[PATCH] prctl: add PR_{SET,GET}_CHILD_REAPER to allow simple process supervision

[Kay Sievers <kay.sievers@vrfy.org>]

From: Lennart Poettering <lennart@poettering.net>
Subject: prctl: add PR_{SET,GET}_CHILD_REAPER to allow simple process supervision

Userspace service managers/supervisors need to track their started
services. Many services daemonize by double-forking and get implicitely
re-parented to PID 1. The process manager will no longer be able to
receive the SIGCHLD signals for them.

With this prctl, a service manager can mark itself as a sort of
'sub-init' process, able to stay as the parent process for all processes
created by the started services. All SIGCHLD signals will be delivered
to the service manager.

As a side effect, the relevant parent PID information does not get lost
by a double-fork, which results in a more elaborate process tree and 'ps'
output.

This is orthogonal to PID namespaces. PID namespaces are isolated
from each other, while a service management process usually requires
the serices to live in the same namespace, to be able to talk to each
other.

Users of this will be the systemd per-user instance, which provides
init-like functionality for the user's login session and D-Bus, which
activates bus services on on-demand. Both will need init-like capabilities
to be able to properly keep track of the services they start.

Signed-off-by: Lennart Poettering <lennart@poettering.net>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
---

 include/linux/prctl.h |    3 +++
 include/linux/sched.h |    2 ++
 kernel/exit.c         |    9 ++++++++-
 kernel/fork.c         |    2 ++
 kernel/sys.c          |    7 +++++++
 5 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index a3baeb2..716b7d3 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -102,4 +102,7 @@
 
 #define PR_MCE_KILL_GET 34
 
+#define PR_SET_CHILD_REAPER 35
+#define PR_GET_CHILD_REAPER 36
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 20b03bf..2dba23b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1300,6 +1300,8 @@ struct task_struct {
 				 * execve */
 	unsigned in_iowait:1;
 
+	/* Reparent child processes to this process instead of pid 1. */
+	unsigned child_reaper:1;
 
 	/* Revert to default priority/policy when forking */
 	unsigned sched_reset_on_fork:1;
diff --git a/kernel/exit.c b/kernel/exit.c
index 2913b35..61a80a4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -700,7 +700,7 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 	__acquires(&tasklist_lock)
 {
 	struct pid_namespace *pid_ns = task_active_pid_ns(father);
-	struct task_struct *thread;
+	struct task_struct *thread, *reaper;
 
 	thread = father;
 	while_each_thread(father, thread) {
@@ -711,6 +711,13 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 		return thread;
 	}
 
+	/* find the first ancestor which is marked as child_reaper */
+	for (reaper = father->parent;
+	     reaper != &init_task && reaper != pid_ns->child_reaper;
+	     reaper = reaper->parent)
+		if (reaper->child_reaper)
+			return reaper;
+
 	if (unlikely(pid_ns->child_reaper == father)) {
 		write_unlock_irq(&tasklist_lock);
 		if (unlikely(pid_ns == &init_pid_ns))
diff --git a/kernel/fork.c b/kernel/fork.c
index e7ceaca..863c5c7 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1326,6 +1326,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->parent_exec_id = current->self_exec_id;
 	}
 
+	p->child_reaper = 0;
+
 	spin_lock(&current->sighand->siglock);
 
 	/*
diff --git a/kernel/sys.c b/kernel/sys.c
index a101ba3..9b41498 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1792,6 +1792,13 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			else
 				error = PR_MCE_KILL_DEFAULT;
 			break;
+		case PR_SET_CHILD_REAPER:
+			me->child_reaper = !!arg2;
+			error = 0;
+			break;
+		case PR_GET_CHILD_REAPER:
+			error = put_user(me->child_reaper, (int __user *) arg2);
+			break;
 		default:
 			error = -EINVAL;
 			break;