2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-23 12:43:55 +08:00
linux-next/kernel/nsproxy.c
Christian Brauner f2a8d52e0a
nsproxy: add struct nsset
Add a simple struct nsset. It holds all necessary pieces to switch to a new
set of namespaces without leaving a task in a half-switched state which we
will make use of in the next patch. This patch switches the existing setns
logic over without causing a change in setns() behavior. This brings
setns() closer to how unshare() works(). The prepare_ns() function is
responsible to prepare all necessary information. This has two reasons.
First it minimizes dependencies between individual namespaces, i.e. all
install handler can expect that all fields are properly initialized
independent in what order they are called in. Second, this makes the code
easier to maintain and easier to follow if it needs to be changed.

The prepare_ns() helper will only be switched over to use a flags argument
in the next patch. Here it will still use nstype as a simple integer
argument which was argued would be clearer. I'm not particularly
opinionated about this if it really helps or not. The struct nsset itself
already contains the flags field since its name already indicates that it
can contain information required by different namespaces. None of this
should have functional consequences.

Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Serge Hallyn <serge@hallyn.com>
Cc: Jann Horn <jannh@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Link: https://lore.kernel.org/r/20200505140432.181565-2-christian.brauner@ubuntu.com
2020-05-09 13:57:12 +02:00

365 lines
8.5 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2006 IBM Corporation
*
* Author: Serge Hallyn <serue@us.ibm.com>
*
* Jun 2006 - namespaces support
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
*/
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/nsproxy.h>
#include <linux/init_task.h>
#include <linux/mnt_namespace.h>
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <net/net_namespace.h>
#include <linux/ipc_namespace.h>
#include <linux/time_namespace.h>
#include <linux/fs_struct.h>
#include <linux/proc_ns.h>
#include <linux/file.h>
#include <linux/syscalls.h>
#include <linux/cgroup.h>
#include <linux/perf_event.h>
static struct kmem_cache *nsproxy_cachep;
struct nsproxy init_nsproxy = {
.count = ATOMIC_INIT(1),
.uts_ns = &init_uts_ns,
#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
.ipc_ns = &init_ipc_ns,
#endif
.mnt_ns = NULL,
.pid_ns_for_children = &init_pid_ns,
#ifdef CONFIG_NET
.net_ns = &init_net,
#endif
#ifdef CONFIG_CGROUPS
.cgroup_ns = &init_cgroup_ns,
#endif
#ifdef CONFIG_TIME_NS
.time_ns = &init_time_ns,
.time_ns_for_children = &init_time_ns,
#endif
};
static inline struct nsproxy *create_nsproxy(void)
{
struct nsproxy *nsproxy;
nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
if (nsproxy)
atomic_set(&nsproxy->count, 1);
return nsproxy;
}
/*
* Create new nsproxy and all of its the associated namespaces.
* Return the newly created nsproxy. Do not attach this to the task,
* leave it to the caller to do proper locking and attach it to task.
*/
static struct nsproxy *create_new_namespaces(unsigned long flags,
struct task_struct *tsk, struct user_namespace *user_ns,
struct fs_struct *new_fs)
{
struct nsproxy *new_nsp;
int err;
new_nsp = create_nsproxy();
if (!new_nsp)
return ERR_PTR(-ENOMEM);
new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs);
if (IS_ERR(new_nsp->mnt_ns)) {
err = PTR_ERR(new_nsp->mnt_ns);
goto out_ns;
}
new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns);
if (IS_ERR(new_nsp->uts_ns)) {
err = PTR_ERR(new_nsp->uts_ns);
goto out_uts;
}
new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns);
if (IS_ERR(new_nsp->ipc_ns)) {
err = PTR_ERR(new_nsp->ipc_ns);
goto out_ipc;
}
new_nsp->pid_ns_for_children =
copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children);
if (IS_ERR(new_nsp->pid_ns_for_children)) {
err = PTR_ERR(new_nsp->pid_ns_for_children);
goto out_pid;
}
new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns,
tsk->nsproxy->cgroup_ns);
if (IS_ERR(new_nsp->cgroup_ns)) {
err = PTR_ERR(new_nsp->cgroup_ns);
goto out_cgroup;
}
new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
if (IS_ERR(new_nsp->net_ns)) {
err = PTR_ERR(new_nsp->net_ns);
goto out_net;
}
new_nsp->time_ns_for_children = copy_time_ns(flags, user_ns,
tsk->nsproxy->time_ns_for_children);
if (IS_ERR(new_nsp->time_ns_for_children)) {
err = PTR_ERR(new_nsp->time_ns_for_children);
goto out_time;
}
new_nsp->time_ns = get_time_ns(tsk->nsproxy->time_ns);
return new_nsp;
out_time:
put_net(new_nsp->net_ns);
out_net:
put_cgroup_ns(new_nsp->cgroup_ns);
out_cgroup:
if (new_nsp->pid_ns_for_children)
put_pid_ns(new_nsp->pid_ns_for_children);
out_pid:
if (new_nsp->ipc_ns)
put_ipc_ns(new_nsp->ipc_ns);
out_ipc:
