summaryrefslogtreecommitdiffstats
path: root/fs/notify/fsnotify.c
blob: e8ee4263d7b2e1da1f56635358a918de78463ab2 (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
/*
 *  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.
 */

#include <linux/dcache.h>
#include <linux/fs.h>
#include <linux/gfp.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/srcu.h>

#include <linux/fsnotify_backend.h>
#include "fsnotify.h"

/*
 * Clear all of the marks on an inode when it is being evicted from core
 */
void __fsnotify_inode_delete(struct inode *inode)
{
	fsnotify_clear_marks_by_inode(inode);
}
EXPORT_SYMBOL_GPL(__fsnotify_inode_delete);

void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
{
	fsnotify_clear_marks_by_mount(mnt);
}

/**
 * fsnotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
 * @sb: superblock being unmounted.
 *
 * Called during unmount with no locks held, so needs to be safe against
 * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
 */
void fsnotify_unmount_inodes(struct super_block *sb)
{
	struct inode *inode, *iput_inode = NULL;

	spin_lock(&sb->s_inode_list_lock);
	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
		/*
		 * We cannot __iget() an inode in state I_FREEING,
		 * I_WILL_FREE, or I_NEW which is fine because by that point
		 * the inode cannot have any associated watches.
		 */
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
			spin_unlock(&inode->i_lock);
			continue;
		}

		/*
		 * If i_count is zero, the inode cannot have any watches and
		 * doing an __iget/iput with SB_ACTIVE clear would actually
		 * evict all inodes with zero i_count from icache which is
		 * unnecessarily violent and may in fact be illegal to do.
		 */
		if (!atomic_read(&inode->i_count)) {
			spin_unlock(&inode->i_lock);
			continue;
		}

		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(&sb->s_inode_list_lock);

		if (iput_inode)
			iput(iput_inode);

		/* for each watch, send FS_UNMOUNT and then remove it */
		fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);

		fsnotify_inode_delete(inode);

		iput_inode = inode;

		cond_resched();
		spin_lock(&sb->s_inode_list_lock);
	}
	spin_unlock(&sb->s_inode_list_lock);

	if (iput_inode)
		iput(iput_inode);
	/* Wait for outstanding inode references from connectors */
	wait_var_event(&sb->s_fsnotify_inode_refs,
		       !atomic_long_read(&sb->s_fsnotify_inode_refs));
}

/*
 * Given an inode, first check if we care what happens to our children.  Inotify
 * and dnotify both tell their parents about events.  If we care about any event
 * on a child we run all of our children and set a dentry flag saying that the
 * parent cares.  Thus when an event happens on a child it can quickly tell if
 * if there is a need to find a parent and send the event to the parent.
 */
void __fsnotify_update_child_dentry_flags(struct inode *inode)
{
	struct dentry *alias;
	int watched;

	if (!S_ISDIR(inode->i_mode))
		return;

	/* determine if the children should tell inode about their events */
	watched = fsnotify_inode_watches_children(inode);

	spin_lock(&inode->i_lock);
	/* run all of the dentries associated with this inode.  Since this is a
	 * directory, there damn well better only be one item on this list */
	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
		struct dentry *child;

		/* run all of the children of the original inode and fix their
		 * d_flags to indicate parental interest (their parent is the
		 * original inode) */
		spin_lock(&alias->d_lock);
		list_for_each_entry(child, &alias->d_subdirs, d_child) {
			if (!child->d_inode)
				continue;

			spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
			if (watched)
				child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
			else
				child->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
			spin_unlock(&child->d_lock);
		}
		spin_unlock(&alias->d_lock);
	}
	spin_unlock(&inode->i_lock);
}

/* Notify this dentry's parent about a child's events. */
int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask)
{
	struct dentry *parent;
	struct inode *p_inode;
	int ret = 0;

	if (!dentry)
		dentry = path->dentry;

	if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
		return 0;

	parent = dget_parent(dentry);
	p_inode = parent->d_inode;

	if (unlikely(!fsnotify_inode_watches_children(p_inode))) {
		__fsnotify_update_child_dentry_flags(p_inode);
	} else if (p_inode->i_fsnotify_mask & mask & ALL_FSNOTIFY_EVENTS) {
		struct name_snapshot name;

		/* we are notifying a parent so come up with the new mask which
		 * specifies these are events which came from a child. */
		mask |= FS_EVENT_ON_CHILD;

		take_dentry_name_snapshot(&name, dentry);
		if (path)
			ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
				       name.name, 0);
		else
			ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
				       name.name, 0);
		release_dentry_name_snapshot(&name);
	}

	dput(parent);

	return ret;
}
EXPORT_SYMBOL_GPL(__fsnotify_parent);

static int send_to_group(struct inode *to_tell,
			 __u32 mask, const void *data,
			 int data_is, u32 cookie,
			 const unsigned char *file_name,
			 struct fsnotify_iter_info *iter_info)
{
	struct fsnotify_group *group = NULL;
	__u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
	__u32 marks_mask = 0;
	__u32 marks_ignored_mask = 0;
	struct fsnotify_mark *mark;
	int type;

	if (WARN_ON(!iter_info->report_mask))
		return 0;

