Linux Security Modules development
 help / color / mirror / Atom feed
From: Jarkko Sakkinen <jarkko@kernel.org>
To: linux-fsdevel@vger.kernel.org
Cc: Jarkko Sakkinen <jarkko@kernel.org>,
	bpf@vger.kernel.org, containers@lists.linux.dev,
	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,
	Aleksa Sarai <aleksa@amutable.com>,
	Alexander Mikhalitsyn <alex@amutable.com>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Andy Lutomirski <luto@amacapital.net>,
	Arnd Bergmann <arnd@arndb.de>,
	Christian Brauner <brauner@kernel.org>,
	David Howells <dhowells@redhat.com>,
	Eric Biggers <ebiggers@kernel.org>,
	Giuseppe Scrivano <giuseppe@scrivano.org>,
	Hugh Dickins <hughd@google.com>, Jan Kara <jack@suse.cz>,
	Jeff Layton <jlayton@kernel.org>,
	Jonathan Corbet <corbet@lwn.net>,
	Josef Bacik <josef@toxicpanda.com>, Kees Cook <kees@kernel.org>,
	KP Singh <kpsingh@kernel.org>,
	Lennart Poettering <lennart@poettering.net>,
	Neal Gompa <neal@gompa.dev>, Oleg Nesterov <oleg@redhat.com>,
	Paul Moore <paul@paul-moore.com>,
	Pavel Tikhomirov <ptikhomirov@virtuozzo.com>,
	Serge Hallyn <sergeh@kernel.org>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Zygmunt Krynicki <zygmunt.krynicki@canonical.com>
Subject: [RFC PATCH v7 01/26] userns: Factor out idmap validation and commit helpers
Date: Sun, 22 Nov 2026 21:35:14 +0200	[thread overview]
Message-ID: <20261122193539.3334213-2-jarkko@kernel.org> (raw)
In-Reply-To: <20261122193539.3334213-1-jarkko@kernel.org>

map_write() and its permission helpers validate extent ranges, check
root and unprivileged self-mappings, translate parent ID ranges, sort
extents, and install the resulting map inline for procfs text writes,
preventing non-procfs callers from reusing the same validation and
commit path.

Extract idmap_maps_root(), unpriv_idmap_permitted(),
validate_and_insert_extent(), free_new_idmap(), resolve_new_idmap(), and
commit_new_idmap() with no functional change.

Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 kernel/user_namespace.c | 229 +++++++++++++++++++++-------------------
 1 file changed, 122 insertions(+), 107 deletions(-)

diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index cd748e1cbace..caba2ac33077 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -884,6 +884,22 @@ VISIBLE_IF_KUNIT int uid_gid_map_sort(struct uid_gid_map *map)
 }
 EXPORT_SYMBOL_IF_KUNIT(uid_gid_map_sort);
 
+static bool idmap_maps_root(const struct uid_gid_map *new_map)
+{
+	unsigned int idx;
+
+	for (idx = 0; idx < new_map->nr_extents; idx++) {
+		const struct uid_gid_extent *e;
+
+		if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
+			e = &new_map->extent[idx];
+		else
+			e = &new_map->forward[idx];
+		if (e->lower_first == 0)
+			return true;
+	}
+	return false;
+}
 /**
  * verify_root_map() - check the uid 0 mapping
  * @file: idmapping file
@@ -900,22 +916,9 @@ static bool verify_root_map(const struct file *file,
 			    struct user_namespace *map_ns,
 			    struct uid_gid_map *new_map)
 {
-	int idx;
 	const struct user_namespace *file_ns = file->f_cred->user_ns;
-	struct uid_gid_extent *extent0 = NULL;
-
-	for (idx = 0; idx < new_map->nr_extents; idx++) {
-		if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
-			extent0 = &new_map->extent[idx];
-		else
-			extent0 = &new_map->forward[idx];
-		if (extent0->lower_first == 0)
-			break;
-
-		extent0 = NULL;
-	}
 
