summaryrefslogtreecommitdiffstats
path: root/fs/notify/inotify/inotify_fsnotify.c
blob: 9ddcbadc98e29e36f460878750a33c2078383963 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * fs/inotify_user.c - inotify support for userspace
 *
 * Authors:
 *	John McCutchan	<ttb@tentacle.dhs.org>
 *	Robert Love	<rml@novell.com>
 *
 * Copyright (C) 2005 John McCutchan
 * Copyright 2006 Hewlett-Packard Development Company, L.P.
 *
 * Copyright (C) 2009 Eric Paris <Red Hat Inc>
 * inotify was largely rewriten to make use of the fsnotify infrastructure
 */

#include <linux/dcache.h> /* d_unlinked */
#include <linux/fs.h> /* struct inode */
#include <linux/fsnotify_backend.h>
#include <linux/inotify.h>
#include <linux/path.h> /* struct path */
#include <linux/slab.h> /* kmem_* */
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/sched/user.h>
#include <linux/sched/mm.h>

#include "inotify.h"

/*
 * Check if 2 events contain the same information.
 */
static bool event_compare(struct fsnotify_event *old_fsn,
			  struct fsnotify_event *new_fsn)
{
	struct inotify_event_info *old, *new;

	old = INOTIFY_E(old_fsn);
	new = INOTIFY_E(new_fsn);
	if (old->mask & FS_IN_IGNORED)
		return false;
	if ((old->mask == new->mask) &&
	    (old->wd == new->wd) &&
	    (old->name_len == new->name_len) &&
	    (!old->name_len || !strcmp(old->name, new->name)))
		return true;
	return false;
}

static int inotify_merge(struct list_head *list,
			  struct fsnotify_event *event)
{
	struct fsnotify_event *last_event;

	last_event = list_entry(list->prev, struct fsnotify_event, list);
	return event_compare(last_event, event);
}

static int inotify_one_event(struct fsnotify_group *group, u32 mask,
			     struct fsnotify_mark *inode_mark,
			     const struct path *path,
			     const struct qstr *file_name, u32 cookie)
{
	struct inotify_inode_mark *i_mark;
	struct inotify_event_info *event;
	struct fsnotify_event *fsn_event;
	int ret;
	int len = 0;
	int alloc_len = sizeof(struct inotify_event_info);
	struct mem_cgroup *old_memcg;

	if ((inode_mark->mask & FS_EXCL_UNLINK) &&
	    path && d_unlinked(path->dentry))
		return 0;

	if (file_name) {
		len = file_name->len;
		alloc_len += len + 1;
	}

	pr_debug("%s: group=%p mark=%p mask=%x\n", __func__, group, inode_mark,
		 mask);

	i_mark = container_of(inode_mark, struct inotify_inode_mark,
			      fsn_mark);

	/*
	 * Whoever is interested in the event, pays for the allocation. Do not
	 * trigger OOM killer in the target monitoring memcg as it may have
	 * security repercussion.
	 */
	old_memcg = set_active_memcg(group->memcg);
	event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
	set_active_memcg(old_memcg);

	if (unlikely(!event)) {
		/*
		 * Treat lost event due to ENOMEM the same way as queue
		 * overflow to let userspace know event was lost.
		 */
		fsnotify_queue_overflow(group);
		return -ENOMEM;
	}

	/*
	 * We now report FS_ISDIR flag with MOVE_SELF and DELETE_SELF events
	 * for fanotify. inotify never reported IN_ISDIR with those events.
	 * It looks like an oversight, but to avoid the risk of breaking
	 * existing inotify programs, mask the flag out from those events.
	 */
	if (mask & (IN_MOVE_SELF | IN_DELETE_SELF))
		mask &= ~IN_ISDIR;

	fsn_event = &event->fse;
	fsnotify_init_event(fsn_event, 0);
	event->mask = mask;
	event->wd = i_mark->wd;
	event->sync_cookie = cookie;
	event->name_len = len;
	if (len)
		strcpy(event->name, file_name->name);

