Linux Security Modules development
 help / color / mirror / Atom feed
From: Christian Brauner <brauner@kernel.org>
To: linux-fsdevel@vger.kernel.org
Cc: linux-security-module@vger.kernel.org,
	 Alexander Viro <viro@zeniv.linux.org.uk>,
	Jan Kara <jack@suse.cz>,
	 bpf@vger.kernel.org, Zhiqi Zhang <zhiqizhangg@gmail.com>,
	 "Christian Brauner (Amutable)" <brauner@kernel.org>
Subject: [PATCH 2/2] ns: don't call the namespace LSM hooks for kernel-internal namespaces
Date: Fri, 20 Nov 2026 13:29:59 +0100	[thread overview]
Message-ID: <20261120-work-ns-mount_subtree-v1-2-06337377f94a@kernel.org> (raw)
In-Reply-To: <20261120-work-ns-mount_subtree-v1-0-06337377f94a@kernel.org>

mount_subtree() allocates a private anonymous mount namespace so that
automounts triggered while it looks up the path have somewhere to go.
That namespace never becomes anyone's namespace and it's gone again
before mount_subtree() returns. btrfs goes through it on every mount:

  btrfs_get_tree()
  -> btrfs_get_tree_subvol()
     -> mount_subvol()
        -> mount_subtree()

and NFS on every NFSv4 mount and whenever it follows a referral:

  nfs4_try_get_tree() / nfs4_get_referral_tree()
  -> do_nfs4_mount()
     -> mount_subtree()

But __ns_common_init() calls security_namespace_init() for it like for
any other namespace. Since commit 15dd86021b57a ("landlock: Enforce
namespace use restrictions") Landlock enforces
LANDLOCK_PERMISSION_NAMESPACE_USE in its namespace_init hook. So a task
in a domain that handles that permission without allowing CLONE_NEWNS
can't mount btrfs or NFSv4 anymore. mount(2) fails with EPERM even
though the caller never asked for a mount namespace.

Mark such namespaces as kernel-internal and don't call the namespace
LSM hooks for them at all. That includes namespace_free. Currently
security_namespace_free() only calls the hook if an LSM requested a
namespace blob and none does. But we shouldn't rely on that. Otherwise
a bpf program attached to namespace_free would see namespaces go away
that it never saw being created.

The anonymous mount namespaces created by open_tree(OPEN_TREE_CLONE)
and fsmount() are handed to userspace and keep going through the hooks.
Landlock covers them on purpose.

Fixes: f675d2e95569 ("lsm: add LSM blob and hooks for namespaces")
Reported-by: Zhiqi Zhang <zhiqizhangg@gmail.com>
Closes: https://lore.kernel.org/20261114141323.19029-1-zhiqizhangg@gmail.com
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
---
 fs/namespace.c                     |  9 +++++++--
 include/linux/ns/ns_common_types.h |  2 ++
 include/linux/ns_common.h          | 20 +++++++++++++-------
 kernel/nscommon.c                  |  9 ++++++---
 4 files changed, 28 insertions(+), 12 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 756f9011cbf1d..82738b818c1d0 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2355,6 +2355,7 @@ void drop_collected_paths(const struct path *paths, const struct path *prealloc)
 
 enum mnt_ns_flags_t {
 	MNT_NS_ANON	= (1 << 0),
+	MNT_NS_KERNEL	= (1 << 1),
 };
 
 static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *,
@@ -4377,10 +4378,14 @@ static void free_mnt_ns(struct mnt_namespace *ns)
 static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns,
 					  enum mnt_ns_flags_t flags)
 {
+	enum ns_common_flags_t ns_flags = 0;
 	struct mnt_namespace *new_ns;
 	struct ucounts *ucounts;
 	int ret;
 
+	if (flags & MNT_NS_KERNEL)
+		ns_flags |= NS_COMMON_KERNEL;
+
 	ucounts = inc_mnt_namespaces(user_ns);
 	if (!ucounts)
 		return ERR_PTR(-ENOSPC);
@@ -4392,7 +4397,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns,
 	}
 
 	if (flags & MNT_NS_ANON)
-		ret = ns_common_init_inum(new_ns, MNT_NS_ANON_INO);
+		ret = ns_common_init_inum(new_ns, MNT_NS_ANON_INO, ns_flags);
 	else
 		ret = ns_common_init(new_ns);
 	if (ret) {
@@ -4515,7 +4520,7 @@ struct dentry *mount_subtree(struct vfsmount *m, const char *name)
 	struct path path;
 	int err;
 
