C++ VFS_I函数代码示例

/*
 * xfs_file_dio_aio_write - handle direct IO writes
 *
 * Lock the inode appropriately to prepare for and issue a direct IO write.
 * By separating it from the buffered write path we remove all the tricky to
 * follow locking changes and looping.
 *
 * If there are cached pages or we're extending the file, we need IOLOCK_EXCL
 * until we're sure the bytes at the new EOF have been zeroed and/or the cached
 * pages are flushed out.
 *
 * In most cases the direct IO writes will be done holding IOLOCK_SHARED
 * allowing them to be done in parallel with reads and other direct IO writes.
 * However, if the IO is not aligned to filesystem blocks, the direct IO layer
 * needs to do sub-block zeroing and that requires serialisation against other
 * direct IOs to the same block. In this case we need to serialise the
 * submission of the unaligned IOs so that we don't get racing block zeroing in
 * the dio layer.  To avoid the problem with aio, we also need to wait for
 * outstanding IOs to complete so that unwritten extent conversion is completed
 * before we try to map the overlapping block. This is currently implemented by
 * hitting it with a big hammer (i.e. inode_dio_wait()).
 *
 * Returns with locks held indicated by @iolock and errors indicated by
 * negative return values.
 */
STATIC ssize_t
xfs_file_dio_aio_write(
	struct kiocb		*iocb,
	struct iov_iter		*from)
{
	struct file		*file = iocb->ki_filp;
	struct address_space	*mapping = file->f_mapping;
	struct inode		*inode = mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	ssize_t			ret = 0;
	int			unaligned_io = 0;
	int			iolock;
	size_t			count = iov_iter_count(from);
	loff_t			end;
	struct iov_iter		data;
	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
					mp->m_rtdev_targp : mp->m_ddev_targp;

	/* DIO must be aligned to device logical sector size */
	if (!IS_DAX(inode) &&
	    ((iocb->ki_pos | count) & target->bt_logical_sectormask))
		return -EINVAL;

	/* "unaligned" here means not aligned to a filesystem block */
	if ((iocb->ki_pos & mp->m_blockmask) ||
	    ((iocb->ki_pos + count) & mp->m_blockmask))
		unaligned_io = 1;

	/*
	 * We don't need to take an exclusive lock unless there page cache needs
	 * to be invalidated or unaligned IO is being executed. We don't need to
	 * consider the EOF extension case here because
	 * xfs_file_aio_write_checks() will relock the inode as necessary for
	 * EOF zeroing cases and fill out the new inode size as appropriate.
	 */
	if (unaligned_io || mapping->nrpages)
		iolock = XFS_IOLOCK_EXCL;
	else
		iolock = XFS_IOLOCK_SHARED;
	xfs_rw_ilock(ip, iolock);

	/*
	 * Recheck if there are cached pages that need invalidate after we got
	 * the iolock to protect against other threads adding new pages while
	 * we were waiting for the iolock.
	 */
	if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
		xfs_rw_iunlock(ip, iolock);
		iolock = XFS_IOLOCK_EXCL;
		xfs_rw_ilock(ip, iolock);
	}

	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
	if (ret)
		goto out;
	count = iov_iter_count(from);
	end = iocb->ki_pos + count - 1;

	/*
	 * See xfs_file_read_iter() for why we do a full-file flush here.
	 */
	if (mapping->nrpages) {
		ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
		if (ret)
			goto out;
		/*
		 * Invalidate whole pages. This can return an error if we fail
		 * to invalidate a page, but this should never happen on XFS.
		 * Warn if it does fail.
		 */
		ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
		WARN_ON_ONCE(ret);
		ret = 0;
	}
//.........这里部分代码省略.........

static int
xfs_iget_cache_miss(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	xfs_trans_t		*tp,
	xfs_ino_t		ino,
	struct xfs_inode	**ipp,
	int			flags,
	int			lock_flags)
{
	struct xfs_inode	*ip;
	int			error;
	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ino);
	int			iflags;

	ip = xfs_inode_alloc(mp, ino);
	if (!ip)
		return -ENOMEM;

	error = xfs_iread(mp, tp, ip, flags);
	if (error)
		goto out_destroy;

	trace_xfs_iget_miss(ip);

	if ((VFS_I(ip)->i_mode == 0) && !(flags & XFS_IGET_CREATE)) {
		error = -ENOENT;
		goto out_destroy;
	}

	/*
	 * Preload the radix tree so we can insert safely under the
	 * write spinlock. Note that we cannot sleep inside the preload
	 * region. Since we can be called from transaction context, don't
	 * recurse into the file system.
	 */
	if (radix_tree_preload(GFP_NOFS)) {
		error = -EAGAIN;
		goto out_destroy;
	}

	/*
	 * Because the inode hasn't been added to the radix-tree yet it can't
	 * be found by another thread, so we can do the non-sleeping lock here.
	 */
	if (lock_flags) {
		if (!xfs_ilock_nowait(ip, lock_flags))
			BUG();
	}

