2008-02-08 15:18:24 +03:00
|
|
|
/*
|
|
|
|
* Pid namespaces
|
|
|
|
*
|
|
|
|
* Authors:
|
|
|
|
* (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc.
|
|
|
|
* (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM
|
|
|
|
* Many thanks to Oleg Nesterov for comments and help
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/pid.h>
|
|
|
|
#include <linux/pid_namespace.h>
|
|
|
|
#include <linux/syscalls.h>
|
|
|
|
#include <linux/err.h>
|
2008-07-25 12:48:47 +04:00
|
|
|
#include <linux/acct.h>
|
2008-02-08 15:18:24 +03:00
|
|
|
|
|
|
|
#define BITS_PER_PAGE (PAGE_SIZE*8)
|
|
|
|
|
|
|
|
struct pid_cache {
|
|
|
|
int nr_ids;
|
|
|
|
char name[16];
|
|
|
|
struct kmem_cache *cachep;
|
|
|
|
struct list_head list;
|
|
|
|
};
|
|
|
|
|
|
|
|
static LIST_HEAD(pid_caches_lh);
|
|
|
|
static DEFINE_MUTEX(pid_caches_mutex);
|
|
|
|
static struct kmem_cache *pid_ns_cachep;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* creates the kmem cache to allocate pids from.
|
|
|
|
* @nr_ids: the number of numerical ids this pid will have to carry
|
|
|
|
*/
|
|
|
|
|
|
|
|
static struct kmem_cache *create_pid_cachep(int nr_ids)
|
|
|
|
{
|
|
|
|
struct pid_cache *pcache;
|
|
|
|
struct kmem_cache *cachep;
|
|
|
|
|
|
|
|
mutex_lock(&pid_caches_mutex);
|
|
|
|
list_for_each_entry(pcache, &pid_caches_lh, list)
|
|
|
|
if (pcache->nr_ids == nr_ids)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL);
|
|
|
|
if (pcache == NULL)
|
|
|
|
goto err_alloc;
|
|
|
|
|
|
|
|
snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids);
|
|
|
|
cachep = kmem_cache_create(pcache->name,
|
|
|
|
sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid),
|
|
|
|
0, SLAB_HWCACHE_ALIGN, NULL);
|
|
|
|
if (cachep == NULL)
|
|
|
|
goto err_cachep;
|
|
|
|
|
|
|
|
pcache->nr_ids = nr_ids;
|
|
|
|
pcache->cachep = cachep;
|
|
|
|
list_add(&pcache->list, &pid_caches_lh);
|
|
|
|
out:
|
|
|
|
mutex_unlock(&pid_caches_mutex);
|
|
|
|
return pcache->cachep;
|
|
|
|
|
|
|
|
err_cachep:
|
|
|
|
kfree(pcache);
|
|
|
|
err_alloc:
|
|
|
|
mutex_unlock(&pid_caches_mutex);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2008-04-30 11:54:31 +04:00
|
|
|
static struct pid_namespace *create_pid_namespace(unsigned int level)
|
2008-02-08 15:18:24 +03:00
|
|
|
{
|
|
|
|
struct pid_namespace *ns;
|
|
|
|
int i;
|
|
|
|
|
2008-07-25 12:48:42 +04:00
|
|
|
ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
|
2008-02-08 15:18:24 +03:00
|
|
|
if (ns == NULL)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
|
|
|
|
if (!ns->pidmap[0].page)
|
|
|
|
goto out_free;
|
|
|
|
|
|
|
|
ns->pid_cachep = create_pid_cachep(level + 1);
|
|
|
|
if (ns->pid_cachep == NULL)
|
|
|
|
goto out_free_map;
|
|
|
|
|
|
|
|
kref_init(&ns->kref);
|
|
|
|
ns->level = level;
|
|
|
|
|
|
|
|
set_bit(0, ns->pidmap[0].page);
|
|
|
|
atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
|
|
|
|
|
2008-07-25 12:48:42 +04:00
|
|
|
for (i = 1; i < PIDMAP_ENTRIES; i++)
|
2008-02-08 15:18:24 +03:00
|
|