-	if (!extent0)
+	if (!idmap_maps_root(new_map))
 		return true;
 
 	if (map_ns == file_ns) {
@@ -938,6 +941,103 @@ static bool verify_root_map(const struct file *file,
 	return true;
 }
 
+static int validate_and_insert_extent(struct uid_gid_map *new_map,
+				      struct uid_gid_extent *extent)
+{
+	if ((extent->first == (u32)-1) || (extent->lower_first == (u32)-1))
+		return -EINVAL;
+
+	if ((extent->first + extent->count) <= extent->first)
+		return -EINVAL;
+	if ((extent->lower_first + extent->count) <= extent->lower_first)
+		return -EINVAL;
+
+	if (mappings_overlap(new_map, extent))
+		return -EINVAL;
+
+	if (new_map->nr_extents >= UID_GID_MAP_MAX_EXTENTS)
+		return -EINVAL;
+
+	return uid_gid_map_insert_extent(new_map, extent);
+}
+
+static void free_new_idmap(struct uid_gid_map *new_map)
+{
+	if (new_map->nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
+		kfree(new_map->forward);
+		kfree(new_map->reverse);
+	}
+	memset(new_map, 0, sizeof(*new_map));
+}
+
+static int resolve_new_idmap(struct uid_gid_map *new_map,
+			     struct uid_gid_map *parent_map)
+{
+	unsigned int idx;
+
+	if (new_map->nr_extents == 0)
+		return -EINVAL;
+
+	for (idx = 0; idx < new_map->nr_extents; idx++) {
+		struct uid_gid_extent *e;
+		u32 lower_first;
+
+		if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
+			e = &new_map->extent[idx];
+		else
+			e = &new_map->forward[idx];
+
+		lower_first = map_id_range_down(parent_map,
+						e->lower_first,
+						e->count);
+		if (lower_first == (u32)-1)
+			return -EPERM;
+
+		e->lower_first = lower_first;
+	}
+
+	return uid_gid_map_sort(new_map);
+}
+
+static void commit_new_idmap(struct uid_gid_map *map,
+			     struct uid_gid_map *new_map)
+{
+	if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
+		memcpy(map->extent, new_map->extent,
+		       new_map->nr_extents * sizeof(new_map->extent[0]));
+	} else {
+		map->forward = new_map->forward;
+		map->reverse = new_map->reverse;
+	}
+	/*
+	 * Pairs with smp_rmb() in map_id_range_down(), map_id_range_up(),
+	 * and m_start().
+	 */
+	smp_wmb();
+	map->nr_extents = new_map->nr_extents;
+	memset(new_map, 0, sizeof(*new_map));
+}
+
+static bool unpriv_idmap_permitted(const struct user_namespace *ns,
+				   const struct cred *cred, int cap_setid,
+				   unsigned long ns_flags,
+				   const struct uid_gid_map *new_map)
+{
+	u32 id;
+
+	if (new_map->nr_extents != 1 || new_map->extent[0].count != 1 ||
+	    !uid_eq(ns->owner, cred->euid))
+		return false;
+
+	id = new_map->extent[0].lower_first;
+	if (cap_setid == CAP_SETUID)
+		return uid_eq(make_kuid(ns->parent, id), cred->euid);
+	if (cap_setid == CAP_SETGID)
+		return !(ns_flags & USERNS_SETGROUPS_ALLOWED) &&
+		       gid_eq(make_kgid(ns->parent, id), cred->egid);
+	return false;
+}
+
 /*
  * Parse the decimal u32 at *pos, up to the next whitespace or NUL, and
  * leave *pos pointing at that character.
@@ -966,8 +1066,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 {
 	struct seq_file *seq = file->private_data;
 	struct user_namespace *map_ns = seq->private;
-	struct uid_gid_map new_map;
-	unsigned idx;
+	struct uid_gid_map new_map = {};
 	struct uid_gid_extent extent;
 	char *kbuf, *pos, *next_line;
 	ssize_t ret;
@@ -1002,8 +1101,6 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	 */
 	mutex_lock(&userns_state_mutex);
 