-	ns = alloc_mnt_ns(&init_user_ns, MNT_NS_ANON);
+	ns = alloc_mnt_ns(&init_user_ns, MNT_NS_ANON | MNT_NS_KERNEL);
 	if (IS_ERR(ns)) {
 		mntput(m);
 		return ERR_CAST(ns);
diff --git a/include/linux/ns/ns_common_types.h b/include/linux/ns/ns_common_types.h
index 47a5cfe2326a3..5f8b0930ae065 100644
--- a/include/linux/ns/ns_common_types.h
+++ b/include/linux/ns/ns_common_types.h
@@ -102,6 +102,7 @@ extern const struct proc_ns_operations utsns_operations;
  *   __ns_ref_active = 1 and remain active forever.
  *
  * @ns_type: type of namespace (e.g., CLONE_NEWNET)
+ * @ns_flags: NS_COMMON_* flags
  * @stashed: cached dentry to be used by the vfs
  * @ops: namespace operations
  * @inum: namespace inode number (quickly recycled for non-initial namespaces)
@@ -113,6 +114,7 @@ struct ns_common {
 		refcount_t __ns_ref; /* do not use directly */
 	} ____cacheline_aligned_in_smp;
 	u32 ns_type;
+	u32 ns_flags;
 	struct dentry *stashed;
 	const struct proc_ns_operations *ops;
 	unsigned int inum;
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index e8b2bf0da5ede..524b77904d3b4 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -8,9 +8,14 @@
 #include <uapi/linux/sched.h>
 #include <uapi/linux/nsfs.h>
 
+enum ns_common_flags_t {
+	/* Kernel-internal namespace. The LSM namespace hooks never see it. */
+	NS_COMMON_KERNEL	= (1 << 0),
+};
+
 bool is_current_namespace(struct ns_common *ns);
 int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops,
-		     int inum, u64 ns_id);
+		     int inum, u64 ns_id, enum ns_common_flags_t flags);
 void __ns_common_free(struct ns_common *ns);
 struct ns_common *__must_check ns_owner(struct ns_common *ns);
 
@@ -47,13 +52,14 @@ static __always_inline bool is_ns_init_id(const struct ns_common *ns)
 			 ns_common_type(__ns),				\
 			 to_ns_operations(__ns),			\
 			 (((__ns) == ns_init_ns(__ns)) ? ns_init_inum(__ns) : 0), \
-			 (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0))
+			 (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0), \
+			 0)
 
-#define ns_common_init_inum(__ns, __inum)        \
-	__ns_common_init(to_ns_common(__ns),     \
-			 ns_common_type(__ns),   \
-			 to_ns_operations(__ns), \
-			 __inum, 0)
+#define ns_common_init_inum(__ns, __inum, __flags) \
+	__ns_common_init(to_ns_common(__ns),       \
+			 ns_common_type(__ns),     \
+			 to_ns_operations(__ns),   \
+			 __inum, 0, __flags)
 
 #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns)))
 
diff --git a/kernel/nscommon.c b/kernel/nscommon.c
index 4438c6b663f91..20fc0d0e98212 100644
--- a/kernel/nscommon.c
+++ b/kernel/nscommon.c
@@ -55,7 +55,7 @@ static void ns_debug(struct ns_common *ns, const struct proc_ns_operations *ops)
 #endif
 
 int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops,
-		     int inum, u64 ns_id)
+		     int inum, u64 ns_id, enum ns_common_flags_t flags)
 {
 	int ret = 0;
 
@@ -66,6 +66,7 @@ int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_ope
 #endif
 	ns->ops = ops;
 	ns->ns_type = ns_type;
+	ns->ns_flags = flags;
 	ns_tree_node_init(&ns->ns_tree_node);
 	ns_tree_node_init(&ns->ns_unified_node);
 	ns_tree_node_init(&ns->ns_owner_node);
@@ -85,7 +86,8 @@ int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_ope
 	/* Allocate the id before the LSM hook so it can track the namespace by it. */
 	__ns_tree_gen_id(ns, ns_id);
 
-	ret = security_namespace_init(ns);
+	if (!(flags & NS_COMMON_KERNEL))
+		ret = security_namespace_init(ns);
 	if (ret) {
 		if (!inum)
 			proc_free_inum(ns->inum);
@@ -106,7 +108,8 @@ int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_ope
 
 void __ns_common_free(struct ns_common *ns)
 {
-	security_namespace_free(ns);
+	if (!(ns->ns_flags & NS_COMMON_KERNEL))
+		security_namespace_free(ns);
 
 	if (ns->inum > MNT_NS_INO_SPECIAL_MAX)
 		proc_free_inum(ns->inum);

-- 
2.53.0


  parent reply	other threads:[~2026-11-20 12:30 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-20 12:29 [PATCH 0/2] ns: don't call the namespace LSM hooks for kernel-internal namespaces Christian Brauner
2026-11-20 12:29 ` [PATCH 1/2] mount: pass flags to alloc_mnt_ns() Christian Brauner
2026-11-20 12:32   ` sashiko-bot
2026-11-20 12:29 ` Christian Brauner [this message]
2026-11-20 12:33   ` [PATCH 2/2] ns: don't call the namespace LSM hooks for kernel-internal namespaces sashiko-bot

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=20261120-work-ns-mount_subtree-v1-2-06337377f94a@kernel.org \
    --to=brauner@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-security-module@vger.kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=zhiqizhangg@gmail.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