summaryrefslogtreecommitdiffstats
path: root/fs/sysfs/file.c
blob: 7f0a79fa2ed808fa44d1d7b7f2db5bff4e2bd89d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
/*
 * fs/sysfs/file.c - sysfs regular (text) file implementation
 *
 * Copyright (c) 2001-3 Patrick Mochel
 * Copyright (c) 2007 SUSE Linux Products GmbH
 * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
 *
 * This file is released under the GPLv2.
 *
 * Please see Documentation/filesystems/sysfs.txt for more information.
 */

#include <linux/module.h>
#include <linux/kobject.h>
#include <linux/kallsyms.h>
#include <linux/slab.h>
#include <linux/fsnotify.h>
#include <linux/namei.h>
#include <linux/poll.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/limits.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
#include <linux/mm.h>

#include "sysfs.h"

/*
 * There's one sysfs_open_file for each open file and one sysfs_open_dirent
 * for each sysfs_dirent with one or more open files.
 *
 * sysfs_dirent->s_attr.open points to sysfs_open_dirent.  s_attr.open is
 * protected by sysfs_open_dirent_lock.
 *
 * filp->private_data points to seq_file whose ->private points to
 * sysfs_open_file.  sysfs_open_files are chained at
 * sysfs_open_dirent->files, which is protected by sysfs_open_file_mutex.
 */
static DEFINE_SPINLOCK(sysfs_open_dirent_lock);
static DEFINE_MUTEX(sysfs_open_file_mutex);

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

static struct sysfs_open_file *sysfs_of(struct file *file)
{
	return ((struct seq_file *)file->private_data)->private;
}

/*
 * Determine the kernfs_ops for the given sysfs_dirent.  This function must
 * be called while holding an active reference.
 */
static const struct kernfs_ops *kernfs_ops(struct sysfs_dirent *sd)
{
	if (sd->s_flags & SYSFS_FLAG_LOCKDEP)
		lockdep_assert_held(sd);
	return sd->s_attr.ops;
}

/*
 * Determine ktype->sysfs_ops for the given sysfs_dirent.  This function
 * must be called while holding an active reference.
 */
static const struct sysfs_ops *sysfs_file_ops(struct sysfs_dirent *sd)
{
	struct kobject *kobj = sd->s_parent->priv;

	if (sd->s_flags & SYSFS_FLAG_LOCKDEP)
		lockdep_assert_held(sd);
	return kobj->ktype ? kobj->ktype->sysfs_ops : NULL;
}

/*
 * Reads on sysfs are handled through seq_file, which takes care of hairy
 * details like buffering and seeking.  The following function pipes
 * sysfs_ops->show() result through seq_file.
 */
static int sysfs_kf_seq_show(struct seq_file *sf, void *v)
{
	struct sysfs_open_file *of = sf->private;
	struct kobject *kobj = of->sd->s_parent->priv;
	const struct sysfs_ops *ops = sysfs_file_ops(of->sd);
	ssize_t count;
	char *buf;

	/* acquire buffer and ensure that it's >= PAGE_SIZE */
	count = seq_get_buf(sf, &buf);
	if (count < PAGE_SIZE) {
		seq_commit(sf, -1);
		return 0;
	}

	/*
	 * Invoke show().  Control may reach here via seq file lseek even
	 * if @ops->show() isn't implemented.
	 */
	if (ops->show) {
		count = ops->show(kobj, of->sd->priv, buf);
		if (count < 0)
			return count;
	}

	/*
	 * The code works fine with PAGE_SIZE return but it's likely to
	 * indicate truncated result or overflow in normal use cases.
	 */
	if (count >= (ssize_t)PAGE_SIZE) {
		print_symbol("fill_read_buffer: %s returned bad count\n",
			(unsigned long)ops->show);
		/* Try to struggle along */
		count = PAGE_SIZE - 1;
	}
	seq_commit(sf, count);
	return 0;
}

static ssize_t sysfs_kf_bin_read(struct sysfs_open_file *of, char *buf,
				 size_t count, loff_t pos)
{
	struct bin_attribute *battr = of->sd->priv;
	struct kobject *kobj = of->sd->s_parent->priv;
	loff_t size = file_inode(of->file)->i_size;

