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 08/13] fs: Support FSCONFIG_SET_ROOTNS in fsconfig()
Date: Tue, 17 Nov 2026 07:08:36 +0200 [thread overview]
Message-ID: <20261117050841.3289652-9-jarkko@kernel.org> (raw)
In-Reply-To: <20261117050841.3289652-1-jarkko@kernel.org>
fsopen() initializes a filesystem context from current's user, network,
PID, and IPC namespaces, preventing an external manager from creating
proc, mqueue, or userns-owned superblocks bound to an unentered root
namespace.
Add FSCONFIG_SET_ROOTNS so callers holding CAP_SYS_ADMIN in the target
rootns user namespace can bind a newly opened fs_context to that rootns
once before offering parameters. Update fc->net_ns, switch fc->user_ns
for non-global FS_USERNS_MOUNT or FS_USERNS_DELEGATABLE filesystems
whose mounter fsuid/fsgid map into the rootns user namespace, and pass
the rootns to ->set_rootns() for proc and mqueue.
Co-developed-by: David Howells <dhowells@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
fs/fsopen.c | 74 +++++++++++++++++++++++++++++++++++---
fs/proc/root.c | 13 +++++++
include/linux/fs_context.h | 3 ++
include/uapi/linux/mount.h | 1 +
ipc/mqueue.c | 12 +++++++
5 files changed, 99 insertions(+), 4 deletions(-)
diff --git a/fs/fsopen.c b/fs/fsopen.c
index 70024870fefa..98d407fd249b 100644
--- a/fs/fsopen.c
+++ b/fs/fsopen.c
@@ -13,9 +13,14 @@
#include <linux/security.h>
#include <linux/anon_inodes.h>
#include <linux/namei.h>
+#include <linux/capability.h>
+#include <linux/nsproxy.h>
+#include <linux/rootns.h>
+#include <linux/user_namespace.h>
#include <linux/file.h>
#include <uapi/linux/mount.h>
#include <linux/audit.h>
+#include <net/net_namespace.h>
#include "internal.h"
#include "mount.h"
@@ -41,6 +46,48 @@ static inline const char *fetch_message_locked(struct fc_log *log, size_t len,
return p;
}
+/**
+ * DOC: FSCONFIG_SET_ROOTNS
+ *
+ * ``fsconfig(fsfd, FSCONFIG_SET_ROOTNS, NULL, NULL, rootnsfd)`` binds a newly
+ * opened filesystem context to @rootnsfd once before any parameters are
+ * supplied (subsequent calls fail with ``-EBUSY``).
+ *
+ * The caller must hold ``CAP_SYS_ADMIN`` in the target ``rootns`` user
+ * namespace. ``fc->net_ns`` is switched to the ``rootns`` network namespace,
+ * ``fc->user_ns`` is delegated for non-global ``FS_USERNS_MOUNT`` or
+ * ``FS_USERNS_DELEGATABLE`` filesystems when the mounter ``fsuid``/``fsgid``
+ * map into the target user namespace, and ``proc`` and ``mqueue`` contexts
+ * bind to the target ``rootns`` PID and IPC namespaces.
+ */
+static int fsconfig_set_rootns(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct user_namespace *user_ns;
+ struct rootns *c;
+
+ if (!is_rootns_file(param->file))
+ return -EINVAL;
+
+ c = param->file->private_data;
+ user_ns = c->cred->user_ns;
+ if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ put_net(fc->net_ns);
+ fc->net_ns = get_net(c->ns->net_ns);
+ if (!fc->global &&
+ (fc->fs_type->fs_flags & (FS_USERNS_MOUNT | FS_USERNS_DELEGATABLE)) &&
+ kuid_has_mapping(user_ns, fc->cred->fsuid) &&
+ kgid_has_mapping(user_ns, fc->cred->fsgid)) {
+ put_user_ns(fc->user_ns);
+ fc->user_ns = get_user_ns(user_ns);
+ }
+ if (fc->ops->set_rootns)
+ fc->ops->set_rootns(fc, c);
+ fc->phase = FS_CONTEXT_CREATE_PARAMS;
+ return 0;
+}
+
/*
* Allow the user to read back any error, warning or informational messages.