	/*
	 * These values must be set before inserting the inode into the radix
	 * tree as the moment it is inserted a concurrent lookup (allowed by the
	 * RCU locking mechanism) can find it and that lookup must see that this
	 * is an inode currently under construction (i.e. that XFS_INEW is set).
	 * The ip->i_flags_lock that protects the XFS_INEW flag forms the
	 * memory barrier that ensures this detection works correctly at lookup
	 * time.
	 */
	iflags = XFS_INEW;
	if (flags & XFS_IGET_DONTCACHE)
		iflags |= XFS_IDONTCACHE;
	ip->i_udquot = NULL;
	ip->i_gdquot = NULL;
	ip->i_pdquot = NULL;
	xfs_iflags_set(ip, iflags);

	/* insert the new inode */
	spin_lock(&pag->pag_ici_lock);
	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
	if (unlikely(error)) {
		WARN_ON(error != -EEXIST);
		XFS_STATS_INC(mp, xs_ig_dup);
		error = -EAGAIN;
		goto out_preload_end;
	}
	spin_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();

	*ipp = ip;
	return 0;

out_preload_end:
	spin_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
out_destroy:
	__destroy_inode(VFS_I(ip));
	xfs_inode_free(ip);
	return error;
}

STATIC ssize_t
xfs_file_aio_read(
	struct kiocb		*iocb,
	const struct iovec	*iovp,
	unsigned long		nr_segs,
	loff_t			pos)
{
	struct file		*file = iocb->ki_filp;
	struct inode		*inode = file->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	size_t			size = 0;
	ssize_t			ret = 0;
	int			ioflags = 0;
	xfs_fsize_t		n;

	XFS_STATS_INC(xs_read_calls);

	BUG_ON(iocb->ki_pos != pos);

	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;
	if (file->f_mode & FMODE_NOCMTIME)
		ioflags |= IO_INVIS;

	ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
	if (ret < 0)
		return ret;

	if (unlikely(ioflags & IO_ISDIRECT)) {
		xfs_buftarg_t	*target =
			XFS_IS_REALTIME_INODE(ip) ?
				mp->m_rtdev_targp : mp->m_ddev_targp;
		/* DIO must be aligned to device logical sector size */
		if ((pos | size) & target->bt_logical_sectormask) {
			if (pos == i_size_read(inode))
				return 0;
			return -XFS_ERROR(EINVAL);
		}
	}

	n = mp->m_super->s_maxbytes - pos;
	if (n <= 0 || size == 0)
		return 0;

	if (n < size)
		size = n;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	/*
	 * Locking is a bit tricky here. If we take an exclusive lock
	 * for direct IO, we effectively serialise all new concurrent
	 * read IO to this file and block it behind IO that is currently in
	 * progress because IO in progress holds the IO lock shared. We only
	 * need to hold the lock exclusive to blow away the page cache, so
	 * only take lock exclusively if the page cache needs invalidation.
	 * This allows the normal direct IO case of no page cache pages to
	 * proceeed concurrently without serialisation.
	 */
	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
	if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);

		if (inode->i_mapping->nrpages) {
			ret = filemap_write_and_wait_range(
							VFS_I(ip)->i_mapping,
							pos, pos + size - 1);
			if (ret) {
				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
				return ret;
			}

			/*
			 * Invalidate whole pages. This can return an error if
			 * we fail to invalidate a page, but this should never
			 * happen on XFS. Warn if it does fail.
			 */
			ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
					pos >> PAGE_CACHE_SHIFT,
					(pos + size - 1) >> PAGE_CACHE_SHIFT);
			WARN_ON_ONCE(ret);
			ret = 0;
		}

int
xfs_setattr_nonsize(
	struct xfs_inode	*ip,
	struct iattr		*iattr,
	int			flags)
{
	xfs_mount_t		*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	int			mask = iattr->ia_valid;
	xfs_trans_t		*tp;
	int			error;
	uid_t			uid = 0, iuid = 0;
	gid_t			gid = 0, igid = 0;
	struct xfs_dquot	*udqp = NULL, *gdqp = NULL;
	struct xfs_dquot	*olddquot1 = NULL, *olddquot2 = NULL;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	error = -inode_change_ok(inode, iattr);
	if (error)
		return XFS_ERROR(error);

	ASSERT((mask & ATTR_SIZE) == 0);

	/*
	 * If disk quotas is on, we make sure that the dquots do exist on disk,
	 * before we start any other transactions. Trying to do this later
	 * is messy. We don't care to take a readlock to look at the ids
	 * in inode here, because we can't hold it across the trans_reserve.
	 * If the IDs do change before we take the ilock, we're covered
	 * because the i_*dquot fields will get updated anyway.
	 */
	if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) {
		uint	qflags = 0;

		if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
			uid = iattr->ia_uid;
			qflags |= XFS_QMOPT_UQUOTA;
		} else {
			uid = ip->i_d.di_uid;
		}
		if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
			gid = iattr->ia_gid;
			qflags |= XFS_QMOPT_GQUOTA;
		}  else {
			gid = ip->i_d.di_gid;
		}

