2005-04-17 05:20:36 +07:00
|
|
|
#ifndef _LINUX_UTSNAME_H
|
|
|
|
#define _LINUX_UTSNAME_H
|
|
|
|
|
2006-10-04 16:15:19 +07:00
|
|
|
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/kref.h>
|
|
|
|
#include <linux/nsproxy.h>
|
2008-02-08 19:18:21 +07:00
|
|
|
#include <linux/err.h>
|
2012-10-13 16:46:48 +07:00
|
|
|
#include <uapi/linux/utsname.h>
|
2006-10-04 16:15:19 +07:00
|
|
|
|
2011-11-03 03:39:22 +07:00
|
|
|
enum uts_proc {
|
|
|
|
UTS_PROC_OSTYPE,
|
|
|
|
UTS_PROC_OSRELEASE,
|
|
|
|
UTS_PROC_VERSION,
|
|
|
|
UTS_PROC_HOSTNAME,
|
|
|
|
UTS_PROC_DOMAINNAME,
|
|
|
|
};
|
|
|
|
|
userns: add a user_namespace as creator/owner of uts_namespace
The expected course of development for user namespaces targeted
capabilities is laid out at https://wiki.ubuntu.com/UserNamespace.
Goals:
- Make it safe for an unprivileged user to unshare namespaces. They
will be privileged with respect to the new namespace, but this should
only include resources which the unprivileged user already owns.
- Provide separate limits and accounting for userids in different
namespaces.
Status:
Currently (as of 2.6.38) you can clone with the CLONE_NEWUSER flag to
get a new user namespace if you have the CAP_SYS_ADMIN, CAP_SETUID, and
CAP_SETGID capabilities. What this gets you is a whole new set of
userids, meaning that user 500 will have a different 'struct user' in
your namespace than in other namespaces. So any accounting information
stored in struct user will be unique to your namespace.
However, throughout the kernel there are checks which
- simply check for a capability. Since root in a child namespace
has all capabilities, this means that a child namespace is not
constrained.
- simply compare uid1 == uid2. Since these are the integer uids,
uid 500 in namespace 1 will be said to be equal to uid 500 in
namespace 2.
As a result, the lxc implementation at lxc.sf.net does not use user
namespaces. This is actually helpful because it leaves us free to
develop user namespaces in such a way that, for some time, user
namespaces may be unuseful.
Bugs aside, this patchset is supposed to not at all affect systems which
are not actively using user namespaces, and only restrict what tasks in
child user namespace can do. They begin to limit privilege to a user
namespace, so that root in a container cannot kill or ptrace tasks in the
parent user namespace, and can only get world access rights to files.
Since all files currently belong to the initila user namespace, that means
that child user namespaces can only get world access rights to *all*
files. While this temporarily makes user namespaces bad for system
containers, it starts to get useful for some sandboxing.
I've run the 'runltplite.sh' with and without this patchset and found no
difference.
This patch:
copy_process() handles CLONE_NEWUSER before the rest of the namespaces.
So in the case of clone(CLONE_NEWUSER|CLONE_NEWUTS) the new uts namespace
will have the new user namespace as its owner. That is what we want,
since we want root in that new userns to be able to have privilege over
it.
Changelog:
Feb 15: don't set uts_ns->user_ns if we didn't create
a new uts_ns.
Feb 23: Move extern init_user_ns declaration from
init/version.c to utsname.h.
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 06:43:16 +07:00
|
|
|
struct user_namespace;
|
|
|
|
extern struct user_namespace init_user_ns;
|
|
|
|
|
2006-10-02 16:18:14 +07:00
|
|
|
struct uts_namespace {
|
|
|
|
struct kref kref;
|
|
|
|
struct new_utsname name;
|
userns: add a user_namespace as creator/owner of uts_namespace
The expected course of development for user namespaces targeted
capabilities is laid out at https://wiki.ubuntu.com/UserNamespace.
Goals:
- Make it safe for an unprivileged user to unshare namespaces. They
will be privileged with respect to the new namespace, but this should
only include resources which the unprivileged user already owns.
- Provide separate limits and accounting for userids in different
namespaces.
Status:
Currently (as of 2.6.38) you can clone with the CLONE_NEWUSER flag to
get a new user namespace if you have the CAP_SYS_ADMIN, CAP_SETUID, and
CAP_SETGID capabilities. What this gets you is a whole new set of
userids, meaning that user 500 will have a different 'struct user' in
your namespace than in other namespaces. So any accounting information
stored in struct user will be unique to your namespace.
