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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* event_inode.c - part of tracefs, a pseudo file system for activating tracing
*
* Copyright (C) 2020-23 VMware Inc, author: Steven Rostedt (VMware) <rostedt@goodmis.org>
* Copyright (C) 2020-23 VMware Inc, author: Ajay Kaher <akaher@vmware.com>
*
* eventfs is used to dynamically create inodes and dentries based on the
* meta data provided by the tracing system.
*
* eventfs stores the meta-data of files/dirs and holds off on creating
* inodes/dentries of the files. When accessed, the eventfs will create the
* inodes/dentries in a just-in-time (JIT) manner. The eventfs will clean up
* and delete the inodes/dentries when they are no longer referenced.
*/
#include <linux/fsnotify.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/tracefs.h>
#include <linux/kref.h>
#include <linux/delay.h>
#include "internal.h"
struct eventfs_inode {
struct list_head e_top_files;
};
/**
* struct eventfs_file - hold the properties of the eventfs files and
* directories.
* @name: the name of the file or directory to create
* @d_parent: holds parent's dentry
* @dentry: once accessed holds dentry
* @list: file or directory to be added to parent directory
* @ei: list of files and directories within directory
* @fop: file_operations for file or directory
* @iop: inode_operations for file or directory
* @data: something that the caller will want to get to later on
* @mode: the permission that the file or directory should have
*/
struct eventfs_file {
const char *name;
struct dentry *d_parent;
struct dentry *dentry;
struct list_head list;
struct eventfs_inode *ei;
const struct file_operations *fop;
const struct inode_operations *iop;
union {
struct list_head del_list; /* list of eventfs_file to delete */
struct rcu_head rcu; /* eventfs_file to delete */
unsigned long is_freed; /* Freed if one of the above is set */
};
void *data;
umode_t mode;
};
static DEFINE_MUTEX(eventfs_mutex);
DEFINE_STATIC_SRCU(eventfs_srcu);
static struct dentry *eventfs_root_lookup(struct inode *dir,
struct dentry *dentry,
unsigned int flags);
static int dcache_dir_open_wrapper(struct inode *inode, struct file *file);
static int eventfs_release(struct inode *inode, struct file *file);
static const struct inode_operations eventfs_root_dir_inode_operations = {
.lookup = eventfs_root_lookup,
};
static const struct file_operations eventfs_file_operations = {
.open = dcache_dir_open_wrapper,
.read = generic_read_dir,
.iterate_shared = dcache_readdir,
.llseek = generic_file_llseek,
.release = eventfs_release,
};
/**
* create_file - create a file in the tracefs filesystem
* @name: the name of the file to create.
* @mode: the permission that the file should have.
* @parent: parent dentry for this file.
* @data: something that the caller will want to get to later on.
* @fop: struct file_operations that should be used for this file.
*
* This is the basic "create a file" function for tracefs. It allows for a
* wide range of flexibility in creating a file.
*
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the tracefs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
* you are responsible here.) If an error occurs, %NULL will be returned.
*
* If tracefs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*/
static struct dentry *create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fop)
{
return NULL;
};
/**
* create_dir - create a dir in the tracefs filesystem
* @name: the name of the file to create.
* @parent: parent dentry for this file.
* @data: something that the caller will want to get to later on.
*
* This is the basic "create a dir" function for eventfs. It allows for a
* wide range of flexibility in creating a dir.
*
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the tracefs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
* you are responsible here.) If an error occurs, %NULL will be returned.