		/*
		 * We take a reference when we initialize udqp and gdqp,
		 * so it is important that we never blindly double trip on
		 * the same variable. See xfs_create() for an example.
		 */
		ASSERT(udqp == NULL);
		ASSERT(gdqp == NULL);
		error = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip),
					 qflags, &udqp, &gdqp);
		if (error)
			return error;
	}

	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
	if (error)
		goto out_dqrele;

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	/*
	 * Change file ownership.  Must be the owner or privileged.
	 */
	if (mask & (ATTR_UID|ATTR_GID)) {
		/*
		 * These IDs could have changed since we last looked at them.
		 * But, we're assured that if the ownership did change
		 * while we didn't have the inode locked, inode's dquot(s)
		 * would have changed also.
		 */
		iuid = ip->i_d.di_uid;
		igid = ip->i_d.di_gid;
		gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
		uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;

		/*
		 * Do a quota reservation only if uid/gid is actually
		 * going to change.
		 */
		if (XFS_IS_QUOTA_RUNNING(mp) &&
		    ((XFS_IS_UQUOTA_ON(mp) && iuid != uid) ||
		     (XFS_IS_GQUOTA_ON(mp) && igid != gid))) {
			ASSERT(tp);
			error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
						capable(CAP_FOWNER) ?
						XFS_QMOPT_FORCE_RES : 0);
//.........这里部分代码省略.........

/*
 * Allocate an inode on disk and return a copy of its in-core version.
 * Set mode, nlink, and rdev appropriately within the inode.
 * The uid and gid for the inode are set according to the contents of
 * the given cred structure.
 *
 * This was once shared with the kernel, but has diverged to the point
 * where it's no longer worth the hassle of maintaining common code.
 */
int
libxfs_ialloc(
	xfs_trans_t	*tp,
	xfs_inode_t	*pip,
	mode_t		mode,
	nlink_t		nlink,
	xfs_dev_t	rdev,
	struct cred	*cr,
	struct fsxattr	*fsx,
	int		okalloc,
	xfs_buf_t	**ialloc_context,
	xfs_inode_t	**ipp)
{
	xfs_ino_t	ino;
	xfs_inode_t	*ip;
	uint		flags;
	int		error;

	/*
	 * Call the space management code to pick
	 * the on-disk inode to be allocated.
	 */
	error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc,
			    ialloc_context, &ino);
	if (error != 0)
		return error;
	if (*ialloc_context || ino == NULLFSINO) {
		*ipp = NULL;
		return 0;
	}
	ASSERT(*ialloc_context == NULL);

	error = xfs_trans_iget(tp->t_mountp, tp, ino, 0, 0, &ip);
	if (error != 0)
		return error;
	ASSERT(ip != NULL);

	VFS_I(ip)->i_mode = mode;
	set_nlink(VFS_I(ip), nlink);
	ip->i_d.di_uid = cr->cr_uid;
	ip->i_d.di_gid = cr->cr_gid;
	xfs_set_projid(&ip->i_d, pip ? 0 : fsx->fsx_projid);
	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG | XFS_ICHGTIME_MOD);

	/*
	 * We only support filesystems that understand v2 format inodes. So if
	 * this is currently an old format inode, then change the inode version
	 * number now.  This way we only do the conversion here rather than here
	 * and in the flush/logging code.
	 */
	if (ip->i_d.di_version == 1) {
		ip->i_d.di_version = 2;
		/*
		 * old link count, projid_lo/hi field, pad field
		 * already zeroed
		 */
	}

	if (pip && (VFS_I(pip)->i_mode & S_ISGID)) {
		ip->i_d.di_gid = pip->i_d.di_gid;
		if ((VFS_I(pip)->i_mode & S_ISGID) && (mode & S_IFMT) == S_IFDIR)
			VFS_I(ip)->i_mode |= S_ISGID;
	}

	ip->i_d.di_size = 0;
	ip->i_d.di_nextents = 0;
	ASSERT(ip->i_d.di_nblocks == 0);
	ip->i_d.di_extsize = pip ? 0 : fsx->fsx_extsize;
	ip->i_d.di_dmevmask = 0;
	ip->i_d.di_dmstate = 0;
	ip->i_d.di_flags = pip ? 0 : fsx->fsx_xflags;

	if (ip->i_d.di_version == 3) {
		ASSERT(ip->i_d.di_ino == ino);
		ASSERT(uuid_equal(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid));
		VFS_I(ip)->i_version = 1;
		ip->i_d.di_flags2 = 0;
		ip->i_d.di_crtime.t_sec = (__int32_t)VFS_I(ip)->i_mtime.tv_sec;
		ip->i_d.di_crtime.t_nsec = (__int32_t)VFS_I(ip)->i_mtime.tv_nsec;
	}

	flags = XFS_ILOG_CORE;
	switch (mode & S_IFMT) {
	case S_IFIFO:
	case S_IFSOCK:
		/* doesn't make sense to set an rdev for these */
		rdev = 0;
		/* FALLTHROUGH */
	case S_IFCHR:
	case S_IFBLK:
		ip->i_d.di_format = XFS_DINODE_FMT_DEV;
//.........这里部分代码省略.........

