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 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: [RFC PATCH v5 11/25] rootns: Add core infrastructure for root namespaces
Date: Sat, 21 Nov 2026 02:08:30 +0200 [thread overview]
Message-ID: <20261121000844.1863324-12-jarkko@kernel.org> (raw)
In-Reply-To: <20261121000844.1863324-1-jarkko@kernel.org>
Linux namespaces can be created and entered individually, but userspace
orchestrators lack a single kernel object that binds a full detached
namespace set and an init process behind a pollable file descriptor.
Add struct rootns, its lifecycle states, reference counting, uAPI
creation flags, ROOTNS_GET_NSFD ioctl, and anonymous inode file
operations under CONFIG_ROOTNS. Drop active and passive namespace
references on final release, send SIGKILL to the rootns init thread
group on close when ROOTNS_KILL_ON_CLOSE is set, report EPOLLHUP from
poll() once the rootns reaches ROOTNS_DEAD, and allow holders with
CAP_SYS_ADMIN in the rootns user namespace to open member nsfs fds.
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/rootns.h | 61 ++++++++++++
include/uapi/linux/rootns.h | 44 +++++++++
init/Kconfig | 9 ++
kernel/Makefile | 2 +
kernel/rootns.c | 187 ++++++++++++++++++++++++++++++++++++
5 files changed, 303 insertions(+)
create mode 100644 include/linux/rootns.h
create mode 100644 include/uapi/linux/rootns.h
create mode 100644 kernel/rootns.c
diff --git a/include/linux/rootns.h b/include/linux/rootns.h
new file mode 100644
index 000000000000..dcdba08cfaeb
--- /dev/null
+++ b/include/linux/rootns.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017-2019 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2026 Opinsys Oy
+ */
+
+#ifndef _LINUX_ROOTNS_H
+#define _LINUX_ROOTNS_H
+
+#include <linux/refcount.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+
+struct file;
+struct nsproxy;
+struct pid;
+struct user_namespace;
+
+enum rootns_state {
+ ROOTNS_INIT = 0,
+ ROOTNS_FORKING = 1,
+ ROOTNS_RUNNING = 2,
+ ROOTNS_DEAD = 3,
+};
+
+/*
+ * The rootns object.
+ */
+struct rootns {
+ refcount_t usage;
+ int exit_code; /* The exit code of 'init' */
+ struct user_namespace *user_ns; /* Owning user namespace */
+ struct nsproxy *ns; /* This rootns's namespaces */
+ struct pid *init_pid; /* The 'init' task's TGID (pid ref) */
+ spinlock_t lock; /* Guards rootns lifecycle state */
+ wait_queue_head_t waitq; /* Someone waiting for init to exit waits here */
+ unsigned int flags; /* Validated rootns() flags */
+ enum rootns_state state; /* Root namespace lifecycle state */
+};
+
+#ifdef CONFIG_ROOTNS
+struct rootns *get_rootns(struct rootns *c);
+void put_rootns(struct rootns *c);
+bool is_rootns_file(struct file *file);
+#else
+static inline struct rootns *get_rootns(struct rootns *c)
+{
+ return NULL;
+}
+
+static inline void put_rootns(struct rootns *c)
+{
+}
+
+static inline bool is_rootns_file(struct file *file)
+{
+ return false;
+}
+#endif /* CONFIG_ROOTNS */
+
+#endif /* _LINUX_ROOTNS_H */
diff --git a/include/uapi/linux/rootns.h b/include/uapi/linux/rootns.h
new file mode 100644
index 000000000000..bd643bdfb43c
--- /dev/null
+++ b/include/uapi/linux/rootns.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2017-2019 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2026 Opinsys Oy
+ */
+
+#ifndef _UAPI_LINUX_ROOTNS_H
+#define _UAPI_LINUX_ROOTNS_H
+
+#include <linux/ioctl.h>
+
+/**
+ * enum rootns_flags - Flags for rootns()
+ * @ROOTNS_KILL_ON_CLOSE: Send %SIGKILL to rootns init on final fd release.
+ * @ROOTNS_CLOSE_ON_EXEC: Set %O_CLOEXEC on the returned control fd.
+ * @ROOTNS_ALL_FLAGS: Mask of all valid flags accepted by rootns().
+ *
+ * Every root namespace allocates a full set of detached namespaces owned
+ * by a fresh user namespace.