	if (!count)
		return 0;

	if (size) {
		if (pos > size)
			return 0;
		if (pos + count > size)
			count = size - pos;
	}

	if (!battr->read)
		return -EIO;

	return battr->read(of->file, kobj, battr, buf, pos, count);
}

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

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

	ops = kernfs_ops(of->sd);
	if (ops->seq_start) {
		return ops->seq_start(sf, ppos);
	} 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 sysfs_open_file *of = sf->private;
	const struct kernfs_ops *ops = kernfs_ops(of->sd);

	if (ops->seq_next) {
		return ops->seq_next(sf, v, ppos);
	} 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 sysfs_open_file *of = sf->private;
	const struct kernfs_ops *ops = kernfs_ops(of->sd);

	if (ops->seq_stop)
		ops->seq_stop(sf, v);

	sysfs_put_active(of->sd);
	mutex_unlock(&of->mutex);
}

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

	of->event = atomic_read(&of->sd->s_attr.open->event);

	return of->sd->s_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 sysfs_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 = kmalloc(len, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

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

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

	sysfs_put_active(of->sd);
	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:
	kfree(buf);
	return len;
}

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

	if (of->sd->s_flags & SYSFS_FLAG_HAS_SEQ_SHOW)
		return seq_read(file, user_buf, count, ppos);
	else
		return kernfs_file_direct_read(of, user_buf, count, ppos);
}

/* kernfs write callback for regular sysfs files */
static ssize_t sysfs_kf_write(struct sysfs_open_file *of, char *buf,
			      size_t count, loff_t pos)
{
	const struct sysfs_ops *ops = sysfs_file_ops(of->sd);
	struct kobject *kobj = of->sd->s_parent->priv;

	if (!count)
		return 0;

	return ops->store(kobj, of->sd->priv, buf, count);
}

/* kernfs write callback for bin sysfs files */
static ssize_t sysfs_kf_bin_write(struct sysfs_open_file *of, char *buf,
				  size_t count, loff_t pos)
{
	struct bin_attribute *battr = of->sd->priv;
	struct kobject *kobj = of->sd->s_parent->priv;
	loff_t size = file_inode(of->file)->i_size;

	if (size) {
		if (size <= pos)
			return 0;
		count = min_t(ssize_t, count, size - pos);
	}
	if (!count)
		return 0;

	if (!battr->write)
		return -EIO;

	return battr->write(of->file, kobj, battr, buf, pos, count);
}

/**
 * kernfs_file_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_file_write(struct file *file, const char __user *user_buf,
				 size_t count, loff_t *ppos)
{
	struct sysfs_open_file *of = sysfs_of(file);
	ssize_t len = min_t(size_t, count, PAGE_SIZE);
	const struct kernfs_ops *ops;
	char *buf;

	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 just to ensure that
	 * the ops aren't called concurrently for the same open file.
	 */
	mutex_lock(&of->mutex);
	if (!sysfs_get_active(of->sd)) {
		mutex_unlock(&of->mutex);
		len = -ENODEV;
		goto out_free;
	}

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

	sysfs_put_active(of->sd);
	mutex_unlock(&of->mutex);

	if (len > 0)
		*ppos += len;
out_free:
	kfree(buf);
	return len;
}

static int sysfs_kf_bin_mmap(struct sysfs_open_file *of,
			     struct vm_area_struct *vma)
{
	struct bin_attribute *battr = of->sd->priv;
	struct kobject *kobj = of->sd->s_parent->priv;

	if (!battr->mmap)
		return -ENODEV;

	return battr->mmap(of->file, kobj, battr, vma);
}

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

	if (!of->vm_ops)
		return;

	if (!sysfs_get_active(of->sd))
		return;

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

	sysfs_put_active(of->sd);
}

static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);
	int ret;

	if (!of->vm_ops)
		return VM_FAULT_SIGBUS;

	if (!sysfs_get_active(of->sd))
		return VM_FAULT_SIGBUS;

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

	sysfs_put_active(of->sd);
	return ret;
}

static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma,
				   struct vm_fault *vmf)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);
	int ret;

	if (!of->vm_ops)
		return VM_FAULT_SIGBUS;

	if (!sysfs_get_active(of->sd))
		return VM_FAULT_SIGBUS;