-	memset(&new_map, 0, sizeof(struct uid_gid_map));
-
 	ret = -EPERM;
 	/* Only allow one successful write to the map */
 	if (map->nr_extents != 0)
@@ -1052,98 +1149,28 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 		if (*pos != '\0')
 			goto out;
 
-		/* Verify we have been given valid starting values */
-		if ((extent.first == (u32) -1) ||
-		    (extent.lower_first == (u32) -1))
-			goto out;
-
-		/* Verify count is not zero and does not cause the
-		 * extent to wrap
-		 */
-		if ((extent.first + extent.count) <= extent.first)
-			goto out;
-		if ((extent.lower_first + extent.count) <=
-		     extent.lower_first)
-			goto out;
-
-		/* Do the ranges in extent overlap any previous extents? */
-		if (mappings_overlap(&new_map, &extent))
-			goto out;
-
-		if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS &&
-		    (next_line != NULL))
-			goto out;
-
-		ret = uid_gid_map_insert_extent(&new_map, &extent);
+		ret = validate_and_insert_extent(&new_map, &extent);
 		if (ret < 0)
 			goto out;
 		ret = -EINVAL;
 	}
-	/* Be very certain the new map actually exists */
+
 	if (new_map.nr_extents == 0)
 		goto out;
 
 	ret = -EPERM;
-	/* Validate the user is allowed to use user id's mapped to. */
 	if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map))
 		goto out;
 
-	ret = -EPERM;
-	/* Map the lower ids from the parent user namespace to the
-	 * kernel global id space.
-	 */
-	for (idx = 0; idx < new_map.nr_extents; idx++) {
-		struct uid_gid_extent *e;
-		u32 lower_first;
-
-		if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
-			e = &new_map.extent[idx];
-		else
-			e = &new_map.forward[idx];
-
-		lower_first = map_id_range_down(parent_map,
-						e->lower_first,
-						e->count);
-
-		/* Fail if we can not map the specified extent to
-		 * the kernel global id space.
-		 */
-		if (lower_first == (u32) -1)
-			goto out;
-
-		e->lower_first = lower_first;
-	}
-
-	/*
-	 * If we want to use binary search for lookup, this clones the extent
-	 * array and sorts both copies.
-	 */
-	ret = uid_gid_map_sort(&new_map);
+	ret = resolve_new_idmap(&new_map, parent_map);
 	if (ret < 0)
 		goto out;
 
-	/* Install the map */
-	if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
-		memcpy(map->extent, new_map.extent,
-		       new_map.nr_extents * sizeof(new_map.extent[0]));
-	} else {
-		map->forward = new_map.forward;
-		map->reverse = new_map.reverse;
-	}
-	smp_wmb();
-	map->nr_extents = new_map.nr_extents;
-
+	commit_new_idmap(map, &new_map);
 	*ppos = count;
 	ret = count;
 out:
-	if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
-		kfree(new_map.forward);
-		kfree(new_map.reverse);
-		map->forward = NULL;
-		map->reverse = NULL;
-		map->nr_extents = 0;
-	}
-
+	free_new_idmap(&new_map);
 	mutex_unlock(&userns_state_mutex);
 	kfree(kbuf);
 	return ret;
@@ -1213,20 +1240,8 @@ static bool new_idmap_permitted(const struct file *file,
 	/* Don't allow mappings that would allow anything that wouldn't
 	 * be allowed without the establishment of unprivileged mappings.
 	 */
-	if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) &&
-	    uid_eq(ns->owner, cred->euid)) {
-		u32 id = new_map->extent[0].lower_first;
-		if (cap_setid == CAP_SETUID) {
-			kuid_t uid = make_kuid(ns->parent, id);
-			if (uid_eq(uid, cred->euid))
-				return true;
-		} else if (cap_setid == CAP_SETGID) {
-			kgid_t gid = make_kgid(ns->parent, id);
-			if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) &&
-			    gid_eq(gid, cred->egid))
-				return true;
-		}
-	}
+	if (unpriv_idmap_permitted(ns, cred, cap_setid, ns->flags, new_map))
+		return true;
 
