mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-05 10:04:12 +08:00
30acd0bdfb
Container admin can create new namespaces and force kernel to allocate up to several pages of memory for the namespaces and its associated structures. Net and uts namespaces have enabled accounting for such allocations. It makes sense to account for rest ones to restrict the host's memory consumption from inside the memcg-limited container. Link: https://lkml.kernel.org/r/5525bcbf-533e-da27-79b7-158686c64e13@virtuozzo.com Signed-off-by: Vasily Averin <vvs@virtuozzo.com> Acked-by: Serge Hallyn <serge@hallyn.com> Acked-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Kirill Tkhai <ktkhai@virtuozzo.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrei Vagin <avagin@gmail.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jiri Slaby <jirislaby@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Roman Gushchin <guro@fb.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Yutian Yang <nglaive@gmail.com> Cc: Zefan Li <lizefan.x@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
226 lines
5.1 KiB
C
226 lines
5.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* linux/ipc/namespace.c
|
|
* Copyright (C) 2006 Pavel Emelyanov <xemul@openvz.org> OpenVZ, SWsoft Inc.
|
|
*/
|
|
|
|
#include <linux/ipc.h>
|
|
#include <linux/msg.h>
|
|
#include <linux/ipc_namespace.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/nsproxy.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/cred.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/user_namespace.h>
|
|
#include <linux/proc_ns.h>
|
|
#include <linux/sched/task.h>
|
|
|
|
#include "util.h"
|
|
|
|
static struct ucounts *inc_ipc_namespaces(struct user_namespace *ns)
|
|
{
|
|
return inc_ucount(ns, current_euid(), UCOUNT_IPC_NAMESPACES);
|
|
}
|
|
|
|
static void dec_ipc_namespaces(struct ucounts *ucounts)
|
|
{
|
|
dec_ucount(ucounts, UCOUNT_IPC_NAMESPACES);
|
|
}
|
|
|
|
static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
|
|
struct ipc_namespace *old_ns)
|
|
{
|
|
struct ipc_namespace *ns;
|
|
struct ucounts *ucounts;
|
|
int err;
|
|
|
|
err = -ENOSPC;
|
|
ucounts = inc_ipc_namespaces(user_ns);
|
|
if (!ucounts)
|
|
goto fail;
|
|
|
|
err = -ENOMEM;
|
|
ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT);
|
|
if (ns == NULL)
|
|
goto fail_dec;
|
|
|
|
err = ns_alloc_inum(&ns->ns);
|
|
if (err)
|
|
goto fail_free;
|
|
ns->ns.ops = &ipcns_operations;
|
|
|
|
refcount_set(&ns->ns.count, 1);
|
|
ns->user_ns = get_user_ns(user_ns);
|
|
ns->ucounts = ucounts;
|
|
|
|
err = mq_init_ns(ns);
|
|
if (err)
|
|
goto fail_put;
|
|
|
|
sem_init_ns(ns);
|
|
msg_init_ns(ns);
|
|
shm_init_ns(ns);
|
|
|
|
return ns;
|
|
|
|
fail_put:
|
|
put_user_ns(ns->user_ns);
|
|
ns_free_inum(&ns->ns);
|
|
fail_free:
|
|
kfree(ns);
|
|
fail_dec:
|
|
dec_ipc_namespaces(ucounts);
|
|
fail:
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
struct ipc_namespace *copy_ipcs(unsigned long flags,
|
|
struct user_namespace *user_ns, struct ipc_namespace *ns)
|
|
{
|
|
if (!(flags & CLONE_NEWIPC))
|
|
return get_ipc_ns(ns);
|
|
return create_ipc_ns(user_ns, ns);
|
|
}
|
|
|
|
/*
|
|
* free_ipcs - free all ipcs of one type
|
|
* @ns: the namespace to remove the ipcs from
|
|
* @ids: the table of ipcs to free
|
|
* @free: the function called to free each individual ipc
|
|
*
|
|
* Called for each kind of ipc when an ipc_namespace exits.
|
|
*/
|
|
void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
|
|
void (*free)(struct ipc_namespace *, struct kern_ipc_perm *))
|
|
{
|
|
struct kern_ipc_perm *perm;
|
|
int next_id;
|
|
int total, in_use;
|
|
|
|
down_write(&ids->rwsem);
|
|
|
|
in_use = ids->in_use;
|
|
|
|
for (total = 0, next_id = 0; total < in_use; next_id++) {
|
|
perm = idr_find(&ids->ipcs_idr, next_id);
|
|
if (perm == NULL)
|
|
continue;
|
|
rcu_read_lock();
|
|
ipc_lock_object(perm);
|
|
free(ns, perm);
|
|
total++;
|
|
}
|
|
up_write(&ids->rwsem);
|
|
}
|
|
|
|
static void free_ipc_ns(struct ipc_namespace *ns)
|
|
{
|
|
/* mq_put_mnt() waits for a grace period as kern_unmount()
|
|
* uses synchronize_rcu().
