summaryrefslogtreecommitdiffstats
path: root/kernel/time/namespace.c
blob: e6ba064ce7730adfb480caa29755db022a660e7e (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
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
// SPDX-License-Identifier: GPL-2.0
/*
 * Author: Andrei Vagin <avagin@openvz.org>
 * Author: Dmitry Safonov <dima@arista.com>
 */

#include <linux/time_namespace.h>
#include <linux/user_namespace.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/clocksource.h>
#include <linux/seq_file.h>
#include <linux/proc_ns.h>
#include <linux/export.h>
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/err.h>
#include <linux/mm.h>

#include <vdso/datapage.h>

ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim,
				struct timens_offsets *ns_offsets)
{
	ktime_t offset;

	switch (clockid) {
	case CLOCK_MONOTONIC:
		offset = timespec64_to_ktime(ns_offsets->monotonic);
		break;
	case CLOCK_BOOTTIME:
	case CLOCK_BOOTTIME_ALARM:
		offset = timespec64_to_ktime(ns_offsets->boottime);
		break;
	default:
		return tim;
	}

	/*
	 * Check that @tim value is in [offset, KTIME_MAX + offset]
	 * and subtract offset.
	 */
	if (tim < offset) {
		/*
		 * User can specify @tim *absolute* value - if it's lesser than
		 * the time namespace's offset - it's already expired.
		 */
		tim = 0;
	} else {
		tim = ktime_sub(tim, offset);
		if (unlikely(tim > KTIME_MAX))
			tim = KTIME_MAX;
	}

	return tim;
}

static struct ucounts *inc_time_namespaces(struct user_namespace *ns)
{
	return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES);
}

static void dec_time_namespaces(struct ucounts *ucounts)
{
	dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES);
}

/**
 * clone_time_ns - Clone a time namespace
 * @user_ns:	User namespace which owns a new namespace.
 * @old_ns:	Namespace to clone
 *
 * Clone @old_ns and set the clone refcount to 1
 *
 * Return: The new namespace or ERR_PTR.
 */
static struct time_namespace *clone_time_ns(struct user_namespace *user_ns,
					  struct time_namespace *old_ns)
{
	struct time_namespace *ns;
	struct ucounts *ucounts;
	int err;

	err = -ENOSPC;
	ucounts = inc_time_namespaces(user_ns);
	if (!ucounts)
		goto fail;

	err = -ENOMEM;
	ns = kmalloc(sizeof(*ns), GFP_KERNEL);
	if (!ns)
		goto fail_dec;

	kref_init(&ns->kref);

	ns->vvar_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
	if (!ns->vvar_page)
		goto fail_free;

	err = ns_alloc_inum(&ns->ns);
	if (err)
		goto fail_free_page;

	ns->ucounts = ucounts;
	ns->ns.ops = &timens_operations;
	ns->user_ns = get_user_ns(user_ns);
	ns->offsets = old_ns->offsets;
	ns->frozen_offsets = false;
	return ns;

fail_free_page:
	__free_page(ns->vvar_page);
fail_free:
	kfree(ns);
fail_dec:
	dec_time_namespaces(ucounts);
fail:
	return ERR_PTR(err);
}

/**
 * copy_time_ns - Create timens_for_children from @old_ns
 * @flags:	Cloning flags
 * @user_ns:	User namespace which owns a new namespace.
 * @old_ns:	Namespace to clone
 *
 * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children;
 * adds a refcounter to @old_ns otherwise.
 *
 * Return: timens_for_children namespace or ERR_PTR.
 */
struct time_namespace *copy_time_ns(unsigned long flags,
	struct user_namespace *user_ns, struct time_namespace *old_ns)
{
	if (!(flags & CLONE_NEWTIME))
		return get_time_ns(old_ns);

	return clone_time_ns(user_ns, old_ns);
}

static struct timens_offset offset_from_ts(struct timespec64 off)
{
	struct timens_offset ret;

	ret.sec = off.tv_sec;
	ret.nsec = off.tv_nsec;

