mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-14 06:35:12 +00:00
2b5f9dad32
Changing a time namespace requires remapping a vvar page, so we don't want
to allow doing that if any other tasks can use the same mm.
Currently, we install a time namespace when a task is created with a new
vm. exec() is another case when a task gets a new mm and so it can switch
a time namespace safely, but it isn't handled now.
One more issue of the current interface is that clone() with CLONE_VM isn't
allowed if the current task has unshared a time namespace
(timens_for_children doesn't match the current timens).
Both these issues make some inconvenience for users. For example, Alexey
and Florian reported that posix_spawn() uses vfork+exec and this pattern
doesn't work with time namespaces due to the both described issues.
LXC needed to workaround the exec() issue by calling setns.
In the commit 133e2d3e81 ("fs/exec: allow to unshare a time namespace on
vfork+exec"), we tried to fix these issues with minimal impact on UAPI. But
it adds extra complexity and some undesirable side effects. Eric suggested
fixing the issues properly because here are all the reasons to suppose that
there are no users that depend on the old behavior.
Cc: Alexey Izbyshev <izbyshev@ispras.ru>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Suggested-by: "Eric W. Biederman" <ebiederm@xmission.com>
Origin-author: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220921003120.209637-1-avagin@google.com
115 lines
3.1 KiB
C
115 lines
3.1 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;
|
|
|
|
/*
|
|
* A structure to encompass all bits needed to install
|
|
* a partial or complete new set of namespaces.
|
|
*
|
|
* If a new user namespace is requested cred will
|
|
* point to a modifiable set of credentials. If a pointer
|
|
* to a modifiable set is needed nsset_cred() must be
|
|
* used and tested.
|
|
*/
|
|
struct nsset {
|
|
unsigned flags;
|
|
struct nsproxy *nsproxy;
|
|
struct fs_struct *fs;
|
|
const struct cred *cred;
|
|
};
|
|
|
|
static inline struct cred *nsset_cred(struct nsset *set)
|
|
{
|
|
if (set->flags & CLONE_NEWUSER)
|
|
return (struct cred *)set->cred;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* 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);
|
|
int exec_task_namespaces(void);
|
|
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
|