+ */
+enum rootns_flags {
+ ROOTNS_KILL_ON_CLOSE = 0x00000001,
+ ROOTNS_CLOSE_ON_EXEC = 0x00000002,
+ ROOTNS_ALL_FLAGS = 0x00000003,
+};
+
+#define ROOTNS_IOCTL_MAGIC 0xB9
+
+/**
+ * DOC: ROOTNS_GET_NSFD
+ *
+ * ``ioctl(rootnsfd, ROOTNS_GET_NSFD, nstype)`` opens an ``nsfs`` file
+ * descriptor (with ``O_CLOEXEC``) for the member namespace identified by
+ * ``nstype`` (one of ``CLONE_NEWNS``, ``CLONE_NEWCGROUP``,
+ * ``CLONE_NEWUTS``, ``CLONE_NEWIPC``, ``CLONE_NEWUSER``, ``CLONE_NEWPID``,
+ * ``CLONE_NEWNET``, or ``CLONE_NEWTIME``).
+ *
+ * Requires ``CAP_SYS_ADMIN`` in the ``rootns`` user namespace. Opening
+ * ``CLONE_NEWPID`` additionally requires running in an ancestor active PID
+ * namespace and that ``rootns`` init is running.
+ */
+#define ROOTNS_GET_NSFD _IO(ROOTNS_IOCTL_MAGIC, 0x01)
+
+#endif /* _UAPI_LINUX_ROOTNS_H */
diff --git a/init/Kconfig b/init/Kconfig
index c8a7cfa60a6e..58eafca2f42a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1283,6 +1283,15 @@ config NET_NS
endif # NAMESPACES
+config ROOTNS
+ bool "Root namespace descriptor support"
+ depends on NAMESPACES && USER_NS && PID_NS && UTS_NS && IPC_NS && NET_NS && CGROUPS
+ help
+ Allow user space to create and manage isolated namespace sets and
+ their init process lifecycle through an anonymous-inode control file
+ descriptor via rootns(), rootns ioctls, FSCONFIG_SET_ROOTNS, and
+ clone3() with CLONE_INTO_ROOTNS.
+
config CHECKPOINT_RESTORE
bool "Checkpoint/restore support"
depends on PROC_FS
diff --git a/kernel/Makefile b/kernel/Makefile
index 4ff92e24680c..7074d2664ce7 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -152,6 +152,8 @@ KCOV_INSTRUMENT_kstack_erase.o := n
obj-$(CONFIG_SCF_TORTURE_TEST) += scftorture.o
+obj-$(CONFIG_ROOTNS) += rootns.o
+
$(obj)/configs.o: $(obj)/config_data.gz
# .config is small, so it is compressed with gzip rather than the image compressor.
diff --git a/kernel/rootns.c b/kernel/rootns.c
new file mode 100644
index 000000000000..033e0aae386f
--- /dev/null
+++ b/kernel/rootns.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017-2019 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2026 Opinsys Oy
+ */
+
+/**
+ * DOC: Overview
+ *
+ * A ``rootns`` is an anonymous-inode control file descriptor (not an ``nsfs``
+ * namespace) that binds a full set of detached namespaces, an initially empty
+ * mount namespace, an owning user namespace, and an init process lifecycle:
+ *
+ * 1. ``rootns()`` allocates a detached ``rootns`` with a fresh user namespace
+ * and dedicated mount (``CLONE_EMPTY_MNTNS``), PID, UTS, IPC, network,
+ * cgroup, and time namespaces, returning its control fd.
+ *
+ * 2. Userspace optionally maps UIDs/GIDs via ``userns_set_idmap()`` on the
+ * ``CLONE_NEWUSER`` fd, configures superblocks via ``FSCONFIG_SET_ROOTNS``,
+ * retrieves the mount namespace fd via ``ioctl(rootnsfd, ROOTNS_GET_NSFD,
+ * CLONE_NEWNS)``, and installs ``"/"`` and relative or cloned
+ * (``MOVE_MOUNT_CLONE``) submounts via ``MOVE_MOUNT_T_MNTNS``.
+ *
+ * 3. ``clone3()`` with ``CLONE_INTO_ROOTNS`` spawns processes into the
+ * ``rootns``; the first call commits PID 1 while concurrent bootstrap
+ * callers wait killably.
+ *
+ * 4. ``ioctl(rootnsfd, ROOTNS_KILL, sig)`` signals all member thread groups.
+ * When PID 1 exits, the PID namespace zaps and reaps all remaining tasks,
+ * ``poll()`` reports ``EPOLLHUP``, and ``ioctl(rootnsfd, ROOTNS_WAIT,
+ * &args)`` returns init's exit status.
