Linux Documentation
 help / color / mirror / Atom feed
From: Alexander Mikhalitsyn <alex@amutable.com>
To: Jarkko Sakkinen <jarkko@kernel.org>, linux-fsdevel@vger.kernel.org
Cc: linux-api@vger.kernel.org, linux-arch@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,
	Albert Ou <aou@eecs.berkeley.edu>,
	 Alexander Gordeev <agordeev@linux.ibm.com>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Alexandre Ghiti <alex@ghiti.fr>,
	 Andreas Larsson <andreas@gaisler.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Andy Lutomirski	 <luto@amacapital.net>,
	Andy Lutomirski <luto@kernel.org>,
	Anna-Maria Behnsen	 <anna-maria@linutronix.de>,
	Arnd Bergmann <arnd@arndb.de>, Ben Segall	 <bsegall@google.com>,
	Borislav Petkov <bp@alien8.de>,
	Casey Schaufler	 <casey@schaufler-ca.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	 Christian Borntraeger <borntraeger@linux.ibm.com>,
	Christian Brauner <brauner@kernel.org>,
	"Christophe Leroy (CS GROUP)"	 <chleroy@kernel.org>,
	Chris Zankel <chris@zankel.net>,
	Dave Hansen	 <dave.hansen@linux.intel.com>,
	David Hildenbrand <david@kernel.org>,
	David Howells <dhowells@redhat.com>,
	Davidlohr Bueso <dave@stgolabs.net>,
	"David S. Miller"	 <davem@davemloft.net>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Frederic Weisbecker <frederic@kernel.org>,
	Geert Uytterhoeven <geert@linux-m68k.org>,
	"Hallgrimur H. Gunnarsson"	 <halg@google.com>,
	Heiko Carstens <hca@linux.ibm.com>, Helge Deller	 <deller@gmx.de>,
	"H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@redhat.com>,
	 "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>,
	Jan Kara <jack@suse.cz>,
	John Johansen	 <john.johansen@canonical.com>,
	John Paul Adrian Glaubitz	 <glaubitz@physik.fu-berlin.de>,
	Jonathan Corbet <corbet@lwn.net>,
	Josef Bacik	 <josef@toxicpanda.com>,
	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>,
	Madhavan Srinivasan	 <maddy@linux.ibm.com>,
	Magnus Lindholm <linmag7@gmail.com>,
	Manfred Spraul	 <manfred@colorfullife.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Matt Turner	 <mattst88@gmail.com>,
	Max Filippov <jcmvbkbc@gmail.com>, Mel Gorman <mgorman@suse.de>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Michal Hocko	 <mhocko@suse.com>, Michal Simek <monstr@monstr.eu>,
	Mike Rapoport	 <rppt@kernel.org>, Neal Gompa <neal@gompa.dev>,
	Nicholas Piggin	 <npiggin@gmail.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Paul Moore	 <paul@paul-moore.com>, Paul Walmsley <pjw@kernel.org>,
	Pavel Tikhomirov	 <ptikhomirov@virtuozzo.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	Richard Henderson <richard.henderson@linaro.org>,
	Rich Felker	 <dalias@libc.org>,
	"Ritesh Harjani (IBM)" <ritesh.list@gmail.com>,
	Russell King	 <linux@armlinux.org.uk>,
	Serge Hallyn <sergeh@kernel.org>,
	Shrikanth Hegde	 <sshegde@linux.ibm.com>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Steven Rostedt	 <rostedt@goodmis.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Sven Schnelle	 <svens@linux.ibm.com>,
	Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
	 Thomas Gleixner	 <tglx@kernel.org>,
	Valentin Schneider <vschneid@redhat.com>,
	Vasily Gorbik	 <gor@linux.ibm.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Vincenzo Frascino <vincenzo.frascino@arm.com>,
	Vlastimil Babka <vbabka@kernel.org>,
	Will Deacon	 <will@kernel.org>,
	Yoshinori Sato <ysato@users.sourceforge.jp>,
	Zygmunt Krynicki <zygmunt.krynicki@canonical.com>
Subject: Re: [RFC PATCH v4 03/14] rootns: Track init lifecycle via copy_process() and pid_namespace
Date: Fri, 20 Nov 2026 14:18:43 +0100	[thread overview]
Message-ID: <e376c8f0ec5c50b417375197a5589a210f151d9b.camel@amutable.com> (raw)
In-Reply-To: <20261119224312.1037966-4-jarkko@kernel.org>

On Fri, 2026-11-20 at 00:43 +0200, Jarkko Sakkinen wrote:
> A root namespace needs to record its init thread group's PID when
> bootstrapped and capture its exit status 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               | 38
> +++++++++++++++++++++++++++++++++++
>  5 files changed, 62 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 3f59415efadb..0557ce75195d 100644
> --- a/include/linux/rootns.h
> +++ b/include/linux/rootns.h
> @@ -13,6 +13,8 @@
>  struct file;
>  struct nsproxy;
>  struct pid;
> +struct pid_namespace;
> +struct task_struct;
>  struct user_namespace;
>  
>  enum rootns_state {
> @@ -41,6 +43,9 @@ 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)
>  {
> @@ -55,6 +60,16 @@ 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;
>  

Dear Jarkko,

>  	acct_exit_ns(pid_ns);
> +	exit_rootns(pid_ns, me);

We have a very similar mechanism around pidfd's to track exit
information for a task. As far as I can see we already have (struct
rootns *)->init_pid reference, so we can get exit information for free
(look for PIDFD_INFO_EXIT).