/* Clear the inode reflink flag if there are no shared extents. */
int
xfs_reflink_clear_inode_flag(
	struct xfs_inode	*ip,
	struct xfs_trans	**tpp)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		fbno;
	xfs_filblks_t		end;
	xfs_agnumber_t		agno;
	xfs_agblock_t		agbno;
	xfs_extlen_t		aglen;
	xfs_agblock_t		rbno;
	xfs_extlen_t		rlen;
	struct xfs_bmbt_irec	map;
	int			nmaps;
	int			error = 0;

	ASSERT(xfs_is_reflink_inode(ip));

	fbno = 0;
	end = XFS_B_TO_FSB(mp, i_size_read(VFS_I(ip)));
	while (end - fbno > 0) {
		nmaps = 1;
		/*
		 * Look for extents in the file.  Skip holes, delalloc, or
		 * unwritten extents; they can't be reflinked.
		 */
		error = xfs_bmapi_read(ip, fbno, end - fbno, &map, &nmaps, 0);
		if (error)
			return error;
		if (nmaps == 0)
			break;
		if (!xfs_bmap_is_real_extent(&map))
			goto next;

		agno = XFS_FSB_TO_AGNO(mp, map.br_startblock);
		agbno = XFS_FSB_TO_AGBNO(mp, map.br_startblock);
		aglen = map.br_blockcount;

		error = xfs_reflink_find_shared(mp, agno, agbno, aglen,
				&rbno, &rlen, false);
		if (error)
			return error;
		/* Is there still a shared block here? */
		if (rbno != NULLAGBLOCK)
			return 0;
next:
		fbno = map.br_startoff + map.br_blockcount;
	}

	/*
	 * We didn't find any shared blocks so turn off the reflink flag.
	 * First, get rid of any leftover CoW mappings.
	 */
	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
	if (error)
		return error;

	/* Clear the inode flag. */
	trace_xfs_reflink_unset_inode_flag(ip);
	ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
	xfs_inode_clear_cowblocks_tag(ip);
	xfs_trans_ijoin(*tpp, ip, 0);
	xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);

	return error;
}

/*
 * Sync all the inodes in the given AG according to the
 * direction given by the flags.
 */
STATIC int
xfs_sync_inodes_ag(
	xfs_mount_t	*mp,
	int		ag,
	int		flags)
{
	xfs_perag_t	*pag = &mp->m_perag[ag];
	int		nr_found;
	uint32_t	first_index = 0;
	int		error = 0;
	int		last_error = 0;
	int		fflag = XFS_B_ASYNC;

	if (flags & SYNC_DELWRI)
		fflag = XFS_B_DELWRI;
	if (flags & SYNC_WAIT)
		fflag = 0;		/* synchronous overrides all */

	do {
		struct inode	*inode;
		xfs_inode_t	*ip = NULL;
		int		lock_flags = XFS_ILOCK_SHARED;

		/*
		 * use a gang lookup to find the next inode in the tree
		 * as the tree is sparse and a gang lookup walks to find
		 * the number of objects requested.
		 */
		read_lock(&pag->pag_ici_lock);
		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
				(void**)&ip, first_index, 1);

		if (!nr_found) {
			read_unlock(&pag->pag_ici_lock);
			break;
		}

		/*
		 * Update the index for the next lookup. Catch overflows
		 * into the next AG range which can occur if we have inodes
		 * in the last block of the AG and we are currently
		 * pointing to the last inode.
		 */
		first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
		if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) {
			read_unlock(&pag->pag_ici_lock);
			break;
		}

		/* nothing to sync during shutdown */
		if (XFS_FORCED_SHUTDOWN(mp)) {
			read_unlock(&pag->pag_ici_lock);
			return 0;
		}

		/*
		 * If we can't get a reference on the inode, it must be
		 * in reclaim. Leave it for the reclaim code to flush.
		 */
		inode = VFS_I(ip);
		if (!igrab(inode)) {
			read_unlock(&pag->pag_ici_lock);
			continue;
		}
		read_unlock(&pag->pag_ici_lock);

		/* avoid new or bad inodes */
		if (is_bad_inode(inode) ||
		    xfs_iflags_test(ip, XFS_INEW)) {
			IRELE(ip);
			continue;
		}

