Add a new clone3() flag CLONE_AUTOREAP that makes a child process
auto-reap on exit without ever becoming a zombie. This is a per-process
property in contrast to the existing auto-reap mechanism via
SA_NOCLDWAIT or SIG_IGN for SIGCHLD which applies to all children of a
given parent.

Currently the only way to automatically reap children is to set
SA_NOCLDWAIT or SIG_IGN on SIGCHLD. This is a parent-scoped property
affecting all children which makes it unsuitable for libraries or
applications that need selective auto-reaping of specific children while
still being able to wait() on others.

CLONE_AUTOREAP stores an autoreap flag in the child's signal_struct.
When the child exits do_notify_parent() checks this flag and returns
autoreap=true causing exit_notify() to transition the task directly to
EXIT_DEAD. Since the flag lives on the child it survives reparenting: if
the original parent exits and the child is reparented to a subreaper or
init the child still auto-reaps when it eventually exits.

CLONE_AUTOREAP requires CLONE_PIDFD because the process will never be
visible to wait(). The parent must use the pidfd to monitor exit via
poll() and retrieve exit status via PIDFD_GET_INFO. No exit signal is
delivered so exit_signal must be zero.

The flag is not inherited by the autoreap process's own children. Each
child that should be autoreaped must be explicitly created with
CLONE_AUTOREAP.

Link: https://github.com/uapi-group/kernel-features/issues/45
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/sched/signal.h |  1 +
 include/uapi/linux/sched.h   |  1 +
 kernel/fork.c                | 16 +++++++++++++++-
 kernel/ptrace.c              |  3 ++-
 kernel/signal.c              |  4 ++++
 5 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 7d6449982822..346ecbad4c2b 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -132,6 +132,7 @@ struct signal_struct {
 	 */
 	unsigned int		is_child_subreaper:1;
 	unsigned int		has_child_subreaper:1;
+	unsigned int		autoreap:1;
 
 #ifdef CONFIG_POSIX_TIMERS
 
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 359a14cc76a4..e6fc5ae621e2 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -36,6 +36,7 @@
 /* Flags for the clone3() syscall. */
 #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
 #define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
+#define CLONE_AUTOREAP 0x400000000ULL /* Auto-reap child on exit, requires CLONE_PIDFD. */
 
 /*
  * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
diff --git a/kernel/fork.c b/kernel/fork.c
index 9c5effbdbdc1..a803bdad2805 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2028,6 +2028,15 @@ __latent_entropy struct task_struct *copy_process(
 			return ERR_PTR(-EINVAL);
 	}
 
+	if (clone_flags & CLONE_AUTOREAP) {
+		if (!(clone_flags & CLONE_PIDFD))
+			return ERR_PTR(-EINVAL);
+		if (clone_flags & CLONE_THREAD)
+			return ERR_PTR(-EINVAL);
+		if (args->exit_signal)
+			return ERR_PTR(-EINVAL);
+	}
+
 	/*
 	 * Force any signals received before this point to be delivered
 	 * before the fork happens.  Collect up signals sent to multiple
@@ -2374,6 +2383,8 @@ __latent_entropy struct task_struct *copy_process(
 		p->parent_exec_id = current->parent_exec_id;
 		if (clone_flags & CLONE_THREAD)
 			p->exit_signal = -1;
+		else if (clone_flags & CLONE_AUTOREAP)
+			p->exit_signal = 0;
 		else
 			p->exit_signal = current->group_leader->exit_signal;
 	} else {
@@ -2435,6 +2446,8 @@ __latent_entropy struct task_struct *copy_process(
 			 */
 			p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper ||
 							 p->real_parent->signal->is_child_subreaper;
+			if (clone_flags & CLONE_AUTOREAP)
+				p->signal->autoreap = 1;
 			list_add_tail(&p->sibling, &p->real_parent->children);
 			list_add_tail_rcu(&p->tasks, &init_task.tasks);
 			attach_pid(p, PIDTYPE_TGID);
@@ -2897,7 +2910,8 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs)
 {
 	/* Verify that no unknown flags are passed along. */
 	if (kargs->flags &
-	    ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP))
+	    ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP |
+	      CLONE_AUTOREAP))
 		return false;
 
 	/*
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 392ec2f75f01..68c17daef8d4 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -549,7 +549,8 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 	if (!dead && thread_group_empty(p)) {
 		if (!same_thread_group(p->real_parent, tracer))
 			dead = do_notify_parent(p, p->exit_signal);
-		else if (ignoring_children(tracer->sighand)) {
+		else if (ignoring_children(tracer->sighand) ||
+			 p->signal->autoreap) {
 			__wake_up_parent(p, tracer);
 			dead = true;
 		}
diff --git a/kernel/signal.c b/kernel/signal.c
index e42b8bd6922f..2fb206c84c07 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2251,6 +2251,10 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
 			sig = 0;
 	}
+	if (!tsk->ptrace && tsk->signal->autoreap) {
+		autoreap = true;
+		sig = 0;
+	}
 	/*
 	 * Send with __send_signal as si_pid and si_uid are in the
 	 * parent's namespaces.

-- 
2.47.3