728dba3a39
The synchronous syncrhonize_rcu in switch_task_namespaces makes setns
a sufficiently expensive system call that people have complained.
Upon inspect nsproxy no longer needs rcu protection for remote reads.
remote reads are rare. So optimize for same process reads and write
by switching using rask_lock instead.
This yields a simpler to understand lock, and a faster setns system call.
In particular this fixes a performance regression observed
by Rafael David Tinoco <rafael.tinoco@canonical.com>.
This is effectively a revert of Pavel Emelyanov's commit
cf7b708c8d Make access to task's nsproxy lighter
from 2007. The race this originialy fixed no longer exists as
do_notify_parent uses task_active_pid_ns(parent) instead of
parent->nsproxy.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
85 lines
2.4 KiB
C
85 lines
2.4 KiB
C
#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 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;
|
|
};
|
|
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
|