);
	else
		len = -EINVAL;

	kernfs_put_active(of->kn);
	mutex_unlock(&of->mutex);

	if (len > 0)
		*ppos += len;

out_free:
	if (buf == of->prealloc_buf)
		mutex_unlock(&of->prealloc_mutex);
	else
		kfree(buf);
	return len;
}

static void kernfs_vma_open(struct vm_area_struct *vma)
{
	struct file *file = vma->vm_file;
	struct kernfs_open_file *of = kernfs_of(file);

	if (!of->vm_ops)
		return;

	if (!kernfs_get_active(of->kn))
		return;

	if (of->vm_ops->open)
		of->vm_ops->open(vma);

	kernfs_put_active(of->kn);
}

static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf)
{
	struct file *file = vmf->vma->vm_file;
	struct kernfs_open_file *of = kernfs_of(file);
	vm_fault_t ret;

	if (!of->vm_ops)
		return VM_FAULT_SIGBUS;

	if (!kernfs_get_active(of->kn))
		return VM_FAULT_SIGBUS;

	ret = VM_FAULT_SIGBUS;
	if (of->vm_ops->fault)
		ret = of->vm_ops->fault(vmf);

	kernfs_put_active(of->kn);
	return ret;
}

static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf)
{
	struct file *file = vmf->vma->vm_file;
	struct kernfs_open_file *of = kernfs_of(file);
	vm_fault_t ret;

	if (!of->vm_ops)
		return VM_FAULT_SIGBUS;

	if (!kernfs_get_active(of->kn))
		return VM_FAULT_SIGBUS;

	ret = 0;
	if (of->vm_ops->page_mkwrite)
		ret = of->vm_ops->page_mkwrite(vmf);
	else
		file_update_time(file);

	kernfs_put_active(of->kn);
	return ret;
}

static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr,
			     void *buf, int len, int write)
{
	struct file *file = vma->vm_file;
	struct kernfs_open_file *of = kernfs_of(file);
	int ret;

	if (!of->vm_ops)
		return -EINVAL;

	if (!kernfs_get_active(of->kn))
		return -EINVAL;

	ret = -EINVAL;
	if (of->vm_ops->access)
		ret = of->vm_ops->access(vma, addr, buf, len, write);

	kernfs_put_active(of->kn);
	return ret;
}

#ifdef CONFIG_NUMA
static int kernfs_vma_set_policy(struct vm_area_struct *vma,
				 struct mempolicy *new)
{
	struct file *file = vma->vm_file;
	struct kernfs_open_file *of = kernfs_of(file);
	int ret;

	if (!of->vm_ops)
		return 0;

	if (!kernfs_get_active(of->kn))
		return -EINVAL;

	ret = 0;
	if (of->vm_ops->set_policy)
		ret = of->vm_ops->set_policy(vma, new);

	kernfs_put_active(of->kn);
	return ret;
}

static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma,
					       unsigned long addr)
{
	struct file *file = vma->vm_file;
	struct kernfs_open_file *of = kernfs_of(file);
	struct mempolicy *pol;

	if (!of->vm_ops)
		return vma->vm_policy;

	if (!kernfs_get_active(of->kn))
		return vma->vm_policy;

	pol = vma->vm_policy;
	if (of->vm_ops->get_policy)
		pol = of->vm_ops->get_policy(vma, addr);

	kernfs_put_active(of->kn);
	return pol;
}

#endif

static const struct vm_operations_struct kernfs_vm_ops = {
	.open		= kernfs_vma_open,
	.fault		= kernfs_vma_fault,
	.page_mkwrite	= kernfs_vma_page_mkwrite,
	.access		= kernfs_vma_access,
#ifdef CONFIG_NUMA
	.set_policy	= kernfs_vma_set_policy,
	.get_policy	= kernfs_vma_get_policy,
#endif
};

static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct kernfs_open_file *of = kernfs_of(file);
	const struct kernfs_ops *ops;
	int rc;

