kernel-ark/kernel/nsproxy.c
Pavel Emelyanov cf7b708c8d Make access to task's nsproxy lighter
When someone wants to deal with some other taks's namespaces it has to lock
the task and then to get the desired namespace if the one exists.  This is
slow on read-only paths and may be impossible in some cases.

E.g.  Oleg recently noticed a race between unshare() and the (sent for
review in cgroups) pid namespaces - when the task notifies the parent it
has to know the parent's namespace, but taking the task_lock() is
impossible there - the code is under write locked tasklist lock.

On the other hand switching the namespace on task (daemonize) and releasing
the namespace (after the last task exit) is rather rare operation and we
can sacrifice its speed to solve the issues above.

The access to other task namespaces is proposed to be performed
like this:

     rcu_read_lock();
     nsproxy = task_nsproxy(tsk);
     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)
         * /
     rcu_read_unlock();

This patch has passed the review by Eric and Oleg :) and,
of course, tested.

[clg@fr.ibm.com: fix unshare()]
[ebiederm@xmission.com: Update get_net_ns_by_pid]
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 11:53:37 -07:00

240 lines
5.1 KiB
C

/*
* Copyright (C) 2006 IBM Corporation
*
* Author: Serge Hallyn <serue@us.ibm.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation, version 2 of the
* License.
*
* Jun 2006 - namespaces support
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
*/
#include <linux/module.h>
#include <linux/version.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>
static struct kmem_cache *nsproxy_cachep;
struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy);
/*
* creates a copy of "orig" with refcount 1.
*/
static inline struct nsproxy *clone_nsproxy(struct nsproxy *orig)
{
struct nsproxy *ns;
ns = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
if (ns) {
memcpy(ns, orig, sizeof(struct nsproxy));
atomic_set(&ns->count, 1);
}
return ns;
}
/*
* 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 fs_struct *new_fs)
{
struct nsproxy *new_nsp;
int err;
new_nsp = clone_nsproxy(tsk->nsproxy);
if (!new_nsp)
return ERR_PTR(-ENOMEM);
new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_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, 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, 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 = copy_pid_ns(flags, task_active_pid_ns(tsk));
if (IS_ERR(new_nsp->pid_ns)) {
err = PTR_ERR(new_nsp->pid_ns);
goto out_pid;
}
new_nsp->user_ns = copy_user_ns(flags, tsk->nsproxy->user_ns);
if (IS_ERR(new_nsp->user_ns)) {
err = PTR_ERR(new_nsp->user_ns);
goto out_user;
}
new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns);
if (IS_ERR(new_nsp->net_ns)) {
err = PTR_ERR(new_nsp->net_ns);
goto out_net;
}
return new_nsp;
out_net:
if (new_nsp->user_ns)
put_user_ns(new_nsp->user_ns);
out_user:
if (new_nsp->pid_ns)
put_pid_ns(new_nsp->pid_ns);
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 nsproxy *new_ns;
int err = 0;
if (!old_ns)
return 0;
get_nsproxy(old_ns);
if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWUSER | CLONE_NEWNET)))
return 0;
if (!capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto out;
}
new_ns = create_new_namespaces(flags, tsk, tsk->fs);
if (IS_ERR(new_ns)) {
err = PTR_ERR(new_ns);
goto out;
}
err = ns_cgroup_clone(tsk);
if (err) {
put_nsproxy(new_ns);
goto out;
}
tsk->nsproxy = new_ns;
out:
put_nsproxy(old_ns);
return err;
}
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)
put_pid_ns(ns->pid_ns);
if (ns->user_ns)
put_user_ns(ns->user_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 fs_struct *new_fs)
{
int err = 0;
if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
CLONE_NEWUSER | CLONE_NEWNET)))
return 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
*new_nsp = create_new_namespaces(unshare_flags, current,
new_fs ? new_fs : current->fs);
if (IS_ERR(*new_nsp)) {
err = PTR_ERR(*new_nsp);
goto out;
}
err = ns_cgroup_clone(current);
if (err)
put_nsproxy(*new_nsp);
out:
return err;
}
void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
{
struct nsproxy *ns;
might_sleep();
ns = p->nsproxy;
rcu_assign_pointer(p->nsproxy, new);
if (ns && atomic_dec_and_test(&ns->count)) {
/*
* wait for others to get what they want from this nsproxy.
*
* cannot release this nsproxy via the call_rcu() since
* put_mnt_ns() will want to sleep
*/
synchronize_rcu();
free_nsproxy(ns);
}
}
void exit_task_namespaces(struct task_struct *p)
{
switch_task_namespaces(p, NULL);
}
static int __init nsproxy_cache_init(void)
{
nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC);
return 0;
}
module_init(nsproxy_cache_init);