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

	sysfs_put_active(of->sd);
	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 sysfs_open_file *of = sysfs_of(file);
	int ret;

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

	if (!sysfs_get_active(of->sd))
		return -EINVAL;

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

	sysfs_put_active(of->sd);
	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 sysfs_open_file *of = sysfs_of(file);
	int ret;

	if (!of->vm_ops)
		return 0;

	if (!sysfs_get_active(of->sd))
		return -EINVAL;

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

	sysfs_put_active(of->sd);
	return ret;
}

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

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

	if (!sysfs_get_active(of->sd))
		return vma->vm_policy;

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

	sysfs_put_active(of->sd);
	return pol;
}

static int kernfs_vma_migrate(struct vm_area_struct *vma,
			      const nodemask_t *from, const nodemask_t *to,
			      unsigned long flags)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);
	int ret;

	if (!of->vm_ops)
		return 0;

	if (!sysfs_get_active(of->sd))
		return 0;

	ret = 0;
	if (of->vm_ops->migrate)
		ret = of->vm_ops->migrate(vma, from, to, flags);

	sysfs_put_active(of->sd);
	return ret;
}
#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,
	.migrate	= kernfs_vma_migrate,
#endif
};

static int kernfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct sysfs_open_file *of = sysfs_of(file);
	const struct kernfs_ops *ops;
	int rc;

	mutex_lock(&of->mutex);

	rc = -ENODEV;
	if (!sysfs_get_active(of->sd))
		goto out_unlock;

	ops = kernfs_ops(of->sd);
	if (ops->mmap)
		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 = 1;
	of->vm_ops = vma->vm_ops;
	vma->vm_ops = &kernfs_vm_ops;
out_put:
	sysfs_put_active(of->sd);
out_unlock:
	mutex_unlock(&of->mutex);

	return rc;
}

/**
 *	sysfs_get_open_dirent - get or create sysfs_open_dirent
 *	@sd: target sysfs_dirent
 *	@of: sysfs_open_file for this instance of open
 *
 *	If @sd->s_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 sysfs_get_open_dirent(struct sysfs_dirent *sd,
				 struct sysfs_open_file *of)
{
	struct sysfs_open_dirent *od, *new_od = NULL;

 retry:
	mutex_lock(&sysfs_open_file_mutex);
	spin_lock_irq(&sysfs_open_dirent_lock);

	if (!sd->s_attr.open && new_od) {
		sd->s_attr.open = new_od;
		new_od = NULL;
	}

	od = sd->s_attr.open;
	if (od) {
		atomic_inc(&od->refcnt);
		list_add_tail(&of->list, &od->files);
	}

	spin_unlock_irq(&sysfs_open_dirent_lock);
	mutex_unlock(&sysfs_open_file_mutex);

	if (od) {
		kfree(new_od);
		return 0;
	}

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

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

/**
 *	sysfs_put_open_dirent - put sysfs_open_dirent
 *	@sd: target sysfs_dirent
 *	@of: associated sysfs_open_file
 *
 *	Put @sd->s_attr.open and unlink @of from the files list.  If
 *	reference count reaches zero, disassociate and free it.
 *
 *	LOCKING:
 *	None.
 */
static void sysfs_put_open_dirent(struct sysfs_dirent *sd,
				  struct sysfs_open_file *of)
{
	struct sysfs_open_dirent *od = sd->s_attr.open;
	unsigned long flags;

	mutex_lock(&sysfs_open_file_mutex);
	spin_lock_irqsave(&sysfs_open_dirent_lock, flags);

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

	if (atomic_dec_and_test(&od->refcnt))
		sd->s_attr.open = NULL;
	else
		od = NULL;

	spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags);
	mutex_unlock(&sysfs_open_file_mutex);

	kfree(od);
}

static int kernfs_file_open(struct inode *inode, struct file *file)
{
	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
	const struct kernfs_ops *ops;
	struct sysfs_open_file *of;
	bool has_read, has_write, has_mmap;
	int error = -EACCES;

	if (!sysfs_get_active(attr_sd))
		return -ENODEV;

	ops = kernfs_ops(attr_sd);