	return ret;
}

/*
 * A time namespace VVAR page has the same layout as the VVAR page which
 * contains the system wide VDSO data.
 *
 * For a normal task the VVAR pages are installed in the normal ordering:
 *     VVAR
 *     PVCLOCK
 *     HVCLOCK
 *     TIMENS   <- Not really required
 *
 * Now for a timens task the pages are installed in the following order:
 *     TIMENS
 *     PVCLOCK
 *     HVCLOCK
 *     VVAR
 *
 * The check for vdso_data->clock_mode is in the unlikely path of
 * the seq begin magic. So for the non-timens case most of the time
 * 'seq' is even, so the branch is not taken.
 *
 * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check
 * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the
 * update to finish and for 'seq' to become even anyway.
 *
 * Timens page has vdso_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which
 * enforces the time namespace handling path.
 */
static void timens_setup_vdso_data(struct vdso_data *vdata,
				   struct time_namespace *ns)
{
	struct timens_offset *offset = vdata->offset;
	struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic);
	struct timens_offset boottime = offset_from_ts(ns->offsets.boottime);

	vdata->seq			= 1;
	vdata->clock_mode		= VDSO_CLOCKMODE_TIMENS;
	offset[CLOCK_MONOTONIC]		= monotonic;
	offset[CLOCK_MONOTONIC_RAW]	= monotonic;
	offset[CLOCK_MONOTONIC_COARSE]	= monotonic;
	offset[CLOCK_BOOTTIME]		= boottime;
	offset[CLOCK_BOOTTIME_ALARM]	= boottime;
}

/*
 * Protects possibly multiple offsets writers racing each other
 * and tasks entering the namespace.
 */
static DEFINE_MUTEX(offset_lock);

static void timens_set_vvar_page(struct task_struct *task,
				struct time_namespace *ns)
{
	struct vdso_data *vdata;
	unsigned int i;

	if (ns == &init_time_ns)
		return;

	/* Fast-path, taken by every task in namespace except the first. */
	if (likely(ns->frozen_offsets))
		return;

	mutex_lock(&offset_lock);
	/* Nothing to-do: vvar_page has been already initialized. */
	if (ns->frozen_offsets)
		goto out;

	ns->frozen_offsets = true;
	vdata = arch_get_vdso_data(page_address(ns->vvar_page));

	for (i = 0; i < CS_BASES; i++)
		timens_setup_vdso_data(&vdata[i], ns);

out:
	mutex_unlock(&offset_lock);
}

void free_time_ns(struct kref *kref)
{
	struct time_namespace *ns;

	ns = container_of(kref, struct time_namespace, kref);
	dec_time_namespaces(ns->ucounts);
	put_user_ns(ns->user_ns);
	ns_free_inum(&ns->ns);
	__free_page(ns->vvar_page);
	kfree(ns);
}

static struct time_namespace *to_time_ns(struct ns_common *ns)
{
	return container_of(ns, struct time_namespace, ns);
}

static struct ns_common *timens_get(struct task_struct *task)
{
	struct time_namespace *ns = NULL;
	struct nsproxy *nsproxy;

	task_lock(task);
	nsproxy = task->nsproxy;
	if (nsproxy) {
		ns = nsproxy->time_ns;
		get_time_ns(ns);
	}
	task_unlock(task);

	return ns ? &ns->ns : NULL;
}

static struct ns_common *timens_for_children_get(struct task_struct *task)
{
	struct time_namespace *ns = NULL;
	struct nsproxy *nsproxy;

	task_lock(task);
	nsproxy = task->nsproxy;
	if (nsproxy) {
		ns = nsproxy->time_ns_for_children;
		get_time_ns(ns);
	}
	task_unlock(task);

	return ns ? &ns->ns : NULL;
}

static void timens_put(struct ns_common *ns)
{
	put_time_ns(to_time_ns(ns));
}

static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
{
	struct time_namespace *ns = to_time_ns(new);
	int err;

	if (!current_is_single_threaded())
		return -EUSERS;

	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
		return -EPERM;

	timens_set_vvar_page(current, ns);

	err = vdso_join_timens(current, ns);
	if (err)
		return err;

	get_time_ns(ns);
	put_time_ns(nsproxy->time_ns);
	nsproxy->time_ns = ns;

	get_time_ns(ns);
	put_time_ns(nsproxy->time_ns_for_children);
	nsproxy->time_ns_for_children = ns;
	return 0;
}

int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
{
	struct ns_common *nsc = &nsproxy->time_ns_for_children->ns;
	struct time_namespace *ns = to_time_ns(nsc);
	int err;

