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>

1 files changed, 7 insertions, 1 deletions

diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index f5bd679be46b..b067bd8c49d0 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -33,6 +33,7 @@ struct pid_namespace {
 #endif
 	gid_t pid_gid;
 	int hide_pid;
+	int reboot;	/* group exit code if this pidns was rebooted */
 };
 
 extern struct pid_namespace init_pid_ns;
@@ -48,6 +49,7 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *ns);
 extern void free_pid_ns(struct kref *kref);
 extern void zap_pid_ns_processes(struct pid_namespace *pid_ns);
+extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd);
 
 static inline void put_pid_ns(struct pid_namespace *ns)
 {
@@ -75,11 +77,15 @@ static inline void put_pid_ns(struct pid_namespace *ns)
 {
 }
 
-
 static inline void zap_pid_ns_processes(struct pid_namespace *ns)
 {
 	BUG();
 }
+
+static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
+{
+	return 0;
+}
 #endif /* CONFIG_PID_NS */
 
 extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);