1 // SPDX-License-Identifier: GPL-2.0-only
2 /*
3 * Copyright (C) 2006 IBM Corporation
4 *
5 * Author: Serge Hallyn <serue@us.ibm.com>
6 *
7 * Jun 2006 - namespaces support
8 * OpenVZ, SWsoft Inc.
9 * Pavel Emelianov <xemul@openvz.org>
10 */
11
12 #include <linux/slab.h>
13 #include <linux/export.h>
14 #include <linux/nsproxy.h>
15 #include <linux/init_task.h>
16 #include <linux/mnt_namespace.h>
17 #include <linux/utsname.h>
18 #include <linux/pid_namespace.h>
19 #include <net/net_namespace.h>
20 #include <linux/ipc_namespace.h>
21 #include <linux/time_namespace.h>
22 #include <linux/fs_struct.h>
23 #include <linux/proc_fs.h>
24 #include <linux/proc_ns.h>
25 #include <linux/file.h>
26 #include <linux/syscalls.h>
27 #include <linux/cgroup.h>
28 #include <linux/perf_event.h>
29
30 static struct kmem_cache *nsproxy_cachep;
31
32 struct nsproxy init_nsproxy = {
33 .count = ATOMIC_INIT(1),
34 .uts_ns = &init_uts_ns,
35 #if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
36 .ipc_ns = &init_ipc_ns,
37 #endif
38 .mnt_ns = NULL,
39 .pid_ns_for_children = &init_pid_ns,
40 #ifdef CONFIG_NET
41 .net_ns = &init_net,
42 #endif
43 #ifdef CONFIG_CGROUPS
44 .cgroup_ns = &init_cgroup_ns,
45 #endif
46 #ifdef CONFIG_TIME_NS
47 .time_ns = &init_time_ns,
48 .time_ns_for_children = &init_time_ns,
49 #endif
50 };
51
create_nsproxy(void)52 static inline struct nsproxy *create_nsproxy(void)
53 {
54 struct nsproxy *nsproxy;
55
56 nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
57 if (nsproxy)
58 atomic_set(&nsproxy->count, 1);
59 return nsproxy;
60 }
61
62 /*
63 * Create new nsproxy and all of its the associated namespaces.
64 * Return the newly created nsproxy. Do not attach this to the task,
65 * leave it to the caller to do proper locking and attach it to task.
66 */
create_new_namespaces(unsigned long flags,struct task_struct * tsk,struct user_namespace * user_ns,struct fs_struct * new_fs)67 static struct nsproxy *create_new_namespaces(unsigned long flags,
68 struct task_struct *tsk, struct user_namespace *user_ns,
69 struct fs_struct *new_fs)
70 {
71 struct nsproxy *new_nsp;
72 int err;
73
74 new_nsp = create_nsproxy();
75 if (!new_nsp)
76 return ERR_PTR(-ENOMEM);
77
78 new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs);
79 if (IS_ERR(new_nsp->mnt_ns)) {
80 err = PTR_ERR(new_nsp->mnt_ns);
81 goto out_ns;
82 }
83
84 new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns);
85 if (IS_ERR(new_nsp->uts_ns)) {
86 err = PTR_ERR(new_nsp->uts_ns);
87 goto out_uts;
88 }
89
90 new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns);
91 if (IS_ERR(new_nsp->ipc_ns)) {
92 err = PTR_ERR(new_nsp->ipc_ns);
93 goto out_ipc;
94 }
95
96 new_nsp->pid_ns_for_children =
97 copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children);
98 if (IS_ERR(new_nsp->pid_ns_for_children)) {
99 err = PTR_ERR(new_nsp->pid_ns_for_children);
100 goto out_pid;
101 }
102
103 new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns,
104 tsk->nsproxy->cgroup_ns);
105 if (IS_ERR(new_nsp->cgroup_ns)) {
106 err = PTR_ERR(new_nsp->cgroup_ns);
