linux/kernel/nsproxy.c
Andrei Vagin 769071ac9f ns: Introduce Time Namespace
Time Namespace isolates clock values.

The kernel provides access to several clocks CLOCK_REALTIME,
CLOCK_MONOTONIC, CLOCK_BOOTTIME, etc.

CLOCK_REALTIME
      System-wide clock that measures real (i.e., wall-clock) time.

CLOCK_MONOTONIC
      Clock that cannot be set and represents monotonic time since
      some unspecified starting point.

CLOCK_BOOTTIME
      Identical to CLOCK_MONOTONIC, except it also includes any time
      that the system is suspended.

For many users, the time namespace means the ability to changes date and
time in a container (CLOCK_REALTIME). Providing per namespace notions of
CLOCK_REALTIME would be complex with a massive overhead, but has a dubious
value.

But in the context of checkpoint/restore functionality, monotonic and
boottime clocks become interesting. Both clocks are monotonic with
unspecified starting points. These clocks are widely used to measure time
slices and set timers. After restoring or migrating processes, it has to be
guaranteed that they never go backward. In an ideal case, the behavior of
these clocks should be the same as for a case when a whole system is
suspended. All this means that it is required to set CLOCK_MONOTONIC and
CLOCK_BOOTTIME clocks, which can be achieved by adding per-namespace
offsets for clocks.

A time namespace is similar to a pid namespace in the way how it is
created: unshare(CLONE_NEWTIME) system call creates a new time namespace,
but doesn't set it to the current process. Then all children of the process
will be born in the new time namespace, or a process can use the setns()
system call to join a namespace.

This scheme allows setting clock offsets for a namespace, before any
processes appear in it.

All available clone flags have been used, so CLONE_NEWTIME uses the highest
bit of CSIGNAL. It means that it can be used only with the unshare() and
the clone3() system calls.

[ tglx: Adjusted paragraph about clone3() to reality and massaged the
  	changelog a bit. ]

Co-developed-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://criu.org/Time_namespace
Link: https://lists.openvz.org/pipermail/criu/2018-June/041504.html
Link: https://lore.kernel.org/r/20191112012724.250792-4-dima@arista.com
2020-01-14 12:20:48 +01:00

301 lines
7.1 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/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);
}
SYSCALL_DEFINE2(setns, int, fd, int, nstype)
{
struct task_struct *tsk = current;
struct nsproxy *new_nsproxy;
struct file *file;
struct ns_common *ns;
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;
new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
if (IS_ERR(new_nsproxy)) {
err = PTR_ERR(new_nsproxy);
goto out;
}
err = ns->ops->install(new_nsproxy, ns);
if (err) {
free_nsproxy(new_nsproxy);
goto out;
}
switch_task_namespaces(tsk, new_nsproxy);
perf_event_namespaces(tsk);
out:
fput(file);
return err;
}
int __init nsproxy_cache_init(void)
{
nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC);
return 0;
}