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

	/* check perms and supported operations */
	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 sysfs_open_file for the file */
	error = -ENOMEM;
	of = kzalloc(sizeof(struct sysfs_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.
	 */
	if (has_mmap)
		mutex_init(&of->mutex);
	else
		mutex_init(&of->mutex);

	of->sd = attr_sd;
	of->file = file;

	/*
	 * 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;

	((struct seq_file *)file->private_data)->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 dirent struct */
	error = sysfs_get_open_dirent(attr_sd, of);
	if (error)
		goto err_close;

	/* open succeeded, put active references */
	sysfs_put_active(attr_sd);
	return 0;

err_close:
	seq_release(inode, file);
err_free:
	kfree(of);
err_out:
	sysfs_put_active(attr_sd);
	return error;
}

static int kernfs_file_release(struct inode *inode, struct file *filp)
{
	struct sysfs_dirent *sd = filp->f_path.dentry->d_fsdata;
	struct sysfs_open_file *of = sysfs_of(filp);

	sysfs_put_open_dirent(sd, of);
	seq_release(inode, filp);
	kfree(of);

	return 0;
}

void sysfs_unmap_bin_file(struct sysfs_dirent *sd)
{
	struct sysfs_open_dirent *od;
	struct sysfs_open_file *of;

	if (!(sd->s_flags & SYSFS_FLAG_HAS_MMAP))
		return;

	spin_lock_irq(&sysfs_open_dirent_lock);
	od = sd->s_attr.open;
	if (od)
		atomic_inc(&od->refcnt);
	spin_unlock_irq(&sysfs_open_dirent_lock);
	if (!od)
		return;

	mutex_lock(&sysfs_open_file_mutex);
	list_for_each_entry(of, &od->files, list) {
		struct inode *inode = file_inode(of->file);
		unmap_mapping_range(inode->i_mapping, 0, 0, 1);
	}
	mutex_unlock(&sysfs_open_file_mutex);

	sysfs_put_open_dirent(sd, NULL);
}

/* Sysfs 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 POLLERR|POLLPRI, 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.
 */
static unsigned int kernfs_file_poll(struct file *filp, poll_table *wait)
{
	struct sysfs_open_file *of = sysfs_of(filp);
	struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata;
	struct sysfs_open_dirent *od = attr_sd->s_attr.open;

	/* need parent for the kobj, grab both */
	if (!sysfs_get_active(attr_sd))
		goto trigger;

	poll_wait(filp, &od->poll, wait);

	sysfs_put_active(attr_sd);

	if (of->event != atomic_read(&od->event))
		goto trigger;

	return DEFAULT_POLLMASK;

 trigger:
	return DEFAULT_POLLMASK|POLLERR|POLLPRI;
}

/**
 * kernfs_notify - notify a kernfs file
 * @sd: file to notify
 *
 * Notify @sd such that poll(2) on @sd wakes up.
 */
void kernfs_notify(struct sysfs_dirent *sd)
{
	struct sysfs_open_dirent *od;
	unsigned long flags;

	spin_lock_irqsave(&sysfs_open_dirent_lock, flags);

	if (!WARN_ON(sysfs_type(sd) != SYSFS_KOBJ_ATTR)) {
		od = sd->s_attr.open;
		if (od) {
			atomic_inc(&od->event);
			wake_up_interruptible(&od->poll);
		}
	}

	spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags);
}
EXPORT_SYMBOL_GPL(kernfs_notify);

void sysfs_notify(struct kobject *k, const char *dir, const char *attr)
{
	struct sysfs_dirent *sd = k->sd, *tmp;

	if (sd && dir)
		sd = kernfs_find_and_get(sd, dir);
	else
		kernfs_get(sd);

	if (sd && attr) {
		tmp = kernfs_find_and_get(sd, attr);
		kernfs_put(sd);
		sd = tmp;
	}

	if (sd) {
		kernfs_notify(sd);
		kernfs_put(sd);
	}
}
EXPORT_SYMBOL_GPL(sysfs_notify);

const struct file_operations kernfs_file_operations = {
	.read		= kernfs_file_read,
	.write		= kernfs_file_write,
	.llseek		= generic_file_llseek,
	.mmap		= kernfs_file_mmap,
	.open		= kernfs_file_open,
	.release	= kernfs_file_release,
	.poll		= kernfs_file_poll,
};

