summaryrefslogtreecommitdiff
path: root/kernel/ucount.c
blob: 4f5613dac2273a1b96feb809e2a5f1449932769b (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
// SPDX-License-Identifier: GPL-2.0-only

#include <linux/stat.h>
#include <linux/sysctl.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/hash.h>
#include <linux/kmemleak.h>
#include <linux/user_namespace.h>

struct ucounts init_ucounts = {
	.ns    = &init_user_ns,
	.uid   = GLOBAL_ROOT_UID,
	.count = ATOMIC_INIT(1),
};

#define UCOUNTS_HASHTABLE_BITS 10
static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)];
static DEFINE_SPINLOCK(ucounts_lock);

#define ucounts_hashfn(ns, uid)						\
	hash_long((unsigned long)__kuid_val(uid) + (unsigned long)(ns), \
		  UCOUNTS_HASHTABLE_BITS)
#define ucounts_hashentry(ns, uid)	\
	(ucounts_hashtable + ucounts_hashfn(ns, uid))


#ifdef CONFIG_SYSCTL
static struct ctl_table_set *
set_lookup(struct ctl_table_root *root)
{
	return &current_user_ns()->set;
}

static int set_is_seen(struct ctl_table_set *set)
{
	return &current_user_ns()->set == set;
}

static int set_permissions(struct ctl_table_header *head,
				  struct ctl_table *table)
{
	struct user_namespace *user_ns =
		container_of(head->set, struct user_namespace, set);
	int mode;

	/* Allow users with CAP_SYS_RESOURCE unrestrained access */
	if (ns_capable(user_ns, CAP_SYS_RESOURCE))
		mode = (table->mode & S_IRWXU) >> 6;
	else
	/* Allow all others at most read-only access */
		mode = table->mode & S_IROTH;
	return (mode << 6) | (mode << 3) | mode;
}

static struct ctl_table_root set_root = {
	.lookup = set_lookup,
	.permissions = set_permissions,
};

static long ue_zero = 0;
static long ue_int_max = INT_MAX;

#define UCOUNT_ENTRY(name)					\
	{							\
		.procname	= name,				\
		.maxlen		= sizeof(long),			\
		.mode		= 0644,				\
		.proc_handler	= proc_doulongvec_minmax,	\
		.extra1		= &ue_zero,			\
		.extra2		= &ue_int_max,			\
	}
static struct ctl_table user_table[] = {
	UCOUNT_ENTRY("max_user_namespaces"),
	UCOUNT_ENTRY("max_pid_namespaces"),
	UCOUNT_ENTRY("max_uts_namespaces"),
	UCOUNT_ENTRY("max_ipc_namespaces"),
	UCOUNT_ENTRY("max_net_namespaces"),
	UCOUNT_ENTRY("max_mnt_namespaces"),
	UCOUNT_ENTRY("max_cgroup_namespaces"),
	UCOUNT_ENTRY("max_time_namespaces"),
#ifdef CONFIG_INOTIFY_USER
	UCOUNT_ENTRY("max_inotify_instances"),
	UCOUNT_ENTRY("max_inotify_watches"),
#endif
#ifdef CONFIG_FANOTIFY
	UCOUNT_ENTRY("max_fanotify_groups"),
	UCOUNT_ENTRY("max_fanotify_marks"),
#endif
	{ },
	{ },
	{ },
	{ },
	{ }
};
#endif /* CONFIG_SYSCTL */

bool setup_userns_sysctls(struct user_namespace *ns)
{
#ifdef CONFIG_SYSCTL
	struct ctl_table *tbl;

	BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS + 1);
	setup_sysctl_set(&ns->set, &set_root, set_is_seen);
	tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL);
	if (tbl) {
		int i;
		for (i = 0; i < UCOUNT_COUNTS; i++) {
			tbl[i].data = &ns->ucount_max[i];
		}
		ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl);
	}
	if (!ns->sysctls) {
		kfree(tbl);
		retire_sysctl_set(&ns->set);
		return false;
	}
#endif
	return true;
}

void retire_userns_sysctls(struct user_namespace *ns)
{
#ifdef CONFIG_SYSCTL
	struct ctl_table *tbl;

	tbl = ns->sysctls->ctl_table_arg;
	unregister_sysctl_table(ns->sysctls);
	retire_sysctl_set(&ns->set);
	kfree(tbl);
#endif
}

static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_head *hashent)
{
	struct ucounts *ucounts;

	hlist_for_each_entry(ucounts, hashent, node) {
		if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns))
			return ucounts;
	}
	return NULL;
}

static void hlist_add_ucounts(struct ucounts *ucounts)
{
	struct hlist_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid);
	spin_lock_irq(&ucounts_lock);
	hlist_add_head(&ucounts->node, hashent);
	spin_unlock_irq(&ucounts_lock);
}

static inline bool get_ucounts_or_wrap(struct ucounts *ucounts)
{
	/* Returns true on a successful get, false if the count wraps. */
	return !atomic_add_negative(1, &ucounts->count);
}

struct ucounts *get_ucounts(struct ucounts *ucounts)
{
	if (!get_ucounts_or_wrap(ucounts)) {
		put_ucounts(ucounts);
		ucounts = NULL;
	}
	return ucounts;
}

struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid)
{
	struct hlist_head *hashent = ucounts_hashentry(ns, uid);
	struct ucounts *ucounts, *new;
	bool wrapped;

