kernel_optimize_test/kernel/cgroup/namespace.c
Christian Brauner f2a8d52e0a
nsproxy: add struct nsset
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
2020-05-09 13:57:12 +02:00

158 lines
3.4 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include "cgroup-internal.h"
#include <linux/sched/task.h>
#include <linux/slab.h>
#include <linux/nsproxy.h>
#include <linux/proc_ns.h>
/* cgroup namespaces */
static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns)
{
return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES);
}
static void dec_cgroup_namespaces(struct ucounts *ucounts)
{
dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES);
}
static struct cgroup_namespace *alloc_cgroup_ns(void)
{
struct cgroup_namespace *new_ns;
int ret;
new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL);
if (!new_ns)
return ERR_PTR(-ENOMEM);
ret = ns_alloc_inum(&new_ns->ns);
if (ret) {
kfree(new_ns);
return ERR_PTR(ret);
}
refcount_set(&new_ns->count, 1);
new_ns->ns.ops = &cgroupns_operations;
return new_ns;
}
void free_cgroup_ns(struct cgroup_namespace *ns)
{
put_css_set(ns->root_cset);
dec_cgroup_namespaces(ns->ucounts);
put_user_ns(ns->user_ns);
ns_free_inum(&ns->ns);
kfree(ns);
}
EXPORT_SYMBOL(free_cgroup_ns);
struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
struct user_namespace *user_ns,
struct cgroup_namespace *old_ns)
{
struct cgroup_namespace *new_ns;
struct ucounts *ucounts;
struct css_set *cset;
BUG_ON(!old_ns);
if (!(flags & CLONE_NEWCGROUP)) {
get_cgroup_ns(old_ns);
return old_ns;
}
/* Allow only sysadmin to create cgroup namespace. */
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
ucounts = inc_cgroup_namespaces(user_ns);
if (!ucounts)
return ERR_PTR(-ENOSPC);
/* It is not safe to take cgroup_mutex here */
spin_lock_irq(&css_set_lock);
cset = task_css_set(current);
get_css_set(cset);
spin_unlock_irq(&css_set_lock);
new_ns = alloc_cgroup_ns();
if (IS_ERR(new_ns)) {
put_css_set(cset);
dec_cgroup_namespaces(ucounts);
return new_ns;
}
new_ns->user_ns = get_user_ns(user_ns);
new_ns->ucounts = ucounts;
new_ns->root_cset = cset;
return new_ns;
}
static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns)
{
return container_of(ns, struct cgroup_namespace, ns);
}
static int cgroupns_install(struct nsset *nsset, struct ns_common *ns)
{
struct nsproxy *nsproxy = nsset->nsproxy;
struct cgroup_namespace *cgroup_ns = to_cg_ns(ns);
if (!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN) ||
!ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
/* Don't need to do anything if we are attaching to our own cgroupns. */
if (cgroup_ns == nsproxy->cgroup_ns)
return 0;
get_cgroup_ns(cgroup_ns);
put_cgroup_ns(nsproxy->cgroup_ns);
nsproxy->cgroup_ns = cgroup_ns;
return 0;
}
static struct ns_common *cgroupns_get(struct task_struct *task)
{
struct cgroup_namespace *ns = NULL;
struct nsproxy *nsproxy;
task_lock(task);
nsproxy = task->nsproxy;
if (nsproxy) {
ns = nsproxy->cgroup_ns;
get_cgroup_ns(ns);
}
task_unlock(task);
return ns ? &ns->ns : NULL;
}
static void cgroupns_put(struct ns_common *ns)
{
put_cgroup_ns(to_cg_ns(ns));
}
static struct user_namespace *cgroupns_owner(struct ns_common *ns)
{
return to_cg_ns(ns)->user_ns;
}
const struct proc_ns_operations cgroupns_operations = {
.name = "cgroup",
.type = CLONE_NEWCGROUP,
.get = cgroupns_get,
.put = cgroupns_put,
.install = cgroupns_install,
.owner = cgroupns_owner,
};
static __init int cgroup_namespaces_init(void)
{
return 0;
}
subsys_initcall(cgroup_namespaces_init);