linux/kernel/pid_namespace.c
Daniel Lezcano cf3f89214e pidns: add reboot_pid_ns() to handle the reboot syscall
In the case of a child pid namespace, rebooting the system does not really
makes sense.  When the pid namespace is used in conjunction with the other
namespaces in order to create a linux container, the reboot syscall leads
to some problems.

A container can reboot the host.  That can be fixed by dropping the
sys_reboot capability but we are unable to correctly to poweroff/
halt/reboot a container and the container stays stuck at the shutdown time
with the container's init process waiting indefinitively.

After several attempts, no solution from userspace was found to reliabily
handle the shutdown from a container.

This patch propose to make the init process of the child pid namespace to
exit with a signal status set to : SIGINT if the child pid namespace
called "halt/poweroff" and SIGHUP if the child pid namespace called
"reboot".  When the reboot syscall is called and we are not in the initial
pid namespace, we kill the pid namespace for "HALT", "POWEROFF",
"RESTART", and "RESTART2".  Otherwise we return EINVAL.

Returning EINVAL is also an easy way to check if this feature is supported
by the kernel when invoking another 'reboot' option like CAD.

By this way the parent process of the child pid namespace knows if it
rebooted or not and can take the right decision.

Test case:
==========

#include <alloca.h>
#include <stdio.h>
#include <sched.h>
#include <unistd.h>
#include <signal.h>
#include <sys/reboot.h>
#include <sys/types.h>
#include <sys/wait.h>

#include <linux/reboot.h>

static int do_reboot(void *arg)
{
        int *cmd = arg;

        if (reboot(*cmd))
                printf("failed to reboot(%d): %m\n", *cmd);
}

int test_reboot(int cmd, int sig)
{
        long stack_size = 4096;
        void *stack = alloca(stack_size) + stack_size;
        int status;
        pid_t ret;

        ret = clone(do_reboot, stack, CLONE_NEWPID | SIGCHLD, &cmd);
        if (ret < 0) {
                printf("failed to clone: %m\n");
                return -1;
        }

        if (wait(&status) < 0) {
                printf("unexpected wait error: %m\n");
                return -1;
        }

        if (!WIFSIGNALED(status)) {
                printf("child process exited but was not signaled\n");
                return -1;
        }

        if (WTERMSIG(status) != sig) {
                printf("signal termination is not the one expected\n");
                return -1;
        }

        return 0;
}

int main(int argc, char *argv[])
{
        int status;

        status = test_reboot(LINUX_REBOOT_CMD_RESTART, SIGHUP);
        if (status < 0)
                return 1;
        printf("reboot(LINUX_REBOOT_CMD_RESTART) succeed\n");

        status = test_reboot(LINUX_REBOOT_CMD_RESTART2, SIGHUP);
        if (status < 0)
                return 1;
        printf("reboot(LINUX_REBOOT_CMD_RESTART2) succeed\n");

        status = test_reboot(LINUX_REBOOT_CMD_HALT, SIGINT);
        if (status < 0)
                return 1;
        printf("reboot(LINUX_REBOOT_CMD_HALT) succeed\n");

        status = test_reboot(LINUX_REBOOT_CMD_POWER_OFF, SIGINT);
        if (status < 0)
                return 1;
        printf("reboot(LINUX_REBOOT_CMD_POWERR_OFF) succeed\n");

        status = test_reboot(LINUX_REBOOT_CMD_CAD_ON, -1);
        if (status >= 0) {
                printf("reboot(LINUX_REBOOT_CMD_CAD_ON) should have failed\n");
                return 1;
        }
        printf("reboot(LINUX_REBOOT_CMD_CAD_ON) has failed as expected\n");

        return 0;
}

[akpm@linux-foundation.org: tweak and add comments]
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Tested-by: Serge Hallyn <serge.hallyn@canonical.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-28 17:14:36 -07:00

261 lines
5.9 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;
/*
* 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);
do {
clear_thread_flag(TIF_SIGPENDING);
rc = sys_wait4(-1, NULL, __WALL, NULL);
} while (rc != -ECHILD);
if (pid_ns->reboot)
current->signal->group_exit_code = pid_ns->reboot;
acct_exit_ns(pid_ns);
return;
}
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", }, { } };
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);
register_sysctl_paths(kern_path, pid_ns_ctl_table);
return 0;
}
__initcall(pid_namespaces_init);