/*
 *	jfs_permission()
 *
 * modified vfs_permission to check posix acl
 */
int jfs_permission(struct inode * inode, int mask, struct nameidata *nd)
{
    umode_t mode = inode->i_mode;
    struct jfs_inode_info *ji = JFS_IP(inode);

    if (mask & MAY_WRITE) {
        /*
         * Nobody gets write access to a read-only fs.
         */
        if (IS_RDONLY(inode) &&
                (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
            return -EROFS;

        /*
         * Nobody gets write access to an immutable file.
         */
        if (IS_IMMUTABLE(inode))
            return -EACCES;
    }

    if (current->fsuid == inode->i_uid) {
        mode >>= 6;
        goto check_mode;
    }

static int utimes_common(struct path *path, struct timespec *times)
{
	int error;
	struct iattr newattrs;
	struct inode *inode = path->dentry->d_inode;

	error = mnt_want_write(path->mnt);
	if (error)
		goto out;

	if (times && times[0].tv_nsec == UTIME_NOW &&
		     times[1].tv_nsec == UTIME_NOW)
		times = NULL;

	newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
	if (times) {
		if (times[0].tv_nsec == UTIME_OMIT)
			newattrs.ia_valid &= ~ATTR_ATIME;
		else if (times[0].tv_nsec != UTIME_NOW) {
			newattrs.ia_atime.tv_sec = times[0].tv_sec;
			newattrs.ia_atime.tv_nsec = times[0].tv_nsec;
			newattrs.ia_valid |= ATTR_ATIME_SET;
		}

		if (times[1].tv_nsec == UTIME_OMIT)
			newattrs.ia_valid &= ~ATTR_MTIME;
		else if (times[1].tv_nsec != UTIME_NOW) {
			newattrs.ia_mtime.tv_sec = times[1].tv_sec;
			newattrs.ia_mtime.tv_nsec = times[1].tv_nsec;
			newattrs.ia_valid |= ATTR_MTIME_SET;
		}
		/*
		 * Tell inode_change_ok(), that this is an explicit time
		 * update, even if neither ATTR_ATIME_SET nor ATTR_MTIME_SET
		 * were used.
		 */
		newattrs.ia_valid |= ATTR_TIMES_SET;
	} else {
		/*
		 * If times is NULL (or both times are UTIME_NOW),
		 * then we need to check permissions, because
		 * inode_change_ok() won't do it.
		 */
		error = -EACCES;
                if (IS_IMMUTABLE(inode))
			goto mnt_drop_write_and_out;

#ifdef CONFIG_FS_SYNO_ACL
		if (IS_SYNOACL(inode)) {
			if (inode->i_op->syno_permission(path->dentry, MAY_WRITE_ATTR | MAY_WRITE_EXT_ATTR)) {
				goto mnt_drop_write_and_out;
			}
		} else
#endif
		if (!inode_owner_or_capable(inode)) {
			error = inode_permission(inode, MAY_WRITE);
			if (error)
				goto mnt_drop_write_and_out;
		}
	}
	mutex_lock(&inode->i_mutex);
	error = notify_change(path->dentry, &newattrs);
	mutex_unlock(&inode->i_mutex);

mnt_drop_write_and_out:
	mnt_drop_write(path->mnt);
out:
	return error;
}

int
xfs_open_by_handle(
	struct file		*parfilp,
	xfs_fsop_handlereq_t	*hreq)
{
	const struct cred	*cred = current_cred();
	int			error;
	int			fd;
	int			permflag;
	struct file		*filp;
	struct inode		*inode;
	struct dentry		*dentry;
	fmode_t			fmode;
	struct path		path;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	dentry = xfs_handlereq_to_dentry(parfilp, hreq);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);
	inode = d_inode(dentry);

	/* Restrict xfs_open_by_handle to directories & regular files. */
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) {
		error = -EPERM;
		goto out_dput;
	}

#if BITS_PER_LONG != 32
	hreq->oflags |= O_LARGEFILE;
#endif

	permflag = hreq->oflags;
	fmode = OPEN_FMODE(permflag);
	if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) &&
	    (fmode & FMODE_WRITE) && IS_APPEND(inode)) {
		error = -EPERM;
		goto out_dput;
	}

	if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
		error = -EACCES;
		goto out_dput;
	}

	/* Can't write directories. */
	if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) {
		error = -EISDIR;
		goto out_dput;
	}

	fd = get_unused_fd_flags(0);
	if (fd < 0) {
		error = fd;
		goto out_dput;
	}

	path.mnt = parfilp->f_path.mnt;
	path.dentry = dentry;
	filp = dentry_open(&path, hreq->oflags, cred);
	dput(dentry);
	if (IS_ERR(filp)) {
		put_unused_fd(fd);
		return PTR_ERR(filp);
	}

	if (S_ISREG(inode->i_mode)) {
		filp->f_flags |= O_NOATIME;
		filp->f_mode |= FMODE_NOCMTIME;
	}

	fd_install(fd, filp);
	return fd;

 out_dput:
	dput(dentry);
	return error;
}

static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
		     struct dentry *dentry)
{
	struct gfs2_inode *dip = GFS2_I(dir);
	struct gfs2_sbd *sdp = GFS2_SB(dir);
	struct inode *inode = old_dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder ghs[2];
	int alloc_required;
	int error;

	if (S_ISDIR(inode->i_mode))
		return -EPERM;

