VFS: Differentiate mount flags (MS_*) from internal superblock flags

Differentiate the MS_* flags passed to mount(2) from the internal flags set
in the super_block's s_flags.  s_flags are now called SB_*, with the names
and the values for the moment mirroring the MS_* flags that they're
equivalent to.

In this patch, just the headers are altered and some kernel code where
blind automated conversion isn't necessarily correct.

Note that this shows up some interesting issues:

 (1) Some MS_* flags get translated to MNT_* flags (such as MS_NODEV ->
     MNT_NODEV) without passing this on to the filesystem, but some
     filesystems set such flags anyway.

 (2) The ->remount_fs() methods of some filesystems adjust the *flags
     argument by setting MS_* flags in it, such as MS_NOATIME - but these
     flags are then scrubbed by do_remount_sb() (only the occupants of
     MS_RMT_MASK are permitted: MS_RDONLY, MS_SYNCHRONOUS, MS_MANDLOCK,
     MS_I_VERSION and MS_LAZYTIME)

I'm not sure what's the best way to solve all these cases.

Suggested-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: David Howells <dhowells@redhat.com>

Author: dhowells

Documentation/filesystems/porting

@@ -228,7 +228,7 @@ anything from oops to silent memory corruption.
 ---
 [mandatory]
 
-	FS_NOMOUNT is gone.  If you use it - just set MS_NOUSER in flags
+	FS_NOMOUNT is gone.  If you use it - just set SB_NOUSER in flags
 (see rootfs for one kind of solution and bdev/socket/pipe for another).
 
 ---

fs/namespace.c

@@ -971,7 +971,7 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
 	if (!mnt)
 		return ERR_PTR(-ENOMEM);
 
-	if (flags & MS_KERNMOUNT)
+	if (flags & SB_KERNMOUNT)
 		mnt->mnt.mnt_flags = MNT_INTERNAL;
 
 	root = mount_fs(type, flags, name, data);
@@ -1003,7 +1003,7 @@ vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
 	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
 		return ERR_PTR(-EPERM);
 
-	return vfs_kern_mount(type, MS_SUBMOUNT, name, data);
+	return vfs_kern_mount(type, SB_SUBMOUNT, name, data);
 }
 EXPORT_SYMBOL_GPL(vfs_submount);
 
@@ -1535,7 +1535,7 @@ static int do_umount(struct mount *mnt, int flags)
 			return -EPERM;
 		down_write(&sb->s_umount);
 		if (!sb_rdonly(sb))
-			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
+			retval = do_remount_sb(sb, SB_RDONLY, NULL, 0);
 		up_write(&sb->s_umount);
 		return retval;
 	}
@@ -2059,7 +2059,7 @@ static void unlock_mount(struct mountpoint *where)
 
 static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
 {
-	if (mnt->mnt.mnt_sb->s_flags & MS_NOUSER)
+	if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER)
 		return -EINVAL;
 
 	if (d_is_dir(mp->m_dentry) !=
@@ -2073,9 +2073,9 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
  * Sanity check the flags to change_mnt_propagation.
  */
 
-static int flags_to_propagation_type(int flags)
+static int flags_to_propagation_type(int ms_flags)
 {
-	int type = flags & ~(MS_REC | MS_SILENT);
+	int type = ms_flags & ~(MS_REC | MS_SILENT);
 
 	/* Fail if any non-propagation flags are set */
 	if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
@@ -2089,18 +2089,18 @@ static int flags_to_propagation_type(int flags)
 /*
  * recursively change the type of the mountpoint.
  */
-static int do_change_type(struct path *path, int flag)
+static int do_change_type(struct path *path, int ms_flags)
 {
 	struct mount *m;
 	struct mount *mnt = real_mount(path->mnt);
-	int recurse = flag & MS_REC;
+	int recurse = ms_flags & MS_REC;
 	int type;
 	int err = 0;
 
 	if (path->dentry != path->mnt->mnt_root)
 		return -EINVAL;
 
-	type = flags_to_propagation_type(flag);
+	type = flags_to_propagation_type(ms_flags);
 	if (!type)
 		return -EINVAL;
 
