Linux filesystem development
 help / color / mirror / Atom feed
From: Jarkko Sakkinen <jarkko@kernel.org>
To: linux-fsdevel@vger.kernel.org
Cc: 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 Mikhalitsyn <alex@amutable.com>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Andy Lutomirski <luto@amacapital.net>,
	Christian Brauner <brauner@kernel.org>,
	David Howells <dhowells@redhat.com>, Jan Kara <jack@suse.cz>,
	Jonathan Corbet <corbet@lwn.net>,
	Josef Bacik <josef@toxicpanda.com>, Kees Cook <kees@kernel.org>,
	Neal Gompa <neal@gompa.dev>, Paul Moore <paul@paul-moore.com>,
	Serge Hallyn <sergeh@kernel.org>,
	Zygmunt Krynicki <zygmunt.krynicki@canonical.com>
Subject: Re: [RFC PATCH v5 14/25] rootns: Add ROOTNS_WAIT ioctl
Date: Sat, 21 Nov 2026 02:17:15 +0200	[thread overview]
Message-ID: <awDjC9hcKSRnCPgJ@kernel.org> (raw)
In-Reply-To: <20261121000844.1863324-15-jarkko@kernel.org>

On Sat, Nov 21, 2026 at 02:08:33AM +0200, Jarkko Sakkinen wrote:
> wait4() and waitid() only allow a parent or subreaper to collect exit
> status, so an external manager holding a rootns file descriptor cannot
> wait on a rootns init process forked by another process or observe exit
> status multiple times across observers.
> 
> Add the ROOTNS_WAIT ioctl and struct rootns_wait_args to wait freezably
> and interruptibly on a rootns file descriptor until its init thread group
> exits and report the recorded wait status. Return the init TGID
> translated into the caller's active PID namespace, 0 for WNOHANG while
> running, or -ECHILD if init was never started or is not visible to the
> caller.
> 
> 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/uapi/linux/rootns.h | 26 +++++++++++++++++++++
>  kernel/rootns.c             | 46 +++++++++++++++++++++++++++++++++++++
>  2 files changed, 72 insertions(+)
> 
> diff --git a/include/uapi/linux/rootns.h b/include/uapi/linux/rootns.h
> index bd643bdfb43c..3fd215185398 100644
> --- a/include/uapi/linux/rootns.h
> +++ b/include/uapi/linux/rootns.h
> @@ -8,6 +8,7 @@
>  #define _UAPI_LINUX_ROOTNS_H
>  
>  #include <linux/ioctl.h>
> +#include <linux/types.h>
>  
>  /**
>   * enum rootns_flags - Flags for rootns()
> @@ -24,6 +25,16 @@ enum rootns_flags {
>  	ROOTNS_ALL_FLAGS	= 0x00000003,
>  };
>  
> +/**
> + * struct rootns_wait_args - Arguments for %ROOTNS_WAIT
> + * @flags: Wait options (0 or %WNOHANG).
> + * @status: Output wait status of rootns init in waitpid(2) format.
> + */
> +struct rootns_wait_args {
> +	__u32 flags;
> +	__s32 status;
> +};
> +
>  #define ROOTNS_IOCTL_MAGIC	0xB9
>  
>  /**
> @@ -41,4 +52,19 @@ enum rootns_flags {
>   */
>  #define ROOTNS_GET_NSFD		_IO(ROOTNS_IOCTL_MAGIC, 0x01)
>  
> +/**
> + * DOC: ROOTNS_WAIT
> + *
> + * ``ioctl(rootnsfd, ROOTNS_WAIT, &args)`` waits interruptibly (unless
> + * ``WNOHANG`` is set in ``args.flags``) until ``rootnsfd`` reaches
> + * ``ROOTNS_DEAD``, then writes the recorded exit status of ``rootns`` init
> + * into ``args.status``.
> + *
> + * Returns the caller-visible TGID of ``rootns`` init on success, ``0`` if
> + * ``WNOHANG`` is set and the ``rootns`` has not terminated, or ``-1`` with
> + * ``errno`` set to ``ECHILD`` if init was never started or is not visible in
> + * the caller's active PID namespace.
> + */
> +#define ROOTNS_WAIT		_IOWR(ROOTNS_IOCTL_MAGIC, 0x02, struct rootns_wait_args)
> +
>  #endif /* _UAPI_LINUX_ROOTNS_H */
> diff --git a/kernel/rootns.c b/kernel/rootns.c
> index 5d59fc9a591d..cb74ddc8363c 100644
> --- a/kernel/rootns.c
> +++ b/kernel/rootns.c
> @@ -117,6 +117,47 @@ static long rootns_get_nsfd(struct rootns *rootns, unsigned long nstype)
>  	return nsproxy_open_namespace(rootns->ns, rootns->user_ns, nstype);
>  }
>  
> +static long rootns_wait(struct rootns *rootns, void __user *uarg)
> +{
> +	struct pid_namespace *pid_ns = task_active_pid_ns(current);
> +	struct rootns_wait_args args;
> +	long ret;
> +
> +	if (!uarg)
> +		return -EINVAL;
> +	if (copy_from_user(&args, uarg, sizeof(args)))
> +		return -EFAULT;
> +	if (args.flags & ~WNOHANG)
> +		return -EINVAL;
> +	if (!pidns_is_ancestor(rootns->ns->pid_ns_for_children, pid_ns))
> +		return -ECHILD;
> +	if (READ_ONCE(rootns->state) == ROOTNS_INIT)
> +		return -ECHILD;
> +
> +	if (!(args.flags & WNOHANG)) {
> +		ret = wait_event_freezable(rootns->waitq,
> +					   READ_ONCE(rootns->state) == ROOTNS_DEAD ||
> +					   READ_ONCE(rootns->state) == ROOTNS_INIT);
> +		if (ret)
> +			return ret;
> +	}
> +
> +	scoped_guard(spinlock, &rootns->lock) {
> +		if (rootns->state == ROOTNS_INIT)
> +			return -ECHILD;
> +		if (rootns->state != ROOTNS_DEAD)
> +			return 0;
> +		ret = pid_nr_ns(rootns->init_pid, pid_ns);
> +		if (ret <= 0)
> +			return -ECHILD;
> +		args.status = rootns->exit_code;
> +	}
> +
> +	if (copy_to_user(uarg, &args, sizeof(args)))
> +		return -EFAULT;
> +	return ret;
> +}
> +
>  static long rootns_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
>  {
>  	struct rootns *rootns = file->private_data;
> @@ -124,6 +165,8 @@ static long rootns_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
>  	switch (cmd) {
>  	case ROOTNS_GET_NSFD:
>  		return rootns_get_nsfd(rootns, arg);
> +	case ROOTNS_WAIT:
> +		return rootns_wait(rootns, (void __user *)arg);
>  	default:
>  		return -ENOIOCTLCMD;
>  	}
> @@ -134,6 +177,8 @@ static long rootns_compat_ioctl(struct file *file, unsigned int cmd,
>  				unsigned long arg)
>  {
>  	switch (cmd) {
> +	case ROOTNS_WAIT:
> +		return rootns_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
>  	case ROOTNS_GET_NSFD:
>  		return rootns_ioctl(file, cmd, arg);
>  	default:
> @@ -328,3 +373,4 @@ SYSCALL_DEFINE1(rootns, unsigned int, flags)
>  
>  	return fd;
>  }
> +
> -- 
> 2.47.3
> 