	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);

	error = gfs2_glock_nq(ghs); /* parent */
	if (error)
		goto out_parent;

	error = gfs2_glock_nq(ghs + 1); /* child */
	if (error)
		goto out_child;

	error = -ENOENT;
	if (inode->i_nlink == 0)
		goto out_gunlock;

	error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
	if (error)
		goto out_gunlock;

	error = gfs2_dir_check(dir, &dentry->d_name, NULL);
	switch (error) {
	case -ENOENT:
		break;
	case 0:
		error = -EEXIST;
	default:
		goto out_gunlock;
	}

	error = -EINVAL;
	if (!dip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EFBIG;
	if (dip->i_entries == (u32)-1)
		goto out_gunlock;
	error = -EPERM;
	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		goto out_gunlock;
	error = -EINVAL;
	if (!ip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EMLINK;
	if (ip->i_inode.i_nlink == (u32)-1)
		goto out_gunlock;

	alloc_required = error = gfs2_diradd_alloc_required(dir, &dentry->d_name);
	if (error < 0)
		goto out_gunlock;
	error = 0;

	if (alloc_required) {
		struct gfs2_qadata *qa = gfs2_qadata_get(dip);

		if (!qa) {
			error = -ENOMEM;
			goto out_gunlock;
		}

		error = gfs2_quota_lock_check(dip);
		if (error)
			goto out_alloc;

		error = gfs2_inplace_reserve(dip, sdp->sd_max_dirres);
		if (error)
			goto out_gunlock_q;

		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
					 gfs2_rg_blocks(dip) +
					 2 * RES_DINODE + RES_STATFS +
					 RES_QUOTA, 0);
		if (error)
			goto out_ipres;
	} else {
		error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
		if (error)
			goto out_ipres;
	}

	error = gfs2_dir_add(dir, &dentry->d_name, ip, IF2DT(inode->i_mode));
	if (error)
		goto out_end_trans;

	error = gfs2_change_nlink(ip, +1);

out_end_trans:
	gfs2_trans_end(sdp);
//.........这里部分代码省略.........

int
xfs_open_by_handle(
	struct file		*parfilp,
	xfs_fsop_handlereq_t	*hreq)
{
	const struct cred	*cred = current_cred();
	int			error;
	int			fd;
	int			permflag;
	struct file		*filp;
	struct inode		*inode;
	struct dentry		*dentry;

	if (!capable(CAP_SYS_ADMIN))
		return -XFS_ERROR(EPERM);

	dentry = xfs_handlereq_to_dentry(parfilp, hreq);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);
	inode = dentry->d_inode;

	/* Restrict xfs_open_by_handle to directories & regular files. */
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) {
		error = -XFS_ERROR(EPERM);
		goto out_dput;
	}

#if BITS_PER_LONG != 32
	hreq->oflags |= O_LARGEFILE;
#endif

	/* Put open permission in namei format. */
	permflag = hreq->oflags;
	if ((permflag+1) & O_ACCMODE)
		permflag++;
	if (permflag & O_TRUNC)
		permflag |= 2;

	if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) &&
	    (permflag & FMODE_WRITE) && IS_APPEND(inode)) {
		error = -XFS_ERROR(EPERM);
		goto out_dput;
	}

	if ((permflag & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
		error = -XFS_ERROR(EACCES);
		goto out_dput;
	}

	/* Can't write directories. */
	if (S_ISDIR(inode->i_mode) && (permflag & FMODE_WRITE)) {
		error = -XFS_ERROR(EISDIR);
		goto out_dput;
	}

	fd = get_unused_fd();
	if (fd < 0) {
		error = fd;
		goto out_dput;
	}

	filp = dentry_open(dentry, mntget(parfilp->f_path.mnt),
			   hreq->oflags, cred);
	if (IS_ERR(filp)) {
		put_unused_fd(fd);
		return PTR_ERR(filp);
	}

	if (inode->i_mode & S_IFREG) {
		filp->f_flags |= O_NOATIME;
		filp->f_mode |= FMODE_NOCMTIME;
	}

	fd_install(fd, filp);
	return fd;

 out_dput:
	dput(dentry);
	return error;
}

//.........这里部分代码省略.........
	error = gfs2_glock_nq(ghs); /* parent */
	if (error)
		goto out_parent;

	error = gfs2_glock_nq(ghs + 1); /* child */
	if (error)
		goto out_child;

	error = -ENOENT;
	if (inode->i_nlink == 0)
		goto out_gunlock;

	error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
	if (error)
		goto out_gunlock;

	error = gfs2_dir_check(dir, &dentry->d_name, NULL);
	switch (error) {
	case -ENOENT:
		break;
	case 0:
		error = -EEXIST;
	default:
		goto out_gunlock;
	}

