vfs: syscall: Add move_mount(2) to move mounts around

Add a move_mount() system call that will move a mount from one place to
another and, in the next commit, allow to attach an unattached mount tree.

The new system call looks like the following:

	int move_mount(int from_dfd, const char *from_path,
		       int to_dfd, const char *to_path,
		       unsigned int flags);
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-api@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

arch/x86/entry/syscalls/syscall_32.tbl

@@ -399,7 +399,8 @@
 385	i386	io_pgetevents		sys_io_pgetevents_time32	__ia32_compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq			__ia32_sys_rseq
 387	i386	open_tree		sys_open_tree			__ia32_sys_open_tree
-# don't use numbers 388 through 392, add new calls at the end
+388	i386	move_mount		sys_move_mount			__ia32_sys_move_mount
+# don't use numbers 389 through 392, add new calls at the end
 393	i386	semget			sys_semget    			__ia32_sys_semget
 394	i386	semctl			sys_semctl    			__ia32_compat_sys_semctl
 395	i386	shmget			sys_shmget    			__ia32_sys_shmget

arch/x86/entry/syscalls/syscall_64.tbl

@@ -344,6 +344,7 @@
 333	common	io_pgetevents		__x64_sys_io_pgetevents
 334	common	rseq			__x64_sys_rseq
 335	common	open_tree		__x64_sys_open_tree
+336	common	move_mount		__x64_sys_move_mount
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
 424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal

fs/namespace.c

@@ -2539,72 +2539,81 @@ static inline int tree_contains_unbindable(struct mount *mnt)
 	return 0;
 }
 
-static int do_move_mount(struct path *path, const char *old_name)
+static int do_move_mount(struct path *old_path, struct path *new_path)
 {
-	struct path old_path, parent_path;
+	struct path parent_path = {.mnt = NULL, .dentry = NULL};
 	struct mount *p;
 	struct mount *old;
 	struct mountpoint *mp;
 	int err;
-	if (!old_name || !*old_name)
-		return -EINVAL;
-	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
-	if (err)
-		return err;
 
-	mp = lock_mount(path);
-	err = PTR_ERR(mp);
+	mp = lock_mount(new_path);
 	if (IS_ERR(mp))
-		goto out;
+		return PTR_ERR(mp);
 
-	old = real_mount(old_path.mnt);
-	p = real_mount(path->mnt);
+	old = real_mount(old_path->mnt);
+	p = real_mount(new_path->mnt);
 
 	err = -EINVAL;
 	if (!check_mnt(p) || !check_mnt(old))
-		goto out1;
+		goto out;
 
-	if (old->mnt.mnt_flags & MNT_LOCKED)
-		goto out1;
+	if (!mnt_has_parent(old))
+		goto out;
 
-	err = -EINVAL;
-	if (old_path.dentry != old_path.mnt->mnt_root)
-		goto out1;
+	if (old->mnt.mnt_flags & MNT_LOCKED)
+		goto out;
 
-	if (!mnt_has_parent(old))
-		goto out1;
+	if (old_path->dentry != old_path->mnt->mnt_root)
+		goto out;
 
-	if (d_is_dir(path->dentry) !=
-	      d_is_dir(old_path.dentry))
-		goto out1;
+	if (d_is_dir(new_path->dentry) !=
+	    d_is_dir(old_path->dentry))
+		goto out;
 	/*
 	 * Don't move a mount residing in a shared parent.
 	 */
 	if (IS_MNT_SHARED(old->mnt_parent))
-		goto out1;
+		goto out;
 	/*
 	 * Don't move a mount tree containing unbindable mounts to a destination
 	 * mount which is shared.
 	 */
 	if (IS_MNT_SHARED(p) && tree_contains_unbindable(old))
-		goto out1;
+		goto out;
 	err = -ELOOP;
 	for (; mnt_has_parent(p); p = p->mnt_parent)
 		if (p == old)
-			goto out1;
+			goto out;
 
-	err = attach_recursive_mnt(old, real_mount(path->mnt), mp, &parent_path);
+	err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp,
+				   &parent_path);
 	if (err)
-		goto out1;
+		goto out;
 
 	/* if the mount is moved, it should no longer be expire
 	 * automatically */
 	list_del_init(&old->mnt_expire);
-out1:
-	unlock_mount(mp);
 out:
+	unlock_mount(mp);
 	if (!err)
 		path_put(&parent_path);
+	return err;
+}
+
+static int do_move_mount_old(struct path *path, const char *old_name)
+{
+	struct path old_path;
+	int err;
+
+	if (!old_name || !*old_name)
+		return -EINVAL;
+
+	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
+	if (err)
+		return err;
+
+	err = do_move_mount(&old_path, path);
 	path_put(&old_path);
 	return err;
 }
@@ -3050,7 +3059,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 	else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
 		retval = do_change_type(&path, flags);
 	else if (flags & MS_MOVE)
-		retval = do_move_mount(&path, dev_name);
+		retval = do_move_mount_old(&path, dev_name);
 	else
 		retval = do_new_mount(&path, type_page, sb_flags, mnt_flags,
 				      dev_name, data_page);
@@ -3278,6 +3287,61 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	return ksys_mount(dev_name, dir_name, type, flags, data);
 }
 