static const struct kernfs_ops sysfs_file_kfops_empty = {
};

static const struct kernfs_ops sysfs_file_kfops_ro = {
	.seq_show	= sysfs_kf_seq_show,
};

static const struct kernfs_ops sysfs_file_kfops_wo = {
	.write		= sysfs_kf_write,
};

static const struct kernfs_ops sysfs_file_kfops_rw = {
	.seq_show	= sysfs_kf_seq_show,
	.write		= sysfs_kf_write,
};

static const struct kernfs_ops sysfs_bin_kfops_ro = {
	.read		= sysfs_kf_bin_read,
};

static const struct kernfs_ops sysfs_bin_kfops_wo = {
	.write		= sysfs_kf_bin_write,
};

static const struct kernfs_ops sysfs_bin_kfops_rw = {
	.read		= sysfs_kf_bin_read,
	.write		= sysfs_kf_bin_write,
	.mmap		= sysfs_kf_bin_mmap,
};

int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd,
			   const struct attribute *attr, bool is_bin,
			   umode_t mode, const void *ns)
{
	struct lock_class_key *key = NULL;
	const struct kernfs_ops *ops;
	struct sysfs_dirent *sd;
	loff_t size;

	if (!is_bin) {
		struct kobject *kobj = dir_sd->priv;
		const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops;

		/* every kobject with an attribute needs a ktype assigned */
		if (WARN(!sysfs_ops, KERN_ERR
			 "missing sysfs attribute operations for kobject: %s\n",
			 kobject_name(kobj)))
			return -EINVAL;

		if (sysfs_ops->show && sysfs_ops->store)
			ops = &sysfs_file_kfops_rw;
		else if (sysfs_ops->show)
			ops = &sysfs_file_kfops_ro;
		else if (sysfs_ops->store)
			ops = &sysfs_file_kfops_wo;
		else
			ops = &sysfs_file_kfops_empty;

		size = PAGE_SIZE;
	} else {
		struct bin_attribute *battr = (void *)attr;

		if ((battr->read && battr->write) || battr->mmap)
			ops = &sysfs_bin_kfops_rw;
		else if (battr->read)
			ops = &sysfs_bin_kfops_ro;
		else if (battr->write)
			ops = &sysfs_bin_kfops_wo;
		else
			ops = &sysfs_file_kfops_empty;

		size = battr->size;
	}

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	if (!attr->ignore_lockdep)
		key = attr->key ?: (struct lock_class_key *)&attr->skey;
#endif
	sd = kernfs_create_file_ns_key(dir_sd, attr->name, mode, size,
				       ops, (void *)attr, ns, key);
	if (IS_ERR(sd)) {
		if (PTR_ERR(sd) == -EEXIST)
			sysfs_warn_dup(dir_sd, attr->name);
		return PTR_ERR(sd);
	}
	return 0;
}

/**
 * kernfs_create_file_ns_key - create a file
 * @parent: directory to create the file in
 * @name: name of the file
 * @mode: mode 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 sysfs_dirent *kernfs_create_file_ns_key(struct sysfs_dirent *parent,
					       const char *name,
					       umode_t mode, loff_t size,
					       const struct kernfs_ops *ops,
					       void *priv, const void *ns,
					       struct lock_class_key *key)
{
	struct sysfs_addrm_cxt acxt;
	struct sysfs_dirent *sd;
	int rc;

	sd = sysfs_new_dirent(name, (mode & S_IALLUGO) | S_IFREG,
			      SYSFS_KOBJ_ATTR);
	if (!sd)
		return ERR_PTR(-ENOMEM);

	sd->s_attr.ops = ops;
	sd->s_attr.size = size;
	sd->s_ns = ns;
	sd->priv = priv;

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	if (key) {
		lockdep_init_map(&sd->dep_map, "s_active", key, 0);
		sd->s_flags |= SYSFS_FLAG_LOCKDEP;
	}
#endif

