summaryrefslogtreecommitdiffstats
path: root/fs/notify/fanotify/fanotify.c
blob: 98197802bbfbd944d0f791e947990de8be442708 (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
// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
#include <linux/fdtable.h>
#include <linux/fsnotify_backend.h>
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/kernel.h> /* UINT_MAX */
#include <linux/mount.h>
#include <linux/sched.h>
#include <linux/sched/user.h>
#include <linux/sched/signal.h>
#include <linux/types.h>
#include <linux/wait.h>
#include <linux/audit.h>
#include <linux/sched/mm.h>

#include "fanotify.h"

static bool should_merge(struct fsnotify_event *old_fsn,
			 struct fsnotify_event *new_fsn)
{
	struct fanotify_event_info *old, *new;

	pr_debug("%s: old=%p new=%p\n", __func__, old_fsn, new_fsn);
	old = FANOTIFY_E(old_fsn);
	new = FANOTIFY_E(new_fsn);

	if (old_fsn->inode == new_fsn->inode && old->pid == new->pid &&
	    old->path.mnt == new->path.mnt &&
	    old->path.dentry == new->path.dentry)
		return true;
	return false;
}

/* and the list better be locked by something too! */
static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
{
	struct fsnotify_event *test_event;
	struct fanotify_event_info *new;

	pr_debug("%s: list=%p event=%p\n", __func__, list, event);
	new = FANOTIFY_E(event);

	/*
	 * Don't merge a permission event with any other event so that we know
	 * the event structure we have created in fanotify_handle_event() is the
	 * one we should check for permission response.
	 */
	if (fanotify_is_perm_event(new->mask))
		return 0;

	list_for_each_entry_reverse(test_event, list, list) {
		if (should_merge(test_event, event)) {
			FANOTIFY_E(test_event)->mask |= new->mask;
			return 1;
		}
	}

	return 0;
}

static int fanotify_get_response(struct fsnotify_group *group,
				 struct fanotify_perm_event_info *event,
				 struct fsnotify_iter_info *iter_info)
{
	int ret;

	pr_debug("%s: group=%p event=%p\n", __func__, group, event);

	wait_event(group->fanotify_data.access_waitq, event->response);

	/* userspace responded, convert to something usable */
	switch (event->response & ~FAN_AUDIT) {
	case FAN_ALLOW:
		ret = 0;
		break;
	case FAN_DENY:
	default:
		ret = -EPERM;
	}

	/* Check if the response should be audited */
	if (event->response & FAN_AUDIT)
		audit_fanotify(event->response & ~FAN_AUDIT);

	event->response = 0;

	pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
		 group, event, ret);
	
	return ret;
}

/*
 * This function returns a mask for an event that only contains the flags
 * that have been specifically requested by the user. Flags that may have
 * been included within the event mask, but have not been explicitly
 * requested by the user, will not be present in the returned mask.
 */
static u32 fanotify_group_event_mask(struct fsnotify_iter_info *iter_info,
				       u32 event_mask, const void *data,
				       int data_type)
{
	__u32 marks_mask = 0, marks_ignored_mask = 0;
	const struct path *path = data;
	struct fsnotify_mark *mark;
	int type;

	pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
		 __func__, iter_info->report_mask, event_mask, data, data_type);

	/* If we don't have enough info to send an event to userspace say no */
	if (data_type != FSNOTIFY_EVENT_PATH)
		return 0;

	/* Sorry, fanotify only gives a damn about files and dirs */
	if (!d_is_reg(path->dentry) &&
	    !d_can_lookup(path->dentry))
		return 0;

	fsnotify_foreach_obj_type(type) {
		if (!fsnotify_iter_should_report_type(iter_info, type))
			continue;
		mark = iter_info->marks[type];
		/*
		 * If the event is for a child and this mark doesn't care about
		 * events on a child, don't send it!
		 */
		if (event_mask & FS_EVENT_ON_CHILD &&
		    (type != FSNOTIFY_OBJ_TYPE_INODE ||
		     !(mark->mask & FS_EVENT_ON_CHILD)))
			continue;

		marks_mask |= mark->mask;
		marks_ignored_mask |= mark->ignored_mask;
	}

	if (d_is_dir(path->dentry) &&
	    !(marks_mask & FS_ISDIR & ~marks_ignored_mask))
		return 0;

	return event_mask & FANOTIFY_OUTGOING_EVENTS & marks_mask &
		~marks_ignored_mask;
}

struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group,
						 struct inode *inode, u32 mask,
						 const struct path *path)
{
	struct fanotify_event_info *event = NULL;
	gfp_t gfp = GFP_KERNEL_ACCOUNT;