	/*
	 * mmap path and of->mutex are prone to triggering spurious lockdep
	 * warnings and we don't want to add spurious locking dependency
	 * between the two.  Check whether mmap is actually implemented
	 * without grabbing @of->mutex by testing HAS_MMAP flag.  See the
	 * comment in kernfs_file_open() for more details.
	 */
	if (!(of->kn->flags & KERNFS_HAS_MMAP))
		return -ENODEV;

	mutex_lock(&of->mutex);

	rc = -ENODEV;
	if (!kernfs_get_active(of->kn))
		goto out_unlock;

	ops = kernfs_ops(of->kn);
	rc = ops->mmap(of, vma);
	if (rc)
		goto out_put;

	/*
	 * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
	 * to satisfy versions of X which crash if the mmap fails: that
	 * substitutes a new vm_file, and we don't then want bin_vm_ops.
	 */
	if (vma->vm_file != file)
		goto out_put;

	rc = -EINVAL;
	if (of->mmapped && of->vm_ops != vma->vm_ops)
		goto out_put;

	/*
	 * It is not possible to successfully wrap close.
	 * So error if someone is trying to use close.
	 */
	rc = -EINVAL;
	if (vma->vm_ops && vma->vm_ops->close)
		goto out_put;

	rc = 0;
	of->mmapped = true;
	of->vm_ops = vma->vm_ops;
	vma->vm_ops = &kernfs_vm_ops;
out_put:
	kernfs_put_active(of->kn);
out_unlock:
	mutex_unlock(&of->mutex);

	return rc;
}

/**
 *	kernfs_get_open_node - get or create kernfs_open_node
 *	@kn: target kernfs_node
 *	@of: kernfs_open_file for this instance of open
 *
 *	If @kn->attr.open exists, increment its reference count; otherwise,
 *	create one.  @of is chained to the files list.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 *
 *	RETURNS:
 *	0 on success, -errno on failure.
 */
static int kernfs_get_open_node(struct kernfs_node *kn,
				struct kernfs_open_file *of)
{
	struct kernfs_open_node *on, *new_on = NULL;

 retry:
	mutex_lock(&kernfs_open_file_mutex);
	spin_lock_irq(&kernfs_open_node_lock);

	if (!kn->attr.open && new_on) {
		kn->attr.open = new_on;
		new_on = NULL;
	}

	on = kn->attr.open;
	if (on) {
		atomic_inc(&on->refcnt);
		list_add_tail(&of->list, &on->files);
	}

	spin_unlock_irq(&kernfs_open_node_lock);
	mutex_unlock(&kernfs_open_file_mutex);

	if (on) {
		kfree(new_on);
		return 0;
	}

	/* not there, initialize a new one and retry */
	new_on = kmalloc(sizeof(*new_on), GFP_KERNEL);
	if (!new_on)
		return -ENOMEM;

	atomic_set(&new_on->refcnt, 0);
	atomic_set(&new_on->event, 1);
	init_waitqueue_head(&new_on->poll);
	INIT_LIST_HEAD(&new_on->files);
	goto retry;
}

/**
 *	kernfs_put_open_node - put kernfs_open_node
 *	@kn: target kernfs_nodet
 *	@of: associated kernfs_open_file
 *
 *	Put @kn->attr.open and unlink @of from the files list.  If
 *	reference count reaches zero, disassociate and free it.
 *
 *	LOCKING:
 *	None.
 */
static void kernfs_put_open_node(struct kernfs_node *kn,
				 struct kernfs_open_file *of)
{
	struct kernfs_open_node *on = kn->attr.open;
	unsigned long flags;

	mutex_lock(&kernfs_open_file_mutex);
	spin_lock_irqsave(&kernfs_open_node_lock, flags);

	if (of)
		list_del(&of->list);

	if (atomic_dec_and_test(&on->refcnt))
		kn->attr.open = NULL;
	else
		on = NULL;

	spin_unlock_irqrestore(&kernfs_open_node_lock, flags);
	mutex_unlock(&kernfs_open_file_mutex);

	kfree(on);
}

static int kernfs_fop_open(struct inode *inode, struct file *file)
{
	struct kernfs_node *kn = inode->i_private;
	struct kernfs_root *root = kernfs_root(kn);
	const struct kernfs_ops *ops;
	struct kernfs_open_file *of;
	bool has_read, has_write, has_mmap;
	int error = -EACCES;

	if (!kernfs_get_active(kn))
		return -ENODEV;

	ops = kernfs_ops(kn);

	has_read = ops->seq_show || ops->read || ops->mmap;
	has_write = ops->write || ops->mmap;
	has_mmap = ops->mmap;