		/*
		 * If we have to flush data or wait for I/O completion
		 * we need to hold the iolock.
		 */
		if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) {
			xfs_ilock(ip, XFS_IOLOCK_SHARED);
			lock_flags |= XFS_IOLOCK_SHARED;
			error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE);
			if (flags & SYNC_IOWAIT)
				xfs_ioend_wait(ip);
		}
		xfs_ilock(ip, XFS_ILOCK_SHARED);

		if ((flags & SYNC_ATTR) && !xfs_inode_clean(ip)) {
			if (flags & SYNC_WAIT) {
				xfs_iflock(ip);
				if (!xfs_inode_clean(ip))
					error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
				else
					xfs_ifunlock(ip);
			} else if (xfs_iflock_nowait(ip)) {
				if (!xfs_inode_clean(ip))
					error = xfs_iflush(ip, XFS_IFLUSH_DELWRI);
//.........这里部分代码省略.........

STATIC int
xfs_vn_mknod(
	struct inode	*dir,
	struct dentry	*dentry,
	int		mode,
	dev_t		rdev)
{
	struct inode	*inode;
	struct xfs_inode *ip = NULL;
	xfs_acl_t	*default_acl = NULL;
	struct xfs_name	name;
	int (*test_default_acl)(struct inode *) = _ACL_DEFAULT_EXISTS;
	int		error;

	/*
	 * Irix uses Missed'em'V split, but doesn't want to see
	 * the upper 5 bits of (14bit) major.
	 */
	if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
		return -EINVAL;

	if (test_default_acl && test_default_acl(dir)) {
		if (!_ACL_ALLOC(default_acl)) {
			return -ENOMEM;
		}
		if (!_ACL_GET_DEFAULT(dir, default_acl)) {
			_ACL_FREE(default_acl);
			default_acl = NULL;
		}
	}

	xfs_dentry_to_name(&name, dentry);

	if (IS_POSIXACL(dir) && !default_acl)
		mode &= ~current->fs->umask;

	switch (mode & S_IFMT) {
	case S_IFCHR:
	case S_IFBLK:
	case S_IFIFO:
	case S_IFSOCK:
		rdev = sysv_encode_dev(rdev);
	case S_IFREG:
		error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip, NULL);
		break;
	case S_IFDIR:
		error = xfs_mkdir(XFS_I(dir), &name, mode, &ip, NULL);
		break;
	default:
		error = EINVAL;
		break;
	}

	if (unlikely(error))
		goto out_free_acl;

	inode = VFS_I(ip);

	error = xfs_init_security(inode, dir);
	if (unlikely(error))
		goto out_cleanup_inode;

	if (default_acl) {
		error = _ACL_INHERIT(inode, mode, default_acl);
		if (unlikely(error))
			goto out_cleanup_inode;
		_ACL_FREE(default_acl);
	}


	d_instantiate(dentry, inode);
	return -error;

 out_cleanup_inode:
	xfs_cleanup_inode(dir, inode, dentry);
 out_free_acl:
	if (default_acl)
		_ACL_FREE(default_acl);
	return -error;
}

STATIC int
xfs_generic_create(
	struct inode	*dir,
	struct dentry	*dentry,
	umode_t		mode,
	dev_t		rdev,
	bool		tmpfile)	/* unnamed file */
{
	struct inode	*inode;
	struct xfs_inode *ip = NULL;
	struct posix_acl *default_acl, *acl;
	struct xfs_name	name;
	int		error;

	/*
	 * Irix uses Missed'em'V split, but doesn't want to see
	 * the upper 5 bits of (14bit) major.
	 */
	if (S_ISCHR(mode) || S_ISBLK(mode)) {
		if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
			return -EINVAL;
		rdev = sysv_encode_dev(rdev);
	} else {
		rdev = 0;
	}

	error = posix_acl_create(dir, &mode, &default_acl, &acl);
	if (error)
		return error;

	if (!tmpfile) {
		xfs_dentry_to_name(&name, dentry, mode);
		error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
	} else {
		error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
	}
	if (unlikely(error))
		goto out_free_acl;

	inode = VFS_I(ip);

	error = xfs_init_security(inode, dir, &dentry->d_name);
	if (unlikely(error))
		goto out_cleanup_inode;

#ifdef CONFIG_XFS_POSIX_ACL
	if (default_acl) {
		error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
		if (error)
			goto out_cleanup_inode;
	}
	if (acl) {
		error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
		if (error)
			goto out_cleanup_inode;
	}
#endif

	if (tmpfile)
		d_tmpfile(dentry, inode);
	else
		d_instantiate(dentry, inode);

	xfs_finish_inode_setup(ip);

 out_free_acl:
	if (default_acl)
		posix_acl_release(default_acl);
	if (acl)
		posix_acl_release(acl);
	return error;

 out_cleanup_inode:
	xfs_finish_inode_setup(ip);
	if (!tmpfile)
		xfs_cleanup_inode(dir, inode, dentry);
	iput(inode);
	goto out_free_acl;
}

static int
xfs_iget_cache_miss(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	xfs_trans_t		*tp,
	xfs_ino_t		ino,
	struct xfs_inode	**ipp,
	int			flags,
	int			lock_flags)
{
	struct xfs_inode	*ip;
	int			error;
	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ino);

	ip = xfs_inode_alloc(mp, ino);
	if (!ip)
		return ENOMEM;

	error = xfs_iread(mp, tp, ip, flags);
	if (error)
		goto out_destroy;

	trace_xfs_iget_miss(ip);

	if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
		error = ENOENT;
		goto out_destroy;
	}

