summaryrefslogtreecommitdiffstats
path: root/kernel/ucount.c
blob: 866850e2eb9292f15fa2ca977929f250a8d75ba6 (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
/*
 *  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, version 2 of the
 *  License.
 */

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

#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 int zero = 0;
static int int_max = INT_MAX;
#define UCOUNT_ENTRY(name) 				\
	{						\
		.procname	= name,			\
		.maxlen		= sizeof(int),		\
		.mode		= 0644,			\
		.proc_handler	= proc_dointvec_minmax,	\
		.extra1		= &zero,		\
		.extra2		= &int_max,		\
	}
static struct ctl_table user_table[] = {
	UCOUNT_ENTRY("max_user_namespaces"),
	UCOUNT_ENTRY("max_pid_namespaces"),
	UCOUNT_ENTRY("max_uts_namespaces"),
	{ }
};
#endif /* CONFIG_SYSCTL */

bool setup_userns_sysctls(struct user_namespace *ns)
{
#ifdef CONFIG_SYSCTL
	struct ctl_table *tbl;
	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 struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
{
	struct hlist_head *hashent = ucounts_hashentry(ns, uid);
	struct ucounts *ucounts, *new;

	spin_lock(&ucounts_lock);
	ucounts = find_ucounts(ns, uid, hashent);
	if (!ucounts) {
		spin_unlock(&ucounts_lock);

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

		new->ns = ns;
		new->uid = uid;
		atomic_set(&new->count, 0);

		spin_lock(&ucounts_lock);
		ucounts = find_ucounts(ns, uid, hashent);
		if (ucounts) {
			kfree(new);
		} else {
			hlist_add_head(&new->node, hashent);
			ucounts = new;
		}
	}
	if (!atomic_add_unless(&ucounts->count, 1, INT_MAX))
		ucounts = NULL;
	spin_unlock(&ucounts_lock);
	return ucounts;
}

static void put_ucounts(struct ucounts *ucounts)
{
	if (atomic_dec_and_test(&ucounts->count)) {
		spin_lock(&ucounts_lock);
		hlist_del_init(&ucounts->node);
		spin_unlock(&ucounts_lock);

		kfree(ucounts);
	}
}

static inline bool atomic_inc_below(atomic_t *v, int u)
{
	int c, old;
	c = atomic_read(v);
	for (;;) {
		if (unlikely(c >= u))
			return false;
		old = atomic_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 = get_ucounts(ns, uid);
	for (iter = ucounts; iter; iter = tns->ucounts) {
		int max;
		tns = iter->ns;
		max = READ_ONCE(tns->ucount_max[type]);
		if (!atomic_inc_below(&iter->ucount[type], max))
			goto fail;
	}
	return ucounts;
fail:
	bad = iter;
	for (iter = ucounts; iter != bad; iter = iter->ns->ucounts)
		atomic_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) {
		int dec = atomic_dec_if_positive(&iter->ucount[type]);
		WARN_ON_ONCE(dec < 0);
	}
	put_ucounts(ucounts);
}

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);
	BUG_ON(!user_header);
	BUG_ON(!setup_userns_sysctls(&init_user_ns));
#endif
	return 0;
}
subsys_initcall(user_namespace_sysctl_init);