7872559664
From: Andrey Vagin <avagin@openvz.org> Each namespace has an owning user namespace and now there is not way to discover these relationships. Pid and user namepaces are hierarchical. There is no way to discover parent-child relationships too. Why we may want to know relationships between namespaces? One use would be visualization, in order to understand the running system. Another would be to answer the question: what capability does process X have to perform operations on a resource governed by namespace Y? One more use-case (which usually called abnormal) is checkpoint/restart. In CRIU we are going to dump and restore nested namespaces. There [1] was a discussion about which interface to choose to determing relationships between namespaces. Eric suggested to add two ioctl-s [2]: > Grumble, Grumble. I think this may actually a case for creating ioctls > for these two cases. Now that random nsfs file descriptors are bind > mountable the original reason for using proc files is not as pressing. > > One ioctl for the user namespace that owns a file descriptor. > One ioctl for the parent namespace of a namespace file descriptor. Here is an implementaions of these ioctl-s. $ man man7/namespaces.7 ... Since Linux 4.X, the following ioctl(2) calls are supported for namespace file descriptors. The correct syntax is: fd = ioctl(ns_fd, ioctl_type); where ioctl_type is one of the following: NS_GET_USERNS Returns a file descriptor that refers to an owning user names‐ pace. NS_GET_PARENT Returns a file descriptor that refers to a parent namespace. This ioctl(2) can be used for pid and user namespaces. For user namespaces, NS_GET_PARENT and NS_GET_USERNS have the same meaning. In addition to generic ioctl(2) errors, the following specific ones can occur: EINVAL NS_GET_PARENT was called for a nonhierarchical namespace. EPERM The requested namespace is outside of the current namespace scope. [1] https://lkml.org/lkml/2016/7/6/158 [2] https://lkml.org/lkml/2016/7/9/101 Changes for v2: * don't return ENOENT for init_user_ns and init_pid_ns. There is nothing outside of the init namespace, so we can return EPERM in this case too. > The fewer special cases the easier the code is to get > correct, and the easier it is to read. // Eric Changes for v3: * rename ns->get_owner() to ns->owner(). get_* usually means that it grabs a reference. Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: "Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com> Cc: "W. Trevor King" <wking@tremily.us> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Serge Hallyn <serge.hallyn@canonical.com>
169 lines
3.6 KiB
C
169 lines
3.6 KiB
C
/*
|
|
* Copyright (C) 2004 IBM Corporation
|
|
*
|
|
* Author: Serge Hallyn <serue@us.ibm.com>
|
|
*
|
|
* 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/export.h>
|
|
#include <linux/uts.h>
|
|
#include <linux/utsname.h>
|
|
#include <linux/err.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/user_namespace.h>
|
|
#include <linux/proc_ns.h>
|
|
|
|
static struct ucounts *inc_uts_namespaces(struct user_namespace *ns)
|
|
{
|
|
return inc_ucount(ns, current_euid(), UCOUNT_UTS_NAMESPACES);
|
|
}
|
|
|
|
static void dec_uts_namespaces(struct ucounts *ucounts)
|
|
{
|
|
dec_ucount(ucounts, UCOUNT_UTS_NAMESPACES);
|
|
}
|
|
|
|
static struct uts_namespace *create_uts_ns(void)
|
|
{
|
|
struct uts_namespace *uts_ns;
|
|
|
|
uts_ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL);
|
|
if (uts_ns)
|
|
kref_init(&uts_ns->kref);
|
|
return uts_ns;
|
|
}
|
|
|
|
/*
|
|
* Clone a new ns copying an original utsname, setting refcount to 1
|
|
* @old_ns: namespace to clone
|
|
* Return ERR_PTR(-ENOMEM) on error (failure to kmalloc), new ns otherwise
|
|
*/
|
|
static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns,
|
|
struct uts_namespace *old_ns)
|
|
{
|
|
struct uts_namespace *ns;
|
|
struct ucounts *ucounts;
|
|
int err;
|
|
|
|
err = -ENOSPC;
|
|
ucounts = inc_uts_namespaces(user_ns);
|
|
if (!ucounts)
|
|
goto fail;
|
|
|
|
err = -ENOMEM;
|
|
ns = create_uts_ns();
|
|
if (!ns)
|
|
goto fail_dec;
|
|
|
|
err = ns_alloc_inum(&ns->ns);
|
|
if (err)
|
|
goto fail_free;
|
|
|
|
ns->ucounts = ucounts;
|
|
ns->ns.ops = &utsns_operations;
|
|
|
|
down_read(&uts_sem);
|
|
memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
|
|
ns->user_ns = get_user_ns(user_ns);
|
|
up_read(&uts_sem);
|
|
return ns;
|
|
|
|
fail_free:
|
|
kfree(ns);
|
|
fail_dec:
|
|
dec_uts_namespaces(ucounts);
|
|
fail:
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
/*
|
|
* Copy task tsk's utsname namespace, or clone it if flags
|
|
* specifies CLONE_NEWUTS. In latter case, changes to the
|
|
* utsname of this process won't be seen by parent, and vice
|
|
* versa.