	/*
	 * Preload the radix tree so we can insert safely under the
	 * write spinlock. Note that we cannot sleep inside the preload
	 * region.
	 */
	if (radix_tree_preload(GFP_KERNEL)) {
		error = EAGAIN;
		goto out_destroy;
	}

	/*
	 * Because the inode hasn't been added to the radix-tree yet it can't
	 * be found by another thread, so we can do the non-sleeping lock here.
	 */
	if (lock_flags) {
		if (!xfs_ilock_nowait(ip, lock_flags))
			BUG();
	}

	spin_lock(&pag->pag_ici_lock);

	/* insert the new inode */
	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
	if (unlikely(error)) {
		WARN_ON(error != -EEXIST);
		XFS_STATS_INC(xs_ig_dup);
		error = EAGAIN;
		goto out_preload_end;
	}

	/* These values _must_ be set before releasing the radix tree lock! */
	ip->i_udquot = ip->i_gdquot = NULL;
	xfs_iflags_set(ip, XFS_INEW);

	spin_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();

	*ipp = ip;
	return 0;

out_preload_end:
	spin_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
out_destroy:
	__destroy_inode(VFS_I(ip));
	xfs_inode_free(ip);
	return error;
}

/*
 * Process a bmap update intent item that was recovered from the log.
 * We need to update some inode's bmbt.
 */
int
xfs_bui_recover(
	struct xfs_mount		*mp,
	struct xfs_bui_log_item		*buip)
{
	int				error = 0;
	unsigned int			bui_type;
	struct xfs_map_extent		*bmap;
	xfs_fsblock_t			startblock_fsb;
	xfs_fsblock_t			inode_fsb;
	xfs_filblks_t			count;
	bool				op_ok;
	struct xfs_bud_log_item		*budp;
	enum xfs_bmap_intent_type	type;
	int				whichfork;
	xfs_exntst_t			state;
	struct xfs_trans		*tp;
	struct xfs_inode		*ip = NULL;
	struct xfs_defer_ops		dfops;
	struct xfs_bmbt_irec		irec;
	xfs_fsblock_t			firstfsb;

	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));

	/* Only one mapping operation per BUI... */
	if (buip->bui_format.bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
		set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
		xfs_bui_release(buip);
		return -EIO;
	}

	/*
	 * First check the validity of the extent described by the
	 * BUI.  If anything is bad, then toss the BUI.
	 */
	bmap = &buip->bui_format.bui_extents[0];
	startblock_fsb = XFS_BB_TO_FSB(mp,
			   XFS_FSB_TO_DADDR(mp, bmap->me_startblock));
	inode_fsb = XFS_BB_TO_FSB(mp, XFS_FSB_TO_DADDR(mp,
			XFS_INO_TO_FSB(mp, bmap->me_owner)));
	switch (bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK) {
	case XFS_BMAP_MAP:
	case XFS_BMAP_UNMAP:
		op_ok = true;
		break;
	default:
		op_ok = false;
		break;
	}
	if (!op_ok || startblock_fsb == 0 ||
	    bmap->me_len == 0 ||
	    inode_fsb == 0 ||
	    startblock_fsb >= mp->m_sb.sb_dblocks ||
	    bmap->me_len >= mp->m_sb.sb_agblocks ||
	    inode_fsb >= mp->m_sb.sb_dblocks ||
	    (bmap->me_flags & ~XFS_BMAP_EXTENT_FLAGS)) {
		/*
		 * This will pull the BUI from the AIL and
		 * free the memory associated with it.
		 */
		set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
		xfs_bui_release(buip);
		return -EIO;
	}

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
	if (error)
		return error;
	budp = xfs_trans_get_bud(tp, buip);

	/* Grab the inode. */
	error = xfs_iget(mp, tp, bmap->me_owner, 0, XFS_ILOCK_EXCL, &ip);
	if (error)
		goto err_inode;

	if (VFS_I(ip)->i_nlink == 0)
		xfs_iflags_set(ip, XFS_IRECOVERY);
	xfs_defer_init(&dfops, &firstfsb);

	/* Process deferred bmap item. */
	state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
			XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
	whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
			XFS_ATTR_FORK : XFS_DATA_FORK;
	bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
	switch (bui_type) {
	case XFS_BMAP_MAP:
	case XFS_BMAP_UNMAP:
		type = bui_type;
		break;
	default:
		error = -EFSCORRUPTED;
		goto err_dfops;
	}
	xfs_trans_ijoin(tp, ip, 0);
//.........这里部分代码省略.........