	/*
	 * sd->s_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)
		sd->s_flags |= SYSFS_FLAG_HAS_SEQ_SHOW;
	if (ops->mmap)
		sd->s_flags |= SYSFS_FLAG_HAS_MMAP;

	sysfs_addrm_start(&acxt);
	rc = sysfs_add_one(&acxt, sd, parent);
	sysfs_addrm_finish(&acxt);

	if (rc) {
		kernfs_put(sd);
		return ERR_PTR(rc);
	}
	return sd;
}

int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
		   bool is_bin)
{
	return sysfs_add_file_mode_ns(dir_sd, attr, is_bin, attr->mode, NULL);
}

/**
 * sysfs_create_file_ns - create an attribute file for an object with custom ns
 * @kobj: object we're creating for
 * @attr: attribute descriptor
 * @ns: namespace the new file should belong to
 */
int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
			 const void *ns)
{
	BUG_ON(!kobj || !kobj->sd || !attr);

	return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode, ns);

}
EXPORT_SYMBOL_GPL(sysfs_create_file_ns);

int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr)
{
	int err = 0;
	int i;

	for (i = 0; ptr[i] && !err; i++)
		err = sysfs_create_file(kobj, ptr[i]);
	if (err)
		while (--i >= 0)
			sysfs_remove_file(kobj, ptr[i]);
	return err;
}
EXPORT_SYMBOL_GPL(sysfs_create_files);

/**
 * sysfs_add_file_to_group - add an attribute file to a pre-existing group.
 * @kobj: object we're acting for.
 * @attr: attribute descriptor.
 * @group: group name.
 */
int sysfs_add_file_to_group(struct kobject *kobj,
		const struct attribute *attr, const char *group)
{
	struct sysfs_dirent *dir_sd;
	int error;

	if (group) {
		dir_sd = kernfs_find_and_get(kobj->sd, group);
	} else {
		dir_sd = kobj->sd;
		kernfs_get(dir_sd);
	}

	if (!dir_sd)
		return -ENOENT;

	error = sysfs_add_file(dir_sd, attr, false);
	kernfs_put(dir_sd);

	return error;
}
EXPORT_SYMBOL_GPL(sysfs_add_file_to_group);

/**
 * sysfs_chmod_file - update the modified mode value on an object attribute.
 * @kobj: object we're acting for.
 * @attr: attribute descriptor.
 * @mode: file permissions.
 *
 */
int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
		     umode_t mode)
{
	struct sysfs_dirent *sd;
	struct iattr newattrs;
	int rc;

	sd = kernfs_find_and_get(kobj->sd, attr->name);
	if (!sd)
		return -ENOENT;

	newattrs.ia_mode = (mode & S_IALLUGO) | (sd->s_mode & ~S_IALLUGO);
	newattrs.ia_valid = ATTR_MODE;

	rc = kernfs_setattr(sd, &newattrs);

	kernfs_put(sd);
	return rc;
}
EXPORT_SYMBOL_GPL(sysfs_chmod_file);

/**
 * sysfs_remove_file_ns - remove an object attribute with a custom ns tag
 * @kobj: object we're acting for
 * @attr: attribute descriptor
 * @ns: namespace tag of the file to remove
 *
 * Hash the attribute name and namespace tag and kill the victim.
 */
void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
			  const void *ns)
{
	struct sysfs_dirent *dir_sd = kobj->sd;

	kernfs_remove_by_name_ns(dir_sd, attr->name, ns);
}
EXPORT_SYMBOL_GPL(sysfs_remove_file_ns);

void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr)
{
	int i;
	for (i = 0; ptr[i]; i++)
		sysfs_remove_file(kobj, ptr[i]);
}
EXPORT_SYMBOL_GPL(sysfs_remove_files);

/**
 * sysfs_remove_file_from_group - remove an attribute file from a group.
 * @kobj: object we're acting for.
 * @attr: attribute descriptor.
 * @group: group name.
 */
void sysfs_remove_file_from_group(struct kobject *kobj,
		const struct attribute *attr, const char *group)
{
	struct sysfs_dirent *dir_sd;

	if (group) {
		dir_sd = kernfs_find_and_get(kobj->sd, group);
	} else {
		dir_sd = kobj->sd;
		kernfs_get(dir_sd);
	}

	if (dir_sd) {
		kernfs_remove_by_name(dir_sd, attr->name);
		kernfs_put(dir_sd);
	}
}
EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group);