	error = -EINVAL;
	if (!dip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EFBIG;
	if (dip->i_entries == (u32)-1)
		goto out_gunlock;
	error = -EPERM;
	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		goto out_gunlock;
	error = -EINVAL;
	if (!ip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EMLINK;
	if (ip->i_inode.i_nlink == (u32)-1)
		goto out_gunlock;

	error = gfs2_diradd_alloc_required(dir, &dentry->d_name, &da);
	if (error < 0)
		goto out_gunlock;

	if (da.nr_blocks) {
		struct gfs2_alloc_parms ap = { .target = da.nr_blocks, };
		error = gfs2_quota_lock_check(dip);
		if (error)
			goto out_gunlock;

		error = gfs2_inplace_reserve(dip, &ap);
		if (error)
			goto out_gunlock_q;

		error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, &da, 2), 0);
		if (error)
			goto out_ipres;
	} else {
		error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
		if (error)
			goto out_ipres;
	}

	error = gfs2_meta_inode_buffer(ip, &dibh);

STATIC int
xfs_open_by_handle(
	xfs_mount_t		*mp,
	unsigned long		arg,
	struct file		*parfilp,
	struct inode		*parinode)
{
	int			error;
	int			new_fd;
	int			permflag;
	struct file		*filp;
	struct inode		*inode;
	struct dentry		*dentry;
	vnode_t			*vp;
	xfs_fsop_handlereq_t	hreq;

	error = xfs_vget_fsop_handlereq(mp, parinode, CAP_SYS_ADMIN, arg,
					sizeof(xfs_fsop_handlereq_t),
					&hreq, &vp, &inode);
	if (error)
		return -error;

	/* Restrict xfs_open_by_handle to directories & regular files. */
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) {
		iput(inode);
		return -XFS_ERROR(EINVAL);
	}

#if BITS_PER_LONG != 32
	hreq.oflags |= O_LARGEFILE;
#endif
	/* Put open permission in namei format. */
	permflag = hreq.oflags;
	if ((permflag+1) & O_ACCMODE)
		permflag++;
	if (permflag & O_TRUNC)
		permflag |= 2;

	if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) &&
	    (permflag & FMODE_WRITE) && IS_APPEND(inode)) {
		iput(inode);
		return -XFS_ERROR(EPERM);
	}

	if ((permflag & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
		iput(inode);
		return -XFS_ERROR(EACCES);
	}

	/* Can't write directories. */
	if ( S_ISDIR(inode->i_mode) && (permflag & FMODE_WRITE)) {
		iput(inode);
		return -XFS_ERROR(EISDIR);
	}

	if ((new_fd = get_unused_fd()) < 0) {
		iput(inode);
		return new_fd;
	}

	dentry = d_alloc_anon(inode);
	if (dentry == NULL) {
		iput(inode);
		put_unused_fd(new_fd);
		return -XFS_ERROR(ENOMEM);
	}

	/* Ensure umount returns EBUSY on umounts while this file is open. */
	mntget(parfilp->f_vfsmnt);

	/* Create file pointer. */
	filp = dentry_open(dentry, parfilp->f_vfsmnt, hreq.oflags);
	if (IS_ERR(filp)) {
		put_unused_fd(new_fd);
		return -XFS_ERROR(-PTR_ERR(filp));
	}
	if (inode->i_mode & S_IFREG)
		filp->f_op = &linvfs_invis_file_operations;

	fd_install(new_fd, filp);
	return new_fd;
}

int notify_change(struct dentry * dentry, struct iattr * attr)
{
	struct inode *inode = dentry->d_inode;
	umode_t mode = inode->i_mode;
	int error;
	struct timespec now;
	unsigned int ia_valid = attr->ia_valid;

	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));

	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
		if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
			return -EPERM;
	}

	if ((ia_valid & ATTR_SIZE) && IS_I_VERSION(inode)) {
		if (attr->ia_size != inode->i_size)
			inode_inc_iversion(inode);
	}

	if ((ia_valid & ATTR_MODE)) {
		umode_t amode = attr->ia_mode;
		/* Flag setting protected by i_mutex */
		if (is_sxid(amode))
			inode->i_flags &= ~S_NOSEC;
	}

	now = current_fs_time(inode->i_sb);

	attr->ia_ctime = now;
	if (!(ia_valid & ATTR_ATIME_SET))
		attr->ia_atime = now;
	if (!(ia_valid & ATTR_MTIME_SET))
		attr->ia_mtime = now;
	if (ia_valid & ATTR_KILL_PRIV) {
		attr->ia_valid &= ~ATTR_KILL_PRIV;
		ia_valid &= ~ATTR_KILL_PRIV;
		error = security_inode_need_killpriv(dentry);
		if (error > 0)
			error = security_inode_killpriv(dentry);
		if (error)
			return error;
	}

