Linux Kernel Selftest development
 help / color / mirror / Atom feed
From: Jarkko Sakkinen <jarkko@kernel.org>
To: linux-fsdevel@vger.kernel.org
Cc: Jarkko Sakkinen <jarkko@kernel.org>,
	linux-api@vger.kernel.org, linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	linux-mm@kvack.org, linux-security-module@vger.kernel.org,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Andrew Morton <akpm@linux-foundation.org>,
	Ben Segall <bsegall@google.com>,
	Christian Brauner <brauner@kernel.org>,
	David Hildenbrand <david@kernel.org>,
	David Howells <dhowells@redhat.com>,
	Davidlohr Bueso <dave@stgolabs.net>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Ingo Molnar <mingo@redhat.com>, Jan Kara <jack@suse.cz>,
	Jonathan Corbet <corbet@lwn.net>,
	Juri Lelli <juri.lelli@redhat.com>, Kees Cook <kees@kernel.org>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	"Liam R. Howlett" <liam@infradead.org>,
	Lorenzo Stoakes <ljs@kernel.org>,
	Manfred Spraul <manfred@colorfullife.com>,
	Mel Gorman <mgorman@suse.de>, Michal Hocko <mhocko@suse.com>,
	Mike Rapoport <rppt@kernel.org>, Neal Gompa <neal@gompa.dev>,
	Paul Moore <paul@paul-moore.com>,
	Pavel Tikhomirov <ptikhomirov@virtuozzo.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	Serge Hallyn <sergeh@kernel.org>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Valentin Schneider <vschneid@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Vlastimil Babka <vbabka@kernel.org>
Subject: [RFC PATCH 03/13] rootns: Track init lifecycle via copy_process() and pid_namespace
Date: Tue, 17 Nov 2026 07:08:31 +0200	[thread overview]
Message-ID: <20261117050841.3289652-4-jarkko@kernel.org> (raw)
In-Reply-To: <20261117050841.3289652-1-jarkko@kernel.org>

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.

Represent the initial host context with a NULL nsproxy->rootns pointer,
commit the bootstrap init PID and wake waiters in copy_rootns(), 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/nsproxy.h       | 16 ++++++++++++++
 include/linux/pid_namespace.h |  4 ++++
 include/linux/rootns.h        | 12 +++++++++++
 kernel/fork.c                 |  2 ++
 kernel/nsproxy.c              |  4 ++++
 kernel/pid_namespace.c        |  2 ++
 kernel/rootns.c               | 40 +++++++++++++++++++++++++++++++++++
 7 files changed, 80 insertions(+)

diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index 23cbeee6b1e4..7d0b636387c6 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -12,6 +12,7 @@ struct ipc_namespace;
 struct pid_namespace;
 struct cgroup_namespace;
 struct fs_struct;
+struct rootns;
 struct user_namespace;
 
 /*
@@ -40,9 +41,24 @@ struct nsproxy {
 	struct time_namespace *time_ns;
 	struct time_namespace *time_ns_for_children;
 	struct cgroup_namespace *cgroup_ns;
+#ifdef CONFIG_ROOTNS
+	struct rootns *rootns;
+#endif
 };
 extern struct nsproxy init_nsproxy;
 
+#ifdef CONFIG_ROOTNS
+static inline struct rootns *task_rootns(const struct task_struct *tsk)
+{
+	return tsk->nsproxy ? tsk->nsproxy->rootns : NULL;
+}
+#else
+static inline struct rootns *task_rootns(const struct task_struct *tsk)
+{
+	return NULL;
+}
+#endif
+
 /*
  * A structure to encompass all bits needed to install
  * a partial or complete new set of namespaces.
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 8464c90863ac..b8437bf21830 100644
--- a/include/linux/rootns.h
+++ b/include/linux/rootns.h
@@ -16,6 +16,7 @@ struct cred;
 struct file;
 struct nsproxy;
 struct pid;
+struct pid_namespace;
 struct task_struct;
 