107 goto out_cgroup;
108 }
109
110 new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
111 if (IS_ERR(new_nsp->net_ns)) {
112 err = PTR_ERR(new_nsp->net_ns);
113 goto out_net;
114 }
115
116 new_nsp->time_ns_for_children = copy_time_ns(flags, user_ns,
117 tsk->nsproxy->time_ns_for_children);
118 if (IS_ERR(new_nsp->time_ns_for_children)) {
119 err = PTR_ERR(new_nsp->time_ns_for_children);
120 goto out_time;
121 }
122 new_nsp->time_ns = get_time_ns(tsk->nsproxy->time_ns);
123
124 return new_nsp;
125
126 out_time:
127 put_net(new_nsp->net_ns);
128 out_net:
129 put_cgroup_ns(new_nsp->cgroup_ns);
130 out_cgroup:
131 if (new_nsp->pid_ns_for_children)
132 put_pid_ns(new_nsp->pid_ns_for_children);
133 out_pid:
134 if (new_nsp->ipc_ns)
135 put_ipc_ns(new_nsp->ipc_ns);
136 out_ipc:
137 if (new_nsp->uts_ns)
138 put_uts_ns(new_nsp->uts_ns);
139 out_uts:
140 if (new_nsp->mnt_ns)
141 put_mnt_ns(new_nsp->mnt_ns);
142 out_ns:
143 kmem_cache_free(nsproxy_cachep, new_nsp);
144 return ERR_PTR(err);
145 }
146
147 /*
148 * called from clone. This now handles copy for nsproxy and all
149 * namespaces therein.
150 */
copy_namespaces(unsigned long flags,struct task_struct * tsk)151 int copy_namespaces(unsigned long flags, struct task_struct *tsk)
152 {
153 struct nsproxy *old_ns = tsk->nsproxy;
154 struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
155 struct nsproxy *new_ns;
156
157 if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
158 CLONE_NEWPID | CLONE_NEWNET |
159 CLONE_NEWCGROUP | CLONE_NEWTIME)))) {
160 if ((flags & CLONE_VM) ||
161 likely(old_ns->time_ns_for_children == old_ns->time_ns)) {
162 get_nsproxy(old_ns);
163 return 0;
164 }
165 } else if (!ns_capable(user_ns, CAP_SYS_ADMIN))
166 return -EPERM;
167
168 /*
169 * CLONE_NEWIPC must detach from the undolist: after switching
170 * to a new ipc namespace, the semaphore arrays from the old
171 * namespace are unreachable. In clone parlance, CLONE_SYSVSEM
172 * means share undolist with parent, so we must forbid using
173 * it along with CLONE_NEWIPC.
174 */
175 if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) ==
176 (CLONE_NEWIPC | CLONE_SYSVSEM))
177 return -EINVAL;
178
179 new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs);
180 if (IS_ERR(new_ns))
181 return PTR_ERR(new_ns);
182
183 if ((flags & CLONE_VM) == 0)
184 timens_on_fork(new_ns, tsk);
185
186 tsk->nsproxy = new_ns;
187 return 0;
188 }
189
free_nsproxy(struct nsproxy * ns)190 void free_nsproxy(struct nsproxy *ns)
191 {
192 if (ns->mnt_ns)
193 put_mnt_ns(ns->mnt_ns);
194 if (ns->uts_ns)
195 put_uts_ns(ns->uts_ns);
196 if (ns->ipc_ns)
197 put_ipc_ns(ns->ipc_ns);
198 if (ns->pid_ns_for_children)
199 put_pid_ns(ns->pid_ns_for_children);
200 if (ns->time_ns)
201 put_time_ns(ns->time_ns);
202 if (ns->time_ns_for_children)
203 put_time_ns(ns->time_ns_for_children);
204 put_cgroup_ns(ns->cgroup_ns);
205 put_net(ns->net_ns);
206 kmem_cache_free(nsproxy_cachep, ns);
207 }
208
209 /*
210 * Called from unshare. Unshare all the namespaces part of nsproxy.
211 * On success, returns the new nsproxy.