|
atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
|
|
|
|
|
|
|
|
return ns;
|
|
|
|
|
|
|
|
out_free_map:
|
|
|
|
kfree(ns->pidmap[0].page);
|
|
|
|
out_free:
|
|
|
|
kmem_cache_free(pid_ns_cachep, ns);
|
|
|
|
out:
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void destroy_pid_namespace(struct pid_namespace *ns)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < PIDMAP_ENTRIES; i++)
|
|
|
|
kfree(ns->pidmap[i].page);
|
|
|
|
kmem_cache_free(pid_ns_cachep, ns);
|
|
|
|
}
|
|
|
|
|
|
|
|
struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns)
|
|
|
|
{
|
|
|
|
struct pid_namespace *new_ns;
|
|
|
|
|
|
|
|
BUG_ON(!old_ns);
|
|
|
|
new_ns = get_pid_ns(old_ns);
|
|
|
|
if (!(flags & CLONE_NEWPID))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
new_ns = ERR_PTR(-EINVAL);
|
|
|
|
if (flags & CLONE_THREAD)
|
|
|
|
goto out_put;
|
|
|
|
|
|
|
|
new_ns = create_pid_namespace(old_ns->level + 1);
|
|
|
|
if (!IS_ERR(new_ns))
|
|
|
|
new_ns->parent = get_pid_ns(old_ns);
|
|
|
|
|
|
|
|
out_put:
|
|
|
|
put_pid_ns(old_ns);
|
|
|
|
out:
|
|
|
|
return new_ns;
|
|
|
|
}
|
|
|
|
|
|
|
|
void free_pid_ns(struct kref *kref)
|
|
|
|
{
|
|
|
|
struct pid_namespace *ns, *parent;
|
|
|
|
|
|
|
|
ns = container_of(kref, struct pid_namespace, kref);
|
|
|
|
|
|
|
|
parent = ns->parent;
|
|
|
|
destroy_pid_namespace(ns);
|
|
|
|
|
|
|
|
if (parent != NULL)
|
|
|
|
put_pid_ns(parent);
|
|
|
|
}
|
|
|
|
|
|
|
|
void zap_pid_ns_processes(struct pid_namespace *pid_ns)
|
|
|
|
{
|
|
|
|
int nr;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The last thread in the cgroup-init thread group is terminating.
|
|
|
|
* Find remaining pid_ts in the namespace, signal and wait for them
|
|
|
|
* to exit.
|
|
|
|
*
|
|
|
|
* Note: This signals each threads in the namespace - even those that
|
|
|
|
* belong to the same thread group, To avoid this, we would have
|
|
|
|
* to walk the entire tasklist looking a processes in this
|
|
|
|
* namespace, but that could be unnecessarily expensive if the
|
|
|
|
* pid namespace has just a few processes. Or we need to
|
|
|
|
* maintain a tasklist for each pid namespace.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
read_lock(&tasklist_lock);
|
|
|
|
nr = next_pidmap(pid_ns, 1);
|
|
|
|
while (nr > 0) {
|
|
|
|
kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr);
|
|
|
|
nr = next_pidmap(pid_ns, nr);
|
|
|
|
}
|
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
|
|
|
|
do {
|
|
|
|
clear_thread_flag(TIF_SIGPENDING);
|
|
|
|
rc = sys_wait4(-1, NULL, __WALL, NULL);
|
|
|
|
} while (rc != -ECHILD);
|
|
|
|
|
|
|
|
|
|
|
|
/* Child reaper for the pid namespace is going away */
|
|
|
|
pid_ns->child_reaper = NULL;
|
2008-07-25 12:48:47 +04:00
|
|
|
acct_exit_ns(pid_ns);
|
2008-02-08 15:18:24 +03:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
static __init int pid_namespaces_init(void)
|
|
|
|
{
|
|
|
|
pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
__initcall(pid_namespaces_init);
|