	/* see the flag definition for details */
	if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) {
		if ((file->f_mode & FMODE_WRITE) &&
		    (!(inode->i_mode & S_IWUGO) || !has_write))
			goto err_out;

		if ((file->f_mode & FMODE_READ) &&
		    (!(inode->i_mode & S_IRUGO) || !has_read))
			goto err_out;
	}

	/* allocate a kernfs_open_file for the file */
	error = -ENOMEM;
	of = kzalloc(sizeof(struct kernfs_open_file), GFP_KERNEL);
	if (!of)
		goto err_out;

	/*
	 * The following is done to give a different lockdep key to
	 * @of->mutex for files which implement mmap.  This is a rather
	 * crude way to avoid false positive lockdep warning around
	 * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and
	 * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under
	 * which mm->mmap_sem nests, while holding @of->mutex.  As each
	 * open file has a separate mutex, it's okay as long as those don't
	 * happen on the same file.  At this point, we can't easily give
	 * each file a separate locking class.  Let's differentiate on
	 * whether the file has mmap or not for now.
	 *
	 * Both paths of the branch look the same.  They're supposed to
	 * look that way and give @of->mutex different static lockdep keys.
	 */
	if (has_mmap)
		mutex_init(&of->mutex);
	else
		mutex_init(&of->mutex);

	of->kn = kn;
	of->file = file;

	/*
	 * Write path needs to atomic_write_len outside active reference.
	 * Cache it in open_file.  See kernfs_fop_write() for details.
	 */
	of->atomic_write_len = ops->atomic_write_len;

	error = -EINVAL;
	/*
	 * ->seq_show is incompatible with ->prealloc,
	 * as seq_read does its own allocation.
	 * ->read must be used instead.
	 */
	if (ops->prealloc && ops->seq_show)
		goto err_free;
	if (ops->prealloc) {
		int len = of->atomic_write_len ?: PAGE_SIZE;
		of->prealloc_buf = kmalloc(len + 1, GFP_KERNEL);
		error = -ENOMEM;
		if (!of->prealloc_buf)
			goto err_free;
		mutex_init(&of->prealloc_mutex);
	}

	/*
	 * Always instantiate seq_file even if read access doesn't use
	 * seq_file or is not requested.  This unifies private data access
	 * and readable regular files are the vast majority anyway.
	 */
	if (ops->seq_show)
		error = seq_open(file, &kernfs_seq_ops);
	else
		error = seq_open(file, NULL);
	if (error)
		goto err_free;

	of->seq_file = file->private_data;
	of->seq_file->private = of;

	/* seq_file clears PWRITE unconditionally, restore it if WRITE */
	if (file->f_mode & FMODE_WRITE)
		file->f_mode |= FMODE_PWRITE;

	/* make sure we have open node struct */
	error = kernfs_get_open_node(kn, of);
	if (error)
		goto err_seq_release;

	if (ops->open) {
		/* nobody has access to @of yet, skip @of->mutex */
		error = ops->open(of);
		if (error)
			goto err_put_node;
	}

	/* open succeeded, put active references */
	kernfs_put_active(kn);
	return 0;

err_put_node:
	kernfs_put_open_node(kn, of);
err_seq_release:
	seq_release(inode, file);
err_free:
	kfree(of->prealloc_buf);
	kfree(of);
err_out:
	kernfs_put_active(kn);
	return error;
}

