kernel-ark/kernel/pid_namespace.c
Eric W. Biederman 6347e90091 pidns: guarantee that the pidns init will be the last pidns process reaped
Today we have a twofold bug.  Sometimes release_task on pid == 1 in a pid
namespace can run before other processes in a pid namespace have had
release task called.  With the result that pid_ns_release_proc can be
called before the last proc_flus_task() is done using upid->ns->proc_mnt,
resulting in the use of a stale pointer.  This same set of circumstances
can lead to waitpid(...) returning for a processes started with
clone(CLONE_NEWPID) before the every process in the pid namespace has
actually exited.

To fix this modify zap_pid_ns_processess wait until all other processes in
the pid namespace have exited, even EXIT_DEAD zombies.

The delay_group_leader and related tests ensure that the thread gruop
leader will be the last thread of a process group to be reaped, or to
become EXIT_DEAD and self reap.  With the change to zap_pid_ns_processes
we get the guarantee that pid == 1 in a pid namespace will be the last
task that release_task is called on.

With pid == 1 being the last task to pass through release_task
pid_ns_release_proc can no longer be called too early nor can wait return
before all of the EXIT_DEAD tasks in a pid namespace have exited.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Louis Rilling <louis.rilling@kerlabs.com>
Cc: Mike Galbraith <efault@gmx.de>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Tested-by: Andrew Wagin <avagin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-20 14:39:36 -07:00

290 lines
6.6 KiB
C

/*
* 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>
#include <linux/acct.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/reboot.h>
#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;
}
static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns)
{
struct pid_namespace *ns;
unsigned int level = parent_pid_ns->level + 1;
int i, err = -ENOMEM;
ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
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;
ns->parent = get_pid_ns(parent_pid_ns);
set_bit(0, ns->pidmap[0].page);
atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
for (i = 1; i < PIDMAP_ENTRIES; i++)
atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
err = pid_ns_prepare_proc(ns);
if (err)
goto out_put_parent_pid_ns;
return ns;
out_put_parent_pid_ns:
put_pid_ns(parent_pid_ns);
out_free_map:
kfree(ns->pidmap[0].page);
out_free:
kmem_cache_free(pid_ns_cachep, ns);
out:
return ERR_PTR(err);
}
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)
{
if (!(flags & CLONE_NEWPID))
return get_pid_ns(old_ns);
if (flags & (CLONE_THREAD|CLONE_PARENT))
return ERR_PTR(-EINVAL);
return create_pid_namespace(old_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;
struct task_struct *task, *me = current;
/* Ignore SIGCHLD causing any terminated children to autoreap */
spin_lock_irq(&me->sighand->siglock);
me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN;
spin_unlock_irq(&me->sighand->siglock);
/*
* 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) {
rcu_read_lock();
task = pid_task(find_vpid(nr), PIDTYPE_PID);
if (task && !__fatal_signal_pending(task))
send_sig_info(SIGKILL, SEND_SIG_FORCED, task);
rcu_read_unlock();
nr = next_pidmap(pid_ns, nr);
}
read_unlock(&tasklist_lock);
/* Firstly reap the EXIT_ZOMBIE children we may have. */
do {
clear_thread_flag(TIF_SIGPENDING);
rc = sys_wait4(-1, NULL, __WALL, NULL);
} while (rc != -ECHILD);
/*
* sys_wait4() above can't reap the TASK_DEAD children.
* Make sure they all go away, see __unhash_process().
*/
for (;;) {
bool need_wait = false;
read_lock(&tasklist_lock);
if (!list_empty(&current->children)) {
__set_current_state(TASK_UNINTERRUPTIBLE);
need_wait = true;
}
read_unlock(&tasklist_lock);
if (!need_wait)
break;
schedule();
}
if (pid_ns->reboot)
current->signal->group_exit_code = pid_ns->reboot;
acct_exit_ns(pid_ns);
return;
}
#ifdef CONFIG_CHECKPOINT_RESTORE
static int pid_ns_ctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table tmp = *table;
if (write && !capable(CAP_SYS_ADMIN))
return -EPERM;
/*
* Writing directly to ns' last_pid field is OK, since this field
* is volatile in a living namespace anyway and a code writing to
* it should synchronize its usage with external means.
*/
tmp.data = &current->nsproxy->pid_ns->last_pid;
return proc_dointvec(&tmp, write, buffer, lenp, ppos);
}
static struct ctl_table pid_ns_ctl_table[] = {
{
.procname = "ns_last_pid",
.maxlen = sizeof(int),
.mode = 0666, /* permissions are checked in the handler */
.proc_handler = pid_ns_ctl_handler,
},
{ }
};
static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
#endif /* CONFIG_CHECKPOINT_RESTORE */
int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
{
if (pid_ns == &init_pid_ns)
return 0;
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART2:
case LINUX_REBOOT_CMD_RESTART:
pid_ns->reboot = SIGHUP;
break;
case LINUX_REBOOT_CMD_POWER_OFF:
case LINUX_REBOOT_CMD_HALT:
pid_ns->reboot = SIGINT;
break;
default:
return -EINVAL;
}
read_lock(&tasklist_lock);
force_sig(SIGKILL, pid_ns->child_reaper);
read_unlock(&tasklist_lock);
do_exit(0);
/* Not reached */
return 0;
}
static __init int pid_namespaces_init(void)
{
pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
#ifdef CONFIG_CHECKPOINT_RESTORE
register_sysctl_paths(kern_path, pid_ns_ctl_table);
#endif
return 0;
}
__initcall(pid_namespaces_init);