212 */
unshare_nsproxy_namespaces(unsigned long unshare_flags,struct nsproxy ** new_nsp,struct cred * new_cred,struct fs_struct * new_fs)213 int unshare_nsproxy_namespaces(unsigned long unshare_flags,
214 struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs)
215 {
216 struct user_namespace *user_ns;
217 int err = 0;
218
219 if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
220 CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP |
221 CLONE_NEWTIME)))
222 return 0;
223
224 user_ns = new_cred ? new_cred->user_ns : current_user_ns();
225 if (!ns_capable(user_ns, CAP_SYS_ADMIN))
226 return -EPERM;
227
228 *new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
229 new_fs ? new_fs : current->fs);
230 if (IS_ERR(*new_nsp)) {
231 err = PTR_ERR(*new_nsp);
232 goto out;
233 }
234
235 out:
236 return err;
237 }
238
switch_task_namespaces(struct task_struct * p,struct nsproxy * new)239 void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
240 {
241 struct nsproxy *ns;
242
243 might_sleep();
244
245 task_lock(p);
246 ns = p->nsproxy;
247 p->nsproxy = new;
248 task_unlock(p);
249
250 if (ns)
251 put_nsproxy(ns);
252 }
253
exit_task_namespaces(struct task_struct * p)254 void exit_task_namespaces(struct task_struct *p)
255 {
256 switch_task_namespaces(p, NULL);
257 }
258
exec_task_namespaces(void)259 int exec_task_namespaces(void)
260 {
261 struct task_struct *tsk = current;
262 struct nsproxy *new;
263
264 if (tsk->nsproxy->time_ns_for_children == tsk->nsproxy->time_ns)
265 return 0;
266
267 new = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
268 if (IS_ERR(new))
269 return PTR_ERR(new);
270
271 timens_on_fork(new, tsk);
272 switch_task_namespaces(tsk, new);
273 return 0;
274 }
275
check_setns_flags(unsigned long flags)276 static int check_setns_flags(unsigned long flags)
277 {
278 if (!flags || (flags & ~(CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
279 CLONE_NEWNET | CLONE_NEWTIME | CLONE_NEWUSER |
280 CLONE_NEWPID | CLONE_NEWCGROUP)))
281 return -EINVAL;
282
283 #ifndef CONFIG_USER_NS
284 if (flags & CLONE_NEWUSER)
285 return -EINVAL;
286 #endif
287 #ifndef CONFIG_PID_NS
288 if (flags & CLONE_NEWPID)
289 return -EINVAL;
290 #endif
291 #ifndef CONFIG_UTS_NS
292 if (flags & CLONE_NEWUTS)
293 return -EINVAL;
294 #endif
295 #ifndef CONFIG_IPC_NS
296 if (flags & CLONE_NEWIPC)
297 return -EINVAL;
298 #endif
299 #ifndef CONFIG_CGROUPS
300 if (flags & CLONE_NEWCGROUP)
301 return -EINVAL;
302 #endif
303 #ifndef CONFIG_NET_NS
304 if (flags & CLONE_NEWNET)
305 return -EINVAL;
306 #endif
307 #ifndef CONFIG_TIME_NS
308 if (flags & CLONE_NEWTIME)
309 return -EINVAL;
310 #endif
311
312 return 0;
313 }
314
put_nsset(struct nsset * nsset)315 static void put_nsset(struct nsset *nsset)
316 {
317 unsigned flags = nsset->flags;
318
319 if (flags & CLONE_NEWUSER)
320 put_cred(nsset_cred(nsset));
321 /*
322 * We only created a temporary copy if we attached to more than just
323 * the mount namespace.
