diff mbox

[daniel.lezcano@free.fr:,[PATCH,1/1,V5] Add reboot_pid_ns to handle the reboot syscall]

Message ID 20120109102107.GB7774@peqn
State New
Headers show

Commit Message

Serge Hallyn Jan. 9, 2012, 10:21 a.m. UTC 
----- Forwarded message from Daniel Lezcano <daniel.lezcano@free.fr> -----

Date: Thu,  5 Jan 2012 10:06:50 +0100
From: Daniel Lezcano <daniel.lezcano@free.fr>
To: akpm@linux-foundation.org
Cc: serge.hallyn@canonical.com, oleg@redhat.com, containers@lists.linux-foundation.org, gkurz@fr.ibm.com,
	linux-kernel@vger.kernel.org, mtk.manpages@gmail.com
Subject: [PATCH 1/1][V5] 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.

Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/pid_namespace.h |    8 +++++++-
 kernel/pid_namespace.c        |   33 +++++++++++++++++++++++++++++++++
 kernel/sys.c                  |    8 ++++++++
 3 files changed, 48 insertions(+), 1 deletions(-)
diff mbox

Patch

diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index e7cf666..b90c798 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -32,6 +32,7 @@  struct pid_namespace {
 #endif
 	gid_t pid_gid;
 	int hide_pid;
+	int reboot;
 };
 
 extern struct pid_namespace init_pid_ns;
@@ -47,6 +48,7 @@  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)
 {
@@ -74,11 +76,15 @@  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);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index a896839..0d355e8 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)
 
@@ -187,6 +188,9 @@  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;
 }
@@ -221,6 +225,35 @@  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 4070153..bd924fa 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -444,6 +444,14 @@  SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	                magic2 != LINUX_REBOOT_MAGIC2C))
 		return -EINVAL;
 
+	/* In case the pid namespaces are enabled, the current task is in a
+	 * child pid_namespace and the command is handled by 'reboot_pid_ns',
+	 * this one will invoke '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.
 	 */