path: root/fs/xattr.c

// SPDX-License-Identifier: GPL-2.0-only
/*
  File: fs/xattr.c

  Extended attribute handling.

  Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org>
  Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com>
  Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
 */
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/xattr.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/evm.h>
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fsnotify.h>
#include <linux/audit.h>
#include <linux/vmalloc.h>
#include <linux/posix_acl_xattr.h>

#include <linux/uaccess.h>

#include "internal.h"

static const char *
strcmp_prefix(const char *a, const char *a_prefix)
{
	while (*a_prefix && *a == *a_prefix) {
		a++;
		a_prefix++;
	}
	return *a_prefix ? NULL : a;
}

/*
 * In order to implement different sets of xattr operations for each xattr
 * prefix, a filesystem should create a null-terminated array of struct
 * xattr_handler (one for each prefix) and hang a pointer to it off of the
 * s_xattr field of the superblock.
 */
#define for_each_xattr_handler(handlers, handler)		\
	if (handlers)						\
		for ((handler) = *(handlers)++;			\
			(handler) != NULL;			\
			(handler) = *(handlers)++)

/*
 * Find the xattr_handler with the matching prefix.
 */
static const struct xattr_handler *
xattr_resolve_name(struct inode *inode, const char **name)
{
	const struct xattr_handler **handlers = inode->i_sb->s_xattr;
	const struct xattr_handler *handler;

	if (!(inode->i_opflags & IOP_XATTR)) {
		if (unlikely(is_bad_inode(inode)))
			return ERR_PTR(-EIO);
		return ERR_PTR(-EOPNOTSUPP);
	}
	for_each_xattr_handler(handlers, handler) {
		const char *n;

		n = strcmp_prefix(*name, xattr_prefix(handler));
		if (n) {
			if (!handler->prefix ^ !*n) {
				if (*n)
					continue;
				return ERR_PTR(-EINVAL);
			}
			*name = n;
			return handler;
		}
	}
	return ERR_PTR(-EOPNOTSUPP);
}

/**
 * may_write_xattr - check whether inode allows writing xattr
 * @mnt_userns:	User namespace of the mount the inode was found from
 * @inode: the inode on which to set an xattr
 *
 * Check whether the inode allows writing xattrs. Specifically, we can never
 * set or remove an extended attribute on a read-only filesystem  or on an
 * immutable / append-only inode.
 *
 * We also need to ensure that the inode has a mapping in the mount to
 * not risk writing back invalid i_{g,u}id values.
 *
 * Return: On success zero is returned. On error a negative errno is returned.
 */
int may_write_xattr(struct user_namespace *mnt_userns, struct inode *inode)
{
	if (IS_IMMUTABLE(inode))
		return -EPERM;
	if (IS_APPEND(inode))
		return -EPERM;
	if (HAS_UNMAPPED_ID(mnt_userns, inode))
		return -EPERM;
	return 0;
}

/*
 * Check permissions for extended attribute access.  This is a bit complicated
 * because different namespaces have very different rules.
 */
static int
xattr_permission(struct user_namespace *mnt_userns, struct inode *inode,
		 const char *name, int mask)
{
	if (mask & MAY_WRITE) {
		int ret;

		ret = may_write_xattr(mnt_userns, inode);
		if (ret)
			return ret;
	}

	/*
	 * No restriction for security.* and system.* from the VFS.  Decision
	 * on these is left to the underlying filesystem / security module.
	 */
	if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) ||
	    !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
		return 0;

	/*
	 * The trusted.* namespace can only be accessed by privileged users.
	 */
	if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
		if (!capable(CAP_SYS_ADMIN))
			return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
		return 0;
	}

	/*
	 * In the user.* namespace, only regular files and directories can have
	 * extended attributes. For sticky directories, only the owner and
	 * privileged users can write attributes.
	 */
	if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) {
		if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
			return (mask & MAY_WRITE)