/*
 * Convert userspace handle data into inode.
 *
 * We use the fact that all the fsop_handlereq ioctl calls have a data
 * structure argument whose first component is always a xfs_fsop_handlereq_t,
 * so we can pass that sub structure into this handy, shared routine.
 *
 * If no error, caller must always iput the returned inode.
 */
STATIC int
xfs_vget_fsop_handlereq(
	xfs_mount_t		*mp,
	struct inode		*parinode,	/* parent inode pointer    */
	xfs_fsop_handlereq_t	*hreq,
	struct inode		**inode)
{
	void			__user *hanp;
	size_t			hlen;
	xfs_fid_t		*xfid;
	xfs_handle_t		*handlep;
	xfs_handle_t		handle;
	xfs_inode_t		*ip;
	xfs_ino_t		ino;
	__u32			igen;
	int			error;

	/*
	 * Only allow handle opens under a directory.
	 */
	if (!S_ISDIR(parinode->i_mode))
		return XFS_ERROR(ENOTDIR);

	hanp = hreq->ihandle;
	hlen = hreq->ihandlen;
	handlep = &handle;

	if (hlen < sizeof(handlep->ha_fsid) || hlen > sizeof(*handlep))
		return XFS_ERROR(EINVAL);
	if (copy_from_user(handlep, hanp, hlen))
		return XFS_ERROR(EFAULT);
	if (hlen < sizeof(*handlep))
		memset(((char *)handlep) + hlen, 0, sizeof(*handlep) - hlen);
	if (hlen > sizeof(handlep->ha_fsid)) {
		if (handlep->ha_fid.fid_len !=
		    (hlen - sizeof(handlep->ha_fsid) -
		            sizeof(handlep->ha_fid.fid_len)) ||
		    handlep->ha_fid.fid_pad)
			return XFS_ERROR(EINVAL);
	}

	/*
	 * Crack the handle, obtain the inode # & generation #
	 */
	xfid = (struct xfs_fid *)&handlep->ha_fid;
	if (xfid->fid_len == sizeof(*xfid) - sizeof(xfid->fid_len)) {
		ino  = xfid->fid_ino;
		igen = xfid->fid_gen;
	} else {
		return XFS_ERROR(EINVAL);
	}

	/*
	 * Get the XFS inode, building a Linux inode to go with it.
	 */
	error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_SHARED, &ip, 0);
	if (error)
		return error;
	if (ip == NULL)
		return XFS_ERROR(EIO);
	if (ip->i_d.di_gen != igen) {
		xfs_iput_new(ip, XFS_ILOCK_SHARED);
		return XFS_ERROR(ENOENT);
	}

	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	*inode = VFS_I(ip);
	return 0;
}

/*
 * Truncate file.  Must have write permission and not be a directory.
 */
int
xfs_setattr_size(
	struct xfs_inode	*ip,
	struct iattr		*iattr)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	xfs_off_t		oldsize, newsize;
	struct xfs_trans	*tp;
	int			error;
	uint			lock_flags = 0;
	uint			commit_flags = 0;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	error = -inode_change_ok(inode, iattr);
	if (error)
		return XFS_ERROR(error);

	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
	ASSERT(S_ISREG(ip->i_d.di_mode));
	ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
		ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);

	oldsize = inode->i_size;
	newsize = iattr->ia_size;

	/*
	 * Short circuit the truncate case for zero length files.
	 */
	if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
		if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
			return 0;

		/*
		 * Use the regular setattr path to update the timestamps.
		 */
		iattr->ia_valid &= ~ATTR_SIZE;
		return xfs_setattr_nonsize(ip, iattr, 0);
	}

	/*
	 * Make sure that the dquots are attached to the inode.
	 */
	error = xfs_qm_dqattach(ip, 0);
	if (error)
		return error;

	/*
	 * Now we can make the changes.  Before we join the inode to the
	 * transaction, take care of the part of the truncation that must be
	 * done without the inode lock.  This needs to be done before joining
	 * the inode to the transaction, because the inode cannot be unlocked
	 * once it is a part of the transaction.
	 */
	if (newsize > oldsize) {
		/*
		 * Do the first part of growing a file: zero any data in the
		 * last block that is beyond the old EOF.  We need to do this
		 * before the inode is joined to the transaction to modify
		 * i_size.
		 */
		error = xfs_zero_eof(ip, newsize, oldsize);
		if (error)
			return error;
	}

	/*
	 * We are going to log the inode size change in this transaction so
	 * any previous writes that are beyond the on disk EOF and the new
	 * EOF that have not been written out need to be written here.  If we
	 * do not write the data out, we expose ourselves to the null files
	 * problem.
	 *
	 * Only flush from the on disk size to the smaller of the in memory
	 * file size or the new size as that's the range we really care about
	 * here and prevents waiting for other data not within the range we
	 * care about here.
	 */
	if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
		error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
						      ip->i_d.di_size, newsize);
		if (error)
			return error;
	}

	/*
	 * Wait for all direct I/O to complete.
	 */
	inode_dio_wait(inode);

//.........这里部分代码省略.........