/* used from release/drain to ensure that ->release() is called exactly once */
static void kernfs_release_file(struct kernfs_node *kn,
				struct kernfs_open_file *of)
{
	/*
	 * @of is guaranteed to have no other file operations in flight and
	 * we just want to synchronize release and drain paths.
	 * @kernfs_open_file_mutex is enough.  @of->mutex can't be used
	 * here because drain path may be called from places which can
	 * cause circular dependency.
	 */
	lockdep_assert_held(&kernfs_open_file_mutex);

	if (!of->released) {
		/*
		 * A file is never detached without being released and we
		 * need to be able to release files which are deactivated
		 * and being drained.  Don't use kernfs_ops().
		 */
		kn->attr.ops->release(of);
		of->released = true;
	}
}

static int kernfs_fop_release(struct inode *inode, struct file *filp)
{
	struct kernfs_node *kn = inode->i_private;
	struct kernfs_open_file *of = kernfs_of(filp);

	if (kn->flags & KERNFS_HAS_RELEASE) {
		mutex_lock(&kernfs_open_file_mutex);
		kernfs_release_file(kn, of);
		mutex_unlock(&kernfs_open_file_mutex);
	}

	kernfs_put_open_node(kn, of);
	seq_release(inode, filp);
	kfree(of->prealloc_buf);
	kfree(of);

	return 0;
}

void kernfs_drain_open_files(struct kernfs_node *kn)
{
	struct kernfs_open_node *on;
	struct kernfs_open_file *of;

	if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE)))
		return;

	spin_lock_irq(&kernfs_open_node_lock);
	on = kn->attr.open;
	if (on)
		atomic_inc(&on->refcnt);
	spin_unlock_irq(&kernfs_open_node_lock);
	if (!on)
		return;

	mutex_lock(&kernfs_open_file_mutex);

	list_for_each_entry(of, &on->files, list) {
		struct inode *inode = file_inode(of->file);

		if (kn->flags & KERNFS_HAS_MMAP)
			unmap_mapping_range(inode->i_mapping, 0, 0, 1);

		if (kn->flags & KERNFS_HAS_RELEASE)
			kernfs_release_file(kn, of);
	}

	mutex_unlock(&kernfs_open_file_mutex);

	kernfs_put_open_node(kn, NULL);
}

/*
 * Kernfs attribute files are pollable.  The idea is that you read
 * the content and then you use 'poll' or 'select' to wait for
 * the content to change.  When the content changes (assuming the
 * manager for the kobject supports notification), poll will
 * return EPOLLERR|EPOLLPRI, and select will return the fd whether
 * it is waiting for read, write, or exceptions.
 * Once poll/select indicates that the value has changed, you
 * need to close and re-open the file, or seek to 0 and read again.
 * Reminder: this only works for attributes which actively support
 * it, and it is not possible to test an attribute from userspace
 * to see if it supports poll (Neither 'poll' nor 'select' return
 * an appropriate error code).  When in doubt, set a suitable timeout value.
 */
__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait)
{
	struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry);
	struct kernfs_open_node *on = kn->attr.open;

	poll_wait(of->file, &on->poll, wait);

	if (of->event != atomic_read(&on->event))
		return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;

	return DEFAULT_POLLMASK;
}

static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
{
	struct kernfs_open_file *of = kernfs_of(filp);
	struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry);
	__poll_t ret;

	if (!kernfs_get_active(kn))
		return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;

	if (kn->attr.ops->poll)
		ret = kn->attr.ops->poll(of, wait);
	else
		ret = kernfs_generic_poll(of, wait);

	kernfs_put_active(kn);
	return ret;
}

static void kernfs_notify_workfn(struct work_struct *work)
{
	struct kernfs_node *kn;
	struct kernfs_super_info *info;
repeat:
	/* pop one off the notify_list */
	spin_lock_irq(&kernfs_notify_lock);
	kn = kernfs_notify_list;
	if (kn == KERNFS_NOTIFY_EOL) {
		spin_unlock_irq(&kernfs_notify_lock);
		return;
	}
	kernfs_notify_list = kn->attr.notify_next;
	kn->attr.notify_next = NULL;
	spin_unlock_irq(&kernfs_notify_lock);

	/* kick fsnotify */
	mutex_lock(&kernfs_mutex);

	list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
		struct kernfs_node *parent;
		struct inode *inode;
		struct qstr name;

