fs: introduce MOUNT_ATTR_IDMAP

Introduce a new mount bind mount property to allow idmapping mounts. The
MOUNT_ATTR_IDMAP flag can be set via the new mount_setattr() syscall
together with a file descriptor referring to a user namespace.

The user namespace referenced by the namespace file descriptor will be
attached to the bind mount. All interactions with the filesystem going
through that mount will be mapped according to the mapping specified in
the user namespace attached to it.

Using user namespaces to mark mounts means we can reuse all the existing
infrastructure in the kernel that already exists to handle idmappings
and can also use this for permission checking to allow unprivileged user
to create idmapped mounts in the future.

Idmapping a mount is decoupled from the caller's user and mount
namespace. This means idmapped mounts can be created in the initial
user namespace which is an important use-case for systemd-homed,
portable usb-sticks between systems, sharing data between the initial
user namespace and unprivileged containers, and other use-cases that
have been brought up. For example, assume a home directory where all
files are owned by uid and gid 1000 and the home directory is brought to
a new laptop where the user has id 12345. The system administrator can
simply create a mount of this home directory with a mapping of
1000:12345:1 and other mappings to indicate the ids should be kept.
(With this it is e.g. also possible to create idmapped mounts on the
host with an identity mapping 1:1:100000 where the root user is not
mapped. A user with root access that e.g. has been pivot rooted into
such a mount on the host will be not be able to execute, read, write, or
create files as root.)

Given that mapping a mount is decoupled from the caller's user namespace
a sufficiently privileged process such as a container manager can set up
an idmapped mount for the container and the container can simply pivot
root to it. There's no need for the container to do anything. The mount
will appear correctly mapped independent of the user namespace the
container uses. This means we don't need to mark a mount as idmappable.

In order to create an idmapped mount the caller must currently be
privileged in the user namespace of the superblock the mount belongs to.
Once a mount has been idmapped we don't allow it to change its mapping.
This keeps permission checking and life-cycle management simple. Users
wanting to change the idmapped can always create a new detached mount
with a different idmapping.

Link: https://lore.kernel.org/r/20210121131959.646623-36-christian.brauner@ubuntu.com
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Howells <dhowells@redhat.com>
Cc: Mauricio Vásquez Bernal <mauricio@kinvolk.io>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

fs/namespace.c

@@ -25,6 +25,7 @@
 #include <linux/proc_ns.h>
 #include <linux/magic.h>
 #include <linux/memblock.h>
+#include <linux/proc_fs.h>
 #include <linux/task_work.h>
 #include <linux/sched/task.h>
 #include <uapi/linux/mount.h>
@@ -79,6 +80,7 @@ struct mount_kattr {
 	unsigned int propagation;
 	unsigned int lookup_flags;
 	bool recurse;
+	struct user_namespace *mnt_userns;
 };
 
 /* /sys/fs */
@@ -3477,7 +3479,7 @@ out_type:
 	(MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \
 	 MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME)
 
-#define MOUNT_SETATTR_VALID_FLAGS FSMOUNT_VALID_FLAGS
+#define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP)
 
 #define MOUNT_SETATTR_PROPAGATION_FLAGS \
 	(MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED)
@@ -3845,6 +3847,36 @@ static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt)
 	return flags;
 }
 
+static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
+{
+	struct vfsmount *m = &mnt->mnt;
+
+	if (!kattr->mnt_userns)
+		return 0;
+
+	/*
+	 * Once a mount has been idmapped we don't allow it to change its
+	 * mapping. It makes things simpler and callers can just create
+	 * another bind-mount they can idmap if they want to.
+	 */
+	if (mnt_user_ns(m) != &init_user_ns)
+		return -EPERM;
+
+	/* The underlying filesystem doesn't support idmapped mounts yet. */
+	if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP))
+		return -EINVAL;
+
+	/* We're not controlling the superblock. */
+	if (!ns_capable(m->mnt_sb->s_user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* Mount has already been visible in the filesystem hierarchy. */
+	if (!is_anon_ns(mnt->mnt_ns))
+		return -EINVAL;
+
+	return 0;
+}
+
 static struct mount *mount_setattr_prepare(struct mount_kattr *kattr,
 					   struct mount *mnt, int *err)
 {
@@ -3869,6 +3901,10 @@ static struct mount *mount_setattr_prepare(struct mount_kattr *kattr,
 			goto out;
 		}
 
+		*err = can_idmap_mount(kattr, m);
+		if (*err)
+			goto out;
+
 		last = m;
 
 		if ((kattr->attr_set & MNT_READONLY) &&
@@ -3883,6 +3919,18 @@ out:
 	return last;
 }
 