324 */
325 if (nsset->fs && (flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS))
326 free_fs_struct(nsset->fs);
327 if (nsset->nsproxy)
328 free_nsproxy(nsset->nsproxy);
329 }
330
prepare_nsset(unsigned flags,struct nsset * nsset)331 static int prepare_nsset(unsigned flags, struct nsset *nsset)
332 {
333 struct task_struct *me = current;
334
335 nsset->nsproxy = create_new_namespaces(0, me, current_user_ns(), me->fs);
336 if (IS_ERR(nsset->nsproxy))
337 return PTR_ERR(nsset->nsproxy);
338
339 if (flags & CLONE_NEWUSER)
340 nsset->cred = prepare_creds();
341 else
342 nsset->cred = current_cred();
343 if (!nsset->cred)
344 goto out;
345
346 /* Only create a temporary copy of fs_struct if we really need to. */
347 if (flags == CLONE_NEWNS) {
348 nsset->fs = me->fs;
349 } else if (flags & CLONE_NEWNS) {
350 nsset->fs = copy_fs_struct(me->fs);
351 if (!nsset->fs)
352 goto out;
353 }
354
355 nsset->flags = flags;
356 return 0;
357
358 out:
359 put_nsset(nsset);
360 return -ENOMEM;
361 }
362
validate_ns(struct nsset * nsset,struct ns_common * ns)363 static inline int validate_ns(struct nsset *nsset, struct ns_common *ns)
364 {
365 return ns->ops->install(nsset, ns);
366 }
367
368 /*
369 * This is the inverse operation to unshare().
370 * Ordering is equivalent to the standard ordering used everywhere else
371 * during unshare and process creation. The switch to the new set of
372 * namespaces occurs at the point of no return after installation of
373 * all requested namespaces was successful in commit_nsset().
374 */
validate_nsset(struct nsset * nsset,struct pid * pid)375 static int validate_nsset(struct nsset *nsset, struct pid *pid)
376 {
377 int ret = 0;
378 unsigned flags = nsset->flags;
379 struct user_namespace *user_ns = NULL;
380 struct pid_namespace *pid_ns = NULL;
381 struct nsproxy *nsp;
382 struct task_struct *tsk;
383
384 /* Take a "snapshot" of the target task's namespaces. */
385 rcu_read_lock();
386 tsk = pid_task(pid, PIDTYPE_PID);
387 if (!tsk) {
388 rcu_read_unlock();
389 return -ESRCH;
390 }
391
392 if (!ptrace_may_access(tsk, PTRACE_MODE_READ_REALCREDS)) {
393 rcu_read_unlock();
394 return -EPERM;
395 }
396
397 task_lock(tsk);
398 nsp = tsk->nsproxy;
399 if (nsp)
400 get_nsproxy(nsp);
401 task_unlock(tsk);
402 if (!nsp) {
403 rcu_read_unlock();
404 return -ESRCH;
405 }
406
407 #ifdef CONFIG_PID_NS
408 if (flags & CLONE_NEWPID) {
409 pid_ns = task_active_pid_ns(tsk);
410 if (unlikely(!pid_ns)) {
411 rcu_read_unlock();
412 ret = -ESRCH;
413 goto out;
414 }
415 get_pid_ns(pid_ns);
416 }
417 #endif
418
419 #ifdef CONFIG_USER_NS
420 if (flags & CLONE_NEWUSER)
421 user_ns = get_user_ns(__task_cred(tsk)->user_ns);
422 #endif
423 rcu_read_unlock();
424
425 /*
426 * Install requested namespaces. The caller will have
427 * verified earlier that the requested namespaces are
428 * supported on this kernel. We don't report errors here
429 * if a namespace is requested that isn't supported.
