769071ac9f
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
91 lines
2.6 KiB
C
91 lines
2.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_NSPROXY_H
|
|
#define _LINUX_NSPROXY_H
|
|
|
|
#include <linux/spinlock.h>
|
|
#include <linux/sched.h>
|
|
|
|
struct mnt_namespace;
|
|
struct uts_namespace;
|
|
struct ipc_namespace;
|
|
struct pid_namespace;
|
|
struct cgroup_namespace;
|
|
struct fs_struct;
|
|
|
|
/*
|
|
* A structure to contain pointers to all per-process
|
|
* namespaces - fs (mount), uts, network, sysvipc, etc.
|
|
*
|
|
* The pid namespace is an exception -- it's accessed using
|
|
* task_active_pid_ns. The pid namespace here is the
|
|
* namespace that children will use.
|
|
*
|
|
* 'count' is the number of tasks holding a reference.
|
|
* The count for each namespace, then, will be the number
|
|
* of nsproxies pointing to it, not the number of tasks.
|
|
*
|
|
* The nsproxy is shared by tasks which share all namespaces.
|
|
* As soon as a single namespace is cloned or unshared, the
|
|
* nsproxy is copied.
|
|
*/
|
|
struct nsproxy {
|
|
atomic_t count;
|
|
struct uts_namespace *uts_ns;
|
|
struct ipc_namespace *ipc_ns;
|
|
struct mnt_namespace *mnt_ns;
|
|
struct pid_namespace *pid_ns_for_children;
|
|
struct net *net_ns;
|
|
struct time_namespace *time_ns;
|
|
struct time_namespace *time_ns_for_children;
|
|
struct cgroup_namespace *cgroup_ns;
|
|
};
|
|
extern struct nsproxy init_nsproxy;
|
|
|
|
/*
|
|
* the namespaces access rules are:
|
|
*
|
|
* 1. only current task is allowed to change tsk->nsproxy pointer or
|
|
* any pointer on the nsproxy itself. Current must hold the task_lock
|
|
* when changing tsk->nsproxy.
|
|
*
|
|
* 2. when accessing (i.e. reading) current task's namespaces - no
|
|
* precautions should be taken - just dereference the pointers
|
|
*
|
|
* 3. the access to other task namespaces is performed like this
|
|
* task_lock(task);
|
|
* nsproxy = task->nsproxy;
|
|
* if (nsproxy != NULL) {
|
|
* / *
|
|
* * work with the namespaces here
|
|
* * e.g. get the reference on one of them
|
|
* * /
|
|
* } / *
|
|
* * NULL task->nsproxy means that this task is
|
|
* * almost dead (zombie)
|
|
* * /
|
|
* task_unlock(task);
|
|
*
|
|
*/
|
|
|
|
int copy_namespaces(unsigned long flags, struct task_struct *tsk);
|
|
void exit_task_namespaces(struct task_struct *tsk);
|
|
void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new);
|
|
void free_nsproxy(struct nsproxy *ns);
|
|
int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **,
|
|
struct cred *, struct fs_struct *);
|
|
int __init nsproxy_cache_init(void);
|
|
|
|
static inline void put_nsproxy(struct nsproxy *ns)
|
|
{
|
|
if (atomic_dec_and_test(&ns->count)) {
|
|
free_nsproxy(ns);
|
|
}
|
|
}
|
|
|
|
static inline void get_nsproxy(struct nsproxy *ns)
|
|
{
|
|
atomic_inc(&ns->count);
|
|
}
|
|
|
|
#endif
|