	/* create_new_namespaces() already incremented the ref counter */
	if (nsproxy->time_ns == nsproxy->time_ns_for_children)
		return 0;

	timens_set_vvar_page(tsk, ns);

	err = vdso_join_timens(tsk, ns);
	if (err)
		return err;

	get_time_ns(ns);
	put_time_ns(nsproxy->time_ns);
	nsproxy->time_ns = ns;

	return 0;
}

static struct user_namespace *timens_owner(struct ns_common *ns)
{
	return to_time_ns(ns)->user_ns;
}

static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts)
{
	seq_printf(m, "%d %lld %ld\n", clockid, ts->tv_sec, ts->tv_nsec);
}

void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m)
{
	struct ns_common *ns;
	struct time_namespace *time_ns;

	ns = timens_for_children_get(p);
	if (!ns)
		return;
	time_ns = to_time_ns(ns);

	show_offset(m, CLOCK_MONOTONIC, &time_ns->offsets.monotonic);
	show_offset(m, CLOCK_BOOTTIME, &time_ns->offsets.boottime);
	put_time_ns(time_ns);
}

int proc_timens_set_offset(struct file *file, struct task_struct *p,
			   struct proc_timens_offset *offsets, int noffsets)
{
	struct ns_common *ns;
	struct time_namespace *time_ns;
	struct timespec64 tp;
	int i, err;

	ns = timens_for_children_get(p);
	if (!ns)
		return -ESRCH;
	time_ns = to_time_ns(ns);

	if (!file_ns_capable(file, time_ns->user_ns, CAP_SYS_TIME)) {
		put_time_ns(time_ns);
		return -EPERM;
	}

	for (i = 0; i < noffsets; i++) {
		struct proc_timens_offset *off = &offsets[i];

		switch (off->clockid) {
		case CLOCK_MONOTONIC:
			ktime_get_ts64(&tp);
			break;
		case CLOCK_BOOTTIME:
			ktime_get_boottime_ts64(&tp);
			break;
		default:
			err = -EINVAL;
			goto out;
		}

		err = -ERANGE;

		if (off->val.tv_sec > KTIME_SEC_MAX ||
		    off->val.tv_sec < -KTIME_SEC_MAX)
			goto out;

		tp = timespec64_add(tp, off->val);
		/*
		 * KTIME_SEC_MAX is divided by 2 to be sure that KTIME_MAX is
		 * still unreachable.
		 */
		if (tp.tv_sec < 0 || tp.tv_sec > KTIME_SEC_MAX / 2)
			goto out;
	}

	mutex_lock(&offset_lock);
	if (time_ns->frozen_offsets) {
		err = -EACCES;
		goto out_unlock;
	}

	err = 0;
	/* Don't report errors after this line */
	for (i = 0; i < noffsets; i++) {
		struct proc_timens_offset *off = &offsets[i];
		struct timespec64 *offset = NULL;

		switch (off->clockid) {
		case CLOCK_MONOTONIC:
			offset = &time_ns->offsets.monotonic;
			break;
		case CLOCK_BOOTTIME:
			offset = &time_ns->offsets.boottime;
			break;
		}

		*offset = off->val;
	}

out_unlock:
	mutex_unlock(&offset_lock);
out:
	put_time_ns(time_ns);

	return err;
}

const struct proc_ns_operations timens_operations = {
	.name		= "time",
	.type		= CLONE_NEWTIME,
	.get		= timens_get,
	.put		= timens_put,
	.install	= timens_install,
	.owner		= timens_owner,
};

const struct proc_ns_operations timens_for_children_operations = {
	.name		= "time_for_children",
	.type		= CLONE_NEWTIME,
	.get		= timens_for_children_get,
	.put		= timens_put,
	.install	= timens_install,
	.owner		= timens_owner,
};

struct time_namespace init_time_ns = {
	.kref		= KREF_INIT(3),
	.user_ns	= &init_user_ns,
	.ns.inum	= PROC_TIME_INIT_INO,
	.ns.ops		= &timens_operations,
	.frozen_offsets	= true,
};

static int __init time_ns_init(void)
{
	return 0;
}
subsys_initcall(time_ns_init);