[PATCH 12/23] VFS: Implement fsmount() to effect a pre-configured mount [ver #4]

[David Howells]

Provide a system call by which a filesystem opened with fsopen() and
configured by a series of writes can be mounted:

	int ret = fsmount(int fsfd, int dfd, const char *path,
			  unsigned int at_flags, unsigned int flags);

where fsfd is the fd returned by fsopen(), dfd, path and at_flags locate
the mountpoint and flags are the applicable MS_* flags.  dfd can be
AT_FDCWD or an fd open to a directory.

In the event that fsmount() fails, it may be possible to get an error
message by calling read().  If no message is available, ENODATA will be
reported.

Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
---

 arch/x86/entry/syscalls/syscall_32.tbl |    1 
 arch/x86/entry/syscalls/syscall_64.tbl |    1 
 fs/namespace.c                         |   96 ++++++++++++++++++++++++++++++++
 include/linux/lsm_hooks.h              |    6 ++
 include/linux/security.h               |    5 ++
 include/linux/syscalls.h               |    2 +
 kernel/sys_ni.c                        |    1 
 security/security.c                    |    5 ++
 security/selinux/hooks.c               |   12 ++++
 9 files changed, 129 insertions(+)

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9bf8d4c62f85..abe6ea95e0e6 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -392,3 +392,4 @@
 383	i386	statx			sys_statx
 384	i386	arch_prctl		sys_arch_prctl			compat_sys_arch_prctl
 385	i386	fsopen			sys_fsopen
+386	i386	fsmount			sys_fsmount
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9b198c5fc412..0977c5079831 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -340,6 +340,7 @@
 331	common	pkey_free		sys_pkey_free
 332	common	statx			sys_statx
 333	common	fsopen			sys_fsopen
+334	common	fsmount			sys_fsmount
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/namespace.c b/fs/namespace.c
index e92bc48accb5..4e9ad16db79c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3239,6 +3239,102 @@ vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
 EXPORT_SYMBOL_GPL(vfs_submount);
 
 /*
+ * Mount a new, prepared superblock (specified by fs_fd) on the location
+ * specified by dfd and dir_name.  dfd can be AT_FDCWD, a dir fd or a container
+ * fd.  This cannot be used for binding, moving or remounting mounts.
+ */
+SYSCALL_DEFINE5(fsmount, int, fs_fd, int, dfd, const char __user *, dir_name,
+		unsigned int, at_flags, unsigned int, flags)
+{
+	struct sb_config *sc;
+	struct inode *inode;
+	struct path mountpoint;
+	struct fd f;
+	unsigned int lookup_flags, mnt_flags = 0;
+	long ret;
+
+	if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+			  AT_EMPTY_PATH)) != 0)
+		return -EINVAL;
+
+	if (flags & ~(MS_RDONLY | MS_NOSUID | MS_NODEV | MS_NOEXEC |
+		      MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME))
+		return -EINVAL;
+
+	if (flags & MS_RDONLY)
+		mnt_flags |= MNT_READONLY;
+	if (flags & MS_NOSUID)
+		mnt_flags |= MNT_NOSUID;
+	if (flags & MS_NODEV)
+		mnt_flags |= MNT_NODEV;
+	if (flags & MS_NOEXEC)
+		mnt_flags |= MNT_NOEXEC;
+	if (flags & MS_NODIRATIME)
+		mnt_flags |= MNT_NODIRATIME;
+
+	if (flags & MS_STRICTATIME) {
+		if (flags & MS_NOATIME)
+			return -EINVAL;
+	} else if (flags & MS_NOATIME) {
+		mnt_flags |= MNT_NOATIME;
+	} else {
+		mnt_flags |= MNT_RELATIME;
+	}
+
+	f = fdget(fs_fd);
+	if (!f.file)
+		return -EBADF;
+
+	ret = -EINVAL;
+	if (f.file->f_op != &fs_fs_fops)
+		goto err_fsfd;
+
+	sc = f.file->private_data;
+
+	ret = -EPERM;
+	if (!may_mount() ||
+	    ((sc->ms_flags & MS_MANDLOCK) && !may_mandlock()))
+		goto err_fsfd;
+
+	/* There must be a valid superblock or we can't mount it */
+	inode = file_inode(f.file);
+	ret = inode_lock_killable(inode);
+	if (ret == 0) {
+		if (!sc->root)
+			ret = invalf("VFS: Root must be obtained before mount");
+		inode_unlock(inode);
+	}
+	if (ret < 0)
+		goto err_fsfd;
+
+	/* Find the mountpoint.  A container can be specified in dfd. */
+	lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+	if (at_flags & AT_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (at_flags & AT_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (at_flags & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+	ret = user_path_at(dfd, dir_name, lookup_flags, &mountpoint);
+	if (ret < 0) {
+		errorf("VFS: Mountpoint lookup failed");
+		goto err_fsfd;
+	}
+
+	ret = security_sb_mountpoint(sc, &mountpoint);
+	if (ret < 0)
+		goto err_mp;
+
+	ret = do_new_mount_sc(sc, &mountpoint, mnt_flags);
+
+err_mp:
+	path_put(&mountpoint);
+err_fsfd:
+	fdput(f);
+	return ret;
+}
+
+/*
  * Return true if path is reachable from root
  *
  * namespace_sem or mount_lock is held
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index e95a918e61ca..7064c0c15386 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -102,6 +102,10 @@
  *	@sc indicates the superblock configuration context.
  *	@sc->root indicates the root that will be mounted.
  *	@sc->root->d_sb points to the superblock.
+ * @sb_mountpoint:
+ *	Equivalent of sb_mount, but with an sb_config.
+ *	@sc indicates the superblock configuration context.
+ *	@mountpoint indicates the path on which the mount will take place.
  *
  * Security hooks for filesystem operations.
  *
@@ -1405,6 +1409,7 @@ union security_list_options {
 	void (*sb_config_free)(struct sb_config *sc);
 	int (*sb_config_parse_option)(struct sb_config *sc, char *opt);
 	int (*sb_get_tree)(struct sb_config *sc);
+	int (*sb_mountpoint)(struct sb_config *sc, struct path *mountpoint);
 
