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
|
/*
* Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; see the file COPYING. If not, write to
* the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/*
* fsnotify inode mark locking/lifetime/and refcnting
*
* REFCNT:
* The group->recnt and mark->refcnt tell how many "things" in the kernel
* currently are referencing the objects. Both kind of objects typically will
* live inside the kernel with a refcnt of 2, one for its creation and one for
* the reference a group and a mark hold to each other.
* If you are holding the appropriate locks, you can take a reference and the
* object itself is guaranteed to survive until the reference is dropped.
*
* LOCKING:
* There are 3 locks involved with fsnotify inode marks and they MUST be taken
* in order as follows:
*
* group->mark_mutex
* mark->lock
* inode->i_lock
*
* group->mark_mutex protects the marks_list anchored inside a given group and
* each mark is hooked via the g_list. It also protects the groups private
* data (i.e group limits).
* mark->lock protects the marks attributes like its masks and flags.
* Furthermore it protects the access to a reference of the group that the mark
* is assigned to as well as the access to a reference of the inode/vfsmount
* that is being watched by the mark.
*
* inode->i_lock protects the i_fsnotify_marks list anchored inside a
* given inode and each mark is hooked via the i_list. (and sorta the
* free_i_list)
*
*
* LIFETIME:
* Inode marks survive between when they are added to an inode and when their
* refcnt==0.
*
* The inode mark can be cleared for a number of different reasons including:
* - The inode is unlinked for the last time. (fsnotify_inode_remove)
* - The inode is being evicted from cache. (fsnotify_inode_delete)
* - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes)
* - Something explicitly requests that it be removed. (fsnotify_destroy_mark)
* - The fsnotify_group associated with the mark is going away and all such marks
* need to be cleaned up. (fsnotify_clear_marks_by_group)
*
* Worst case we are given an inode and need to clean up all the marks on that
* inode. We take i_lock and walk the i_fsnotify_marks safely. For each
* mark on the list we take a reference (so the mark can't disappear under us).
* We remove that mark form the inode's list of marks and we add this mark to a
* private list anchored on the stack using i_free_list; we walk i_free_list
* and before we destroy the mark we make sure that we dont race with a
* concurrent destroy_group by getting a ref to the marks group and taking the
* groups mutex.
* Very similarly for freeing by group, except we use free_g_list.
*
* This has the very interesting property of being able to run concurrently with
* any (or all) other directions.
*/
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/srcu.h>
#include <linux/atomic.h>
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
#define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */
struct srcu_struct fsnotify_mark_srcu;
static DEFINE_SPINLOCK(destroy_lock);
static LIST_HEAD(destroy_list);
static void fsnotify_mark_destroy_workfn(struct work_struct *work);
static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn);
void fsnotify_get_mark(struct fsnotify_mark *mark)
{
atomic_inc(&mark->refcnt);
}
void fsnotify_put_mark(struct fsnotify_mark *mark)
{
if (atomic_dec_and_test(&mark->refcnt)) {
if (mark->group)
fsnotify_put_group(mark->group);
mark->free_mark(mark);
}
}
/* Calculate mask of events for a list of marks */
u32 fsnotify_recalc_mask(struct hlist_head *head)
{
u32 new_mask = 0;
struct fsnotify_mark *mark;
hlist_for_each_entry(mark, head, obj_list)
new_mask |= mark->mask;
return new_mask;
}
/*
* Remove mark from inode / vfsmount list, group list, drop inode reference
* if we got one.
*
* Must be called with group->mark_mutex held.
*/
void fsnotify_detach_mark(struct fsnotify_mark *mark)
{
struct inode *inode = NULL;
struct fsnotify_group *group = mark->group;
BUG_ON(!mutex_is_locked(&group->mark_mutex));
spin_lock(&mark->lock);
/* something else already called this function on this mark */
if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
spin_unlock(&mark->lock);
return;
}
mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED;
if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
inode = mark->inode;
fsnotify_destroy_inode_mark(mark);
} else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT)
fsnotify_destroy_vfsmount_mark(mark);
else
BUG();
/*
* Note that we didn't update flags telling whether inode cares about
* what's happening with children. We update these flags from
* __fsnotify_parent() lazily when next event happens on one of our
* children.