* Only one message is returned for each read(2) call.
@@ -147,7 +194,7 @@ SYSCALL_DEFINE2(fsopen, const char __user *, _fs_name, unsigned int, flags)
if (IS_ERR(fc))
return PTR_ERR(fc);
- fc->phase = FS_CONTEXT_CREATE_PARAMS;
+ fc->phase = FS_CONTEXT_CREATE_NS;
ret = fscontext_alloc_log(fc);
if (ret < 0)
@@ -222,7 +269,8 @@ static int vfs_cmd_create(struct fs_context *fc, bool exclusive)
struct super_block *sb;
int ret;
- if (fc->phase != FS_CONTEXT_CREATE_PARAMS)
+ if (fc->phase != FS_CONTEXT_CREATE_NS &&
+ fc->phase != FS_CONTEXT_CREATE_PARAMS)
return -EBUSY;
if (!mount_capable(fc))
@@ -298,9 +346,16 @@ static int vfs_fsconfig_locked(struct fs_context *fc, int cmd,
return vfs_cmd_create(fc, true);
case FSCONFIG_CMD_RECONFIGURE:
return vfs_cmd_reconfigure(fc);
+ case FSCONFIG_SET_ROOTNS:
+ if (fc->phase != FS_CONTEXT_CREATE_NS)
+ return -EBUSY;
+ return fsconfig_set_rootns(fc, param);
+
default:
- if (fc->phase != FS_CONTEXT_CREATE_PARAMS &&
- fc->phase != FS_CONTEXT_RECONF_PARAMS)
+ if (fc->phase == FS_CONTEXT_CREATE_NS)
+ fc->phase = FS_CONTEXT_CREATE_PARAMS;
+ else if (fc->phase != FS_CONTEXT_CREATE_PARAMS &&
+ fc->phase != FS_CONTEXT_RECONF_PARAMS)
return -EBUSY;
return vfs_parse_fs_param(fc, param);
@@ -390,6 +445,10 @@ SYSCALL_DEFINE5(fsconfig,
if (!_key || _value || aux < 0)
return -EINVAL;
break;
+ case FSCONFIG_SET_ROOTNS:
+ if (_key || _value || aux < 0)
+ return -EINVAL;
+ break;
case FSCONFIG_CMD_CREATE:
case FSCONFIG_CMD_CREATE_EXCL:
case FSCONFIG_CMD_RECONFIGURE:
@@ -457,6 +516,12 @@ SYSCALL_DEFINE5(fsconfig,
goto out_key;
param.dirfd = aux;
break;
+ case FSCONFIG_SET_ROOTNS:
+ ret = -EBADF;
+ param.file = fget(aux);
+ if (!param.file)
+ goto out_key;
+ break;
default:
break;
}
@@ -482,6 +547,7 @@ SYSCALL_DEFINE5(fsconfig,
putname(param.name);
break;
case FSCONFIG_SET_FD:
+ case FSCONFIG_SET_ROOTNS:
if (param.file)
fput(param.file);
break;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 7fbbe92bf73a..5976029ad3f8 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -15,6 +15,8 @@
#include <linux/sched/stat.h>
#include <linux/module.h>
#include <linux/bitops.h>
+#include <linux/nsproxy.h>
+#include <linux/rootns.h>
#include <linux/user_namespace.h>
#include <linux/fs_context.h>
#include <linux/mount.h>
@@ -323,6 +325,16 @@ static int proc_get_tree(struct fs_context *fc)
return get_tree_nodev(fc, proc_fill_super);
}
+static void proc_set_rootns(struct fs_context *fc, struct rootns *rootns)
+{
+ struct proc_fs_context *ctx = fc->fs_private;
+
+ put_pid_ns(ctx->pid_ns);
+ ctx->pid_ns = get_pid_ns(rootns->ns->pid_ns_for_children);
+ put_user_ns(fc->user_ns);
+ fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+}
+
static void proc_fs_context_free(struct fs_context *fc)
{
struct proc_fs_context *ctx = fc->fs_private;
@@ -334,6 +346,7 @@ static void proc_fs_context_free(struct fs_context *fc)
static const struct fs_context_operations proc_fs_context_ops = {
.free = proc_fs_context_free,
.parse_param = proc_parse_param,
+ .set_rootns = proc_set_rootns,
.get_tree = proc_get_tree,
.reconfigure = proc_reconfigure,
};
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index d1727dffecc5..cb978273c8bc 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -21,6 +21,7 @@ struct file_system_type;
struct mnt_namespace;
struct net;
struct pid_namespace;
+struct rootns;
struct super_block;
struct user_namespace;
struct vfsmount;
@@ -36,6 +37,7 @@ enum fs_context_purpose {
* Userspace usage phase for fsopen/fspick.