+static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
+{
+	struct user_namespace *mnt_userns;
+
+	if (!kattr->mnt_userns)
+		return;
+
+	mnt_userns = get_user_ns(kattr->mnt_userns);
+	/* Pairs with smp_load_acquire() in mnt_user_ns(). */
+	smp_store_release(&mnt->mnt.mnt_userns, mnt_userns);
+}
+
 static void mount_setattr_commit(struct mount_kattr *kattr,
 				 struct mount *mnt, struct mount *last,
 				 int err)
@@ -3893,6 +3941,7 @@ static void mount_setattr_commit(struct mount_kattr *kattr,
 		if (!err) {
 			unsigned int flags;
 
+			do_idmap_mount(kattr, m);
 			flags = recalc_flags(kattr, m);
 			WRITE_ONCE(m->mnt.mnt_flags, flags);
 		}
@@ -3965,7 +4014,62 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
 	return err;
 }
 
-static int build_mount_kattr(const struct mount_attr *attr,
+static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
+				struct mount_kattr *kattr, unsigned int flags)
+{
+	int err = 0;
+	struct ns_common *ns;
+	struct user_namespace *mnt_userns;
+	struct file *file;
+
+	if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP))
+		return 0;
+
+	/*
+	 * We currently do not support clearing an idmapped mount. If this ever
+	 * is a use-case we can revisit this but for now let's keep it simple
+	 * and not allow it.
+	 */
+	if (attr->attr_clr & MOUNT_ATTR_IDMAP)
+		return -EINVAL;
+
+	if (attr->userns_fd > INT_MAX)
+		return -EINVAL;
+
+	file = fget(attr->userns_fd);
+	if (!file)
+		return -EBADF;
+
+	if (!proc_ns_file(file)) {
+		err = -EINVAL;
+		goto out_fput;
+	}
+
+	ns = get_proc_ns(file_inode(file));
+	if (ns->ops->type != CLONE_NEWUSER) {
+		err = -EINVAL;
+		goto out_fput;
+	}
+
+	/*
+	 * The init_user_ns is used to indicate that a vfsmount is not idmapped.
+	 * This is simpler than just having to treat NULL as unmapped. Users
+	 * wanting to idmap a mount to init_user_ns can just use a namespace
+	 * with an identity mapping.
+	 */
+	mnt_userns = container_of(ns, struct user_namespace, ns);
+	if (mnt_userns == &init_user_ns) {
+		err = -EPERM;
+		goto out_fput;
+	}
+	kattr->mnt_userns = get_user_ns(mnt_userns);
+
+out_fput:
+	fput(file);
+	return err;
+}
+
+static int build_mount_kattr(const struct mount_attr *attr, size_t usize,
 			     struct mount_kattr *kattr, unsigned int flags)
 {
 	unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW;
@@ -3991,9 +4095,6 @@ static int build_mount_kattr(const struct mount_attr *attr,
 	if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS)
 		return -EINVAL;
 
-	if (attr->userns_fd)
-		return -EINVAL;
-
 	kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set);
 	kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr);
 
@@ -4032,7 +4133,13 @@ static int build_mount_kattr(const struct mount_attr *attr,
 			return -EINVAL;
 	}
 
-	return 0;
+	return build_mount_idmapped(attr, usize, kattr, flags);
+}
+
+static void finish_mount_kattr(struct mount_kattr *kattr)
+{
+	put_user_ns(kattr->mnt_userns);
+	kattr->mnt_userns = NULL;
 }
 
 SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
@@ -4070,7 +4177,7 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
 	    attr.propagation == 0)
 		return 0;
 
-	err = build_mount_kattr(&attr, &kattr, flags);
+	err = build_mount_kattr(&attr, usize, &kattr, flags);
 	if (err)
 		return err;
 
@@ -4079,6 +4186,7 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
 		return err;
 
 	err = do_mount_setattr(&target, &kattr);
+	finish_mount_kattr(&kattr);
 	path_put(&target);
 	return err;
 }

fs/proc_namespace.c

@@ -79,6 +79,9 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt)
 		if (mnt->mnt_flags & fs_infop->flag)
 			seq_puts(m, fs_infop->str);
 	}
+
+	if (mnt_user_ns(mnt) != &init_user_ns)
+		seq_puts(m, ",idmapped");
 }
 
 static inline void mangle(struct seq_file *m, const char *s)

include/linux/mount.h

@@ -77,7 +77,8 @@ struct vfsmount {
 
 static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt)
 {
-	return mnt->mnt_userns;
+	/* Pairs with smp_store_release() in do_idmap_mount(). */
+	return smp_load_acquire(&mnt->mnt_userns);
 }
 
 struct file; /* forward dec */

include/uapi/linux/mount.h

@@ -119,6 +119,7 @@ enum fsconfig_command {
 #define MOUNT_ATTR_NOATIME	0x00000010 /* - Do not update access times. */
 #define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
 #define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
+#define MOUNT_ATTR_IDMAP	0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
 
 /*
  * mount_setattr()