	/* clear ignored on inode modification */
	if (mask & FS_MODIFY) {
		fsnotify_foreach_obj_type(type) {
			if (!fsnotify_iter_should_report_type(iter_info, type))
				continue;
			mark = iter_info->marks[type];
			if (mark &&
			    !(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
				mark->ignored_mask = 0;
		}
	}

	fsnotify_foreach_obj_type(type) {
		if (!fsnotify_iter_should_report_type(iter_info, type))
			continue;
		mark = iter_info->marks[type];
		/* does the object mark tell us to do something? */
		if (mark) {
			group = mark->group;
			marks_mask |= mark->mask;
			marks_ignored_mask |= mark->ignored_mask;
		}
	}

	pr_debug("%s: group=%p to_tell=%p mask=%x marks_mask=%x marks_ignored_mask=%x"
		 " data=%p data_is=%d cookie=%d\n",
		 __func__, group, to_tell, mask, marks_mask, marks_ignored_mask,
		 data, data_is, cookie);

	if (!(test_mask & marks_mask & ~marks_ignored_mask))
		return 0;

	return group->ops->handle_event(group, to_tell, mask, data, data_is,
					file_name, cookie, iter_info);
}

static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp)
{
	struct fsnotify_mark_connector *conn;
	struct hlist_node *node = NULL;

	conn = srcu_dereference(*connp, &fsnotify_mark_srcu);
	if (conn)
		node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu);

	return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
}

static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark)
{
	struct hlist_node *node = NULL;

	if (mark)
		node = srcu_dereference(mark->obj_list.next,
					&fsnotify_mark_srcu);

	return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
}

/*
 * iter_info is a multi head priority queue of marks.
 * Pick a subset of marks from queue heads, all with the
 * same group and set the report_mask for selected subset.
 * Returns the report_mask of the selected subset.
 */
static unsigned int fsnotify_iter_select_report_types(
		struct fsnotify_iter_info *iter_info)
{
	struct fsnotify_group *max_prio_group = NULL;
	struct fsnotify_mark *mark;
	int type;

	/* Choose max prio group among groups of all queue heads */
	fsnotify_foreach_obj_type(type) {
		mark = iter_info->marks[type];
		if (mark &&
		    fsnotify_compare_groups(max_prio_group, mark->group) > 0)
			max_prio_group = mark->group;
	}

	if (!max_prio_group)
		return 0;

	/* Set the report mask for marks from same group as max prio group */
	iter_info->report_mask = 0;
	fsnotify_foreach_obj_type(type) {
		mark = iter_info->marks[type];
		if (mark &&
		    fsnotify_compare_groups(max_prio_group, mark->group) == 0)
			fsnotify_iter_set_report_type(iter_info, type);
	}

	return iter_info->report_mask;
}

/*
 * Pop from iter_info multi head queue, the marks that were iterated in the
 * current iteration step.
 */
static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
{
	int type;

	fsnotify_foreach_obj_type(type) {
		if (fsnotify_iter_should_report_type(iter_info, type))
			iter_info->marks[type] =
				fsnotify_next_mark(iter_info->marks[type]);
	}
}

/*
 * This is the main call to fsnotify.  The VFS calls into hook specific functions
 * in linux/fsnotify.h.  Those functions then in turn call here.  Here will call
 * out to all of the registered fsnotify_group.  Those groups can then use the
 * notification event in whatever means they feel necessary.
 */
int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
	     const unsigned char *file_name, u32 cookie)
{
	struct fsnotify_iter_info iter_info = {};
	struct mount *mnt;
	int ret = 0;
	__u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);

	if (data_is == FSNOTIFY_EVENT_PATH)
		mnt = real_mount(((const struct path *)data)->mnt);
	else
		mnt = NULL;

	/* An event "on child" is not intended for a mount mark */
	if (mask & FS_EVENT_ON_CHILD)
		mnt = NULL;

	/*
	 * Optimization: srcu_read_lock() has a memory barrier which can
	 * be expensive.  It protects walking the *_fsnotify_marks lists.
	 * However, if we do not walk the lists, we do not have to do
	 * SRCU because we have no references to any objects and do not
	 * need SRCU to keep them "alive".
	 */
	if (!to_tell->i_fsnotify_marks &&
	    (!mnt || !mnt->mnt_fsnotify_marks))
		return 0;
	/*
	 * if this is a modify event we may need to clear the ignored masks
	 * otherwise return if neither the inode nor the vfsmount care about
	 * this type of event.
	 */
	if (!(mask & FS_MODIFY) &&
	    !(test_mask & to_tell->i_fsnotify_mask) &&
	    !(mnt && test_mask & mnt->mnt_fsnotify_mask))
		return 0;

	iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);

	iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
		fsnotify_first_mark(&to_tell->i_fsnotify_marks);
	if (mnt) {
		iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] =
			fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
	}

	/*
	 * We need to merge inode & vfsmount mark lists so that inode mark
	 * ignore masks are properly reflected for mount mark notifications.
	 * That's why this traversal is so complicated...
	 */
	while (fsnotify_iter_select_report_types(&iter_info)) {
		ret = send_to_group(to_tell, mask, data, data_is, cookie,
				    file_name, &iter_info);

		if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
			goto out;

		fsnotify_iter_next(&iter_info);
	}
	ret = 0;
out:
	srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx);

	return ret;
}
EXPORT_SYMBOL_GPL(fsnotify);

extern struct kmem_cache *fsnotify_mark_connector_cachep;

static __init int fsnotify_init(void)
{
	int ret;

	BUG_ON(hweight32(ALL_FSNOTIFY_BITS) != 23);

	ret = init_srcu_struct(&fsnotify_mark_srcu);
	if (ret)
		panic("initializing fsnotify_mark_srcu");

	fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector,
						    SLAB_PANIC);

	return 0;
}
core_initcall(fsnotify_init);