[RFC PATCH v3 03/13] rootns: Track init lifecycle via copy_process() and pid_namespace

From
Jarkko Sakkinen <jarkko@kernel.org>
Date
2026-11-18 19:36:01
Also in
linux-doc, linux-fsdevel, linux-kselftest, linux-mm, linux-security-module, lkml
Reply to
Jarkko Sakkinen, 2026-11-18
A root namespace needs to record its init thread group's PID when
bootstrapped and capture its exit status and resource usage once all
processes in the root namespace have terminated, without serializing
normal fork() and exit() paths inside the container.

Commit the bootstrap child reaper, bind pid_ns->rootns, and wake waiters
in copy_rootns() after attach_pid(PIDTYPE_PID), and invoke exit_rootns()
from zap_pid_ns_processes() after the root namespace's PID namespace has
killed and reaped all member tasks.

Co-developed-by: David Howells <dhowells@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 include/linux/pid_namespace.h |  4 ++++
 include/linux/rootns.h        | 15 +++++++++++++
 kernel/fork.c                 |  3 +++
 kernel/pid_namespace.c        |  2 ++
 kernel/rootns.c               | 41 +++++++++++++++++++++++++++++++++++
 5 files changed, 65 insertions(+)
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index b20baaa7e62b..6fd959f4d0d4 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -15,6 +15,7 @@
 #define MAX_PID_NS_LEVEL 32
 
 struct fs_pin;
+struct rootns;
 
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
 /* modes for vm.memfd_noexec sysctl */
@@ -45,6 +46,9 @@ struct pid_namespace {
 	struct user_namespace *user_ns;
 	struct ucounts *ucounts;
 	int reboot;	/* group exit code if this pidns was rebooted */
+#ifdef CONFIG_ROOTNS
+	struct rootns *rootns;
+#endif
 	struct ns_common ns;
 	struct work_struct	work;
 } __randomize_layout;
diff --git a/include/linux/rootns.h b/include/linux/rootns.h
index a1b2c3f8958b..2c34d6cd211a 100644
--- a/include/linux/rootns.h
+++ b/include/linux/rootns.h
@@ -14,6 +14,8 @@
 struct file;
 struct nsproxy;
 struct pid;
+struct pid_namespace;
+struct task_struct;
 struct user_namespace;
 
 enum rootns_state {
@@ -43,6 +45,9 @@ struct rootns {
 struct rootns *get_rootns(struct rootns *c);
 void put_rootns(struct rootns *c);
 bool is_rootns_file(struct file *file);
+void copy_rootns(struct task_struct *tsk, struct pid *pid,
+		 struct rootns *rootns);
+void exit_rootns(struct pid_namespace *pid_ns, struct task_struct *tsk);
 #else
 static inline struct rootns *get_rootns(struct rootns *c)
 {
@@ -57,6 +62,16 @@ static inline bool is_rootns_file(struct file *file)
 {
 	return false;
 }
+
+static inline void copy_rootns(struct task_struct *tsk, struct pid *pid,
+			       struct rootns *rootns)
+{
+}
+
+static inline void exit_rootns(struct pid_namespace *pid_ns,
+			       struct task_struct *tsk)
+{
+}
 #endif /* CONFIG_ROOTNS */
 
 #endif /* _LINUX_ROOTNS_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index 5efceb8d58a7..08fc28ad1eed 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -83,6 +83,7 @@
 #include <linux/fs_struct.h>
 #include <linux/magic.h>
 #include <linux/perf_event.h>
+#include <linux/rootns.h>
 #include <linux/posix-timers.h>
 #include <linux/user-return-notifier.h>
 #include <linux/oom.h>
@@ -2576,6 +2577,8 @@ __latent_entropy struct task_struct *copy_process(
 					  &p->signal->thread_head);
 		}
 		attach_pid(p, PIDTYPE_PID);
+		if (thread_group_leader(p))
+			copy_rootns(p, pid, NULL);
 		nr_threads++;
 	}
 	total_forks++;
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 127a5fd23e70..081c27aa85bd 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -24,6 +24,7 @@
 #include <linux/sched/signal.h>
 #include <linux/idr.h>
 #include <linux/nstree.h>
+#include <linux/rootns.h>
 #include <uapi/linux/wait.h>
 #include "pid_sysctl.h"
 
@@ -280,6 +281,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 		current->signal->group_exit_code = pid_ns->reboot;
 
 	acct_exit_ns(pid_ns);
+	exit_rootns(pid_ns, me);
 	return;
 }
 
diff --git a/kernel/rootns.c b/kernel/rootns.c
index 4c08ac575f6c..4f40dac4225f 100644
--- a/kernel/rootns.c
+++ b/kernel/rootns.c
@@ -158,3 +158,44 @@ bool is_rootns_file(struct file *file)
 {
 	return file->f_op == &rootns_fops;
 }
+
+void copy_rootns(struct task_struct *tsk, struct pid *pid, struct rootns *c)
+{
+	if (likely(!c || !is_child_reaper(pid)))
+		return;
+
+	scoped_guard(spinlock, &c->lock) {
+		if (c->state != ROOTNS_FORKING)
+			return;
+		ns_of_pid(pid)->rootns = get_rootns(c);
+		WRITE_ONCE(c->init_pid, get_pid(pid));
+		WRITE_ONCE(c->state, ROOTNS_RUNNING);
+	}
+	wake_up_all(&c->waitq);
+}
+
+void exit_rootns(struct pid_namespace *pid_ns, struct task_struct *tsk)
+{
+	struct rootns *c = pid_ns->rootns;
+	struct task_struct *leader;
+	struct rusage rusage;
+	int status;
+
+	if (!c)
+		return;
+
+	leader = tsk->group_leader;
+	status = (tsk->signal->flags & SIGNAL_GROUP_EXIT) ?
+		 tsk->signal->group_exit_code : leader->exit_code;
+	getrusage(leader, RUSAGE_BOTH, &rusage);
+
+	scoped_guard(spinlock, &c->lock) {
+		c->exit_code = status;
+		c->rusage = rusage;
+		WRITE_ONCE(c->state, ROOTNS_DEAD);
+	}
+
+	pid_ns->rootns = NULL;
+	wake_up_poll(&c->waitq, EPOLLHUP);
+	put_rootns(c);
+}
-- 
2.47.3
Thread (21 messages) 21 messages, 2 authors, last reply 1d ago
Keyboard shortcuts
hback out one level
jnext message in thread / next series-diff position
kprevious message in thread / previous series-diff position
ldrill in
Escclose help / fold thread tree
?toggle this help