*
* If tracefs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*/
static struct dentry *create_dir(const char *name, struct dentry *parent, void *data)
{
return NULL;
}
/**
* eventfs_set_ef_status_free - set the ef->status to free
* @dentry: dentry who's status to be freed
*
* eventfs_set_ef_status_free will be called if no more
* references remain
*/
void eventfs_set_ef_status_free(struct dentry *dentry)
{
struct tracefs_inode *ti_parent;
struct eventfs_file *ef;
mutex_lock(&eventfs_mutex);
ti_parent = get_tracefs(dentry->d_parent->d_inode);
if (!ti_parent || !(ti_parent->flags & TRACEFS_EVENT_INODE))
goto out;
ef = dentry->d_fsdata;
if (!ef)
goto out;
dentry->d_fsdata = NULL;
ef->dentry = NULL;
out:
mutex_unlock(&eventfs_mutex);
}
/**
* eventfs_post_create_dir - post create dir routine
* @ef: eventfs_file of recently created dir
*
* Map the meta-data of files within an eventfs dir to their parent dentry
*/
static void eventfs_post_create_dir(struct eventfs_file *ef)
{
struct eventfs_file *ef_child;
struct tracefs_inode *ti;
/* srcu lock already held */
/* fill parent-child relation */
list_for_each_entry_srcu(ef_child, &ef->ei->e_top_files, list,
srcu_read_lock_held(&eventfs_srcu)) {
ef_child->d_parent = ef->dentry;
}
ti = get_tracefs(ef->dentry->d_inode);
ti->private = ef->ei;
}
/**
* create_dentry - helper function to create dentry
* @ef: eventfs_file of file or directory to create
* @parent: parent dentry
* @lookup: true if called from lookup routine
*
* Used to create a dentry for file/dir, executes post dentry creation routine
*/
static struct dentry *
create_dentry(struct eventfs_file *ef, struct dentry *parent, bool lookup)
{
bool invalidate = false;
struct dentry *dentry;
mutex_lock(&eventfs_mutex);
if (ef->is_freed) {
mutex_unlock(&eventfs_mutex);
return NULL;
}
if (ef->dentry) {
dentry = ef->dentry;
/* On dir open, up the ref count */
if (!lookup)
dget(dentry);
mutex_unlock(&eventfs_mutex);
return dentry;
}
mutex_unlock(&eventfs_mutex);
if (!lookup)
inode_lock(parent->d_inode);
if (ef->ei)
dentry = create_dir(ef->name, parent, ef->data);
else
dentry = create_file(ef->name, ef->mode, parent,
ef->data, ef->fop);
if (!lookup)
inode_unlock(parent->d_inode);
mutex_lock(&eventfs_mutex);
if (IS_ERR_OR_NULL(dentry)) {
/* If the ef was already updated get it */
dentry = ef->dentry;
if (dentry && !lookup)
dget(dentry);
mutex_unlock(&eventfs_mutex);
return dentry;
}
if (!ef->dentry && !ef->is_freed) {
ef->dentry = dentry;
if (ef->ei)
eventfs_post_create_dir(ef);
dentry->d_fsdata = ef;
} else {
/* A race here, should try again (unless freed) */
invalidate = true;
}
mutex_unlock(&eventfs_mutex);
if (invalidate)
d_invalidate(dentry);
if (lookup || invalidate)
dput(dentry);
return invalidate ? NULL : dentry;
}
static bool match_event_file(struct eventfs_file *ef, const char *name)
{
bool ret;
mutex_lock(&eventfs_mutex);
ret = !ef->is_freed && strcmp(ef->name, name) == 0;
mutex_unlock(&eventfs_mutex);
return ret;
}
/**
* eventfs_root_lookup - lookup routine to create file/dir
* @dir: in which a lookup is being done
* @dentry: file/dir dentry
* @flags: to pass as flags parameter to simple lookup
*
* Used to create a dynamic file/dir within @dir. Use the eventfs_inode
* list of meta data to find the information needed to create the file/dir.
*/
static struct dentry *eventfs_root_lookup(struct inode *dir,
struct dentry *dentry,
unsigned int flags)
{
struct tracefs_inode *ti;
struct eventfs_inode *ei;
struct eventfs_file *ef;
struct dentry *ret = NULL;
int idx;
ti = get_tracefs(dir);
if (!(ti->flags & TRACEFS_EVENT_INODE))
return NULL;
ei = ti->private;
idx = srcu_read_lock(&eventfs_srcu);
list_for_each_entry_srcu(ef, &ei->e_top_files, list,
srcu_read_lock_held(&eventfs_srcu)) {
if (!match_event_file(ef, dentry->d_name.name))
continue;
ret = simple_lookup(dir, dentry, flags);
create_dentry(ef, ef->d_parent, true);
break;
}
srcu_read_unlock(&eventfs_srcu, idx);
return ret;
}
/**
* eventfs_release - called to release eventfs file/dir
* @inode: inode to be released
* @file: file to be released (not used)
*/
static int eventfs_release(struct inode *inode, struct file *file)
{
struct tracefs_inode *ti;
struct eventfs_inode *ei;
struct eventfs_file *ef;
struct dentry *dentry;
int idx;
ti = get_tracefs(inode);
if (!(ti->flags & TRACEFS_EVENT_INODE))
return -EINVAL;
ei = ti->private;
idx = srcu_read_lock(&eventfs_srcu);
list_for_each_entry_srcu(ef, &ei->e_top_files, list,
srcu_read_lock_held(&eventfs_srcu)) {
mutex_lock(&eventfs_mutex);
dentry = ef->dentry;
mutex_unlock(&eventfs_mutex);
if (dentry)
dput(dentry);
}
srcu_read_unlock(&eventfs_srcu, idx);
return dcache_dir_close(inode, file);
}
/**
* dcache_dir_open_wrapper - eventfs open wrapper
* @inode: not used
* @file: dir to be opened (to create its child)
*
* Used to dynamically create the file/dir within @file. @file is really a
* directory and all the files/dirs of the children within @file will be
* created. If any of the files/dirs have already been created, their
* reference count will be incremented.