 	int (*sb_alloc_security)(struct super_block *sb);
 	void (*sb_free_security)(struct super_block *sb);
@@ -1721,6 +1726,7 @@ struct security_hook_heads {
 	struct list_head sb_config_free;
 	struct list_head sb_config_parse_option;
 	struct list_head sb_get_tree;
+	struct list_head sb_mountpoint;
 	struct list_head sb_alloc_security;
 	struct list_head sb_free_security;
 	struct list_head sb_copy_data;
diff --git a/include/linux/security.h b/include/linux/security.h
index f6eb735987d1..8c06e158c195 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -230,6 +230,7 @@ int security_sb_config_dup(struct sb_config *sc, struct sb_config *src_sc);
 void security_sb_config_free(struct sb_config *sc);
 int security_sb_config_parse_option(struct sb_config *sc, char *opt);
 int security_sb_get_tree(struct sb_config *sc);
+int security_sb_mountpoint(struct sb_config *sc, struct path *mountpoint);
 int security_sb_alloc(struct super_block *sb);
 void security_sb_free(struct super_block *sb);
 int security_sb_copy_data(char *orig, char *copy);
@@ -546,6 +547,10 @@ static inline int security_sb_get_tree(struct sb_config *sc)
 {
 	return 0;
 }
+static inline int security_sb_mountpoint(struct sb_config *sc, struct path *mountpoint)
+{
+	return 0;
+}
 
 static inline int security_sb_alloc(struct super_block *sb)
 {
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 91ec8802ad5d..07e4f775f24d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -906,5 +906,7 @@ asmlinkage long sys_pkey_free(int pkey);
 asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 			  unsigned mask, struct statx __user *buffer);
 asmlinkage long sys_fsopen(const char *fs_name, int containerfd, unsigned int flags);
+asmlinkage long sys_fsmount(int fsfd, int dfd, const char *path, unsigned int at_flags,
+			    unsigned int flags);
 
 #endif
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index de1dc63e7e47..a0fe764bd5dd 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -261,3 +261,4 @@ cond_syscall(sys_pkey_free);
 
 /* fd-based mount */
 cond_syscall(sys_fsopen);
+cond_syscall(sys_fsmount);
diff --git a/security/security.c b/security/security.c
index ed086c6c8f0b..f4136ca5cb1b 100644
--- a/security/security.c
+++ b/security/security.c
@@ -341,6 +341,11 @@ int security_sb_get_tree(struct sb_config *sc)
 	return call_int_hook(sb_get_tree, 0, sc);
 }
 
+int security_sb_mountpoint(struct sb_config *sc, struct path *mountpoint)
+{
+	return call_int_hook(sb_mountpoint, 0, sc, mountpoint);
+}
+
 int security_sb_alloc(struct super_block *sb)
 {
 	return call_int_hook(sb_alloc_security, 0, sb);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 1deafdbf8716..877b7e7bd2d5 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2970,6 +2970,17 @@ static int selinux_sb_get_tree(struct sb_config *sc)
 	return rc;
 }
 
+static int selinux_sb_mountpoint(struct sb_config *sc, struct path *mountpoint)
+{
+	const struct cred *cred = current_cred();
+	int ret;
+
+	ret = path_has_perm(cred, mountpoint, FILE__MOUNTON);
+	if (ret < 0)
+		errorf("SELinux: Mount on mountpoint not permitted");
+	return ret;
+}
+
 /* inode security operations */
 
 static int selinux_inode_alloc_security(struct inode *inode)
@@ -6303,6 +6314,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(sb_config_free, selinux_sb_config_free),
 	LSM_HOOK_INIT(sb_config_parse_option, selinux_sb_config_parse_option),
 	LSM_HOOK_INIT(sb_get_tree, selinux_sb_get_tree),
+	LSM_HOOK_INIT(sb_mountpoint, selinux_sb_mountpoint),
 
 	LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security),
 	LSM_HOOK_INIT(sb_free_security, selinux_sb_free_security),