@@ -2222,8 +2222,8 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
  * If you've mounted a non-root directory somewhere and want to do remount
  * on it - tough luck.
  */
-static int do_remount(struct path *path, int flags, int mnt_flags,
-		      void *data)
+static int do_remount(struct path *path, int ms_flags, int sb_flags,
+		      int mnt_flags, void *data)
 {
 	int err;
 	struct super_block *sb = path->mnt->mnt_sb;
@@ -2267,12 +2267,12 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 		return err;
 
 	down_write(&sb->s_umount);
-	if (flags & MS_BIND)
-		err = change_mount_flags(path->mnt, flags);
+	if (ms_flags & MS_BIND)
+		err = change_mount_flags(path->mnt, ms_flags);
 	else if (!capable(CAP_SYS_ADMIN))
 		err = -EPERM;
 	else
-		err = do_remount_sb(sb, flags, data, 0);
+		err = do_remount_sb(sb, sb_flags, data, 0);
 	if (!err) {
 		lock_mount_hash();
 		mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
@@ -2437,7 +2437,7 @@ static bool mount_too_revealing(struct vfsmount *mnt, int *new_mnt_flags);
  * create a new mount for userspace and request it to be added into the
  * namespace's tree
  */
-static int do_new_mount(struct path *path, const char *fstype, int flags,
+static int do_new_mount(struct path *path, const char *fstype, int sb_flags,
 			int mnt_flags, const char *name, void *data)
 {
 	struct file_system_type *type;
@@ -2451,7 +2451,7 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 	if (!type)
 		return -ENODEV;
 
-	mnt = vfs_kern_mount(type, flags, name, data);
+	mnt = vfs_kern_mount(type, sb_flags, name, data);
 	if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
 	    !mnt->mnt_sb->s_subtype)
 		mnt = fs_set_subtype(mnt, fstype);
@@ -2706,8 +2706,8 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 		const char *type_page, unsigned long flags, void *data_page)
 {
 	struct path path;
+	unsigned int mnt_flags = 0, sb_flags;
 	int retval = 0;
-	int mnt_flags = 0;
 
 	/* Discard magic */
 	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
@@ -2717,6 +2717,9 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 	if (data_page)
 		((char *)data_page)[PAGE_SIZE - 1] = 0;
 
+	if (flags & MS_NOUSER)
+		return -EINVAL;
+
 	/* ... and get the mountpoint */
 	retval = user_path(dir_name, &path);
 	if (retval)
@@ -2726,7 +2729,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 				   type_page, flags, data_page);
 	if (!retval && !may_mount())
 		retval = -EPERM;
-	if (!retval && (flags & MS_MANDLOCK) && !may_mandlock())
+	if (!retval && (flags & SB_MANDLOCK) && !may_mandlock())
 		retval = -EPERM;
 	if (retval)
 		goto dput_out;
@@ -2748,7 +2751,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 		mnt_flags |= MNT_NODIRATIME;
 	if (flags & MS_STRICTATIME)
 		mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
-	if (flags & MS_RDONLY)
+	if (flags & SB_RDONLY)
 		mnt_flags |= MNT_READONLY;
 
 	/* The default atime for remount is preservation */
@@ -2759,12 +2762,15 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 		mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
 	}
 
-	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
-		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
-		   MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT);
+	sb_flags = flags & (SB_RDONLY |
+			    SB_SYNCHRONOUS |
+			    SB_MANDLOCK |
+			    SB_DIRSYNC |
+			    SB_SILENT |
+			    SB_POSIXACL);
 
 	if (flags & MS_REMOUNT)
-		retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
+		retval = do_remount(&path, flags, sb_flags, mnt_flags,
 				    data_page);
 	else if (flags & MS_BIND)
 		retval = do_loopback(&path, dev_name, flags & MS_REC);
@@ -2773,7 +2779,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 	else if (flags & MS_MOVE)
 		retval = do_move_mount(&path, dev_name);
 	else
-		retval = do_new_mount(&path, type_page, flags, mnt_flags,
+		retval = do_new_mount(&path, type_page, sb_flags, mnt_flags,
 				      dev_name, data_page);
 dput_out:
 	path_put(&path);
@@ -3223,7 +3229,7 @@ void put_mnt_ns(struct mnt_namespace *ns)
 struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
 {
 	struct vfsmount *mnt;
-	mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
+	mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, data);
 	if (!IS_ERR(mnt)) {
 		/*
 		 * it is a longterm mount, don't release mnt until