*/
static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
{
struct tracefs_inode *ti;
struct eventfs_inode *ei;
struct eventfs_file *ef;
struct dentry *dentry = file_dentry(file);
struct inode *f_inode = file_inode(file);
int idx;
ti = get_tracefs(f_inode);
if (!(ti->flags & TRACEFS_EVENT_INODE))
return -EINVAL;
ei = ti->private;
idx = srcu_read_lock(&eventfs_srcu);
list_for_each_entry_rcu(ef, &ei->e_top_files, list) {
create_dentry(ef, dentry, false);
}
srcu_read_unlock(&eventfs_srcu, idx);
return dcache_dir_open(inode, file);
}
/**
* eventfs_prepare_ef - helper function to prepare eventfs_file
* @name: the name of the file/directory to create.
* @mode: the permission that the file should have.
* @fop: struct file_operations that should be used for this file/directory.
* @iop: struct inode_operations that should be used for this file/directory.
* @data: something that the caller will want to get to later on. The
* inode.i_private pointer will point to this value on the open() call.
*
* This function allocates and fills the eventfs_file structure.
*/
static struct eventfs_file *eventfs_prepare_ef(const char *name, umode_t mode,
const struct file_operations *fop,
const struct inode_operations *iop,
void *data)
{
struct eventfs_file *ef;
ef = kzalloc(sizeof(*ef), GFP_KERNEL);
if (!ef)
return ERR_PTR(-ENOMEM);
ef->name = kstrdup(name, GFP_KERNEL);
if (!ef->name) {
kfree(ef);
return ERR_PTR(-ENOMEM);
}
if (S_ISDIR(mode)) {
ef->ei = kzalloc(sizeof(*ef->ei), GFP_KERNEL);
if (!ef->ei) {
kfree(ef->name);
kfree(ef);
return ERR_PTR(-ENOMEM);
}
INIT_LIST_HEAD(&ef->ei->e_top_files);
} else {
ef->ei = NULL;
}
ef->iop = iop;
ef->fop = fop;
ef->mode = mode;
ef->data = data;
return ef;
}
/**
* eventfs_create_events_dir - create the trace event structure
* @name: the name of the directory to create.
* @parent: parent dentry for this file. This should be a directory dentry
* if set. If this parameter is NULL, then the directory will be
* created in the root of the tracefs filesystem.
*
* This function creates the top of the trace event directory.
*/
struct dentry *eventfs_create_events_dir(const char *name,
struct dentry *parent)
{
struct dentry *dentry = tracefs_start_creating(name, parent);
struct eventfs_inode *ei;
struct tracefs_inode *ti;
struct inode *inode;
if (IS_ERR(dentry))
return dentry;
ei = kzalloc(sizeof(*ei), GFP_KERNEL);
if (!ei)
return ERR_PTR(-ENOMEM);
inode = tracefs_get_inode(dentry->d_sb);
if (unlikely(!inode)) {
kfree(ei);
tracefs_failed_creating(dentry);
return ERR_PTR(-ENOMEM);
}
INIT_LIST_HEAD(&ei->e_top_files);
ti = get_tracefs(inode);
ti->flags |= TRACEFS_EVENT_INODE;
ti->private = ei;
inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
inode->i_op = &eventfs_root_dir_inode_operations;
inode->i_fop = &eventfs_file_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
d_instantiate(dentry, inode);
inc_nlink(dentry->d_parent->d_inode);
fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
return tracefs_end_creating(dentry);
}
/**
* eventfs_add_subsystem_dir - add eventfs subsystem_dir to list to create later
* @name: the name of the file to create.
