linux/kernel/utsname.c
Eric W. Biederman 98f842e675 proc: Usable inode numbers for the namespace file descriptors.
Assign a unique proc inode to each namespace, and use that
inode number to ensure we only allocate at most one proc
inode for every namespace in proc.

A single proc inode per namespace allows userspace to test
to see if two processes are in the same namespace.

This has been a long requested feature and only blocked because
a naive implementation would put the id in a global space and
would ultimately require having a namespace for the names of
namespaces, making migration and certain virtualization tricks
impossible.

We still don't have per superblock inode numbers for proc, which
appears necessary for application unaware checkpoint/restart and
migrations (if the application is using namespace file descriptors)
but that is now allowd by the design if it becomes important.

I have preallocated the ipc and uts initial proc inode numbers so
their structures can be statically initialized.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2012-11-20 04:19:49 -08:00

140 lines
2.8 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_fs.h>
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 NULL 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;
int err;
ns = create_uts_ns();
if (!ns)
return ERR_PTR(-ENOMEM);
err = proc_alloc_inum(&ns->proc_inum);
if (err) {
kfree(ns);
return ERR_PTR(err);
}
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;
}
/*
* 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);
put_user_ns(ns->user_ns);
proc_free_inum(ns->proc_inum);
kfree(ns);
}
static void *utsns_get(struct task_struct *task)
{
struct uts_namespace *ns = NULL;
struct nsproxy *nsproxy;
rcu_read_lock();
nsproxy = task_nsproxy(task);
if (nsproxy) {
ns = nsproxy->uts_ns;
get_uts_ns(ns);
}
rcu_read_unlock();
return ns;
}
static void utsns_put(void *ns)
{
put_uts_ns(ns);
}
static int utsns_install(struct nsproxy *nsproxy, void *new)
{
struct uts_namespace *ns = new;
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
get_uts_ns(ns);
put_uts_ns(nsproxy->uts_ns);
nsproxy->uts_ns = ns;
return 0;
}
static unsigned int utsns_inum(void *vp)
{
struct uts_namespace *ns = vp;
return ns->proc_inum;
}
const struct proc_ns_operations utsns_operations = {
.name = "uts",
.type = CLONE_NEWUTS,
.get = utsns_get,
.put = utsns_put,
.install = utsns_install,
.inum = utsns_inum,
};