summaryrefslogtreecommitdiff
path: root/kernel/user.c
blob: 03cedc366dc9e1a3733b1e05a0f58356dbaee725 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * The "user cache".
 *
 * (C) Copyright 1991-2000 Linus Torvalds
 *
 * We have a per-user structure to keep track of how many
 * processes, files etc the user has claimed, in order to be
 * able to have per-user limits for system resources. 
 */

#include <linux/init.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/bitops.h>
#include <linux/key.h>
#include <linux/sched/user.h>
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
#include <linux/binfmts.h>
#include <linux/proc_ns.h>

#if IS_ENABLED(CONFIG_BINFMT_MISC)
struct binfmt_misc init_binfmt_misc = {
	.entries = LIST_HEAD_INIT(init_binfmt_misc.entries),
	.enabled = true,
	.entries_lock = __RW_LOCK_UNLOCKED(init_binfmt_misc.entries_lock),
};
EXPORT_SYMBOL_GPL(init_binfmt_misc);
#endif

/*
 * userns count is 1 for root user, 1 for init_uts_ns,
 * and 1 for... ?
 */
struct user_namespace init_user_ns = {
	.uid_map = {
		.nr_extents = 1,
		{
			.extent[0] = {
				.first = 0,
				.lower_first = 0,
				.count = 4294967295U,
			},
		},
	},
	.gid_map = {
		.nr_extents = 1,
		{
			.extent[0] = {
				.first = 0,
				.lower_first = 0,
				.count = 4294967295U,
			},
		},
	},
	.projid_map = {
		.nr_extents = 1,
		{
			.extent[0] = {
				.first = 0,
				.lower_first = 0,
				.count = 4294967295U,
			},
		},
	},
	.ns.count = REFCOUNT_INIT(3),
	.owner = GLOBAL_ROOT_UID,
	.group = GLOBAL_ROOT_GID,
	.ns.inum = PROC_USER_INIT_INO,
#ifdef CONFIG_USER_NS
	.ns.ops = &userns_operations,
#endif
	.flags = USERNS_INIT_FLAGS,
#ifdef CONFIG_KEYS
	.keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list),
	.keyring_sem = __RWSEM_INITIALIZER(init_user_ns.keyring_sem),
#endif
#if IS_ENABLED(CONFIG_BINFMT_MISC)
	.binfmt_misc = &init_binfmt_misc,
#endif
};
EXPORT_SYMBOL_GPL(init_user_ns);

/*
 * UID task count cache, to get fast user lookup in "alloc_uid"
 * when changing user ID's (ie setuid() and friends).
 */

#define UIDHASH_BITS	(CONFIG_BASE_SMALL ? 3 : 7)
#define UIDHASH_SZ	(1 << UIDHASH_BITS)
#define UIDHASH_MASK		(UIDHASH_SZ - 1)
#define __uidhashfn(uid)	(((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK)
#define uidhashentry(uid)	(uidhash_table + __uidhashfn((__kuid_val(uid))))

static struct kmem_cache *uid_cachep;
static struct hlist_head uidhash_table[UIDHASH_SZ];

/*
 * The uidhash_lock is mostly taken from process context, but it is
 * occasionally also taken from softirq/tasklet context, when
 * task-structs get RCU-freed. Hence all locking must be softirq-safe.
 * But free_uid() is also called with local interrupts disabled, and running
 * local_bh_enable() with local interrupts disabled is an error - we'll run
 * softirq callbacks, and they can unconditionally enable interrupts, and
 * the caller of free_uid() didn't expect that..
 */
static DEFINE_SPINLOCK(uidhash_lock);

/* root_user.__count is 1, for init task cred */
struct user_struct root_user = {
	.__count	= REFCOUNT_INIT(1),
	.uid		= GLOBAL_ROOT_UID,
	.ratelimit	= RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0),
};

/*
 * These routines must be called with the uidhash spinlock held!
 */
static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
{
	hlist_add_head(&up->uidhash_node, hashent);
}

static void uid_hash_remove(struct user_struct *up)
{
	hlist_del_init(&up->uidhash_node);
}

static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
{
	struct user_struct *user;

	hlist_for_each_entry(user, hashent, uidhash_node) {
		if (uid_eq(user->uid, uid)) {
			refcount_inc(&user->__count);
			return user;
		}
	}

	return NULL;
}

static int user_epoll_alloc(struct user_struct *up)
{
#ifdef CONFIG_EPOLL
	return percpu_counter_init(&up->epoll_watches, 0, GFP_KERNEL);
#else
	return 0;
#endif
}

static void user_epoll_free(struct user_struct *up)
{
#ifdef CONFIG_EPOLL
	percpu_counter_destroy(&up->epoll_watches);
#endif
}

/* IRQs are disabled and uidhash_lock is held upon function entry.
 * IRQ state (as stored in flags) is restored and uidhash_lock released
 * upon function exit.
 */
static void free_user(struct user_struct *up, unsigned long flags)
	__releases(&uidhash_lock)
{
	uid_hash_remove(up);
	spin_unlock_irqrestore(&uidhash_lock, flags);
	user_epoll_free(up);
	kmem_cache_free(uid_cachep, up);
}

/*
 * Locate the user_struct for the passed UID.  If found, take a ref on it.  The
 * caller must undo that ref with free_uid().
 *
 * If the user_struct could not be found, return NULL.
 */
struct user_struct *find_user(kuid_t uid)
{
	struct user_struct *ret;
	unsigned long flags;

	spin_lock_irqsave(&uidhash_lock, flags);
	ret = uid_hash_find(uid, uidhashentry(uid));
	spin_unlock_irqrestore(&uidhash_lock, flags);
	return ret;
}

void free_uid(struct user_struct *up)
{
	unsigned long flags;

	if (!up)
		return;

	if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags))
		free_user(up, flags);
}
EXPORT_SYMBOL_GPL(free_uid);

struct user_struct *alloc_uid(kuid_t uid)
{
	struct hlist_head *hashent = uidhashentry(uid);
	struct user_struct *up, *new;

	spin_lock_irq(&uidhash_lock);
	up = uid_hash_find(uid, hashent);
	spin_unlock_irq(&uidhash_lock);

	if (!up) {
		new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL);
		if (!new)
			return NULL;

		new->uid = uid;
		refcount_set(&new->__count, 1);
		if (user_epoll_alloc(new)) {
			kmem_cache_free(uid_cachep, new);
			return NULL;
		}
		ratelimit_state_init(&new->ratelimit, HZ, 100);
		ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE);

		/*
		 * Before adding this, check whether we raced
		 * on adding the same user already..
		 */
		spin_lock_irq(&uidhash_lock);
		up = uid_hash_find(uid, hashent);
		if (up) {
			user_epoll_free(new);
			kmem_cache_free(uid_cachep, new);
		} else {
			uid_hash_insert(new, hashent);
			up = new;
		}
		spin_unlock_irq(&uidhash_lock);
	}

	return up;
}

static int __init uid_cache_init(void)
{
	int n;

	uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct),
			0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);

	for(n = 0; n < UIDHASH_SZ; ++n)
		INIT_HLIST_HEAD(uidhash_table + n);

	if (user_epoll_alloc(&root_user))
		panic("root_user epoll percpu counter alloc failed");

	/* Insert the root user immediately (init already runs as root) */
	spin_lock_irq(&uidhash_lock);
	uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
	spin_unlock_irq(&uidhash_lock);

	return 0;
}
subsys_initcall(uid_cache_init);