fs: port ->permission() to pass mnt_idmap

Convert to struct mnt_idmap.

Last cycle we merged the necessary infrastructure in
256c8aed2b42 ("fs: introduce dedicated idmap type for mounts").
This is just the conversion to struct mnt_idmap.

Currently we still pass around the plain namespace that was attached to a
mount. This is in general pretty convenient but it makes it easy to
conflate namespaces that are relevant on the filesystem with namespaces
that are relevent on the mount level. Especially for non-vfs developers
without detailed knowledge in this area this can be a potential source for
bugs.

Once the conversion to struct mnt_idmap is done all helpers down to the
really low-level helpers will take a struct mnt_idmap argument instead of
two namespace arguments. This way it becomes impossible to conflate the two
eliminating the possibility of any bugs. All of the vfs and all filesystems
only operate on struct mnt_idmap.

Acked-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>

1 files changed, 27 insertions, 24 deletions

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index f23d0d399b9f..80c7feb30770 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -898,10 +898,11 @@ free_pending:
  *     nfs_async_unlink().
  */
 
-static int btrfs_may_delete(struct user_namespace *mnt_userns,
+static int btrfs_may_delete(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *victim, int isdir)
 {
 	int error;
+	struct user_namespace *mnt_userns = mnt_idmap_owner(idmap);
 
 	if (d_really_is_negative(victim))
 		return -ENOENT;
@@ -909,7 +910,7 @@ static int btrfs_may_delete(struct user_namespace *mnt_userns,
 	BUG_ON(d_inode(victim->d_parent) != dir);
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
-	error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC);
+	error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
 	if (error)
 		return error;
 	if (IS_APPEND(dir))
@@ -933,16 +934,16 @@ static int btrfs_may_delete(struct user_namespace *mnt_userns,
 }
 
 /* copy of may_create in fs/namei.c() */
-static inline int btrfs_may_create(struct user_namespace *mnt_userns,
+static inline int btrfs_may_create(struct mnt_idmap *idmap,
 				   struct inode *dir, struct dentry *child)
 {
 	if (d_really_is_positive(child))
 		return -EEXIST;
 	if (IS_DEADDIR(dir))
 		return -ENOENT;
-	if (!fsuidgid_has_mapping(dir->i_sb, mnt_userns))
+	if (!fsuidgid_has_mapping(dir->i_sb, idmap))
 		return -EOVERFLOW;
-	return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC);
+	return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
 }
 
 /*
@@ -951,7 +952,7 @@ static inline int btrfs_may_create(struct user_namespace *mnt_userns,
  * inside this filesystem so it's quite a bit simpler.
  */
 static noinline int btrfs_mksubvol(const struct path *parent,
-				   struct user_namespace *mnt_userns,
+				   struct mnt_idmap *idmap,
 				   const char *name, int namelen,
 				   struct btrfs_root *snap_src,
 				   bool readonly,
@@ -961,18 +962,19 @@ static noinline int btrfs_mksubvol(const struct path *parent,
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
 	struct dentry *dentry;
 	struct fscrypt_str name_str = FSTR_INIT((char *)name, namelen);
+	struct user_namespace *mnt_userns = mnt_idmap_owner(idmap);
 	int error;
 
 	error = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
 	if (error == -EINTR)
 		return error;
 
-	dentry = lookup_one(mnt_userns, name, parent->dentry, namelen);
+	dentry = lookup_one(idmap, name, parent->dentry, namelen);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto out_unlock;
 
-	error = btrfs_may_create(mnt_userns, dir, dentry);
+	error = btrfs_may_create(idmap, dir, dentry);
 	if (error)
 		goto out_dput;
 
@@ -1007,7 +1009,7 @@ out_unlock:
 }
 
 static noinline int btrfs_mksnapshot(const struct path *parent,
-				   struct user_namespace *mnt_userns,
+				   struct mnt_idmap *idmap,
 				   const char *name, int namelen,
 				   struct btrfs_root *root,
 				   bool readonly,
@@ -1037,7 +1039,7 @@ static noinline int btrfs_mksnapshot(const struct path *parent,
 
 	btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1);
 