However, throughout the kernel there are checks which
- simply check for a capability. Since root in a child namespace
has all capabilities, this means that a child namespace is not
constrained.
- simply compare uid1 == uid2. Since these are the integer uids,
uid 500 in namespace 1 will be said to be equal to uid 500 in
namespace 2.
As a result, the lxc implementation at lxc.sf.net does not use user
namespaces. This is actually helpful because it leaves us free to
develop user namespaces in such a way that, for some time, user
namespaces may be unuseful.
Bugs aside, this patchset is supposed to not at all affect systems which
are not actively using user namespaces, and only restrict what tasks in
child user namespace can do. They begin to limit privilege to a user
namespace, so that root in a container cannot kill or ptrace tasks in the
parent user namespace, and can only get world access rights to files.
Since all files currently belong to the initila user namespace, that means
that child user namespaces can only get world access rights to *all*
files. While this temporarily makes user namespaces bad for system
containers, it starts to get useful for some sandboxing.
I've run the 'runltplite.sh' with and without this patchset and found no
difference.
This patch:
copy_process() handles CLONE_NEWUSER before the rest of the namespaces.
So in the case of clone(CLONE_NEWUSER|CLONE_NEWUTS) the new uts namespace
will have the new user namespace as its owner. That is what we want,
since we want root in that new userns to be able to have privilege over
it.
Changelog:
Feb 15: don't set uts_ns->user_ns if we didn't create
a new uts_ns.
Feb 23: Move extern init_user_ns declaration from
init/version.c to utsname.h.
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 06:43:16 +07:00
|
|
|
struct user_namespace *user_ns;
|
2011-06-16 00:21:48 +07:00
|
|
|
unsigned int proc_inum;
|
2006-10-02 16:18:14 +07:00
|
|
|
};
|
|
|
|
extern struct uts_namespace init_uts_ns;
|
|
|
|
|
2008-02-08 19:18:21 +07:00
|
|
|
#ifdef CONFIG_UTS_NS
|
2006-10-02 16:18:14 +07:00
|
|
|
static inline void get_uts_ns(struct uts_namespace *ns)
|
|
|
|
{
|
|
|
|
kref_get(&ns->kref);
|
|
|
|
}
|
|
|
|
|
2007-07-16 13:41:15 +07:00
|
|
|
extern struct uts_namespace *copy_utsname(unsigned long flags,
|
2012-07-26 18:02:49 +07:00
|
|
|
struct user_namespace *user_ns, struct uts_namespace *old_ns);
|
2006-10-02 16:18:14 +07:00
|
|
|
extern void free_uts_ns(struct kref *kref);
|
|
|
|
|
|
|
|
static inline void put_uts_ns(struct uts_namespace *ns)
|
|
|
|
{
|
|
|
|
kref_put(&ns->kref, free_uts_ns);
|
|
|
|
}
|
2008-02-08 19:18:21 +07:00
|
|
|
#else
|
|
|
|
static inline void get_uts_ns(struct uts_namespace *ns)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void put_uts_ns(struct uts_namespace *ns)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct uts_namespace *copy_utsname(unsigned long flags,
|
2012-07-26 18:02:49 +07:00
|
|
|
struct user_namespace *user_ns, struct uts_namespace *old_ns)
|
2008-02-08 19:18:21 +07:00
|
|
|
{
|
|
|
|
if (flags & CLONE_NEWUTS)
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
2012-07-26 18:02:49 +07:00
|
|
|
return old_ns;
|
2008-02-08 19:18:21 +07:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2011-11-03 03:39:22 +07:00
|
|
|
#ifdef CONFIG_PROC_SYSCTL
|
|
|
|
extern void uts_proc_notify(enum uts_proc proc);
|
|
|
|
#else
|
|
|
|
static inline void uts_proc_notify(enum uts_proc proc)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2006-10-02 16:18:10 +07:00
|
|
|
static inline struct new_utsname *utsname(void)
|
|
|
|
{
|
2006-10-02 16:18:14 +07:00
|
|
|
return ¤t->nsproxy->uts_ns->name;
|
2006-10-02 16:18:10 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct new_utsname *init_utsname(void)
|
|
|
|
{
|
2006-10-02 16:18:14 +07:00
|
|
|
return &init_uts_ns.name;
|
2006-10-02 16:18:10 +07:00
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
extern struct rw_semaphore uts_sem;
|
2006-10-04 16:15:19 +07:00
|
|
|
|
|
|
|
#endif /* _LINUX_UTSNAME_H */
|