* @parent: parent dentry for this dir.
*
* This function adds eventfs subsystem dir to list.
* And all these dirs are created on the fly when they are looked up,
* and the dentry and inodes will be removed when they are done.
*/
struct eventfs_file *eventfs_add_subsystem_dir(const char *name,
struct dentry *parent)
{
struct tracefs_inode *ti_parent;
struct eventfs_inode *ei_parent;
struct eventfs_file *ef;
if (!parent)
return ERR_PTR(-EINVAL);
ti_parent = get_tracefs(parent->d_inode);
ei_parent = ti_parent->private;
ef = eventfs_prepare_ef(name, S_IFDIR, NULL, NULL, NULL);
if (IS_ERR(ef))
return ef;
mutex_lock(&eventfs_mutex);
list_add_tail(&ef->list, &ei_parent->e_top_files);
ef->d_parent = parent;
mutex_unlock(&eventfs_mutex);
return ef;
}
/**
* eventfs_add_dir - add eventfs dir to list to create later
* @name: the name of the file to create.
* @ef_parent: parent eventfs_file for this dir.
*
* This function adds eventfs dir to list.
* And all these dirs are created on the fly when they are looked up,
* and the dentry and inodes will be removed when they are done.
*/
struct eventfs_file *eventfs_add_dir(const char *name,
struct eventfs_file *ef_parent)
{
struct eventfs_file *ef;
if (!ef_parent)
return ERR_PTR(-EINVAL);
ef = eventfs_prepare_ef(name, S_IFDIR, NULL, NULL, NULL);
if (IS_ERR(ef))
return ef;
mutex_lock(&eventfs_mutex);
list_add_tail(&ef->list, &ef_parent->ei->e_top_files);
ef->d_parent = ef_parent->dentry;
mutex_unlock(&eventfs_mutex);
return ef;
}
/**
* eventfs_add_events_file - add the data needed to create a file for later reference
* @name: the name of the file to create.
* @mode: the permission that the file should have.
* @parent: parent dentry for this file.
* @data: something that the caller will want to get to later on.
* @fop: struct file_operations that should be used for this file.
*
* This function is used to add the information needed to create a
* dentry/inode within the top level events directory. The file created
* will have the @mode permissions. The @data will be used to fill the
* inode.i_private when the open() call is done. The dentry and inodes are
* all created when they are referenced, and removed when they are no
* longer referenced.
*/
int eventfs_add_events_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fop)
{
struct tracefs_inode *ti;
struct eventfs_inode *ei;
struct eventfs_file *ef;
if (!parent)
return -EINVAL;
if (!(mode & S_IFMT))
mode |= S_IFREG;
if (!parent->d_inode)
return -EINVAL;
ti = get_tracefs(parent->d_inode);
if (!(ti->flags & TRACEFS_EVENT_INODE))
return -EINVAL;
ei = ti->private;
ef = eventfs_prepare_ef(name, mode, fop, NULL, data);
if (IS_ERR(ef))
return -ENOMEM;
mutex_lock(&eventfs_mutex);
list_add_tail(&ef->list, &ei->e_top_files);
ef->d_parent = parent;
mutex_unlock(&eventfs_mutex);
return 0;
}
/**
* eventfs_add_file - add eventfs file to list to create later
* @name: the name of the file to create.
* @mode: the permission that the file should have.
* @ef_parent: parent eventfs_file for this file.
* @data: something that the caller will want to get to later on.
* @fop: struct file_operations that should be used for this file.
*
* This function is used to add the information needed to create a
* file within a subdirectory of the events directory. The file created
* will have the @mode permissions. The @data will be used to fill the
* inode.i_private when the open() call is done. The dentry and inodes are
* all created when they are referenced, and removed when they are no
* longer referenced.
*/
int eventfs_add_file(const char *name, umode_t mode,
struct eventfs_file *ef_parent,
void *data,
const struct file_operations *fop)
{
struct eventfs_file *ef;
if (!ef_parent)
return -EINVAL;
if (!(mode & S_IFMT))
mode |= S_IFREG;
ef = eventfs_prepare_ef(name, mode, fop, NULL, data);
if (IS_ERR(ef))
return -ENOMEM;
mutex_lock(&eventfs_mutex);
list_add_tail(&ef->list, &ef_parent->ei->e_top_files);
ef->d_parent = ef_parent->dentry;
mutex_unlock(&eventfs_mutex);
return 0;
}
|