Commit 769071ac authored by Andrei Vagin's avatar Andrei Vagin Committed by Thomas Gleixner
Browse files

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: default avatarDmitry Safonov <dima@arista.com>
Signed-off-by: default avatarAndrei Vagin <avagin@gmail.com>
Signed-off-by: default avatarDmitry Safonov <dima@arista.com>
Signed-off-by: default avatarThomas 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
parent c966533f

MAINTAINERS

+2 −0
Original line number Diff line number Diff line
@@ -13214,6 +13214,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core 
S:	Maintained

F:	fs/timerfd.c

F:	include/linux/timer*

F:	include/linux/time_namespace.h

F:	kernel/time_namespace.c

F:	kernel/time/*timer*















POWER MANAGEMENT CORE

































fs/proc/namespaces.c



+4
−0






























Original line number
Diff line number
Diff line








@@ -33,6 +33,10 @@ static const struct proc_ns_operations *ns_entries[] = {













#ifdef CONFIG_CGROUPS















	&cgroupns_operations,















#endif













#ifdef CONFIG_TIME_NS













	&timens_operations,













	&timens_for_children_operations,













#endif















};































static const char *proc_ns_get_link(struct dentry *dentry,

































include/linux/nsproxy.h



+2
−0






























Original line number
Diff line number
Diff line








@@ -35,6 +35,8 @@ struct nsproxy {













	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;

































include/linux/proc_ns.h



+3
−0






























Original line number
Diff line number
Diff line








@@ -32,6 +32,8 @@ extern const struct proc_ns_operations pidns_for_children_operations;













extern const struct proc_ns_operations userns_operations;















extern const struct proc_ns_operations mntns_operations;















extern const struct proc_ns_operations cgroupns_operations;













extern const struct proc_ns_operations timens_operations;













extern const struct proc_ns_operations timens_for_children_operations;































/*















 * We always define these enumerators









@@ -43,6 +45,7 @@ enum {













	PROC_USER_INIT_INO	= 0xEFFFFFFDU,















	PROC_PID_INIT_INO	= 0xEFFFFFFCU,















	PROC_CGROUP_INIT_INO	= 0xEFFFFFFBU,













	PROC_TIME_INIT_INO	= 0xEFFFFFFAU,















};































#ifdef CONFIG_PROC_FS

































include/linux/time_namespace.h
0 → 100644



+71
−0






























Original line number
Diff line number
Diff line













/* SPDX-License-Identifier: GPL-2.0 */













#ifndef _LINUX_TIMENS_H













#define _LINUX_TIMENS_H









































#include <linux/sched.h>













#include <linux/kref.h>













#include <linux/nsproxy.h>













#include <linux/ns_common.h>













#include <linux/err.h>



























struct user_namespace;













extern struct user_namespace init_user_ns;



























struct time_namespace {













	struct kref		kref;













	struct user_namespace	*user_ns;













	struct ucounts		*ucounts;













	struct ns_common	ns;













} __randomize_layout;



























extern struct time_namespace init_time_ns;



























#ifdef CONFIG_TIME_NS













static inline struct time_namespace *get_time_ns(struct time_namespace *ns)













{













	kref_get(&ns->kref);













	return ns;













}



























struct time_namespace *copy_time_ns(unsigned long flags,













				    struct user_namespace *user_ns,













				    struct time_namespace *old_ns);













void free_time_ns(struct kref *kref);













int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk);



























static inline void put_time_ns(struct time_namespace *ns)













{













	kref_put(&ns->kref, free_time_ns);













}



























#else













static inline struct time_namespace *get_time_ns(struct time_namespace *ns)













{













	return NULL;













}



























static inline void put_time_ns(struct time_namespace *ns)













{













}



























static inline













struct time_namespace *copy_time_ns(unsigned long flags,













				    struct user_namespace *user_ns,













				    struct time_namespace *old_ns)













{













	if (flags & CLONE_NEWTIME)













		return ERR_PTR(-EINVAL);



























	return old_ns;













}



























static inline int timens_on_fork(struct nsproxy *nsproxy,













				 struct task_struct *tsk)













{













	return 0;













}



























#endif



























#endif /* _LINUX_TIMENS_H */
































































CRA Git | Maintained and supported by SUSTech CRA and CCSE