if (new_nsp->uts_ns)
put_uts_ns(new_nsp->uts_ns);
out_uts:
if (new_nsp->mnt_ns)
put_mnt_ns(new_nsp->mnt_ns);
out_ns:
kmem_cache_free(nsproxy_cachep, new_nsp);
return ERR_PTR(err);
}
/*
* called from clone. This now handles copy for nsproxy and all
* namespaces therein.
*/
int copy_namespaces(unsigned long flags, struct task_struct *tsk)
{
struct nsproxy *old_ns = tsk->nsproxy;
struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
struct nsproxy *new_ns;
int ret;
if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
CLONE_NEWPID | CLONE_NEWNET |
CLONE_NEWCGROUP | CLONE_NEWTIME)))) {
if (likely(old_ns->time_ns_for_children == old_ns->time_ns)) {
get_nsproxy(old_ns);
return 0;
}
} else if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
/*
* CLONE_NEWIPC must detach from the undolist: after switching
* to a new ipc namespace, the semaphore arrays from the old
* namespace are unreachable. In clone parlance, CLONE_SYSVSEM
* means share undolist with parent, so we must forbid using
* it along with CLONE_NEWIPC.
*/
if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) ==
(CLONE_NEWIPC | CLONE_SYSVSEM))
return -EINVAL;
new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs);
if (IS_ERR(new_ns))
return PTR_ERR(new_ns);
ret = timens_on_fork(new_ns, tsk);
if (ret) {
free_nsproxy(new_ns);
return ret;
}
tsk->nsproxy = new_ns;
return 0;
}
void free_nsproxy(struct nsproxy *ns)
{
if (ns->mnt_ns)
put_mnt_ns(ns->mnt_ns);
if (ns->uts_ns)
put_uts_ns(ns->uts_ns);
if (ns->ipc_ns)
put_ipc_ns(ns->ipc_ns);
if (ns->pid_ns_for_children)
put_pid_ns(ns->pid_ns_for_children);
if (ns->time_ns)
put_time_ns(ns->time_ns);
if (ns->time_ns_for_children)
put_time_ns(ns->time_ns_for_children);
put_cgroup_ns(ns->cgroup_ns);
put_net(ns->net_ns);
kmem_cache_free(nsproxy_cachep, ns);
}
/*
* Called from unshare. Unshare all the namespaces part of nsproxy.
* On success, returns the new nsproxy.
*/
int unshare_nsproxy_namespaces(unsigned long unshare_flags,
struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs)
{
struct user_namespace *user_ns;
int err = 0;
if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP |
CLONE_NEWTIME)))
return 0;
user_ns = new_cred ? new_cred->user_ns : current_user_ns();
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
*new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
new_fs ? new_fs : current->fs);
if (IS_ERR(*new_nsp)) {
err = PTR_ERR(*new_nsp);
goto out;
}
out:
return err;
}
void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
{
struct nsproxy *ns;
might_sleep();
task_lock(p);
ns = p->nsproxy;
p->nsproxy = new;
task_unlock(p);
if (ns && atomic_dec_and_test(&ns->count))
free_nsproxy(ns);
}
void exit_task_namespaces(struct task_struct *p)
{
switch_task_namespaces(p, NULL);
}
static void put_nsset(struct nsset *nsset)
{
unsigned flags = nsset->flags;
if (flags & CLONE_NEWUSER)
put_cred(nsset_cred(nsset));
if (nsset->nsproxy)
free_nsproxy(nsset->nsproxy);
}
static int prepare_nsset(int nstype, struct nsset *nsset)
{
struct task_struct *me = current;
nsset->nsproxy = create_new_namespaces(0, me, current_user_ns(), me->fs);
if (IS_ERR(nsset->nsproxy))
return PTR_ERR(nsset->nsproxy);
if (nstype == CLONE_NEWUSER)
nsset->cred = prepare_creds();
else
nsset->cred = current_cred();
if (!nsset->cred)
goto out;
if (nstype == CLONE_NEWNS)
nsset->fs = me->fs;
nsset->flags = nstype;
return 0;
out:
put_nsset(nsset);
return -ENOMEM;
}
/*
* This is the point of no return. There are just a few namespaces
* that do some actual work here and it's sufficiently minimal that
* a separate ns_common operation seems unnecessary for now.
* Unshare is doing the same thing. If we'll end up needing to do
* more in a given namespace or a helper here is ultimately not
* exported anymore a simple commit handler for each namespace
* should be added to ns_common.
*/
static void commit_nsset(struct nsset *nsset)
{
unsigned flags = nsset->flags;
struct task_struct *me = current;
#ifdef CONFIG_USER_NS
if (flags & CLONE_NEWUSER) {
/* transfer ownership */
commit_creds(nsset_cred(nsset));
nsset->cred = NULL;
}
#endif
#ifdef CONFIG_IPC_NS
if (flags & CLONE_NEWIPC)
exit_sem(me);
#endif
/* transfer ownership */
switch_task_namespaces(me, nsset->nsproxy);
nsset->nsproxy = NULL;
}
SYSCALL_DEFINE2(setns, int, fd, int, nstype)
{
struct file *file;
struct ns_common *ns;
struct nsset nsset = {};
int err;
file = proc_ns_fget(fd);
if (IS_ERR(file))
return PTR_ERR(file);
err = -EINVAL;
ns = get_proc_ns(file_inode(file));
if (nstype && (ns->ops->type != nstype))
goto out;
err = prepare_nsset(ns->ops->type, &nsset);
if (err)
goto out;
err = ns->ops->install(&nsset, ns);
if (!err) {
commit_nsset(&nsset);
perf_event_namespaces(current);
}
put_nsset(&nsset);
out:
fput(file);
return err;
}
int __init nsproxy_cache_init(void)
{
nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC);
return 0;
}