	/*
	 * We now pass ATTR_KILL_S*ID to the lower level setattr function so
	 * that the function has the ability to reinterpret a mode change
	 * that's due to these bits. This adds an implicit restriction that
	 * no function will ever call notify_change with both ATTR_MODE and
	 * ATTR_KILL_S*ID set.
	 */
	if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) &&
	    (ia_valid & ATTR_MODE))
		BUG();

	if (ia_valid & ATTR_KILL_SUID) {
		if (mode & S_ISUID) {
			ia_valid = attr->ia_valid |= ATTR_MODE;
			attr->ia_mode = (inode->i_mode & ~S_ISUID);
		}
	}
	if (ia_valid & ATTR_KILL_SGID) {
		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
			if (!(ia_valid & ATTR_MODE)) {
				ia_valid = attr->ia_valid |= ATTR_MODE;
				attr->ia_mode = inode->i_mode;
			}
			attr->ia_mode &= ~S_ISGID;
		}
	}
	if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID)))
		return 0;

	error = security_inode_setattr(dentry, attr);
	if (error)
		return error;

	if (inode->i_op->setattr)
		error = inode->i_op->setattr(dentry, attr);
	else
		error = simple_setattr(dentry, attr);

	if (!error) {
		fsnotify_change(dentry, ia_valid);
		ima_inode_post_setattr(dentry);
		evm_inode_post_setattr(dentry, ia_valid);
	}

	return error;
}

int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	long ret;

	if (offset < 0 || len <= 0)
		return -EINVAL;

	/* Return error if mode is not supported */
	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
		return -EOPNOTSUPP;

	/* Punch hole must have keep size set */
	if ((mode & FALLOC_FL_PUNCH_HOLE) &&
	    !(mode & FALLOC_FL_KEEP_SIZE))
		return -EOPNOTSUPP;

	if (!(file->f_mode & FMODE_WRITE))
		return -EBADF;

	/* It's not possible punch hole on append only file */
	if (mode & FALLOC_FL_PUNCH_HOLE && IS_APPEND(inode))
		return -EPERM;

	if (IS_IMMUTABLE(inode))
		return -EPERM;

	/*
	 * Revalidate the write permissions, in case security policy has
	 * changed since the files were opened.
	 */
	ret = security_file_permission(file, MAY_WRITE);
	if (ret)
		return ret;

	ret = provenance_file_permission(file, MAY_WRITE);
	if (ret)
		return ret;

	if (S_ISFIFO(inode->i_mode))
		return -ESPIPE;

	/*
	 * Let individual file system decide if it supports preallocation
	 * for directories or not.
	 */
	if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
		return -ENODEV;

	/* Check for wrap through zero too */
	if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
		return -EFBIG;

	if (!inode->i_op->fallocate)
		return -EOPNOTSUPP;

	sb_start_write(inode->i_sb);
	ret = inode->i_op->fallocate(inode, mode, offset, len);
	sb_end_write(inode->i_sb);
	return ret;
}

/* If times==NULL, set access and modification to current time,
 * must be owner or have write permission.
 * Else, update from *times, must be owner or super user.
 */
long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags)
{
	int error;
	struct nameidata nd;
	struct dentry *dentry;
	struct inode *inode;
	struct iattr newattrs;
	struct file *f = NULL;

	error = -EINVAL;
	if (times && (!nsec_valid(times[0].tv_nsec) ||
		      !nsec_valid(times[1].tv_nsec))) {
		goto out;
	}

	if (flags & ~AT_SYMLINK_NOFOLLOW)
		goto out;

	if (filename == NULL && dfd != AT_FDCWD) {
		error = -EINVAL;
		if (flags & AT_SYMLINK_NOFOLLOW)
			goto out;

		error = -EBADF;
		f = fget(dfd);
		if (!f)
			goto out;
		dentry = f->f_path.dentry;
	} else {
		error = __user_walk_fd(dfd, filename, (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW, &nd);
		if (error)
			goto out;

		dentry = nd.dentry;
	}

	inode = dentry->d_inode;

	error = -EROFS;
	if (IS_RDONLY(inode))
		goto dput_and_out;

	/* Don't worry, the checks are done in inode_change_ok() */
	newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
	if (times) {
		error = -EPERM;
                if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
                        goto dput_and_out;

		if (times[0].tv_nsec == UTIME_OMIT)
			newattrs.ia_valid &= ~ATTR_ATIME;
		else if (times[0].tv_nsec != UTIME_NOW) {
			newattrs.ia_atime.tv_sec = times[0].tv_sec;
			newattrs.ia_atime.tv_nsec = times[0].tv_nsec;
			newattrs.ia_valid |= ATTR_ATIME_SET;
		}

		if (times[1].tv_nsec == UTIME_OMIT)
			newattrs.ia_valid &= ~ATTR_MTIME;
		else if (times[1].tv_nsec != UTIME_NOW) {
			newattrs.ia_mtime.tv_sec = times[1].tv_sec;
			newattrs.ia_mtime.tv_nsec = times[1].tv_nsec;
			newattrs.ia_valid |= ATTR_MTIME_SET;
		}
	} else {
		error = -EACCES;
                if (IS_IMMUTABLE(inode))
                        goto dput_and_out;

		if (!is_owner_or_cap(inode)) {
			if (f) {
				if (!(f->f_mode & FMODE_WRITE))
					goto dput_and_out;
			} else {
				error = vfs_permission(&nd, MAY_WRITE);
				if (error)
					goto dput_and_out;
			}
		}
	}
	mutex_lock(&inode->i_mutex);
	error = notify_change(dentry, &newattrs);
	mutex_unlock(&inode->i_mutex);
dput_and_out:
	if (f)
		fput(f);
	else
		path_release(&nd);
out:
	return error;
}

int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
	struct inode *inode = file_inode(file);
	long ret;

	if (offset < 0 || len <= 0)
		return -EINVAL;