|
|
*/
|
|
struct uts_namespace *copy_utsname(unsigned long flags,
|
|
struct user_namespace *user_ns, struct uts_namespace *old_ns)
|
|
{
|
|
struct uts_namespace *new_ns;
|
|
|
|
BUG_ON(!old_ns);
|
|
get_uts_ns(old_ns);
|
|
|
|
if (!(flags & CLONE_NEWUTS))
|
|
return old_ns;
|
|
|
|
new_ns = clone_uts_ns(user_ns, old_ns);
|
|
|
|
put_uts_ns(old_ns);
|
|
return new_ns;
|
|
}
|
|
|
|
void free_uts_ns(struct kref *kref)
|
|
{
|
|
struct uts_namespace *ns;
|
|
|
|
ns = container_of(kref, struct uts_namespace, kref);
|
|
dec_uts_namespaces(ns->ucounts);
|
|
put_user_ns(ns->user_ns);
|
|
ns_free_inum(&ns->ns);
|
|
kfree(ns);
|
|
}
|
|
|
|
static inline struct uts_namespace *to_uts_ns(struct ns_common *ns)
|
|
{
|
|
return container_of(ns, struct uts_namespace, ns);
|
|
}
|
|
|
|
static struct ns_common *utsns_get(struct task_struct *task)
|
|
{
|
|
struct uts_namespace *ns = NULL;
|
|
struct nsproxy *nsproxy;
|
|
|
|
task_lock(task);
|
|
nsproxy = task->nsproxy;
|
|
if (nsproxy) {
|
|
ns = nsproxy->uts_ns;
|
|
get_uts_ns(ns);
|
|
}
|
|
task_unlock(task);
|
|
|
|
return ns ? &ns->ns : NULL;
|
|
}
|
|
|
|
static void utsns_put(struct ns_common *ns)
|
|
{
|
|
put_uts_ns(to_uts_ns(ns));
|
|
}
|
|
|
|
static int utsns_install(struct nsproxy *nsproxy, struct ns_common *new)
|
|
{
|
|
struct uts_namespace *ns = to_uts_ns(new);
|
|
|
|
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
|
|
!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
get_uts_ns(ns);
|
|
put_uts_ns(nsproxy->uts_ns);
|
|
nsproxy->uts_ns = ns;
|
|
return 0;
|
|
}
|
|
|
|
static struct user_namespace *utsns_owner(struct ns_common *ns)
|
|
{
|
|
return to_uts_ns(ns)->user_ns;
|
|
}
|
|
|
|
const struct proc_ns_operations utsns_operations = {
|
|
.name = "uts",
|
|
.type = CLONE_NEWUTS,
|
|
.get = utsns_get,
|
|
.put = utsns_put,
|
|
.install = utsns_install,
|
|
.owner = utsns_owner,
|
|
};
|