/**
 *	sysfs_create_bin_file - create binary file for object.
 *	@kobj:	object.
 *	@attr:	attribute descriptor.
 */
int sysfs_create_bin_file(struct kobject *kobj,
			  const struct bin_attribute *attr)
{
	BUG_ON(!kobj || !kobj->sd || !attr);

	return sysfs_add_file(kobj->sd, &attr->attr, true);
}
EXPORT_SYMBOL_GPL(sysfs_create_bin_file);

/**
 *	sysfs_remove_bin_file - remove binary file for object.
 *	@kobj:	object.
 *	@attr:	attribute descriptor.
 */
void sysfs_remove_bin_file(struct kobject *kobj,
			   const struct bin_attribute *attr)
{
	kernfs_remove_by_name(kobj->sd, attr->attr.name);
}
EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);

struct sysfs_schedule_callback_struct {
	struct list_head	workq_list;
	struct kobject		*kobj;
	void			(*func)(void *);
	void			*data;
	struct module		*owner;
	struct work_struct	work;
};

static struct workqueue_struct *sysfs_workqueue;
static DEFINE_MUTEX(sysfs_workq_mutex);
static LIST_HEAD(sysfs_workq);
static void sysfs_schedule_callback_work(struct work_struct *work)
{
	struct sysfs_schedule_callback_struct *ss = container_of(work,
			struct sysfs_schedule_callback_struct, work);

	(ss->func)(ss->data);
	kobject_put(ss->kobj);
	module_put(ss->owner);
	mutex_lock(&sysfs_workq_mutex);
	list_del(&ss->workq_list);
	mutex_unlock(&sysfs_workq_mutex);
	kfree(ss);
}

/**
 * sysfs_schedule_callback - helper to schedule a callback for a kobject
 * @kobj: object we're acting for.
 * @func: callback function to invoke later.
 * @data: argument to pass to @func.
 * @owner: module owning the callback code
 *
 * sysfs attribute methods must not unregister themselves or their parent
 * kobject (which would amount to the same thing).  Attempts to do so will
 * deadlock, since unregistration is mutually exclusive with driver
 * callbacks.
 *
 * Instead methods can call this routine, which will attempt to allocate
 * and schedule a workqueue request to call back @func with @data as its
 * argument in the workqueue's process context.  @kobj will be pinned
 * until @func returns.
 *
 * Returns 0 if the request was submitted, -ENOMEM if storage could not
 * be allocated, -ENODEV if a reference to @owner isn't available,
 * -EAGAIN if a callback has already been scheduled for @kobj.
 */
int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
		void *data, struct module *owner)
{
	struct sysfs_schedule_callback_struct *ss, *tmp;

	if (!try_module_get(owner))
		return -ENODEV;

	mutex_lock(&sysfs_workq_mutex);
	list_for_each_entry_safe(ss, tmp, &sysfs_workq, workq_list)
		if (ss->kobj == kobj) {
			module_put(owner);
			mutex_unlock(&sysfs_workq_mutex);
			return -EAGAIN;
		}
	mutex_unlock(&sysfs_workq_mutex);

	if (sysfs_workqueue == NULL) {
		sysfs_workqueue = create_singlethread_workqueue("sysfsd");
		if (sysfs_workqueue == NULL) {
			module_put(owner);
			return -ENOMEM;
		}
	}

	ss = kmalloc(sizeof(*ss), GFP_KERNEL);
	if (!ss) {
		module_put(owner);
		return -ENOMEM;
	}
	kobject_get(kobj);
	ss->kobj = kobj;
	ss->func = func;
	ss->data = data;
	ss->owner = owner;
	INIT_WORK(&ss->work, sysfs_schedule_callback_work);
	INIT_LIST_HEAD(&ss->workq_list);
	mutex_lock(&sysfs_workq_mutex);
	list_add_tail(&ss->workq_list, &sysfs_workq);
	mutex_unlock(&sysfs_workq_mutex);
	queue_work(sysfs_workqueue, &ss->work);
	return 0;
}
EXPORT_SYMBOL_GPL(sysfs_schedule_callback);