	/* Return error if mode is not supported */
	if (mode & ~FALLOC_FL_SUPPORTED_MASK)
		return -EOPNOTSUPP;

	/* Punch hole and zero range are mutually exclusive */
	if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) ==
	    (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
		return -EOPNOTSUPP;

	/* Punch hole must have keep size set */
	if ((mode & FALLOC_FL_PUNCH_HOLE) &&
	    !(mode & FALLOC_FL_KEEP_SIZE))
		return -EOPNOTSUPP;

	/* Collapse range should only be used exclusively. */
	if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
	    (mode & ~FALLOC_FL_COLLAPSE_RANGE))
		return -EINVAL;

	/* Insert range should only be used exclusively. */
	if ((mode & FALLOC_FL_INSERT_RANGE) &&
	    (mode & ~FALLOC_FL_INSERT_RANGE))
		return -EINVAL;

	/* Unshare range should only be used with allocate mode. */
	if ((mode & FALLOC_FL_UNSHARE_RANGE) &&
	    (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE)))
		return -EINVAL;

	if (!(file->f_mode & FMODE_WRITE))
		return -EBADF;

	/*
	 * We can only allow pure fallocate on append only files
	 */
	if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode))
		return -EPERM;

	if (IS_IMMUTABLE(inode))
		return -EPERM;

	/*
	 * We cannot allow any fallocate operation on an active swapfile
	 */
	if (IS_SWAPFILE(inode))
		return -ETXTBSY;

	/*
	 * Revalidate the write permissions, in case security policy has
	 * changed since the files were opened.
	 */
	ret = security_file_permission(file, MAY_WRITE);
	if (ret)
		return ret;

	if (S_ISFIFO(inode->i_mode))
		return -ESPIPE;

	if (S_ISDIR(inode->i_mode))
		return -EISDIR;

	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
		return -ENODEV;

	/* Check for wrap through zero too */
	if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
		return -EFBIG;

	if (!file->f_op->fallocate)
		return -EOPNOTSUPP;

	file_start_write(file);
	ret = file->f_op->fallocate(file, mode, offset, len);

	/*
	 * Create inotify and fanotify events.
	 *
	 * To keep the logic simple always create events if fallocate succeeds.
	 * This implies that events are even created if the file size remains
	 * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE.
	 */
	if (ret == 0)
		fsnotify_modify(file);

	file_end_write(file);
	return ret;
}

//.........这里部分代码省略.........
	error = gfs2_glock_nq(ghs); /* parent */
	if (error)
		goto out_parent;

	error = gfs2_glock_nq(ghs + 1); /* child */
	if (error)
		goto out_child;

	error = -ENOENT;
	if (inode->i_nlink == 0)
		goto out_gunlock;

	error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
	if (error)
		goto out_gunlock;

	error = gfs2_dir_check(dir, &dentry->d_name, NULL);
	switch (error) {
	case -ENOENT:
		break;
	case 0:
		error = -EEXIST;
	default:
		goto out_gunlock;
	}

	error = -EINVAL;
	if (!dip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EFBIG;
	if (dip->i_entries == (u32)-1)
		goto out_gunlock;
	error = -EPERM;
	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		goto out_gunlock;
	error = -EINVAL;
	if (!ip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EMLINK;
	if (ip->i_inode.i_nlink == (u32)-1)
		goto out_gunlock;

	alloc_required = error = gfs2_diradd_alloc_required(dir, &dentry->d_name);
	if (error < 0)
		goto out_gunlock;
	error = 0;

	if (alloc_required) {
		struct gfs2_alloc *al = gfs2_alloc_get(dip);
		if (!al) {
			error = -ENOMEM;
			goto out_gunlock;
		}

		error = gfs2_quota_lock_check(dip);
		if (error)
			goto out_alloc;

		al->al_requested = sdp->sd_max_dirres;

		error = gfs2_inplace_reserve(dip);
		if (error)
			goto out_gunlock_q;

		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
					 gfs2_rg_blocks(al) +

static int h_permission(struct inode *h_inode, int mask,
			struct path *h_path, int brperm)
{
	int err;
	const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));

	err = -EPERM;
	if (write_mask && IS_IMMUTABLE(h_inode))
		goto out;

	err = -EACCES;
	if (((mask & MAY_EXEC)
	     && S_ISREG(h_inode->i_mode)
	     && (path_noexec(h_path)
		 || !(h_inode->i_mode & S_IXUGO))))
		goto out;