Ought to be dropped but seemed too irrelevant detail for the time
being.

Br, Jarkko

  reply	other threads:[~2026-11-21  0:17 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-21  0:08 [RFC PATCH v5 00/25] rootns: fd-bound process closures Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 01/25] userns: Factor out idmap validation and commit helpers Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 02/25] userns: Add userns_set_idmap() system call Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 03/25] arch: Wire up " Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 04/25] mount: Add mnt_ns_get_root() Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 05/25] mount: Enforce mount_too_revealing() for foreign mntns Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 06/25] mount: Support MOVE_MOUNT_T_MNTNS in move_mount() Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 07/25] mount: Support MOVE_MOUNT_CLONE with MOVE_MOUNT_T_MNTNS Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 08/25] userns: Factor out install_user_ns_cred() Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 09/25] nsfs: Add nsproxy_open_namespace() Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 10/25] nsproxy: Pass nsproxy to create_new_namespaces() Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 11/25] rootns: Add core infrastructure for root namespaces Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 12/25] rootns: Track init lifecycle via copy_process() and pid_namespace Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 13/25] rootns: Add rootns() system call Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 14/25] rootns: Add ROOTNS_WAIT ioctl Jarkko Sakkinen
2026-11-21  0:17   ` Jarkko Sakkinen [this message]
2026-11-21  0:18     ` Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 15/25] rootns: Add ROOTNS_KILL ioctl Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 16/25] fork: Support CLONE_INTO_ROOTNS in clone3() Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 17/25] fs: Support FSCONFIG_SET_ROOTNS in fsconfig() Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 18/25] proc: Implement ->set_rootns() fs_context operation Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 19/25] ipc/mqueue: " Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 20/25] security: Add rootns LSM hooks Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 21/25] bpf: Register " Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 22/25] arch: Wire up rootns() system call Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 23/25] docs: Document root namespace uAPI Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 24/25] selftests/rootns: Add root namespace test suite Jarkko Sakkinen
2026-11-21  0:08 ` [RFC PATCH v5 25/25] 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=awDjC9hcKSRnCPgJ@kernel.org \
    --to=jarkko@kernel.org \
    --cc=alex@amutable.com \
    --cc=brauner@kernel.org \
    --cc=corbet@lwn.net \
    --cc=dhowells@redhat.com \
    --cc=jack@suse.cz \
    --cc=josef@toxicpanda.com \
    --cc=kees@kernel.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=luto@amacapital.net \
    --cc=neal@gompa.dev \
    --cc=paul@paul-moore.com \
    --cc=sergeh@kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --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