summaryrefslogtreecommitdiffstats
path: root/kernel/capability.c
blob: 0a3d2c863a1c784431a04d1b43456d7c4bb51049 (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
/*
 * linux/kernel/capability.c
 *
 * Copyright (C) 1997  Andrew Main <zefram@fysh.org>
 *
 * Integrated into 2.1.97+,  Andrew G. Morgan <morgan@kernel.org>
 * 30 May 2002:	Cleanup, Robert M. Love <rml@tech9.net>
 */

#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <asm/uaccess.h>

/*
 * Leveraged for setting/resetting capabilities
 */

const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET;
const kernel_cap_t __cap_full_set = CAP_FULL_SET;
const kernel_cap_t __cap_init_eff_set = CAP_INIT_EFF_SET;

EXPORT_SYMBOL(__cap_empty_set);
EXPORT_SYMBOL(__cap_full_set);
EXPORT_SYMBOL(__cap_init_eff_set);

int file_caps_enabled = 1;

static int __init file_caps_disable(char *str)
{
	file_caps_enabled = 0;
	return 1;
}
__setup("no_file_caps", file_caps_disable);

/*
 * More recent versions of libcap are available from:
 *
 *   http://www.kernel.org/pub/linux/libs/security/linux-privs/
 */

static void warn_legacy_capability_use(void)
{
	static int warned;
	if (!warned) {
		char name[sizeof(current->comm)];

		printk(KERN_INFO "warning: `%s' uses 32-bit capabilities"
		       " (legacy support in use)\n",
		       get_task_comm(name, current));
		warned = 1;
	}
}

/*
 * Version 2 capabilities worked fine, but the linux/capability.h file
 * that accompanied their introduction encouraged their use without
 * the necessary user-space source code changes. As such, we have
 * created a version 3 with equivalent functionality to version 2, but
 * with a header change to protect legacy source code from using
 * version 2 when it wanted to use version 1. If your system has code
 * that trips the following warning, it is using version 2 specific
 * capabilities and may be doing so insecurely.
 *
 * The remedy is to either upgrade your version of libcap (to 2.10+,
 * if the application is linked against it), or recompile your
 * application with modern kernel headers and this warning will go
 * away.
 */

static void warn_deprecated_v2(void)
{
	static int warned;

	if (!warned) {
		char name[sizeof(current->comm)];

		printk(KERN_INFO "warning: `%s' uses deprecated v2"
		       " capabilities in a way that may be insecure.\n",
		       get_task_comm(name, current));
		warned = 1;
	}
}

/*
 * Version check. Return the number of u32s in each capability flag
 * array, or a negative value on error.
 */
static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
{
	__u32 version;

	if (get_user(version, &header->version))
		return -EFAULT;

	switch (version) {
	case _LINUX_CAPABILITY_VERSION_1:
		warn_legacy_capability_use();
		*tocopy = _LINUX_CAPABILITY_U32S_1;
		break;
	case _LINUX_CAPABILITY_VERSION_2:
		warn_deprecated_v2();
		/*
		 * fall through - v3 is otherwise equivalent to v2.
		 */
	case _LINUX_CAPABILITY_VERSION_3:
		*tocopy = _LINUX_CAPABILITY_U32S_3;
		break;
	default:
		if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version))
			return -EFAULT;
		return -EINVAL;
	}

	return 0;
}

/*
 * The only thing that can change the capabilities of the current
 * process is the current process. As such, we can't be in this code
 * at the same time as we are in the process of setting capabilities
 * in this process. The net result is that we can limit our use of
 * locks to when we are reading the caps of another process.
 */
static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
				     kernel_cap_t *pIp, kernel_cap_t *pPp)
{
	int ret;

	if (pid && (pid != task_pid_vnr(current))) {
		struct task_struct *target;

		rcu_read_lock();

		target = find_task_by_vpid(pid);
		if (!target)
			ret = -ESRCH;
		else
			ret = security_capget(target, pEp, pIp, pPp);

		rcu_read_unlock();
	} else
		ret = security_capget(current, pEp, pIp, pPp);

	return ret;
}

/**
 * sys_capget - get the capabilities of a given process.
 * @header: pointer to struct that contains capability version and
 *	target pid data
 * @dataptr: pointer to struct that contains the effective, permitted,
 *	and inheritable capabilities that are returned
 *
 * Returns 0 on success and < 0 on error.
 */
SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
{
	int ret = 0;
	pid_t pid;
	unsigned tocopy;
	kernel_cap_t pE, pI, pP;

	ret = cap_validate_magic(header, &tocopy);
	if ((dataptr == NULL) || (ret != 0))
		return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret;

	if (get_user(pid, &header->pid))
		return -EFAULT;

	if (pid < 0)
		return -EINVAL;

	ret = cap_get_target_pid(pid, &pE, &pI, &pP);
	if (!ret) {
		struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
		unsigned i;

		for (i = 0; i < tocopy; i++) {
			kdata[i].effective = pE.cap[i];
			kdata[i].permitted = pP.cap[i];
			kdata[i].inheritable = pI.cap[i];
		}

