mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 05:45:09 +07:00
f2a8d52e0a
Add a simple struct nsset. It holds all necessary pieces to switch to a new set of namespaces without leaving a task in a half-switched state which we will make use of in the next patch. This patch switches the existing setns logic over without causing a change in setns() behavior. This brings setns() closer to how unshare() works(). The prepare_ns() function is responsible to prepare all necessary information. This has two reasons. First it minimizes dependencies between individual namespaces, i.e. all install handler can expect that all fields are properly initialized independent in what order they are called in. Second, this makes the code easier to maintain and easier to follow if it needs to be changed. The prepare_ns() helper will only be switched over to use a flags argument in the next patch. Here it will still use nstype as a simple integer argument which was argued would be clearer. I'm not particularly opinionated about this if it really helps or not. The struct nsset itself already contains the flags field since its name already indicates that it can contain information required by different namespaces. None of this should have functional consequences. Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Reviewed-by: Serge Hallyn <serge@hallyn.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Serge Hallyn <serge@hallyn.com> Cc: Jann Horn <jannh@google.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Aleksa Sarai <cyphar@cyphar.com> Link: https://lore.kernel.org/r/20200505140432.181565-2-christian.brauner@ubuntu.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);
|
|
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
|