	ASSERT(completion_done(&ip->i_flush));

	kmem_zone_free(xfs_inode_zone, ip);
}

/*
 * Check the validity of the inode we just found it the cache
 */
static int
xfs_iget_cache_hit(
	struct xfs_perag	*pag,
	struct xfs_inode	*ip,
	int			flags,
	int			lock_flags) __releases(pag->pag_ici_lock)
{
	struct inode		*inode = VFS_I(ip);
	struct xfs_mount	*mp = ip->i_mount;
	int			error;

	spin_lock(&ip->i_flags_lock);

	/*
	 * If we are racing with another cache hit that is currently
	 * instantiating this inode or currently recycling it out of
	 * reclaimabe state, wait for the initialisation to complete
	 * before continuing.
	 *
	 * XXX(hch): eventually we should do something equivalent to
	 *	     wait_on_inode to wait for these flags to be cleared
	 *	     instead of polling for it.
	 */

/*
 * Unmap a range of blocks from a file, then map other blocks into the hole.
 * The range to unmap is (destoff : destoff + srcioff + irec->br_blockcount).
 * The extent irec is mapped into dest at irec->br_startoff.
 */
STATIC int
xfs_reflink_remap_extent(
	struct xfs_inode	*ip,
	struct xfs_bmbt_irec	*irec,
	xfs_fileoff_t		destoff,
	xfs_off_t		new_isize)
{
	struct xfs_mount	*mp = ip->i_mount;
	bool			real_extent = xfs_bmap_is_real_extent(irec);
	struct xfs_trans	*tp;
	xfs_fsblock_t		firstfsb;
	unsigned int		resblks;
	struct xfs_defer_ops	dfops;
	struct xfs_bmbt_irec	uirec;
	xfs_filblks_t		rlen;
	xfs_filblks_t		unmap_len;
	xfs_off_t		newlen;
	int			error;

	unmap_len = irec->br_startoff + irec->br_blockcount - destoff;
	trace_xfs_reflink_punch_range(ip, destoff, unmap_len);

	/* No reflinking if we're low on space */
	if (real_extent) {
		error = xfs_reflink_ag_has_free_space(mp,
				XFS_FSB_TO_AGNO(mp, irec->br_startblock));
		if (error)
			goto out;
	}

	/* Start a rolling transaction to switch the mappings */
	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
	if (error)
		goto out;

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, ip, 0);

	/* If we're not just clearing space, then do we have enough quota? */
	if (real_extent) {
		error = xfs_trans_reserve_quota_nblks(tp, ip,
				irec->br_blockcount, 0, XFS_QMOPT_RES_REGBLKS);
		if (error)
			goto out_cancel;
	}

	trace_xfs_reflink_remap(ip, irec->br_startoff,
				irec->br_blockcount, irec->br_startblock);

	/* Unmap the old blocks in the data fork. */
	rlen = unmap_len;
	while (rlen) {
		xfs_defer_init(&dfops, &firstfsb);
		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1,
				&firstfsb, &dfops);
		if (error)
			goto out_defer;

		/*
		 * Trim the extent to whatever got unmapped.
		 * Remember, bunmapi works backwards.
		 */
		uirec.br_startblock = irec->br_startblock + rlen;
		uirec.br_startoff = irec->br_startoff + rlen;
		uirec.br_blockcount = unmap_len - rlen;
		unmap_len = rlen;

		/* If this isn't a real mapping, we're done. */
		if (!real_extent || uirec.br_blockcount == 0)
			goto next_extent;

		trace_xfs_reflink_remap(ip, uirec.br_startoff,
				uirec.br_blockcount, uirec.br_startblock);

		/* Update the refcount tree */
		error = xfs_refcount_increase_extent(mp, &dfops, &uirec);
		if (error)
			goto out_defer;

		/* Map the new blocks into the data fork. */
		error = xfs_bmap_map_extent(mp, &dfops, ip, &uirec);
		if (error)
			goto out_defer;

		/* Update quota accounting. */
		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT,
				uirec.br_blockcount);

		/* Update dest isize if needed. */
		newlen = XFS_FSB_TO_B(mp,
				uirec.br_startoff + uirec.br_blockcount);
		newlen = min_t(xfs_off_t, newlen, new_isize);
		if (newlen > i_size_read(VFS_I(ip))) {
			trace_xfs_reflink_update_inode_size(ip, newlen);
//.........这里部分代码省略.........