		/*
		 * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S,
		 * we silently drop the upper capabilities here. This
		 * has the effect of making older libcap
		 * implementations implicitly drop upper capability
		 * bits when they perform a: capget/modify/capset
		 * sequence.
		 *
		 * This behavior is considered fail-safe
		 * behavior. Upgrading the application to a newer
		 * version of libcap will enable access to the newer
		 * capabilities.
		 *
		 * An alternative would be to return an error here
		 * (-ERANGE), but that causes legacy applications to
		 * unexpectidly fail; the capget/modify/capset aborts
		 * before modification is attempted and the application
		 * fails.
		 */
		if (copy_to_user(dataptr, kdata, tocopy
				 * sizeof(struct __user_cap_data_struct))) {
			return -EFAULT;
		}
	}

	return ret;
}

/**
 * sys_capset - set capabilities for a process or (*) a group of processes
 * @header: pointer to struct that contains capability version and
 *	target pid data
 * @data: pointer to struct that contains the effective, permitted,
 *	and inheritable capabilities
 *
 * Set capabilities for the current process only.  The ability to any other
 * process(es) has been deprecated and removed.
 *
 * The restrictions on setting capabilities are specified as:
 *
 * I: any raised capabilities must be a subset of the old permitted
 * P: any raised capabilities must be a subset of the old permitted
 * E: must be set to a subset of new permitted
 *
 * Returns 0 on success and < 0 on error.
 */
SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
{
	struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
	unsigned i, tocopy, copybytes;
	kernel_cap_t inheritable, permitted, effective;
	struct cred *new;
	int ret;
	pid_t pid;

	ret = cap_validate_magic(header, &tocopy);
	if (ret != 0)
		return ret;

	if (get_user(pid, &header->pid))
		return -EFAULT;

	/* may only affect current now */
	if (pid != 0 && pid != task_pid_vnr(current))
		return -EPERM;

	copybytes = tocopy * sizeof(struct __user_cap_data_struct);
	if (copybytes > sizeof(kdata))
		return -EFAULT;

	if (copy_from_user(&kdata, data, copybytes))
		return -EFAULT;

	for (i = 0; i < tocopy; i++) {
		effective.cap[i] = kdata[i].effective;
		permitted.cap[i] = kdata[i].permitted;
		inheritable.cap[i] = kdata[i].inheritable;
	}
	while (i < _KERNEL_CAPABILITY_U32S) {
		effective.cap[i] = 0;
		permitted.cap[i] = 0;
		inheritable.cap[i] = 0;
		i++;
	}

	new = prepare_creds();
	if (!new)
		return -ENOMEM;

	ret = security_capset(new, current_cred(),
			      &effective, &inheritable, &permitted);
	if (ret < 0)
		goto error;

	audit_log_capset(pid, new, current_cred());

	return commit_creds(new);

error:
	abort_creds(new);
	return ret;
}

/**
 * capable - Determine if the current task has a superior capability in effect
 * @cap: The capability to be tested for
 *
 * Return true if the current task has the given superior capability currently
 * available for use, false if not.
 *
 * This sets PF_SUPERPRIV on the task if the capability is available on the
 * assumption that it's about to be used.
 */
bool capable(int cap)
{
	return ns_capable(&init_user_ns, cap);
}
EXPORT_SYMBOL(capable);

/**
 * ns_capable - Determine if the current task has a superior capability in effect
 * @ns:  The usernamespace we want the capability in
 * @cap: The capability to be tested for
 *
 * Return true if the current task has the given superior capability currently
 * available for use, false if not.
 *
 * This sets PF_SUPERPRIV on the task if the capability is available on the
 * assumption that it's about to be used.
 */
bool ns_capable(struct user_namespace *ns, int cap)
{
	if (unlikely(!cap_valid(cap))) {
		printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap);
		BUG();
	}

	if (security_capable(ns, current_cred(), cap) == 0) {
		current->flags |= PF_SUPERPRIV;
		return true;
	}
	return false;
}
EXPORT_SYMBOL(ns_capable);

/**
 * task_ns_capable - Determine whether current task has a superior
 * capability targeted at a specific task's user namespace.
 * @t: The task whose user namespace is targeted.
 * @cap: The capability in question.
 *
 *  Return true if it does, false otherwise.
 */
bool task_ns_capable(struct task_struct *t, int cap)
{
	return ns_capable(task_cred_xxx(t, user)->user_ns, cap);
}
EXPORT_SYMBOL(task_ns_capable);