	/*
	 * For queues with unlimited length lost events are not expected and
	 * can possibly have security implications. Avoid losing events when
	 * memory is short.
	 */
	if (group->max_events == UINT_MAX)
		gfp |= __GFP_NOFAIL;

	/* Whoever is interested in the event, pays for the allocation. */
	memalloc_use_memcg(group->memcg);

	if (fanotify_is_perm_event(mask)) {
		struct fanotify_perm_event_info *pevent;

		pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
		if (!pevent)
			goto out;
		event = &pevent->fae;
		pevent->response = 0;
		goto init;
	}
	event = kmem_cache_alloc(fanotify_event_cachep, gfp);
	if (!event)
		goto out;
init: __maybe_unused
	fsnotify_init_event(&event->fse, inode);
	event->mask = mask;
	if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
		event->pid = get_pid(task_pid(current));
	else
		event->pid = get_pid(task_tgid(current));
	if (path) {
		event->path = *path;
		path_get(&event->path);
	} else {
		event->path.mnt = NULL;
		event->path.dentry = NULL;
	}
out:
	memalloc_unuse_memcg();
	return event;
}

static int fanotify_handle_event(struct fsnotify_group *group,
				 struct inode *inode,
				 u32 mask, const void *data, int data_type,
				 const unsigned char *file_name, u32 cookie,
				 struct fsnotify_iter_info *iter_info)
{
	int ret = 0;
	struct fanotify_event_info *event;
	struct fsnotify_event *fsn_event;

	BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS);
	BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY);
	BUILD_BUG_ON(FAN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
	BUILD_BUG_ON(FAN_CLOSE_WRITE != FS_CLOSE_WRITE);
	BUILD_BUG_ON(FAN_OPEN != FS_OPEN);
	BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);
	BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW);
	BUILD_BUG_ON(FAN_OPEN_PERM != FS_OPEN_PERM);
	BUILD_BUG_ON(FAN_ACCESS_PERM != FS_ACCESS_PERM);
	BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR);
	BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
	BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);

	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 12);

	mask = fanotify_group_event_mask(iter_info, mask, data, data_type);
	if (!mask)
		return 0;

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

	if (fanotify_is_perm_event(mask)) {
		/*
		 * fsnotify_prepare_user_wait() fails if we race with mark
		 * deletion.  Just let the operation pass in that case.
		 */
		if (!fsnotify_prepare_user_wait(iter_info))
			return 0;
	}

	event = fanotify_alloc_event(group, inode, mask, data);
	ret = -ENOMEM;
	if (unlikely(!event)) {
		/*
		 * We don't queue overflow events for permission events as
		 * there the access is denied and so no event is in fact lost.
		 */
		if (!fanotify_is_perm_event(mask))
			fsnotify_queue_overflow(group);
		goto finish;
	}

	fsn_event = &event->fse;
	ret = fsnotify_add_event(group, fsn_event, fanotify_merge);
	if (ret) {
		/* Permission events shouldn't be merged */
		BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS);
		/* Our event wasn't used in the end. Free it. */
		fsnotify_destroy_event(group, fsn_event);

		ret = 0;
	} else if (fanotify_is_perm_event(mask)) {
		ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event),
					    iter_info);
		fsnotify_destroy_event(group, fsn_event);
	}
finish:
	if (fanotify_is_perm_event(mask))
		fsnotify_finish_user_wait(iter_info);

	return ret;
}

static void fanotify_free_group_priv(struct fsnotify_group *group)
{
	struct user_struct *user;

	user = group->fanotify_data.user;
	atomic_dec(&user->fanotify_listeners);
	free_uid(user);
}

static void fanotify_free_event(struct fsnotify_event *fsn_event)
{
	struct fanotify_event_info *event;

	event = FANOTIFY_E(fsn_event);
	path_put(&event->path);
	put_pid(event->pid);
	if (fanotify_is_perm_event(event->mask)) {
		kmem_cache_free(fanotify_perm_event_cachep,
				FANOTIFY_PE(fsn_event));
		return;
	}
	kmem_cache_free(fanotify_event_cachep, event);
}

static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
{
	kmem_cache_free(fanotify_mark_cache, fsn_mark);
}

const struct fsnotify_ops fanotify_fsnotify_ops = {
	.handle_event = fanotify_handle_event,
	.free_group_priv = fanotify_free_group_priv,
	.free_event = fanotify_free_event,
	.free_mark = fanotify_free_mark,
};