+/*
+ * Move a mount from one place to another.
+ *
+ * Note the flags value is a combination of MOVE_MOUNT_* flags.
+ */
+SYSCALL_DEFINE5(move_mount,
+		int, from_dfd, const char *, from_pathname,
+		int, to_dfd, const char *, to_pathname,
+		unsigned int, flags)
+{
+	struct path from_path, to_path;
+	unsigned int lflags;
+	int ret = 0;
+
+	if (!may_mount())
+		return -EPERM;
+
+	if (flags & ~MOVE_MOUNT__MASK)
+		return -EINVAL;
+
+	/* If someone gives a pathname, they aren't permitted to move
+	 * from an fd that requires unmount as we can't get at the flag
+	 * to clear it afterwards.
+	 */
+	lflags = 0;
+	if (flags & MOVE_MOUNT_F_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
+	if (flags & MOVE_MOUNT_F_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
+	if (flags & MOVE_MOUNT_F_EMPTY_PATH)	lflags |= LOOKUP_EMPTY;
+
+	ret = user_path_at(from_dfd, from_pathname, lflags, &from_path);
+	if (ret < 0)
+		return ret;
+
+	lflags = 0;
+	if (flags & MOVE_MOUNT_T_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
+	if (flags & MOVE_MOUNT_T_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
+	if (flags & MOVE_MOUNT_T_EMPTY_PATH)	lflags |= LOOKUP_EMPTY;
+
+	ret = user_path_at(to_dfd, to_pathname, lflags, &to_path);
+	if (ret < 0)
+		goto out_from;
+
+	ret = security_move_mount(&from_path, &to_path);
+	if (ret < 0)
+		goto out_to;
+
+	ret = do_move_mount(&from_path, &to_path);
+
+out_to:
+	path_put(&to_path);
+out_from:
+	path_put(&from_path);
+	return ret;
+}
+
 /*
  * Return true if path is reachable from root
  *

include/linux/lsm_hooks.h

@@ -160,6 +160,10 @@
  *	Parse a string of security data filling in the opts structure
  *	@options string containing all mount options known by the LSM
  *	@opts binary data structure usable by the LSM
+ * @move_mount:
+ *	Check permission before a mount is moved.
+ *	@from_path indicates the mount that is going to be moved.
+ *	@to_path indicates the mountpoint that will be mounted upon.
  * @dentry_init_security:
  *	Compute a context for a dentry as the inode is not yet available
  *	since NFSv4 has no label backed by an EA anyway.
@@ -1501,6 +1505,7 @@ union security_list_options {
 					unsigned long *set_kern_flags);
 	int (*sb_add_mnt_opt)(const char *option, const char *val, int len,
 			      void **mnt_opts);
+	int (*move_mount)(const struct path *from_path, const struct path *to_path);
 	int (*dentry_init_security)(struct dentry *dentry, int mode,
 					const struct qstr *name, void **ctx,
 					u32 *ctxlen);
@@ -1835,6 +1840,7 @@ struct security_hook_heads {
 	struct hlist_head sb_set_mnt_opts;
 	struct hlist_head sb_clone_mnt_opts;
 	struct hlist_head sb_add_mnt_opt;
+	struct hlist_head move_mount;
 	struct hlist_head dentry_init_security;
 	struct hlist_head dentry_create_files_as;
 #ifdef CONFIG_SECURITY_PATH

include/linux/security.h

@@ -250,6 +250,7 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb,
 				unsigned long *set_kern_flags);
 int security_add_mnt_opt(const char *option, const char *val,
 				int len, void **mnt_opts);
+int security_move_mount(const struct path *from_path, const struct path *to_path);
 int security_dentry_init_security(struct dentry *dentry, int mode,
 					const struct qstr *name, void **ctx,
 					u32 *ctxlen);
@@ -611,6 +612,12 @@ static inline int security_add_mnt_opt(const char *option, const char *val,
 	return 0;
 }
 
+static inline int security_move_mount(const struct path *from_path,
+				      const struct path *to_path)
+{
+	return 0;
+}
+
 static inline int security_inode_alloc(struct inode *inode)
 {
 	return 0;

include/linux/syscalls.h

@@ -986,6 +986,9 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len,
 			 int flags, uint32_t sig);
 asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags);
+asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path,
+			       int to_dfd, const char __user *to_path,
+			       unsigned int ms_flags);
 asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
 				       siginfo_t __user *info,
 				       unsigned int flags);

include/uapi/linux/mount.h

@@ -61,4 +61,15 @@
 #define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
 #define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
 
+/*
+ * move_mount() flags.
+ */
+#define MOVE_MOUNT_F_SYMLINKS		0x00000001 /* Follow symlinks on from path */
+#define MOVE_MOUNT_F_AUTOMOUNTS		0x00000002 /* Follow automounts on from path */
+#define MOVE_MOUNT_F_EMPTY_PATH		0x00000004 /* Empty from path permitted */
+#define MOVE_MOUNT_T_SYMLINKS		0x00000010 /* Follow symlinks on to path */
+#define MOVE_MOUNT_T_AUTOMOUNTS		0x00000020 /* Follow automounts on to path */
+#define MOVE_MOUNT_T_EMPTY_PATH		0x00000040 /* Empty to path permitted */
+#define MOVE_MOUNT__MASK		0x00000077
+
 #endif /* _UAPI_LINUX_MOUNT_H */

security/security.c

@@ -866,6 +866,11 @@ int security_add_mnt_opt(const char *option, const char *val, int len,
 }
 EXPORT_SYMBOL(security_add_mnt_opt);
 
+int security_move_mount(const struct path *from_path, const struct path *to_path)
+{
+	return call_int_hook(move_mount, 0, from_path, to_path);
+}
+
 int security_inode_alloc(struct inode *inode)
 {
 	int rc = lsm_inode_alloc(inode);