	/*
	 * - skip the lower fs test in the case of write to ro branch.
	 * - nfs dir permission write check is optimized, but a policy for
	 *   link/rename requires a real check.
	 * - nfs always sets SB_POSIXACL regardless its mount option 'noacl.'
	 *   in this case, generic_permission() returns -EOPNOTSUPP.
	 */
	if ((write_mask && !au_br_writable(brperm))
	    || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode)
		&& write_mask && !(mask & MAY_READ))
	    || !h_inode->i_op->permission) {
		/* AuLabel(generic_permission); */
		/* AuDbg("get_acl %pf\n", h_inode->i_op->get_acl); */
		err = generic_permission(h_inode, mask);
		if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode))
			err = h_inode->i_op->permission(h_inode, mask);
		AuTraceErr(err);
	} else {
		/* AuLabel(h_inode->permission); */
		err = h_inode->i_op->permission(h_inode, mask);
		AuTraceErr(err);
	}

	if (!err)
		err = devcgroup_inode_permission(h_inode, mask);
	if (!err)
		err = security_inode_permission(h_inode, mask);

#if 0
	if (!err) {
		/* todo: do we need to call ima_path_check()? */
		struct path h_path = {
			.dentry	=
			.mnt	= h_mnt
		};
		err = ima_path_check(&h_path,
				     mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
				     IMA_COUNT_LEAVE);
	}
#endif

out:
	return err;
}

STATIC int
xfs_open_by_handle(
	xfs_mount_t		*mp,
	void			__user *arg,
	struct file		*parfilp,
	struct inode		*parinode)
{
	int			error;
	int			new_fd;
	int			permflag;
	struct file		*filp;
	struct inode		*inode;
	struct dentry		*dentry;
	xfs_fsop_handlereq_t	hreq;

	if (!capable(CAP_SYS_ADMIN))
		return -XFS_ERROR(EPERM);
	if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
		return -XFS_ERROR(EFAULT);

	error = xfs_vget_fsop_handlereq(mp, parinode, &hreq, &inode);
	if (error)
		return -error;

	/* Restrict xfs_open_by_handle to directories & regular files. */
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) {
		iput(inode);
		return -XFS_ERROR(EINVAL);
	}

#if BITS_PER_LONG != 32
	hreq.oflags |= O_LARGEFILE;
#endif
	/* Put open permission in namei format. */
	permflag = hreq.oflags;
	if ((permflag+1) & O_ACCMODE)
		permflag++;
	if (permflag & O_TRUNC)
		permflag |= 2;

	if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) &&
	    (permflag & FMODE_WRITE) && IS_APPEND(inode)) {
		iput(inode);
		return -XFS_ERROR(EPERM);
	}

	if ((permflag & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
		iput(inode);
		return -XFS_ERROR(EACCES);
	}

	/* Can't write directories. */
	if ( S_ISDIR(inode->i_mode) && (permflag & FMODE_WRITE)) {
		iput(inode);
		return -XFS_ERROR(EISDIR);
	}

	if ((new_fd = get_unused_fd()) < 0) {
		iput(inode);
		return new_fd;
	}

	dentry = d_obtain_alias(inode);
	if (IS_ERR(dentry)) {
		put_unused_fd(new_fd);
		return PTR_ERR(dentry);
	}

	/* Ensure umount returns EBUSY on umounts while this file is open. */
	mntget(parfilp->f_path.mnt);

	/* Create file pointer. */
	filp = dentry_open(dentry, parfilp->f_path.mnt, hreq.oflags);
	if (IS_ERR(filp)) {
		put_unused_fd(new_fd);
		return -XFS_ERROR(-PTR_ERR(filp));
	}
	if (inode->i_mode & S_IFREG) {
		/* invisible operation should not change atime */
		filp->f_flags |= O_NOATIME;
		filp->f_op = &xfs_invis_file_operations;
	}

	fd_install(new_fd, filp);
	return new_fd;
}

int ovl_permission(struct inode *inode, int mask)
{
	struct ovl_entry *oe;
	struct dentry *alias = NULL;
	struct inode *realinode;
	struct dentry *realdentry;
	bool is_upper;
	int err;

	if (S_ISDIR(inode->i_mode)) {
		oe = inode->i_private;
	} else if (mask & MAY_NOT_BLOCK) {
		return -ECHILD;
	} else {
		/*
		 * For non-directories find an alias and get the info
		 * from there.
		 */
		spin_lock(&inode->i_lock);
		if (WARN_ON(list_empty(&inode->i_dentry))) {
			spin_unlock(&inode->i_lock);
			return -ENOENT;
		}
		alias = list_entry(inode->i_dentry.next,
				   struct dentry, d_alias);
		dget(alias);
		spin_unlock(&inode->i_lock);
		oe = alias->d_fsdata;
	}

	realdentry = ovl_entry_real(oe, &is_upper);

	/* Careful in RCU walk mode */
	realinode = ACCESS_ONCE(realdentry->d_inode);
	if (!realinode) {
		WARN_ON(!(mask & MAY_NOT_BLOCK));
		err = -ENOENT;
		goto out_dput;
	}

	if (mask & MAY_WRITE) {
		umode_t mode = realinode->i_mode;

		/*
		 * Writes will always be redirected to upper layer, so
		 * ignore lower layer being read-only.
		 *
		 * If the overlay itself is read-only then proceed
		 * with the permission check, don't return EROFS.
		 * This will only happen if this is the lower layer of
		 * another overlayfs.
		 *
		 * If upper fs becomes read-only after the overlay was
		 * constructed return EROFS to prevent modification of
		 * upper layer.
		 */
		err = -EROFS;
		if (is_upper && !IS_RDONLY(inode) && IS_RDONLY(realinode) &&
		    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
			goto out_dput;