+ */
+
+#include <linux/poll.h>
+#include <linux/wait.h>
+#include <uapi/linux/wait.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/rootns.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+#include <linux/mnt_namespace.h>
+#include <linux/nsproxy.h>
+#include <linux/ns_common.h>
+#include <linux/nsfs.h>
+#include <linux/pid.h>
+#include <linux/pid_namespace.h>
+#include <linux/time_namespace.h>
+#include <linux/user_namespace.h>
+#include <linux/compat.h>
+#include <linux/idr.h>
+#include <uapi/linux/rootns.h>
+
+/*
+ * Get a reference to a rootns.
+ */
+struct rootns *get_rootns(struct rootns *c)
+{
+ refcount_inc(&c->usage);
+ return c;
+}
+
+/*
+ * Drop a reference on a rootns and clear it if it is no longer in use.
+ */
+void put_rootns(struct rootns *c)
+{
+ if (!c || !refcount_dec_and_test(&c->usage))
+ return;
+
+ if (c->ns)
+ put_nsproxy(c->ns);
+ if (c->init_pid)
+ put_pid(c->init_pid);
+ if (c->user_ns) {
+ ns_ref_active_put(c->user_ns);
+ put_user_ns(c->user_ns);
+ }
+ kfree(c);
+}
+
+/*
+ * Allow the user to poll for the rootns dying.
+ */
+static __poll_t rootns_poll(struct file *file, poll_table *wait)
+{
+ struct rootns *rootns = file->private_data;
+ __poll_t mask = 0;
+
+ poll_wait(file, &rootns->waitq, wait);
+
+ if (READ_ONCE(rootns->state) == ROOTNS_DEAD)
+ mask |= EPOLLHUP;
+
+ return mask;
+}
+
+static long rootns_get_nsfd(struct rootns *rootns, unsigned long nstype)
+{
+ if (nstype > UINT_MAX)
+ return -EINVAL;
+ if (!ns_capable(rootns->user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (nstype == CLONE_NEWPID) {
+ if (!pidns_is_ancestor(rootns->ns->pid_ns_for_children,
+ task_active_pid_ns(current)))
+ return -EXDEV;
+ if (READ_ONCE(rootns->state) != ROOTNS_RUNNING)
+ return -ESRCH;
+ }
+
+ return nsproxy_open_namespace(rootns->ns, rootns->user_ns, nstype);
+}
+
+static long rootns_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct rootns *rootns = file->private_data;
+
+ switch (cmd) {
+ case ROOTNS_GET_NSFD:
+ return rootns_get_nsfd(rootns, arg);
+ default:
+ return -ENOIOCTLCMD;
+ }
+}
+
+#ifdef CONFIG_COMPAT
+static long rootns_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ switch (cmd) {
+ case ROOTNS_GET_NSFD:
+ return rootns_ioctl(file, cmd, arg);
+ default:
+ return -ENOIOCTLCMD;
+ }
+}
+#endif
+
+static int __rootns_kill(struct rootns *rootns, int sig, bool priv)
+{
+ struct pid *pid = NULL;
+ int ret;
+
+ scoped_guard(spinlock, &rootns->lock) {
+ if (rootns->state == ROOTNS_RUNNING)
+ pid = get_pid(rootns->init_pid);
+ }
+ if (!pid)
+ return -ESRCH;
+
+ ret = kill_pid(pid, sig, priv);
+ put_pid(pid);
+ return ret;
+}
+
+static int rootns_release(struct inode *inode, struct file *file)
+{
+ struct rootns *rootns = file->private_data;
+
+ if (rootns->flags & ROOTNS_KILL_ON_CLOSE)
+ __rootns_kill(rootns, SIGKILL, true);
+ put_rootns(rootns);
+ return 0;
+}
+
+static const struct file_operations rootns_fops = {
+ .poll = rootns_poll,
+ .unlocked_ioctl = rootns_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = rootns_compat_ioctl,
+#endif
+ .release = rootns_release,
+};
+
+/*
+ * Returns true if the file is a rootns.
+ */
+bool is_rootns_file(struct file *file)
+{
+ return file->f_op == &rootns_fops;
+}
--
2.47.3
next prev parent reply other threads:[~2026-11-21 0:09 UTC|newest]
Thread overview: 29+ 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 ` Jarkko Sakkinen [this message]
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
2026-11-21 0:18 ` Jarkko Sakkinen
2026-11-21 1:09 ` 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=20261121000844.1863324-12-jarkko@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