430 */
431 #ifdef CONFIG_USER_NS
432 if (flags & CLONE_NEWUSER) {
433 ret = validate_ns(nsset, &user_ns->ns);
434 if (ret)
435 goto out;
436 }
437 #endif
438
439 if (flags & CLONE_NEWNS) {
440 ret = validate_ns(nsset, from_mnt_ns(nsp->mnt_ns));
441 if (ret)
442 goto out;
443 }
444
445 #ifdef CONFIG_UTS_NS
446 if (flags & CLONE_NEWUTS) {
447 ret = validate_ns(nsset, &nsp->uts_ns->ns);
448 if (ret)
449 goto out;
450 }
451 #endif
452
453 #ifdef CONFIG_IPC_NS
454 if (flags & CLONE_NEWIPC) {
455 ret = validate_ns(nsset, &nsp->ipc_ns->ns);
456 if (ret)
457 goto out;
458 }
459 #endif
460
461 #ifdef CONFIG_PID_NS
462 if (flags & CLONE_NEWPID) {
463 ret = validate_ns(nsset, &pid_ns->ns);
464 if (ret)
465 goto out;
466 }
467 #endif
468
469 #ifdef CONFIG_CGROUPS
470 if (flags & CLONE_NEWCGROUP) {
471 ret = validate_ns(nsset, &nsp->cgroup_ns->ns);
472 if (ret)
473 goto out;
474 }
475 #endif
476
477 #ifdef CONFIG_NET_NS
478 if (flags & CLONE_NEWNET) {
479 ret = validate_ns(nsset, &nsp->net_ns->ns);
480 if (ret)
481 goto out;
482 }
483 #endif
484
485 #ifdef CONFIG_TIME_NS
486 if (flags & CLONE_NEWTIME) {
487 ret = validate_ns(nsset, &nsp->time_ns->ns);
488 if (ret)
489 goto out;
490 }
491 #endif
492
493 out:
494 if (pid_ns)
495 put_pid_ns(pid_ns);
496 if (nsp)
497 put_nsproxy(nsp);
498 put_user_ns(user_ns);
499
500 return ret;
501 }
502
503 /*
504 * This is the point of no return. There are just a few namespaces
505 * that do some actual work here and it's sufficiently minimal that
506 * a separate ns_common operation seems unnecessary for now.
507 * Unshare is doing the same thing. If we'll end up needing to do
508 * more in a given namespace or a helper here is ultimately not
509 * exported anymore a simple commit handler for each namespace
510 * should be added to ns_common.
511 */
commit_nsset(struct nsset * nsset)512 static void commit_nsset(struct nsset *nsset)
513 {
514 unsigned flags = nsset->flags;
515 struct task_struct *me = current;
516
517 #ifdef CONFIG_USER_NS
518 if (flags & CLONE_NEWUSER) {
519 /* transfer ownership */
520 commit_creds(nsset_cred(nsset));
521 nsset->cred = NULL;
522 }
523 #endif
524
525 /* We only need to commit if we have used a temporary fs_struct. */
526 if ((flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS)) {
527 set_fs_root(me->fs, &nsset->fs->root);
528 set_fs_pwd(me->fs, &nsset->fs->pwd);
529 }
530
531 #ifdef CONFIG_IPC_NS
532 if (flags & CLONE_NEWIPC)
533 exit_sem(me);
534 #endif
535
536 #ifdef CONFIG_TIME_NS
537 if (flags & CLONE_NEWTIME)
538 timens_commit(me, nsset->nsproxy->time_ns);
539 #endif
540
541 /* transfer ownership */
542 switch_task_namespaces(me, nsset->nsproxy);
543 nsset->nsproxy = NULL;
544 }
545
SYSCALL_DEFINE2(setns,int,fd,int,flags)546 SYSCALL_DEFINE2(setns, int, fd, int, flags)
547 {
548 struct file *file;
549 struct ns_common *ns = NULL;
550 struct nsset nsset = {};
551 int err = 0;
552
553 file = fget(fd);
554 if (!file)
555 return -EBADF;
556
557 if (proc_ns_file(file)) {
558 ns = get_proc_ns(file_inode(file));
559 if (flags && (ns->ops->type != flags))
560 err = -EINVAL;
561 flags = ns->ops->type;
562 } else if (!IS_ERR(pidfd_pid(file))) {
563 err = check_setns_flags(flags);
564 } else {
565 err = -EINVAL;
566 }
567 if (err)
568 goto out;
569
570 err = prepare_nsset(flags, &nsset);
571 if (err)
572 goto out;
573
574 if (proc_ns_file(file))
575 err = validate_ns(&nsset, ns);
576 else
577 err = validate_nsset(&nsset, file->private_data);
578 if (!err) {
579 commit_nsset(&nsset);
580 perf_event_namespaces(current);
581 }
582 put_nsset(&nsset);
583 out:
584 fput(file);
585 return err;
586 }
587
nsproxy_cache_init(void)588 int __init nsproxy_cache_init(void)
589 {
590 nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC|SLAB_ACCOUNT);
591 return 0;
592 }
593