Kind regards,
Alex

>  	return;
>  }
>  
> diff --git a/kernel/rootns.c b/kernel/rootns.c
> index 3bbf7677080e..bde7cf4baebe 100644
> --- a/kernel/rootns.c
> +++ b/kernel/rootns.c
> @@ -183,3 +183,41 @@ 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;
> +	int status;
> +
> +	if (!c)
> +		return;
> +
> +	leader = tsk->group_leader;
> +	status = (tsk->signal->flags & SIGNAL_GROUP_EXIT) ?
> +		 tsk->signal->group_exit_code : leader->exit_code;
> +
> +	scoped_guard(spinlock, &c->lock) {
> +		c->exit_code = status;
> +		WRITE_ONCE(c->state, ROOTNS_DEAD);
> +	}
> +
> +	pid_ns->rootns = NULL;
> +	wake_up_poll(&c->waitq, EPOLLHUP);
> +	put_rootns(c);
> +}

  reply	other threads:[~2026-11-20 13:18 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-19 22:42 [RFC PATCH v4 00/14] Namespace for namespace roots Jarkko Sakkinen
2026-11-19 22:42 ` [RFC PATCH v4 01/14] nsproxy: Pass nsproxy to create_new_namespaces() Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 02/14] rootns: Add core infrastructure for root namespaces Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 03/14] rootns: Track init lifecycle via copy_process() and pid_namespace Jarkko Sakkinen
2026-11-20 13:18   ` Alexander Mikhalitsyn [this message]
2026-11-20 13:30     ` Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 04/14] rootns: Add rootns() system call Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 05/14] rootns: Add ROOTNS_WAIT ioctl Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 06/14] rootns: Add ROOTNS_KILL ioctl Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 07/14] fork: Support CLONE_INTO_ROOTNS in clone3() Jarkko Sakkinen
2026-11-20 10:33   ` Jarkko Sakkinen
2026-11-20 12:47     ` Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 08/14] fs: Support FSCONFIG_SET_ROOTNS in fsconfig() Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 09/14] fs: Support MOVE_MOUNT_T_MNTNS in move_mount() Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 10/14] security: Add rootns LSM hooks Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 11/14] arch: Wire up rootns() system call Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 12/14] docs: Document root namespace uAPI Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 13/14] selftests/rootns: Add root namespace test suite Jarkko Sakkinen
2026-11-19 22:43 ` [RFC PATCH v4 14/14] MAINTAINERS: Add entry for ROOT NAMESPACE Jarkko Sakkinen
2026-11-20  5:58 ` [RFC PATCH v4 00/14] Namespace for namespace roots Jarkko Sakkinen
2026-11-20 10:10   ` Jarkko Sakkinen
2026-11-20 10:24     ` 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=e376c8f0ec5c50b417375197a5589a210f151d9b.camel@amutable.com \
    --to=alex@amutable.com \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=agordeev@linux.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=alex@ghiti.fr \
    --cc=andreas@gaisler.com \
    --cc=anna-maria@linutronix.de \
    --cc=aou@eecs.berkeley.edu \
    --cc=arnd@arndb.de \
    --cc=borntraeger@linux.ibm.com \
    --cc=bp@alien8.de \
    --cc=brauner@kernel.org \
    --cc=bsegall@google.com \
    --cc=casey@schaufler-ca.com \
    --cc=catalin.marinas@arm.com \
    --cc=chleroy@kernel.org \
    --cc=chris@zankel.net \
    --cc=corbet@lwn.net \
    --cc=dalias@libc.org \
    --cc=dave.hansen@linux.intel.com \
    --cc=dave@stgolabs.net \
    --cc=davem@davemloft.net \
    --cc=david@kernel.org \
    --cc=deller@gmx.de \
    --cc=dhowells@redhat.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=frederic@kernel.org \
    --cc=geert@linux-m68k.org \
    --cc=glaubitz@physik.fu-berlin.de \
    --cc=gor@linux.ibm.com \
    --cc=halg@google.com \
    --cc=hca@linux.ibm.com \
    --cc=hpa@zytor.com \
    --cc=jack@suse.cz \
    --cc=jarkko@kernel.org \
    --cc=jcmvbkbc@gmail.com \
    --cc=john.johansen@canonical.com \
    --cc=josef@toxicpanda.com \
    --cc=juri.lelli@redhat.com \
    --cc=kees@kernel.org \
    --cc=kprateek.nayak@amd.com \
    --cc=liam@infradead.org \
    --cc=linmag7@gmail.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-arch@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=linux@armlinux.org.uk \
    --cc=ljs@kernel.org \
    --cc=luto@amacapital.net \
    --cc=luto@kernel.org \
    --cc=maddy@linux.ibm.com \
    --cc=manfred@colorfullife.com \
    --cc=mark.rutland@arm.com \
    --cc=mattst88@gmail.com \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=mingo@redhat.com \
    --cc=monstr@monstr.eu \
    --cc=mpe@ellerman.id.au \
    --cc=neal@gompa.dev \
    --cc=npiggin@gmail.com \
    --cc=palmer@dabbelt.com \
    --cc=paul@paul-moore.com \
    --cc=peterz@infradead.org \
    --cc=pjw@kernel.org \
    --cc=ptikhomirov@virtuozzo.com \
    --cc=rdunlap@infradead.org \
    --cc=richard.henderson@linaro.org \
    --cc=ritesh.list@gmail.com \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=sergeh@kernel.org \
    --cc=skhan@linuxfoundation.org \
    --cc=sshegde@linux.ibm.com \
    --cc=surenb@google.com \
    --cc=svens@linux.ibm.com \
    --cc=tglx@kernel.org \
    --cc=tsbogend@alpha.franken.de \
    --cc=vbabka@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vincenzo.frascino@arm.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=vschneid@redhat.com \
    --cc=will@kernel.org \
    --cc=ysato@users.sourceforge.jp \
    --cc=zygmunt.krynicki@canonical.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