*/
enum fs_context_phase {
+ FS_CONTEXT_CREATE_NS, /* Set namespaces for sb creation */
FS_CONTEXT_CREATE_PARAMS, /* Loading params for sb creation */
FS_CONTEXT_CREATING, /* A superblock is being created */
FS_CONTEXT_AWAITING_MOUNT, /* Superblock created, awaiting fsmount() */
@@ -117,6 +119,7 @@ struct fs_context_operations {
int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
int (*parse_param)(struct fs_context *fc, struct fs_parameter *param);
int (*parse_monolithic)(struct fs_context *fc, void *data);
+ void (*set_rootns)(struct fs_context *fc, struct rootns *rootns);
int (*get_tree)(struct fs_context *fc);
int (*reconfigure)(struct fs_context *fc);
};
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index ac865edac517..cb55cfcfc92e 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -105,6 +105,7 @@ enum fsconfig_command {
FSCONFIG_CMD_CREATE = 6, /* Create new or reuse existing superblock */
FSCONFIG_CMD_RECONFIGURE = 7, /* Invoke superblock reconfiguration */
FSCONFIG_CMD_CREATE_EXCL = 8, /* Create new superblock, fail if reusing existing superblock */
+ FSCONFIG_SET_ROOTNS = 9, /* Set a rootns, supplied by fd */
};
/*
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 322c3dd98c44..a85ca188d370 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -32,6 +32,7 @@
#include <linux/mutex.h>
#include <linux/nsproxy.h>
#include <linux/pid.h>
+#include <linux/rootns.h>
#include <linux/ipc_namespace.h>
#include <linux/user_namespace.h>
#include <linux/slab.h>
@@ -400,6 +401,16 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
return ERR_PTR(ret);
}
+static void mqueue_set_rootns(struct fs_context *fc, struct rootns *rootns)
+{
+ struct mqueue_fs_context *ctx = fc->fs_private;
+
+ put_ipc_ns(ctx->ipc_ns);
+ ctx->ipc_ns = get_ipc_ns(rootns->ns->ipc_ns);
+ put_user_ns(fc->user_ns);
+ fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);
+}
+
static int mqueue_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct inode *inode;
@@ -1613,6 +1624,7 @@ static const struct super_operations mqueue_super_ops = {
static const struct fs_context_operations mqueue_fs_context_ops = {
.free = mqueue_fs_context_free,
+ .set_rootns = mqueue_set_rootns,
.get_tree = mqueue_get_tree,
};
--
2.47.3
next prev 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 ` [RFC PATCH 03/13] rootns: Track init lifecycle via copy_process() and pid_namespace Jarkko Sakkinen
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 ` Jarkko Sakkinen [this message]
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=20261117050841.3289652-9-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