 	/* Allow anyone to set a mapping that doesn't require privilege */
 	if (!cap_valid(cap_setid))
-- 
2.47.3


  reply	other threads:[~2026-11-22 19:36 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-22 19:35 [RFC PATCH v7 00/26] userland: Userland containers Jarkko Sakkinen
2026-11-22 19:35 ` Jarkko Sakkinen [this message]
2026-11-22 19:35 ` [RFC PATCH v7 02/26] userns: Add userns_set_idmap() system call Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 03/26] arch: Wire up " Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 04/26] mount: Add mnt_ns_get_root() Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 05/26] mount: Enforce mount_too_revealing() for foreign mntns Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 06/26] mount: Support MOVE_MOUNT_T_MNTNS in move_mount() Jarkko Sakkinen
2026-11-22 20:02   ` sashiko-bot
2026-11-22 19:35 ` [RFC PATCH v7 07/26] mount: Support MOVE_MOUNT_CLONE with MOVE_MOUNT_T_MNTNS Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 08/26] userns: Factor out install_user_ns_cred() Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 09/26] nsproxy: Expose create_new_namespaces() Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 10/26] userland: Add core infrastructure Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 11/26] userland: Track init lifecycle via copy_process() and pid_namespace Jarkko Sakkinen
2026-11-22 20:09   ` bot+bpf-ci
2026-11-22 19:35 ` [RFC PATCH v7 12/26] userland: Add userland_open() system call Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 13/26] userland: Add USERLAND_GET_NSFD ioctl Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 14/26] userland: Add USERLAND_SHARE_NSFD ioctl Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 15/26] exit: Support P_USERLAND in waitid() Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 16/26] signal: Support userland fds in pidfd_send_signal() Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 17/26] fork: Support CLONE_INTO_USERLAND in clone3() Jarkko Sakkinen
2026-11-22 20:01   ` sashiko-bot
2026-11-22 19:35 ` [RFC PATCH v7 18/26] fs: Support FSCONFIG_SET_USERLAND in fsconfig() Jarkko Sakkinen
2026-11-22 19:58   ` sashiko-bot
2026-11-22 19:35 ` [RFC PATCH v7 19/26] proc: Implement ->set_userland() fs_context operation Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 20/26] ipc/mqueue: " Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 21/26] security: Add userland LSM hooks Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 22/26] bpf: Register " Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 23/26] arch: Wire up userland_open() system call Jarkko Sakkinen
2026-11-22 19:35 ` [RFC PATCH v7 24/26] docs: Document userland uAPI Jarkko Sakkinen
2026-11-22 20:09   ` bot+bpf-ci
2026-11-22 19:35 ` [RFC PATCH v7 25/26] selftests/userland: Add userland test suite Jarkko Sakkinen
2026-11-22 19:52   ` sashiko-bot
2026-11-22 19:35 ` [RFC PATCH v7 26/26] MAINTAINERS: Add entry for USERLAND Jarkko Sakkinen
2026-11-22 20:02 ` [RFC PATCH v7 00/26] userland: Userland containers 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=20261122193539.3334213-2-jarkko@kernel.org \
    --to=jarkko@kernel.org \
    --cc=aleksa@amutable.com \
    --cc=alex@amutable.com \
    --cc=arnd@arndb.de \
    --cc=bpf@vger.kernel.org \
    --cc=brauner@kernel.org \
    --cc=containers@lists.linux.dev \
    --cc=corbet@lwn.net \
    --cc=dhowells@redhat.com \
    --cc=ebiggers@kernel.org \
    --cc=giuseppe@scrivano.org \
    --cc=hughd@google.com \
    --cc=jack@suse.cz \
    --cc=jlayton@kernel.org \
    --cc=josef@toxicpanda.com \
    --cc=kees@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=lennart@poettering.net \
    --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=luto@amacapital.net \
    --cc=neal@gompa.dev \
    --cc=oleg@redhat.com \
    --cc=paul@paul-moore.com \
    --cc=ptikhomirov@virtuozzo.com \
    --cc=sergeh@kernel.org \
    --cc=skhan@linuxfoundation.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