		/*
		 * Nobody gets write access to an immutable file.
		 */
		err = -EACCES;
		if (IS_IMMUTABLE(realinode))
			goto out_dput;
	}

	if (realinode->i_op->permission)
		err = realinode->i_op->permission(realinode, mask);
	else
		err = generic_permission(realinode, mask);

	if (!err)
		err = devcgroup_inode_permission(realinode, mask);
	if (!err)
		err = security_inode_permission(realinode, mask);
out_dput:
	dput(alias);
	return err;
}

int pvfs2_permission(struct inode *inode, int mask, struct nameidata *nd)
#endif
{
#ifdef HAVE_CURRENT_FSUID
    int fsuid = current_fsuid();
#else
    int fsuid = current->fsuid;
#endif

#ifdef HAVE_GENERIC_PERMISSION
    int ret;

    ret = generic_permission(inode, mask, pvfs2_check_acl);
    if (ret != 0)
    {
        gossip_debug(GOSSIP_ACL_DEBUG, "pvfs2_permission failed: inode: %llu mask = %o"
                "mode = %o current->fsuid = %d "
                "inode->i_uid = %d, inode->i_gid = %d "
                "in_group_p = %d "
                "(ret = %d)\n",
                llu(get_handle_from_ino(inode)), mask, inode->i_mode, fsuid, 
                inode->i_uid, inode->i_gid, 
                in_group_p(inode->i_gid),
                ret);
        gossip_debug(GOSSIP_ACL_DEBUG, "pvfs2_permission: mode [%o] & mask [%o] "
                " & S_IRWXO [%o] = %o == mask [%o]?\n", 
                inode->i_mode, mask, S_IRWXO, 
                (inode->i_mode & mask & S_IRWXO), mask);
        gossip_debug(GOSSIP_ACL_DEBUG, "pvfs2_permission: did we check ACL's? (mode & S_IRWXG = %d)\n",
                inode->i_mode & S_IRWXG);
    }
    else {
        gossip_debug(GOSSIP_ACL_DEBUG, "pvfs2_permission succeeded on inode %llu\n",
                llu(get_handle_from_ino(inode)));
    }
    return ret;
#else
    /* We sort of duplicate the code below from generic_permission. */
    int mode = inode->i_mode;
    int error;

    gossip_debug(GOSSIP_ACL_DEBUG, "pvfs2_permission: inode: %llu mask = %o"
            "mode = %o current->fsuid = %d "
            "inode->i_uid = %d, inode->i_gid = %d"
            "in_group_p = %d\n", 
            llu(get_handle_from_ino(inode)), mask, mode, fsuid,
            inode->i_uid, inode->i_gid,
            in_group_p(inode->i_gid));

    /* No write access on a rdonly FS */
    if ((mask & MAY_WRITE) && IS_RDONLY(inode) &&
            (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
    {
        gossip_debug(GOSSIP_ACL_DEBUG, "pvfs2_permission: cannot write to a "
                "read-only-file-system!\n");
        return -EROFS;
    }
    /* No write access to any immutable files */
    if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode)) 
    {
        gossip_err("pvfs2_permission: cannot write to an immutable file!\n");
        return -EACCES;
    }
    if (fsuid == inode->i_uid) 
    {
        mode >>= 6;
    }

//.........这里部分代码省略.........
	error = gfs2_glock_nq(ghs); /* parent */
	if (error)
		goto out_parent;

	error = gfs2_glock_nq(ghs + 1); /* child */
	if (error)
		goto out_child;

	error = -ENOENT;
	if (inode->i_nlink == 0)
		goto out_gunlock;

	error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
	if (error)
		goto out_gunlock;

	error = gfs2_dir_check(dir, &dentry->d_name, NULL);
	switch (error) {
	case -ENOENT:
		break;
	case 0:
		error = -EEXIST;
	default:
		goto out_gunlock;
	}

	error = -EINVAL;
	if (!dip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EFBIG;
	if (dip->i_entries == (u32)-1)
		goto out_gunlock;
	error = -EPERM;
	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		goto out_gunlock;
	error = -EINVAL;
	if (!ip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EMLINK;
	if (ip->i_inode.i_nlink == (u32)-1)
		goto out_gunlock;

	error = gfs2_diradd_alloc_required(dir, &dentry->d_name, &da);
	if (error < 0)
		goto out_gunlock;

	if (da.nr_blocks) {
		struct gfs2_alloc_parms ap = { .target = da.nr_blocks, };
		error = gfs2_quota_lock_check(dip, &ap);
		if (error)
			goto out_gunlock;

		error = gfs2_inplace_reserve(dip, &ap);
		if (error)
			goto out_gunlock_q;

		error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, &da, 2), 0);
		if (error)
			goto out_ipres;
	} else {
		error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
		if (error)
			goto out_ipres;
	}

	error = gfs2_meta_inode_buffer(ip, &dibh);

