mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-29 07:34:06 +08:00
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
93 lines
2.8 KiB
C
93 lines
2.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* procfs namespace bits
|
|
*/
|
|
#ifndef _LINUX_PROC_NS_H
|
|
#define _LINUX_PROC_NS_H
|
|
|
|
#include <linux/ns_common.h>
|
|
|
|
struct pid_namespace;
|
|
struct nsproxy;
|
|
struct path;
|
|
struct task_struct;
|
|
struct inode;
|
|
|
|
struct proc_ns_operations {
|
|
const char *name;
|
|
const char *real_ns_name;
|
|
int type;
|
|
struct ns_common *(*get)(struct task_struct *task);
|
|
void (*put)(struct ns_common *ns);
|
|
int (*install)(struct nsproxy *nsproxy, struct ns_common *ns);
|
|
struct user_namespace *(*owner)(struct ns_common *ns);
|
|
struct ns_common *(*get_parent)(struct ns_common *ns);
|
|
} __randomize_layout;
|
|
|
|
extern const struct proc_ns_operations netns_operations;
|
|
extern const struct proc_ns_operations utsns_operations;
|
|
extern const struct proc_ns_operations ipcns_operations;
|
|
extern const struct proc_ns_operations pidns_operations;
|
|
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
|
|
*/
|
|
enum {
|
|
PROC_ROOT_INO = 1,
|
|
PROC_IPC_INIT_INO = 0xEFFFFFFFU,
|
|
PROC_UTS_INIT_INO = 0xEFFFFFFEU,
|
|
PROC_USER_INIT_INO = 0xEFFFFFFDU,
|
|
PROC_PID_INIT_INO = 0xEFFFFFFCU,
|
|
PROC_CGROUP_INIT_INO = 0xEFFFFFFBU,
|
|
PROC_TIME_INIT_INO = 0xEFFFFFFAU,
|
|
};
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
|
|
extern int pid_ns_prepare_proc(struct pid_namespace *ns);
|
|
extern void pid_ns_release_proc(struct pid_namespace *ns);
|
|
extern int proc_alloc_inum(unsigned int *pino);
|
|
extern void proc_free_inum(unsigned int inum);
|
|
|
|
#else /* CONFIG_PROC_FS */
|
|
|
|
static inline int pid_ns_prepare_proc(struct pid_namespace *ns) { return 0; }
|
|
static inline void pid_ns_release_proc(struct pid_namespace *ns) {}
|
|
|
|
static inline int proc_alloc_inum(unsigned int *inum)
|
|
{
|
|
*inum = 1;
|
|
return 0;
|
|
}
|
|
static inline void proc_free_inum(unsigned int inum) {}
|
|
|
|
#endif /* CONFIG_PROC_FS */
|
|
|
|
static inline int ns_alloc_inum(struct ns_common *ns)
|
|
{
|
|
atomic_long_set(&ns->stashed, 0);
|
|
return proc_alloc_inum(&ns->inum);
|
|
}
|
|
|
|
#define ns_free_inum(ns) proc_free_inum((ns)->inum)
|
|
|
|
extern struct file *proc_ns_fget(int fd);
|
|
#define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private)
|
|
extern void *ns_get_path(struct path *path, struct task_struct *task,
|
|
const struct proc_ns_operations *ns_ops);
|
|
typedef struct ns_common *ns_get_path_helper_t(void *);
|
|
extern void *ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb,
|
|
void *private_data);
|
|
|
|
extern int ns_get_name(char *buf, size_t size, struct task_struct *task,
|
|
const struct proc_ns_operations *ns_ops);
|
|
extern void nsfs_init(void);
|
|
|
|
#endif /* _LINUX_PROC_NS_H */
|