	ret = fsnotify_add_event(group, fsn_event, inotify_merge);
	if (ret) {
		/* Our event wasn't used in the end. Free it. */
		fsnotify_destroy_event(group, fsn_event);
	}

	if (inode_mark->mask & IN_ONESHOT)
		fsnotify_destroy_mark(inode_mark, group);

	return 0;
}

int inotify_handle_event(struct fsnotify_group *group, u32 mask,
			 const void *data, int data_type, struct inode *dir,
			 const struct qstr *file_name, u32 cookie,
			 struct fsnotify_iter_info *iter_info)
{
	const struct path *path = fsnotify_data_path(data, data_type);
	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
	struct fsnotify_mark *child_mark = fsnotify_iter_child_mark(iter_info);
	int ret = 0;

	if (WARN_ON(fsnotify_iter_vfsmount_mark(iter_info)))
		return 0;

	/*
	 * Some events cannot be sent on both parent and child marks
	 * (e.g. IN_CREATE).  Those events are always sent on inode_mark.
	 * For events that are possible on both parent and child (e.g. IN_OPEN),
	 * event is sent on inode_mark with name if the parent is watching and
	 * is sent on child_mark without name if child is watching.
	 * If both parent and child are watching, report the event with child's
	 * name here and report another event without child's name below.
	 */
	if (inode_mark)
		ret = inotify_one_event(group, mask, inode_mark, path,
					file_name, cookie);
	if (ret || !child_mark)
		return ret;

	return inotify_one_event(group, mask, child_mark, path, NULL, 0);
}

static void inotify_freeing_mark(struct fsnotify_mark *fsn_mark, struct fsnotify_group *group)
{
	inotify_ignored_and_remove_idr(fsn_mark, group);
}

/*
 * This is NEVER supposed to be called.  Inotify marks should either have been
 * removed from the idr when the watch was removed or in the
 * fsnotify_destroy_mark_by_group() call when the inotify instance was being
 * torn down.  This is only called if the idr is about to be freed but there
 * are still marks in it.
 */
static int idr_callback(int id, void *p, void *data)
{
	struct fsnotify_mark *fsn_mark;
	struct inotify_inode_mark *i_mark;
	static bool warned = false;

	if (warned)
		return 0;

	warned = true;
	fsn_mark = p;
	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);

	WARN(1, "inotify closing but id=%d for fsn_mark=%p in group=%p still in "
		"idr.  Probably leaking memory\n", id, p, data);

	/*
	 * I'm taking the liberty of assuming that the mark in question is a
	 * valid address and I'm dereferencing it.  This might help to figure
	 * out why we got here and the panic is no worse than the original
	 * BUG() that was here.
	 */
	if (fsn_mark)
		printk(KERN_WARNING "fsn_mark->group=%p wd=%d\n",
			fsn_mark->group, i_mark->wd);
	return 0;
}

static void inotify_free_group_priv(struct fsnotify_group *group)
{
	/* ideally the idr is empty and we won't hit the BUG in the callback */
	idr_for_each(&group->inotify_data.idr, idr_callback, group);
	idr_destroy(&group->inotify_data.idr);
	if (group->inotify_data.ucounts)
		dec_inotify_instances(group->inotify_data.ucounts);
}

static void inotify_free_event(struct fsnotify_event *fsn_event)
{
	kfree(INOTIFY_E(fsn_event));
}

/* ding dong the mark is dead */
static void inotify_free_mark(struct fsnotify_mark *fsn_mark)
{
	struct inotify_inode_mark *i_mark;

	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);

	kmem_cache_free(inotify_inode_mark_cachep, i_mark);
}

const struct fsnotify_ops inotify_fsnotify_ops = {
	.handle_event = inotify_handle_event,
	.free_group_priv = inotify_free_group_priv,
	.free_event = inotify_free_event,
	.freeing_mark = inotify_freeing_mark,
	.free_mark = inotify_free_mark,
};