STATIC int
xfs_attrmulti_by_handle(
	xfs_mount_t		*mp,
	unsigned long		arg,
	struct file		*parfilp,
	struct inode		*parinode)
{
	int			error;
	xfs_attr_multiop_t	*ops;
	xfs_fsop_attrmulti_handlereq_t am_hreq;
	struct inode		*inode;
	vnode_t			*vp;
	unsigned int		i, size;

	error = xfs_vget_fsop_handlereq(mp, parinode, CAP_SYS_ADMIN, arg,
					sizeof(xfs_fsop_attrmulti_handlereq_t),
					(xfs_fsop_handlereq_t *)&am_hreq,
					&vp, &inode);
	if (error)
		return -error;

	size = am_hreq.opcount * sizeof(attr_multiop_t);
	if (!size || size > 16 * PAGE_SIZE) {
		VN_RELE(vp);
		return -XFS_ERROR(E2BIG);
	}

	ops = (xfs_attr_multiop_t *)kmalloc(size, GFP_KERNEL);
	if (!ops) {
		VN_RELE(vp);
		return -XFS_ERROR(ENOMEM);
	}

	if (copy_from_user(ops, am_hreq.ops, size)) {
		kfree(ops);
		VN_RELE(vp);
		return -XFS_ERROR(EFAULT);
	}

	for (i = 0; i < am_hreq.opcount; i++) {
		switch(ops[i].am_opcode) {
		case ATTR_OP_GET:
			VOP_ATTR_GET(vp,ops[i].am_attrname, ops[i].am_attrvalue,
					&ops[i].am_length, ops[i].am_flags,
					NULL, ops[i].am_error);
			break;
		case ATTR_OP_SET:
			if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) {
				ops[i].am_error = EPERM;
				break;
			}
			VOP_ATTR_SET(vp,ops[i].am_attrname, ops[i].am_attrvalue,
					ops[i].am_length, ops[i].am_flags,
					NULL, ops[i].am_error);
			break;
		case ATTR_OP_REMOVE:
			if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) {
				ops[i].am_error = EPERM;
				break;
			}
			VOP_ATTR_REMOVE(vp, ops[i].am_attrname, ops[i].am_flags,
					NULL, ops[i].am_error);
			break;
		default:
			ops[i].am_error = EINVAL;
		}
	}

	if (copy_to_user(am_hreq.ops, ops, size))
		error = -XFS_ERROR(EFAULT);

	kfree(ops);
	VN_RELE(vp);
	return error;
}

/*
 * Check that the two inodes are eligible for cloning, the ranges make
 * sense, and then flush all dirty data.  Caller must ensure that the
 * inodes have been locked against any other modifications.
 *
 * If there's an error, then the usual negative error code is returned.
 * Otherwise returns 0 with *len set to the request length.
 */
int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
				  struct file *file_out, loff_t pos_out,
				  loff_t *len, unsigned int remap_flags)
{
	struct inode *inode_in = file_inode(file_in);
	struct inode *inode_out = file_inode(file_out);
	bool same_inode = (inode_in == inode_out);
	int ret;

	/* Don't touch certain kinds of inodes */
	if (IS_IMMUTABLE(inode_out))
		return -EPERM;

	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
		return -ETXTBSY;

	/* Don't reflink dirs, pipes, sockets... */
	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
		return -EISDIR;
	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
		return -EINVAL;

	/* Zero length dedupe exits immediately; reflink goes to EOF. */
	if (*len == 0) {
		loff_t isize = i_size_read(inode_in);

		if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
			return 0;
		if (pos_in > isize)
			return -EINVAL;
		*len = isize - pos_in;
		if (*len == 0)
			return 0;
	}

	/* Check that we don't violate system file offset limits. */
	ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
			remap_flags);
	if (ret)
		return ret;

	/* Wait for the completion of any pending IOs on both files */
	inode_dio_wait(inode_in);
	if (!same_inode)
		inode_dio_wait(inode_out);

	ret = filemap_write_and_wait_range(inode_in->i_mapping,
			pos_in, pos_in + *len - 1);
	if (ret)
		return ret;

	ret = filemap_write_and_wait_range(inode_out->i_mapping,
			pos_out, pos_out + *len - 1);
	if (ret)
		return ret;

	/*
	 * Check that the extents are the same.
	 */
	if (remap_flags & REMAP_FILE_DEDUP) {
		bool		is_same = false;

		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
				inode_out, pos_out, *len, &is_same);
		if (ret)
			return ret;
		if (!is_same)
			return -EBADE;
	}

	ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
			remap_flags);
	if (ret)
		return ret;

	/* If can't alter the file contents, we're done. */
	if (!(remap_flags & REMAP_FILE_DEDUP)) {
		/* Update the timestamps, since we can alter file contents. */
		if (!(file_out->f_mode & FMODE_NOCMTIME)) {
			ret = file_update_time(file_out);
			if (ret)
				return ret;
		}

		/*
		 * Clear the security bits if the process is not being run by
		 * root.  This keeps people from modifying setuid and setgid
		 * binaries.
		 */
		ret = file_remove_privs(file_out);
		if (ret)
			return ret;
//.........这里部分代码省略.........