 enum rootns_state {
@@ -47,6 +48,8 @@ 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 rootns *rootns);
+void exit_rootns(struct pid_namespace *pid_ns, struct task_struct *tsk);
 #else
 static inline struct rootns *get_rootns(struct rootns *c)
 {
@@ -61,6 +64,15 @@ static inline bool is_rootns_file(struct file *file)
 {
 	return false;
 }
+
+static inline void copy_rootns(struct task_struct *tsk, 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..99e22b3cd213 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>
@@ -2565,6 +2566,7 @@ __latent_entropy struct task_struct *copy_process(
 			attach_pid(p, PIDTYPE_TGID);
 			attach_pid(p, PIDTYPE_PGID);
 			attach_pid(p, PIDTYPE_SID);
+			copy_rootns(p, NULL);
 			__this_cpu_inc(process_counts);
 		} else {
 			current->signal->nr_threads++;
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 8a3c6d4e94e2..a76837b3ee33 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/nsproxy.h>
 #include <linux/ns/ns_common_types.h>
+#include <linux/rootns.h>
 #include <linux/init_task.h>
 #include <linux/mnt_namespace.h>
 #include <linux/utsname.h>
@@ -142,6 +143,9 @@ struct nsproxy *create_new_namespaces(u64 flags,
 		goto out_time;
 	}
 	new_nsp->time_ns = get_time_ns(ns->time_ns);
+#ifdef CONFIG_ROOTNS
+	new_nsp->rootns = ns->rootns;
+#endif
 
 	return new_nsp;
 
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 e75d918b93ec..e3b203322ae2 100644
--- a/kernel/rootns.c
+++ b/kernel/rootns.c
@@ -16,6 +16,7 @@
 #include <linux/ns_common.h>
 #include <linux/nsfs.h>
 #include <linux/pid.h>
+#include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/compat.h>
 #include <uapi/linux/rootns.h>
@@ -105,3 +106,42 @@ bool is_rootns_file(struct file *file)
 {
 	return file->f_op == &rootns_fops;
 }
+
+void copy_rootns(struct task_struct *tsk, struct rootns *c)
+{
+	if (likely(!c || READ_ONCE(c->state) != ROOTNS_FORKING))
+		return;
+
+	scoped_guard(spinlock, &c->lock) {
+		get_rootns(c);
+		WRITE_ONCE(c->init_pid, get_task_pid(tsk, PIDTYPE_TGID));
+		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


  parent reply	other threads:[~2026-11-17  5:09 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-17  5:08 [RFC PATCH 00/13] Namespace for namespace roots Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 01/13] nsproxy: Pass nsproxy to create_new_namespaces() Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 02/13] rootns: Add core infrastructure for root namespaces Jarkko Sakkinen
2026-11-17  5:08 ` Jarkko Sakkinen [this message]
2026-11-17  5:08 ` [RFC PATCH 04/13] rootns: Add rootns_create() system call Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 05/13] rootns: Add rootns_wait() " Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 06/13] rootns: Add rootns_kill() " Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 07/13] rootns: Add rootns_enter() " Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 08/13] fs: Support FSCONFIG_SET_ROOTNS in fsconfig() Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 09/13] fs: Support installing rootns mount trees via move_mount() Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 10/13] arch: Wire up rootns system calls Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 11/13] docs: Document root namespace uAPI Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 12/13] selftests/rootns: Add root namespace test suite Jarkko Sakkinen
2026-11-17  5:08 ` [RFC PATCH 13/13] MAINTAINERS: Add entry for ROOT NAMESPACE Jarkko Sakkinen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261117050841.3289652-4-jarkko@kernel.org \
    --to=jarkko@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=brauner@kernel.org \
    --cc=bsegall@google.com \
    --cc=corbet@lwn.net \
    --cc=dave@stgolabs.net \
    --cc=david@kernel.org \
    --cc=dhowells@redhat.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=jack@suse.cz \
    --cc=juri.lelli@redhat.com \
    --cc=kees@kernel.org \
    --cc=kprateek.nayak@amd.com \
    --cc=liam@infradead.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-security-module@vger.kernel.org \
    --cc=ljs@kernel.org \
    --cc=manfred@colorfullife.com \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=mingo@redhat.com \
    --cc=neal@gompa.dev \
    --cc=paul@paul-moore.com \
    --cc=peterz@infradead.org \
    --cc=ptikhomirov@virtuozzo.com \
    --cc=rdunlap@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=sergeh@kernel.org \
    --cc=skhan@linuxfoundation.org \
    --cc=surenb@google.com \
    --cc=vbabka@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=vschneid@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox