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>

2 files changed, 42 insertions, 0 deletions

diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 17b232869a04..57bc1fd35b3c 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -15,6 +15,7 @@
 #include <linux/acct.h>
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
+#include <linux/reboot.h>
 
 #define BITS_PER_PAGE		(PAGE_SIZE*8)
 
@@ -183,6 +184,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 		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;
 }
@@ -217,6 +221,35 @@ static struct ctl_table pid_ns_ctl_table[] = {
 
 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);
diff --git a/kernel/sys.c b/kernel/sys.c
index 9eb7fcab8df6..e7006eb6c1e4 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -444,6 +444,15 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	                magic2 != LINUX_REBOOT_MAGIC2C))
 		return -EINVAL;
 
+	/*
+	 * If pid namespaces are enabled and the current task is in a child
+	 * pid_namespace, the command is handled by reboot_pid_ns() which will
+	 * call do_exit().
+	 */
+	ret = reboot_pid_ns(task_active_pid_ns(current), cmd);
+	if (ret)
+		return ret;
+
 	/* Instead of trying to make the power_off code look like
 	 * halt when pm_power_off is not set do it the easy way.
 	 */