|
|
*/
|
|
mq_put_mnt(ns);
|
|
sem_exit_ns(ns);
|
|
msg_exit_ns(ns);
|
|
shm_exit_ns(ns);
|
|
|
|
dec_ipc_namespaces(ns->ucounts);
|
|
put_user_ns(ns->user_ns);
|
|
ns_free_inum(&ns->ns);
|
|
kfree(ns);
|
|
}
|
|
|
|
static LLIST_HEAD(free_ipc_list);
|
|
static void free_ipc(struct work_struct *unused)
|
|
{
|
|
struct llist_node *node = llist_del_all(&free_ipc_list);
|
|
struct ipc_namespace *n, *t;
|
|
|
|
llist_for_each_entry_safe(n, t, node, mnt_llist)
|
|
free_ipc_ns(n);
|
|
}
|
|
|
|
/*
|
|
* The work queue is used to avoid the cost of synchronize_rcu in kern_unmount.
|
|
*/
|
|
static DECLARE_WORK(free_ipc_work, free_ipc);
|
|
|
|
/*
|
|
* put_ipc_ns - drop a reference to an ipc namespace.
|
|
* @ns: the namespace to put
|
|
*
|
|
* If this is the last task in the namespace exiting, and
|
|
* it is dropping the refcount to 0, then it can race with
|
|
* a task in another ipc namespace but in a mounts namespace
|
|
* which has this ipcns's mqueuefs mounted, doing some action
|
|
* with one of the mqueuefs files. That can raise the refcount.
|
|
* So dropping the refcount, and raising the refcount when
|
|
* accessing it through the VFS, are protected with mq_lock.
|
|
*
|
|
* (Clearly, a task raising the refcount on its own ipc_ns
|
|
* needn't take mq_lock since it can't race with the last task
|
|
* in the ipcns exiting).
|
|
*/
|
|
void put_ipc_ns(struct ipc_namespace *ns)
|
|
{
|
|
if (refcount_dec_and_lock(&ns->ns.count, &mq_lock)) {
|
|
mq_clear_sbinfo(ns);
|
|
spin_unlock(&mq_lock);
|
|
|
|
if (llist_add(&ns->mnt_llist, &free_ipc_list))
|
|
schedule_work(&free_ipc_work);
|
|
}
|
|
}
|
|
|
|
static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns)
|
|
{
|
|
return container_of(ns, struct ipc_namespace, ns);
|
|
}
|
|
|
|
static struct ns_common *ipcns_get(struct task_struct *task)
|
|
{
|
|
struct ipc_namespace *ns = NULL;
|
|
struct nsproxy *nsproxy;
|
|
|
|
task_lock(task);
|
|
nsproxy = task->nsproxy;
|
|
if (nsproxy)
|
|
ns = get_ipc_ns(nsproxy->ipc_ns);
|
|
task_unlock(task);
|
|
|
|
return ns ? &ns->ns : NULL;
|
|
}
|
|
|
|
static void ipcns_put(struct ns_common *ns)
|
|
{
|
|
return put_ipc_ns(to_ipc_ns(ns));
|
|
}
|
|
|
|
static int ipcns_install(struct nsset *nsset, struct ns_common *new)
|
|
{
|
|
struct nsproxy *nsproxy = nsset->nsproxy;
|
|
struct ipc_namespace *ns = to_ipc_ns(new);
|
|
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
|
|
!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
put_ipc_ns(nsproxy->ipc_ns);
|
|
nsproxy->ipc_ns = get_ipc_ns(ns);
|
|
return 0;
|
|
}
|
|
|
|
static struct user_namespace *ipcns_owner(struct ns_common *ns)
|
|
{
|
|
return to_ipc_ns(ns)->user_ns;
|
|
}
|
|
|
|
const struct proc_ns_operations ipcns_operations = {
|
|
.name = "ipc",
|
|
.type = CLONE_NEWIPC,
|
|
.get = ipcns_get,
|
|
.put = ipcns_put,
|
|
.install = ipcns_install,
|
|
.owner = ipcns_owner,
|
|
};
|