-	ret = btrfs_mksubvol(parent, mnt_userns, name, namelen,
+	ret = btrfs_mksubvol(parent, idmap, name, namelen,
 			     root, readonly, inherit);
 out:
 	if (snapshot_force_cow)
@@ -1240,13 +1242,14 @@ out_drop:
 }
 
 static noinline int __btrfs_ioctl_snap_create(struct file *file,
-				struct user_namespace *mnt_userns,
+				struct mnt_idmap *idmap,
 				const char *name, unsigned long fd, int subvol,
 				bool readonly,
 				struct btrfs_qgroup_inherit *inherit)
 {
 	int namelen;
 	int ret = 0;
+	struct user_namespace *mnt_userns = mnt_idmap_owner(idmap);
 
 	if (!S_ISDIR(file_inode(file)->i_mode))
 		return -ENOTDIR;
@@ -1268,7 +1271,7 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file,
 	}
 
 	if (subvol) {
-		ret = btrfs_mksubvol(&file->f_path, mnt_userns, name,
+		ret = btrfs_mksubvol(&file->f_path, idmap, name,
 				     namelen, NULL, readonly, inherit);
 	} else {
 		struct fd src = fdget(fd);
@@ -1290,7 +1293,7 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file,
 			 */
 			ret = -EPERM;
 		} else {
-			ret = btrfs_mksnapshot(&file->f_path, mnt_userns,
+			ret = btrfs_mksnapshot(&file->f_path, idmap,
 					       name, namelen,
 					       BTRFS_I(src_inode)->root,
 					       readonly, inherit);
@@ -1317,7 +1320,7 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
 		return PTR_ERR(vol_args);
 	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 
-	ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file),
+	ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file),
 					vol_args->name, vol_args->fd, subvol,
 					false, NULL);
 
@@ -1377,7 +1380,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 		}
 	}
 
-	ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file),
+	ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file),
 					vol_args->name, vol_args->fd, subvol,
 					readonly, inherit);
 	if (ret)
@@ -1870,7 +1873,7 @@ out:
 	return ret;
 }
 
-static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns,
+static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap,
 				struct inode *inode,
 				struct btrfs_ioctl_ino_lookup_user_args *args)
 {
@@ -1962,7 +1965,7 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns,
 				ret = PTR_ERR(temp_inode);
 				goto out_put;
 			}
-			ret = inode_permission(mnt_userns, temp_inode,
+			ret = inode_permission(idmap, temp_inode,
 					       MAY_READ | MAY_EXEC);
 			iput(temp_inode);
 			if (ret) {
@@ -2101,7 +2104,7 @@ static int btrfs_ioctl_ino_lookup_user(struct file *file, void __user *argp)
 		return -EACCES;
 	}
 
-	ret = btrfs_search_path_in_tree_user(file_mnt_user_ns(file), inode, args);
+	ret = btrfs_search_path_in_tree_user(file_mnt_idmap(file), inode, args);
 
 	if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
 		ret = -EFAULT;
@@ -2335,7 +2338,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	struct btrfs_root *dest = NULL;
 	struct btrfs_ioctl_vol_args *vol_args = NULL;
 	struct btrfs_ioctl_vol_args_v2 *vol_args2 = NULL;
-	struct user_namespace *mnt_userns = file_mnt_user_ns(file);
+	struct mnt_idmap *idmap = file_mnt_idmap(file);
 	char *subvol_name, *subvol_name_ptr = NULL;
 	int subvol_namelen;
 	int err = 0;
@@ -2428,7 +2431,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 			 * anywhere in the filesystem the user wouldn't be able
 			 * to delete without an idmapped mount.
 			 */
-			if (old_dir != dir && mnt_userns != &init_user_ns) {
+			if (old_dir != dir && idmap != &nop_mnt_idmap) {
 				err = -EOPNOTSUPP;
 				goto free_parent;
 			}
@@ -2471,7 +2474,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	err = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
 	if (err == -EINTR)
 		goto free_subvol_name;
-	dentry = lookup_one(mnt_userns, subvol_name, parent, subvol_namelen);
+	dentry = lookup_one(idmap, subvol_name, parent, subvol_namelen);
 	if (IS_ERR(dentry)) {
 		err = PTR_ERR(dentry);
 		goto out_unlock_dir;
@@ -2513,13 +2516,13 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		if (root == dest)
 			goto out_dput;
 
-		err = inode_permission(mnt_userns, inode, MAY_WRITE | MAY_EXEC);
+		err = inode_permission(idmap, inode, MAY_WRITE | MAY_EXEC);
 		if (err)
 			goto out_dput;
 	}
 
 	/* check if subvolume may be deleted by a user */
-	err = btrfs_may_delete(mnt_userns, dir, dentry, 1);
+	err = btrfs_may_delete(idmap, dir, dentry, 1);
 	if (err)
 		goto out_dput;
 
@@ -2582,7 +2585,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 		 * running and allows defrag on files open in read-only mode.
 		 */
 		if (!capable(CAP_SYS_ADMIN) &&
-		    inode_permission(&init_user_ns, inode, MAY_WRITE)) {
+		    inode_permission(&nop_mnt_idmap, inode, MAY_WRITE)) {
 			ret = -EPERM;
 			goto out;
 		}