		/*
		 * We want fsnotify_modify() on @kn but as the
		 * modifications aren't originating from userland don't
		 * have the matching @file available.  Look up the inodes
		 * and generate the events manually.
		 */
		inode = ilookup(info->sb, kn->id.ino);
		if (!inode)
			continue;

		name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name));
		parent = kernfs_get_parent(kn);
		if (parent) {
			struct inode *p_inode;

			p_inode = ilookup(info->sb, parent->id.ino);
			if (p_inode) {
				fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
					 inode, FSNOTIFY_EVENT_INODE, &name, 0);
				iput(p_inode);
			}

			kernfs_put(parent);
		}

		fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
			 &name, 0);
		iput(inode);
	}

	mutex_unlock(&kernfs_mutex);
	kernfs_put(kn);
	goto repeat;
}

/**
 * kernfs_notify - notify a kernfs file
 * @kn: file to notify
 *
 * Notify @kn such that poll(2) on @kn wakes up.  Maybe be called from any
 * context.
 */
void kernfs_notify(struct kernfs_node *kn)
{
	static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn);
	unsigned long flags;
	struct kernfs_open_node *on;

	if (WARN_ON(kernfs_type(kn) != KERNFS_FILE))
		return;

	/* kick poll immediately */
	spin_lock_irqsave(&kernfs_open_node_lock, flags);
	on = kn->attr.open;
	if (on) {
		atomic_inc(&on->event);
		wake_up_interruptible(&on->poll);
	}
	spin_unlock_irqrestore(&kernfs_open_node_lock, flags);

	/* schedule work to kick fsnotify */
	spin_lock_irqsave(&kernfs_notify_lock, flags);
	if (!kn->attr.notify_next) {
		kernfs_get(kn);
		kn->attr.notify_next = kernfs_notify_list;
		kernfs_notify_list = kn;
		schedule_work(&kernfs_notify_work);
	}
	spin_unlock_irqrestore(&kernfs_notify_lock, flags);
}
EXPORT_SYMBOL_GPL(kernfs_notify);

const struct file_operations kernfs_file_fops = {
	.read		= kernfs_fop_read,
	.write		= kernfs_fop_write,
	.llseek		= generic_file_llseek,
	.mmap		= kernfs_fop_mmap,
	.open		= kernfs_fop_open,
	.release	= kernfs_fop_release,
	.poll		= kernfs_fop_poll,
	.fsync		= noop_fsync,
};

/**
 * __kernfs_create_file - kernfs internal function to create a file
 * @parent: directory to create the file in
 * @name: name of the file
 * @mode: mode of the file
 * @uid: uid of the file
 * @gid: gid of the file
 * @size: size of the file
 * @ops: kernfs operations for the file
 * @priv: private data for the file
 * @ns: optional namespace tag of the file
 * @key: lockdep key for the file's active_ref, %NULL to disable lockdep
 *
 * Returns the created node on success, ERR_PTR() value on error.
 */
struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
					 const char *name,
					 umode_t mode, kuid_t uid, kgid_t gid,
					 loff_t size,
					 const struct kernfs_ops *ops,
					 void *priv, const void *ns,
					 struct lock_class_key *key)
{
	struct kernfs_node *kn;
	unsigned flags;
	int rc;

	flags = KERNFS_FILE;

	kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG,
			     uid, gid, flags);
	if (!kn)
		return ERR_PTR(-ENOMEM);

	kn->attr.ops = ops;
	kn->attr.size = size;
	kn->ns = ns;
	kn->priv = priv;

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	if (key) {
		lockdep_init_map(&kn->dep_map, "kn->count", key, 0);
		kn->flags |= KERNFS_LOCKDEP;
	}
#endif

	/*
	 * kn->attr.ops is accesible only while holding active ref.  We
	 * need to know whether some ops are implemented outside active
	 * ref.  Cache their existence in flags.
	 */
	if (ops->seq_show)
		kn->flags |= KERNFS_HAS_SEQ_SHOW;
	if (ops->mmap)
		kn->flags |= KERNFS_HAS_MMAP;
	if (ops->release)
		kn->flags |= KERNFS_HAS_RELEASE;

	rc = kernfs_add_one(kn);
	if (rc) {
		kernfs_put(kn);
		return ERR_PTR(rc);
	}
	return kn;
}