*/
list_del_init(&mark->g_list);
spin_unlock(&mark->lock);
if (inode && (mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED))
iput(inode);
atomic_dec(&group->num_marks);
}
/*
* Prepare mark for freeing and add it to the list of marks prepared for
* freeing. The actual freeing must happen after SRCU period ends and the
* caller is responsible for this.
*
* The function returns true if the mark was added to the list of marks for
* freeing. The function returns false if someone else has already called
* __fsnotify_free_mark() for the mark.
*/
static bool __fsnotify_free_mark(struct fsnotify_mark *mark)
{
struct fsnotify_group *group = mark->group;
spin_lock(&mark->lock);
/* something else already called this function on this mark */
if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
spin_unlock(&mark->lock);
return false;
}
mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
spin_unlock(&mark->lock);
/*
* Some groups like to know that marks are being freed. This is a
* callback to the group function to let it know that this mark
* is being freed.
*/
if (group->ops->freeing_mark)
group->ops->freeing_mark(mark, group);
spin_lock(&destroy_lock);
list_add(&mark->g_list, &destroy_list);
spin_unlock(&destroy_lock);
return true;
}
/*
* Free fsnotify mark. The freeing is actually happening from a workqueue which
* first waits for srcu period end. Caller must have a reference to the mark
* or be protected by fsnotify_mark_srcu.
*/
void fsnotify_free_mark(struct fsnotify_mark *mark)
{
if (__fsnotify_free_mark(mark)) {
queue_delayed_work(system_unbound_wq, &reaper_work,
FSNOTIFY_REAPER_DELAY);
}
}
void fsnotify_destroy_mark(struct fsnotify_mark *mark,
struct fsnotify_group *group)
{
mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
fsnotify_detach_mark(mark);
mutex_unlock(&group->mark_mutex);
fsnotify_free_mark(mark);
}
void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock)
{
struct fsnotify_mark *mark;
while (1) {
/*
* We have to be careful since we can race with e.g.
* fsnotify_clear_marks_by_group() and once we drop 'lock',
* mark can get removed from the obj_list and destroyed. But
* we are holding mark reference so mark cannot be freed and
* calling fsnotify_destroy_mark() more than once is fine.
*/
spin_lock(lock);
if (hlist_empty(head)) {
spin_unlock(lock);
break;
}
mark = hlist_entry(head->first, struct fsnotify_mark, obj_list);
/*
* We don't update i_fsnotify_mask / mnt_fsnotify_mask here
* since inode / mount is going away anyway. So just remove
* mark from the list.
*/
hlist_del_init_rcu(&mark->obj_list);
fsnotify_get_mark(mark);
spin_unlock(lock);
fsnotify_destroy_mark(mark, mark->group);
fsnotify_put_mark(mark);
}
}
void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
{
assert_spin_locked(&mark->lock);
mark->mask = mask;
if (mark->flags & FSNOTIFY_MARK_FLAG_INODE)
fsnotify_set_inode_mark_mask_locked(mark, mask);
}
void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mask)
{
assert_spin_locked(&mark->lock);
mark->ignored_mask = mask;
}
/*
* Sorting function for lists of fsnotify marks.
*
* Fanotify supports different notification classes (reflected as priority of
* notification group). Events shall be passed to notification groups in
* decreasing priority order. To achieve this marks in notification lists for
* inodes and vfsmounts are sorted so that priorities of corresponding groups
* are descending.
*
* Furthermore correct handling of the ignore mask requires processing inode
* and vfsmount marks of each group together. Using the group address as
* further sort criterion provides a unique sorting order and thus we can
* merge inode and vfsmount lists of marks in linear time and find groups
* present in both lists.
*
* A return value of 1 signifies that b has priority over a.
* A return value of 0 signifies that the two marks have to be handled together.
* A return value of -1 signifies that a has priority over b.
*/
int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
{
if (a == b)
return 0;
if (!a)
return 1;
if (!b)
return -1;
if (a->priority < b->priority)
return 1;
if (a->priority > b->priority)
return -1;
if (a < b)
return 1;
return -1;
}
/* Add mark into proper place in given list of marks */
int fsnotify_add_mark_list(struct hlist_head *head, struct fsnotify_mark *mark,
int allow_dups)
{
struct fsnotify_mark *lmark, *last = NULL;
int cmp;
/* is mark the first mark? */
if (hlist_empty(head)) {
hlist_add_head_rcu(&mark->obj_list, head);
return 0;
}
/* should mark be in the middle of the current list? */
hlist_for_each_entry
|