	spin_lock_irq(&ucounts_lock);
	ucounts = find_ucounts(ns, uid, hashent);
	if (!ucounts) {
		spin_unlock_irq(&ucounts_lock);

		new = kzalloc(sizeof(*new), GFP_KERNEL);
		if (!new)
			return NULL;

		new->ns = ns;
		new->uid = uid;
		atomic_set(&new->count, 1);

		spin_lock_irq(&ucounts_lock);
		ucounts = find_ucounts(ns, uid, hashent);
		if (ucounts) {
			kfree(new);
		} else {
			hlist_add_head(&new->node, hashent);
			spin_unlock_irq(&ucounts_lock);
			return new;
		}
	}
	wrapped = !get_ucounts_or_wrap(ucounts);
	spin_unlock_irq(&ucounts_lock);
	if (wrapped) {
		put_ucounts(ucounts);
		return NULL;
	}
	return ucounts;
}

void put_ucounts(struct ucounts *ucounts)
{
	unsigned long flags;

	if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) {
		hlist_del_init(&ucounts->node);
		spin_unlock_irqrestore(&ucounts_lock, flags);
		kfree(ucounts);
	}
}

static inline bool atomic_long_inc_below(atomic_long_t *v, int u)
{
	long c, old;
	c = atomic_long_read(v);
	for (;;) {
		if (unlikely(c >= u))
			return false;
		old = atomic_long_cmpxchg(v, c, c+1);
		if (likely(old == c))
			return true;
		c = old;
	}
}

struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid,
			   enum ucount_type type)
{
	struct ucounts *ucounts, *iter, *bad;
	struct user_namespace *tns;
	ucounts = alloc_ucounts(ns, uid);
	for (iter = ucounts; iter; iter = tns->ucounts) {
		long max;
		tns = iter->ns;
		max = READ_ONCE(tns->ucount_max[type]);
		if (!atomic_long_inc_below(&iter->ucount[type], max))
			goto fail;
	}
	return ucounts;
fail:
	bad = iter;
	for (iter = ucounts; iter != bad; iter = iter->ns->ucounts)
		atomic_long_dec(&iter->ucount[type]);

	put_ucounts(ucounts);
	return NULL;
}

void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
{
	struct ucounts *iter;
	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
		long dec = atomic_long_dec_if_positive(&iter->ucount[type]);
		WARN_ON_ONCE(dec < 0);
	}
	put_ucounts(ucounts);
}

long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
{
	struct ucounts *iter;
	long ret = 0;

	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
		long max = READ_ONCE(iter->ns->ucount_max[type]);
		long new = atomic_long_add_return(v, &iter->ucount[type]);
		if (new < 0 || new > max)
			ret = LONG_MAX;
		else if (iter == ucounts)
			ret = new;
	}
	return ret;
}

bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
{
	struct ucounts *iter;
	long new = -1; /* Silence compiler warning */
	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
		long dec = atomic_long_sub_return(v, &iter->ucount[type]);
		WARN_ON_ONCE(dec < 0);
		if (iter == ucounts)
			new = dec;
	}
	return (new == 0);
}

static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
				struct ucounts *last, enum ucount_type type)
{
	struct ucounts *iter, *next;
	for (iter = ucounts; iter != last; iter = next) {
		long dec = atomic_long_sub_return(1, &iter->ucount[type]);
		WARN_ON_ONCE(dec < 0);
		next = iter->ns->ucounts;
		if (dec == 0)
			put_ucounts(iter);
	}
}

void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type)
{
	do_dec_rlimit_put_ucounts(ucounts, NULL, type);
}

long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
{
	/* Caller must hold a reference to ucounts */
	struct ucounts *iter;
	long dec, ret = 0;

	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
		long max = READ_ONCE(iter->ns->ucount_max[type]);
		long new = atomic_long_add_return(1, &iter->ucount[type]);
		if (new < 0 || new > max)
			goto unwind;
		if (iter == ucounts)
			ret = new;
		/*
		 * Grab an extra ucount reference for the caller when
		 * the rlimit count was previously 0.
		 */
		if (new != 1)
			continue;
		if (!get_ucounts(iter))
			goto dec_unwind;
	}
	return ret;
dec_unwind:
	dec = atomic_long_sub_return(1, &iter->ucount[type]);
	WARN_ON_ONCE(dec < 0);
unwind:
	do_dec_rlimit_put_ucounts(ucounts, iter, type);
	return 0;
}

bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max)
{
	struct ucounts *iter;
	if (get_ucounts_value(ucounts, type) > max)
		return true;
	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
		max = READ_ONCE(iter->ns->ucount_max[type]);
		if (get_ucounts_value(iter, type) > max)
			return true;
	}
	return false;
}

static __init int user_namespace_sysctl_init(void)
{
#ifdef CONFIG_SYSCTL
	static struct ctl_table_header *user_header;
	static struct ctl_table empty[1];
	/*
	 * It is necessary to register the user directory in the
	 * default set so that registrations in the child sets work
	 * properly.
	 */
	user_header = register_sysctl("user", empty);
	kmemleak_ignore(user_header);
	BUG_ON(!user_header);
	BUG_ON(!setup_userns_sysctls(&init_user_ns));
#endif
	hlist_add_ucounts(&init_ucounts);
	inc_rlimit_ucounts(&init_ucounts, UCOUNT_RLIMIT_NPROC, 1);
	return 0;
}
subsys_initcall(user_namespace_sysctl_init);